BACKGROUND: Epidermal growth factor receptor (EGFR) sensitive mutation is one of the effective targets of targeted therapy for non-small cell lung cancer (NSCLC). However, due to the difficulty of obtaining some primary tissues and the economic factors in some underdeveloped areas, some patients cannot undergo traditional genetic testing. The aim of this study is to establish a machine learning (ML) model using non-invasive peripheral blood markers to explore the biomarkers closely related to EGFR mutation status in NSCLC and evaluate their potential prognostic value. METHODS: 2642 lung cancer patients who visited Jiangsu Cancer Hospital from November 2016 to May 2023 were retrospectively enrolled and finally 175 NSCLC patients with complete follow-up data were included in the study. The ML model was constructed based on peripheral blood indicators and divided into training set and test set according to the ratio of 8:2. Unsupervised learning algorithms were used for clustering blood features and mutual information method for feature selection, and an ensemble learning algorithm based on Shapley value was designed to calculate the contribution of each feature to the model prediction result. The receiver operating characteristic (ROC) curve was used to evaluate the predictive ability of the model. RESULTS: Through the feature extraction and contribution analysis of the predictive results of the interpretable ML model based on the Shapley value, the top ten indicators with the highest contribution were: pathological type, phosphorus, eosinophils, monocyte count, activated partial thromboplastin time, potassium, total bilirubin, sodium, eosinophil percentage, and total cholesterol. The area under the curve (AUC) of the model was 0.80. In addition, patients with hyponatremia and squamous cell carcinoma group had a poor prognosis (P<0.05). CONCLUSIONS The interpretable model constructed in this study provides a new approach for the prediction of EGFR mutation status in NSCLC patients, which provides a scientific basis for the diagnosis and treatment of patients who cannot undergo genetic testing.
Humans ; Carcinoma, Non-Small-Cell Lung/diagnosis* ; Machine Learning ; Lung Neoplasms/diagnosis* ; Male ; Female ; Mutation ; Middle Aged ; ErbB Receptors/genetics* ; Prognosis ; Aged ; Retrospective Studies ; Adult ; Biomarkers, Tumor/genetics*

BACKGROUND: Hypertension is a serious chronic disease that can significantly lead to various cardiovascular diseases, affecting vital organs such as the heart, brain, and kidneys. Our goal is to predict the risk of new onset hypertension using machine learning algorithms and identify the characteristics of patients with new onset hypertension. METHODS: We analyzed data from the 2011 China Health and Nutrition Survey cohort of individuals who were not hypertensive at baseline and had follow-up results available for prediction by 2015. We tested and evaluated the performance of four traditional machine learning algorithms commonly used in epidemiological studies: Logistic Regression, Support Vector Machine, XGBoost, LightGBM, and two deep learning algorithms: TabNet and AMFormer model. We modeled using 16 and 29 features, respectively. SHAP values were applied to select key features associated with new onset hypertension. RESULTS: A total of 4,982 participants were included in the analysis, of whom 1,017 developed hypertension during the 4-year follow-up. Among the 16-feature models, Logistic Regression had the highest AUC of 0.784(0.775∼0.806). In the 29-feature prediction models, AMFormer performed the best with an AUC of 0.802(0.795∼0.820), and also scored the highest in MCC (0.417, 95%CI: 0.400∼0.434) and F1 (0.503, 95%CI: 0.484∼0.505) metrics, demonstrating superior overall performance compared to the other models. Additionally, key features selected based on the AMFormer, such as age, province, waist circumference, urban or rural location, education level, employment status, weight, WHR, and BMI, played significant roles. CONCLUSION We used the AMFormer model for the first time in predicting new onset hypertension and achieved the best results among the six algorithms tested. Key features associated with new onset hypertension can be determined through this algorithm. The practice of machine learning algorithms can further enhance the predictive efficacy of diseases and identify risk factors for diseases.
Humans ; China/epidemiology* ; Hypertension/diagnosis* ; Machine Learning ; Male ; Female ; Middle Aged ; Adult ; Nutrition Surveys ; Algorithms ; Aged ; Risk Factors

In recent years, China has continued to face a high prevalence of oral diseases, along with uneven access to high-quality dental care. Against this backdrop, artificial intelligence (AI), as a data-driven, algorithm-supported, and model-centered technology system, has rapidly expanded its role in transforming the landscape of stomatology. This review summarizes recent advances in the application of AI in stomatology across clinical care, biomedical and materials research, education, and hospital management. In clinical settings, AI has improved diagnostic accuracy, streamlined treatment planning, and enhanced surgical precision and efficiency. In research, machine learning has accelerated the identification of disease biomarkers, deepened insights into the oral microbiome, and supported the development of novel biomaterials. In education, AI has enabled the construction of knowledge graphs, facilitated personalized learning, and powered simulation-based training, driving innovation in teaching methodologies. Meanwhile, in hospital operations, intelligent agents based on large language models (LLMs) have been widely deployed for intelligent triage, structured pre-consultations, automated clinical documentation, and quality control, contributing to more standardized and efficient healthcare delivery. Building on these foundations, a multi-agent collaborative framework centered around an AI assistant for stomatology is gradually emerging, integrating task-specific agents for imaging, treatment planning, surgical navigation, follow-up prediction, patient communication, and administrative coordination. Through shared interfaces and unified knowledge systems, these agents support seamless human-AI collaboration across the full continuum of care. Despite these achievements, the broader deployment of AI still faces challenges including data privacy, model robustness, cross-institution generalization, and interpretability. Addressing these issues will require the development of federated learning frameworks, multi-center validation, causal reasoning approaches, and strong ethical governance. With these foundations in place, AI is poised to move from a supportive tool to a trusted partner in advancing accessible, efficient, and high-quality stomatology services in China.
Artificial Intelligence ; Humans ; Oral Medicine/trends* ; China ; Delivery of Health Care ; Machine Learning

In recent years, cardiovascular disease has become a common disease. With the development of machine learning and big data technologies, the processing ability of electrocardiogram (ECG) signals has been greatly enhanced through new computer technologies, enabling the auxiliary diagnosis technology for cardiovascular disease (CVD) to achieve new improvements. This article discusses the application of machine learning in ECG processing, especially in the auxiliary diagnosis of diseases. Firstly, the conventional signal preprocessing methods are introduced, and then the EEG signal processing methods based on feature extraction and fuzzy classification are explored. Secondly, the application of auxiliary diagnosis in CVD is further summarized. Finally, the advantages and disadvantages of the two methods are analyzed, and based on this, a design of an auxiliary diagnostic system compatible with the two methods is proposed, providing a new perspective for similar applied researches in the future.
Machine Learning ; Cardiovascular Diseases/diagnosis* ; Humans ; Electrocardiography ; Signal Processing, Computer-Assisted ; Diagnosis, Computer-Assisted ; Fuzzy Logic ; Electroencephalography

INTRODUCTION: Obstructive sleep apnoea (OSA) is a serious but underdiagnosed condition. Demand for the gold standard diagnostic polysomnogram (PSG) far exceeds its availability. More efficient diagnostic methods are needed, even in tertiary settings. Machine learning (ML) models have strengths in disease prediction and early diagnosis. We explored the use of ML with oximetry, demographic and anthropometric data to diagnose OSA. METHODS: A total of 2,996 patients were included for modelling and divided into test and training sets. Seven commonly used supervised learning algorithms were trained with the data. Sensitivity (recall), specificity, positive predictive value (PPV) (precision), negative predictive value, area under the receiver operating characteristic curve (AUC) and F1 measure were reported for each model. RESULTS: In the best performing four-class model (neural network model predicting no, mild, moderate or severe OSA), a prediction of moderate and/or severe disease had a combined PPV of 94%; one out of 335 patients had no OSA and 19 had mild OSA. In the best performing two-class model (logistic regression model predicting no-mild vs. moderate-severe OSA), the PPV for moderate-severe OSA was 92%; two out of 350 patients had no OSA and 26 had mild OSA. CONCLUSION Our study showed that the prediction of moderate-severe OSA in a tertiary setting with an ML approach is a viable option to facilitate early identification of OSA. Prospective studies with home-based oximeters and analysis of other oximetry variables are the next steps towards formal implementation.
Humans ; Oximetry/methods* ; Sleep Apnea, Obstructive/diagnosis* ; Male ; Female ; Middle Aged ; Machine Learning ; Polysomnography ; Adult ; Anthropometry ; ROC Curve ; Aged ; Algorithms ; Predictive Value of Tests ; Sensitivity and Specificity ; Neural Networks, Computer ; Demography

OBJECTIVE: To screen the population for acupuncture treatment of neck pain, using functional magnetic resonance imaging (fMRI) technology and based on machine learning algorithms. METHODS: Eighty patients with neck pain were recruited. Using FPX25 handheld pressure algometer, the tender points were detected in the areas with high-frequent onset of neck pain and high degree of acupoint sensitization. Acupuncture was delivered at 4 tender points with the lowest pain threshold, once every two days; and the treatment was given 3 times a week and for 2 consecutive weeks. The amplitude of low-frequency fluctuation (ALFF) of the brain before treatment was taken as a predictive feature to construct support vector machine (SVM), logistic regression (LR), and K-nearest neighbors (KNN) models to predict the responses of neck pain patients to acupuncture treatment. A longitudinal analysis of the ALFF features was performed before and after treatment to reveal the potential biological markers of the reactivity to the acupuncture therapy. RESULTS: The SVM model could successfully distinguish high responders (48 cases) and low responders (32 cases) to acupuncture treatment, and its accuracy rate reached 82.5%. Based on the SVM model, the ALFF values of 4 brain regions were identified as the consistent predictive features, including the right middle temporal gyrus, the right superior occipital gyrus, and the bilateral posterior cingulate gyrus. In the patients with high acupuncture response, the ALFF value in the left posterior cingulate gyrus decreased after treatment (P<0.05), whereas in the patients with low acupuncture response, the ALFF value in the right superior occipital gyrus increased after treatment (P<0.01). The longitudinal functional connectivity (FC) analysis found that compared with those before treatment, the high responders showed the enhanced FC after treatment between the left posterior cingulate gyrus and various regions, including the bilateral Crus1 of the cerebellum, the right insula, the bilateral angular gyrus, the left medial superior frontal gyrus, and the left middle cingulate gyrus (GRF: corrected, voxel level: P<0.05, mass level: P<0.05). In contrast, the low responders exhibited the enhanced FC between the left posterior cingulate gyrus and the left Crus2 of the cerebellum, the left middle temporal gyrus, the right posterior cingulate gyrus, and the left angular gyrus; besides, FC was reduced in low responders between the left posterior cingulate gyrus and the right supramarginal gyrus (GRF: corrected, voxel level: P<0.05, mass level: P<0.05). CONCLUSION This study validates the practicality of pre-treatment ALFF feature prediction for acupuncture efficacy on neck pain. The therapeutic effect of acupuncture on neck pain is potentially associated with its impact on the default mode network, and then, alter the pain perception and emotional regulation.
Humans ; Neck Pain/physiopathology* ; Acupuncture Therapy ; Female ; Male ; Adult ; Middle Aged ; Machine Learning ; Magnetic Resonance Imaging ; Young Adult ; Brain/physiopathology* ; Acupuncture Points ; Aged

The machine learning is used increasingly and widely in acupuncture prescription optimization, intelligent treatment and precision medicine, and has obtained a certain achievement. But, there are still some problems remained to be solved such as the poor interpretability of the model, the inconsistency of data quality of acupuncture research, and the clinical application of constructed models. Researches in future should focus on the acquisition of high-quality clinical and experimental data sets, take various machine learning algorithms as the basis, and construct professional models to solve various problems, so as to drive the high-quality development of acupuncture research.
Acupuncture Therapy/trends* ; Machine Learning ; Humans ; Algorithms

OBJECTIVE: To construct a prediction model for the clinical effect of eye acupuncture combined with rehabilitation therapy on ischemic stroke based on interpretable machine learning. METHODS: From January 1st, 2020 to October 1st, 2024, the clinical data of 470 patients with ischemic stroke were collected in the the Second Department of Encephalopathy Rehabilitation of the Affiliated Hospital of Liaoning University of TCM. The modified Barthel index (MBI) score before and after treatment was used to divide the patients into an effect group (291 cases) and a non-effect group (179 cases). Random forest and recursive feature elimination with cross-validation were combined to screen the predictors of the therapeutic effect of patients. Seven representative machine learning models with different principles were established according to the screening results. The predictive effect of the best model was evaluated by receiver operating characteristics (ROC), calibration, and clinical decision-making (DCA) curves. Finally, the Shapley additive explanation (SHAP) framework was used to interpret the prediction results of the best model. RESULT: ①All the machine learning models presented the area under curve (AUC) to be above 85%. Of these models, the random forest model showed the best prediction ability, with AUC of 0.96 and the precision of 0.87. ②The prediction probability of calibration curve and the actual probability showed a good prediction consistency. ③The net benefit rate of DCA curve in the range of 0.1 to 1.0 was higher than the risk threshold, indicating a good effect of model. ④SHAP explained the characteristic values of variables that affected the prediction effect of the model, meaning, more days of treatment, lower MBI score before treatment, lower level of fibrinogen, shorter days of onset and younger age. These values demonstrated the better effect of eye acupuncture rehabilitation therapy. CONCLUSION The rehabilitation effect prediction model constructed in this study presents a good performance, which is conductive to assisting doctors in formulating targeted personalized rehabilitation programs, and identifying the benefit groups of eye acupuncture combined with rehabilitation therapy and finding the advantageous groups with clinical effect. It provides more ideas for the treatment of ischemic stroke with eye acupuncture combined with rehabilitation therapy.
Humans ; Acupuncture Therapy ; Machine Learning ; Male ; Female ; Middle Aged ; Ischemic Stroke/rehabilitation* ; Aged ; Stroke Rehabilitation ; Adult ; Eye

OBJECTIVE: To develop an objective quantitative evaluative model of manual acupuncture manipulation (MAM) using three-dimensional motion tracking technology and machine learning, so as to provide a new approach to the study on acupuncture and moxibustion education and manipulation standardization. METHODS: A total of 120 undergraduate students in the major of acupuncture-moxibustion and tuina were recruited. The Simi Motion Ver.8.5 motion tracking system was used to collect the data of three types of MAM, balanced reinforcing and reducing by twisting, reinforcing technique by twisting and reducing technique by twisting. Eight quantitative parameters covering movement performance and stability were established. With 5 types of machine learning algorithms (logistic regression, random forest, support vector machine, K-nearest neighbor, and decision tree) adopted, the evaluative model was constructed, and the feature importance analyzed. RESULTS: In the evaluation of different types of MAM, the support vector machine presented the best for the effects of the balanced reinforcing and reducing by twisting, and the reducing by twisting (accuracy rates were both 0.88); and the logistic regression algorithm showed the optimal performance in evaluating the reinforcing by twisting (1.00 of accuracy rate). Feature importance analysis revealed that twisting velocity was the dominant parameter for evaluating the balanced reinforcing-reducing manipulation. The reinforcing and reducing of acupuncture techniques were more dependent on the left-hand twisting parameters and comprehensive performances, respectively. CONCLUSION The objective evaluative model of MAM based on three-dimensional motion tracking technology and machine learning demonstrates a reliable evaluative performance, providing a new technical approach to standardized assessment in acupuncture and moxibustion education.
Humans ; Male ; Acupuncture Therapy/instrumentation* ; Machine Learning ; Female ; Young Adult ; Adult ; Motion

OBJECTIVE: To propose a machine learning-based method for predicting the trajectories during manual acupuncture manipulation (MAM), aiming to improve the precision and consistency of acupuncture practitioner' operation and provide the real-time suggestions on MAM error correction. METHODS: Computer vision technology was used to analyze the hand micromotion when holding needle during acupuncture, and provide a three-dimensional coordinate description method of the index finger joints of the holding hand. Focusing on the 4 typical motions of MAM, a machine learning-based MAM trajectory predictive model was designed. By integrating the changes of phalangeal joint angle and hand skeletal information of acupuncture practitioner, the motion trajectory of the index finger joint was predicted accurately. Besides, the roles of machine learning-based MAM trajectory predictive model in the skill transmission of acupuncture manipulation were verified by stratified randomized controlled trial. RESULTS: The performance of MAM trajectory predictive model, based on the long short-term memory network (LSTM), obtained the highest stability and precision, up to 98%. The learning effect was improved when the model applied to the skill transmission of acupuncture manipulation. CONCLUSION The machine learning-based MAM predictive model provides acupuncture practitioner with precise action prediction and feedback. It is valuable and significant for the inheritance and error correction of manual operation of acupuncture.
Humans ; Acupuncture Therapy/instrumentation* ; Machine Learning ; Adult ; Male ; Female