About this Research Topic
Our individual and collective existence has become increasingly digitized and interconnected. This includes nearly every aspect of our health, such as encounters with the health care system and public health, daily exercise routines, food consumption habits, health-seeking behaviors, and interactions with social media. The ever-increasing availability and scope of data generated and stored from these activities broadly presents new opportunities to gain insights into our most challenging health problems at the personal and population level. However, a tangible, sustainable, and equitable impact on health will require many innovations in the analysis and interpretation of observational data generated by these emerging technologies. This Research Topic will showcase the cutting-edge work of researchers who are at the forefront of building the next generation of tools that can harness the wealth of raw data generated from our digitized lives to improve individual health outcomes and thereby society at large.
The central goal of this Research Topic is to present work from leading physicians, scientists, researchers, and engineers whose efforts lie in aggregating and processing vast pools of digital health data towards the goal of improving health outcomes. Major challenges in the field include ensuring data quality, statistical problems in predicting and inferring with highly complex data, the lack of implementation trials, end-user engagement, inequitable performance for under-represented populations, and deployment in resource-limited settings, to name just a few. Without solutions to these problems, the massive amounts of health-applicable digital data generated daily will remain unusable. By bringing forth state-of-the-art interdisciplinary research we aim to inspire individuals from diverse backgrounds to engage and collaborate within this burgeoning field, as well as advancing the science necessary to solve its problems.
Articles that are within the scope of this Research Topic include (but are not limited to):
- Use of publicly available text and image datasets for inference about a health issue, including disease epidemiology, diagnostics, disease progression modeling, and comparative effectiveness
- Applications of machine learning to non-traditional data sources such as wearable sensors, social media repositories, cellular phones, and internet search engines, for personal and population health
- Research on improving prediction and inference from passively collected data, from non-traditional data sources or observational datasets characterized by sparse, noisy, high-dimensional, biased, and dynamic data
- Applications of digital health data to ameliorate health problems in resource-limited settings
- Exploration of fairness and health equity for machine learning algorithms trained on digital health data
- Implementation trials that evaluate the real-world impact of a digital health tool
Articles may be in the form of original research, review articles, case studies, and brief reports.
The central goal of this Research Topic is to present work from leading physicians, scientists, researchers, and engineers whose efforts lie in aggregating and processing vast pools of digital health data towards the goal of improving health outcomes. Major challenges in the field include ensuring data quality, statistical problems in predicting and inferring with highly complex data, the lack of implementation trials, end-user engagement, inequitable performance for under-represented populations, and deployment in resource-limited settings, to name just a few. Without solutions to these problems, the massive amounts of health-applicable digital data generated daily will remain unusable. By bringing forth state-of-the-art interdisciplinary research we aim to inspire individuals from diverse backgrounds to engage and collaborate within this burgeoning field, as well as advancing the science necessary to solve its problems.
Articles that are within the scope of this Research Topic include (but are not limited to):
- Use of publicly available text and image datasets for inference about a health issue, including disease epidemiology, diagnostics, disease progression modeling, and comparative effectiveness
- Applications of machine learning to non-traditional data sources such as wearable sensors, social media repositories, cellular phones, and internet search engines, for personal and population health
- Research on improving prediction and inference from passively collected data, from non-traditional data sources or observational datasets characterized by sparse, noisy, high-dimensional, biased, and dynamic data
- Applications of digital health data to ameliorate health problems in resource-limited settings
- Exploration of fairness and health equity for machine learning algorithms trained on digital health data
- Implementation trials that evaluate the real-world impact of a digital health tool
Articles may be in the form of original research, review articles, case studies, and brief reports.
Keywords: Digital health data, Machine learning, Public health, Global health, Wearable sensors, Disease modeling, Precision medicine, Personalized medicine
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
