Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Artificial Intelligence-based Decision Support Systems for Precision and Digital Health

Nina Deliu, Bibhas Chakraborty

TL;DR

This work discusses the opportunity offered by AI, more specifically RL, to current trends in healthcare, providing a methodological survey of RL methods in the context of precision and digital health, and expands the methodological survey with illustrative case studies that used RL in real practice.

Abstract

Precision health, increasingly supported by digital technologies, is a domain of research that broadens the paradigm of precision medicine, advancing everyday healthcare. This vision goes hand in hand with the groundbreaking advent of artificial intelligence (AI), which is reshaping the way we diagnose, treat, and monitor both clinical subjects and the general population. AI tools powered by machine learning have shown considerable improvements in a variety of healthcare domains. In particular, reinforcement learning (RL) holds great promise for sequential and dynamic problems such as dynamic treatment regimes and just-in-time adaptive interventions in digital health. In this work, we discuss the opportunity offered by AI, more specifically RL, to current trends in healthcare, providing a methodological survey of RL methods in the context of precision and digital health. Focusing on the area of adaptive interventions, we expand the methodological survey with illustrative case studies that used RL in real practice. This invited article has undergone anonymous review and is intended as a book chapter for the volume "Frontiers of Statistics and Data Science" edited by Subhashis Ghoshal and Anindya Roy for the International Indian Statistical Association Series on Statistics and Data Science, published by Springer. It covers the material from a short course titled "Artificial Intelligence in Precision and Digital Health" taught by the author Bibhas Chakraborty at the IISA 2022 Conference, December 26-30 2022, at the Indian Institute of Science, Bengaluru.

Artificial Intelligence-based Decision Support Systems for Precision and Digital Health

TL;DR

This work discusses the opportunity offered by AI, more specifically RL, to current trends in healthcare, providing a methodological survey of RL methods in the context of precision and digital health, and expands the methodological survey with illustrative case studies that used RL in real practice.

Abstract

Precision health, increasingly supported by digital technologies, is a domain of research that broadens the paradigm of precision medicine, advancing everyday healthcare. This vision goes hand in hand with the groundbreaking advent of artificial intelligence (AI), which is reshaping the way we diagnose, treat, and monitor both clinical subjects and the general population. AI tools powered by machine learning have shown considerable improvements in a variety of healthcare domains. In particular, reinforcement learning (RL) holds great promise for sequential and dynamic problems such as dynamic treatment regimes and just-in-time adaptive interventions in digital health. In this work, we discuss the opportunity offered by AI, more specifically RL, to current trends in healthcare, providing a methodological survey of RL methods in the context of precision and digital health. Focusing on the area of adaptive interventions, we expand the methodological survey with illustrative case studies that used RL in real practice. This invited article has undergone anonymous review and is intended as a book chapter for the volume "Frontiers of Statistics and Data Science" edited by Subhashis Ghoshal and Anindya Roy for the International Indian Statistical Association Series on Statistics and Data Science, published by Springer. It covers the material from a short course titled "Artificial Intelligence in Precision and Digital Health" taught by the author Bibhas Chakraborty at the IISA 2022 Conference, December 26-30 2022, at the Indian Institute of Science, Bengaluru.
Paper Structure (16 sections, 28 equations, 5 figures, 3 tables)

This paper contains 16 sections, 28 equations, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. The Reinforcement Learning Framework
  3. Basic ingredients
  4. Mathematical formalization of the general RL
  5. Dynamic Treatment Regimes in Precision Health
  6. RL methods for constructing optimal DTRs
  7. Indirect RL methods in DTRs
  8. Direct RL methods in DTRs
  9. Data sources for constructing DTRs
  10. Case study: PROJECT QUIT – FOREVER FREE
  11. Just-in-time Adaptive Interventions in Digital Health
  12. RL methods for JITAIs in digital health
  13. The multi-armed bandit framework
  14. Data sources for building JITAIs in digital health
  15. Case study: DIAMANTE trial
  16. ...and 1 more sections

Figures (5)

  • Figure 1: Illustration of the general RL framework.
  • Figure 2: Illustrative comparison of direct vs indirect RL methods.
  • Figure 3: Representation of a feed-forward neural network with four layers used within Q-learning.
  • Figure 4: Schematic of the SMART design of the weight loss management study in pfammatter_smart_2019. App denotes a mobile app, TXT a support text message, and MR meal replacement. The response is defined as a weight loss of at least $0.5$ lb on average per week.
  • Figure 5: Schematic of the MRT design of the DIAMANTE Study.