Rigamonti Lia, Estel Katharina, Gehlen Tobias, Wolfarth Bernd, Lawrence James B, Back David A
Center of Sport Medicine, Department Sport and Health Science, University of Potsdam, University Outpatient Clinic, Am Neuen Palais 10, 14469, Potsdam, Germany.
Clinic of Traumatology and Orthopedics, Bundeswehr Hospital Berlin, Berlin, Germany.
BMC Sports Sci Med Rehabil. 2021 Feb 16;13(1):13. doi: 10.1186/s13102-021-00243-x.
Artificial intelligence (AI) is one of the most promising areas in medicine with many possibilities for improving health and wellness. Already today, diagnostic decision support systems may help patients to estimate the severity of their complaints. This fictional case study aimed to test the diagnostic potential of an AI algorithm for common sports injuries and pathologies.
Based on a literature review and clinical expert experience, five fictional "common" cases of acute, and subacute injuries or chronic sport-related pathologies were created: Concussion, ankle sprain, muscle pain, chronic knee instability (after ACL rupture) and tennis elbow. The symptoms of these cases were entered into a freely available chatbot-guided AI app and its diagnoses were compared to the pre-defined injuries and pathologies.
A mean of 25-36 questions were asked by the app per patient, with optional explanations of certain questions or illustrative photos on demand. It was stressed, that the symptom analysis would not replace a doctor's consultation. A 23-yr-old male patient case with a mild concussion was correctly diagnosed. An ankle sprain of a 27-yr-old female without ligament or bony lesions was also detected and an ER visit was suggested. Muscle pain in the thigh of a 19-yr-old male was correctly diagnosed. In the case of a 26-yr-old male with chronic ACL instability, the algorithm did not sufficiently cover the chronic aspect of the pathology, but the given recommendation of seeing a doctor would have helped the patient. Finally, the condition of the chronic epicondylitis in a 41-yr-old male was correctly detected.
All chosen injuries and pathologies were either correctly diagnosed or at least tagged with the right advice of when it is urgent for seeking a medical specialist. However, the quality of AI-based results could presumably depend on the data-driven experience of these programs as well as on the understanding of their users. Further studies should compare existing AI programs and their diagnostic accuracy for medical injuries and pathologies.
人工智能（AI）是医学领域最具前景的领域之一，在改善健康状况方面有诸多可能性。如今，诊断决策支持系统已可帮助患者评估自身症状的严重程度。本虚拟案例研究旨在测试一种人工智能算法对常见运动损伤和病症的诊断潜力。
基于文献综述和临床专家经验，创建了五个虚构的急性和亚急性损伤或慢性运动相关病症的“常见”案例：脑震荡、脚踝扭伤、肌肉疼痛、慢性膝关节不稳定（前交叉韧带断裂后）和网球肘。将这些案例的症状输入到一款免费的聊天机器人引导的人工智能应用程序中，并将其诊断结果与预先定义的损伤和病症进行比较。
该应用程序每位患者平均提出25 - 36个问题，并可根据需求提供某些问题的可选解释或示例照片。需要强调的是，症状分析不能替代医生的咨询。一名23岁男性轻度脑震荡患者被正确诊断。一名27岁无韧带或骨损伤的女性脚踝扭伤也被检测到，并建议其前往急诊室就诊。一名19岁男性大腿肌肉疼痛被正确诊断。对于一名26岁患有慢性前交叉韧带不稳定的男性患者，该算法未充分涵盖该病症的慢性方面，但给出的就医建议对患者会有帮助。最后，一名41岁男性慢性肱骨外上髁炎的病情被正确检测到。
所有选定的损伤和病症要么被正确诊断，要么至少给出了何时急需寻求医学专家建议的正确提示。然而，基于人工智能的结果质量可能取决于这些程序的数据驱动经验以及用户的理解。进一步的研究应比较现有的人工智能程序及其对医学损伤和病症的诊断准确性。
