Nonalcoholic fatty liver disease (NAFLD), a leading cause of chronic hepatic disease, can progress to liver fibrosis, cirrhosis, and hepatocellular carcinoma. Therefore, it is extremely important to explore early diagnosis and screening methods. In this study, we developed models based on computer tongue image analysis technology to observe the tongue characteristics of 1778 participants (831 cases of NAFLD and 947 cases of non-NAFLD). Combining quantitative tongue image features, basic information, and serological indexes, including the hepatic steatosis index (HSI) and fatty liver index (FLI), we utilized machine learning methods, including Logistic Regression, Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Adaptive Boosting Algorithm (AdaBoost), Naïve Bayes, and Neural Network for NAFLD diagnosis. The best fusion model for diagnosing NAFLD by Logistic Regression, which contained the tongue image parameters, waist circumference, BMI, GGT, TG, and ALT/AST, achieved an AUC of 0.897 (95% CI, 0.882-0.911), an accuracy of 81.70% with a sensitivity of 77.62% and a specificity of 85.22%; in addition, the positive likelihood ratio and negative likelihood ratio were 5.25 and 0.26, respectively. The application of computer intelligent tongue diagnosis technology can improve the accuracy of NAFLD diagnosis and may provide a convenient technical reference for the establishment of early screening methods for NAFLD, which is worth further research and verification.

Background. Research on intelligent tongue diagnosis is a main direction in the modernization of tongue diagnosis technology. Identification of tongue shape and texture features is a difficult task for tongue diagnosis in traditional Chinese medicine (TCM). This study aimed to explore the application of deep learning techniques in tongue image analyses. Methods. A total of 8676 tongue images were annotated by clinical experts, into seven categories, including the fissured tongue, tooth-marked tongue, stasis tongue, spotted tongue, greasy coating, peeled coating, and rotten coating. Based on the labeled tongue images, the deep learning model faster region-based convolutional neural networks (Faster R-CNN) was utilized to classify tongue images. Four performance indices, i.e., accuracy, recall, precision, and F1-score, were selected to evaluate the model. Also, we applied it to analyze tongue image features of 3601 medical checkup participants in order to explore gender and age factors and the correlations among tongue features in diseases through complex networks. Results. The average accuracy, recall, precision, and F1-score of our model achieved 90.67, 91.25, 99.28, and 95.00, respectively. Over the tongue images from the medical checkup population, the model Faster R-CNN detected 41.49 fissured tongue images, 37.16 tooth-marked tongue images, 29.66 greasy coating images, 18.66 spotted tongue images, 9.97 stasis tongue images, 3.97 peeled coating images, and 1.22 rotten coating images. There were significant differences in the incidence of the fissured tongue, tooth-marked tongue, spotted tongue, and greasy coating among age and gender. Complex networks revealed that fissured tongue and tooth-marked were closely related to hypertension, dyslipidemia, overweight and nonalcoholic fatty liver disease (NAFLD), and a greasy coating tongue was associated with hypertension and overweight. Conclusion. The model Faster R-CNN shows good performance in the tongue image classification. And we have preliminarily revealed the relationship between tongue features and gender, age, and metabolic diseases in a medical checkup population.

Background and objective: To establish a nomogram prediction model for patients with chronic obstructive pulmonary disease (COPD) based on Lasso feature screening using acoustic features and general clinical data, as well as a risk warning model for patients with acute exacerbation of COPD (AECOPD), and to investigate the performance and value of these two models. Methods: A total of 240 male COPD patients, including 41 patients with acute exacerbation, and 82 healthy control male volunteers were enrolled as subjects from October 2022 to January 2024. Acoustic features and general clinical data were collected. Lasso regression was used to screen variables related to COPD and AECOPD diagnosis, and nomogram models were separately established and verified by the receiver operating characteristic (ROC) curve, calibration curve, and decision curve. Results: Variables related to COPD diagnosis screened by Lasso regression included age, smoking history, a_Jitter, e_MFCC1, e_F2 frequency, i_H1-A3, i_F1 amplitude, o_F1 amplitude, and u_MFCC4， and the variables related to AECOPD included expectoration, mMRC grade, i_Jitter, i_F2 frequency, i_Alpha Ratio, and u_H1-H2. The ROC Curve showed that the Area Under the Curve (AUC) of the COPD nomogram model was 0.95, and the AUC of the AECOPD risk warning model was 0.83. The calibration curve indicated that nomogram models showed reasonable consistency, and the Mean Absolute Error (MAE) values were 0.026 and 0.028, respectively. The decision curve indicated that nomogram models showed good benefit, and the benefit thresholds were nearly full threshold, and 0.11–81 and 0.88–0.99, respectively. Conclusion: The nomogram models for COPD prediction and risk warning of AECOPD can be used as a clinical auxiliary diagnostic and early screening method, providing new insights into the intelligent auscultation of COPD.