Ensemble-based regression analysis of multimodal medical data for osteopenia diagnosis

Areal bone mineral density (aBMD) is used in clinical practice to diagnose osteoporosis. In previous studies, aBMD was estimated from diagnostic computed tomography (dCT) images, but a battery of medical tests was also taken that can be used to improve the regression performance. However, it is difficult to exploit the multimodal data as the additional features have poor informativeness and may lead to overfitting. An ensemble-based framework is proposed to improve the regression accuracy and robustness on multimodal medical data with a high relative dimensionality. Instead of case-wise bootstrap aggregating, a filtering-based metalearner scheme was employed to build feature-wise ensembles. The proposed approach was evaluated on clinical data and was found to be superior to bagging and other ensemble methods. The feature-wise ensembling approach can also be used to automatically determine if any multimodal features are related to bone mineral density. Several blood measurements were identified to be linked with bone mineral density, and a literature search supported the automatic identification results.

► A filtering-based ensemble regression method for multimodal medical data sets is proposed.
► A filtering method selects a diverse set of regressors from feature-wise bootstraps.
► Accuracy and robustness are improved for multimodal medical data sets.
► The filtering approach can also be used to identify potential relationships between features and the target variable.