Neurodegenerative diseases (NDs) are a type of chronic and complex diseases that seriously affect the quality of human life. Their pathogenesis involves aspects such as genetics, environment, and metabolism. In recent years, the close relationship between gut microbiota and host health has gradually attracted attention, especially with the promotion of the concept of “gut-brain axis,” and the role of gut microbiota in nervous system diseases has become a research focus. At the same time, the rapid development of AI technology has provided powerful tools for modeling and data analysis of complex biological systems. This paper reviews the molecular mechanism and therapeutic approaches of gut microbiota in NDs and discusses the application potential of AI in this field, aiming to provide new ideas for the molecular mechanism research and precise treatment of NDs.

Isoprene is a typical physiological marker that can be used to screen for chronic liver disease. This work developed a portable micro-integrated chromatography analysis system based on micro-electromechanical system technology, nanomaterials technology and embedded microcontroller technology. The system integrated components such as graphene oxide quantum dots modified semi-packed microcolumn, In₂O₃ nanoflower (NF) gas-sensitive detector and 3D printed miniature solenoid valve group. The effectiveness of the separation effect of the micro-integrated system was verified by gas mixture test; the laws of the influence of carrier gas pressure and column temperature on the chromatographic separation performance, respectively, were investigated, and the working conditions (column temperature 90 °C and carrier gas pressure 7.5 kPa) for system testing were determined. The percentages of relative standard deviation of the peak areas and retention times obtained for the separated gases were in the range of 0.95%–6.06%, indicating the good reproducibility of the system. Meanwhile, the microintegrated system could detect isoprene down to 50 ppb at small injection volume (1 ml). The system response increased with increasing isoprene concentration and was linearly correlated with isoprene concentration (R ² = 0.986), indicating that the system was expected to be used for trace detection of isoprene, a marker gas for liver disease, in the future.

Cerebral small vessel disease (CSVD) poses major public health challenges, yet current MRI based diagnosis detects only established damage, and existing auxiliary methods, mostly based on conventional statistics, lack sufficient feature extraction capability and generalizability, thereby limiting early warning and precision management. Accordingly, we developed an intelligent auxiliary diagnostic system grounded in an interpretable ensemble learning framework, aiming to enable early detection and warning of CSVD. To support this development, a total of 597 sets of electronic medical record data from Quzhou Affiliated Hospital of Wenzhou Medical University were used as the study cohort. Firstly, a multidimensional feature evaluation and selection method was proposed, identifying 12 key predictive factors out of 23 relevant variables. Subsequently, the optimal algorithm was selected from Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, Gradient Boosting Machine, XGBoost, and Multilayer Perceptron Classifier, based on Area Under the Curve (AUC) and Accuracy metrics, and a stacking ensemble learning strategy was then employed for model construction. The developed model demonstrated excellent discriminative performance, achieving an AUC of 0.881 while maintaining a low Brier score of 0.1271. By integrating the SHAP interpretability algorithm, the model provided intuitive visualizations of feature importance, thereby enhancing transparency and facilitating clinical adoption. Ultimately, this study achieved effective integration of early warning and auxiliary diagnostic functions for CSVD. These results indicate that the proposed system possesses high accuracy, interpretability, and deployability, underscoring its broad potential for early warning and personalized management of CSVD.

Cerebral small vessel disease (CSVD) poses major public health challenges, yet current MRI based diagnosis detects only established damage, and existing auxiliary methods, mostly based on conventional statistics, lack sufficient feature extraction capability and generalizability, thereby limiting early warning and precision management. Accordingly, we developed an intelligent auxiliary diagnostic system grounded in an interpretable ensemble learning framework, aiming to enable early detection and warning of CSVD. To support this development, a total of 597 sets of electronic medical record data from Quzhou Affiliated Hospital of Wenzhou Medical University were used as the study cohort. Firstly, a multidimensional feature evaluation and selection method was proposed, identifying 12 key predictive factors out of 23 relevant variables. Subsequently, the optimal algorithm was selected from Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, Gradient Boosting Machine, XGBoost, and Multilayer Perceptron Classifier, based on Area Under the Curve (AUC) and Accuracy metrics, and a stacking ensemble learning strategy was then employed for model construction. The developed model demonstrated excellent discriminative performance, achieving an AUC of 0.924 while maintaining a low Brier score of 0.1065. By integrating the SHAP interpretability algorithm, the model provided intuitive visualizations of feature importance, thereby enhancing transparency and facilitating clinical adoption. Ultimately, this study achieved effective integration of early warning and auxiliary diagnostic functions for CSVD. These results indicate that the proposed system possesses high accuracy, interpretability, and deployability, underscoring its broad potential for early warning and personalized management of CSVD.