Areias Anabela C, Janela Dora, Moulder Robert G, Molinos Maria, Bento Virgílio, Moreira Carolina, Yanamadala Vijay, Correia Fernando Dias, Costa Fabíola
Sword Health, Inc., Draper, UT 84043, USA.
Institute for Cognitive Science, University of Colorado Boulder, Boulder, CO 80309, USA.
J Clin Med. 2024 Jul 26;13(15):4366. doi: 10.3390/jcm13154366.
: The rising prevalence of musculoskeletal (MSK) conditions has not been balanced by a sufficient increase in healthcare providers. Scalability challenges are being addressed through the use of artificial intelligence (AI) in some healthcare sectors, with this showing potential to also improve MSK care. Digital care programs (DCP) generate automatically collected data, thus making them ideal candidates for AI implementation into workflows, with the potential to unlock care scalability. In this study, we aimed to assess the impact of scaling care through AI in patient outcomes, engagement, satisfaction, and adverse events. : Post hoc analysis of a prospective, pre-post cohort study assessing the impact on outcomes after a 2.3-fold increase in PT-to-patient ratio, supported by the implementation of a machine learning-based tool to assist physical therapists (PTs) in patient care management. The intervention group (IG) consisted of a DCP supported by an AI tool, while the comparison group (CG) consisted of the DCP alone. The primary outcome concerned the pain response rate (reaching a minimal clinically important change of 30%). Other outcomes included mental health, program engagement, satisfaction, and the adverse event rate. : Similar improvements in pain response were observed, regardless of the group (response rate: 64% vs. 63%; = 0.399). Equivalent recoveries were also reported in mental health outcomes, specifically in anxiety ( = 0.928) and depression ( = 0.187). Higher completion rates were observed in the IG (79.9% (N = 19,252) vs. CG 70.1% (N = 8489); < 0.001). Patient engagement remained consistent in both groups, as well as high satisfaction (IG: 8.76/10, SD 1.75 vs. CG: 8.60/10, SD 1.76; = 0.021). Intervention-related adverse events were rare and even across groups (IG: 0.58% and CG 0.69%; = 0.231). : The study underscores the potential of scaling MSK care that is supported by AI without compromising patient outcomes, despite the increase in PT-to-patient ratios.
肌肉骨骼疾病（MSK）患病率的上升并未伴随着医疗服务提供者数量的相应增加。在一些医疗领域，通过使用人工智能（AI）来应对可扩展性挑战，这显示出改善MSK护理的潜力。数字护理计划（DCP）可自动收集数据，因此使其成为将AI应用于工作流程的理想选择，有可能实现护理的可扩展性。在本研究中，我们旨在评估通过AI扩大护理规模对患者预后、参与度、满意度和不良事件的影响。：对一项前瞻性前后队列研究进行事后分析，该研究评估了在基于机器学习的工具支持物理治疗师（PT）进行患者护理管理后，PT与患者比例提高2.3倍对预后的影响。干预组（IG）由一个由AI工具支持的DCP组成，而对照组（CG）仅由DCP组成。主要结局关注疼痛缓解率（达到最小临床重要变化30%）。其他结局包括心理健康、项目参与度、满意度和不良事件发生率。：无论组别如何，均观察到疼痛缓解有类似改善（缓解率：64%对63%；P = 0.399）。心理健康结局方面也报告了相当的恢复情况，特别是在焦虑（P = 0.928）和抑郁（P = 0.187）方面。IG的完成率更高（79.9%（N = 19252）对CG的70.1%（N = 8489）；P < 0.001）。两组患者的参与度均保持一致，满意度也都很高（IG：8.76/10，标准差1.75对CG：8.60/10，标准差1.76；P = 0.021）。与干预相关的不良事件很少且两组相当（IG：0.58%，CG：0.69%；P = 0.231）。：该研究强调了在不影响患者预后的情况下，由AI支持扩大MSK护理规模的潜力，尽管PT与患者的比例有所增加。
