OBJECTIVES

The challenges faced by patients with diabetes in rural Philippine communities highlight
the need to look into how we can improve ways of communicating health education and self-management strategies. Patient education materials play a vital role in promoting regimen adherence, yet their acceptability and effectiveness in resource-limited settings remain insufficiently investigated. Therefore, this study aimed to explore participants’ experiences with and perceptions of a community-based diabetes learning module through qualitative inquiry.

Using purposive sampling, 13 participants who successfully completed the Blood Sugar Bantayan, Diabetes Malikayan pilot health program from January to July 2022 in a rural community in southern Philippines consented to engage in in-depth interviews. A semi-structured topic guide was developed, validated by experts, and pretested.
Interviews were conducted in the local language, audio-recorded, transcribed, translated, and analyzed using Braun and Clarke's reflexive thematic approach.

Five major themes emerged from the analysis: initial perceptions of the module, aspects of the module found useful, perceived impact on regimen adherence, hindrances to adherence, and overall feedback with likelihood of recommendation. Participants valued the module’s visual appeal, use of local language, and comprehensive coverage of diabetes management. The module served as a guide that enabled participants to gain better control over their condition through improved self-discipline and health practices, often motivated by family support. However, challenges including time constraints, resource limitations, and competing priorities affected consistent implementation of recommended practices. Despite these barriers, participants expressed strong satisfaction with the module and willingness to share it with others, though sharing decisions were often based on perceived relevance to others’ health status.

Community-based learning modules can serve as valuable educational tools for diabetes care in rural Filipino communities. Findings underpin the importance of developing culturally appropriate and responsive campaigns for diabetes education in remote
environments, but multi-modal strategies that cut across sectors are still imperative to address persisting structural factors that pervade health program efforts.

Artificial intelligence (AI) technology enhances the function of acupuncture clinical decision support system (CDSS) by promoting the accuracy of its diagnosis, assisting the formulation of personalized therapeutic regimen, and realizing the scientific and precise evaluation of its therapeutic effect. This paper deeply analyzes the unique advantages of AI-based acupuncture CDSS, including the intelligence and high efficiency. Besides, it points out the challenges of data security, the lack of model interpretation and the complexity of interdisciplinary cooperation in the development of acupuncture CDSS. With the continuous development and improvement of AI technology, acupuncture CDSS is expected to play a more important role in the fields of personalized medicine, telemedicine and disease prevention, and to further advance the efficiency and effect of acupuncture treatment, drive the modernization of acupuncture, and enhance its position and influence in the global healthcare system.
Humans ; Acupuncture Therapy ; Artificial Intelligence ; Decision Support Systems, Clinical

BACKGROUND: Over 20 million colonoscopies are performed in China annually. An automatic clinical decision support system (CDSS) with accurate semantic recognition of colonoscopy reports and guideline-based is helpful to relieve the increasing medical burden and standardize the healthcare. In this study, the CDSS was built under a hierarchical-label interpretable classification framework, trained by a state-of-the-art transformer-based model, and validated in a multi-center style. METHODS: We conducted stratified sampling on a previously established dataset containing 302,965 electronic colonoscopy reports with pathology, identified 2041 patients' records representative of overall features, and randomly divided into the training and testing sets (7:3). A total of five main labels and 22 sublabels were applied to annotate each record on a network platform, and the data were trained respectively by three pre-training models on Chinese corpus website, including bidirectional encoder representations from transformers (BERT)-base-Chinese (BC), the BERT-wwm-ext-Chinese (BWEC), and ernie-3.0-base-zh (E3BZ). The performance of trained models was subsequently compared with a randomly initialized model, and the preferred model was selected. Model fine-tuning was applied to further enhance the capacity. The system was validated in five other hospitals with 3177 consecutive colonoscopy cases. RESULTS: The E3BZ pre-trained model exhibited the best performance, with a 90.18% accuracy and a 69.14% Macro-F1 score overall. The model achieved 100% accuracy in identifying cancer cases and 99.16% for normal cases. In external validation, the model exhibited favorable consistency and good performance among five hospitals. CONCLUSIONS The novel CDSS possesses high-level semantic recognition of colonoscopy reports, provides appropriate recommendations, and holds the potential to be a powerful tool for physicians and patients. The hierarchical multi-label strategy and pre-training method should be amendable to manage more medical text in the future.
Humans ; Colonoscopy/methods* ; Deep Learning ; Decision Support Systems, Clinical ; Female ; Male

Nutritional support therapy is one of the extremely important treatment methods for patients in the intensive care unit. Timely and effective nutritional support regimens can improve patients' immune function, reduce complications, and optimize clinical outcomes. Energy expenditure is influenced by multiple factors, including patients' baseline characteristics (such as physical condition, gender, age) and dynamic changes in indicators (such as body temperature, nutritional support regimens, and therapeutic interventions). The currently recognized "gold standard" for accurately assessing energy metabolism in clinical practice is the indirect calorimetry system, also known as the metabolic cart. This device monitors carbon dioxide production and oxygen consumption in real time and uses specific algorithms to estimate the metabolic proportions of the three major nutrients (carbohydrates, fats, and proteins) in energy expenditure. An appropriate nutrient ratio helps maintain the balance between supply and demand in the body's nutritional metabolism. In the management of critically ill patients, the application of the metabolic cart enables personalized nutritional therapy, avoiding over- or under-supply of energy and optimizing the use of medical resources. Furthermore, with real-time, quantitative data support from the energy metabolism monitoring system, clinicians can develop more precise nutritional intervention strategies, thereby improving patient prognosis. This article provides a systematic review of the technical features of the metabolic cart and its application value in various critical care scenarios, aiming to offer a reference for indirect calorimetry in clinical practice.
Humans ; Critical Illness/therapy* ; Nutritional Support ; Energy Metabolism ; Calorimetry, Indirect

OBJECTIVE: To construct machine learning prediction model for sepsis-associated encephalopathy (SAE), and analyze the application value of the model on early identification of SAE risk in elderly septic patients. METHODS: Patients aged over 60 years with a primary diagnosis of sepsis admitted to intensive care unit (ICU) from 2008 to 2023 were selected from Medical Information Mart for Intensive Care-IV 2.2 (MIMIC-IV 2.2). Demographic variables, disease severity scores, comorbidities, interventions, laboratory indicators, and hospitalization details were collected. Key factors associated with SAE were identified using univariate Logistic regression analysis. The data were randomly divided into training and validation sets in a 7 : 3 ratio. Multivariable Logistic regression analysis was conducted in the training set and visualized using a nomogram model for prediction of SAE. The discrimination of the model was evaluated in the validation set using the receiver operator characteristic curve (ROC curve), and its calibration was assessed using calibration curve. Furthermore, multiple machine learning algorithms, including multi-layer perceptron (MLP), support vector machine (SVM), naive bayes (NB), gradient boosting machine (GBM), random forest (RF), and extreme gradient boosting (XGB), were constructed in the training set. Their predictive performance was subsequently evaluated on the validation set. Taking the XGB model as an example, the interpretability of the model through the SHapley Additive exPlanations (SHAP) algorithm was enhanced to identify the key predictive factors and their contributions. RESULTS: A total of 2 204 septic patients were finally enrolled, of whom 840 developed SAE (38.1%). A total of 21 variables associated with SAE were screened through univariate Logistic regression analysis. Multivariable Logistic regression analysis showed that endotracheal intubation [odds ratio (OR) = 0.40, 95% confidence interval (95%CI) was 0.19-0.88, P < 0.001], oxygen therapy (OR = 0.76, 95%CI was 0.53-0.95, P = 0.023), tracheotomy (OR = 0.20, 95%CI was 0.07-0.53, P < 0.001), continuous renal replacement therapy (CRRT; OR = 0.32, 95%CI was 0.15-0.70, P < 0.001), cerebrovascular disease (OR = 0.31, 95%CI was 0.16-0.60, P < 0.001), rheumatic disease (OR = 0.44, 95%CI was 0.19-0.99, P < 0.001), male (OR = 0.68, 95%CI was 0.54-0.86, P = 0.001), and maximum anion gap (AG; OR = 0.95, 95%CI was 0.93-0.97, P < 0.001) were associated with an decreased probability of SAE, and age (OR = 1.05, 95%CI was 1.03-1.06, P < 0.001), acute physiology score III (APSIII; OR = 1.02, 95%CI was 1.01-1.02, P < 0.001), Oxford acute severity of illness score (OASIS; OR = 1.04, 95%CI was 1.03-1.06, P < 0.001), and length of hospital stay (OR = 1.01, 95%CI was 1.01-1.02, P < 0.001) were associated with an increased probability of SAE. A nomogram model was constructed based on these variables. In the validation set, ROC curve analysis showed that the model achieved an area under the ROC curve (AUC) of 0.723, and the calibration curve showed good consistency between the predicted probability of the model and the observed probability. Among the machine learning algorithms, including MLP, SVM, NB, GBM, RF, and XGB, the SVM model and RF model demonstrated relatively good predictive performance, with AUC of 0.748 and 0.739, respectively, and the sensitivity was both exceeding 85%. The predictive performance of the XGB model was explained through SHAP analysis, and the results indicated that APSIII score (SHAP value was 0.871), age (SHAP value was 0.521), and OASIS score (SHAP value was 0.443) were important factors affecting the predictive performance of the model. CONCLUSIONS The machine learning-based SAE prediction model exhibits good predictive capability and holds significant application value for the early identification of SAE risk in elderly septic patients.
Humans ; Machine Learning ; Aged ; Sepsis-Associated Encephalopathy ; Sepsis/complications* ; Intensive Care Units ; Logistic Models ; Middle Aged ; Male ; ROC Curve ; Female ; Bayes Theorem ; Nomograms ; Support Vector Machine ; Algorithms

Cancer is a serious global health problem and a major cause of human death. Conventional cancer treatments often run the risk of impairing vital organ functions. Anticancer peptides (ACPs) are considered to be one of the most promising therapeutic agents against common human cancers due to their small sizes, high specificity, and low toxicity. Since ACP recognition is highly limited to the laboratory, expensive, and time-consuming, we proposed pLM4ACP, a model for predicting ACPs based on machine learning and protein language models. In this model, the protein language model ProtT5 was used to extract the features of ACPs, and the extracted features were input into the support vector machine (SVM) classification algorithm for optimization and performance evaluation. The model showcased significantly higher accuracy than other methods, with the overall accuracy of 0.763, F1-score of 0.767, Matthews correlation coefficient of 0.527, and area under the curve of 0.827 on the independent test set. This study constructs an efficient anticancer peptide prediction model based on protein language models, further advancing the application of artificial intelligence in the biomedical field and promoting the development of precision medicine and computational biology.
Machine Learning ; Antineoplastic Agents/chemistry* ; Humans ; Peptides/chemistry* ; Support Vector Machine ; Algorithms ; Computational Biology/methods* ; Neoplasms/drug therapy*

Objective To analyze the caregiver presence needs and their influencing factors among hospitalized elderly non-surgical patients and provide a basis for formulating relevant policies.Methods A descriptive qualitative study method was adopted.Through purposive sampling,semi-structured interviews were conducted on elderly non-surgical patients and their families and medical staff in Peking Union Medical College Hospital from September to October 2023.MAXQDA 2020 and the 7-step phenomenological analysis method of Colaizzi were used to classify and code the interview contents and identify themes.Results The categories of caregiver presence needs of elderly non-surgical patients included basic living assistance needs,disease monitoring needs,psychological support needs,as well as the needs for family members to provide economic support and participate in treatment decision-making.The influencing factors included advanced age,frailty,the lack of self-care ability in patients with comorbidities,the susceptibility of patients to sudden situations during the disease exacerbation period,the increased risk of unexpected events in patients with psychological distress,and patients' concerns about social support and medical decision-making.Conclusion The caregiver presence needs of elderly non-surgical patients during hospitalization are high and influenced by multiple factors.
Humans ; Caregivers/psychology* ; Aged ; Hospitalization ; Social Support ; Male ; Qualitative Research ; Female

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

Emotion classification and recognition is a crucial area in emotional computing. Physiological signals, such as electroencephalogram (EEG), provide an accurate reflection of emotions and are difficult to disguise. However, emotion recognition still faces challenges in single-modal signal feature extraction and multi-modal signal integration. This study collected EEG, electromyogram (EMG), and electrodermal activity (EDA) signals from participants under three emotional states: happiness, sadness, and fear. A feature-weighted fusion method was applied for integrating the signals, and both support vector machine (SVM) and extreme learning machine (ELM) were used for classification. The results showed that the classification accuracy was highest when the fusion weights were set to EEG 0.7, EMG 0.15, and EDA 0.15, achieving accuracy rates of 80.19% and 82.48% for SVM and ELM, respectively. These rates represented an improvement of 5.81% and 2.95% compared to using EEG alone. This study offers methodological support for emotion classification and recognition using multi-modal physiological signals.
Humans ; Emotions/physiology* ; Electroencephalography ; Support Vector Machine ; Electromyography ; Signal Processing, Computer-Assisted ; Galvanic Skin Response/physiology* ; Machine Learning ; Male

Existing emotion recognition research is typically limited to static laboratory settings and has not fully handle the changes in emotional states in dynamic scenarios. To address this problem, this paper proposes a method for dynamic continuous emotion recognition based on electroencephalography (EEG) and eye movement signals. Firstly, an experimental paradigm was designed to cover six dynamic emotion transition scenarios including happy to calm, calm to happy, sad to calm, calm to sad, nervous to calm, and calm to nervous. EEG and eye movement data were collected simultaneously from 20 subjects to fill the gap in current multimodal dynamic continuous emotion datasets. In the valence-arousal two-dimensional space, emotion ratings for stimulus videos were performed every five seconds on a scale of 1 to 9, and dynamic continuous emotion labels were normalized. Subsequently, frequency band features were extracted from the preprocessed EEG and eye movement data. A cascade feature fusion approach was used to effectively combine EEG and eye movement features, generating an information-rich multimodal feature vector. This feature vector was input into four regression models including support vector regression with radial basis function kernel, decision tree, random forest, and K-nearest neighbors, to develop the dynamic continuous emotion recognition model. The results showed that the proposed method achieved the lowest mean square error for valence and arousal across the six dynamic continuous emotions. This approach can accurately recognize various emotion transitions in dynamic situations, offering higher accuracy and robustness compared to using either EEG or eye movement signals alone, making it well-suited for practical applications.
Humans ; Electroencephalography/methods* ; Emotions/physiology* ; Eye Movements/physiology* ; Signal Processing, Computer-Assisted ; Support Vector Machine ; Algorithms