基于全国数据库开发的全关节置换术后30天并发症机器学习算法的预测准确性存在种族和民族差异
该回顾性队列研究从全国结局数据库纳入2013至2020年267194例初次全关节置换术患者,按种族和民族分层评估两种机器学习算法预测30天并发症的表现。非西班牙裔白人队列判别力优异(AUC均为0.86),而西班牙裔白人、黑人、西班牙裔黑人、非西班牙裔亚裔及总体队列判别力下降(AUC 0.75至0.79),美洲印第安人队列判别力和校准最差(AUC 0.67至0.68)。作者认为这可能与少数族群在数据库中代表性不足有关。
要点
- 非西班牙裔白人队列中两种算法判别力优异,AUC均为0.86,校准和准确性良好。
- 西班牙裔白人、黑人、西班牙裔黑人、非西班牙裔亚裔及总体队列判别力下降至AUC 0.75至0.79,但校准仍良好。
- 美洲印第安人队列判别力(AUC 0.67至0.68)和校准最差,样本量仅1870例。
核心结论
- 在现有医疗大数据上训练的机器学习算法,对种族和民族少数族群初次全关节置换术后30天并发症的预测能力较差。
- 作者认为这可能归因于少数族群在数据库中代表性不足,表现为可用于训练模型的样本量较小。
- 作者指出,使用较小数据集(如种族和民族少数族群)开发的机器学习模型可能不如较大数据集准确,强调需要公平意识驱动的模型开发。
研究设计与样本
- 回顾性队列研究(证据等级III),从全国结局数据库识别2013年至2020年接受初次全关节置换术的患者共267194例。
- 患者队列按种族分层,并进一步按西班牙裔或非西班牙裔民族分层。
- 采用两种机器学习算法——直方图梯度提升(HGB)和随机森林(RF),在总体人群中建模预测初次全关节置换术后30天并发症,随后在各 racial 和民族亚队列中评估判别力、校准、准确性和潜在临床 usefulness。
主要发现
- 非西班牙裔白人队列(N=224073)中,两种模型判别力优异(AUCHGB=AUCRF=0.86),校准和准确性良好(HGB:斜率=1.00,截距=-0.03,Brier评分=0.12;RF:斜率=0.97,截距=0.02,Brier评分=0.12)。
- 西班牙裔白人队列(N=10429;AUC=0.75至0.76)、黑人队列(N=25116;AUC=0.77)、西班牙裔黑人队列(N=240;AUC=0.78)、非西班牙裔亚裔队列(N=4809;AUC=0.78至0.79)及总体队列(N=267194;AUC=0.75至0.76)判别力下降,但校准仍良好。
- 美洲印第安人队列(N=1870;AUC=0.67至0.68)模型判别力和校准最差。
关键数值与推荐
- 非西班牙裔白人队列:AUC均为0.86,HGB斜率=1.00、截距=-0.03、Brier评分=0.12,RF斜率=0.97、截距=0.02、Brier评分=0.12。
- 西班牙裔白人队列:AUC=0.75至0.76;黑人队列:AUC=0.77;西班牙裔黑人队列:AUC=0.78;非西班牙裔亚裔队列:AUC=0.78至0.79;总体队列:AUC=0.75至0.76。
- 美洲印第安人队列:AUC=0.67至0.68,校准最差。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: While predictive capabilities of machine learning (ML) algorithms for hip and knee total joint arthroplasty (TJA) have been demonstrated in previous studies, their performance in racial and ethnic minority patients has not been investigated. This study aimed to assess the performance of ML algorithms in predicting 30-days complications following TJA in racial and ethnic minority patients. METHODS: A total of 267,194 patients undergoing primary TJA between 2013 and 2020 were identified from a national outcomes database. The patient cohort was stratified according to race, with further substratification into Hispanic or non-Hispanic ethnicity. There were two ML algorithms, histogram-based gradient boosting (HGB), and random forest (RF), that were modeled to predict 30-days complications following primary TJA in the overall population. They were subsequently assessed in each racial and ethnic subcohort using discrimination, calibration, accuracy, and potential clinical usefulness. RESULTS: Both models achieved excellent (Area under the curve (AUC) > 0.8) discrimination (AUCHGB = AUCRF = 0.86), calibration, and accuracy (HGB: slope = 1.00, intercept = -0.03, Brier score = 0.12; RF: slope = 0.97, intercept = 0.02, Brier score = 0.12) in the non-Hispanic White population (N = 224,073). Discrimination decreased in the White Hispanic (N = 10,429; AUC = 0.75 to 0.76), Black (N = 25,116; AUC = 0.77), Black Hispanic (N = 240; AUC = 0.78), Asian non-Hispanic (N = 4,809; AUC = 0.78 to 0.79), and overall (N = 267,194; AUC = 0.75 to 0.76) cohorts, but remained well-calibrated. We noted the poorest model discrimination (N = 1,870; AUC = 0.67 to 0.68) and calibration in the American-Indian cohort. CONCLUSIONS: The ML algorithms demonstrate an inferior predictive ability for 30-days complications following primary TJA in racial and ethnic minorities when trained on existing healthcare big data. This may be attributed to the disproportionate underrepresentation of minority groups within these databases, as demonstrated by the smaller sample sizes available to train the ML models. The ML models developed using smaller datasets (e.g., in racial and ethnic minorities) may not be as accurate as larger datasets, highlighting the need for equity-conscious model development. LEVEL OF EVIDENCE: III; retrospective cohort study.
引用
- Pean CA, Buddhiraju A, Lin-Wei Chen T, et al. Racial and Ethnic Disparities in Predictive Accuracy of Machine Learning Algorithms Developed Using a National Database for 30-Day Complications Following Total Joint Arthroplasty. J Arthroplasty. 2024. PMID: 39433263. doi:10.1016/j.arth.2024.10.060
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。