Log in to MyACC
Translation of AI to Clinical Practice: Friend or Foe?
The use of artificial intelligence (AI) technology has great potential in assisting cardiologists in making a prompt clinical diagnosis by improving interpretation skills.
There are several fields within the practice of cardiology where there is a huge potential for AI technology in reforming care, including cardiac imaging, event monitoring, robotics in cath lab and more. AI technology can allow diagnosis of coronary artery disease and arrhythmias, and aid in the management of heart failure. Several AI algorithms have been developed with continued improvements and modification for diagnostic images, image reconstruction and image quality control in the field of medical imaging.
Various digital devices such as smartphones, smartwatches, smart bands, earlobe sensors and wearable devices are being increasingly used for detection of arrhythmias in the ambulatory setting. These devices are noninvasive, user friendly and convenient for the general population. The use of voice technology is already reforming current practices in medical charting; AI in the form of voice assistant technology is used for paperless medical history taking and telehealth.
Image processing software and various devices have been developed for analysis of images for the assessment of cardiovascular diseases. For instance, there are devices for quantification and reporting of cardiovascular function, analysis of previously acquired angiography data, ambulatory ECG rhythm assessment, detection and amplification of heart sounds, and more.
The new generation of trainees must familiarize themselves with this developing technology and recognize that AI applications complement their ability to provide patient care and health care delivery.
However, since AI is relatively new, unfamiliar and still developing significantly, the use of medical devices in AI technology may threaten to dehumanize medicine. For example, despite continued improvements in the computerized interpretation of ECGs, it still has limitations in the accuracy of the diagnosis from purely AI algorithms; systematic human reading of ECGs is still necessary [1,2]. A human mind will always be required to make the best medical decisions for patients and AI technology can greatly assist in making these decisions.
AI has risks if unregulated and robust quality control systems will need to be implemented where AI is a part of routine clinical practice. AI technology needs collaboration of clinicians with computer scientists and clinical investigators for developing problem solving strategies in routine clinical practice and the best approaches to attain enhanced and improved patient care in the coming generations [1,3].
Human interaction cannot be replaced by AI in the practice of clinical medicine, but AI should be utilized to complement the clinician's ability to accurately diagnose and treat patients.
References:
- Chung CT, Lee S, King E, Liu T, Armoundas AA, Bazoukis G, Tse G. Clinical significance, challenges and limitations in using artificial intelligence for electrocardiography-based diagnosis. Int J Arrhythmia. 2022;23(1):24. doi: 10.1186/s42444-022-00075-x. Epub 2022 Oct 1. PMID: 36212507; PMCID: PMC9525157.
- Bhattad P, Jain V (May 09, 2020) Artificial Intelligence in Modern Medicine – The Evolving Necessity of the Present and Role in Transforming the Future of Medical Care. Cureus 12(5): e8041. doi:10.7759/cureus.8041
- Bhattad P, Jain S. (Jan, 2022). The Power of Artificial Intelligence in Reforming Medicine.
This article was written by Pradnya Brijmohan Bhattad, MD, a FIT at Saint Vincent Hospital in Worcester, MA.
This content was developed independently from the content developed for ACC.org. This content was not reviewed by the American College of Cardiology (ACC) for medical accuracy and the content is provided on an "as is" basis. Inclusion on ACC.org does not constitute a guarantee or endorsement by the ACC and ACC makes no warranty that the content is accurate, complete or error-free. The content is not a substitute for personalized medical advice and is not intended to be used as the sole basis for making individualized medical or health-related decisions. Statements or opinions expressed in this content reflect the views of the authors and do not reflect the official policy of ACC.
