Search

Joseph S Ross,1–4 Jonathan Bates,4 Craig S Parzynski,4 Joseph G Akar,4,5 Jeptha P Curtis,4,5 Nihar R Desai,4,5 James V Freeman,4,5 Ginger M Gamble,4 Richard Kuntz,6 Shu-Xia Li,4 Danica Marinac-Dabic,7 Frederick A Masoudi,8 Sharon-Lise T Normand,9,10 Isuru Ranasinghe,11 Richard E Shaw,12 Harlan M Krumholz2–5 1Section of General Medicine, Department of Medicine, 2Robert Wood Johnson Foundation Clinical Scholars Program, Yale School of Medicine, 3Department of Health Policy and Management, Yale School of Public Health, 4Center for Outcomes Research and Evaluation, Yale–New Haven Hospital, 5Section of Cardiovascular Medicine, Department of Medicine, Yale School of Medicine, New Haven, CT, 6Medtronic Inc, Minneapolis, MN, 7Division of Epidemiology, Center for Devices and Radiological Health, US Food and Drug Administration, Silver Spring, MD, 8Division of Cardiology, Department of Medicine, University of Colorado, Aurora, CO, 9Department of Health Care Policy, Harvard Medical School, 10Department of Biostatistics, Harvard TH Chan School of Public Health, Boston, MA, USA; 11Discipline of Medicine, University of Adelaide, Adelaide, SA, Australia; 12Department of Clinical Informatics, California Pacific Medical Center, San Francisco, CA, USA Background: Machine learning methods may complement traditional analytic methods for medical device surveillance.Methods and results: Using data from the National Cardiovascular Data Registry for implantable cardioverter–defibrillators (ICDs) linked to Medicare administrative claims for longitudinal follow-up, we applied three statistical approaches to safety-signal detection for commonly used dual-chamber ICDs that used two propensity score (PS) models: one specified by subject-matter experts (PS-SME), and the other one by machine learning-based selection (PS-ML). The first approach used PS-SME and cumulative incidence (time-to-event), the second approach used PS-SME and cumulative risk (Data Extraction and Longitudinal Trend Analysis [DELTA]), and the third approach used PS-ML and cumulative risk (embedded feature selection). Safety-signal surveillance was conducted for eleven dual-chamber ICD models implanted at least 2,000 times over 3 years. Between 2006 and 2010, there were 71,948 Medicare fee-for-service beneficiaries who received dual-chamber ICDs. Cumulative device-specific unadjusted 3-year event rates varied for three surveyed safety signals: death from any cause, 12.8%–20.9%; nonfatal ICD-related adverse events, 19.3%–26.3%; and death from any cause or nonfatal ICD-related adverse event, 27.1%–37.6%. Agreement among safety signals detected/not detected between the time-to-event and DELTA approaches was 90.9% (360 of 396, k=0.068), between the time-to-event and embedded feature-selection approaches was 91.7% (363 of 396, k=–0.028), and between the DELTA and embedded feature selection approaches was 88.1% (349 of 396, k=–0.042).Conclusion: Three statistical approaches, including one machine learning method, identified important safety signals, but without exact agreement. Ensemble methods may be needed to detect all safety signals for further evaluation during medical device surveillance. Keywords: implanted cardioverter–defibrillator, methodology, surveillance

Background: Cardiovascular observational registries characterise patients and describe the manner and use of therapeutic strategies. They facilitate analyses on the quality of care among participating institutions and document variations in clinical practice which can be benchmarked against best practice recommendations. The Cooperative National Registry of Acute Coronary care, Guideline Adherence and Clinical Events (CONCORDANCE) is an Australian observational registry that describes management and outcomes in patients with acute coronary syndromes (ACS) and feeds back both performance and outcome measures to participating hospitals. Methods: The CONCORDANCE registry has been designed within a comparative effectiveness research (CER) framework to collect and report data from hospitals located in geographically diverse regions of Australia. Information including patient demographics, presenting characteristics, past medical history, in-hospital management and outcomes at six months and two years are entered into a web-based database using an electronic clinical record form (eCRF). Individual hospital information is returned to the sites in a real time confidential report detailing information on key performance indicator (KPI) process measures and outcomes benchmarked against the aggregated study cohort. Governance rules ensure data security and protect patient and clinician confidentiality. Consistent with a CER framework, additional characteristics of the registry include: (a) the capacity to evaluate associations between the inter and intra hospital systems and the provision of evidence based care and outcomes, (b) ongoing data collection from representative hospitals which allow spatial and temporal analysis of change in practice and the application of treatment modalities in the real world setting and (c) the provision of a data spine for quality improvement strategies and practical clinical trials. Conclusion: The CONCORDANCE registry is a clinician-driven initiative describing clinical care for ACS patients admitted to Australian hospitals. The registry generates high quality data which is fed back to clinicians, and key stakeholders in ACS care. Using a CER approach, the registry describes the translation of randomised trial evidence into practice, and provides insights into strategies that could improve care and ultimately patient outcomes. Refereed/Peer-reviewed