Technology and Health Care最新文献

{"title":"Interpretable machine learning algorithms for diagnostic prediction of diabetic retinopathy.","authors":"Yifeng Dou, Jiantao Liu","doi":"10.1177/09287329251410736","DOIUrl":"10.1177/09287329251410736","url":null,"abstract":"<p><p>BackgroundDiabetic Retinopathy (DR) remains a leading cause of blindness among diabetic patients worldwide, necessitating early and accurate diagnostic interventions. While traditional screening methods rely heavily on manual ophthalmologic evaluations, recent advancements in machine learning (ML) and deep learning (DL) have opened new avenues for automated, scalable, and interpretable diagnostic tools. However, challenges persist in developing models that are not only high-performing but also transparent enough to gain clinical trust.ObjectiveThis study introduces a novel, standardized, and interpretable ML framework designed specifically to enhance diagnostic efficiency and accuracy for DR risk prediction. By prioritizing model interpretability alongside predictive performance, our approach aims to bridge the gap between cutting-edge AI technology and clinical applicability.MethodsWe evaluated eleven ML algorithms, optimizing hyperparameters via grid search and five-fold cross-validation to identify top-performing models. A key innovation lies in our dynamic weighted voting ensemble (Voting_soft), which integrates multiple classifiers based on model confidence, thereby leveraging the strengths of diverse algorithms. Model performance was rigorously assessed using accuracy, sensitivity, and area under the curve (AUC) metrics, with ROC and PR curves comparing performance across varying training dataset proportions. Crucially, we employed SHAP (SHapley Additive exPlanations) for interpretability analysis, providing clinicians with actionable insights into feature contributions.ResultsThrough LightGBM-based correlation analysis and AUC curve determination, fourteen clinical features were identified as optimal predictors. Notably, the CatBoost model achieved superior performance on a 20% test set, while the Extreme Random Tree model demonstrated robustness on a 30% test set. Our dynamic weighted voting ensemble (Voting_soft) outperformed individual models in terms of AUC across both datasets. SHAP analysis revealed that age, triglycerides, sex, and HDL-C were key predictors of DR prevalence, offering clinically meaningful explanations for model decisions.ConclusionsThis study presents a groundbreaking ML-based DR risk prediction system that excels in both accuracy and interpretability. The integration of SHAP analysis not only enhances model transparency but also empowers clinicians with a deeper understanding of diagnostic decision-making, ultimately improving the precision and efficiency of DR screening. Our dynamic voting ensemble approach sets a new benchmark for interpretable, multi-model integration in medical diagnostics.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"124-135"},"PeriodicalIF":1.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145858769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of the rules of acupoint selection along meridians in the treatment of insomnia by guasha therapy.","authors":"Yanhuan Qi, Haimin Li, Yun Chen, Yinqin Zhong, Meixia Ye, Jie Chen, Ying Liu","doi":"10.1177/09287329251358625","DOIUrl":"10.1177/09287329251358625","url":null,"abstract":"<p><p>BackgroundInsomnia is a prevalent global health issue that significantly impacts quality of life and poses a substantial economic burden. While conventional pharmacological and non-pharmacological treatments exist, they are often limited by side effects, dependency, or low clinical applicability. Guasha therapy, a traditional Chinese medicine nursing technique, shows promise for treating insomnia, but lacks standardized, evidence-based guidelines for its clinical application.ObjectiveTo analyze the regularity of meridian and acupoint selection in the treatment of insomnia with scraping therapy by using data mining technology.MethodsA computer-based search of PubMed, Web of Science, China National Knowledge Infrastructure (CNKI), Wanfang Data Knowledge Service Platform, Weipu Database(VIP), and Chinese Biomedical Literature Database (CBM) was conducted to retrieve the literature on scraping therapy for insomnia from the establishment of the database to March 15,2024.Excel was used to establish a database of acupoints for scraping therapy for insomnia, and the frequency of acupoints and meridians and the meridian tropism of acupoints were analyzed. SPSS 26.0 was used to cluster the high-frequency acupoints. The Apriori algorithm model provided by SPSS Modeler 18.0 was used to analyze the association rules of acupoint compatibility. Cytoscape 3.10.1 software was used to construct a complex network of meridian compatibility, and to analyze the core meridian of scraping in the treatment of insomnia.ResultsA total of 119 literatures were finally included, including 144 acupoints, with a total of 1121 frequencies. The most commonly used acupoints were Xinshu (BL15), Baihui (GV20), and Shenmen (HT7), and the commonly used compatibility acupoints were Xinshu-Pishu (BL20) and Xinshu-Pishu-Shenmen. The main meridians are Bladder meridian of foot-taiyang, Governor vessel, Gallbladder meridian of foot-shaoyang and Heart meridian of hand-shaoyin, which are the core meridian routes.ConclusionsData mining can effectively analyze the commonly used acupoints, acupoint compatibility rules and meridian rules of Gua Sha in the treatment of insomnia. The analysis results align with the traditional Chinese medicine principle of primarily following meridians, combining syndrome and root, enhancing the treatment effectiveness of insomnia, and providing a reference for clinical practice and research.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"63-74"},"PeriodicalIF":1.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144643935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Localization of drug-resistant epilepsy using chemical exchange saturation transfer and magnetic resonance spectroscopy.","authors":"Gen Yan, Yinghua Xuan, Yanyan Tang, Jing Xu, Yongmin Chang, Renhua Wu","doi":"10.1177/09287329251389492","DOIUrl":"10.1177/09287329251389492","url":null,"abstract":"<p><p>This study investigates the efficacy of two advanced magnetic resonance technologies, proton magnetic resonance spectroscopy (1H MRS) and chemical exchange saturation transfer (CEST), for the precise detection of epileptic foci through the quantification of glutamate in a patient with drug-resistant epilepsy. A 21-year old female patient with drug-resistant epilepsy was examined using magnetic resonance imaging (MRI), MRS, and CEST with a 3.0-T MRI scanner with an 8-channel phased array head coil. Despite the absence of identifiable lesions on conventional MRI scans, CEST identified regions of high glutamate concentration in the left hippocampus, consistent with an epileptic focus. These results were confirmed with MRS. The findings of this investigation indicate that CEST is an effective method for the detection of high levels of glutamate, which correspond with epileptic foci. We therefore propose that CEST and MRS be incorporated into the standard diagnostic protocol used for patients with drug-resistant, MRI-negative epilepsy.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"75-82"},"PeriodicalIF":1.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145402543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance verification of blood vessel detection system using near-infrared light.","authors":"Jieun Park, Junghun Kim","doi":"10.1177/09287329251414328","DOIUrl":"10.1177/09287329251414328","url":null,"abstract":"<p><p>BackgroundNear-infrared (NIR) imaging technology has been increasingly applied in clinical and biomedical engineering fields for subcutaneous vein detection and vascular guidance. However, most existing systems still face limitations such as inconsistent visualization under various skin tones and difficulties in achieving real-time projection alignment.ObjectiveThe objective of this study is to develop a near-infrared (NIR)-based vascular detection system and to evaluate its performance.MethodsThe developed system provides intuitive visualization by projecting vascular images in real time onto the same skin region. Performance validation was conducted using a vascular model and the abdominal vessels of rabbits.ResultsIn the vascular model experiment, the localization accuracy was 98.9%, and in the rabbit experiment, the detection success rate for vessels with a diameter of ≥1 mm was 100%.ConclusionsThe proposed method was confirmed to reduce the time required for acquiring anatomical knowledge and to minimize complications by preventing incorrect venipuncture.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"313-321"},"PeriodicalIF":1.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146208207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Valproic acid physiological pharmacokinetics simulation for epilepsy patients via a refined seven-compartmental model: A pilot study.","authors":"Tsung-Han Lin, Shih-Hsun Huang, Keng-Yi Wu, Tzu-Hsien Chao, Lung-Kwang Pan, Ya-Hui Lin, Bing-Ru Peng","doi":"10.1177/09287329261417461","DOIUrl":"10.1177/09287329261417461","url":null,"abstract":"<p><p>This study simulated valproic acid (VPA) physiological pharmacokinetics for epilepsy patients via a refined seven-compartmental model. The seven compartments were defined as oral, GI Tract, liver, whole body (WB), cerebrospinal fluid (CSF), kidney, and bladder. A first-order system of seven differential equations was defined according to this specific model and solved by a self-developed program run in MATLAB to evaluate the VPA time-dependent change among compartments. Each compartment's preset dissolving half-life (in hours) was as follows: oral 0.05, GI Tract 0.10, liver 0.5, WB 2.2, CSF 0.8, kidney 1.2, and bladder 0.5, respectively. The derived results were reorganized according to various presets of dissolving half-lives of the liver, WB, CSF, or kidney to analyze the VPA time-dependent changes under various scenarios. Either the liver or WB was the dominant compartment in this model, which mainly controlled the VPA changes. In contrast, others compartments followed the principle of secular equilibrium in the chain decay of radioactive nuclides. Accordingly, the VPA degradation changes in WB (\"mother\" compartment) mainly affected the VPA changes in other (\"daughter\") compartments. Thus, the predicted VPA degradation in CSF, kidney, or bladder was always longer than in WB despite its dissolving half-life changes. The predicted results of VPA changes in various compartments were also compared with other studies, and a reasonable agreement was reached on whether the dissolving half-life of the liver or WB ranged from the original 0.2/2.2 to 1.4/0.9 h. The programable capability of this self-developed program allows one to easily modify the primary preset to comply with findings from other studies and has great potential in similar applications.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"208-221"},"PeriodicalIF":1.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146214601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Checkpoint blockade immunotherapy for multiple recurrences of radiation-induced maxillary sinus sarcoma: A case report.","authors":"Yuge Li, Yan Zhong, Lijuan Ge, Guiyuan Peng","doi":"10.1177/09287329251358636","DOIUrl":"10.1177/09287329251358636","url":null,"abstract":"<p><p>BackgroundRadiotherapy has become a fundamental treatment modality of head and neck (HN) malignancies, which provides a chance of long-term survival. However, radiation also amplifies the risk of developing radiation-induced sarcoma (RIS) in the irradiated tissue. Radiation-induced maxillary sinus sarcoma (RIMSS) is an extremely rare and highly lethal malignancy of the HN. RIS is mainly treated with surgery, but the anatomical district and the infiltrative nature of RIS make it challenging to achieve negative margins, resulting in high fatality rate with the mean survival time of approximately one year. Immunotherapy, as an effective treatment option is rapidly evolving for HN tumors. However, checkpoint Blockade Immunotherapy (CBI) combined with chemotherapy as maintenance therapy for RIS of HN is rarely reported.Case presentationThe study presents a 36-year-old female with numerous recurrences of RIMSS, who experienced a dramatic response to checkpoint blockade immunotherapy after rapidly progressing on involved-field radiotherapy and multiple surgeries. After using immunotherapy combined with chemotherapy, the patient had a nearly complete response (CR) and maintained with single-agent programmed cell death 1 (PD-1) inhibitors.ResultsThe patient achieved a durable response, with progression-free survival (PFS) lasting 18 months.ConclusionUsing CBI as maintenance therapy for RIMSS represents a novel treatment option, especially for unresectable patients. Further investigation is warranted to optimize a multimodal treatment and improve response.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"83-89"},"PeriodicalIF":1.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144692094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimating ground reaction forces and moments during gait from multiple kinematic variables using a feedforward neural network.","authors":"Jeheon Moon, Taewhan Kim, Sangwoo Lee, Gustavo Adrian Ruiz Sanchez, Jeongwoo Seo, Sungmin Kim","doi":"10.1177/09287329251414523","DOIUrl":"10.1177/09287329251414523","url":null,"abstract":"<p><p>BackgroundGround reaction force (GRF) and ground reaction moment (GRM) are critical in gait analysis. While force plates provide accurate measurements, they are costly and spatially limiting.ObjectiveThis study aimed to evaluate the reliability and accuracy of GRF and GRM predictions using a feedforward neural network (FNN) integrating infrared camera-based positional data with accelerometer (ACC) data from wearable devices.MethodsEighty participants walked at their usual pace along a 10-meter walkway over force plates. Positional and ACC data of body segments were used to train the FNN to predict GRF and GRM. Prediction accuracy was assessed using multiple metrics, including root mean square error (RMSE) and normalized RMSE (NRMSE).ResultsCombining positional and ACC data improved GRF prediction in all directions (vertical, anterior-posterior, medial-lateral). The combined dataset achieved a correlation coefficient of 0.979 for medial-lateral GRF and an NRMSE of 6.07%. GRM predictions also benefited from ACC integration, especially in the sagittal plane, where <i>R</i>² reached 0.939, outperforming other models. The vertical direction and transverse axis yielded the lowest RMSE and NRMSE.ConclusionsThese findings surpass many previously reported results, demonstrating the superior performance of the proposed model compared with current state-of-the-art methods. The approach offers a cost-effective, flexible alternative to traditional force plates for clinical and sports assessments.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"300-312"},"PeriodicalIF":1.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147345478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A study on image processing of vein extraction images according to development of vein detector.","authors":"So-Hyeon Bang, Seung-Hun Kim, Jin-Hyoung Jeong","doi":"10.1177/09287329251389493","DOIUrl":"10.1177/09287329251389493","url":null,"abstract":"<p><p>BackgroundIntravenous infusion often faces difficulties in patients with obesity, aging, or dark skin. Low-cost vein detection using near-infrared (NIR) light is gaining attention to improve vascular access. Previous studies focused mainly on high-end devices or single algorithm performance.ObjectiveThis study aimed to develop a low-cost vein detection system using 850 nm NIR LEDs and Raspberry Pi 4. It also sought to evaluate and compare multiple image enhancement algorithms. Performance was assessed using Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM) metrics.MethodsThe device consisted of an NIR LED module, IR-sensitive camera, and Raspberry Pi 4. Algorithms used were Contrast Limited Adaptive Histogram Equalization (CLAHE), Unsharp Masking, Median Filter, and Fuzzy Adaptive Gamma. Images from 13 subjects were enhanced and evaluated using three quantitative metrics.ResultsUnsharp Masking achieved the lowest MSE (36.17) and highest PSNR (32.98), showing strong contrast enhancement. Median Filtering produced the highest SSIM (0.926), effectively preserving structural consistency. Combining CLAHE + Unsharp Masking + Median Filter yielded the best overall performance. However, this combination led to a slight SSIM decrease due to over-enhancement and edge distortion. Hardware limitations (low resolution and processing speed of Raspberry Pi 4) also impacted image quality and SSIM.ConclusionThe proposed low-cost vein detection system effectively enhanced vascular images using selected algorithms. Unsharp Masking and Median Filtering were particularly effective in improving contrast and maintaining structure. Future work should focus on real-time optimization and hardware upgrades to improve clinical applicability.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"167-178"},"PeriodicalIF":1.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145497306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of hip extensor exercises on neck disability, cervical alignment, muscle imbalance, and blood flow in forward head posture.","authors":"Yunhwan Kim, Youngjoo Cha, Samwon Yoon","doi":"10.1177/09287329251392400","DOIUrl":"10.1177/09287329251392400","url":null,"abstract":"<p><p>BackgroundForward head posture (FHP) is a common disorder worsened by prolonged use of electronic devices, causing increased neck load and musculoskeletal issues. While McKenzie neck exercises (MNE) are widely used to address FHP, the potential benefits of hip extensor exercises (HEE) remain underexplored.ObjectiveThis study aims to compare the effects of MNE and HEE on neck disability index (NDI), craniovertebral angle (CVA), cranial rotation angle (CRA), and the thickness of the LC muscle and carotid artery (CA) in individuals with FHP.MethodsTwenty participants with FHP were randomly assigned to either the MNE or HEE group, undergoing their respective exercises for 20 min per session, three times a week for two weeks. Pre- and post-intervention assessments included NDI questionnaire, CVA, CRA measurements, and ultrasonographic evaluation of LC muscle and CA thickness.ResultsBoth MNE and HEE groups showed significant improvements in NDI, CVA, CRA, and LC muscle thickness post-intervention (P < 0.05), with no significant group differences (P > 0.05). CA thickness increased in both groups, though not significantly.ConclusionsBoth MNE and HEE effectively improved symptoms and alignment associated with forward head posture. These findings suggest that hip extensor exercises may be a beneficial approach to mitigating FHP, similar to MNE.</p>","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"145-153"},"PeriodicalIF":1.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145497289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Special issue: Progress in medical and health technologies for diagnosis, intervention, and care.","authors":"Carlos Gómez, Feng Liu","doi":"10.1177/09287329261425824","DOIUrl":"10.1177/09287329261425824","url":null,"abstract":"","PeriodicalId":48978,"journal":{"name":"Technology and Health Care","volume":" ","pages":"39"},"PeriodicalIF":1.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147311431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}