[go: up one dir, main page]

WO2024072849A1 - Discrimination activée par intelligence artificielle de maladie et d'étiologie de maladie - Google Patents

Discrimination activée par intelligence artificielle de maladie et d'étiologie de maladie Download PDF

Info

Publication number
WO2024072849A1
WO2024072849A1 PCT/US2023/033803 US2023033803W WO2024072849A1 WO 2024072849 A1 WO2024072849 A1 WO 2024072849A1 US 2023033803 W US2023033803 W US 2023033803W WO 2024072849 A1 WO2024072849 A1 WO 2024072849A1
Authority
WO
WIPO (PCT)
Prior art keywords
werene
cam
moe
macneearnn
waveormaas
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/US2023/033803
Other languages
English (en)
Inventor
Steven LUBITZ
Puneet BATRA
Julian HAIMOVICH
Nathaniel DIAMANT
Shaan KHURSHID
Jennifer Ho
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
General Hospital Corp
Broad Institute Inc
Original Assignee
General Hospital Corp
Broad Institute Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by General Hospital Corp, Broad Institute Inc filed Critical General Hospital Corp
Publication of WO2024072849A1 publication Critical patent/WO2024072849A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
    • A61B5/0004—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by the type of physiological signal transmitted
    • A61B5/0006—ECG or EEG signals
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/339—Displays specially adapted therefor
    • A61B5/341—Vectorcardiography [VCG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/63—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for local operation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/327—Generation of artificial ECG signals based on measured signals, e.g. to compensate for missing leads
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/36—Detecting PQ interval, PR interval or QT interval
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/361—Detecting fibrillation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks

Definitions

  • the subject matter disclosed herein is related to utilizing electrocardiogram data to detect diseases or disease etiologies. Particular examples relate to providing a system, a computer- implemented method, and a device to utilize data obtained from electrocardiograms of a subject to discriminate and detect potential diseases or disease etiology with machine learning models.
  • BACKGROUND [0004]
  • the modern resting electrocardiogram (ECG) utilizes waveform data generated from surface electrodes to represent cardiac activation and impulse conduction. Introduced in the early 1900s, the original ECG was primarily used for arrhythmia detection, but its diagnostic utility expanded rapidly to include identification of coronary artery disease and other cardiac structural abnormalities.
  • aarrseearse ma comrse venrcuarerro ane venrcuarerro ma comrsero .e aeas one eoo oee aorc senoss, a carac amooss,erroc caromoa,eas n onen exameree,nsev veenearrcuasrease.er r oane eeoo o r venrc ros r venrcuarerro, ane a are uarerro comrsesumonarerenson,umonar crross, rennr a oenns aeo euxn ra, em cro ,even e,c r oero unsmenasoee mmao ccomurmsoenaraees,er seeneso an.nea, croncversease, esease ma e
  • comrsenear cassers oomsuce cr-amsseemrse,neaes maen noesw,ores, r macneearnn moe ma marxacorzaon,enarov moe, suor vecor macanne,om-moeraenss, c neuusrear nne,w oorrs-, neeaarrnesn n meoeor m.a ceom macrsene coenarransnve meoae ma comrse a neura newor.
  • eooes comnrese esx am onee or em moorem eeecnr,o acarevoceoranosn one moreseases orsease suec a soraeevce an arocessor communracmaveeas coour oeaonne s woarvaeeormevcae,a wroem a erocessor execues a caon coensruconsa are ren e ssemo: recor waveor sorene soraeevceo causeearnn moe erenae,masaea ornome wea suveeocrmraocae,s ussne waeve moarcmnaeae uasn a macne sease orsease eoo an enerae aanosc ou rnn moe, a orsease e u comr
  • casser arecson euaorevaence o eoon moes . eo -oec veevrseurs o noeran c comaraacraerosr.ce ccuervves oeeearnn an comarson comarson moese a er oeran caracersc curves o eea, -eeanex, eoeasures aneeearnn moes -e, - corresonn an coneno eoo versus no comaraor w execeerorm cenervas sownneeen.asene sows .anc -e ore “cnsoo sn re”ca ranom casser a o..
  • eoo versus n curves oeeearnn an comarson moes moese anoex, comeaarsauorers.
  • aenceveeer oeearrannn m coareacersc curves o comarson -eea eoo eoo versus no s comara-oer w, c-eea, area unererecson reca curves an con orresonn ne sows execeerormance o “no s” ranomen cceassneervra as sreocwsnonn eeuaeoenr.evase o eoo aence casscaon o.n -e s eeasm o ce oa.ra vceerrsuscs o cnca rues versuseeearnn moesor secc anosverecs no a
  • eence raes oearaure araraon, an mora raon, a ncence raeser erson-ears o mora, ara a nearaureer, erson-earsere orece -e carac wmonoowssn a cnaracer amrooc coasrso omroaerro rsc ex cacruonmonav.uasrrne vaaon same conencener orars reresen carac amo.vas oss -.
  • rs couns wnown carac amo an erroc conence or eacere are sowneow eaco.rrorars reresen carac amo.ne oss -rva anums.uaveerncroencce c oa cnca oucomesrece -e rs oncence oearaure romoa srae mae sex.umuave e rs o carac am, aoraoss arnaon, aner mroorac caromeroesa onocrre masanesnreec vea - same excunnvuas wnown carac amo anerr aon rs counsor eacere are sowneow oc caromoa.nervas.
  • eaco.rrorars reresen conence car .
  • -umuavencence o cnca oucomesrece -e rs oncaecnc aem ooeaorssa aunre, araerrroaocn c,a arno mmoroaa sreare emae sex.umuave e rs o carac amooss an err es oncreasnrece - vaaon same excunnvua oc caromoaoremaesne caromoa.
  • rs counsor eacser we are snoowwnn cearowac eac amoo.r arnorars reerrroec conencenervas. sen sacee.ara -eowroceasram o auoencoer anenoe vecorervaonoraen auoencoero encoe an recosnsorruco- a-nea s anne s-enae-eas m uosnes.ecan ssrane an aase - .
  • areorusraveuroses on an are no necessarrawno enerae meann as cnn oemsmsons onene un oerseorwose,e ocnen oca o arnna srce sncnermes a urseo werecnavsesceo sasumree eoraecnus.areonnno:ns oa coomramoornearmnusa a,n nd e ecnonuesn moaemcuraoro,oor maeounn oecuaronn:aoraoranua, th eon reen asc, ananas roocosnoecuaroo ..usue e a.
  • crcumsance or sus meansae suseuenescre even, weree even or crcuumensan mcae o occru mrsa an nons ocacnucre,s a wnereaoeeescronncuesnsances susume wen recea reosne ocv neum raenrecsa, a rsan wees as een reonsncus neos a. numers anracons eerms “aou” or “aroxmae” as usceee erenn wones.
  • vaue suc as aarameer an amou n reerrno a measurae varaons o anrome secen va, auee,m sucora as vuarraaoonn,s an o-ee, o arrees ms,ean-o e oncomass oress, an-. oress o anrome sece vaue,nso ress,- aroraeoerormnescosenvenon.
  • ar suc varaons are moer “aou” or “aroxmae” soe unersooae vaueo wce s useeren, reerssse aso secca, anreera,scose.
  • reero a vererae,reera a mamma, morereera auman.am no nomeo, murnes, smans,umans,arm anmas, masncue,u are erroen o aooca en oanen v sor anmas, anes.ssues, ces an arous emomens arees vo or cuuren vro are aso encomasse. emomens are nonene as an ecreerenaer.
  • emomen meansa a saerccucaaroneaour “eo,n seru ecmuroe omre cna”r,ac “aenrs emcoescmrene,”n “a cn exame we emomensncuen aeas one emomen oeresennvenonnecon aearances oerases “n one emomen,” “n an emomen, on.us, emomen”n varousacesrouous seccaon are ” or “an exame same emomenu ma.urermore,earc no necessar a reerrnoe e comnen an suae uareaures, srucures or caracerscs ma scosure,n on manner, as woue aareno aerson sene arromsncue someue o nro m oor
  • eereaseen ssem meoon anae nvocnecaraa acowsesa ssesse mmaac as eova muaanoens o on assoecaon, a nee exssor a aa, suc as- or eco forbiddenm-aseeaur seween waveorm a uses aeeearnn moeo e es, an aroa rane oseaseenoes an sneeae ncoe an reconsruc waveormaa,ncuno-ea reaeana aa.ese meos anevceescreerenroveor more waveormaoas, ws oer cear curarce-nre maeeosseaase,.
  • eec one or moresease ooeserenrove a comuer-memene meoo recorn ec s orsease eooes, comrsn, aeas one9.99vce:ea o semiconductor meoo recorn ec s orsease eooes, comrsn, aeas one9.99vce:ea o semiconductor meoo recorn ec s orsease eooes, comrsn, aeas one wagevce:ea o christmasmaa o a suecrocessne eco christmasmaa usn a macne srenasne.
  • oeecnuesescre ansecae arne con.u,reeo s csomemmuncues newor negligencevcesssems or va an su ncae w one anoer va one or more newors neworevaccess nea swe eomr commun s nccauoens aec wnroeo or.
  • wreesseecommuncaon means wc eac newor canncunce aunn oeovsecesescr,e,e arenn suc c aasn eexc neawnoeraa.oer exame, .
  • ecure or ssemaacaes soue unersooaeerms “aa” aronu “onuormeaosnc”u assreo unse o enxaemrcaen emeaomeerns, reeroex,maes, auo, veo, or an oerorm onor eno ase envronmen.
  • e comm maona can exsn a comuer- mae smar neworsoun necawoornecn ooro an a uernzaeve comemeuvncceasosnseecmsnoo,., an avn a comamcun necawoorn m coomuue cnaaevec oesra
  • wr,e oer w nereweosrs anevceassnossemcs newo,r o,e arn are oerae user,aa acuson ssem oeraors, e user comaors, resecve.
  • acuson server eaa s em comrses aaa sorae un an an srucure ac orae un canncue anoca or remoeaa sorae sorae uncess caenoncueea oane ac oru msoreona snseme com suuear-reeaoar seo sronnormaon.
  • a sorae un mae a
  • a dissolves sem, suc a raeevces, oreaa cou-ase sorae servce s aerensca or vrua macne or a evce ann onoer aseec,.
  • recornevce recor amuaor recorn waveormaaor a sorero o se eecrca acv o aear.e., recornevce recor mee.., aroxmae secons.muaor reaeran se eecrca acv o aearor arooneero omee.., recornenv acn se e, ec wxoanms.
  • ereen eme eoecmrecna acev o recoerenaevce comrses an amuaoreas mnue, aeas, aeas rs measureor aeas secons, aeasa, aeasas, aeas manus,e as, aeaseasmonou,r a, aeaesas moonurss,, o ar aeaseasoeuarrs., an a mno enxaomr, ae eomero momneno,r, evee snan moanro orr, amacu maoor evce comrses a mu-ea surace e.., smar wac nor,manae monor, or consumerevce sanar sura mceu.
  • eecroes.ecroes are comrse o scex ameor,,, an- aone cesrecora.eeas ,,, an exremeas an sx ceseas.e sxmeas corresonoe an sx unoare eaecsro.ee as.,e a sx, anm aea.s ceoamr csoerr oesorneesoooare eaecsro.e.e,s, an ,ea corresonsoo e R ecro L es an F anea correson an an.eas a, a, an anvua corresono an onesoo eecroes , an an are R assn L eeen F n one neeurn mo o eecroecro
  • orersona us comrse an monorrevous menoneu areesne s e.onsumerevces ma aso comrse wearae moeevcese.., omna orrw aaaccees.oonesumoeroev mcoen moorn anors r mecaor co emecrrscea a a sneevce or mueevces worn nernaonaaen caon ,erenccorvo oeear.ee,or exame, n exame emomens, “eaess” recorrae reerencens enre.
  • recornevces use wreessecnoo nevces are use.eaess eecrca acv oeear. an aeaswoons o measuremeno recore measurem n exame emomens,eaess recornevces recor ons muesnser oomwoons oeoe.., r arme arm or reee.ewo suaeewne surace o a suece..,o oose eac oer wereeears .eenewoons.ee,or exame,nernaonaaen caon cocaro waves, wccra aom rceare naocor uramn e roeceov urc mane n eaersv.ces so uusne urasoun, or ver ußc sounraverou an meum.n an
  • nasruocerram eecroes are aeoe suec’s ces monor,s move overe suecoransm, w socuns w caovmemounecaevaer an couo cereaoe a morvocessor an oe oeraon oeear an vaves,emaesenrocesse nmaes erocessor an monor.ransesoaea , recore ansae ons aace a one eco Lankam uzes a smmerransucer, wc roce en o aonue annserenoe esoaus.
  • s recon o acve can wece u one sn assransmerouououeo.e vareenn on weaevreoerm eecaraca.e a.c,vrecsono on aoewaercso onr, a uwawarrom or aoeawnwar, ma caracersceaure os eecrca acv comrses oreee w .eca comex, an wave.n exame os waveo aves:e wave, wave eauer.arooxane.onon:emrm cane seennure ose, vaaerom: nc.nm.n.ovoos ec,aere.aer,onuerne .
  • sermee ara mamsouunav e we aovr eems are snusoaucuaonsnressuree sze o eacressure wave wavese sanceeweenewo wavesse waveen, ane numer o e wnr seeco rnanes oe-reu menco.no cr mceescear a seconcaons,z,e anre eucenocca or uorraasounensoower en os secrum.- z.ca,n caracman,e ecocar ss ae uzereeerenman moes:wo-mensona, moeara o moorams me, anoer sues.
  • wcurer comrses a moueorn ouusasseoeanosc server emomen,e macneearnn o eneraneanosc ouu.n an exame electionvce were uuransmeoeaa acuson ssem or user sease anseaseo eanosc ouusenerae oseevcesssems.
  • e waveuraon ameers assocae w carovascuar mora are roone ane,an-ereanraoc, aneeermna neav oe waven, semeneresson an eevnaeorvna,s, wavesurnaveorne an,r waavmee anxaeso,n s,auna aenraenscewoecen, anaz anne vecavoerso,rmremaaa oure a s réellenercc,uaer m coancranceoenasr,n ann newor caerro crera.n aroaeanoss o asease or an eoo o asease neermne an ouu seasenoc ,eanosc ouu comrsn.
  • mcoreo ecxecunaeeonwscrucaro onrsoorcmaemraemnsn can ree sreescen a oeraon or se.n exame emomens,eunconsacsn aoc can e sownneures an non reuresae oeraons occur ou oe orer or exame,woocs sownn successive eerormene orerusrae.
  • concurren.n ano son can execue concurren or essena varaons, mocaonesr, e suxamsue,onso,c as caonns,e or ex reecuuceonnneo rcevse arse orer.urermore, use w an oeaerarams, strigros,ow car noruncons mae a o wc are exc conemaeeren. s anocaramsscusseeren, one anoer,neaare orrna wramose,.
  • ssem ma comrsesnc soware moues emoe on a a reaae sorae cuteme moues canncue,or exame, an or a oe anro norame eaemoenn, asne oncee, sonmee or aoc oaera mmos aunesorocescsr ane orer seun-mo wuaes o exame escre.
  • meo ses canene carre ou usnesnc sowa su-ocs su-moues oe ssem, asescre aove, execun re moue
  • we unersooa eacoc oe or more emomens oeresen arams, an comnaons oocsneowc owcarusraons anorocmemene comuer reaaero arusraons anorocarams, cane Credevc ceo,m suecera reauraosee croor mraam umn nnssrru euc vco con enss.
  • ornes croumcounes can asoe soren a comuer reaae aarauses, anor oerevceso revces,rorammaeaarocessn moues.e comuer r carr oueunconacs oerocessor-memene moues s eaae sorae meum conann a orararocessor-memenemowecmaerno an arseecs,er oene,ra coomns,r osres se ans aorcee oero mrmaneua ocureenucnuconnacns srueccones wnce comuer reaomor auo eec sro rreaaa earam meeruooc mra o wmrno nscr ausc.
  • nsruco uer reaaeroramnsruconsescreeren cane assemer eenennsn,srnuscruocnso,n m-scer-oacroce,ecrumrewarensruncsoruncs, sonase,-s macnensrucons, macne or oec coe.
  • comuer reaaeroramn enaa, or eer source coeanuae suc as come ornerre srucons cane wrenn anrorammn e oec-orenerorammn eanuaes.n aon,erorammnanuae cananuaese.., anuaee.., “” or convenonaroceurarorammnnsrucons.e “ c”om oru aenr r ceoamaneaoronraemreons mruacoens us ce
  • sane- caoomneueror reraama, meouroe,r saumronusrnuec, oor oer un suaeor usen a speci or on mu e comuers a one se ns can execue enre on one comuer newor,or exame o or across mu e ses connece a communcaon acae,ar onen us uesre'sr' cso cmomuuere ar,narar on one a u rseemr'so ceo cmomueur,e ars o ar s ean-aone soware comuer or server.
  • e comuer reaaeroramnsr nre on a remoe ene remoe comuer cane conn ucons are execue enre remoe, e connecon cane m eceoe user's comuerrou an e o newor, or crcurn aeo an exerna comuer.n exames emomens, eecronc arras cu, on,u nomeo,rorammaeoc crcur,e-rorammaeaensru rrorammaeoc arras can execuee comuer reaaeroramnsruccoonnss.oecerrosonnca czrecuer e caencr uoncze c srcauern,oroma exoecnu oeuenc coomuer reaaeroram emomens o
  • moues or meca sescre erenncueoc or a numer o comonens,memene nsms. oues ma comrse eer soware moues orarware- r moues. soware moue ma e coe emoe on a non-ransor macne- ceaaaaee o meeruomrm ornn c aerraannsm osesraonon ss anna. maarew caorne-mureem oern areran moeunes aan e un n exame emomens, one or more comuer ssem a ceran manner.
  • comuer ssem or one or more se.., a sanaone, cen or server or a caonoron rocessors ma e conure sowaree.., an a caon oeraons a as aarware-memene moue a oeraesoerorm ceran mecancans o ee rxsac emre eceron eemre caon.
  • ms,erncesreseneeren mae ae eescrea asa a snunevuoa a m meaacsurnaeeearrnoner a oor ame cnaonmeeno connsenere o aserevaeu.re, we coc can oeaures reaeoa o anneenen varae usen sascaecnues s nce usennear reresson.eerormance o a macneearnn uc asose casscaon an reressons eenen on coo aormnaern reconon,neeneneaures.eaures ma comrs snnormave,scrmnan, an srns,ras, ormae e numercaaa, caeorcaaa,me-seresaa, waveor s.
  • menoasneoresnn are oneev oero meoreoesneases m oerannseauseo eroonos oes.en ve ecxoame exrac semanc meannsew r an ranne eena sace.
  • uunearveseeeraarnnnnn canaan.vonve anro evxamne a e omr aoomreonn, o suaeerveseranenarnnaaos aa mseac onneeearnronv meouae,e were taen mnacanae,e aanrnne m ououues aereer emnenr ac ocnee or more ouus eenn one areemenoe acua oucome oerannaa.e or correce suervseearnn o macneearnn ssems caneo n some exames,aesorerannnu, ane se o rues a verne a se o rues anor a se onerences o a macneearnn mou nor se oaes mae use
  • ner,rec,enerae, oreer nrane cane useo ouu, esmae, resus. rane mne,or smc eseerms w coecve e reerreo as s suc,enu maaca canneeea ursnen as m aonuneu caon reeceravenen muacanae anear onnera moenerae resus.
  • rane macneearnnnuaa can comr soreneran new resus.n exame emomens, resusn ouuaa ssuec wa avse oonrem ora maor aen,s weaseens orrovseeaseo e aoraonees.
  • neenenneenen varae maavee same o n oneneenen varae, eac aveer own one or moreunn varanees. or meo nruemunern o vanraeeens oenr ea vcar,a seesar aane,un ma varaes we unersooo one sene aroreroemen sove.
  • n emomens, waveormaa are use aseneenen var n exame moue, wc, aerrann,s useo es aesoran a macneearnn e mae,or exame, one or moreseases orsease ooosces.e oscenre re os sns seon on e,xa omo ene co enmsoereme an,osec m reorees,son macneearnnsmemene.
  • wo meno e meoso evauaeenerence, orreca,n au on roa o anearocruaerm aossnsnramevne our vaosueess.ore eacrs v maeraoe.nvoevoesn comrouan ceanon consereerouc o eac cononaroa an,n somensances, eoarm oarouc.e secon meosarov canonearo comrsese ememene wene same szesare.
  • wc can aorms an w noe o samesruon e assumoscusseneaeren. aes cassers.s assunm o coonnmoneasnereeesn noen cocrere oa voanraeewseeonrmsereenanssuoreave s a resu,e numer o comueroaess sncan reuce a aures.
  • sascaeno ar or nnnes ex maomees enmuoencmeen,euoraoceaw noerurs arememene.s are aam orane on a reaveareaasee..,, o a newors oeran.s cane rec an ouuaeens on r more an useo esmae, aroxmae, or cae “ne aare numer onuseaures.s cane envsone as so- eecroncu sromnaosr, orc “”m sessseamess” o.nmercaonnecerocessor eemens, or “neurons”, an excane conneconsa carr messaeseweernooeo soc-aca neeur “onsa,sce c”on one scnoanscn neurosranasm carrer eeec srroenn
  • convouona ouerraaor newaore arns an comnurs ses,nanoe enxerraac,weoau mreasn o come sonnean.s.rs,e auoencoeraearns a se o snasrom annu an reco econ, an comnnesewo comonens,e earnse nsrucse snano an ouu.
  • a eenencesecome morecuo caureec ns.n s,onerm cane wrann orucua auseearameers or wes eero no ecreaseso zero, resunn noe c raaneo.e wse occusrs or waernameeers, or exraoneenn exonenaonn, resunnare canesne wes oraram ancreases eenen one numer oaers an m eers.s exonena eecs vansnexonraensmeme ucaveraen.
  • sor,-erm. memor over recursve onvouon a cass ona asne u eu rxraame er aew e emmoronmeon r,e a cconvouona neura neworsmemene.
  • anoonaers eexs oracreeeaaureesr s: s cuocnvo asuoons,eooesncr, aenuere connece.e convouon comrses o mue maemaca oeraons n.e convouonaaer en a convouon.eu c suc as onear oeraons, a secazeenuaa, suc as waveormaonan,e mcaeea reerr ceosmenenesn ae erxr,ac.ee., anea arurresno an ouu.e oarameers, cae aerne, oeraes as an o a o numers.r osonner.xraceeau mzaeeaure exracor ans aeo eac s ouuno res maecomeerarcca more comex as oneaereesn
  • con marx comrsn one or moreseases orsease enar avanae ono evxeamo saee s ecmaoamreonvs, m aoeeonrearcov an m oouecomse.memaernoev. mn aes arovrocess, wereneroa o an oucomes s oe assumes a ne case o ,s assume an unn oeeenen onerevous even. even.n comrses a newor o coownnne ocr “e noene”s.
  • aano cnas er sxesamac een n ee emo nm-enmse,n ssuonoar veceorr manaecsnne-s areememene.
  • s reresson an casscaonroems.era rane an are usenorannrocess o an .
  • nes areecsonounareseveoeurne eaures.or ex emensona o aeraneeens one numer onu we a ame, a wwonueaures wave anear-mensonaerane eranes o wmzereoeanveueeaarureess m warnav oer s aaaanersan-cemreonmsonea neareseraaaneo.n uosre eaocevaeaoee.neer caansee.
  • wneeanr reereesasuornes an a casscaon anear euaons escreeerane.
  • scnae somee s nemarors oew aneoene nre casso.rsno on ree euxcaemee e ermroro o emene, neso arns o a onaer cass “ou-von” near uze.n exame emomens, waveormaa are useor ov moe aroacs moue, wc, aerrann,s useo esmae one or mor an a macneearnn oerorm one or more osunconaes,eseases orsease eooes.
  • monre ceraranwa erexamroceess eomrso anme mnas, oene con or muroereoarewroarremroec oeraons conureoncue an one or more oe mouesescreere essors are an oreover, anwo or more oese moues mae comn.neno a sne moue es.unucroenrmsorees,c arcceornereon vaorro aus s , mou enxame meo emueo mmaense, m suouvesees acmon mue enmemene wn a sne macne,aaase, orevce maesrureeren as macnes,aaases, orevces.e mue macnes,aaase across mue communcave coueo enae
  • a convenona comuer ssem a rouer or oer newor noe, a evce, a smarone, a se-oox, aos, w aee vecuarnormaon ssem, one or morerocessors assocae mucvseorne,o a. cuseom comzeu mnac mnaec, anne oer maarwear aeaorm, or an comnaon or uncon usn m srue ssem conureo e oune oe Chr macnesnerconnece va aaa newor orus ssem.
  • sora-e me a aa ma versnacuee asca“rs”,, a aou-rs, a comacsc rea as memor, oer non-voae memorevc asc, a manecae, a evce, an oca soraeevce, an eecrec,a a so sora saeeervvcee,“ an e”e,c anrom maanneecc s soorraaee neovn-cree,m aonva seem mceonau,c anor s ooreareaeav scoer,a aneevcsec,a or- aanse soraeevce, an removae an non-exausves o more secc exames oe comnaon or mucereo.
  • acemessae seuencnnormaon, enc nerove,or exame, asnormaon, anransmsso asuaoneaers anorooers, szeme anorar cec va n vercaonnormaon suc as ccc reunanc cec s ues.ommuncaons cane mae encoeencre, or oerwse mae seuccure a,s, anuor noecrmeeoe,coaea usnncr oneon or maonrea crrora,cvarnocoecosn acnroro anorams, , aves-amr-eman aorm, ae-eman aorm, a secure soncar rooco suc asecureocesaer orransoraerecur , anoreas ornna aureonooromsese.ereenr
  • ueo aorc senoss cans as ueo aorc senoss, an aeoo-ea an sne-seesasee w exaveenorom waca c aoure-eraenceee anearnsncrm monaee a amaonns e aoeronaevse o moes.
  • receivesonuunaam ameu -aor ccaarnsooen caere a au a muae-nnss aueona aceaars or oer wo ssemasseneraram.
  • auomae aorm was vaae emonsrae a aroram reorsn aneason a su auor an .
  • osverecve vaue o an neaverecve vaue o .eeae ae et e.oorn-aseensavseormecescaracersocssverecveooea.ve e vrentrcuar vaue vauerecve troreort .
  • aam reors were rev m aenewse wooru ea acanos eso oo. o carac amooss orerroc caromoa eooww.n aucaon were s consereorncusonne eco forbiddenc caeores errouc car avoamaoa an areanosc moa sourcesor carac amooss an ae.uvaa noreesenneanmaees-. -ea eecro sandalm ervaon same.:, aaon same:, ae.anoscoaourceoxraracmoossnervaoname.
  • x oa m ra ecac ne amumoorosos 99 saae scnra , an carac s or.aaosx, ae.anoscoaourceoxraracmoossn aaone.
  • x oarra oac os amaeo sconssraa , osx, 99m ecneum ae.anoscoaour acne coarrace . e rrocaromoa.
  • carormrooac • • • :: : • • • :: ac caromoacnansenecnueon o anv reuaarses ws o ec carocaarco amraoco css an erroc eoenamerec sensv o eco wasteor nesesreaseersao,r.ouven e ccarocoamrorac seeeow was no reureor a carac amooss orerroc novauas wanoss,erroc caromnovaua mse w ec carac amooss, an anoss.
  • mensona vecor reresenaon usn arevous escre eeearnn axro no a - aenonrasveearnn oeresenaons wcs omzeorrananc enocwennc as onu mreonn.aenc aanns o uusea aenucs avroamaea c cornevaoesu nounmaer nceaura re neworrane waveorms wc emaszeerenceseween s resenaons o smareseween srome samenvua.n romerennvuas an s noes
  • eac oe a newor moesoner mssn maxmum voae amuesor wave, -wveavee,a asnncue-wanve.e cnccaansnaze ru eeasc: o-ew naevue,ra new-woarves, w ae- wes o are m-oraeneea-s moees ucroeeoa averaeoonaereea- u.comroa an avaae a aer, oneu cnosnneuceemaerre ceamsasseerm woee_ezrooe wa.ereoa averaeoon waveorm‘casseraer’.noeru conneceaerv reernesseuesoen am wasureesenne casse asresen‘reressonaer’ or waves cassca
  • conencenervasor -e ane cnca rues carac amoocsanss an evauaeerrooecn caar asosmocoaaons o w o-sereverenceroa o ncen araraon, an mora excunnvuasne vaaonc saemnee waranoure, carac amooss orerroc caromo wn arara a.
  • cans aso cacuae anases wereerormecen raesoor eac cnca oucome. ‘ensorow’, an ‘en n v. usnacaes ‘anas’, ‘searn’, e es’. ususouaon erroc carcaonmsoncaue, eco,caronravucas w, o ar noa encosocsar o carac amooss, m amoonen w soamme wasuereema.e ane mean aerev waason.
  • zes causes o ennceurenna nno a sec,c caucsaen osoe.., carac amoossrom a oer comarson moesn one versus res casscaounn oa e-oeo a,so c oaussernorm cee amooss an erroc caromoa w s o. ,. arac . c ocaror , ae m . a-e s r.o ve r e m re , a- r rae ens e n c t c e :e e c -.
  • oen couns are sooa same szesor eac sraum are sowneneae suroue.ase accurae ceaewn sseearn cen. mo eeosorane onu srensee-a w.aveeorms -eeas an aso casscaon o carac amooss anerroc caromo sor -eea e.s .or comarso a were. ,.- r no easures , an. ,.-.
  • rotera:rettera ertenson..:., ..:., ..:., ..:., ..:., ..:., ..:., zes ae.urouv:eranass oa:e sex- seexemae:ea:e ⁇ oeer:eo >rmance.
  • rotera:rettera . . zes
  • sronerormance acr sn eooes -e maaveoena cnca u as au auomoasse an screennooor an rare eooes w acaon on-o-care sneea ev oo-ea s an moe casscaonr oor worces erroa.scemonsraee caa o -aseeeearnn moesor o e a. caromoa, carac amooss, an ecoddlingc.
  • e ru cesn acna emon rusrease are s usnecnan rounme crovneca seracceo cass ,e arensensve. -e comareoe nsvoreecon o eco forbiddenc wenm cnca rues. -eureremonsraeerormance casrsovceameonns onerr eoooc ca crasosmcoaon w a near.-omrovemenn sensvor acaon oesuesse oaao-screm mnaonesa srrua.
  • aure manaemen oerensveearsease.roenrarcuoavrascersr.oo con:es-ve.ear , e a..erroaavco csar,omaoaaars: a,n useeae reve,aramsos,oouos,ousas earaev w onanoss,ronoss, anreamen. rcan.. eoeonce,-enaa:aera- u,.eus asunom-aeeson,ura,asumaa,no, e a.
  • aorn ca,.enonee,ncem an c,onvmenon,aman,ossm cre, e a.omarne venrcuarerro usn eec raoreecne .aron. erro Malawi.uroace. :-. :- roc caromoa: a ssemac revew. . carac amo.oaseesz:z. s,easeerrnoe,s aunara cnc,a cvoaurs,eso one, meaonne,e es. a.rcusemc :- aon. ecrocaro.raavace.
  • sosueaseo sesnoemaesca eevvaeuoaen ass aocaeeonseaeween-aseeaures reconsruc waveormaa,ncuno-ea rnn moeo encoe an .nrann,srom aervaon se wereaee an sneeaea s.ure rou , seases, rerese accornoeresence or asence o asscaon oseas ne ecoes, or areaerouns onernaona oesen oamozaone coes useoene cnca meannuseaseenoes.
  • nveenseaseenoe assocae weoson oe corresonnecoe cuse aen sace we -aseeaures anseaseenoe rs.oes assocaonseween suese nreeeren s, canserormeenome-we assocaon mea-anaze resu aases,ncunworueoou ses. cansen seasesn s,nn sncan assocaonseween waveormaa an e e-ea moe an seasesn sxnecee, suc aseunerancoc .
  • wavecaonrms seeaeucrees aoene a,u woenocou aer mooneaencaourmses rearnaenemoracs or cnca oucomes.
  • cansurer sannn over,nvuas,ncunwo sa caracersc emonsraeowaen sace moen cane useo aens.
  • eauresoreecae conons ano cncaroenvua eos aen emorac anca cnnsa’a ca sseus nor umazoen,nrceeunaase-s,ea a o ws.c cocnanasnenvua-eve aasesromeommunareoorroec , arev ervewo o our comrsn over, aus ae ears wo transmit ous esase coor eevenosas wneassenera eonunarmar care a one o aa wareouse.
  • 26 aases ram newor, wcsne a common - aase an a cncue a coorromeassacuseseneraosa aase.er, exernaaaoseorromeram anomen’sosa - aseer ceoor su comrsn au wsasromerveenromeenomo aaen, a-roseaercs ave e cnorommmuenn.
  • % oe sar o cncaoow u cue e acusonae was no wnreeearsror vs oe eares ,eneor eacnvua a 2 s 6 eme oe seconrmar care rereseneoruanar, asrevousescre.n one ernvua was e naeureans n we ar mcuecuere was,e mos recen was use.
  • connece convouo s a varan oensene,eaurn severaense erarameersnnaocs oeran a erenme resouons.rcecure vaaesanercauramne were o,meza,o acvaon, normazaon, an reuarzaon were cosen seaseenoe n.
  • c ecorervaon rar s:oeewsn eac oereeaases were maeo auc avaaeecoe snus cas ascaao.orecoes_ccm.srevousescre,ecoes conc esrom conros usnerarccarouns o an coesoeerene ca meannuseaseenoes.nrevaenecoes were use,.e., a orrre cseroannnecoe cso,easracaonse wreseonunaeaeceone’s cuar wro vrero semar acu csooesn waeree.
  • avens rvaon cans exe ease, reresene aecoe,as a sncanmac one , srueo aceeren emoceaonnsnae a rueoreensceoner-ersveromaenn svacuea rsea wveoe emseeasenosmaa rcer oensenes, orormnevuas e wmeouneoessea nsoe.
  • ane counareas cauereseseaasese-raese eaures,en cans execeereoe no sncan reaons evan emensneaen sace aneresence or asen eweeneoson o canseneeesens o encoce osease.ouan s execaon, osve cenro”or cases a nsaes asavnesease“sease- sease“sease-neavneesens o enconsaee as noavne reresen e cenro”or conros.acecoe wasereore saa v e s cenroar, anenea connecsems reerreo aseenoe uencor.ure.n encoe wneaen sace,ncun enconsrom ean
  • an eacenoe vecor was normazeonsoave norm an sanarevaon o one, reaeness o eac anecoe wasuaneavee enac s oanme.ee-mensona saa o avenenoe vecor.susraeeown euaon,’ esa ccomonen ennerecon emen”, roecs ono eacenoe v con“ “como i ecor, p .eroece comonen, scaenene ip e”ns ca ocuaerome aneeweene encon aneenoe vecor, o a snenvua aone a sn.eus,eneoroee vceceo cr.omonen sneseaen saceoson ea moe,e auoenco
  • mevee sncean numreesro o, un wuce weacsoeesn aceros uss an m aonerron- eanases wereerorme usneacae mea.on w ea-anases.
  • the best performing architecture contained over 11 million neurons and used mish activations, 2 dense convolutional blocks (each with 5 layers of convolutions per block), a 71 timestep convolutional kernel, layer normalization, and 256 neurons in the fully connected layer.
  • the autoencoder performed well across datasets.
  • the 12-lead model had a Pearson correlation coefficient of 0.96 (95% CI: 0.93 - 0.97) in the MGH-C3PO testing set, 0.95 (95% CI: 0.92 - 0.97) in BWH-C3PO, and 0.92 (95% CI: 0.89 - 0.93) in the UK Biobank.
  • ceranseaseeasse w-ec wec-ceaanaveorms eaures were conssen w execaon.or exaramceer,z meean wa mvea noirsaenoens, moe-erve unerancocsease-osve cenroemons raeromeene r-serecoraeas- raejur, smaerna r waves , 38 reaveo mean waveorms,en anerae warvoem surernseanse-neeea-vsee ceneraos, aure, .rooornaoonaemuar,e moe-.enr mveane oauerersnnscanuceeseocwreeavseer,s weave amue an reave aeare morooca smar vsua.ese no ase case an conro s man
  • seccaemocs nasnon ss a nove acaon o auoencoereeearnn moes seneraes a muranmenoswon aa maoeen sraacneeao c eanncoee us aeno re ecxonosrreu rceao-n an sne-ea waveormeaures an cnca reevanseaseenoes seween rous assocaonseween wave a scae.
  • cans’ resus sues en comareo an nervas moromea, aeurnose anncoers-eaassees, acaroesns m suacee m ooreans s resems.
  • n -rouounvuaron usn eas-acure oranze ann coencerus uonn,ersanca snuscenmcoansnraoermaoowna coenna sace moen cane useo anoscs.e corresonn anas ne wn curren avaae wea osease-s s suorseaca waveormaa conans a evauaee sncaanenooremnaao one-on an sen crec-ueaaor wa sveseomrm. auure sues souurer ron.
  • creenoreraemaromeecervoecaormoenram an.aaaorn oo a,ee--earnn.oeo voaeaa u.sna auneae, neu.r,a e n a.recon o morarom-ea eecro Lankam .ara-orren,., ee awo.rr.eace,- . eaecor nucaeavorromonunaecronc ecronce.s.
  • ornnaseaen e.a,rnanr,ro.m., aooo,r-.er.moerme,a..rs .enase ocraeaonn o. ecee,nea . eearnn.ee.un,., e. a.ee sanrom eecrocarora an resraon wee rrocar.omomoa,a.,. ee a.ecro seinecanesnverrross-uesor .eo,., e a.eccrnaaunas .
  • earsne vss a suos awonnn samaee.,eree waner ae was earsnerann same an an, eaensneeran,n an va anaon, s men an, ne vaaon same was mm. ames, resecve.ean-
  • ae:ouaonaracerscs corre ne vaaon same, aensa cnca reore , wc execaeer wens w- cncar ea. mean asoue error. mm.e- emonsrae . mmerm 2 .,ouwreesr:ear veernr-cuar e correae w ero massnex ., an ere venrcuar en-asocameceeornra.c momn.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Physics & Mathematics (AREA)
  • Molecular Biology (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Pathology (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Theoretical Computer Science (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Surgery (AREA)
  • Cardiology (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Physiology (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Signal Processing (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • General Business, Economics & Management (AREA)
  • Business, Economics & Management (AREA)
  • Fuzzy Systems (AREA)
  • Psychiatry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Tires In General (AREA)

Abstract

La présente invention divulgue l'utilisation de données de forme d'onde d'un sujet pour détecter une ou plusieurs maladies ou étiologies de maladie. Des exemples particuliers concernent la fourniture d'un système, d'un procédé mis en œuvre par ordinateur et d'un produit-programme informatique permettant, au moyen de données de forme d'onde, de détecter et de différencier des maladies et des étiologies de maladie particulières à l'aide de modèles d'apprentissage automatique.
PCT/US2023/033803 2022-09-27 2023-09-27 Discrimination activée par intelligence artificielle de maladie et d'étiologie de maladie Ceased WO2024072849A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202263410489P 2022-09-27 2022-09-27
US63/410,489 2022-09-27

Publications (1)

Publication Number Publication Date
WO2024072849A1 true WO2024072849A1 (fr) 2024-04-04

Family

ID=88517367

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2023/033803 Ceased WO2024072849A1 (fr) 2022-09-27 2023-09-27 Discrimination activée par intelligence artificielle de maladie et d'étiologie de maladie

Country Status (1)

Country Link
WO (1) WO2024072849A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200260979A1 (en) * 2017-11-27 2020-08-20 Lepu Medical Technology (Bejing) Co., Ltd. Artificial intelligence self-learning-based static electrocardiography analysis method and apparatus
WO2020181367A1 (fr) 2019-03-08 2020-09-17 The Access Technologies Moniteur d'électrocardiogramme sans fil
WO2021228672A1 (fr) * 2020-05-11 2021-11-18 Koninklijke Philips N.V. Conversion de données chronologiques pour application de modèle d'apprentissage automatique
US20210401349A1 (en) * 2020-06-26 2021-12-30 Alivecor, Inc. Two-lead qt interval prediction
CN114519370A (zh) * 2022-01-28 2022-05-20 复旦大学附属中山医院 一种基于深度学习早停机制的左心室肥大检测方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200260979A1 (en) * 2017-11-27 2020-08-20 Lepu Medical Technology (Bejing) Co., Ltd. Artificial intelligence self-learning-based static electrocardiography analysis method and apparatus
WO2020181367A1 (fr) 2019-03-08 2020-09-17 The Access Technologies Moniteur d'électrocardiogramme sans fil
WO2021228672A1 (fr) * 2020-05-11 2021-11-18 Koninklijke Philips N.V. Conversion de données chronologiques pour application de modèle d'apprentissage automatique
US20210401349A1 (en) * 2020-06-26 2021-12-30 Alivecor, Inc. Two-lead qt interval prediction
CN114519370A (zh) * 2022-01-28 2022-05-20 复旦大学附属中山医院 一种基于深度学习早停机制的左心室肥大检测方法及系统

Non-Patent Citations (100)

* Cited by examiner, † Cited by third party
Title
"Antibodies, A Laboratory Manual", 1988
"Methods in Enzymology", 1995, ACADEMIC PRESS, INC., article "PCR 2: A Practical Approach"
A. BERGER: "Echocardiography", BMJ, vol. 321, no. 7255, 22 July 2000 (2000-07-22), pages 218
AL-ALUSI, M.A.DING, E.MCMANUS, D.D.LUBITZ, S.A.: "Wearing Your Heart on Your Sleeve: the Future of Cardiac Rhythm Monitoring", CURR CARDIOL REP, vol. 21, 2019, pages 158, XP036952475, DOI: 10.1007/s11886-019-1223-8
AL-ZAITI, S. ET AL.: "Machine learning-based prediction of acute coronary syndrome using only the pre-hospital 12-lead electrocardiogram", NAT COMMUN, vol. 11, 2020, pages 3966, XP055890414, DOI: 10.1038/s41467-020-17804-2
APPLE WATCH ECG APP DE NOVO CLASSIFICATION GRANTED, 14 August 2018 (2018-08-14)
ATTIA, Z.I. ET AL.: "Age and Sex Estimation Using Artificial Intelligence From Standard 12-Lead ECGs", CIRC ARRHYTHM ELECTROPHYSIOL, vol. 12, 2019, pages e007284
ATTIA, Z.I. ET AL.: "An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction", LANCET, vol. 394, 2019, pages 861 - 867, XP085804088, DOI: 10.1016/S0140-6736(19)31721-0
ATTIA, Z.I. ET AL.: "Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram", NAT MED, vol. 25, 2019, pages 70 - 74, XP036668628, DOI: 10.1038/s41591-018-0240-2
BACHMAYER, K.: "Clinical Course and Management of Hypertrophic Cardiomyopathy", N ENGL J MED, vol. 379, 2018, pages 1976
BARAK-CORREN, Y. ET AL.: "Predicting Suicidal Behavior From Longitudinal Electronic Health Records", AM J PSYCHIATRY, vol. 174, 2017, pages 154 - 162
BAROLD, S.S.: "Willem Einthoven and the birth of clinical electrocardiography a hundred years ago", CARD ELECTROPHYSIOL REV, vol. 7, 2003, pages 99 - 104
BOLDRINI MCAPPELLI FCHACKO LRESTREPO-CORDOBA MARIA ALOPEZ-SAINZ AGIANNONI A ET AL.: "Multiparametric Echocardiography Scores for the Diagnosis of Cardiac Amyloidosis", JACC: CARDIOVASCULAR IMAGING, vol. 13, no. 4, 2020, pages 909 - 20
BRENYO, A.ZARUBA, W.: "Prognostic significance of QRS duration and morphology", CARDIOL J, vol. 18, 2011, pages 8 - 17
CARREIRAS, C. ET AL., BIOSPPY: BIOSIGNAL PROCESSING IN PYTHON, 2015
CASTIGLIONE, A.ODENING, K.: "QT Interval and Its Prolongation - What Does It Mean?", DTSCHMED WOCHENSCHR, vol. 145, 2020, pages 536 - 542
CHEN, X. ET AL.: "Incremental changes in QRS duration as predictor for cardiovascular disease: a 21-year follow-up of a randomly selected general population", SCI REP, vol. 11, 2021, pages 13652
CHRISTOPOULOS GGRAFF-RADFORD JLOPEZ CLYAO XATTIA ZIRABINSTEIN AA ET AL.: "Artificial Intelligence-Electrocardiography to Predict Incident Atrial Fibrillation: A Population-Based Study", CIRC ARRHYTHM ELECTROPHYSIOL, vol. 13, no. 12, 2020, pages e009355
CHUNG EHGUISE KD: "QTC intervals can be assessed with the AliveCor heart monitor in patients on dofetilide for atrial fibrillation", J ELECTROCARDIOL, vol. 48, no. 1, 2015, pages 8 - 9
CIKES, M. ET AL.: "Machine learning-based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy", EUR J HEART FAIL, vol. 21, 2019, pages 74 - 85
CORDEIRO, R.KARIMIAN, N.PARK, Y.: "Hyperglycemia Identification Using ECG in Deep Learning Era", SENSORS (BASEL), 2021, pages 21
CYRILLE NBGOLDSMITH JALVAREZ JMAURER MS: "Prevalence and prognostic significance of low QRS voltage among the three main types of cardiac amyloidosis", AM J CARDIOL, vol. 114, no. 7, 2014, pages 1089 - 93, XP029052043, DOI: 10.1016/j.amjcard.2014.07.026
DAVIDSON-PILON C: "lifelines: survival analysis in Python", JOURNAL OF OPEN SOURCE SOFTWARE, vol. 4, no. 40, 2019, pages 1317
DENNY, J.C. ET AL., PHECODE MAP 1.2 WITH ICD-10CM CODES (BETA, vol. 2022
DENNY, J.C. ET AL.: "PheWAS: demonstrating the feasibility of a phenome-wide scan to discover gene-disease associations", BIOINFORMATICS, vol. 26, 2010, pages 1205 - 1210
DENNY, J.C. ET AL.: "Systematic comparison of phenome-wide association study of electronic medical record data and genome-wide association study data", NAT BIOTECHNOL, vol. 31, 2013, pages 1102 - 1110
DEO, R. ET AL.: "Electrocardiographic Measures and Prediction of Cardiovascular and Noncardiovascular Death in CKD", JAM SOC NEPHROL, vol. 27, 2016, pages 559 - 569
DUBREY SWCHA KANDERSON JCHAMARTHI BREISINGER JSKINNER M ET AL.: "The clinical features of immunoglobulin light-chain (AL) amyloidosis with heart involvement", QJM, vol. 91, no. 2, 1998, pages 141 - 57, XP002485302, DOI: 10.1093/qjmed/91.2.141
ESTRADA, A.H. ET AL.: "Diagnostic accuracy of computer aided electrocardiogram analysis in dogs", J SMALL ANIMPRACT, vol. 62, 2021, pages 145 - 149
FEENY, A.K. ET AL.: "Artificial Intelligence and Machine Learning in Arrhythmias and Cardiac Electrophysiology", CIRC ARRHYTHM ELECTROPHYSIOL, vol. 13, 2020, pages e007952, XP055862000, DOI: 10.1161/CIRCEP.119.007952
FINOCCHIARO, G. ET AL.: "The electrocardiogram in the diagnosis and management of patients with hypertrophic cardiomyopathy", HEART RHYTHM, vol. 17, 2020, pages 142 - 151, XP086044651, DOI: 10.1016/j.hrthm.2019.07.019
GALLOWAY, C.D. ET AL.: "Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram", JAMA CARDIOL, vol. 4, 2019, pages 428 - 436
GAO, M.QUAN, Y.ZHOU, X.H.ZHANG, H.Y.: "PheWAS-Based Systems Genetics Methods for Anti-Breast Cancer Drug Discovery", GENES (BASEL), 2019, pages 10
GERDTS EIZZO RMANCUSI CLOSI MAMANZI NWCANCIELLO G ET AL.: "Left ventricular hypertrophy offsets the sex difference in cardiovascular risk (the Campania Salute Network", INT J CARDIOL, vol. 258, 2018, pages 257 - 61, XP085359512, DOI: 10.1016/j.ijcard.2017.12.086
GERTZ MACOMENZO RFALK RHFERMAND JPHAZENBERG BPHAWKINS PN ET AL.: "Definition of organ involvement and treatment response in immunoglobulin light chain amyloidosis (AL): a consensus opinion from the 10th International Symposium on Amyloid and Amyloidosis, Tours, France", AM J HEMATOL, vol. 79, no. 4, 18 April 2004 (2004-04-18), pages 319 - 28
GERTZ MADISPENZIERI A: "Systemic Amyloidosis Recognition, Prognosis, and Therapy: A Systematic Review", JAMA, vol. 324, no. 1, 2020, pages 79 - 89
GOFF DC, JR.PANDEY DKCHAN FAORTIZ CNICHAMAN MZ: "Congestive heart failure in the United States: is there more than meets the I(CD code)? The Corpus Christi Heart Project", ARCH INTERN MED, vol. 160, no. 2, 2000, pages 197 - 202
GOTO SMAHARA KBEUSSINK-NELSON LIKURA HKATSUMATA YENDO J ET AL.: "Artificial intelligence-enabled fully automated detection of cardiac amyloidosis using electrocardiograms and echocardiograms", NAT COMMUN, vol. 12, no. 1, 2021, pages 2726
GRADMAN AHALFAYOUMI F: "From left ventricular hypertrophy to congestive heart failure: management of hypertensive heart disease", PROG CARDIOVASC DIS, vol. 48, no. 5, 2006, pages 326 - 41, XP026039124, DOI: 10.1016/j.pcad.2006.02.001
HALCOX JPJWAREHAM KCARDEW AGILMORE MBARRY JPPHILLIPS C ET AL.: "Assessment of Remote Heart Rhythm Sampling Using the AliveCor Heart Monitor to Screen for Atrial Fibrillation: The REHEARSE-AF Study", CIRCULATION, vol. 136, no. 19, 2017, pages 1784 - 94
HANCOCK EWDEAL BJMIRVIS DMOKIN PKLIGFIELD PGETTES LS ET AL.: "AHA/ACCF/HRS recommendations for the standardization and interpretation of the electrocardiogram: part V: electrocardiogram changes associated with cardiac chamber hypertrophy: a scientific statement from the American Heart Association Electrocardiography and Arrhythmias Committee", J AM COLL CARDIOL, vol. 53, no. 11, 2009, pages 992 - 1002, XP029650137, DOI: 10.1016/j.jacc.2008.12.015
HANNUN AYRAJPURKAR PHAGHPANAHI MTISON GHBOURN CTURAKHIA NW ET AL.: "Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network", NAT MED, vol. 25, no. 1, 2019, pages 65 - 9, XP036683917, DOI: 10.1038/s41591-018-0268-3
HANNUN, A.Y. ET AL.: "Publisher Correction: Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network", NAT MED, vol. 25, 2019, pages 530, XP036722148, DOI: 10.1038/s41591-019-0359-9
HEART FAILURE SOCITY OF A, HEART RHYTHM S ET AL., 2011 ACCF/AHA GUIDELINES FOR THE DIAGNOSIS AND TREATMENT OF HYPERTOPHIC CARDIOMYOPATHY
HULME OLKHURSHID SWENG LCANDERSON CDWANG EYASHBURNER JM ET AL.: "Development and Validation of a Prediction Model for Atrial Fibrillation Using Electronic Health Records", JACC CLIN ELECTROPHYSIOL, vol. 5, no. 11, 2019, pages 1331 - 41
IANDOLA, F.N. ET AL.: "DenseNet: Implementing Efficient ConvNet Descriptor Pyramids", CORR, 2014
JAPP, A.G.GULATI, A.COOK, S.A.COWIE, M.R.PRASAD, S.K.: "The Diagnosis and Evaluation of Dilated Cardiomyopathy", JAM COLL CARDIOL, vol. 67, 2016, pages 2996 - 3010, XP029618466, DOI: 10.1016/j.jacc.2016.03.590
JOHNSON JNGRIFONI CBOS JMSABER-AYAD MOMMEN SRNISTRI S ET AL.: "Prevalence and clinical correlates of QT prolongation in patients with hypertrophic cardiomyopathy", EUR HEART J, vol. 32, no. 9, 2011, pages 1114 - 20
KARDIAMOBILE SYSTEM 510(K) APPROVAL LETTER
KHURSHID SKEANEY JELLINOR PTLUBITZ SA: "A Simple and Portable Algorithm for Identifying Atrial Fibrillation in the Electronic Medical Record", AM J CARDIOL, vol. 117, no. 2, 2016, pages 221 - 5, XP029377291, DOI: 10.1016/j.amjcard.2015.10.031
KHURSHID SREEDER C.HARRINGTON L.SINGH P.SARMA G.FRIEDMAN S. ET AL.: "Cohort Design and Natural Language Processing to Reduce Bias in Electronic Health Records Research: The Community Care Cohort Project", MEDRXIV, 2021
KO WYSIONTIS KCATTIA ZICARTER REKAPA SOMMEN SR ET AL.: "Detection of Hypertrophic Cardiomyopathy Using a Convolutional Neural Network-Enabled Electrocardiogram", J AM COLL CARDIOL, vol. 75, no. 7, 2020, pages 722 - 33, XP086051355, DOI: 10.1016/j.jacc.2019.12.030
KWON JMJEON KHKIM HMKIM MJLIM SMKIM KH ET AL.: "Comparing the performance of artificial intelligence and conventional diagnosis criteria for detecting left ventricular hypertrophy using electrocardiography", EUROPACE, vol. 22, no. 3, 2020, pages 412 - 9
LAKDAWALA NKTHUNE JJMARON BJCIRINO ALHAVNDRUP OBUNDGAARD H ET AL.: "Electrocardiographic features of sarcomere mutation carriers with and without clinically overt hypertrophic cardiomyopathy", AM J CARDIOL, vol. 108, no. 11, 2011, pages 1606 - 13, XP028108020, DOI: 10.1016/j.amjcard.2011.07.019
LEVIS, J.T.: "ECG diagnosis: hypokalemia", PERM J, vol. 16, 2012, pages 57
LI, A.CHEN, S.QUAN, S.F.POWERS, L.S.ROVEDA, J.M.: "A deep learning-based algorithm for detection of cortical arousal during sleep", SLEEP, 2020, pages 43
LIAO YCOOPER RSMENSAH GAMCGEE DL: "Left ventricular hypertrophy has a greater impact on survival in women than in men", CIRCULATION, vol. 92, no. 4, 1995, pages 805 - 10
LIN GEN-MIN ET AL: "An Electrocardiographic System With Anthropometrics via Machine Learning to Screen Left Ventricular Hypertrophy among Young Adults", IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE, IEEE, USA, vol. 8, 24 April 2020 (2020-04-24), pages 1 - 11, XP011787757, DOI: 10.1109/JTEHM.2020.2990073 *
LITTLEJOHNS, T.J.SUDLOW, C.ALLEN, N.E.COLLINS, R.: "UK Biobank: opportunities for cardiovascular research", EUROPEAN HEART JOURNAL, vol. 40, 2017, pages 1158 - 1166
LIU, C.WANG, F.HU, J.XIONG, H.: "Temporal Phenotyping from Longitudinal Electronic Health Records: A Graph Based Framework", PROCEEDINGS OF THE 21 TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING 705-714 (ASSOCIATION FOR COMPUTING MACHINERY, 2015
LIU, Y.JUN, E.LI, Q.HEER, J.: "Latent Space Cartography: Visual Analysis of Vector Space Embeddings", COMPUTER GRAPHICS FORUM (PROC. EUROVIS, 2019
MAHIN MUHTASHEEM AJWAD ET AL: "Diagnosis of Left Ventricular Hypertrophy from ECG Signals Based on CCS Methodology using SVM", 2021 5TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING AND INFORMATION & COMMUNICATION TECHNOLOGY (ICEEICT), IEEE, 18 November 2021 (2021-11-18), pages 1 - 6, XP034000813, DOI: 10.1109/ICEEICT53905.2021.9667877 *
MAKAVOS GKAPPAAIRIS CTSELEGKIDI MEKARAMITSOS TRIGOPOULOS AGNOUTSIAS M ET AL.: "Hypertrophic cardiomyopathy: an updated review on diagnosis, prognosis, and treatment", HEART FAIL REV, vol. 24, no. 4, 2019, pages 439 - 59, XP036803191, DOI: 10.1007/s10741-019-09775-4
MARON BJ: "Hypertrophic cardiomyopathy: a systematic review", JAMA, vol. 287, no. 10, 2002, pages 1308 - 20
MARTIN ABADI AAPAUL BARHAMEUGENE BREVDOZHIFENG CHEN CCGREG S. CORRADOANDY DAVISJEFFREY DEAN MDSANJAY GHEMAWATIAN GOODFELLOWANDREW , TENSORFLOW: LARGE-SCALE MACHINE LEARNING ON HETEROGENEOUS SYSTEMS, 2015
MCKINNEY W, PANDAS, 2020
MUKHERJEE, D.DHAR, K.SCHWENKER, F.SARKAR, R.: "Ensemble of Deep Learning Models for Sleep Apnea Detection: An Experimental Study", SENSORS (BASEL), 2021, pages 21
MURTAGH BHAMMILL SCGERTZ MAKYLE RATAJIK AJGROGAN M: "Electrocardiographic findings in primary systemic amyloidosis and biopsy-proven cardiac involvement", AM J CARDIOL, vol. 95, no. 4, 2005, pages 535 - 7, XP004760125, DOI: 10.1016/j.amjcard.2004.10.028
PEDREGOSAFVAROQUAUX, G.GRAMFORT, A.MICHEL, V.: "Scikit-learn: Machine Learning in Python", JOURNAL OF MACHINE LEARNING RESEARCH, vol. 12, 2011, pages 2825 - 30
PEGUERO JGLO PRESTI SPEREZ JISSA OBRENES JCTOLENTINO A: "Electrocardiographic Criteria for the Diagnosis of Left Ventricular Hypertrophy", J AM COLL CARDIOL, vol. 69, no. 13, 2017, pages 1694 - 703, XP029956925, DOI: 10.1016/j.jacc.2017.01.037
RAGHUNATH, S. ET AL.: "Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network", NAT MED, vol. 26, 2020, pages 886 - 891, XP037173399, DOI: 10.1038/s41591-020-0870-z
RAPEZZI CMERLINI GQUARTA CCRIVA LLONGHI SLEONE O ET AL.: "Systemic cardiac amyloidoses: disease profiles and clinical courses of the 3 main types", CIRCULATION, vol. 120, no. 13, 2009, pages 1203 - 12
RASMUSSEN, P.V. ET AL.: "Electrocardiographic PR Interval Duration and Cardiovascular Risk: Results From the Copenhagen ECG Study", CAN J CARDIOL, vol. 33, 2017, pages 674 - 681
RAWLINS JBHAN ASHARMA S: "Left ventricular hypertrophy in athletes", EUR J ECHOCARDIOGR, vol. 10, no. 3, 2009, pages 350 - 6
RICKERS CWILKE NMJEROSCH-HEROLD MCASEY SAPANSE PPANSE N ET AL.: "Utility of cardiac magnetic resonance imaging in the diagnosis of hypertrophic cardiomyopathy", CIRCULATION, vol. 112, no. 6, 2005, pages 855 - 61
RIVERA-RUIZ, M.CAJAVILCA, C.VARON, J.: "Einthoven's string galvanometer: the first electrocardiograph", TEX HEART INST J, vol. 35, 2008, pages 174 - 178
RUBERG FLBERK JL: "Transthyretin (TTR) cardiac amyloidosis", CIRCULATION, vol. 126, no. 10, 2012, pages 1286 - 300
SALVATI, M. ET AL.: "Electrocardiographic changes in subarachnoid hemorrhage secondary to cerebral aneurysm. Report of 70 cases", ITALJ NEUROL SCI, vol. 13, 1992, pages 409 - 413
SAMBROOKFRITSCHMANIATIS: "Molecular Cloning: A Laboratory Manual", 1989
SAVAGE DDGARRISON RJKANNEL WBLEVY DANDERSON SJSTOKES J ET AL.: "The spectrum of left ventricular hypertrophy in a general population sample: the Framingham Study", CIRCULATION, vol. 75, 1987, pages 126 - 33
SAVAGE DDSEIDES SFCLARK CEHENRY WLMARON BJROBINSON FC ET AL.: "Electrocardiographic findings in patients with obstructive and nonobstructive hypertrophic cardiomyopathy", CIRCULATION, vol. 58, 1978, pages 402 - 8
SCHILLACI GVERDECCHIA PBORGIONI CCIUCCI AGUERRIERI MZAMPI I ET AL.: "Improved electrocardiographic diagnosis of left ventricular hypertrophy", AM J CARDIOL, vol. 74, no. 7, 1994, pages 714 - 9, XP023279747, DOI: 10.1016/0002-9149(94)90316-6
SNOEK, J.LAROCHELLE, H.ADAMS, R.P.: "Proceedings of the 25th International Conference on Neural Information Processing Systems", vol. 2, 2012, CURRAN ASSOCIATES INC., article "Practical Bayesian optimization of machine learning algorithms", pages: 2951 - 2959
SUN, H. ET AL.: "Sleep staging from electrocardiography and respiration with deep learning", SLEEP, 2020, pages 43
SURAWICZ, B: "Relationship between electrocardiogram and electrolytes", AM HEART J, vol. 73, 1967, pages 814 - 834, XP022926072, DOI: 10.1016/0002-8703(67)90233-5
TAN, N.Y.WITT, C.M.OH, J.K.CHA, Y.M.: "Left Bundle Branch Block: Current and Future Perspectives", CIRC ARRHYTHM ELECTROPHYSIOL, vol. 13, 2020, pages e008239
TOMA, L. ET AL.: "Electrocardiographic Changes in Liver Cirrhosis-Clues for Cirrhotic Cardiomyopathy", MEDICINA (KAZINAS), 2020, pages 56
TROBEC, R.TOMASIC, I.: "Synthesis of the 12-lead electrocardiogram from differential leads", IEEE TRANS INF TECHNOL BIOMED, vol. 15, 2011, pages 615 - 621, XP011329660, DOI: 10.1109/TITB.2011.2159236
URTNASAN, E.PARK, J.U.JOO, E.Y.LEE, K.J.: "Identification of Sleep Apnea Severity Based on Deep Learning from a Short-term Normal ECG", J KOREAN MED SCI, vol. 35, 2020, pages e399
VAKILI BAOKIN PMDEVEREUX RB: "Prognostic implications of left ventricular hypertrophy", AM HEART J, vol. 141, no. 3, 2001, pages 334 - 41
VAN MIEGHEM, C.SABBE, M.KNOCKAERT, D.: "The clinical value of the ECG in noncardiac conditions", CHEST, vol. 125, 2004, pages 1561 - 1576
VAN ROSSUM GDRAKE FL, PYTHON 3 REFERENCE MANUAL, 2009
VERWEIJ, N. ET AL.: "The Genetic Makeup of the Electrocardiogram", CELL SYST, vol. 11, 2020, pages 229 - 238
WANG, L.MU, Y.ZHAO, J.WANG, X.CHE, H.: "Deep Learning Model for Non-Invasive, Real-Time Diagnosis of Prediabetes through Electrocardiograms", SENSORS (BASEL), 2020, pages 20
XIAO, L.WANG, J.: "LatentVis: Investigating and Comparing Variational AutoEncoders via Their Latent Space", 3RD WORKSHOP ADVANCES IN INTERPRETABLE MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE (AIMLAI) OF CIKM, 2020
YAMAMOTO HYOKOCHI T: "Transthyretin cardiac amyloidosis: an update on diagnosis and treatment", ESC HEART FAIL, vol. 6, no. 6, 2019, pages 1128 - 39
YAMASHITA, R. ET AL.: "Convolutional neural networks: an overview and application in radiology", INSIGHTS IMAGING, vol. 9, 2018, pages 611 - 629, XP055580998, DOI: 10.1007/s13244-018-0639-9
YASIN, O.Z. ET AL.: "Noninvasive blood potassium measurement using signal-processed, single-lead ecg acquired from a handheld smartphone", J ELECTROCARDIOL, vol. 50, 2017, pages 620 - 625, XP085159364, DOI: 10.1016/j.jelectrocard.2017.06.008
ZHAO, J. ET AL.: "Learning from Longitudinal Data in Electronic Health Record and Genetic Data to Improve Cardiovascular Event Prediction", SCI REP, vol. 9, 2019, pages 717
ZHU, XIAODAN ET AL.: "Long short-term memory over recursive structures", INTERNATIONAL CONFERENCE ON MACHINE LEARNING, 2015

Similar Documents

Publication Publication Date Title
Hatamizadeh et al. Fastervit: Fast vision transformers with hierarchical attention
Cui et al. MDSSD: multi-scale deconvolutional single shot detector for small objects
US9853592B2 (en) Method and device for controlling an energy-generating system which can be operated with a renewable energy source
CN113011365A (zh) 一种结合轻量化网络的目标检测方法
CN103593799B (zh) 自然人信息设置方法、系统及相应的好友推荐方法、系统
GB2600872A (en) System-aware selective quantization for performance optimized distributed deep learning
WO2024072744A1 (fr) Procédés et systèmes pour l'annotation de données génomiques
CN115131476A (zh) 虚拟对象的骨骼绑定迁移方法、装置、设备及存储介质
WO2024072849A1 (fr) Discrimination activée par intelligence artificielle de maladie et d'étiologie de maladie
Ortiz et al. Energy-efficient on-board radio resource management for satellite communications via neuromorphic computing
CN113554624A (zh) 异常检测方法、装置及计算机存储介质
CN109685805A (zh) 一种图像分割方法及装置
CN104866460B (zh) 一种基于SoC的容错自适应可重构系统与方法
CN115810293B (zh) 一种多台无人驾驶航空器的联动控制方法、系统和介质
CN108009370B (zh) 一种结构应力敏度求解方法
US11640581B2 (en) Methods for improved delta velocity determination using machine learning and devices thereof
Zhang et al. A novel method for constructing ensemble classifiers
US9754134B2 (en) Creating mechanical stamps to produce machine-readable optical labels
US20250088431A1 (en) Method and apparatus for distributed inference
CN109828857B (zh) 车辆故障原因定位方法、装置、设备和存储介质
CN111275062A (zh) 模型训练方法、装置、服务器及计算机可读存储介质
CN112230615B (zh) 核电厂安全级dcs优选通信网络冗余处理方法、装置和介质
CN117151436A (zh) 一种应急救援演习方法、系统及介质
CN106504250A (zh) 图像块标识匹配方法和远端服务器
CN115705487A (zh) Ai计算的校验方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23794142

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 23794142

Country of ref document: EP

Kind code of ref document: A1