Scholarlink

Background <p>Diffuse brain swelling (DBS) significantly contributes to intracranial hypertension and poses a substantial risk of early neurological deterioration (END). This study aimed to develop and validate various machine learning (ML) models for predicting END in patients with traumatic DBS.</p> Methods <p>Clinical data were retrospectively collected from 208 consecutive adult patients diagnosed with traumatic DBS on admission (within 6&#xa0;h after injury) at two centers. END was assessed within 72&#xa0;h of admission, and predictors for END were identified using least absolute shrinkage and selection operator regression and multivariate logistic regression analysis. Six ML algorithms were trained to develop prediction models. The performance of the&#xa0;ML models was evaluated by the area under the receiver operating characteristic curve (AUROC), Brier score, and decision curve analysis and was externally verified in the validation cohort. The optimal model was internally cross-validated, interpreted using Shapley Additive Explanations, and ultimately deployed as a Web-based risk calculator.</p> Results <p>A total of 79 patients experienced END, with an incidence of 38.0%. The&#xa0;four confirmed predictors of END were subdural hemorrhage, severe traumatic subarachnoid hemorrhage, hemoglobin levels, and fibrinogen levels. The extreme gradient boosting model outperformed the other five models in discrimination, achieving an AUROC of 0.879, and had better calibration and clinical utility. This model had an acceptable generalizability, achieving mean AUROCs of 0.762 ± 0.033 and 0.770 ± 0.109 in fivefold and tenfold cross-validations, respectively, and an AUROC of 0.862 in the validation cohort.</p> Conclusions <p>The developed ML model shows clinical promise in accurately predicting END following traumatic DBS. However, multicenter external validation remains essential before its widespread clinical application.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Interpretable Machine Learning Model for Predicting Early Neurological Deterioration Following Posttraumatic Acute Diffuse Brain Swelling

  • 期刊论文

  • 发表日期：

    2025年8月11日

查看全文
  • Shilong Fu,
  • Xianqun Wu,
  • Guofeng Wang,
  • Zongping Wu,
  • Shousen Wang

摘要

Background

Diffuse brain swelling (DBS) significantly contributes to intracranial hypertension and poses a substantial risk of early neurological deterioration (END). This study aimed to develop and validate various machine learning (ML) models for predicting END in patients with traumatic DBS.

Methods

Clinical data were retrospectively collected from 208 consecutive adult patients diagnosed with traumatic DBS on admission (within 6 h after injury) at two centers. END was assessed within 72 h of admission, and predictors for END were identified using least absolute shrinkage and selection operator regression and multivariate logistic regression analysis. Six ML algorithms were trained to develop prediction models. The performance of the ML models was evaluated by the area under the receiver operating characteristic curve (AUROC), Brier score, and decision curve analysis and was externally verified in the validation cohort. The optimal model was internally cross-validated, interpreted using Shapley Additive Explanations, and ultimately deployed as a Web-based risk calculator.

Results

A total of 79 patients experienced END, with an incidence of 38.0%. The four confirmed predictors of END were subdural hemorrhage, severe traumatic subarachnoid hemorrhage, hemoglobin levels, and fibrinogen levels. The extreme gradient boosting model outperformed the other five models in discrimination, achieving an AUROC of 0.879, and had better calibration and clinical utility. This model had an acceptable generalizability, achieving mean AUROCs of 0.762 ± 0.033 and 0.770 ± 0.109 in fivefold and tenfold cross-validations, respectively, and an AUROC of 0.862 in the validation cohort.

Conclusions

The developed ML model shows clinical promise in accurately predicting END following traumatic DBS. However, multicenter external validation remains essential before its widespread clinical application.