A model for diagnosis of kidney disease using machine learning techniques
Today, the application of artificial intelligence in the field of health systems has been expanded. Machine learning as one of the sub-branches of artificial intelligence has many applications in the field of medical diagnosis. Chronic kidney disease is one of the most common kidney diseases around the world, which facilitation and acceleration in its diagnosis will have a very favorable outcome for its future treatment. The purpose of this study is to provide an intelligent model based on machine learning techniques for diagnosis of kidney diseases.
The data used in this study was extracted from 400 patients and non-patients in India. These data were pre-processed in the Python environment and cleared from noisy and outlying observations. Then support vector machine, multilayer perceptron, and decision tree were used for data classification. Accuracy, Recall and Precision evaluation metrics were calculated for performance evaluation of these classifiers.
For the support vector machine algorithm, the Accuracy, Recall and Precision metrics were calculated to be 0.97, 0.961, and 0.986, respectively. The findings indicated that the support vector machine algorithm performs better in terms of Accuracy. In terms of Recall, the decision tree algorithm with the value of 0.963 had the best performance, and in terms of Precision, multi-layer perceptron algorithm with 0.994 had the best performance in data classification.
The results showed that machine learning techniques could be effective in the diagnosis of kidney disease. The use of these techniques can facilitate and expedite the diagnosis and treatment of these patients and increase the likelihood of recovery. The results also showed that the model presented on the basis of machine learning techniques is more accurate, simpler and less expensive than other techniques.
- حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران میشود.
- پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانههای چاپی و دیجیتال را به کاربر نمیدهد.