Machine Learning for Cardiovascular Outcomes From Wearable Data: Systematic Review From a Technology Readiness Level Point of View

Abstract

Background Wearable technology has the potential to improve cardiovascular health monitoring by using machine learning. Such technology enables remote health monitoring and allows for the diagnosis and prevention of cardiovascular diseases. In addition to the detection of cardiovascular disease, it can exclude this diagnosis in symptomatic patients, thereby preventing unnecessary hospital visits. In addition, early warning systems can aid cardiologists in timely treatment and prevention. Objective This study aims to systematically assess the literature on detecting and predicting outcomes of patients with cardiovascular diseases by using machine learning with data obtained from wearables to gain insights into the current state, challenges, and limitations of this technology. Methods We searched PubMed, Scopus, and IEEE Xplore on September 26, 2020, with no restrictions on the publication date and by using keywords such as “wearables,” “machine learning,” and “cardiovascular disease.” Methodologies were categorized and analyzed according to machine learning–based technology readiness levels (TRLs), which score studies on their potential to be deployed in an operational setting from 1 to 9 (most ready). Results After the removal of duplicates, application of exclusion criteria, and full-text screening, 55 eligible studies were included in the analysis, covering a variety of cardiovascular diseases. We assessed the quality of the included studies and found that none of the studies were integrated into a health care system (TRL<6), prospective phase 2 and phase 3 trials were absent (TRL<7 and 8), and group cross-validation was rarely used. These issues limited these studies’ ability to demonstrate the effectiveness of their methodologies. Furthermore, there seemed to be no agreement on the sample size needed to train these studies’ models, the size of the observation window used to make predictions, how long participants should be observed, and the type of machine learning model that is suitable for predicting cardiovascular outcomes. Conclusions Although current studies show the potential of wearables to monitor cardiovascular events, their deployment as a diagnostic or prognostic cardiovascular clinical tool is hampered by the lack of a realistic data set and proper systematic and prospective evaluation.

Adaptation of the technology readiness levels for impact assessment in implementation sciences: The TRL-IS checklist

“…2 ). Of these, four are review articles [ [40] , [41] , [42] , [43] ], four are research articles [ 19 , [44] , [45] , [46] ], one is a science-policy brief [ 47 ], one is a conference paper [ 48 ], and one is a research report [ 18 ]. Excluding the reviews, two studies were located in Spain, two in France, and one each in USA, Ecuador, and Guatemala.…”

“…Selected studies most frequently referenced or used the US Department of Energy version of the TRL [ 40 , 42 , 43 ], and the HORIZON 2020 version [ 19 , 45 , 48 ]. Other versions referenced or used are US Department of Health and Human Services [ 18 ], US Department of Defense [ 47 ], TRL scale for development of innovative medical devices and drugs [ 44 ], and TRL for medical machine learning [ 41 ]. One study did not reference a TRL [ 46 ].…”

“…The utilisation of Technology Readiness Levels (TRLs) in the context of health, medicine, and social science studies is particularly prominent in the development and review of health monitoring technologies. Specifically, five studies, namely Cruz et al [ 40 ], Fattal et al [ 46 ], Jahfari et al [ 41 ], Lapierre et al [ 42 ], and Liu et al [ 43 ], have focused on this area, demonstrating an emphasis on the advancement and assessment of health monitoring technologies. Of these studies, four are comprehensive reviews that aim to enhance understanding of the current state of knowledge.…”

Smart Home Technology Solutions for Cardiovascular Diseases: A Systematic Review

“…A study observed that activity data from wearables could monitor CVD patients remotely, enabling safer and higher resolution monitoring of patients [105]. However, on the downside, although current studies highlight the wearables' potential to monitor cardiovascular events, the lack of a real data set and proper systematic and prospective evaluation hampers their deployment as a diagnostic or prognostic cardiovascular clinical tool [106]. Additionally, to date, wearable devices possess challenges in cardiovascular care, such as device accuracy, clinical validity, a lack of standardised regulatory policies and concerns for patient privacy hindering the widespread adoption of smart wearable technologies in clinical practice [32].…”

A Digital Infrastructure for Cardiovascular Patient Care Based on Mobile Health Data and Patient-Reported Outcomes: Concept Details of the Helios TeleWear Project Including Preliminary Experiences

“…Patients with heart failure (HF) [ 8 ] and coronary artery disease [ 9 , 10 ] may also benefit from mHealth interventions; however, further research is needed as study results are in part inconsistent [ 11 , 12 ], and limitations with respect to patients’ digital capabilities exist [ 13 ]. Moreover, mHealth technologies are not yet implemented routinely in CVD patient care, mostly due to the lack of solid data [ 14 ].…”