Bashar Zaidat, Mark Kurapatti, Jonathan S Gal, Samuel K Cho, Jun S Kim
{"title":"用可解释的机器学习方法预测成人脊柱畸形患者在重症监护室住院时间的延长:机器学习优于逻辑回归","authors":"Bashar Zaidat, Mark Kurapatti, Jonathan S Gal, Samuel K Cho, Jun S Kim","doi":"10.1177/21925682241277771","DOIUrl":null,"url":null,"abstract":"<p><strong>Study design: </strong>Retrospective cohort study.</p><p><strong>Objectives: </strong>Prolonged ICU stay is a driver of higher costs and inferior outcomes in Adult Spinal Deformity (ASD) patients. Machine learning (ML) models have recently been seen as a viable method of predicting pre-operative risk but are often 'black boxes' that do not fully explain the decision-making process. This study aims to demonstrate ML can achieve similar or greater predictive power as traditional statistical methods and follows traditional clinical decision-making processes.</p><p><strong>Methods: </strong>Five ML models (Decision Tree, Random Forest, Support Vector Classifier, GradBoost, and a CNN) were trained on data collected from a large urban academic center to predict whether prolonged ICU stay would be required post-operatively. 535 patients who underwent posterior fusion or combined fusion for treatment of ASD were included in each model with a 70-20-10 train-test-validation split. Further analysis was performed using Shapley Additive Explanation (SHAP) values to provide insight into each model's decision-making process.</p><p><strong>Results: </strong>The model's Area Under the Receiver Operating Curve (AUROC) ranged from 0.67 to 0.83. The Random Forest model achieved the highest score. The model considered length of surgery, complications, and estimated blood loss to be the greatest predictors of prolonged ICU stay based on SHAP values.</p><p><strong>Conclusions: </strong>We developed a ML model that was able to predict whether prolonged ICU stay was required in ASD patients. Further SHAP analysis demonstrated our model aligned with traditional clinical thinking. Thus, ML models have strong potential to assist with risk stratification and more effective and cost-efficient care.</p>","PeriodicalId":12680,"journal":{"name":"Global Spine Journal","volume":null,"pages":null},"PeriodicalIF":2.6000,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Explainable Machine Learning Approach to Prediction of Prolonged Intesive Care Unit Stay in Adult Spinal Deformity Patients: Machine Learning Outperforms Logistic Regression.\",\"authors\":\"Bashar Zaidat, Mark Kurapatti, Jonathan S Gal, Samuel K Cho, Jun S Kim\",\"doi\":\"10.1177/21925682241277771\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Study design: </strong>Retrospective cohort study.</p><p><strong>Objectives: </strong>Prolonged ICU stay is a driver of higher costs and inferior outcomes in Adult Spinal Deformity (ASD) patients. Machine learning (ML) models have recently been seen as a viable method of predicting pre-operative risk but are often 'black boxes' that do not fully explain the decision-making process. This study aims to demonstrate ML can achieve similar or greater predictive power as traditional statistical methods and follows traditional clinical decision-making processes.</p><p><strong>Methods: </strong>Five ML models (Decision Tree, Random Forest, Support Vector Classifier, GradBoost, and a CNN) were trained on data collected from a large urban academic center to predict whether prolonged ICU stay would be required post-operatively. 535 patients who underwent posterior fusion or combined fusion for treatment of ASD were included in each model with a 70-20-10 train-test-validation split. Further analysis was performed using Shapley Additive Explanation (SHAP) values to provide insight into each model's decision-making process.</p><p><strong>Results: </strong>The model's Area Under the Receiver Operating Curve (AUROC) ranged from 0.67 to 0.83. The Random Forest model achieved the highest score. The model considered length of surgery, complications, and estimated blood loss to be the greatest predictors of prolonged ICU stay based on SHAP values.</p><p><strong>Conclusions: </strong>We developed a ML model that was able to predict whether prolonged ICU stay was required in ASD patients. Further SHAP analysis demonstrated our model aligned with traditional clinical thinking. Thus, ML models have strong potential to assist with risk stratification and more effective and cost-efficient care.</p>\",\"PeriodicalId\":12680,\"journal\":{\"name\":\"Global Spine Journal\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2024-08-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Global Spine Journal\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1177/21925682241277771\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Global Spine Journal","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/21925682241277771","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0
摘要
研究设计研究目的:回顾性队列研究:延长重症监护室住院时间是导致成人脊柱畸形(ASD)患者费用增加和预后变差的原因之一。机器学习(ML)模型最近被视为预测术前风险的可行方法,但往往是 "黑盒子",不能完全解释决策过程。本研究旨在证明 ML 可以达到与传统统计方法相似或更高的预测能力,并遵循传统的临床决策过程:方法:在一个大型城市学术中心收集的数据上训练了五个 ML 模型(决策树、随机森林、支持向量分类器、GradBoost 和 CNN),以预测术后是否需要延长重症监护室的住院时间。每个模型都纳入了 535 名接受后路融合术或联合融合术治疗 ASD 的患者,训练-测试-验证的比例为 70-20-10。使用夏普利加性解释(SHAP)值进行了进一步分析,以深入了解每个模型的决策过程:结果:模型的接收者工作曲线下面积(AUROC)在 0.67 到 0.83 之间。随机森林模型得分最高。根据SHAP值,该模型认为手术时间、并发症和估计失血量是ICU住院时间延长的最大预测因素:结论:我们建立了一个 ML 模型,该模型能够预测 ASD 患者是否需要延长 ICU 住院时间。进一步的 SHAP 分析表明,我们的模型符合传统的临床思维。因此,ML 模型在协助风险分层和提供更有效、更具成本效益的护理方面具有强大的潜力。
Explainable Machine Learning Approach to Prediction of Prolonged Intesive Care Unit Stay in Adult Spinal Deformity Patients: Machine Learning Outperforms Logistic Regression.
Study design: Retrospective cohort study.
Objectives: Prolonged ICU stay is a driver of higher costs and inferior outcomes in Adult Spinal Deformity (ASD) patients. Machine learning (ML) models have recently been seen as a viable method of predicting pre-operative risk but are often 'black boxes' that do not fully explain the decision-making process. This study aims to demonstrate ML can achieve similar or greater predictive power as traditional statistical methods and follows traditional clinical decision-making processes.
Methods: Five ML models (Decision Tree, Random Forest, Support Vector Classifier, GradBoost, and a CNN) were trained on data collected from a large urban academic center to predict whether prolonged ICU stay would be required post-operatively. 535 patients who underwent posterior fusion or combined fusion for treatment of ASD were included in each model with a 70-20-10 train-test-validation split. Further analysis was performed using Shapley Additive Explanation (SHAP) values to provide insight into each model's decision-making process.
Results: The model's Area Under the Receiver Operating Curve (AUROC) ranged from 0.67 to 0.83. The Random Forest model achieved the highest score. The model considered length of surgery, complications, and estimated blood loss to be the greatest predictors of prolonged ICU stay based on SHAP values.
Conclusions: We developed a ML model that was able to predict whether prolonged ICU stay was required in ASD patients. Further SHAP analysis demonstrated our model aligned with traditional clinical thinking. Thus, ML models have strong potential to assist with risk stratification and more effective and cost-efficient care.
期刊介绍:
Global Spine Journal (GSJ) is the official scientific publication of AOSpine. A peer-reviewed, open access journal, devoted to the study and treatment of spinal disorders, including diagnosis, operative and non-operative treatment options, surgical techniques, and emerging research and clinical developments.GSJ is indexed in PubMedCentral, SCOPUS, and Emerging Sources Citation Index (ESCI).