Opportunities for Artificial Intelligence in Operational Medicine: Lessons from the United States Military

Abstract

Conducted in challenging environments such as disaster or conflict areas, operational medicine presents unique challenges for the delivery of efficient and quality healthcare. It exposes first responders and medical personnel to many unexpected health risks and dangerous situations. To tackle these issues, artificial intelligence (AI) has been progressively incorporated into operational medicine, both on the front lines and also more recently in support roles. The ability of AI to rapidly analyze high-dimensional data and make inferences has opened up a wide variety of opportunities and increased efficiency for its early adopters, notably for the United States military, for non-invasive medical imaging and for mental health applications. This review discusses the current state of AI and highlights its broad array of potential applications in operational medicine as developed for the United States military.

Keywords: artificial intelligence; bioengineering; biomedical technology; disaster medicine; machine learning; military medicine.

Figure 1

Visualization of a neural network used in operational medicine. Neural networks can use a variety of data types (left column) and process them across several layers, typically including an encoder, a bottleneck, and then a decoder, in which connected nodes are able to learn complex patterns. A trained network can then produce a wide array of outputs (right column) that can facilitate the completion of tasks related to operational medicine.

Figure 2

Accelerated acquisition of MRI data using AI. The traditional collection of MRI frequency data (k-space) takes a long time (left). Undersampling the frequency data can reduce the acquisition time but produces a low-resolution output (middle). AI is able to process undersampled data rapidly to reconstruct high-resolution data (right).

Figure 3

Roadmap for getting started in AI. To implement AI, one can start by exploring AI platforms, progressing to using essential Python packages, taking courses, composing an ML algorithm, incorporating data from publicly available datasets, processing data using more advanced AI techniques, and staying involved in recent AI developments through conferences and publications.