Gedeborg Rolf, Svennblad Bodil, Byberg Liisa, Michaëlsson Karl, Thiblin Ingemar
Dept. of Surgical Sciences, Anesthesiology and Intensive Care, Uppsala University, Uppsala, Sweden; Uppsala Clinical Research Center, Uppsala University, Uppsala, Sweden.
Uppsala Clinical Research Center, Uppsala University, Uppsala, Sweden.
Forensic Sci Int. 2017 Dec;281:92-97. doi: 10.1016/j.forsciint.2017.10.015. Epub 2017 Oct 20.
To predict mortality risk in victims of violent crimes based on individual injury diagnoses and other information available in health care registries.
Data from the Swedish hospital discharge registry and the cause of death registry were combined to identify 15,000 hospitalisations or prehospital deaths related to violent crimes. The ability of patient characteristics, injury type and severity, and cause of injury to predict death was modelled using conventional, Lasso, or Bayesian logistic regression in a development dataset and evaluated in a validation dataset.
Of 14,470 injury events severe enough to cause death or hospitalization 3.7% (556) died before hospital admission and 0.5% (71) during the hospital stay. The majority (76%) of hospital survivors had minor injury severity and most (67%) were discharged from hospital within 1day. A multivariable model with age, sex, the ICD-10 based injury severity score (ICISS), cause of injury, and major injury region provided predictions with very good discrimination (C-index=0.99) and calibration. Adding information on major injury interactions further improved model performance. Modeling individual injury diagnoses did not improve predictions over the combined ICISS score.
Mortality risk after violent crimes can be accurately estimated using administrative data. The use of Bayesian regression models provides meaningful risk assessment with more straightforward interpretation of uncertainty of the prediction, potentially also on the individual level. This can aid estimation of incidence trends over time and comparisons of outcome of violent crimes for injury surveillance and in forensic medicine.
基于个体损伤诊断及医疗保健登记处的其他可用信息，预测暴力犯罪受害者的死亡风险。
将瑞典医院出院登记处和死亡原因登记处的数据相结合，以识别15000例与暴力犯罪相关的住院治疗或院前死亡病例。在一个开发数据集中，使用传统、套索或贝叶斯逻辑回归对患者特征、损伤类型和严重程度以及损伤原因预测死亡的能力进行建模，并在一个验证数据集中进行评估。
在14470例严重到足以导致死亡或住院的损伤事件中，3.7%（556例）在入院前死亡，0.5%（71例）在住院期间死亡。大多数（76%）医院幸存者的损伤严重程度较轻，且大多数（67%）在1天内出院。一个包含年龄、性别、基于国际疾病分类第十版的损伤严重程度评分（ICISS）、损伤原因和主要损伤区域的多变量模型提供了具有非常好的区分度（C指数=0.99）和校准的预测。添加关于主要损伤相互作用的信息进一步改善了模型性能。对个体损伤诊断进行建模并没有比综合ICISS评分在预测方面有更大改善。
使用行政数据可以准确估计暴力犯罪后的死亡风险。贝叶斯回归模型的使用提供了有意义的风险评估，对预测不确定性的解释更直接，可能在个体层面也是如此。这有助于估计随时间推移的发病率趋势，并比较暴力犯罪的结果，以进行损伤监测和法医学研究。
