The Role of Artificial Intelligence in Digital Health
Digital medicine and health herald the era of technological advances such as apps, wearable technology and remote monitoring, telemedicine and communication tools, and other diagnostic devices to affect a more optimal quality of care as well as a more timely response to any situation. The overarching theme in digital health and medicine in the use of AI in orchestrating, storing, and interpreting the huge amounts of data derived from the devices to facilitate acute and chronic disease diagnosis and management via AI-enabled acquisition and interpretation of data. This strategy will both increase the ability to proactively intervene when appropriate as well as decrease the burden on both the patient and the caretakers when the decisions are relatively straightforward.
In the near future, embedded AI (eAI) and machine learning algorithms evolve toward the internet of everything (IoE) and will bring together people, process, data, and things; this strategy will allow the accrued data to be streamlined and organized in the cloud proactively in an overall paradigm of personalized precision medicine. As these devices become more intelligent, increasingly higher levels of sophistication in decision support can also be part of both (1) preventive medicine (such as retinal images for retinopathy screening or skin lesions for melanoma detection) as well as (2) chronic disease care management (such as diabetes, hypertension, or heart failure).
KeywordsArtificial intelligence Digital medicine Wearable technology Apps Telemedicine Telehealth Bid data Machine learning Deep learning Natural language processing Cognitive computing Internet of things Internet of everything
I would like to express my deep gratitude to Ms. Audrey He, my research assistant, for her tireless dedication and utmost support for the work on this chapter.
- 2.Copeland J. The essential turing. Oxford: Oxford University Press; 2004.Google Scholar
- 5.Gunning D. Talk at DARPA. 2016.Google Scholar
- 6.Krizhevsky A, Sututskever I, Hinto GE. ImageNet classification withDeep convolutional neural networks, vol. 1. La Jolla, CA: Neural Information Processing Systems Foundation Inc; 2012. p. 4.Google Scholar
- 8.Porter J, editor. Deep learning: fundamentals, methods, and applications. New York: Nova Science Publishers; 2016.Google Scholar
- 10.Groopman J. How doctors think. Boston: Houghton Mifflin; 2007.Google Scholar
- 11.Kahneman D. Thinking, fast and slow. New York: Farrar, Straus, and Giroux; 2011.Google Scholar
- 13.Chang AC, et al. Artificial intelligence in pediatric cardiology: an innovative transformation in patient care, clinical research, and medical education. Cong Card Today. 2012;10:1–12.Google Scholar
- 16.Healthcare Content Management White Paper. Unstructured data in electronic health record (HER) systems: challenges and solutions. 2013. www.datamark.net.
- 17.Hughes G. How big is “Big Data” in healthcare? SAS Blogs. 2011.Google Scholar
- 26.Is digital medicine different? Editorial in Lancet. 2018;392:95.Google Scholar