The era of big data in medicine
1is undoubtedly upon us, and the volume of data available to clinicians and researchers for predictive analytics will continue to expand as we increasingly incorporate information from electronic health records, wearable biosensors, genomics, proteomics, and other metabolomics data in the future.
- Shah ND
- Steyerberg EW
- Kent DM
Big data and predictive analytics: recalibrating expectations.
JAMA. 2018; 320: 27-28
2With this explosion in data, there is increasing interest in—and enthusiasm for—the potential of artificial intelligence (particularly predictive analytics based on machine learning [ML] approaches) to usher in an era of data-driven precision medicine. In fact, the Food and Drug Administration has already approved a number of ML products for use in cardiology (such as the AliveCor Heart Monitor [AliveCor Inc, Mountain View, California] for detecting atrial fibrillation) and ML-derived polygenic risk scores have been reported for several cardiac conditions.
- McAlister FA
- Laupacis A
- Armstrong PW
Finding the right balance between precision medicine and personalized care.
CMAJ. 2017; 189: E1065-E1068
3However, the systematic review by Cho et al.,
- Quer G
- Arnaout R
- Henne M
- Arnaout R
Machine learning and the future of cardiovascular care.
J Am Coll Cardiol. 2021; 77: 300-313
4comparing the performance of predictive models generated by ML methods with those arising from conventional statistical methods in this issue of the Canadian Journal of Cardiology is a sobering reminder that, as Chen and Asch warned, “machine learning now rides atop the peak of inflated expectations.”
- Cho SM
- Austin PC
- Ross HJ
- et al.
Machine learning compared with conventional statistical models for predicting myocardial infarction readmission and mortality: a systematic review.
Can J Cardiol. 2021; 37: 1207-1214
- Chen JH
- Asch SM
Machine learning and prediction in medicine: beyond the peak of inflated expectations.
N Engl J Med. 2017; 376: 2507-2509
To read this article in full you will need to make a payment
Purchase one-time access:Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
One-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:Subscribe to Canadian Journal of Cardiology
Already a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
- Big data and predictive analytics: recalibrating expectations.JAMA. 2018; 320: 27-28
- Finding the right balance between precision medicine and personalized care.CMAJ. 2017; 189: E1065-E1068
- Machine learning and the future of cardiovascular care.J Am Coll Cardiol. 2021; 77: 300-313
- Machine learning compared with conventional statistical models for predicting myocardial infarction readmission and mortality: a systematic review.Can J Cardiol. 2021; 37: 1207-1214
- Machine learning and prediction in medicine: beyond the peak of inflated expectations.N Engl J Med. 2017; 376: 2507-2509
- A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models.J Clin Epidemiol. 2019; 110: 12-22
- for the Evaluating diagnostic tests and prediction models Topic Group of the STRATOS initiative. Calibration: the Achilles heel of predictive analytics.BMC Med. 2019; 17: 230
- Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement.BMJ. 2015; 350: g7594
- PROBAST: a tool to assess the risk of bias and applicability of prediction model studies.Ann Intern Med. 2019; 170: 51-58
- Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs.JAMA. 2016; 316: 2402-2410
- for the CAMELYON16 Consortium. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer.JAMA. 2017; 318: 2199-2210
- Usefulness of machine learning-based detection and classification of cardiac arrhythmias with 12-lead electrocardiograms.Can J Cardiol. 2021; 37: 94-104
- AI can be sexist and racist: it's time to make it fair.Nature. 2018; 559: 324-326
- Machine learning in cardiovascular medicine: are we there yet?.Heart. 2018; 104: 1156-1164
- Biomedical data privacy: problems, perspectives, and recent advances.J Am Med Inform Assoc. 2013; 20: 2-6
- Artificial intelligence in health care: will the value match the hype?.JAMA. 2019; 321: 2281-2282
- Prognosis Research Strategy (PROGRESS) 3: prognostic model research.PLoS Med. 2013; 10e1001381
- From knowledge to practice in chronic cardiovascular disease: a long and winding road.J Am Coll Cardiol. 2004; 43: 1738-1742
- The role of physicians in the era of big data.Can J Cardiol. 2020; 36: 19-21
Published online: March 09, 2021
Accepted: March 2, 2021
Received: February 16, 2021
See article by Cho et al., pages 1207–1214 of this issue.
See page 1158 for disclosure information.
© 2021 Canadian Cardiovascular Society. Published by Elsevier Inc. All rights reserved.
ScienceDirectAccess this article on ScienceDirect
- Machine Learning Compared With Conventional Statistical Models for Predicting Myocardial Infarction Readmission and Mortality: A Systematic ReviewCanadian Journal of CardiologyVol. 37Issue 8
- PreviewMachine learning (ML) methods are increasingly used in addition to conventional statistical modelling (CSM) for predicting readmission and mortality in patients with myocardial infarction (MI). However, the two approaches have not been systematically compared across studies of prognosis in patients with MI.