Daisuke Ichikawa1, Toki Saito2, Waka Ujita2, Hiroshi Oyama2. 1. Dep. of Clinical Information Engineering, Division of Social Medicine, Graduate School of Medicine, Univ. of Tokyo, Japan. Electronic address: ichikawa-kyu@umin.ac.jp. 2. Dep. of Clinical Information Engineering, Division of Social Medicine, Graduate School of Medicine, Univ. of Tokyo, Japan.
Abstract
OBJECT: Our purpose was to develop a new machine-learning approach (a virtual health check-up) toward identification of those at high risk of hyperuricemia. Applying the system to general health check-ups is expected to reduce medical costs compared with administering an additional test. METHODS: Data were collected during annual health check-ups performed in Japan between 2011 and 2013 (inclusive). We prepared training and test datasets from the health check-up data to build prediction models; these were composed of 43,524 and 17,789 persons, respectively. Gradient-boosting decision tree (GBDT), random forest (RF), and logistic regression (LR) approaches were trained using the training dataset and were then used to predict hyperuricemia in the test dataset. Undersampling was applied to build the prediction models to deal with the imbalanced class dataset. RESULTS: The results showed that the RF and GBDT approaches afforded the best performances in terms of sensitivity and specificity, respectively. The area under the curve (AUC) values of the models, which reflected the total discriminative ability of the classification, were 0.796 [95% confidence interval (CI): 0.766-0.825] for the GBDT, 0.784 [95% CI: 0.752-0.815] for the RF, and 0.785 [95% CI: 0.752-0.819] for the LR approaches. No significant differences were observed between pairs of each approach. Small changes occurred in the AUCs after applying undersampling to build the models. CONCLUSIONS: We developed a virtual health check-up that predicted the development of hyperuricemia using machine-learning methods. The GBDT, RF, and LR methods had similar predictive capability. Undersampling did not remarkably improve predictive power. Copyright Â
OBJECT: Our purpose was to develop a new machine-learning approach (a virtual health check-up) toward identification of those at high risk of hyperuricemia. Applying the system to general health check-ups is expected to reduce medical costs compared with administering an additional test. METHODS: Data were collected during annual health check-ups performed in Japan between 2011 and 2013 (inclusive). We prepared training and test datasets from the health check-up data to build prediction models; these were composed of 43,524 and 17,789 persons, respectively. Gradient-boosting decision tree (GBDT), random forest (RF), and logistic regression (LR) approaches were trained using the training dataset and were then used to predict hyperuricemia in the test dataset. Undersampling was applied to build the prediction models to deal with the imbalanced class dataset. RESULTS: The results showed that the RF and GBDT approaches afforded the best performances in terms of sensitivity and specificity, respectively. The area under the curve (AUC) values of the models, which reflected the total discriminative ability of the classification, were 0.796 [95% confidence interval (CI): 0.766-0.825] for the GBDT, 0.784 [95% CI: 0.752-0.815] for the RF, and 0.785 [95% CI: 0.752-0.819] for the LR approaches. No significant differences were observed between pairs of each approach. Small changes occurred in the AUCs after applying undersampling to build the models. CONCLUSIONS: We developed a virtual health check-up that predicted the development of hyperuricemia using machine-learning methods. The GBDT, RF, and LR methods had similar predictive capability. Undersampling did not remarkably improve predictive power. Copyright Â