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

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: An intelligent moxibustion instrument based on electromyography was designed to evaluate the real-time therapeutic effect of moxibustion. METHODS: Taking Shenshu (BL23) as the subject, surface electromyography (sEMG) at the center and equidistant points of Shenshu (BL23) were collected. The characteristic parameters, integrated electromyography (iEMG) and root mean square (RMS) were calculated before and after moxibustion. After analyzing the effect of moxibustion, a function algorithm for the end-of-moxibustion was obtained. Using this algorithm and combined with STM32 technology, the control system of moxibustion instrument and the upper computer software were designed to achieve the precise control during moxibustion delivery. Finally, the function, stability and safety of the moxibustion instrument were verified through clinical trials to ensure its effectiveness in practical application. RESULTS: During one cycle of moxibustion at the center of Shenshu (BL23), the iEMG of sEMG decreased over time, meaning the decrease in muscle fatigue degree, and after one cycle of moxibustion, it elevated over time, showing the increase in muscle fatigue degree. RMS increased by 1.90% before and after moxibustion at the equidistant points of Shenshu (BL23), and the system indicated the end of moxibustion when RMS increased by 0.15%, and decreased by 0.13% at the center of Shenshu (BL23). The intelligent moxibustion instrument designed based on this algorithm can realize the function of mild moxibustion, and the effect of moxibustion can be evaluated by the real-time monitoring of RMS changes through the upper computer. During the operation of moxibustion instrument, moxa stick was fixed stably, remained a safe distance of 3 cm to 4 cm away from the skin surface. When the length of moxa stick was less than 5 cm left after ignited and the skin temperature exceeded the preset safety threshold of 48 ℃, the system was alarmed automatically. CONCLUSION The intelligent moxibustion instrument designed in the research can effectively evaluate the effect of moxibustion, and ensure the safety and stability during moxibustion delivery.
Humans ; Moxibustion/methods* ; Electromyography/instrumentation* ; Adult ; Male ; Female ; Young Adult ; Acupuncture Points ; Algorithms ; Middle Aged

INTRODUCTION: Elevated troponin, while essential for diagnosing myocardial infarction, can also be present in non-myocardial infarction conditions. The myocardial-ischaemic-injury-index (MI3) algorithm is a machine learning algorithm that considers age, sex and cardiac troponin I (TnI) results to risk-stratify patients for type 1 myocardial infarction. METHOD: Patients aged ≥25 years who presented to the emergency department (ED) of Singapore General Hospital with symptoms suggestive of acute coronary syndrome with no diagnostic 12-lead electrocardiogram (ECG) changes were included. Participants had serial ECGs and high-sensitivity troponin assays performed at 0, 2 and 7 hours. The primary outcome was the adjudicated diagnosis of type 1 myocardial infarction at 30 days. We compared the performance of MI3 in predicting the primary outcome with the European Society of Cardiology (ESC) 0/2-hour algorithm as well as the 99th percentile upper reference limit (URL) for TnI. RESULTS: There were 1351 patients included (66.7% male, mean age 56 years), 902 (66.8%) of whom had only 0-hour troponin results and 449 (33.2%) with serial (both 0 and 2-hour) troponin results available. MI3 ruled out type 1 myocardial infarction with a higher sensitivity (98.9, 95% confidence interval [CI] 93.4-99.9%) and similar negative predictive value (NPV) 99.8% (95% CI 98.6-100%) as compared to the ESC strategy. The 99th percentile cut-off strategy had the lowest sensitivity, specificity, positive predictive value and NPV. CONCLUSION The MI3 algorithm was accurate in risk stratifying ED patients for myocardial infarction. The 99th percentile URL cut-off was the least accurate in ruling in and out myocardial infarction compared to the other strategies.
Humans ; Male ; Female ; Emergency Service, Hospital ; Middle Aged ; Electrocardiography ; Machine Learning ; Singapore ; Chest Pain/blood* ; Troponin I/blood* ; Myocardial Infarction/blood* ; Risk Assessment/methods* ; Aged ; Algorithms ; Acute Coronary Syndrome/blood* ; Adult ; Sensitivity and Specificity

BACKGROUND: Postoperative pulmonary complications (PPCs) are major adverse events in neurosurgical patients. This study aimed to develop and validate machine learning models predicting PPCs after neurosurgery. METHODS: PPCs were defined according to the European Perioperative Clinical Outcome standards as occurring within 7 postoperative days. Data of cases meeting inclusion/exclusion criteria were extracted from the anesthesia information management system to create three datasets: The development (data of Huashan Hospital, Fudan University from 2018 to 2020), temporal validation (data of Huashan Hospital, Fudan University in 2021) and external validation (data of other three hospitals in 2023) datasets. Machine learning models of six algorithms were trained using either 35 retrievable and plausible features or the 11 features selected by Lasso regression. Temporal validation was conducted for all models and the 11-feature models were also externally validated. Independent risk factors were identified and feature importance in top models was analyzed. RESULTS: PPCs occurred in 712 of 7533 (9.5%), 258 of 2824 (9.1%), and 207 of 2300 (9.0%) patients in the development, temporal validation and external validation datasets, respectively. During cross-validation training, all models except Bayes demonstrated good discrimination with an area under the receiver operating characteristic curve (AUC) of 0.840. In temporal validation of full-feature models, deep neural network (DNN) performed the best with an AUC of 0.835 (95% confidence interval [CI]: 0.805-0.858) and a Brier score of 0.069, followed by Logistic regression (LR), random forest and XGBoost. The 11-feature models performed comparable to full-feature models with very close but statistically significantly lower AUCs, with the top models of DNN and LR in temporal and external validations. An 11-feature nomogram was drawn based on the LR algorithm and it outperformed the minimally modified Assess respiratory RIsk in Surgical patients in CATalonia (ARISCAT) and Laparoscopic Surgery Video Educational Guidelines (LAS VEGAS) scores with a higher AUC (LR: 0.824, ARISCAT: 0.672, LAS: 0.663). Independent risk factors based on multivariate LR mostly overlapped with Lasso-selected features, but lacked consistency with the important features using the Shapley additive explanation (SHAP) method of the LR model. CONCLUSIONS: The developed models, especially the DNN model and the nomogram, had good discrimination and calibration, and could be used for predicting PPCs in neurosurgical patients. The establishment of machine learning models and the ascertainment of risk factors might assist clinical decision support for improving surgical outcomes. TRIAL REGISTRATION ChiCTR 2100047474; https://www.chictr.org.cn/showproj.html?proj=128279 .
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Algorithms ; Lung Diseases/etiology* ; Machine Learning ; Neurosurgical Procedures/adverse effects* ; Postoperative Complications/diagnosis* ; Risk Factors ; ROC Curve

Microsatellite instability (MSI) serves as a molecular marker for DNA mismatch repair deficiency (dMMR), present in approximately 15% of colorectal cancer patients. The MSI status provides predictive information guiding treatment decisions; for instance, patients with microsatellite instability-high colorectal cancer demonstrate better responses to immune checkpoint inhibitor therapy. Currently, MSI testing requires methods such as immunohistochemistry or next-generation sequencing. Although multiple clinical guidelines recommend routine MSI testing, its widespread adoption within China remains limited due to various constraints. Deep learning algorithms offer a novel AI-driven pattern recognition classification strategy, presenting a feasible approach to overcome limitations in MSI testing and enhance immunotherapy efficacy evaluation. Consequently, the Colorectal Surgery Group of the Surgery Branch of the Chinese Medical Association, in collaboration with Beihang University and drawing on current research utilizing artificial intelligence systems to assess colorectal cancer immunotherapy efficacy, has formulated the "Expert consensus on clinical application of immunotherapy intelligent prediction for colorectal cancer based on artificial intelligence platform（2025 version）". This consensus aims to facilitate the prediction of MSI status and other relevant indicators in colorectal cancer patients, while also supporting clinical decision-making regarding the selection and application of immunotherapy regimens.
Humans ; Colorectal Neoplasms/immunology* ; Artificial Intelligence ; Immunotherapy ; Microsatellite Instability ; Consensus ; Deep Learning ; Algorithms

In this paper, near-infrared spectroscopy(NIRS) was employed to analyze 129 batches of commercial products of Reduning Injection. The batch reporting rate was estimated according to the report of Reduning Injection in the direct adverse drug reaction(ADR) reporting system of the drug marketing authorization holder of the Center for Drug Reevaluation of the National Medical Products Administration(National Center for ADR Monitoring) from August 2021 to August 2022. According to the batch reporting rate, the samples of Reduning Injection were classified into those with potential risks and those being safe. No processing, random oversampling(ROS), random undersampling(RUS), and synthetic minority over-sampling technique(SMOTE) were then employed to balance the unbalanced data. After the samples were classified according to appropriate sampling methods, competitive adaptive reweighted sampling(CARS), successive projections algorithm(SPA), uninformative variables elimination(UVE), and genetic algorithm(GA) were respectively adopted to screen the features of spectral data. Then, support vector machine(SVM), logistic regression(LR), k-nearest neighbors(KNN), naive bayes(NB), random forest(RF), and artificial neural network(ANN) were adopted to establish the risk prediction models. The effects of the four feature extraction methods on the accuracy of the models were compared. The optimal method was selected, and bayesian optimization was performned to optimize the model parameters to improve the accuracy and robustness of model prediction. To explore the correlations between potential risks of clinical use and quality test data, TreeNet was employed to identify potential quality parameters affecting the clinical safety of Reduning Injection. The results showed that the models established with the SVM, LR, KNN, NB, RF, and ANN algorithms had the F1 scores of 0.85, 0.85, 0.86, 0.80, 0.88, and 0.85 and the accuracy of 88%, 88%, 88%, 85%, 91%, and 88%, respectively, and the prediction time was less than 5 s. The results indicated that the established models were accurate and efficient. Therefore, near infrared spectroscopy combined with machine learning algorithms can quickly predict the potential risks of clinical use of Reduning Injection in batches. Three key quality parameters that may affect clinical safety were identified by TreeNet, which provided a scientific basis for improving the safety standards of Reduning Injection.
Spectroscopy, Near-Infrared/methods* ; Drugs, Chinese Herbal/administration & dosage* ; Machine Learning ; Algorithms ; Humans ; Quality Control

Cervi Cornu Pantotrichum is a precious animal-derived Chinese medicinal material, while there are often adulterants derived from animals not specified in the Chinese Pharmacopeia in the market, which disturbs the safety of medication. This study was conducted with the aim of strengthening the quality control of Cervi Cornu Pantotrichum and standardizing the medication. To achieve digital identification of Cervi Cornu Pantotrichum from different sources, a digital identification model was constructed based on ultra-high performance liquid chromatography tandem quadrupole time-of-flight mass spectrometry(UHPLC-QTOF-MS~E) combined with an adaptive boosting algorithm(Adaboost). The young furred antlers of sika deer, red deer, elk, and reindeer were processed and then subjected to polypeptide analysis by UHPLC-QTOF-MS~E. Then, the mass spectral data reflecting the polypeptide information were obtained by digital quantification. Next, the key data were obtained by feature screening based on Gini index, and the digital identification model was constructed by Adaboost. The model was evaluated based on the recall rate, F_1 composite score, and accuracy. Finally, the results of identification based on the constructed digital identification model were validated. The results showed that when the Gini index was used to screen the data of top 100 characteristic polypeptides, the digital identification model based on Adaboost had the best performance, with the recall rate, F_1 composite score, and accuracy not less than 0.953. The validation analysis showed that the accuracy of the identification of the 10 batches of samples was as high as 100.0%. Therefore, based on UHPLC-QTOF-MS~E and Adaboost algorithm, the digital identification of Cervi Cornu Pantotrichum can be realized efficiently and accurately, which can provide reference for the quality control and original animal identification of Cervi Cornu Pantotrichum.
Animals ; Algorithms ; Antlers/chemistry* ; Boosting Machine Learning Algorithms ; Chromatography, High Pressure Liquid/methods* ; Deer ; Drugs, Chinese Herbal/chemistry* ; Mass Spectrometry/methods* ; Quality Control ; Reindeer ; Tandem Mass Spectrometry/methods* ; Tissue Extracts/analysis*

Cardiovascular diseases and psychological disorders represent two major threats to human physical and mental health. Research on electrocardiogram (ECG) signals offers valuable opportunities to address these issues. However, existing methods are constrained by limitations in understanding ECG features and transferring knowledge across tasks. To address these challenges, this study developed a multi-resolution feature encoding network based on residual networks, which effectively extracted local morphological features and global rhythm features of ECG signals, thereby enhancing feature representation. Furthermore, a model compression-based continual learning method was proposed, enabling the structured transfer of knowledge from simpler tasks to more complex ones, resulting in improved performance in downstream tasks. The multi-resolution learning model demonstrated superior or comparable performance to state-of-the-art algorithms across five datasets, including tasks such as ECG QRS complex detection, arrhythmia classification, and emotion classification. The continual learning method achieved significant improvements over conventional training approaches in cross-domain, cross-task, and incremental data scenarios. These results highlight the potential of the proposed method for effective cross-task knowledge transfer in ECG analysis and offer a new perspective for multi-task learning using ECG signals.
Humans ; Electrocardiography/methods* ; Mental Health ; Algorithms ; Signal Processing, Computer-Assisted ; Machine Learning ; Arrhythmias, Cardiac/diagnosis* ; Cardiovascular Diseases ; Neural Networks, Computer ; Mental Disorders

This paper proposes a motor imagery recognition algorithm based on feature fusion and transfer adaptive boosting (TrAdaboost) to address the issue of low accuracy in motor imagery (MI) recognition across subjects, thereby increasing the reliability of MI-based brain-computer interfaces (BCI) for cross-individual use. Using the autoregressive model, power spectral density and discrete wavelet transform, time-frequency domain features of MI can be obtained, while the filter bank common spatial pattern is used to extract spatial domain features, and multi-scale dispersion entropy is employed to extract nonlinear features. The IV-2a dataset from the 4 ^th International BCI Competition was used for the binary classification task, with the pattern recognition model constructed by combining the improved TrAdaboost integrated learning algorithm with support vector machine (SVM), k nearest neighbor (KNN), and mind evolutionary algorithm-based back propagation (MEA-BP) neural network. The results show that the SVM-based TrAdaboost integrated learning algorithm has the best performance when 30% of the target domain instance data is migrated, with an average classification accuracy of 86.17%, a Kappa value of 0.723 3, and an AUC value of 0.849 8. These results suggest that the algorithm can be used to recognize MI signals across individuals, providing a new way to improve the generalization capability of BCI recognition models.
Brain-Computer Interfaces ; Humans ; Support Vector Machine ; Algorithms ; Neural Networks, Computer ; Imagination/physiology* ; Pattern Recognition, Automated/methods* ; Electroencephalography ; Wavelet Analysis