Rothman Institute, Thomas Jefferson University Hospital, Philadelphia, Pennsylvania.
Avant-garde Health, Boston, Massachusetts.
JBJS Rev. 2024 Aug 22;12(8). doi: e24.00075. eCollection 2024 Aug 1.
Numerous applications and strategies have been utilized to help assess the trends and patterns of readmissions after orthopaedic surgery in an attempt to extrapolate possible risk factors and causative agents. The aim of this work is to systematically summarize the available literature on the extent to which natural language processing, machine learning, and artificial intelligence (AI) can help improve the predictability of hospital readmissions after orthopaedic and spine surgeries.
This is a systematic review and meta-analysis. PubMed, Embase and Google Scholar were searched, up until August 30, 2023, for studies that explore the use of AI, natural language processing, and machine learning tools for the prediction of readmission rates after orthopedic procedures. Data regarding surgery type, patient population, readmission outcomes, advanced models utilized, comparison methods, predictor sets, the inclusion of perioperative predictors, validation method, size of training and testing sample, accuracy, and receiver operating characteristics (C-statistic), among other factors, were extracted and assessed.
A total of 26 studies were included in our final dataset. The overall summary C-statistic showed a mean of 0.71 across all models, indicating a reasonable level of predictiveness. A total of 15 articles (57%) were attributed to the spine, making it the most commonly explored orthopaedic field in our study. When comparing accuracy of prediction models between different fields, models predicting readmissions after hip/knee arthroplasty procedures had a higher prediction accuracy (mean C-statistic = 0.79) than spine (mean C-statistic = 0.7) and shoulder (mean C-statistic = 0.67). In addition, models that used single institution data, and those that included intraoperative and/or postoperative outcomes, had a higher mean C-statistic than those utilizing other data sources, and that include only preoperative predictors. According to the Prediction model Risk of Bias Assessment Tool, the majority of the articles in our study had a high risk of bias.
AI tools perform reasonably well in predicting readmissions after orthopaedic procedures. Future work should focus on standardizing study methodologies and designs, and improving the data analysis process, in an attempt to produce more reliable and tangible results.
Level III. See Instructions for Authors for a complete description of levels of evidence.
为了推断可能的风险因素和致病因素，许多应用程序和策略已被用于帮助评估骨科手术后的再入院趋势和模式。本研究旨在系统地总结关于自然语言处理、机器学习和人工智能 (AI) 在多大程度上可以帮助提高骨科和脊柱手术后住院再入院预测能力的现有文献。
这是一项系统评价和荟萃分析。截至 2023 年 8 月 30 日，我们在 PubMed、Embase 和 Google Scholar 上搜索了探索使用 AI、自然语言处理和机器学习工具预测骨科手术后再入院率的研究。提取和评估了有关手术类型、患者人群、再入院结局、使用的先进模型、比较方法、预测因子集、围手术期预测因子的纳入、验证方法、训练和测试样本的大小、准确性和接收者操作特征 (C 统计量) 等因素的数据。
共有 26 项研究纳入最终数据集。总体汇总 C 统计量显示所有模型的平均值为 0.71，表明具有合理的预测水平。共有 15 篇文章（57%）涉及脊柱，使其成为本研究中最常探索的骨科领域。当比较不同领域的预测模型准确性时，预测髋/膝关节置换术后再入院的模型具有更高的预测准确性（平均 C 统计量=0.79），而脊柱（平均 C 统计量=0.7）和肩部（平均 C 统计量=0.67）。此外，使用单机构数据的模型和纳入术中及/或术后结局的模型比使用其他数据源和仅纳入术前预测因子的模型具有更高的平均 C 统计量。根据预测模型风险评估工具，我们研究中的大多数文章都具有较高的偏倚风险。
AI 工具在预测骨科手术后再入院方面表现相当不错。未来的工作应侧重于标准化研究方法和设计，并改进数据分析过程，以产生更可靠和切实的结果。
三级。请参阅作者指南以获取完整的证据水平描述。
