An evaluation model for children's foot & ankle deformity severity using sparse multi-objective feature selection algorithm.

Foot & ankle deformity is a chronic disease with high incidence and is best treated in childhood. However, the current diagnostic procedures rely on doctor's consultation and empirical judgment, and lack objective and quantitative evaluation methods, resulting in low screening rates. To solve this problem, this paper aims to construct an evaluation model for children's foot & ankle deformity through data mining and machine learning technologies. Firstly, it proposes the grading rules for children's foot & ankle deformity severity based on analyzing the existing quantitative indexes and expert experience. Then the 3D foot scanner is used to collect the sample data including 30 foot structure indexes. Finally, an advanced sparse multi-objective evolutionary algorithm (sparse MO-FS) is present for feature selection. The effectiveness of the proposed sparse MO-FS and its search efficiency are proved by comparing 8 feature selection methods and 7 search strategies. Using sparse MO-FS, foot length, arch index, ankle index, and hallux valgus index are selected, which not only simplifies the evaluation model but also improves the average classification accuracy of random forest to more than 98%.

Associations between bone mineral density and chronic obstructive pulmonary disease.

OBJECTIVE: To assess the relationship between chronic obstructive pulmonary disease (COPD) severity and bone mineral density (BMD) in the whole body and different body areas. METHODS: This retrospective, cross-sectional study included patients with COPD. Demographic and lung function data, COPD severity scales, BMD, and T scores were collected. Patients were grouped by high (≥-1) and low (<-1) T scores, and stratified by body mass index, airway obstruction, dyspnoea, and exercise capacity (BODE) index. The relationship between whole-body BMD and BODE was evaluated by Kendall's tau-b correlation coefficient. Risk factors associated with COPD severity were identified by univariate analyses. BMD as an independent predictor of severe COPD (BODE ≥5) was verified by multivariate logistic regression. BMD values in different body areas for predicting severe COPD were assessed by receiver operating characteristic curves. RESULTS: Of 88 patients with COPD, lung-function indicators and COPD severity were significantly different between those with high and low T scores. Whole-body BMD was inversely related to COPD severity scales, including BODE. Multivariate logistic regression revealed that BMD was independently associated with COPD severity. The area under the curve for pelvic BMD in predicting severe COPD was 0.728. CONCLUSION: BMD may be a novel marker in predicting COPD severity, and pelvic BMD may have the strongest relative predictive power.