Journal of Medical Systems最新文献

{"title":"Ten Steps for Implementing a Hospital Rapid Response System.","authors":"Luca Cioccari, Céline Bolliger, Nora Luethi","doi":"10.1007/s10916-025-02186-z","DOIUrl":"https://doi.org/10.1007/s10916-025-02186-z","url":null,"abstract":"<p><p>Rapid response systems (RRS) were introduced in the 1990s to address acute patient deterioration outside intensive care units, aiming to prevent adverse outcomes through timely assessment and intervention. While RRS have been widely adopted across many countries, their effectiveness and optimal implementation strategies continue to be debated. These uncertainties arise from differences in study designs, hospital settings, and implementation approaches, highlighting the challenges of implementing and evaluating such complex interventions. This review outlines the key steps for successful RRS implementation, explores strategies to overcome implementation barriers, and highlights strategies for continuous improvement and evaluation of established RRS initiatives.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"55"},"PeriodicalIF":3.5,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144022769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Target-Controlled Infusion of Propofol: A Systematic Review of Recent Results.","authors":"Pavla Šafránková, Jan Bruthans","doi":"10.1007/s10916-025-02187-y","DOIUrl":"https://doi.org/10.1007/s10916-025-02187-y","url":null,"abstract":"<p><p>This study presents a systematic review conducted according to the PRISMA 2020 guidelines, evaluating pharmacokinetic-pharmacodynamic (PK-PD) models for target-controlled infusion (TCI) of propofol. A structured search was performed across PubMed, Summon, Google Scholar, Web of Science, and Scopus, identifying 427 sources, of which 17 met the inclusion criteria. The analysis revealed that nine studies compared existing models, six focused on the development of new PK-PD models, and two explored broader implications of TCI in anesthesia. Comparative studies indicate that while the Eleveld model generally offers superior predictive accuracy, it does not consistently outperform the Marsh and Schnider models across all populations. The Schnider model demonstrated better bias control in elderly patients, while the Eleveld model improved drug clearance estimation in obese patients. However, inconsistencies remain in predicting brain concentrations of propofol. Newly proposed models introduce adaptive dosing strategies, incorporating allometric scaling, lean body weight, and machine learning techniques, yet require further external validation. The results highlight ongoing challenges in achieving universal applicability of TCI models, underscoring the need for future research in refining precision dosing and personalized anesthesia management.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"54"},"PeriodicalIF":3.5,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12034585/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144040351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DeepSeek Deployed in 90 Chinese Tertiary Hospitals: How Artificial Intelligence Is Transforming Clinical Practice.","authors":"Jishizhan Chen, Chunying Miao","doi":"10.1007/s10916-025-02181-4","DOIUrl":"https://doi.org/10.1007/s10916-025-02181-4","url":null,"abstract":"<p><p>The integration of artificial intelligence (AI) into clinical practice has reached a new milestone in China, with the deployment of DeepSeek across nearly 90 tertiary hospitals. This large-scale adoption represents a significant shift in how AI is utilized beyond diagnostic assistance, extending into hospital administration, research facilitation, and patient management. Notably, DeepSeek's AI-powered systems have demonstrated transformative effects, such as a 40-fold increase in efficiency for patient follow-ups. Our comment explores the implications of DeepSeek's expansion within China's healthcare landscape, situating it within broader national policies promoting AI-driven hospital digitalization. We discuss how hospitals are leveraging DeepSeek, Notably, DeepSeek's role in imaging analysis, clinical decision support, and administrative automation. We also address the ongoing challenges of AI integration. As China accelerates its transition toward \"smart hospitals,\" the widespread adoption of AI like DeepSeek offers a compelling case study on the future of digital health in large-scale healthcare systems.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"53"},"PeriodicalIF":3.5,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144029063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of Patient Visits for Skin Diseases through Enhanced Evolutionary Computation and Ensemble Learning.","authors":"Wenting Leng, Chenglin Yang, Menggang Kou, Kequan Zhang, Xinyue Liu","doi":"10.1007/s10916-025-02185-0","DOIUrl":"https://doi.org/10.1007/s10916-025-02185-0","url":null,"abstract":"<p><p>Skin diseases are an important global public health issue, causing significant health and psychological burdens. Predicting dermatology outpatient visits is essential for optimizing hospital resources and improving diagnosis and treatment methods. Based on machine learning technology and ensemble learning theory, this study integrates four neural network models to construct an optimal prediction model for daily outpatient visits related to skin diseases. To address the issue of local optima entrapment in sand cat swarm optimization (SCSO), an enhanced SCSO is proposed by incorporating the chaotic mapping, the spiral search strategy, and the sparrow warning mechanism. The enhanced SCSO is then utilized to optimize two critical parameters of variational mode decomposition, enabling the extraction of periodic patterns from the skin disease time series. Finally, the enhanced SCSO is applied again to determine the optimal weights for the ensemble model, thereby achieving optimal fusion predictions. We utilized ten years of outpatient data from the dermatology department of a hospital in China, and selected acne, the most prevalent skin condition in the region, as a case study. Experimental results demonstrate that the proposed model effectively combines the strengths of each module, achieving an root mean squared error (RMSE) of 4.43 and an R-squared (R²) of 0.98. Compared to individual models, the RMSE and R² are improved by 79.69% and 36.97%, respectively, effectively overcoming the limitations of single-model approaches. This research provides valuable insights for leveraging medical time series data and optimizing healthcare resource allocation.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"52"},"PeriodicalIF":3.5,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144024088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of an Artificial Intelligence-Enabled Electrocardiography to Detect 23 Cardiac Arrhythmias and Predict Cardiovascular Outcomes.","authors":"Wen-Yu Lin, Chin Lin, Wen-Cheng Liu, Wei-Ting Liu, Chiao-Hsiang Chang, Hung-Yi Chen, Chiao-Chin Lee, Yu-Cheng Chen, Chen-Shu Wu, Chia-Cheng Lee, Chih-Hung Wang, Chun-Cheng Liao, Chin-Sheng Lin","doi":"10.1007/s10916-025-02177-0","DOIUrl":"https://doi.org/10.1007/s10916-025-02177-0","url":null,"abstract":"<p><p>Arrhythmias are common and can affect individuals with or without structural heart disease. Deep learning models (DLMs) have shown the ability to recognize arrhythmias using 12-lead electrocardiograms (ECGs). However, the limited types of arrhythmias and dataset robustness have hindered widespread adoption. This study aimed to develop a DLM capable of detecting various arrhythmias across diverse datasets. This algorithm development study utilized 22,130 ECGs, divided into development, tuning, validation, and competition sets. External validation was conducted on three open datasets (CODE-test, PTB-XL, CPSC2018) comprising 32,495 ECGs. The study also assessed the long-term risks of new-onset atrial fibrillation (AF), heart failure (HF), and mortality in individuals with false-positive AF detection by the DLM. In the validation set, the DLM achieved area under the receiver operating characteristic curve above 0.97 and sensitivity/specificity exceeding 90% across most arrhythmia classes. It demonstrated cardiologist-level performance, ranking first in balanced accuracy in a human-machine competition. External validation confirmed comparable performance. Individuals with false-positive AF detection had a significantly higher risk of new-onset AF (hazard ration [HR]: 1.69, 95% confidence interval [CI]: 1.11-2.59), HF (HR: 1.73, 95% CI: 1.20-2.51), and mortality (HR: 1.40, 95% CI: 1.02-1.92) compared to true-negative individuals after adjusting for age and sex. We developed an accurate DLM capable of detecting 23 cardiac arrhythmias across multiple datasets. This DLM serves as a valuable screening tool to aid physicians in identifying high-risk patients, with potential implications for early intervention and risk stratification.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"51"},"PeriodicalIF":3.5,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144007799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Letter to the Editor of the Journal of Medical Systems: Regarding \"Evaluation of the Performance of Three Large Language Models in Clinical Decision Support: A Comparative Study Based on Actual Cases\".","authors":"Jinze Li, Zhuojun Li, Fengzeng Jian","doi":"10.1007/s10916-025-02184-1","DOIUrl":"https://doi.org/10.1007/s10916-025-02184-1","url":null,"abstract":"","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"50"},"PeriodicalIF":3.5,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144021552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The AI Efficiency Paradox: Reclaiming Quality Patient Care in an Era of Optimization.","authors":"Julian Michael Burwell","doi":"10.1007/s10916-025-02183-2","DOIUrl":"https://doi.org/10.1007/s10916-025-02183-2","url":null,"abstract":"<p><p>We examine how artificial intelligence (AI) integration in healthcare may create an \"efficiency paradox\" where technologies designed to reduce workload can instead generate new layers of inefficiency. We argue that AI implementation strategies prioritizing efficiency metrics over meaningful patient interactions risk undermining care quality. A framework is proposed for evaluating AI adoption that balances technological optimization with perseveration of the physician-patient relationship.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"49"},"PeriodicalIF":3.5,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143970281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimating 90th Percentile Times To Complete Multiple Pre-Operative Regional Anesthesia Procedures To Mitigate First-Case Start Operating Room Delays Caused by the Nerve Blocks.","authors":"Franklin Dexter, Richard H Epstein, Rakesh V Sondekoppam, Anil A Marian","doi":"10.1007/s10916-025-02179-y","DOIUrl":"https://doi.org/10.1007/s10916-025-02179-y","url":null,"abstract":"<p><p>When multiple patients are scheduled to receive regional blocks as part of their anesthetic, planning insufficient preoperative time can cause first-case operating room delays. Prediction of the time to perform multiple regional blocks depends on the probability distributions (e.g., 90th percentiles) of the procedure completion times. We tested hypotheses that, if supported, can be applied for planning how early regional blocks should start to mitigate late first-case of the day starts. The retrospective cohort study used data from two academic hospital surgical suites for all regional anesthetic procedures performed before the adult patients entered the operating room for a first-case of the day. Days with more total minutes of regional procedures had greater total lateness (negative if early) and tardiness (zero if early) of first-case starts for both suites (all four Bonferroni adjusted P < 0.0001). Increases in the numbers of procedures per day were not associated with significant differences in the 0.5 quantile (median) among days of the time per procedure for both the inpatient surgical suite (unadjusted P = 0.46) and the ambulatory surgery center (P = 0.14). The result supported our hypothesis that average times add arithmetically among procedures. Increases in the numbers of procedures per day were associated with significant decreases in the 0.9 quantile among days of the time per procedure for both the inpatient surgical suite (-0.83 min per procedure, Bonferroni adjusted P < 0.0001) and the ambulatory surgery center (-0.90 min per procedure, adjusted P = 0.0002). Because both slopes were reliably negative, the result supported our second hypothesis that the longest time to plan to complete a series of procedures (represented by the 0.9 quantile) is considerably less than as calculated by taking the sum of the individual procedures' 0.9 quantiles. Quantile regression or an Excel 365 formula based on the log-normal distribution for block times can consequently be used to predict the time when anesthesiologists should start procedures and have a low risk of causing first-case start delays. For example, with 7 blocks, the sum of individual 0.9 quantiles would suggest that the anesthesiologist needs to start ≈35 min earlier than necessary based on the 0.9 quantile. Sufficient time can be planned to perform multiple procedures before the first-case of the day starts using quantile regression or an Excel formula. The estimated times are briefer than the sum of the 0.9 quantiles, but longer than the sum of the 0.5 quantiles.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"48"},"PeriodicalIF":3.5,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144030067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MLG2Net: Molecular Global Graph Network for Drug Response Prediction in Lung Cancer Cell Lines.","authors":"Thi-Oanh Tran, Thanh-Huy Nguyen, Tuan Tung Nguyen, Nguyen Quoc Khanh Le","doi":"10.1007/s10916-025-02182-3","DOIUrl":"https://doi.org/10.1007/s10916-025-02182-3","url":null,"abstract":"<p><p>Drug response prediction (DRP) is a central task in the era of precision medicine. Over the past decade, the emergence of deep learning (DL) has greatly contributed to addressing DRP challenges. Notably, the prediction of DRP for cancer cell lines benefits significantly from data availability for model development. However, an effective predictive model is still challenging due to issues with data quality, high-dimensional data, and multi-omics data integration. In this study, we introduce MLG2Net, a deep-learning model inspired by graph neural networks designed to predict DRP in lung cancer cell lines based on pharmacogenomics data. Our model comprises two key components: drug SMILES described by local and global graph networks and cell line genomics are illustrated as a map. Our results show that MLG2Net outperforms three reference graph networks. MLG2Net performance reached a Pearson coefficient correlation ( <math> <mrow><mrow><mi>C</mi></mrow> <msub><mrow><mi>C</mi></mrow> <mrow><mi>p</mi></mrow> </msub> </mrow> </math> ) of 0.8616 and a root mean square error (RMSE) of 2.94e-6 in predicting drug responses for Lung Adenocarcinoma (LUAD) cell lines. Subsequent testing on the Lung Squamous Cell Carcinoma (LUSC) dataset reveals lower performance ( <math> <mrow><mrow><mi>C</mi></mrow> <msub><mrow><mi>C</mi></mrow> <mrow><mi>p</mi></mrow> </msub> </mrow> </math> : 0.7999, RMSE: 4.08e-6), attributed to the dataset's smaller size influencing model capacity. Moreover, we assessed the model's architecture by isolating its components, with results indicating that the global network is particularly effective in this task. In conclusion, MLG2Net exhibited promising applications in DRP for cancer cell lines, with potential advancements by incorporating larger datasets.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"47"},"PeriodicalIF":3.5,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144015763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Personalized Health Prediction AI Models Using Transfer Learning and Strategic Overfitting on Wearable Device Data.","authors":"Inyong Jeong, Seokjin Kong, Yeongmin Kim, Yihyun Kim, Byeongsu Kim, Se-Jin Ahn, Ju-Wan Kim, Hwamin Lee","doi":"10.1007/s10916-025-02180-5","DOIUrl":"https://doi.org/10.1007/s10916-025-02180-5","url":null,"abstract":"<p><p>The increasing availability of wearable device data provides an opportunity for developing personalized models for health monitoring and condition prediction. Unlike conventional approaches that rely on pooled data from diverse individuals, our study explores the strategy of intentionally overfitting models to personal data and subsequently applying a transfer learning technique to refine performance for each user. We predicted Next-Day Condition (NDC) and Next-Day Emotion (NDC) while considering diverse features such as physical activity, sleep patterns, environmental context, and self-reported measures. Initial experiments showed that models trained at the sample level performed better on evaluation data but failed to generalize effectively during external validation. In contrast, our personalized learning approach, initiated with a pre-trained model, significantly enhanced accuracy within ten days of incremental user-specific training. Although generalization across the entire cohort diminished after individual tailoring, extended individualized training increased the overall predictive accuracy for each participant's personal data. The interpretation of feature importance using Shapley's additive explanations revealed substantial variability in the features influencing predictions across individuals, emphasizing the need for tailored health models. These findings highlight the potential of combining intentional overfitting and transfer learning in constructing high-performance user-specific predictive models from wearable data. Future research should expand the number of participants, extend the training period, and refine these methods to bolster personalized digital health solutions.</p>","PeriodicalId":16338,"journal":{"name":"Journal of Medical Systems","volume":"49 1","pages":"45"},"PeriodicalIF":3.5,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143810761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}