RESUMO
The ease of interpretation of a classification model is essential for the task of validating it. Sometimes it is required to clearly explain the classification process of a model's predictions. Models which are inherently easier to interpret can be effortlessly related to the context of the problem, and their predictions can be, if necessary, ethically and legally evaluated. In this paper, we propose a novel method to generate rule-based classifiers from categorical data that can be readily interpreted. Classifiers are generated using a multi-objective optimization approach focusing on two main objectives: maximizing the performance of the learned classifier and minimizing its number of rules. The multi-objective evolutionary algorithms ENORA and NSGA-II have been adapted to optimize the performance of the classifier based on three different machine learning metrics: accuracy, area under the ROC curve, and root mean square error. We have extensively compared the generated classifiers using our proposed method with classifiers generated using classical methods such as PART, JRip, OneR and ZeroR. The experiments have been conducted in full training mode, in 10-fold cross-validation mode, and in train/test splitting mode. To make results reproducible, we have used the well-known and publicly available datasets Breast Cancer, Monk's Problem 2, Tic-Tac-Toe-Endgame, Car, kr-vs-kp and Nursery. After performing an exhaustive statistical test on our results, we conclude that the proposed method is able to generate highly accurate and easy to interpret classification models.
RESUMO
Bone Strain Index (BSI) is a new dual-energy x-ray absorptiometry (DXA)-based index. We retrospectively evaluated data from 153 postmenopausal women with a history of type 2 diabetes mellitus (T2DM). Lumbar spine and femoral Bone Strain Index (BSI) were sensitive to skeletal impairment in postmenopausal women suffering from T2DM. PURPOSE: Bone Strain Index (BSI) is a new dual-energy X-ray absorptiometry (DXA)-based measurement. We evaluated the performance of BSI in predicting the presence of fragility fractures in type 2 diabetes mellitus (T2DM) postmenopausal women. METHODS: We retrospectively evaluated data from a case-control study of 153 postmenopausal women with a history of at least 5 years of T2DM (age from 40 to 90 years). For each subject, we assessed the personal or familiar history of previous fragility fractures and menopause age, and we collected data about bone mineral density (BMD), BSI, and Trabecular Bone Score (TBS) measurements. Statistical analysis was performed having as outcome the history of fragility fractures. RESULTS: Out of a total of 153 subjects, n = 22 (14.4%) presented at least one major fragility fracture. A negative correlation was found between lumbar BSI and lumbar BMD (r = - 0.49, p < 0.001) and between total femur BSI and total femur BMD (r = - 0.49, p < 0.001). A negative correlation was found between femoral neck BSI and femoral neck BMD (r = - 0.22, p < 0.001). Most DXA-based variables were individually able to discriminate between fractured and non-fractured subjects (p < 0.05), and lumbar BSI was the index with the most relative difference between the two populations, followed by femoral BSI. CONCLUSION: Lumbar spine and femoral BSI are sensitive to skeletal impairment in postmenopausal women suffering from T2DM. The use of BSI in conjunction with BMD and TBS can improve fracture risk assessment.