Van Deynse Helena, Cools Wilfried, De Deken Viktor-Jan, Depreitere Bart, Hubloue Ives, Kimpe Eva, Moens Maarten, Pien Karen, Tisseghem Ellen, Van Belleghem Griet, Putman Koen
Interuniversity Centre for Health Economics Research (I-CHER), Vrije Universiteit Brussel, Brussels, Belgium.
Support for Quantitative and Qualitative Research (SQUARE), Vrije Universiteit Brussel, Brussels, Belgium.
Int J Med Inform. 2023 Oct;178:105201. doi: 10.1016/j.ijmedinf.2023.105201. Epub 2023 Aug 24.
Accurate patient-specific predictions on return-to-work after traumatic brain injury (TBI) can support both clinical practice and policymaking. The use of machine learning on large administrative data provides interesting opportunities to create such prognostic models.
The current study assesses whether return-to-work one year after TBI can be predicted accurately from administrative data. Additionally, this study explores how model performance and feature importance change depending on whether a distinction is made between mild and moderate-to-severe TBI.
This study used a population-based dataset that combined discharge, claims and social security data of patients hospitalized with a TBI in Belgium during the year 2016. The prediction of TBI was attempted with three algorithms, elastic net logistic regression, random forest and gradient boosting and compared in their performance by their accuracy, sensitivity, specificity and area under the receiver operator curve (ROC AUC).
The distinct modelling algorithms resulted in similar results, with 83% accuracy (ROC AUC 85%) for a binary classification of employed vs. not employed and up to 76% (ROC AUC 82%) for a multiclass operationalization of employment outcome. Modelling mild and moderate-to-severe TBI separately did not result in considerable differences in model performance and feature importance. The features of main importance for return-to-work prediction were related to pre-injury employment.
While clearly offering some information beneficial for predicting return-to-work, administrative data needs to be supplemented with additional information to allow further improvement of patient-specific prognose.
对创伤性脑损伤（TBI）后患者恢复工作情况进行准确的个体化预测，可为临床实践和政策制定提供支持。利用机器学习处理大型行政数据为创建此类预后模型提供了有趣的机会。
本研究评估能否根据行政数据准确预测TBI后一年的恢复工作情况。此外，本研究还探讨了根据轻度与中度至重度TBI是否区分，模型性能和特征重要性如何变化。
本研究使用了一个基于人群的数据集，该数据集结合了2016年在比利时因TBI住院患者的出院、理赔和社会保障数据。尝试使用三种算法（弹性网络逻辑回归、随机森林和梯度提升）对TBI进行预测，并通过准确率、灵敏度、特异性和受试者工作特征曲线下面积（ROC AUC）比较它们的性能。
不同的建模算法得出了相似的结果，对于就业与否的二元分类，准确率为83%（ROC AUC为85%），对于就业结果的多分类操作，准确率高达76%（ROC AUC为82%）。分别对轻度和中度至重度TBI进行建模，在模型性能和特征重要性方面没有产生显著差异。对恢复工作预测最重要的特征与伤前就业情况有关。
虽然行政数据显然提供了一些有助于预测恢复工作情况的信息，但需要补充额外信息，以进一步改善个体化预后。
