Artificial Intelligence-Based Diagnosis of Diabetes Mellitus: Combining Fundus Photography with Traditional Chinese Medicine Diagnostic Methodology

Abstract

In this study, we propose a technique for diagnosing both type 1 and type 2 diabetes in a quick, noninvasive way by using equipment that is easy to transport. Diabetes mellitus is a chronic disease that affects public health globally. Although diabetes mellitus can be accurately diagnosed using conventional methods, these methods require the collection of data in a clinical setting and are unlikely to be feasible in areas with few medical resources. This technique combines an analysis of fundus photography of the physical and physiological features of the patient, namely, the tongue and the pulse, which are used in Traditional Chinese Medicine. A random forest algorithm was used to analyze the data, and the accuracy, precision, recall, and F1 scores for the correct classification of diabetes were 0.85, 0.89, 0.67, and 0.76, respectively. The proposed technique for diabetes diagnosis offers a new approach to the diagnosis of diabetes, in that it may be convenient in regions that lack medical resources, where the early detection of diabetes is difficult to achieve.

Effect Western Medicines Combined With Nao-Xue-Shu in Patients With Hypertensive Intracerebral Hemorrhage: A Network Meta-Analysis

“…Traditional medicine, especially Chinese medicine, is a complete medical system with thousands of years of application history, and its clinical practice mainly focuses on diagnosis and treatment. Chinese medicine has been shown to play a vital role in treating diseases such as diabetes, cancer, and rheumatoid arthritis ( Wang S et al, 2021 ; Wang Y et al, 2021 ; Li et al, 2021 ; Xiang et al, 2021 ). Therefore, an increasing number of Chinese scholars began to explore the efficacy and safety of Chinese medicine therapy in patients with HICH.…”

Extraction of human understandable insight from machine learning model for diabetes prediction

“…Machine learning and artificial intelligent model have become indispensable tool for tasks such as disease prediction. Today's machine learning models are achieving excellent performance even exceeding the human intelligence [4]. However, complex machine learning models are not providing an information about how the model has arrived at particular prediction outcome.…”

Current status and trends of artificial intelligence research on the four traditional Chinese medicine diagnostic methods: a scientometric study

“…Many meaningful tongue and pulse features for the diagnosis of various diseases have been discovered using large amounts of complicated clinical data via AI-based data mining methods. For instance, the multistep approach (4), Genetic Algorithm_Extreme Gradient Boosting (GA_XGBT) model (5), random forest (6), and convolutional neural network (MIMT-CNN) (7) have been widely applied in diabetic tongue research, while AdaBoost (8), Support Vector Machine (SVM) (9), and logistic regression (10) have been applied in pulse research. The use of AI to understand the clinical data of diseases can help to objectively and efficiently improve the accuracy and precision of diagnosis (2).…”