Domain Shifts in Machine Learning Based Covid-19 Diagnosis From Blood Tests.
Many previous studies claim to have developed machine learning models that diagnose COVID-19 from blood tests. However, we hypothesize that changes in the underlying distribution of the data, so called domain shifts, affect the predictive performance and reliability and are a reason for the failure...
| Publicado en: | Journal of Medical Systems Vol. 46; no. 5; pp. 1 - 13 |
|---|---|
| Autores principales: | , , , , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Springer Nature
May2022
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=156788437&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 156788437 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 01485598 4N0 jtl: Journal of Medical Systems issn: 01485598 maglogo: N pubinfo: dt: May2022 vid: 46 iid: 5 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 156788437 156788437 156788437 10.1007/s10916-022-01807-1 156788437 ppf: 1 ppct: 12 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Domain Shifts in Machine Learning Based Covid-19 Diagnosis From Blood Tests. aug: au: Roland, Theresa Böck, Carl Tschoellitsch, Thomas Maletzky, Alexander Hochreiter, Sepp Meier, Jens Klambauer, Günter affil: ELLIS Unit Linz, LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria sug: subj: Machine Learning COVID-19 Diagnosis Hematologic Tests COVID-19 Mortality Human Reverse Transcriptase Polymerase Chain Reaction COVID-19 Testing Mutation Risk Assessment ab: Many previous studies claim to have developed machine learning models that diagnose COVID-19 from blood tests. However, we hypothesize that changes in the underlying distribution of the data, so called domain shifts, affect the predictive performance and reliability and are a reason for the failure of such machine learning models in clinical application. Domain shifts can be caused, e.g., by changes in the disease prevalence (spreading or tested population), by refined RT-PCR testing procedures (way of taking samples, laboratory procedures), or by virus mutations. Therefore, machine learning models for diagnosing COVID-19 or other diseases may not be reliable and degrade in performance over time. We investigate whether domain shifts are present in COVID-19 datasets and how they affect machine learning methods. We further set out to estimate the mortality risk based on routinely acquired blood tests in a hospital setting throughout pandemics and under domain shifts. We reveal domain shifts by evaluating the models on a large-scale dataset with different assessment strategies, such as temporal validation. We present the novel finding that domain shifts strongly affect machine learning models for COVID-19 diagnosis and deteriorate their predictive performance and credibility. Therefore, frequent re-training and re-assessment are indispensable for robust models enabling clinical utility. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|