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

OBJECTIVE: To construct a predictive model for the reduction in methadone maintenance treatment (MMT) and evaluate the effects of different interventions and other clinical factors on methadone reduction using Shapley additive explanations (SHAP). METHODS: Two clinical trials of acupuncture for methadone reduction in MMT patients were analyzed, and the baseline data, MMT related information, intervention measures, the data related to dose-reduction outcomes were collected. The predictive model was constructed by means of 6 machine learning algorithms including support vector machine (SVM), K-nearest neighbors (KNN), logistic regression (LR), Naive Bayes (NB), random forest (RF) and categorical-boosting (CatBoost), and 2 integration methods, blending-ensemble method (Blending) and Stacking-ensemble method (Stacking). SHAP was employed for the interpretability analysis of the optimal model. RESULTS: A total of 251 MMT patients were included, 128 cases in the acupuncture group and 123 cases in the non-acupuncture group. CatBoost and Stacking performed optimally in the test set. CatBoost obtained an accuracy of 0.780 0±0.060 8, a precision of 0.500 0±0.120 0, a recall of 0.818 2±0.140 2, F1 score of 0.620 7±0.114 0, and receiver operating characteristic-area under curve (ROC-AUC) of 0.857 8±0.140 2 for the subjects. In MMT patients with acupuncture as an adjunctive therapy, the top 5 important features for methadone reduction, included intervention measures, body mass index (BMI), the duration of MMT, the history of opioid use and occupation; and SHAP values were 1.25, 0.36, 0.21, 0.19 and 0.12, respectively. The SHAP feature dependence plot showed that BMI, MMT duration and the history of opioid use presented a nonlinear negative correlation with the reduction effect. CONCLUSION In acupuncture as adjunctive therapy for methadone reduction, the clinical factors should be considered comprehensively; and the interpretable predictive model provides a scientific basis for it, which is conducive to the improvement of clinical strategy of acupuncture for methadone reduction and the development of personalized reduction scheme.
Humans ; Methadone/therapeutic use* ; Acupuncture Therapy ; Adult ; Female ; Male ; Machine Learning ; Middle Aged ; Opiate Substitution Treatment ; Young Adult

OBJECTIVE: To investigate the effect of manual acupuncture manipulations (MAMs) on subcutaneous muscle tissue, by developing quantitative models of "lifting and thrusting" and "twisting and rotating", based on machine learning techniques. METHODS: A depth camera was used to capture the acupuncture operator's hand movements during "lifting and thrusting" and "twisting and rotating" of needle. Simultaneously, the ultrasound imaging was employed to record the muscle tissue responses of the participants. Amplitude and angular features were extracted from the movement data of operators, and muscle fascicle slope features were derived from the data of ultrasound images. The dynamic time warping barycenter averaging algorithm was adopted to align the dual-source data. Various machine learning techniques were applied to build quantitative models, and the performance of each model was compared. The most optimal model was further analyzed for its interpretability. RESULTS: Among the quantitative models built for the two types of MAMs, the random forest model demonstrated the best performance. For the quantitative model of the "lifting and thrusting" technique, the coefficient of determination (R²) was 0.825. For the "twisting and rotating" technique, R² reached 0.872. CONCLUSION Machine learning can be used to effectively develop the models and quantify the effects of MAMs on subcutaneous muscle tissue. It provides a new perspective to understand the mechanism of acupuncture therapy and lays a foundation for optimizing acupuncture technology and designing personalized treatment regimen in the future.
Humans ; Acupuncture Therapy/methods* ; Machine Learning ; Male ; Adult ; Female ; Subcutaneous Tissue/diagnostic imaging* ; Young Adult

Intelligent acupuncture-moxibustion medical equipment is an important force in promoting the inheritance, innovation, and modernization of acupuncture-moxibustion. This paper reviews the development status of intelligent acupuncture-moxibustion medical equipment and related new technologies, as well as the challenges faced. It is found that, with the advancement of technologies such as big data and artificial intelligence, acupuncture-moxibustion medical equipment has shown characteristics of greater precision, miniaturization, intelligence, and portability. However, deficiencies remain in areas such as standardization and regulation, including relatively low rates of effective transformation and a lack of innovation in research outcomes. Therefore, there is an urgent need to formulate corresponding strategies: improving the development of relevant standards for intelligent acupuncture-moxibustion medical equipment, encouraging the integration of medicine and engineering, cultivating interdisciplinary talents, and strengthening the protection of invention patents. It is necessary to establish a demand-oriented pathway connecting "equipment development, equipment evaluation, product formation" through multiple stages such as talent training and research project initiation, thereby promoting the modernization and standardization of intelligent acupuncture-moxibustion medical equipment and supporting the revitalization of traditional medicine.
Moxibustion/instrumentation* ; Humans ; Acupuncture Therapy/trends* ; Artificial Intelligence

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

INTRODUCTION: An interdisciplinary panel, comprising professionals from medicine, AI and data science, law and ethics, and patient advocacy, convened to discuss key principles on regulation, implementation and evaluation of AI models in healthcare for Singapore. METHOD: The panel considered 14 statements split across 4 themes: "The Role and Scope of Regulatory Entities," "Regulatory Processes," "Pre-Approval Evaluation of AI Models" and "Medical AI in Practice". Moderated by a thematic representative, the panel deliberated on each statement and modified it until a majority agreement threshold is met. The roundtable meeting was convened in Singapore on 1 July 2024. While the statements reflect local perspectives, they may serve as a reference for other countries navigating similar challenges in AI governance in healthcare. RESULTS: Balanced testing approaches, differentiated regulatory standards for autonomous and assistive AI, and context-sensitive requirements are essential in regulating AI models in healthcare. A hybrid approach-integrating global standards with local needs to ensure AI comple-ments human decision-making and enhances clinical expertise-was recommended. Additionally, the need for patient involvement at multiple levels was underscored. There are active ongoing efforts towards development and refinement of AI governance guidelines and frameworks balancing between regulation and freedom. The statements defined therein provide guidance on how prevailing values and viewpoints can streamline AI implementation into healthcare. CONCLUSION This roundtable discussion is among the first in Singapore to develop a structured set of state-ments tailored for the regulation, implementation and evaluation of AI models in healthcare, drawing on interdisciplinary expertise from medicine, AI, data science, law, ethics and patient advocacy.
Singapore ; Humans ; Artificial Intelligence/standards* ; Delivery of Health Care/organization & administration*

INTRODUCTION: Interpretation and analysis of magnetic resonance imaging (MRI) scans in clinical settings comprise time-consuming visual ratings and complex neuroimage processing that require trained professionals. To combat these challenges, artificial intelligence (AI) techniques can aid clinicians in interpreting brain MRI for accurate diagnosis of neurodegenerative diseases but they require extensive validation. Thus, the aim of this study was to validate the use of AI-based AQUA (Neurophet Inc., Seoul, Republic of Korea) segmentation software in a Southeast Asian community-based cohort with normal cognition, mild cognitive impairment (MCI) and dementia. METHOD: Study participants belonged to the community-based Biomarker and Cognition Study in Singapore. Participants aged between 30 and 95 years, having cognitive concerns, with no diagnosis of major psychiatric, neurological or systemic disorders who were recruited consecutively between April 2022 and July 2023 were included. Participants underwent neuropsychological assessments and structural MRI, and were classified as cognitively normal, with MCI or with dementia. MRI pre-processing using automated pipelines, along with human-based visual ratings, were compared against AI-based automated AQUA output. Default mode network grey matter (GM) volumes were compared between cognitively normal, MCI and dementia groups. RESULTS: A total of 90 participants (mean age at visit was 63.32±10.96 years) were included in the study (30 cognitively normal, 40 MCI and 20 dementia). Non-parametric Spearman correlation analysis indicated that AQUA-based and human-based visual ratings were correlated with total (ρ=0.66; P<0.0001), periventricular (ρ=0.50; P<0.0001) and deep (ρ=0.57; P<0.0001) white matter hyperintensities (WMH). Additionally, volumetric WMH obtained from AQUA and automated pipelines was also strongly correlated (ρ=0.84; P<0.0001) and these correlations remained after controlling for age at visit, sex and diagnosis. Linear regression analyses illustrated significantly different AQUA-derived default mode network GM volumes between cognitively normal, MCI and dementia groups. Dementia participants had significant atrophy in the posterior cingulate cortex compared to cognitively normal participants (P=0.021; 95% confidence interval [CI] -1.25 to -0.08) and in the hippocampus compared to cognitively normal (P=0.0049; 95% CI -1.05 to -0.16) and MCI participants (P=0.0036; 95% CI -1.02 to -0.17). CONCLUSION Our findings demonstrate high concordance between human-based visual ratings and AQUA-based ratings of WMH. Additionally, the AQUA GM segmentation pipeline showed good differentiation in key regions between cognitively normal, MCI and dementia participants. Based on these findings, the automated AQUA software could aid clinicians in examining MRI scans of patients with cognitive impairment.
Humans ; Cognitive Dysfunction/pathology* ; Magnetic Resonance Imaging/methods* ; Male ; Middle Aged ; Female ; Aged ; Artificial Intelligence ; Software ; Dementia/diagnostic imaging* ; Aged, 80 and over ; Adult ; Singapore ; Neuropsychological Tests ; Brain/pathology* ; Cohort Studies ; Gray Matter/pathology* ; Southeast Asian People

Research on IgG4-related disease (IgG4-RD), an autoimmune condition recognized to be a unique disease entity only two decades ago, has processed from describing patients' symptoms and signs to summarizing its critical pathological features, and further to investigating key pathogenic mechanisms. Challenges in gaining a better understanding of the disease, however, stem from its relative rarity-potentially attributed to underrecognition-and the absence of ideal experimental animal models. Recently, with the development of various high-throughput techniques, "omics" studies at different levels (particularly the single-cell omics) have shown promise in providing detailed molecular features of IgG4-RD. While, the application of omics approaches in IgG4-RD is still at an early stage. In this paper, we review the current progress of omics research in IgG4-RD and discuss the value of machine learning methods in analyzing the data with high dimensionality.
Humans ; Immunoglobulin G4-Related Disease/metabolism* ; Immunoglobulin G/metabolism* ; Machine Learning ; Animals ; Proteomics/methods*

BACKGROUND: There is little literature describing the artificial intelligence (AI)-aided diagnosis of severe pneumonia (SP) subphenotypes and the association of the subphenotypes with the ventilatory treatment efficacy. The aim of our study is to illustrate whether clinical and biological heterogeneity, such as ventilation and gas-exchange, exists among patients with SP using chest computed tomography (CT)-based AI-aided latent class analysis (LCA). METHODS: This retrospective study included 413 patients hospitalized at Xinhua Hospital diagnosed with SP from June 1, 2015 to May 30, 2020. AI quantification results of chest CT and their combination with additional clinical variables were used to develop LCA models in an SP population. The optimal subphenotypes were determined though evaluating statistical indicators of all the LCA models, and clinical implications of them such as guiding ventilation strategies were further explored by statistical methods. RESULTS: The two-class LCA model based on AI quantification results of chest CT can describe the biological characteristics of the SP population well and hence yielded the two clinical subphenotypes. Patients with subphenotype-1 had milder infections ( P <0.001) than patients with subphenotype-2 and had lower 30-day ( P <0.001) and 90-day ( P <0.001) mortality, and lower in-hospital ( P = 0.001) and 2-year ( P <0.001) mortality. Patients with subphenotype-1 showed a better match between the percentage of non-infected lung volume (used to quantify ventilation) and oxygen saturation (used to reflect gas exchange), compared with patients with subphenotype-2. There were significant differences in the matching degree of lung ventilation and gas exchange between the two subphenotypes ( P <0.001). Compared with patients with subphenotype-2, those with subphenotype-1 showed a relatively better match between CT-based AI metrics of the non-infected region and oxygenation, and their clinical outcomes were effectively improved after receiving invasive ventilation treatment. CONCLUSIONS A two-class LCA model based on AI quantification results of chest CT in the SP population particularly revealed clinical heterogeneity of lung function. Identifying the degree of match between ventilation and gas-exchange may help guide decisions about assisted ventilation.
Humans ; Tomography, X-Ray Computed/methods* ; Male ; Female ; Retrospective Studies ; Middle Aged ; Artificial Intelligence ; Aged ; Pneumonia/diagnosis* ; Latent Class Analysis ; Adult