Research summary of: Ramkumar PN, Luu BC, Haeberle HS, Karnuta JM, Nwachukwu BU, Williams RJ. Sports Medicine and Artificial Intelligence: A Primer. The American Journal of Sports Medicine. 2022;50(4):1166-1174.
“Recent research efforts into implementation of AI in the field of orthopaedic surgery and sports medicine have demonstrated great promise in predicting athlete injury risk, interpreting advanced imaging, evaluating patient-reported outcomes, reporting value-based metrics, and augmenting the patient experience.”
The questions covered:
AI is the science and engineering of creating ‘intelligent’ machines that have the ability to achieve tasks that otherwise would require human input. The AI revolution is often considered to be the fourth industrial revolution of human innovation [1760’s steam engine, 1870’s electricity and petroleum, 1970’s computers and microprocessors] and an ongoing phenomenon. In Sports Medicine, AI presents an opportunity to personalize care utilizing data to optimize treatment and automate tasks to allow for more face-to-face interaction between provider and patient. Different types of machine learning algorithms (just like different medications and treatment plans) are better suited for different clinical applications and insights. For example, expert systems are programs that can be developed to mimic the decision making of expert clinicians while Bayesian models can be used to stratify patient risk prior to surgery.
There are a wide range of opportunities for AI-based techniques in sports medicine, notably the ability to automate non-clinical administrative tasks performed by sports medicine specialists to provide more time to be spent with patients. One study found that the average patient’s health record was associated with approximately 32,000 unique data elements, of which the physician is tasked with synthesizing and determining a clinical decision. The introduction of AI tools and their predictive components may reduce information overload for clinical decision support.The application of AI in sports medicine in clinical practice is in its early stages and thus it is important to recognize these tools carry some limitations. The quality and quantity of longitudinal data required to feed many AI applications in order to provide actionable insights is one such limitation. This however is also becoming increasingly streamlined and automated through more objective and practical data collection instrumentation. Additionally the black box nature of some machine learning techniques may limit the ability to interpret the specific inferences evaluated by the algorithm without additional analysis for explainability.
The authors reference many research articles from the existing literature showing significant promise for AI in predicting athlete injury risk, interpreting advanced imaging, evaluating patient-reported outcomes, reporting value-based metrics, and augmenting the patient experience. For example, one study utilized a ML model built on wearable data and was able to demonstrate clinical utility for early prediction of patients most at risk of developing poor postoperative functional outcomes and patient reported outcome measures. It is important that sports medicine specialists not consider this area of research (AI/ML) outside their expected scope and take a participatory role in its responsible deployment.
Artificial intelligence (AI) represents the fourth industrial revolution and the next frontier in medicine poised to transform the field of orthopaedics and sports medicine, though widespread understanding of the fundamental principles and adoption of applications remain nascent. Recent research efforts into implementation of AI in the field of orthopaedic surgery and sports medicine have demonstrated great promise in predicting athlete injury risk, interpreting advanced imaging, evaluating patient-reported outcomes, reporting value-based metrics, and augmenting the patient experience. Not unlike the recent emphasis thrust upon physicians to understand the business of medicine, the future practice of sports medicine specialists will require a fundamental working knowledge of the strengths, limitations, and applications of AI-based tools. With appreciation, caution, and experience applying AI to sports medicine, the potential to automate tasks and improve data-driven insights may be realized to fundamentally improve patient care. In this Current Concepts review, we discuss the definitions, strengths, limitations, and applications of AI from the current literature as it relates to orthopaedic sports medicine.