James Bridges, Norris C Talbot, Michael Folse, Stephen Whipple, Bharat Guthikonda, Navdeep Samra, Deepak Kumbhare
{"title":"外伤性脊髓损伤患者出院的预测因素识别和预测模型的建立:对国家创伤数据库的回顾性分析。","authors":"James Bridges, Norris C Talbot, Michael Folse, Stephen Whipple, Bharat Guthikonda, Navdeep Samra, Deepak Kumbhare","doi":"10.20408/jti.2025.0049","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Previous studies have shown that early rehabilitation is associated with better long-term outcomes in patients with traumatic spinal cord injury. However, data are still limited regarding which factors are associated with discharge to a rehabilitation facility. This study aims to expand on prior research by identifying factors associated with disposition and by introducing a prediction model for these factors.</p><p><strong>Methods: </strong>The National Trauma Data Bank was queried for patients aged 18 years or older who presented to US trauma centers from 2019 to 2021 with traumatic spinal cord injury. Multivariate logistic regression models were used to determine which patient, injury, and hospital variables were significant factors for disposition to a rehabilitation facility, compared to home and intermediate care facilities. Prediction modeling was then performed using these factors.</p><p><strong>Results: </strong>Overall, 14,597 patients were identified, of whom 6,220 were discharged to a rehabilitation facility, 2,647 to an intermediate care facility, and 5,730 to home. Significant factors associated with discharge to a rehabilitation facility compared to home included age, injury location and severity, insurance type, estimated length of stay, systolic blood pressure at admission, and admission blood alcohol level and drug screen results. Similarly, when comparing discharge to a rehabilitation facility with discharge to an intermediate care facility, sex, age, race, estimated length of stay, systolic blood pressure at admission, drug screen results, and coexisting substance use and metabolic conditions all significantly influenced disposition. Fine tree binary classification achieved a prediction accuracy of 72.5% when comparing discharge to a rehabilitation facility and home, and a prediction accuracy of 70.0% when comparing discharge to a rehabilitation facility and an intermediate care facility.</p><p><strong>Conclusions: </strong>This study demonstrates significant factors associated with discharge to a rehabilitation facility in patients with traumatic spinal cord injury. Further studies are needed to improve prediction accuracy.</p>","PeriodicalId":52698,"journal":{"name":"Journal of Trauma and Injury","volume":"38 3","pages":"255-267"},"PeriodicalIF":0.2000,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Identification of predictive factors and development of a prediction model for rehabilitation facility discharge in patients with traumatic spinal cord injury: a retrospective analysis of the National Trauma Data Bank.\",\"authors\":\"James Bridges, Norris C Talbot, Michael Folse, Stephen Whipple, Bharat Guthikonda, Navdeep Samra, Deepak Kumbhare\",\"doi\":\"10.20408/jti.2025.0049\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>Previous studies have shown that early rehabilitation is associated with better long-term outcomes in patients with traumatic spinal cord injury. However, data are still limited regarding which factors are associated with discharge to a rehabilitation facility. This study aims to expand on prior research by identifying factors associated with disposition and by introducing a prediction model for these factors.</p><p><strong>Methods: </strong>The National Trauma Data Bank was queried for patients aged 18 years or older who presented to US trauma centers from 2019 to 2021 with traumatic spinal cord injury. Multivariate logistic regression models were used to determine which patient, injury, and hospital variables were significant factors for disposition to a rehabilitation facility, compared to home and intermediate care facilities. Prediction modeling was then performed using these factors.</p><p><strong>Results: </strong>Overall, 14,597 patients were identified, of whom 6,220 were discharged to a rehabilitation facility, 2,647 to an intermediate care facility, and 5,730 to home. Significant factors associated with discharge to a rehabilitation facility compared to home included age, injury location and severity, insurance type, estimated length of stay, systolic blood pressure at admission, and admission blood alcohol level and drug screen results. Similarly, when comparing discharge to a rehabilitation facility with discharge to an intermediate care facility, sex, age, race, estimated length of stay, systolic blood pressure at admission, drug screen results, and coexisting substance use and metabolic conditions all significantly influenced disposition. Fine tree binary classification achieved a prediction accuracy of 72.5% when comparing discharge to a rehabilitation facility and home, and a prediction accuracy of 70.0% when comparing discharge to a rehabilitation facility and an intermediate care facility.</p><p><strong>Conclusions: </strong>This study demonstrates significant factors associated with discharge to a rehabilitation facility in patients with traumatic spinal cord injury. Further studies are needed to improve prediction accuracy.</p>\",\"PeriodicalId\":52698,\"journal\":{\"name\":\"Journal of Trauma and Injury\",\"volume\":\"38 3\",\"pages\":\"255-267\"},\"PeriodicalIF\":0.2000,\"publicationDate\":\"2025-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Trauma and Injury\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.20408/jti.2025.0049\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/9/29 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Trauma and Injury","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.20408/jti.2025.0049","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/9/29 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
Identification of predictive factors and development of a prediction model for rehabilitation facility discharge in patients with traumatic spinal cord injury: a retrospective analysis of the National Trauma Data Bank.
Purpose: Previous studies have shown that early rehabilitation is associated with better long-term outcomes in patients with traumatic spinal cord injury. However, data are still limited regarding which factors are associated with discharge to a rehabilitation facility. This study aims to expand on prior research by identifying factors associated with disposition and by introducing a prediction model for these factors.
Methods: The National Trauma Data Bank was queried for patients aged 18 years or older who presented to US trauma centers from 2019 to 2021 with traumatic spinal cord injury. Multivariate logistic regression models were used to determine which patient, injury, and hospital variables were significant factors for disposition to a rehabilitation facility, compared to home and intermediate care facilities. Prediction modeling was then performed using these factors.
Results: Overall, 14,597 patients were identified, of whom 6,220 were discharged to a rehabilitation facility, 2,647 to an intermediate care facility, and 5,730 to home. Significant factors associated with discharge to a rehabilitation facility compared to home included age, injury location and severity, insurance type, estimated length of stay, systolic blood pressure at admission, and admission blood alcohol level and drug screen results. Similarly, when comparing discharge to a rehabilitation facility with discharge to an intermediate care facility, sex, age, race, estimated length of stay, systolic blood pressure at admission, drug screen results, and coexisting substance use and metabolic conditions all significantly influenced disposition. Fine tree binary classification achieved a prediction accuracy of 72.5% when comparing discharge to a rehabilitation facility and home, and a prediction accuracy of 70.0% when comparing discharge to a rehabilitation facility and an intermediate care facility.
Conclusions: This study demonstrates significant factors associated with discharge to a rehabilitation facility in patients with traumatic spinal cord injury. Further studies are needed to improve prediction accuracy.