Machine learning for subtype definition and risk prediction in heart failure, acute coronary syndromes and atrial fibrillation: systematic review of validity and clinical utility

BMC Medicine

Johanna Mielke¹  Daniel F. Freitag¹  Ghazaleh Fatemifar²  Suliang Chen²  Spiros Denaxas³  Harry Hemingway⁴  R. Thomas Lumbers⁵  Amitava Banerjee⁶  Mohamad Zeina⁷  Simrat Gill⁸  Dipak Kotecha⁹ 

[1] Bayer AG, Division Pharmaceuticals, Open Innovation & Digital Technologies, Wuppertal, Germany;Institute of Health Informatics, University College London, 222 Euston Road, NW1 2DA, London, UK;Health Data Research UK, University College London, London, UK;Institute of Health Informatics, University College London, 222 Euston Road, NW1 2DA, London, UK;Health Data Research UK, University College London, London, UK;The Alan Turing Institute, London, UK;Institute of Health Informatics, University College London, 222 Euston Road, NW1 2DA, London, UK;Health Data Research UK, University College London, London, UK;University College London Hospitals Biomedical Research Centre (UCLH BRC), London, UK;Institute of Health Informatics, University College London, 222 Euston Road, NW1 2DA, London, UK;Health Data Research UK, University College London, London, UK;University College London Hospitals NHS Trust, 235 Euston Road, London, UK;Institute of Health Informatics, University College London, 222 Euston Road, NW1 2DA, London, UK;Health Data Research UK, University College London, London, UK;University College London Hospitals NHS Trust, 235 Euston Road, London, UK;Barts Health NHS Trust, The Royal London Hospital, Whitechapel Rd, London, UK;Medical School, King’s College London, London, UK;University of Birmingham Institute of Cardiovascular Sciences and University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK;University of Birmingham Institute of Cardiovascular Sciences and University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK;Department of Cardiology, University Medical Centre Utrecht, Utrecht, the Netherlands;

关键词: Cardiovascular disease;    Machine learning;    Subtype;    Risk prediction;    Informatics;    Systematic review;   

DOI  :  10.1186/s12916-021-01940-7

来源: Springer

【 摘 要 】

BackgroundMachine learning (ML) is increasingly used in research for subtype definition and risk prediction, particularly in cardiovascular diseases. No existing ML models are routinely used for cardiovascular disease management, and their phase of clinical utility is unknown, partly due to a lack of clear criteria. We evaluated ML for subtype definition and risk prediction in heart failure (HF), acute coronary syndromes (ACS) and atrial fibrillation (AF).MethodsFor ML studies of subtype definition and risk prediction, we conducted a systematic review in HF, ACS and AF, using PubMed, MEDLINE and Web of Science from January 2000 until December 2019. By adapting published criteria for diagnostic and prognostic studies, we developed a seven-domain, ML-specific checklist.ResultsOf 5918 studies identified, 97 were included. Across studies for subtype definition (n = 40) and risk prediction (n = 57), there was variation in data source, population size (median 606 and median 6769), clinical setting (outpatient, inpatient, different departments), number of covariates (median 19 and median 48) and ML methods. All studies were single disease, most were North American (n = 61/97) and only 14 studies combined definition and risk prediction. Subtype definition and risk prediction studies respectively had limitations in development (e.g. 15.0% and 78.9% of studies related to patient benefit; 15.0% and 15.8% had low patient selection bias), validation (12.5% and 5.3% externally validated) and impact (32.5% and 91.2% improved outcome prediction; no effectiveness or cost-effectiveness evaluations).ConclusionsStudies of ML in HF, ACS and AF are limited by number and type of included covariates, ML methods, population size, country, clinical setting and focus on single diseases, not overlap or multimorbidity. Clinical utility and implementation rely on improvements in development, validation and impact, facilitated by simple checklists. We provide clear steps prior to safe implementation of machine learning in clinical practice for cardiovascular diseases and other disease areas.

【 授权许可】

CC BY