44. 骨质疏松性椎体压缩性骨折骨质疏松性椎体骨水泥成形术后邻近骨折预测的新型机器学习模型的建立

IF 2.5 Q3 Medicine

North American Spine Society Journal Pub Date : 2025-07-01 DOI:10.1016/j.xnsj.2025.100738

Yu-Cheng Yao MD , Po-Hsin Chou MD , Bruce H Lin MD , Shih-Tien Wang MD

{"title":"44. 骨质疏松性椎体压缩性骨折骨质疏松性椎体骨水泥成形术后邻近骨折预测的新型机器学习模型的建立","authors":"Yu-Cheng Yao MD , Po-Hsin Chou MD , Bruce H Lin MD , Shih-Tien Wang MD","doi":"10.1016/j.xnsj.2025.100738","DOIUrl":null,"url":null,"abstract":"<div><h3>BACKGROUND CONTEXT</h3><div>There are approximately 30% of patients with osteoporotic vertebral compression fracture (OVCF) who need cementoplasty for treatment. However, the occurrence of adjacent vertebral fracture (AVF) postoperatively can lead to increased pain, delayed recovery, and poorer prognosis. Current literature identifies over 30 risk factors for AVF, including patient-specific factors, preoperative and postoperative radiographical features, and surgical-related factors. There is no effective predictive model in understanding the probability of AVF occurrence preoperatively.</div></div><div><h3>PURPOSE</h3><div>This study aims to develop a robust AVF predictive model using machine learning method.</div></div><div><h3>STUDY DESIGN/SETTING</h3><div>Retrospective cohort study.</div></div><div><h3>PATIENT SAMPLE</h3><div>A total of 238 patients with OVCF who underwent single level cementoplasty were included for analysis.</div></div><div><h3>OUTCOME MEASURES</h3><div>Adjacent fracture.</div></div><div><h3>METHODS</h3><div>This is a retrospective cohort analysis. Patients with OVCF who underwent single level cementoplasty between January 2016 and December 2021 were included. Exclusion criteria were pathological fractures, patients with prior cementoplasty or spinal surgeries, and follow-up less than 12 months. Total 32 preoperative clinical and radiographic features were recorded, include patient demographics, DXA, chronic diseases, vertebral height (VH), wedge angle (WA) of fracture vertebra, local kyphotic angle (LKA), presence of posterior wall fracture (PostWall), and presence of diffuse idiopathic skeletal hyperostosis (DISH), CT vertebral Hounsfield units (HU), CT psoas lumbar vertebral index (PLVI). Ten different machine learning algorithms were used to find the best model. Confusion matrix and related indicators include Accuracy, sensitivity (Se), specificity (Sp) and ROC-AUC were used to evaluate the model performance.</div></div><div><h3>RESULTS</h3><div>A total of 238 patients were included for analysis, with an average age of 77 years and 69% were female. Most fractures located at the TL junction (64%). The AVF rate was 27.3% during the follow-up and it occurred at postoperative 3.2 months. We found the random forest model had the best performance with 83% accuracy, AUC 0.92, Se: 82%, and Sp: 85%. Among the total 32 features, we found that the 11 most important features by orders were PostWall, HU_L2, DISH, L4_PLVI, WA, MVH, BMI, LKA, Age, and fracture level. Even using those 11 features alone, the model performance could reach 78% accuracy, AUC 0.88, Se: 80%, and Sp 76%.</div></div><div><h3>CONCLUSIONS</h3><div>The novel machine learning model for predicting AVF using preoperative features demonstrated excellent performance, achieving an AUC of 0.92. This model can assist clinicians and patients with OVCF in understanding the probability of AVF occurrence after cementoplasty. For patients identified as high-risk, prophylactic cementoplasty at adjacent levels or other medical interventions may provide some benefits.</div></div><div><h3>FDA Device/Drug Status</h3><div>This abstract does not discuss or include any applicable devices or drugs.</div></div>","PeriodicalId":34622,"journal":{"name":"North American Spine Society Journal","volume":"22 ","pages":"Article 100738"},"PeriodicalIF":2.5000,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"44. Development of a novel machine learning model for prediction of adjacent fracture after cementoplasty in treating osteoporotic vertebral compression fracture\",\"authors\":\"Yu-Cheng Yao MD , Po-Hsin Chou MD , Bruce H Lin MD , Shih-Tien Wang MD\",\"doi\":\"10.1016/j.xnsj.2025.100738\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>BACKGROUND CONTEXT</h3><div>There are approximately 30% of patients with osteoporotic vertebral compression fracture (OVCF) who need cementoplasty for treatment. However, the occurrence of adjacent vertebral fracture (AVF) postoperatively can lead to increased pain, delayed recovery, and poorer prognosis. Current literature identifies over 30 risk factors for AVF, including patient-specific factors, preoperative and postoperative radiographical features, and surgical-related factors. There is no effective predictive model in understanding the probability of AVF occurrence preoperatively.</div></div><div><h3>PURPOSE</h3><div>This study aims to develop a robust AVF predictive model using machine learning method.</div></div><div><h3>STUDY DESIGN/SETTING</h3><div>Retrospective cohort study.</div></div><div><h3>PATIENT SAMPLE</h3><div>A total of 238 patients with OVCF who underwent single level cementoplasty were included for analysis.</div></div><div><h3>OUTCOME MEASURES</h3><div>Adjacent fracture.</div></div><div><h3>METHODS</h3><div>This is a retrospective cohort analysis. Patients with OVCF who underwent single level cementoplasty between January 2016 and December 2021 were included. Exclusion criteria were pathological fractures, patients with prior cementoplasty or spinal surgeries, and follow-up less than 12 months. Total 32 preoperative clinical and radiographic features were recorded, include patient demographics, DXA, chronic diseases, vertebral height (VH), wedge angle (WA) of fracture vertebra, local kyphotic angle (LKA), presence of posterior wall fracture (PostWall), and presence of diffuse idiopathic skeletal hyperostosis (DISH), CT vertebral Hounsfield units (HU), CT psoas lumbar vertebral index (PLVI). Ten different machine learning algorithms were used to find the best model. Confusion matrix and related indicators include Accuracy, sensitivity (Se), specificity (Sp) and ROC-AUC were used to evaluate the model performance.</div></div><div><h3>RESULTS</h3><div>A total of 238 patients were included for analysis, with an average age of 77 years and 69% were female. Most fractures located at the TL junction (64%). The AVF rate was 27.3% during the follow-up and it occurred at postoperative 3.2 months. We found the random forest model had the best performance with 83% accuracy, AUC 0.92, Se: 82%, and Sp: 85%. Among the total 32 features, we found that the 11 most important features by orders were PostWall, HU_L2, DISH, L4_PLVI, WA, MVH, BMI, LKA, Age, and fracture level. Even using those 11 features alone, the model performance could reach 78% accuracy, AUC 0.88, Se: 80%, and Sp 76%.</div></div><div><h3>CONCLUSIONS</h3><div>The novel machine learning model for predicting AVF using preoperative features demonstrated excellent performance, achieving an AUC of 0.92. This model can assist clinicians and patients with OVCF in understanding the probability of AVF occurrence after cementoplasty. For patients identified as high-risk, prophylactic cementoplasty at adjacent levels or other medical interventions may provide some benefits.</div></div><div><h3>FDA Device/Drug Status</h3><div>This abstract does not discuss or include any applicable devices or drugs.</div></div>\",\"PeriodicalId\":34622,\"journal\":{\"name\":\"North American Spine Society Journal\",\"volume\":\"22 \",\"pages\":\"Article 100738\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2025-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"North American Spine Society Journal\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2666548425001581\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Medicine\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"North American Spine Society Journal","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666548425001581","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Medicine","Score":null,"Total":0}

引用次数: 0

摘要

大约30%的骨质疏松性椎体压缩性骨折（OVCF）患者需要骨水泥成形术进行治疗。然而，术后发生相邻椎体骨折（AVF）可导致疼痛增加，恢复延迟，预后较差。目前的文献确定了30多种AVF的危险因素，包括患者特异性因素、术前和术后影像学特征以及手术相关因素。术前没有有效的预测模型来了解AVF发生的概率。目的利用机器学习方法建立稳健的AVF预测模型。研究设计/设置：回顾性队列研究。患者SAMPLEA共纳入238例接受单水平骨水泥成形术的OVCF患者进行分析。结果：邻近骨折。方法回顾性队列分析。在2016年1月至2021年12月期间接受单节段骨水泥成形术的OVCF患者纳入研究。排除标准为病理性骨折，既往骨质成形术或脊柱手术患者，随访时间少于12个月。共记录32个术前临床和影像学特征，包括患者人口统计学特征、DXA、慢性疾病、椎体高度（VH）、骨折椎体楔形角（WA）、局部后凸角（LKA）、是否存在后壁骨折（PostWall）、是否存在弥漫性特发性骨骼肥厚（DISH）、CT椎体Hounsfield单位（HU）、CT腰椎间盘指数（PLVI）。使用了10种不同的机器学习算法来寻找最佳模型。使用混淆矩阵及相关指标准确性、敏感性（Se）、特异性（Sp）和ROC-AUC来评价模型的性能。结果238例患者纳入分析，平均年龄77岁，女性占69%。大多数骨折位于左端交界处（64%）。随访期间AVF发生率为27.3%，发生于术后3.2个月。我们发现随机森林模型具有最佳性能，准确率为83%，AUC为0.92，Se为82%，Sp为85%。在32个特征中，我们发现按顺序排列最重要的11个特征是PostWall、HU_L2、DISH、L4_PLVI、WA、MVH、BMI、LKA、Age和骨折程度。即使仅使用这11个特征，模型性能也可以达到78%的准确率，AUC为0.88，Se为80%，Sp为76%。结论利用术前特征预测AVF的机器学习模型表现优异，AUC为0.92。该模型可以帮助临床医生和OVCF患者了解骨水泥成形术后AVF发生的概率。对于确定为高危的患者，预防性相邻水平的骨水泥成形术或其他医疗干预可能会带来一些好处。FDA器械/药物状态本摘要不讨论或包括任何适用的器械或药物。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

44. Development of a novel machine learning model for prediction of adjacent fracture after cementoplasty in treating osteoporotic vertebral compression fracture

BACKGROUND CONTEXT

There are approximately 30% of patients with osteoporotic vertebral compression fracture (OVCF) who need cementoplasty for treatment. However, the occurrence of adjacent vertebral fracture (AVF) postoperatively can lead to increased pain, delayed recovery, and poorer prognosis. Current literature identifies over 30 risk factors for AVF, including patient-specific factors, preoperative and postoperative radiographical features, and surgical-related factors. There is no effective predictive model in understanding the probability of AVF occurrence preoperatively.

PURPOSE

This study aims to develop a robust AVF predictive model using machine learning method.

STUDY DESIGN/SETTING

Retrospective cohort study.

PATIENT SAMPLE

A total of 238 patients with OVCF who underwent single level cementoplasty were included for analysis.

OUTCOME MEASURES

Adjacent fracture.

METHODS

This is a retrospective cohort analysis. Patients with OVCF who underwent single level cementoplasty between January 2016 and December 2021 were included. Exclusion criteria were pathological fractures, patients with prior cementoplasty or spinal surgeries, and follow-up less than 12 months. Total 32 preoperative clinical and radiographic features were recorded, include patient demographics, DXA, chronic diseases, vertebral height (VH), wedge angle (WA) of fracture vertebra, local kyphotic angle (LKA), presence of posterior wall fracture (PostWall), and presence of diffuse idiopathic skeletal hyperostosis (DISH), CT vertebral Hounsfield units (HU), CT psoas lumbar vertebral index (PLVI). Ten different machine learning algorithms were used to find the best model. Confusion matrix and related indicators include Accuracy, sensitivity (Se), specificity (Sp) and ROC-AUC were used to evaluate the model performance.

RESULTS

A total of 238 patients were included for analysis, with an average age of 77 years and 69% were female. Most fractures located at the TL junction (64%). The AVF rate was 27.3% during the follow-up and it occurred at postoperative 3.2 months. We found the random forest model had the best performance with 83% accuracy, AUC 0.92, Se: 82%, and Sp: 85%. Among the total 32 features, we found that the 11 most important features by orders were PostWall, HU_L2, DISH, L4_PLVI, WA, MVH, BMI, LKA, Age, and fracture level. Even using those 11 features alone, the model performance could reach 78% accuracy, AUC 0.88, Se: 80%, and Sp 76%.

CONCLUSIONS

The novel machine learning model for predicting AVF using preoperative features demonstrated excellent performance, achieving an AUC of 0.92. This model can assist clinicians and patients with OVCF in understanding the probability of AVF occurrence after cementoplasty. For patients identified as high-risk, prophylactic cementoplasty at adjacent levels or other medical interventions may provide some benefits.