Potential of machine learning methods to identify patients with nonvalvular atrial fibrillation.
Aim: Nonvalvular atrial fibrillation (NVAF) is associated with an increased risk of stroke however many patients are diagnosed after onset. This study assessed the potential of machine-learning algorithms to detect NVAF. Materials & methods: A retrospective database study using a Japanese claims dat...
| Publicado en: | Future Cardiology Vol. 16; no. 1; pp. 43 - 52 |
|---|---|
| Autores principales: | , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Taylor & Francis Ltd
Jan2020
|
| 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=141102136&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 141102136 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 14796678 3CMM jtl: Future Cardiology issn: 14796678 maglogo: N pubinfo: dt: Jan2020 vid: 16 iid: 1 pid: 377 pub: Taylor & Francis Ltd place: Philadelphia, Pennsylvania artinfo: ui: 141102136 141102136 NLM31793345 141102136 10.2217/fca-2019-0056 NLM31793345 141102136 ppf: 43 ppct: 9 formats: tig: atl: Potential of machine learning methods to identify patients with nonvalvular atrial fibrillation. aug: au: Suzuki, Ryoko Katada, Jun Ramagopalan, Sreeram McDonald, Laura affil: Cardiovascular Medical, Bristol-Myers Squibb K.K., Tokyo, Japan sug: subj: Stroke Prevention and Control Atrial Fibrillation Diagnosis Algorithms Male Prospective Studies Retrospective Design Risk Factors Stroke Etiology Atrial Fibrillation Complications Aged Female Human Aged: 65+ years Male Female ab: Aim: Nonvalvular atrial fibrillation (NVAF) is associated with an increased risk of stroke however many patients are diagnosed after onset. This study assessed the potential of machine-learning algorithms to detect NVAF. Materials & methods: A retrospective database study using a Japanese claims database. Patients with and without NVAF were selected. 41 variables were included in different classification algorithms. Results: Machine learning algorithms identified NVAF with an area under the curve of >0.86; corresponding sensitivity/specificity was also high. The stacking model which combined multiple algorithms outperformed single-model approaches (area under the curve ≥0.90, sensitivity/specificity ≥0.80/0.82), although differences were small. Conclusion: Machine-learning based algorithms can detect atrial fibrillation with accuracy. Although additional validation is needed, this methodology could encourage a new approach to detect NVAF. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|