Rule extraction from biased random forest and fuzzy support vector machine for early diagnosis of diabetes

Abstract

Due to concealed initial symptoms, many diabetic patients are not diagnosed in time, which delays treatment. Machine learning methods have been applied to increase the diagnosis rate, but most of them are black boxes lacking interpretability. Rule extraction is usually used to turn on the black box. As the number of diabetic patients is far less than that of healthy people, the rules obtained by the existing rule extraction methods tend to identify healthy people rather than diabetic patients. To address the problem, a method for extracting reduced rules based on biased random forest and fuzzy support vector machine is proposed. Biased random forest uses the k-nearest neighbor (k-NN) algorithm to identify critical samples and generates more trees that tend to diagnose diabetes based on critical samples to improve the tendency of the generated rules for diabetic patients. In addition, the conditions and rules are reduced based on the error rate and coverage rate to enhance interpretability. Experiments on the Diabetes Medical Examination Data collected by Beijing Hospital (DMED-BH) dataset demonstrate that the proposed approach has outstanding results (MCC = 0.8802) when the rules are similar in number. Moreover, experiments on the Pima Indian Diabetes (PID) and China Health and Nutrition Survey (CHNS) datasets prove the generalization of the proposed method.

Study on the Effect of Straw Mulching on Farmland Soil Water

“…The main indexes tested in this study mainly include soil water storage, crop water consumption, and the comprehensive water use efficiency of crops [ 11 – 13 ], and the calculation formulas of each index are as follows: Soil water storage is an important index reflecting the water storage capacity of soil, and its calculation formula is …”

“…The main indexes tested in this study mainly include soil water storage, crop water consumption, and the comprehensive water use efficiency of crops [11][12][13], and the calculation formulas of each index are as follows:…”

Chronic Diseases Prediction Using Machine Learning With Data Preprocessing Handling: A Critical Review

“…Some other studies that predict diabetes using fuzzy do not fully use fuzzy but are combined with other machine learning algorithms such as SVM [149], neural network [150], and optimization [56]. Praveen, et al [151], predicted kidney failure by utilizing a Neuro-fuzzy approach, achieving a predictive result with an accuracy of 97%, 94% of precision, 96% of specificity, 94% of recall, and 96% of F1-score.…”

“…The generated predictions are accurate, and their implementation is straightforward XGBoost [121], [156] n_estimators: 100, scale_pos_weight: 1 Having parameters scale_pos_weight can assist in addressing this class imbalance Fuzzy Logic [149], [150] Mamdani Technique Providing flexibility in describing complex relationships among variables SVM [71], [89], [149], [181], [182], [185], [186] kernel: sigmoid Providing a viable solution KNN [71], [167], [168], [182] K: 1 to 200…”