van der Ploeg Tjeerd, Gobbens Robbert
Faculty of Health, Sports and Social Work, Inholland University of Applied Sciences, Amsterdam, Netherlands.
Zonnehuisgroep Amstelland, Amstelveen, Netherlands.
JMIR Med Inform. 2022 Mar 30;10(3):e31480. doi: 10.2196/31480.
Modern modeling techniques may potentially provide more accurate predictions of dichotomous outcomes than classical techniques.
In this study, we aimed to examine the predictive performance of eight modeling techniques to predict mortality by frailty.
We performed a longitudinal study with a 7-year follow-up. The sample consisted of 479 Dutch community-dwelling people, aged 75 years and older. Frailty was assessed with the Tilburg Frailty Indicator (TFI), a self-report questionnaire. This questionnaire consists of eight physical, four psychological, and three social frailty components. The municipality of Roosendaal, a city in the Netherlands, provided the mortality dates. We compared modeling techniques, such as support vector machine (SVM), neural network (NN), random forest, and least absolute shrinkage and selection operator, as well as classical techniques, such as logistic regression, two Bayesian networks, and recursive partitioning (RP). The area under the receiver operating characteristic curve (AUROC) indicated the performance of the models. The models were validated using bootstrapping.
We found that the NN model had the best validated performance (AUROC=0.812), followed by the SVM model (AUROC=0.705). The other models had validated AUROC values below 0.700. The RP model had the lowest validated AUROC (0.605). The NN model had the highest optimism (0.156). The predictor variable "difficulty in walking" was important for all models.
Because of the high optimism of the NN model, we prefer the SVM model for predicting mortality among community-dwelling older people using the TFI, with the addition of "gender" and "age" variables. External validation is a necessary step before applying the prediction models in a new setting.
与传统技术相比，现代建模技术可能会更准确地预测二分结果。
在本研究中，我们旨在检验八种建模技术通过衰弱来预测死亡率的预测性能。
我们进行了一项为期7年随访的纵向研究。样本包括479名年龄在75岁及以上的荷兰社区居民。使用蒂尔堡衰弱指标（TFI）这一自我报告问卷评估衰弱情况。该问卷由八个身体、四个心理和三个社会衰弱成分组成。荷兰城市罗森达尔市提供了死亡日期。我们比较了支持向量机（SVM）、神经网络（NN）、随机森林和最小绝对收缩和选择算子等建模技术，以及逻辑回归、两个贝叶斯网络和递归划分（RP）等传统技术。受试者工作特征曲线下面积（AUROC）表明了模型的性能。使用自助法对模型进行验证。
我们发现NN模型具有最佳的验证性能（AUROC = 0.812），其次是SVM模型（AUROC = 0.705）。其他模型的验证AUROC值低于0.700。RP模型的验证AUROC最低（0.605）。NN模型的乐观度最高（0.156）。预测变量“行走困难”对所有模型都很重要。
由于NN模型的乐观度较高，我们更倾向于使用SVM模型，通过TFI并添加“性别”和“年龄”变量来预测社区居住老年人的死亡率。在新环境中应用预测模型之前，外部验证是必要的一步。
