Health Care Science最新文献

{"title":"Evaluating ChatGPT's Adherence to Medical Ethics: A Prerequisite for Artificial Intelligence in Medicine.","authors":"Ying Zhang, Yuyang Liu, Tingyu Lv, Junhui Wang, Hui Liu, Xiaoying Li","doi":"10.1002/hcs2.70067","DOIUrl":"https://doi.org/10.1002/hcs2.70067","url":null,"abstract":"<p><strong>Background: </strong>As artificial intelligence continues to play an expanding role in healthcare, ensuring its compliance with medical ethics is essential. However, the ethical performance of artificial intelligence in medical contexts remains insufficiently studied. This study aimed to evaluate the ability of ChatGPT to address questions related to medical ethics and to compare its performance with that of human experts.</p><p><strong>Methods: </strong>A Medical Ethics Evaluation dataset was developed, consisting of 465 single-choice questions derived from a range of medical ethics standards. These questions were used to assess two artificial intelligence models, GPT-3.5 and GPT-4. Model responses were compared with those provided by two medical ethics experts. Each test was conducted independently twice to ensure consistency. Accuracy was calculated for each model and expert, and chi-square tests were used to compare differences in performance.</p><p><strong>Results: </strong>GPT-3.5 achieved an overall accuracy of 38.92%, while GPT-4 achieved 27.10%. In comparison, two medical ethics experts achieved substantially higher accuracies of 86.23% and 78.32%, respectively. Both experts performed significantly better than GPT-3.5 and GPT-4. These findings indicate a substantial gap between artificial intelligence models and human experts in understanding and applying medical ethics principles. The relatively low performance of the models, compared with their reported strengths in diagnostic tasks, may reflect the complexity and nuance of ethical reasoning in medicine. Nevertheless, the large language models showed some ability to align with core medical ethics principles, particularly in ethical dilemma scenarios, and were also able to generate responses that addressed psychological needs.</p><p><strong>Conclusions: </strong>Artificial intelligence models currently show limited accuracy in medical ethics decision-making compared with human experts. Although these models demonstrate some alignment with fundamental ethical principles, the performance is not yet sufficient for reliable use in ethically sensitive medical contexts. Further optimization is needed to improve their ability to meet the ethical demands of medical practice.</p>","PeriodicalId":100601,"journal":{"name":"Health Care Science","volume":"5 2","pages":"98-108"},"PeriodicalIF":3.3,"publicationDate":"2026-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13109837/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147793871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance Measurement for Surgery at National Level in China.","authors":"Tianyi Zhang, Qian Zhuang, Wei Liu, Yuehui Liu, Boya Zhang, Mingming Zhang, Xuan Zhang, Lin Li, Jianchao Liu, Zhouheng Ye","doi":"10.1002/hcs2.70066","DOIUrl":"https://doi.org/10.1002/hcs2.70066","url":null,"abstract":"<p><strong>Background: </strong>Performance assessment is the first step to improve the quality of surgery. To date, no studies have systematically evaluated the surgical performance measures in China. This study aims to investigate the performance measures in surgical care at national level in China, with the objective of identifying existing gaps and potential opportunities in performance measurement of surgical care.</p><p><strong>Methods: </strong>We summarized and evaluated surgery related performance measures from five officially published performance evaluation indicator systems in China, and compared with those endorsed by National Quality Forum (NQF), the clearing house for all federal performance measures in the United States. The evaluation and comparison include: (1) the process of measure development; (2) the characteristics of the measures, including stewards, Donabedian frames, risk adjustment, and so on; (3) the keywords of the measures using word cloud analysis.</p><p><strong>Results: </strong>A total of 85 measures relevant to surgery were included in the analysis. Among them, the majority was outcome measures, which was similar to NQF measures (76.47% <i>vs.</i> 70.27%, <i>p</i> = 0.9875). The development of surgical performance measures in China was primarily led by the government, but lacked a third-party evaluation mechanism. Further, compared with NQF, the performance measures were more generic and limited in specialty association engagement, risk adjustment, and payment linkage.</p><p><strong>Conclusions: </strong>While China has made significant progress in the performance measures in surgery, the opportunities for improvement remain in this area, including the involvement of special societies, the establishment of an evaluation mechanism, and the implementation of risk adjustment for measures.</p>","PeriodicalId":100601,"journal":{"name":"Health Care Science","volume":"5 2","pages":"109-116"},"PeriodicalIF":3.3,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13109843/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147793899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fight for the People's Health: The Application of Al Multiagent Systems in Medical Consortia.","authors":"Zihao Bian, Zhiyi Luo, Wenhui Zhang, Fanyi Kong, Yiyi Yang, Yiyang Chen, Chenjia Liao, Ziyi Chen, Wei Wang, Wanyun Zhong, Tuo Li, Nan Wang, Rongfang Zhu, Gen Li, Kangwei Shi, Ruizhe Shi, Zeyu Zhang, Zongjiu Zhang","doi":"10.1002/hcs2.70037","DOIUrl":"https://doi.org/10.1002/hcs2.70037","url":null,"abstract":"<p><strong>Background: </strong>The nationwide implementation of medical consortia at both district and county levels has reshaped China's healthcare system profoundly by establishing collaborative institutional networks and tiered service delivery pathways. However, difficulties such as loose referral, fragmented information, and resource disparity have hampered the delivery of integrated care in these consortia. Leveraging cutting-edge information technology, this study aims to propose a set of AI-driven integrated medical alliance solutions catering to the needs of patients, medical workers, and administrators.</p><p><strong>Methods: </strong>In the study, we introduce a multiagent system using the coordinator worker model and role-based architecture. The system uses the retrieval-augmented generation (RAG) framework, the ERNIE model, the chain of thought (CoT) reasoning mechanism, and an interactive platform. It is capable of enhancing full life-cycle healthcare service by supporting patients' navigation of the system, doctors' clinical decision-making, and hospital management, providing key functions like triage guidance, medical research assistance, and real-time hospital operational data analysis.</p><p><strong>Results: </strong>This intelligent medical decision support platform provides tailored healthcare, ensures treatment continuity, improves decision-making quality, and optimizes resource allocation efficiency.</p><p><strong>Discussion: </strong>Following the detailed analysis of the applications and advantages of the framework, the study further explores the challenges faced during the implementation of this platform, particularly related to hallucination, data security, and cost control.</p><p><strong>Conclusions: </strong>Finally, it calls for continued efforts to build intelligent, equitable, and high-value healthcare systems through expanded applications of medical multiagent systems.</p>","PeriodicalId":100601,"journal":{"name":"Health Care Science","volume":"5 2","pages":"158-168"},"PeriodicalIF":3.3,"publicationDate":"2026-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13109845/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147793887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Health Influence and Association Analysis of Inpatient Service Under-Utilization in Older Adults With Multimorbidities: A National Study in China.","authors":"Yunlian Xue, Zhuomin Huang, Jinqi Ye, Guihao Liu","doi":"10.1002/hcs2.70063","DOIUrl":"https://doi.org/10.1002/hcs2.70063","url":null,"abstract":"<p><strong>Background: </strong>In the Chinese aging population characterized by rising chronic comorbidities, this study investigated under-utilization of inpatient services (hospitalization) among elderly individuals with multimorbidities, aiming to elucidate its health impacts and contributing factors so as to inform policy.</p><p><strong>Methods: </strong>A national household investigation was conducted using cross-sectional and prospective methods. The study included 3636 adults aged ≥ 60 with multimorbidities from the China Health and Retirement Longitudinal Study (CHARLS 2015), with follow-up health assessments in 2018. Cox regression was employed to analyze the health consequences of non-hospitalization; logistic regression analysis identified contributing factors.</p><p><strong>Results: </strong>Overall, 8.7% of elderly adults with multimorbidities declined hospitalization despite medical necessity. After adjusting for demographics and lifestyle factors, we found that this refusal was significantly linked to a deterioration in self-rated health (hazard ratio [HR]: 1.273; 95% confidence interval [CI]: 1.091-1.484) and inability to work normally (HR: 1.244; 95% CI: 1.060-1.459) and inability to perform normal household tasks (HR: 1.579; 95% CI: 1.250-1.996) after 3 years. In the fully adjusted model, non-hospitalization despite medical necessity remained a statistically significant risk factor for a decreased ability to perform normal household chores (HR: 1.403; 95% CI: 1.064-1.851), particularly affecting families with poor economic status (HR: 1.529; 95% CI: 1.003-2.332). Key independent factors for non-hospitalization despite medical needs included physical dysfunctions (odds ratio [OR]: 2.646; 95% CI: 1.644-4.260), inadequacy of long-term care (OR: 1.341; 95% CI: 1.006-1.787), being very dissatisfied with marriage (OR: 2.629; 95% CI: 1.137-6.079), and increased number of chronic multimorbidities (OR: 1.292; 95% CI: 1.190-1.402).</p><p><strong>Conclusions: </strong>Inadequate inpatient service utilization among multimorbid elderly individuals exacerbates health risks, particularly for those with physical limitations, marital distress, care deficits, and high chronic disease burdens. Therefore, targeted interventions are urgently required.</p>","PeriodicalId":100601,"journal":{"name":"Health Care Science","volume":"5 2","pages":"117-127"},"PeriodicalIF":3.3,"publicationDate":"2026-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13109839/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147793885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ischemic Stroke Burden in China and Other G20 Nations (1990-2021): A Comparative Analysis From the Global Burden of Disease Study 2021 and Trend Projections Through 2031.","authors":"Bin Luo, Yi Xiang, Hecheng Ren, Lin Ma, Ying Huang","doi":"10.1002/hcs2.70064","DOIUrl":"https://doi.org/10.1002/hcs2.70064","url":null,"abstract":"<p><strong>Background: </strong>Ischemic stroke (IS) persists as a major global health challenge. This study assesses IS burden, epidemiological trends, and associations with the Socio-demographic Index (SDI) across China and G20 nations (1990-2021), projecting trends to 2031 to inform resource prioritization.</p><p><strong>Methods: </strong>Utilizing Global Burden of Disease (GBD) 2021 data, we analyzed age-standardized incidence rates (ASIR) and age-standardized mortality rates (ASMR), disability-adjusted life years (DALYs), and mortality-to-incidence ratio (MIR) using Joinpoint regression (trends), autoregressive integrated moving average (projections), and Pearson correlation (SDI linkage), stratified by age and sex.</p><p><strong>Results: </strong>From 1990 to 2021, China experienced rising crude IS incidence (+27.4%) contrasting with G20 declines. Although ASMR and DALYs decreased globally, China's ASMR initially increased (1999-2004) before declining, unlike sustained G20 reductions. China's ASIR rose 35.7% versus a 15.6% G20 reduction. Projections indicate stable ASMR with rising ASIR in China, diverging from declining ASMR and stable ASIR in the G20. SDI-linked disparities persisted, with China's ASIR/ASMR exceeding G20 averages relative to SDI.</p><p><strong>Conclusions: </strong>China's distinct trajectory-characterized by rising incidence and delayed mortality decline-underscores the necessity for tailored interventions. Addressing SDI-driven disparities is essential for equitable global prevention and care strategies.</p>","PeriodicalId":100601,"journal":{"name":"Health Care Science","volume":"5 2","pages":"141-157"},"PeriodicalIF":3.3,"publicationDate":"2026-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13109835/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147793859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Refining Osteoarthritis Risk Prediction: Average Sagittal Abdominal Diameter Complements and Enhances Body Mass Index With Sex-Specific Insights From National Health and Nutrition Examination Survey.","authors":"Yuwei Zhang, Xiaoshuai Wang, Hu Zhu, Haowei Chen, Zhaohua Zhu, Liangbin Zhou, Michael Tim Yun Ong, Dongquan Shi, Xin Zhang, David J Hunter, Changhai Ding, Rocky S Tuan, Zhong Alan Li","doi":"10.1002/hcs2.70061","DOIUrl":"https://doi.org/10.1002/hcs2.70061","url":null,"abstract":"<p><strong>Background: </strong>Osteoarthritis (OA), the most prevalent joint disease and a leading cause of disability globally, has its disease burden inadequately captured by body mass index (BMI). As the sole quantified risk factor in current Global Burden of Disease estimates, BMI accounted for only 20% of OA burden. A critical limitation of BMI is its inability to distinguish fat distribution patterns, particularly abdominal adiposity, which is increasingly recognized as a key driver of metabolic and musculoskeletal pathologies. Herein, we hypothesize that anthropometric indicators reflecting central adiposity, such as average sagittal abdominal diameter (ASAD), may outperform BMI in predicting OA risk, especially when considering sex and age differences.</p><p><strong>Methods: </strong>This cross-sectional study analyzed 27,791 National Health and Nutrition Examination Survey participants (1999-2023) with complete OA diagnosis, anthropometric, and metabolic data. Participants were stratified by sex and age (40-year cutoff). Multivariable logistic regression, adjusted for confounders, estimated predictor-OA associations via standardized odds ratios (sORs), and these associations were evaluated by the area under the receiver operating characteristic curve (AUROC). Data were split into training (70%) and validation (30%) sets, with DeLong's test comparing different predictors against BMI.</p><p><strong>Results: </strong>In the overall population, ASAD showed a stronger association with OA (sOR = 1.483) than BMI (sOR = 1.436), with comparable validation AUROC (ASAD: 0.857; BMI: 0.854). Sex-stratified analysis revealed that BMI was the optimal predictor for males (sOR = 1.466; validation AUROC = 0.844), while ASAD outperformed BMI in females (sOR = 1.486 vs. 1.450; validation AUROC = 0.865 vs. 0.863). Further age stratification revealed that in males under 40, both BMI (sOR = 1.261; validation AUROC = 0.750) and ASAD (sOR = 1.194; validation AUROC = 0.889) were the strongest predictors, and that ASAD (sOR = 1.490; validation AUROC = 0.769) and BMI (sOR = 1.482; validation AUROC = 0.736) remained strong for males aged 40 and above. In age-stratified analyses of females, ASAD showed the strongest consistent association with OA risk, both in participants under 40 (sOR = 1.472; validation AUROC = 0.801) and those aged 40 and above (sOR = 1.421; validation AUROC = 0.764).</p><p><strong>Conclusions: </strong>ASAD emerges as a superior predictor for females and a competitive population-level complement to BMI. BMI remains an optimal OA predictor for males. Within the National Health and Nutrition Examination Survey framework, these findings underscore the necessity of integrating abdominal adiposity metrics, particularly ASAD, into OA risk assessment to improve sex-specific prevention strategies.</p>","PeriodicalId":100601,"journal":{"name":"Health Care Science","volume":"5 2","pages":"128-140"},"PeriodicalIF":3.3,"publicationDate":"2026-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13109838/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147793897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Relationship Between Missed Nursing Care and Nursing Teamwork in Jordan","authors":"Muna Salahat,&nbsp;Ali Saleh","doi":"10.1002/hcs2.70055","DOIUrl":"10.1002/hcs2.70055","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>The effective delivery of nursing care is crucial in hospital settings because it directly affects patient outcomes. However, nursing care can be missed because of various factors, including inadequate teamwork among nursing staff. Understanding the interplay between missed nursing care and nursing teamwork is essential for enhancing care quality in inpatient settings. This study therefore explored the relationship between missed nursing care and nursing teamwork among registered nurses in hospital inpatient units.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>A descriptive, correlational, cross-sectional study was conducted, involving 375 registered nurses from four hospitals in three healthcare sectors in Jordan. Missed nursing care and nursing teamwork were measured using the Missed Nursing Care Survey and the Nursing Teamwork Survey. Data collection occurred between September and October 2024, with convenience sampling used for participant recruitment. Descriptive and inferential statistics, including mean, standard deviation, percentage, frequency, and Pearson's <i>r</i> correlation coefficient, were used to analyze the data.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The overall average missed nursing care score was 2.35 out of 5, suggesting that nursing care is rarely missed. The most frequently missed care activities reported by registered nurses included attending interdisciplinary care conferences, providing mouth care, and ambulating patients three times daily or as ordered. Activities least often missed included medication administration within 30 min of the scheduled time, assessing vital signs as ordered, and performing patient assessments each shift. The overall mean score for nursing teamwork was 3.5 out of 5 (standard deviation = 1.06). There was a moderate but significant negative correlation between missed nursing care and nursing teamwork (<i>r</i> = −0.310, <i>p</i> &lt; 0.001).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>The results underscore the urgent need for targeted interventions to enhance resource allocation and teamwork, ultimately reducing missed nursing care and improving patient outcomes. Addressing these areas will foster a more effective healthcare system and enable nursing professionals to consistently deliver high-quality care.</p>\u0000 </section>\u0000 </div>","PeriodicalId":100601,"journal":{"name":"Health Care Science","volume":"5 1","pages":"58-73"},"PeriodicalIF":3.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12946711/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147329049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Validation of the World Health Organization Disability Assessment Schedule-II for Measuring Women With a History of Potentially Life-Threatening Maternal Conditions at Six Months Postpartum in Tigray, Northern Ethiopia","authors":"Fitiwi Tinsae Baykemagn,&nbsp;Girmatsion Fisseha Abreha,&nbsp;Yibrah Berhe Zelelow,&nbsp;Alemayehu Bayray Kahsay","doi":"10.1002/hcs2.70054","DOIUrl":"10.1002/hcs2.70054","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>The World Health Organization Disability Assessment Schedule 2.0 (WHODAS 2.0) is a popular tool for evaluating functioning and disability in a range of population demographics and medical situations. However, very little is known about the WHODAS 2.0's validity and reliability, particularly when dealing with potentially life-threatening maternal conditions (PLTCs). The aim of this study was to evaluate the validity of the WHODAS 2.0 Tigrigna version.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>This cross-sectional study was conducted in Tigray, northern Ethiopia, from December 15 to 20, 2023. Following translation and back translation, women who had experienced PLTCs during a recent pregnancy, childbirth, or postpartum period were administered the 36-item WHODAS 2.0 in Tigrigna version 6 months after the childbirth. In total, 121 women with a history of PLTCs participated. Cronbach′s α was used to evaluate internal consistency in all six WHODAS 2.0 domains, while Spearman′s correlation coefficient was used to evaluate convergent validity. With confirmatory factor analysis, construct validity was also examined.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>All domain scores of the Tigrigna version of the WHODAS 2.0 indicated excellent internal consistency (<i>α</i> = 0.917–0.978 for 36 items and <i>α</i> = 0.874–0.940 for 12 items), while the Cronbach′s α coefficients for the summary score were 0.981 and 0.952 for 36 and 12 items, respectively. The convergent validity between the 36-item and 12-item WHODAS 2.0 showed a strong correlation between similar constructs (<i>r</i> = 0.909–0.981).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>Despite the small sample limitation, the WHODAS 2.0 tool adapted to the Tigrigna version indicated an acceptable reliability and validity and therefore could be applied to women with a history of PLTCs at 6 months postpartum.</p>\u0000 </section>\u0000 </div>","PeriodicalId":100601,"journal":{"name":"Health Care Science","volume":"5 1","pages":"29-39"},"PeriodicalIF":3.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12946705/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147329003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Deep Neural Network Based on Two-Stage Training for Estimating Heart Rate Variability From Camera Videos","authors":"Lan Lan,&nbsp;Jin Yin,&nbsp;Haohan Zhang,&nbsp;Hua Jiang,&nbsp;Rui Qin,&nbsp;Xia Zhao,&nbsp;Yu Zhang,&nbsp;Yilong Wang,&nbsp;Jiajun Qiu","doi":"10.1002/hcs2.70047","DOIUrl":"10.1002/hcs2.70047","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Studies have shown that heart rate variability (HRV) is a predictor of the prognosis of cardiovascular diseases. Contact heartbeat monitoring equipment is widely used, especially in hospitals, and benefits from the rapidity and accuracy of the detection of physiological health indicators. However, long-term contact with equipment has many adverse effects. The purpose of this study was to improve the accuracy of HRV detection via noncontact equipment, thus enabling HRV to be assessed in various scenarios.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>A novel deep learning approach was proposed for measuring heartbeats through camera videos. First, we performed facial segmentation and divided the face into 16 grid cells with different light balance scores. After the trend is filtered by the Hamming window, a transformer-based neural network is used to further filter the signal. Finally, heart rate (HR) and HRV are estimated.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>We used 1 million synthetic data points for pretraining and a public dataset in combination with a dataset that we constructed for task training. The final results were obtained on a test dataset that we constructed. The accuracy for HR with a low light balance score (0.867–0.983) was greater than that with a high score (0.667–0.750). Our method had higher accuracy in estimating HR than traditional filtering methods (0.167–0.417) and state-of-the-art neural network filtering methods (0.783–0.917) did. The root mean square error of the HRV from the time domain was the lowest, and the correlation index score was the highest for the HRV from the frequency domain estimated by our method compared with those estimated by two neural networks.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>Light balance, large sample training, and two-stage training can improve the accuracy of HRV estimation.</p>\u0000 </section>\u0000 </div>","PeriodicalId":100601,"journal":{"name":"Health Care Science","volume":"5 1","pages":"74-84"},"PeriodicalIF":3.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12946708/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147328901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Preferences of Chinese Dermatologists for Large Language Model Responses in Clinical Psoriasis Scenarios: A Nationwide Cross-Sectional Survey in China","authors":"Jungang Yang,&nbsp;Jingkai Xu,&nbsp;Xuejiao Song,&nbsp;Chengxu Li,&nbsp;Lili Chen,&nbsp;Lingbo Bi,&nbsp;Tingting Jiang,&nbsp;Xianbo Zuo,&nbsp;Yong Cui","doi":"10.1002/hcs2.70057","DOIUrl":"10.1002/hcs2.70057","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Large language models (LLMs) have shown considerable promise in supporting clinical decision-making. However, their adoption and evaluation in dermatology remains limited. This study aimed to explore the preferences of Chinese dermatologists regarding LLM-generated responses in clinical psoriasis scenarios and to assess how they prioritize key quality dimensions, including accuracy, traceability, and logicality.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;A cross-sectional, web-based survey was conducted between December 25, 2024, and January 22, 2025, following the Checklist for Reporting Results of Internet E-Surveys guidelines. A total of 1247 valid responses were collected from practicing dermatologists across 33 of China's provincial-level administrative divisions. Participants evaluated responses to five categories of clinical questions (etiology, clinical presentation, differential diagnosis, treatment, and case study) generated by five LLMs: ChatGPT-4o, Kimi.ai, Doubao, ZuoYiGPT, and Lingyi-agent. Statistical associations between participant characteristics and model preferences were examined using chi-square tests.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;ChatGPT-4o (Model 1) emerged as the most preferred model across all clinical tasks, consistently receiving the highest number of votes in case study (&lt;i&gt;n&lt;/i&gt; = 740), clinical presentation (&lt;i&gt;n&lt;/i&gt; = 666), differential diagnosis (&lt;i&gt;n&lt;/i&gt; = 707), etiology (&lt;i&gt;n&lt;/i&gt; = 602), and treatment (&lt;i&gt;n&lt;/i&gt; = 656). Significant variation in model preference by professional title was observed only for the differential diagnosis task (&lt;i&gt;χ&lt;/i&gt;&lt;sup&gt;2&lt;/sup&gt; = 21.13, &lt;i&gt;df&lt;/i&gt; = 12, &lt;i&gt;p&lt;/i&gt; = 0.0485), while no significant differences were found across hospital tiers (&lt;i&gt;p&lt;/i&gt; &gt; 0.05). In terms of evaluation dimensions, accuracy was most frequently rated as “very important” (&lt;i&gt;n&lt;/i&gt; = 635). A significant association existed between hospital tier and the most valued dimension (&lt;i&gt;χ&lt;/i&gt;&lt;sup&gt;2&lt;/sup&gt; = 27.667, &lt;i&gt;df&lt;/i&gt; = 9, &lt;i&gt;p&lt;/i&gt; = 0.0011), with dermatologists in primary hospitals prioritizing traceability more than their peers in higher-tier hospitals. No significant associations were found across professional titles (&lt;i&gt;p&lt;/i&gt; = 0.127).&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Conclusions&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Chinese dermatologists suggest a strong preference for ChatGPT-4o over domestic LLMs in psoriasis-related clinical tasks. While accuracy remains the primary criterion, traceability and logicality are also critical, particularly for clinicians in lower-tier hospitals. Thes","PeriodicalId":100601,"journal":{"name":"Health Care Science","volume":"5 1","pages":"40-48"},"PeriodicalIF":3.3,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12946707/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147328970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}