Utilization of machine learning methods for predicting surgical outcomes after total knee arthroplasty.
Utilization of machine learning methods for predicting surgical outcomes after total knee arthroplasty.
复制标题
DOI：
10.1371/journal.pone.0263897
复制
发表时间：
2022
期刊：
影响因子：
3.7
通讯作者：
Ma Y
中科院分区：
文献类型：
--
作者：
Mohammed H;Huang Y;Memtsoudis S;Parks M;Huang Y;Ma Y
预测模型可以帮助临床医生识别导致全膝关节置换术(TKA)后不良事件的危险因素，从而允许适当的术前预防干预和资源分配。使用2010-2014年的全国住院患者样本数据集，建立Logistic回归(LR)、梯度助推法(GBM)、随机森林(RF)和人工神经网络(ANN)预测模型，预测TKA出院时处置、术后并发症和输血后的三种临床相关结果。使用Brier评分作为校正指标，以ROC曲线下面积(AUC)和F1评分作为判别指标来评估模型的性能。观察到，基于GBM的预测模型比其他模型具有更好的校准和区分性；因此，表明相对更好的整体性能。GBM模型预测结果的Brier分数在0.09-0.14之间，AUC在79-87%之间，F1-分数在41-73%之间。对GBM模型的变量重要性分析表明，入院月份、患者所在地和患者的收入水平是所有结果的显著预测因素。此外，术后并发症和输血可通过缺乏性贫血、住院时间和年龄组的出院倾向进行显著预测。值得注意的是，接受输血的患者也能显著预测手术后的任何并发症。使用国家住院患者样本(NIS)的数据成功地展示了ML模型的预测能力，表明在获得矫形外科手术后并发症的准确预测方面具有广泛的临床应用。
Predictive models could help clinicians identify risk factors that cause adverse events after total knee arthroplasty (TKA), allowing for appropriate preoperative preventive interventions and allocation of resources. The National Inpatient Sample datasets from 2010–2014 were used to build Logistic Regression (LR), Gradient Boosting Method (GBM), Random Forest (RF), and Artificial Neural Network (ANN) predictive models for three clinically relevant outcomes after TKA—disposition at discharge, any post-surgical complications, and blood transfusion. Model performance was evaluated using the Brier scores as calibration measures, and area under the ROC curve (AUC) and F1 scores as discrimination measures. GBM-based predictive models were observed to have better calibration and discrimination than the other models; thus, indicating comparatively better overall performance. The Brier scores for GBM models predicting the outcomes under investigation ranged from 0.09–0.14, AUCs ranged from 79–87%, and F1-scores ranged from 41–73%. Variable importance analysis for GBM models revealed that admission month, patient location, and patient’s income level were significant predictors for all the outcomes. Additionally, any post-surgical complications and blood transfusions were significantly predicted by deficiency anemias, and discharge disposition by length of stay and age groups. Notably, any post-surgical complications were also significantly predicted by the patient undergoing blood transfusion. The predictive abilities of the ML models were successfully demonstrated using data from the National Inpatient Sample (NIS), indicating a wide range of clinical applications for obtaining accurate prognoses of complications following orthopedic surgical procedures.
登录
查看更多内容
DOI：
10.1016/j.cjca.2020.11.010
发表时间：
2021-09
期刊：
The Canadian journal of cardiology
影响因子：
--
作者：
Austin PC;White IR;Lee DS;van Buuren S
通讯作者：
van Buuren S
影响因子：
1.8
作者：
PICARD, RR;BERK, KN
通讯作者：
BERK, KN
影响因子：
7.4
作者：
Myrtveit, I;Stensrud, E;Olsson, UH
通讯作者：
Olsson, UH
影响因子：
4.3
作者：
Henry, Antonia J.;Hevelone, Nathanael D.;Nguyen, Louis L.
通讯作者：
Nguyen, Louis L.
DOI：
10.1302/0301-620x.86b5.14887
发表时间：
2004-07-01
影响因子：
--
作者：
Blom, AW;Brown, J;Bannister, GC
通讯作者：
Bannister, GC