Digital Health Digest: Curated by Dr. Jennifer Joe – Digital Biomarkers

JMIR Publications?publishes 30 journals covering the breadth of digital health. The flagship title,?Journal of Medical Internet Research, has been a leader Open Access for over 20 years and is the largest journal in the field.

In my role as JMIR Publications Chief Ambassador, my focus is translating knowledge and making traditional peer-reviewed scientific information and data more accessible. The goal of this series it to highlight excellent, evidence-based medicine for my digital health followers and enthusiasts, particularly those investing in related startups.

We should all be working towards meaningful digital health tools to improve patient care.

Over the last 10 years, digital sensing technologies such as smartphones, smartwatches, wearables, ingestibles, and implantables have become omnipresent in our daily lives, and are increasingly used by individuals and clinicians to capture health outcomes or behavioral and physiological characteristics of individuals. As the data output from these devices are used more in clinical practice, we call them “digital clinical measures.”

I recently had the pleasure of sitting down with Mr. John Patena of the Brown-Lifespan Center for Digital Health to discuss his paper, “Recent Academic Research on Clinically Relevant Digital Measures: Systematic Review,” which was done in collaboration with the Digital Medicine Society (DiME). Mr. Patena and team performed a systematic review to characterize the nature of academic research on digital clinical measures and to compare and contrast the types of sensors used and the sources of funding support for specific subareas of this research.

The search retrieved 4240 articles of interest. The authors found that the top five research subareas included operations research, analytical validation, usability and utility, verification, and clinical validation. The three most underrepresented areas of research into digital clinical measures were ethics, security, and data rights and governance. Movement and activity trackers were the most commonly studied sensor type, and physiological (mechanical) sensors were the least frequently studied. The authors found that government agencies are providing the most funding for research on digital clinical measures, followed by independent foundations and industries, with the remaining 12% of these studies completely unfunded.

With “digital clinical measures,” the idea is to combine these novel data sources to develop “digital biomarkers.” In the simplest terms, digital biomarkers are a specific collection of objective, quantifiable, physiological, and behavioral data that are collected and measured using digital devices such as portables, wearables, implantables, or digestibles that are predictive, diagnostic, or prognostic of a specific disease or disease state.

Here, I highlight interesting digital biomarker research to give you specific examples and to lay the foundation for you to think about the potential for digital biomarkers to fundamentally change how medicine is currently practiced.

Digital Biomarkers for Depression Screening With Wearable Devices: Cross-sectional Study With Machine Learning Modeling from corresponding author, Josip Car, MD, PhD (Centre for Population Health Sciences, Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore) published on October 25, 2021 – The objective of this study was to examine the predictive ability of digital biomarkers, based on sensor data from consumer-grade wearables, to detect risk of depression in a working population. This was a cross-sectional study of 290 healthy working adults. Participants wore Fitbit Charge 2 devices for 14 consecutive days and completed a health survey, including screening for depressive symptoms. The authors then extracted a range of known and novel digital biomarkers characterizing physical activity, sleep patterns, and circadian rhythms from wearables using steps, heart rate, energy expenditure, and sleep data. The authors found that a greater severity of depressive symptoms was robustly associated with greater variation of nighttime heart rate between 2 AM and 4 AM and between 4 AM and 6 AM. Despite several reliable associations, the authors note that their evidence showed limited ability of digital biomarkers to detect depression in the whole sample of working adults.

Dissecting Digital Card Games to Yield Digital Biomarkers for the Assessment of Mild Cognitive Impairment: Methodological Approach and Exploratory Study by corresponding author, Karsten Gielis, MSc, PhD (e-Media Research Lab, Katholieke Universiteit Leuven, Leuven, Belgium) published on November 4, 2021 – The paper aimed to explore how the player actions of Klondike Solitaire relate to cognitive functions and to what extent the digital biomarkers derived from these player actions are indicative of mild cognitive impairment (MCI). Mild cognitive impairment (MCI), the intermediate cognitive status between normal cognitive decline and pathological decline, is an important clinical construct for signaling possible prodromes of dementia. However, this condition is underdiagnosed. 23 healthy participants and 23 participants living with MCI were asked to play 3 rounds of Klondike Solitaire, which took 17 minutes on average to complete. Of the 23 potential digital biomarkers, 12 (52%) were revealed by the generalized linear mixed model analysis to have sizeable effects and significance levels. The analysis indicates sensitivity of the derived digital biomarkers to MCI. The authors concluded that commercial off-the-shelf games such as digital card games show potential as a complementary tool for screening and monitoring cognition.

Using Acoustic Speech Patterns From Smartphones to Investigate Mood Disorders: Scoping Review - by corresponding author,?Frederick Sundram, BMedSc, MB BCh BAO, FRCPsych, MA, MSc, PhD (Department of Psychological Medicine, University of Auckland, Auckland, New Zealand) published on September 17, 2021 - The aim of this review is to synthesize research on using speech patterns from smartphones to diagnose and monitor mood disorders. Literature searches of major databases, Medline, PsycInfo, EMBASE, and CINAHL, initially identified 832 relevant articles using the search terms “mood disorders”, “smartphone”, “voice analysis”, and their variants. Only 13 studies met inclusion criteria: use of a smartphone for capturing voice data, focus on diagnosing or monitoring a mood disorder(s), clinical populations recruited prospectively, and in the English language only. Studies showed that voice data alone had reasonable accuracy in predicting mood states and mood fluctuations based on objectively monitored speech patterns. While a fusion of different sensor modalities revealed the highest accuracy (97.4%), nearly 80% of included studies were pilot trials or feasibility studies without control groups and had small sample sizes ranging from 1 to 73 participants. The authors concluded that the current body of evidence supports the value of speech patterns to monitor, classify, and predict mood states in real time. However, many challenges remain around the robustness, cost-effectiveness, and acceptability of such an approach and further work is required.

These studies show early we are in developing true digital biomarkers that can provide as much diagnostic and prognostic significance as established biomarkers of disease. However, with more time, more data, and advances in algorithm development, we could be using everything from Fitbits to Solitaire card games to acoustic speech patterns to diagnose disease and disease progression. How exciting!

As a reminder, driven by a commitment to democratizing access to important scientific and healthcare-related information, JMIR Publications is a pioneer of open-access and open science.

That means that all articles are free and available for anyone in the world to read the entire research article along with supporting images, graphics, and data.

Feel free to share with friends and colleagues.

#JMIRPublications #JMIR #DigitalHealth #DigitalBiomarkers #Biomarkers #SeriousGames #Smartphones #Fitbit