International Journal of Medical Informatics最新文献_第9页

Ensemble machine learning for early mortality risk stratification in septic orthopedic trauma: an international cohort study 集成机器学习用于感染性骨科创伤早期死亡风险分层：一项国际队列研究

IF 4.1 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2025-12-23 DOI: 10.1016/j.ijmedinf.2025.106240

Jun Guo , Fan Xiong , Baisheng Sun , Mingxing Lei , Yong Qin

Background

Sepsis represents a life-threatening complication in severe orthopedic trauma, significantly increasing short-term mortality risk. Despite the clinical urgency for early prognosis assessment, current predictive tools remain inadequate. To address this gap, this study used a machine learning (ML)-based framework for mortality risk stratification in this high-risk population.

Methods

This retrospective cohort study established ML models to predict 30-day all-cause mortality in critically ill patients with orthopedic trauma and sepsis. Data from 2,060 eligible patients were extracted from the intensive care unit (ICU) of Beth Israel Deaconess Medical Center (2008–2019) in the United State and randomly split into training (80 %) and internal validation (20 %) sets. After handling missing data and addressing class imbalance, seven ML algorithms (including CatBoost [Categorical Boosting], RF [Random Forest], and SVM [Support Vector Machine]) were trained and optimized using 10-fold cross-validation. Model performance was assessed based on discrimination (AUC [Area Under the Curve], accuracy, F1-score), calibration (Brier score, calibration slope), and clinical utility. The top-performing models were further validated on an independent external Chinese cohort (n = 273, 2020–2024).

Results

The study cohort had a mean age of 62.8 years and a 30-day mortality rate of 19.9 % (410/2060). Non-survivors were significantly older, had a higher comorbidity burden, and more severe physiological derangements. The LASSO analysis identified 16 prognostic variables, with age, hematologic parameters (RDW, WBC), SOFA scores, hemodynamic measures (SBP), and antihypertensive therapy emerging as significant predictors. Among all models, the CatBoost algorithm demonstrated superior performance in the internal validation set, achieving the highest AUC (0.955), accuracy (0.884), and F1-score (0.878), along with excellent calibration (Brier score: 0.081). A soft voting ensemble model, integrating the top three algorithms (CatBoost, RF, SVM), was subsequently constructed. In external validation, this ensemble model generalized robustly, maintaining strong discrimination (AUC: 0.842, Accuracy: 0.737) and calibration (Brier score: 0.173), outperforming the standalone CatBoost model. SHapley Additive exPlanations analysis provided interpretable, individualized risk assessments.

Conclusions

This study trains, optimizes, and evaluates a high-performing ML-based prediction model for 30-day mortality in patients with critical orthopedic trauma and sepsis. The CatBoost model and the soft voting ensemble, particularly the latter, demonstrates strong generalizability and clinical utility, offering a potential tool for early risk stratification and personalized management in this vulnerable population.

脓毒症是严重骨科创伤中一种危及生命的并发症，显著增加短期死亡风险。尽管临床迫切需要早期预后评估，但目前的预测工具仍然不足。为了解决这一差距，本研究在这一高危人群中使用了基于机器学习（ML）的死亡率风险分层框架。方法回顾性队列研究建立ML模型，预测骨科创伤合并脓毒症危重患者30天全因死亡率。从美国贝斯以色列女执事医疗中心（Beth Israel Deaconess Medical Center）重症监护室（ICU）提取2060例符合条件的患者数据（2008-2019），随机分为训练组（80%）和内部验证组（20%）。在处理缺失数据和解决类不平衡问题后，使用10倍交叉验证对七种ML算法（包括CatBoost [Categorical Boosting]， RF [Random Forest]和SVM [Support Vector Machine]）进行了训练和优化。模型性能评估基于鉴别（AUC[曲线下面积]，准确性，f1评分），校准（Brier评分，校准斜率）和临床实用性。在一个独立的外部中国队列（n = 273, 2020-2024）上进一步验证了表现最好的模型。结果研究队列的平均年龄为62.8岁，30天死亡率为19.9%（410/2060）。非幸存者明显更老，有更高的合并症负担，更严重的生理紊乱。LASSO分析确定了16个预后变量，其中年龄、血液学参数（RDW、WBC）、SOFA评分、血流动力学测量（SBP）和抗高血压治疗成为重要的预测因素。在所有模型中，CatBoost算法在内部验证集中表现优异，AUC（0.955）、准确率（0.884）和f1评分（0.878）最高，校准效果也很好（Brier评分：0.081）。随后构建了一个软投票集成模型，该模型集成了前三种算法（CatBoost、RF、SVM）。在外部验证中，该集成模型具有鲁棒性泛化，保持了较强的判别性（AUC: 0.842，准确度：0.737）和校准性（Brier评分：0.173），优于独立的CatBoost模型。SHapley加性解释分析提供了可解释的、个性化的风险评估。本研究训练、优化并评估了一种高性能的基于ml的骨科创伤和脓毒症患者30天死亡率预测模型。CatBoost模型和软投票集合，特别是后者，显示出很强的通用性和临床实用性，为这一弱势群体的早期风险分层和个性化管理提供了潜在的工具。

{"title":"Ensemble machine learning for early mortality risk stratification in septic orthopedic trauma: an international cohort study","authors":"Jun Guo , Fan Xiong , Baisheng Sun , Mingxing Lei , Yong Qin","doi":"10.1016/j.ijmedinf.2025.106240","DOIUrl":"10.1016/j.ijmedinf.2025.106240","url":null,"abstract":"<div><h3>Background</h3><div>Sepsis represents a life-threatening complication in severe orthopedic trauma, significantly increasing short-term mortality risk. Despite the clinical urgency for early prognosis assessment, current predictive tools remain inadequate. To address this gap, this study used a machine learning (ML)-based framework for mortality risk stratification in this high-risk population.</div></div><div><h3>Methods</h3><div>This retrospective cohort study established ML models to predict 30-day all-cause mortality in critically ill patients with orthopedic trauma and sepsis. Data from 2,060 eligible patients were extracted from the intensive care unit (ICU) of Beth Israel Deaconess Medical Center (2008–2019) in the United State and randomly split into training (80 %) and internal validation (20 %) sets. After handling missing data and addressing class imbalance, seven ML algorithms (including CatBoost [Categorical Boosting], RF [Random Forest], and SVM [Support Vector Machine]) were trained and optimized using 10-fold cross-validation. Model performance was assessed based on discrimination (AUC [Area Under the Curve], accuracy, F1-score), calibration (Brier score, calibration slope), and clinical utility. The top-performing models were further validated on an independent external Chinese cohort (n = 273, 2020–2024).</div></div><div><h3>Results</h3><div>The study cohort had a mean age of 62.8 years and a 30-day mortality rate of 19.9 % (410/2060). Non-survivors were significantly older, had a higher comorbidity burden, and more severe physiological derangements. The LASSO analysis identified 16 prognostic variables, with age, hematologic parameters (RDW, WBC), SOFA scores, hemodynamic measures (SBP), and antihypertensive therapy emerging as significant predictors. Among all models, the CatBoost algorithm demonstrated superior performance in the internal validation set, achieving the highest AUC (0.955), accuracy (0.884), and F1-score (0.878), along with excellent calibration (Brier score: 0.081). A soft voting ensemble model, integrating the top three algorithms (CatBoost, RF, SVM), was subsequently constructed. In external validation, this ensemble model generalized robustly, maintaining strong discrimination (AUC: 0.842, Accuracy: 0.737) and calibration (Brier score: 0.173), outperforming the standalone CatBoost model. SHapley Additive exPlanations analysis provided interpretable, individualized risk assessments.</div></div><div><h3>Conclusions</h3><div>This study trains, optimizes, and evaluates a high-performing ML-based prediction model for 30-day mortality in patients with critical orthopedic trauma and sepsis. The CatBoost model and the soft voting ensemble, particularly the latter, demonstrates strong generalizability and clinical utility, offering a potential tool for early risk stratification and personalized management in this vulnerable population.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"208 ","pages":"Article 106240"},"PeriodicalIF":4.1,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A review of evaluation system for Internet hospitals 互联网医院评价体系述评。

IF 4.1 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2025-12-22 DOI: 10.1016/j.ijmedinf.2025.106234

Zheqing Li , Liyang Tang , Yin Li , Yuanyuan Dang , Lin Yao

Context

Internet hospitals have emerged as a digital innovation in healthcare, optimizing resource allocation and enhancing patient experience. They also support hierarchical diagnosis and treatment and contribute to the Healthy China initiative.

Objectives

To establish a comprehensive evaluation system to promote the sustainable development of Internet hospitals.

Methods

A systematic review of literature related to the evaluation of Internet-based healthcare services was conducted. Using Web of Science and CNKI as data sources, studies published between 2015 and 2024 were screened based on predefined criteria, focusing on high-quality journals and research reports. The selected literature was coded and analyzed across four dimensions: patient services, doctor services, management services, and information security.

Results

The final analysis included 34 papers, with 25 mentioning patient services indicators, 20 mentioning doctor services indicators, 18 mentioning medical services process management indicators, and 9 mentioning information security. This study identifies key evaluation indicators and examines their interrelationships, highlighting potential systemic risks from localized optimizations.

Conclusion

This review analyzed Internet hospital evaluation across patient services, doctor services, services management, and information security. While it highlights potential efficiency gains, it notes the lack of comprehensive indicators, limiting assessment and improvement. For sustainable development, a more comprehensive evaluation system should integrate multi-stakeholder perspectives (patients, doctors, institutions), address systemic risks from localized optimization, and incorporate coordinated policy considerations.

背景：互联网医院作为医疗领域的数字化创新，优化了资源配置，提升了患者体验。他们还支持分级诊疗，为“健康中国”倡议做出贡献。目的：建立促进互联网医院可持续发展的综合评价体系。方法：系统回顾与互联网医疗服务评价相关的文献。以Web of Science和CNKI为数据来源，根据预先设定的标准筛选2015 - 2024年间发表的研究，重点筛选高质量的期刊和研究报告。对选定的文献进行编码，并从四个方面进行分析：患者服务、医生服务、管理服务和信息安全。结果：最终分析共纳入34篇论文，其中患者服务指标25篇，医生服务指标20篇，医疗服务流程管理指标18篇，信息安全9篇。本研究确定了关键的评估指标，并检查了它们之间的相互关系，突出了局部优化带来的潜在系统性风险。结论：本综述分析了互联网医院在患者服务、医生服务、服务管理和信息安全方面的评价。虽然它强调了潜在的效率提高，但它指出缺乏全面的指标，限制了评估和改进。为了实现可持续发展，更全面的评价体系应该整合多方利益相关者（患者、医生、机构）的视角，从局部优化中解决系统性风险，并纳入协调一致的政策考虑。

{"title":"A review of evaluation system for Internet hospitals","authors":"Zheqing Li , Liyang Tang , Yin Li , Yuanyuan Dang , Lin Yao","doi":"10.1016/j.ijmedinf.2025.106234","DOIUrl":"10.1016/j.ijmedinf.2025.106234","url":null,"abstract":"<div><h3>Context</h3><div>Internet hospitals have emerged as a digital innovation in healthcare, optimizing resource allocation and enhancing patient experience. They also support hierarchical diagnosis and treatment and contribute to the Healthy China initiative.</div></div><div><h3>Objectives</h3><div>To establish a comprehensive evaluation system to promote the sustainable development of Internet hospitals.</div></div><div><h3>Methods</h3><div>A systematic review of literature related to the evaluation of Internet-based healthcare services was conducted. Using Web of Science and CNKI as data sources, studies published between 2015 and 2024 were screened based on predefined criteria, focusing on high-quality journals and research reports. The selected literature was coded and analyzed across four dimensions: patient services, doctor services, management services, and information security.</div></div><div><h3>Results</h3><div>The final analysis included 34 papers, with 25 mentioning patient services indicators, 20 mentioning doctor services indicators, 18 mentioning medical services process management indicators, and 9 mentioning information security. This study identifies key evaluation indicators and examines their interrelationships, highlighting potential systemic risks from localized optimizations.</div></div><div><h3>Conclusion</h3><div>This review analyzed Internet hospital evaluation across patient services, doctor services, services management, and information security. While it highlights potential efficiency gains, it notes the lack of comprehensive indicators, limiting assessment and improvement. For sustainable development, a more comprehensive evaluation system should integrate multi-stakeholder perspectives (patients, doctors, institutions), address systemic risks from localized optimization, and incorporate coordinated policy considerations.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"209 ","pages":"Article 106234"},"PeriodicalIF":4.1,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145913911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advancing healthcare with large language models: A scoping review of applications and future directions 使用大型语言模型推进医疗保健：对应用程序和未来方向的范围审查。

IF 4.1 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2025-12-22 DOI: 10.1016/j.ijmedinf.2025.106231

Zhihong Zhang , Mohamad Javad Momeni Nezhad , Seyed Mohammad Bagher Hosseini , Ali Zolnour , Zahra Zonour , Seyedeh Mahdis Hosseini , Maxim Topaz , Maryam Zolnoori

Background

The release of ChatGPT has spurred the widespread adoption of generative large language models (LLMs) in healthcare. This scoping review systematically examines their use in healthcare.

Methods

A systematic search was conducted using PubMed, a comprehensive and representative database on biomedical and health science, to identify studies published between January 1, 2023, and July 30, 2024. Studies were included if they assessed the performance of generative LLMs in healthcare applications; review or perspective articles were excluded.

Results

A total of 415 studies were included, with a significant increase in publications observed after April 2023. Generative LLMs were applied across various medical specialties, primarily supporting clinical decision-making (26.7%) and providing patient information (23.9%). Smaller proportions were focused on professional education and training (18.1%), research (16.1%), and workflow support (12.5%). These applications were mainly supported by three key NLP tasks: question answering (36.1%), text classification (27.5%), and text generation (26.3%). Public datasets appeared in 20% of studies, and 15% used clinical patient data. Of the 98 LLMs used, GPT-4 (51.3%), GPT-3.5 (36.6%), and ChatGPT (22.4%) were the most common. Direct prompting was the most common adaptation method (92.5%), with reinforcement learning rarely utilized (1.4%). Accuracy was the most frequently assessed metric, while errors and safety (9.4%) and time efficiency (7.0%) were less commonly evaluated.

Conclusion

LLMs hold promise across healthcare applications. Expanding their use in workflow optimization, trainee education, and research tools could enhance healthcare delivery and innovation. Comprehensive evaluation using standardized criteria is essential for LLMs integration into healthcare.

背景：ChatGPT的发布促进了生成式大型语言模型（llm）在医疗保健领域的广泛采用。本综述系统地考察了它们在医疗保健中的应用。方法：系统检索具有代表性的综合性生物医学与健康科学数据库PubMed，检索2023年1月1日至2024年7月30日期间发表的研究。如果研究评估生成法学硕士在医疗保健应用中的表现，则纳入研究；综述或透视文章被排除在外。结果：共纳入415项研究，在2023年4月之后观察到的出版物显著增加。生成法学硕士应用于不同的医学专业，主要是支持临床决策（26.7%）和提供患者信息（23.9%）。较小的比例集中在专业教育和培训（18.1%），研究（16.1%）和工作流程支持（12.5%）。这些应用主要由三个关键的NLP任务支持：问答（36.1%）、文本分类（27.5%）和文本生成（26.3%）。20%的研究使用了公共数据集，15%的研究使用了临床患者数据。在使用的98个llm中，最常见的是GPT-4（51.3%）、GPT-3.5（36.6%）和ChatGPT（22.4%）。直接提示是最常见的适应方法（92.5%），强化学习很少使用（1.4%）。准确性是最常被评估的指标，而错误和安全性（9.4%）以及时间效率（7.0%）则不常被评估。结论：llm在医疗保健应用中具有前景。扩大它们在工作流程优化、培训生教育和研究工具中的应用，可以增强医疗保健服务和创新。使用标准化标准的综合评估对于法学硕士融入医疗保健至关重要。

{"title":"Advancing healthcare with large language models: A scoping review of applications and future directions","authors":"Zhihong Zhang , Mohamad Javad Momeni Nezhad , Seyed Mohammad Bagher Hosseini , Ali Zolnour , Zahra Zonour , Seyedeh Mahdis Hosseini , Maxim Topaz , Maryam Zolnoori","doi":"10.1016/j.ijmedinf.2025.106231","DOIUrl":"10.1016/j.ijmedinf.2025.106231","url":null,"abstract":"<div><h3>Background</h3><div>The release of ChatGPT has spurred the widespread adoption of generative large language models (LLMs) in healthcare. This scoping review systematically examines their use in healthcare.</div></div><div><h3>Methods</h3><div>A systematic search was conducted using PubMed, a comprehensive and representative database on biomedical and health science, to identify studies published between January 1, 2023, and July 30, 2024. Studies were included if they assessed the performance of generative LLMs in healthcare applications; review or perspective articles were excluded.</div></div><div><h3>Results</h3><div>A total of 415 studies were included, with a significant increase in publications observed after April 2023. Generative LLMs were applied across various medical specialties, primarily supporting clinical decision-making (26.7%) and providing patient information (23.9%). Smaller proportions were focused on professional education and training (18.1%), research (16.1%), and workflow support (12.5%). These applications were mainly supported by three key NLP tasks: question answering (36.1%), text classification (27.5%), and text generation (26.3%). Public datasets appeared in 20% of studies, and 15% used clinical patient data. Of the 98 LLMs used, GPT-4 (51.3%), GPT-3.5 (36.6%), and ChatGPT (22.4%) were the most common. Direct prompting was the most common adaptation method (92.5%), with reinforcement learning rarely utilized (1.4%). Accuracy was the most frequently assessed metric, while errors and safety (9.4%) and time efficiency (7.0%) were less commonly evaluated.</div></div><div><h3>Conclusion</h3><div>LLMs hold promise across healthcare applications. Expanding their use in workflow optimization, trainee education, and research tools could enhance healthcare delivery and innovation. Comprehensive evaluation using standardized criteria is essential for LLMs integration into healthcare.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"208 ","pages":"Article 106231"},"PeriodicalIF":4.1,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145829162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A clinical-AI correlation for integrating artificial intelligence into stroke care: a systematized literature review and practice framework 将人工智能整合到中风治疗中的临床与人工智能的相关性：系统化的文献综述和实践框架。

IF 4.1 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2025-12-21 DOI: 10.1016/j.ijmedinf.2025.106233

João Brainer Clares de Andrade , Thiago S. Carneiro , George N. Nunes Mendes , Joao Pedro Nardari dos Santos , Jussie Correia Lima

Background and purpose

The rapid integration of artificial intelligence (AI) into stroke care has outpaced many clinicians’ ability to critically evaluate and safely implement these tools. We conducted a systematized literature review and developed a practical framework to guide neurologists in the responsible integration of AI into stroke practice.

Methods

We performed a systematized review of PubMed, EMBASE, and gray literature (January 2018-June 2025) following adapted PRISMA guidelines. Search strategies combined AI-related terms with stroke care concepts. We assessed risk of bias using QUADAS-2, RoB 2, and ROBINS-I tools. Expert consultation with stroke neurologists and AI developers informed framework development.

Results

From 8,635 identified records, 152 studies met inclusion criteria (47 in quantitative synthesis). AI applications spanned large vessel occlusion detection (30 %), ASPECTS scoring (21 %), outcome prediction (18 %), hemorrhage detection (15 %), and treatment selection (16 %). Only 23% of studies showed low risk of bias, with main concerns including selection bias (29 %), confounding (38 %), and limited external validation (8 % prospective validation). The Clinical-AI Correlation Framework emphasizes three pillars: (1) problem identification and tool selection, (2) clinical correlation using Bayesian reasoning and topographic pattern recognition, and (3) continuous feedback and quality improvement.

Conclusions

Safe AI integration in stroke care requires structured clinical correlation, robust governance frameworks, and continuous monitoring. Our framework provides practical guidance for maintaining clinical judgment while leveraging AI capabilities, emphasizing human oversight for high-risk decisions and systematic documentation of AI-clinician interactions.

背景和目的：人工智能（AI）与中风治疗的快速整合已经超过了许多临床医生批判性评估和安全实施这些工具的能力。我们进行了系统的文献综述，并制定了一个实用框架，以指导神经科医生负责地将人工智能整合到中风实践中。方法：我们根据改编的PRISMA指南，对PubMed、EMBASE和灰色文献（2018年1月至2025年6月）进行了系统回顾。将人工智能相关术语与中风护理概念相结合的搜索策略。我们使用QUADAS-2、rob2和ROBINS-I工具评估偏倚风险。与中风神经科医生和人工智能开发人员的专家咨询为框架的开发提供了信息。结果：在8635份确定的记录中，152项研究符合纳入标准（47项为定量综合）。人工智能的应用范围包括大血管闭塞检测（30%）、ASPECTS评分（21%）、结果预测（18%）、出血检测（15%）和治疗选择（16%）。只有23%的研究显示低偏倚风险，主要问题包括选择偏倚（29%）、混淆（38%）和有限的外部验证（8%的前瞻性验证）。临床-人工智能相关框架强调三个支柱：(1)问题识别和工具选择；(2)使用贝叶斯推理和地形模式识别的临床相关性；(3)持续反馈和质量改进。结论：人工智能在卒中治疗中的安全整合需要结构化的临床相关性、健全的治理框架和持续监测。我们的框架为维持临床判断提供了实用指导，同时利用人工智能能力，强调人类对高风险决策的监督，并系统地记录人工智能与临床医生的互动。

{"title":"A clinical-AI correlation for integrating artificial intelligence into stroke care: a systematized literature review and practice framework","authors":"João Brainer Clares de Andrade , Thiago S. Carneiro , George N. Nunes Mendes , Joao Pedro Nardari dos Santos , Jussie Correia Lima","doi":"10.1016/j.ijmedinf.2025.106233","DOIUrl":"10.1016/j.ijmedinf.2025.106233","url":null,"abstract":"<div><h3>Background and purpose</h3><div>The rapid integration of artificial intelligence (AI) into stroke care has outpaced many clinicians’ ability to critically evaluate and safely implement these tools. We conducted a systematized literature review and developed a practical framework to guide neurologists in the responsible integration of AI into stroke practice.</div></div><div><h3>Methods</h3><div>We performed a systematized review of PubMed, EMBASE, and gray literature (January 2018-June 2025) following adapted PRISMA guidelines. Search strategies combined AI-related terms with stroke care concepts. We assessed risk of bias using QUADAS-2, RoB 2, and ROBINS-I tools. Expert consultation with stroke neurologists and AI developers informed framework development.</div></div><div><h3>Results</h3><div>From 8,635 identified records, 152 studies met inclusion criteria (47 in quantitative synthesis). AI applications spanned large vessel occlusion detection (30 %), ASPECTS scoring (21 %), outcome prediction (18 %), hemorrhage detection (15 %), and treatment selection (16 %). Only 23% of studies showed low risk of bias, with main concerns including selection bias (29 %), confounding (38 %), and limited external validation (8 % prospective validation). The Clinical-AI Correlation Framework emphasizes three pillars: (1) problem identification and tool selection, (2) clinical correlation using Bayesian reasoning and topographic pattern recognition, and (3) continuous feedback and quality improvement.</div></div><div><h3>Conclusions</h3><div>Safe AI integration in stroke care requires structured clinical correlation, robust governance frameworks, and continuous monitoring. Our framework provides practical guidance for maintaining clinical judgment while leveraging AI capabilities, emphasizing human oversight for high-risk decisions and systematic documentation of AI-clinician interactions.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"208 ","pages":"Article 106233"},"PeriodicalIF":4.1,"publicationDate":"2025-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145821995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

De-identification of clinical data: A systematic review of free text, image and tabular data approaches 临床数据的去识别化：对自由文本、图像和表格数据方法的系统回顾

IF 4.1 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2025-12-19 DOI: 10.1016/j.ijmedinf.2025.106225

Pedro Faustini , Annabelle McIver , Ryan Sullivan , Mark Dras

Background: The digitisation of healthcare has generated vast amounts of data in various formats, including free-text notes, tabular records and medical images. This data is critical for research and innovation, but often contains sensitive information that must be de-identified to ensure patient privacy and regulatory compliance. Natural Language Processing (NLP) enables automated de-identification of sensitive information to safely share medical datasets.

Objective: This study aims to systematically review the literature on NLP-based de-identification techniques applied to free-text medical reports, tabular data, and burned-in text within medical images over the past decade. It seeks to identify state-of-the-art methods, analyse how de-identification tasks are assessed, and find existing gaps for future research.

Methods: We systematically searched five important databases (PubMed, Web of Science, DBLP, ACM and IEEE) for articles published from January 2015 to December 2024 (10 years) about de-identification of medical data in free text, tabular data and burned-in pixels in images. We filtered the articles based on their titles and abstracts against inclusion and exclusion criteria, followed by a quality filter.

Results: From a set of 734 papers, 83 articles were deemed relevant. Most studies de-identify free text, with a few working with tabular data and a much scarcer number dealing with text embedded in the pixels of the images.

Conclusions: De-identification techniques have evolved, with increased use of Language Models and a decline in recurrence-based neural networks. Off-the-shelf tools often require customisation for optimal performance. Most studies de-identify English content, supported by the prevalence of English datasets. Key challenges include the phenomenon of code-mixing (i.e., more than one language used in the same sentence) and the scarcity of available datasets for reproducibility.

背景：医疗保健的数字化产生了各种格式的大量数据，包括自由文本注释、表格记录和医学图像。这些数据对研究和创新至关重要，但通常包含必须去识别的敏感信息，以确保患者隐私和法规遵从性。自然语言处理（NLP）实现了敏感信息的自动去识别，以安全地共享医疗数据集。目的：本研究旨在系统回顾过去十年来基于nlp的去识别技术在医学图像中应用于自由文本医学报告、表格数据和烧入文本的文献。它试图确定最先进的方法，分析如何评估去识别任务，并为未来的研究找到现有的差距。方法：系统检索5个重要数据库（PubMed、Web of Science、DBLP、ACM和IEEE），检索2015年1月至2024年12月（10年）发表的关于自由文本、表格数据和图像中烧毁像素的医疗数据去识别的文章。我们根据标题和摘要对文章进行筛选，然后进行质量筛选。结果：在734篇论文中，83篇文章被认为是相关的。大多数研究都去识别自由文本，只有少数研究处理表格数据，而处理嵌入图像像素中的文本的研究则少得多。结论：随着语言模型的使用增加和基于递归的神经网络的减少，去识别技术已经发展。现成的工具通常需要定制以获得最佳性能。由于英语数据集的普及，大多数研究都去识别英语内容。主要的挑战包括代码混合现象（即，在同一个句子中使用多种语言）和缺乏可用于再现性的可用数据集。

{"title":"De-identification of clinical data: A systematic review of free text, image and tabular data approaches","authors":"Pedro Faustini , Annabelle McIver , Ryan Sullivan , Mark Dras","doi":"10.1016/j.ijmedinf.2025.106225","DOIUrl":"10.1016/j.ijmedinf.2025.106225","url":null,"abstract":"<div><div><em>Background:</em> The digitisation of healthcare has generated vast amounts of data in various formats, including free-text notes, tabular records and medical images. This data is critical for research and innovation, but often contains sensitive information that must be de-identified to ensure patient privacy and regulatory compliance. Natural Language Processing (NLP) enables automated de-identification of sensitive information to safely share medical datasets.</div><div><em>Objective:</em> This study aims to systematically review the literature on NLP-based de-identification techniques applied to free-text medical reports, tabular data, and burned-in text within medical images over the past decade. It seeks to identify state-of-the-art methods, analyse how de-identification tasks are assessed, and find existing gaps for future research.</div><div><em>Methods:</em> We systematically searched five important databases (PubMed, Web of Science, DBLP, ACM and IEEE) for articles published from January 2015 to December 2024 (10 years) about de-identification of medical data in free text, tabular data and burned-in pixels in images. We filtered the articles based on their titles and abstracts against inclusion and exclusion criteria, followed by a quality filter.</div><div><em>Results:</em> From a set of 734 papers, 83 articles were deemed relevant. Most studies de-identify free text, with a few working with tabular data and a much scarcer number dealing with text embedded in the pixels of the images.</div><div><em>Conclusions:</em> De-identification techniques have evolved, with increased use of Language Models and a decline in recurrence-based neural networks. Off-the-shelf tools often require customisation for optimal performance. Most studies de-identify English content, supported by the prevalence of English datasets. Key challenges include the phenomenon of code-mixing (i.e., more than one language used in the same sentence) and the scarcity of available datasets for reproducibility.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"208 ","pages":"Article 106225"},"PeriodicalIF":4.1,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The role of digital twin technology in modern emergency care 数字孪生技术在现代急救中的作用

IF 4.1 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2025-12-19 DOI: 10.1016/j.ijmedinf.2025.106229

David B. Olawade , Osazuwa Ighodaro , Emmanuel Oghenetejiri Erhieyovwe , Nebere Elias Hankamo , Ismail Tajudeen Hamza , Claret Chinenyenwa Analikwu

Background

Emergency care is operationally defined as time-critical acute care across pre-hospital services, emergency departments, and critical care units (excluding routine urgent care and elective admissions), demanding rapid decision-making under pressure. Digital twin technology, creating real-time virtual replicas through continuous data integration, represents a transformative shift in managing acute conditions, resource allocation, and outcome prediction in emergency medicine.

Aim

This review examines the current applications, benefits, challenges, and future directions of digital twin technology in emergency care and medicine, highlighting its potential to revolutionise emergency healthcare delivery.

Method

A comprehensive narrative literature review was conducted using PubMed, IEEE Xplore, Scopus, and Web of Science databases. Studies published between January 2015 and June 2025 focusing on digital twin applications in emergency departments, trauma care, critical care, and prehospital emergency services were included. Grey literature, conference proceedings, and technical reports were also reviewed to capture emerging developments.

Results

Digital twins demonstrate significant utility across multiple emergency care domains including patient monitoring, resource allocation, workflow optimisation, predictive analytics, and training simulations. Key applications include real time patient condition prediction, emergency department capacity management, trauma response coordination, and personalised treatment planning. Despite promising outcomes, implementation challenges persist, including data integration complexities, computational requirements, and regulatory considerations.

Conclusion

Digital twin technology holds substantial promise for enhancing emergency care delivery through improved decision support, resource optimisation, and predictive capabilities. Continued research, standardisation efforts, and interdisciplinary collaboration are essential for successful clinical integration and widespread adoption.

急诊护理在操作上被定义为院前服务、急诊科和重症监护病房（不包括常规急诊护理和选择性住院）的时间紧迫的急性护理，要求在压力下快速决策。数字孪生技术通过持续的数据集成创建实时虚拟副本，代表了急诊医学在急症管理、资源分配和结果预测方面的革命性转变。本综述探讨了数字孪生技术在急诊护理和医学中的当前应用、益处、挑战和未来方向，强调了其革命性的急诊医疗服务的潜力。方法采用PubMed、IEEE explore、Scopus、Web of Science等数据库进行综合叙述性文献综述。2015年1月至2025年6月期间发表的研究重点是数字双胞胎在急诊科、创伤护理、重症监护和院前急救服务中的应用。还审查了灰色文献、会议记录和技术报告，以捕捉新的发展。结果数字孪生在多个急诊护理领域展示了重要的实用性，包括患者监测、资源分配、工作流程优化、预测分析和培训模拟。主要应用包括实时患者病情预测、急诊科能力管理、创伤反应协调和个性化治疗计划。尽管取得了可喜的成果，但实施方面的挑战依然存在，包括数据集成的复杂性、计算需求和监管方面的考虑。结论数字孪生技术通过改进决策支持、资源优化和预测能力，在加强急诊护理服务方面具有重要前景。持续的研究、标准化工作和跨学科合作对于成功的临床整合和广泛采用至关重要。

{"title":"The role of digital twin technology in modern emergency care","authors":"David B. Olawade , Osazuwa Ighodaro , Emmanuel Oghenetejiri Erhieyovwe , Nebere Elias Hankamo , Ismail Tajudeen Hamza , Claret Chinenyenwa Analikwu","doi":"10.1016/j.ijmedinf.2025.106229","DOIUrl":"10.1016/j.ijmedinf.2025.106229","url":null,"abstract":"<div><h3>Background</h3><div>Emergency care is operationally defined as time-critical acute care across pre-hospital services, emergency departments, and critical care units (excluding routine urgent care and elective admissions), demanding rapid decision-making under pressure. Digital twin technology, creating real-time virtual replicas through continuous data integration, represents a transformative shift in managing acute conditions, resource allocation, and outcome prediction in emergency medicine.</div></div><div><h3>Aim</h3><div>This review examines the current applications, benefits, challenges, and future directions of digital twin technology in emergency care and medicine, highlighting its potential to revolutionise emergency healthcare delivery.</div></div><div><h3>Method</h3><div>A comprehensive narrative literature review was conducted using PubMed, IEEE Xplore, Scopus, and Web of Science databases. Studies published between January 2015 and June 2025 focusing on digital twin applications in emergency departments, trauma care, critical care, and prehospital emergency services were included. Grey literature, conference proceedings, and technical reports were also reviewed to capture emerging developments.</div></div><div><h3>Results</h3><div>Digital twins demonstrate significant utility across multiple emergency care domains including patient monitoring, resource allocation, workflow optimisation, predictive analytics, and training simulations. Key applications include real time patient condition prediction, emergency department capacity management, trauma response coordination, and personalised treatment planning. Despite promising outcomes, implementation challenges persist, including data integration complexities, computational requirements, and regulatory considerations.</div></div><div><h3>Conclusion</h3><div>Digital twin technology holds substantial promise for enhancing emergency care delivery through improved decision support, resource optimisation, and predictive capabilities. Continued research, standardisation efforts, and interdisciplinary collaboration are essential for successful clinical integration and widespread adoption.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"208 ","pages":"Article 106229"},"PeriodicalIF":4.1,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145799857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comment on “Medication-based mortality prediction in COPD using machine learning and conventional statistical methods” 对“利用机器学习和传统统计方法预测COPD药物死亡率”的评论

IF 4.1 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2025-12-19 DOI: 10.1016/j.ijmedinf.2025.106228

Siyi Liu , Zekai Yu

引用次数: 0

Efficient medical NER with limited data: Enhancing LLM performance through annotation guidelines 有限数据的高效医疗NER：通过注释指南增强LLM性能。

IF 4.1 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2025-12-18 DOI: 10.1016/j.ijmedinf.2025.106230

Emiko Shinohara, Yoshimasa Kawazoe

Background

Named entity recognition (NER) is critical in natural language processing (NLP), particularly in the medical field, where accurate identification of entities, such as patient information and clinical events, is essential. Traditional NER approaches rely heavily on large, annotated corpora, which are resource intensive. Large language models (LLMs) offer new NER approaches, particularly through in-context and few-shot learning.

Objective

This study investigates the effects of incorporating annotation guidelines into prompts for NER via LLMs, with a specific focus on their impact on few-shot learning performance across various medical corpora.

Methods

We designed eight different prompt patterns, combining few-shot examples with annotation guidelines of varying complexity, and evaluated their performance via three prominent LLMs: GPT-4o, Claude 3.5 Sonnet, and gpt-oss-120b. Additionally, we employed three diverse medical corpora: i2b2-2014, i2b2-2012, and MedTxt-CR. Accuracy was assessed via precision, recall, and the F1 score, with evaluation methods aligned with those used in relevant shared tasks to ensure the comparability of the results.

Results

Our findings indicate that adding detailed annotation guidelines to few-shot prompts improves the recall and F1 score in most cases.

Conclusion

Including annotation guidelines in prompts enhances the performance of LLMs in NER tasks, making this a practical approach for developing accurate NLP systems in resource-constrained environments. Although annotation guidelines are essential for evaluation and example creation, their integration into LLM prompts can further optimize few-shot learning, especially within specialized domains such as medical NLP.

背景：命名实体识别（NER）在自然语言处理（NLP）中至关重要，特别是在医学领域，准确识别实体（如患者信息和临床事件）至关重要。传统的NER方法严重依赖于大型的、带注释的语料库，这是资源密集型的。大型语言模型（llm）提供了新的NER方法，特别是通过上下文学习和少镜头学习。目的：本研究探讨了通过llm将注释指南纳入NER提示的效果，并特别关注了它们对跨各种医学语料库的少射学习性能的影响。方法：我们设计了8种不同的提示模式，结合了不同复杂性的注释指南，并通过三个著名的llm: gpt- 40、Claude 3.5 Sonnet和gpt- ss-120b来评估它们的性能。此外，我们还采用了三种不同的医疗资料库：i2b2-2014、i2b2-2012和MedTxt-CR。准确性通过精密度、召回率和F1分数来评估，评估方法与相关共享任务中使用的方法一致，以确保结果的可比性。结果：我们的研究结果表明，在大多数情况下，为少量提示添加详细的注释指南可以提高召回率和F1分数。结论：在提示中包含注释指南可以增强llm在NER任务中的性能，使其成为在资源受限环境中开发准确的NLP系统的实用方法。尽管注释指南对于评估和示例创建至关重要，但将它们集成到LLM提示中可以进一步优化少量学习，特别是在医疗NLP等专业领域中。

{"title":"Efficient medical NER with limited data: Enhancing LLM performance through annotation guidelines","authors":"Emiko Shinohara, Yoshimasa Kawazoe","doi":"10.1016/j.ijmedinf.2025.106230","DOIUrl":"10.1016/j.ijmedinf.2025.106230","url":null,"abstract":"<div><h3>Background</h3><div>Named entity recognition (NER) is critical in natural language processing (NLP), particularly in the medical field, where accurate identification of entities, such as patient information and clinical events, is essential. Traditional NER approaches rely heavily on large, annotated corpora, which are resource intensive. Large language models (LLMs) offer new NER approaches, particularly through in-context and few-shot learning.</div></div><div><h3>Objective</h3><div>This study investigates the effects of incorporating annotation guidelines into prompts for NER via LLMs, with a specific focus on their impact on few-shot learning performance across various medical corpora.</div></div><div><h3>Methods</h3><div>We designed eight different prompt patterns, combining few-shot examples with annotation guidelines of varying complexity, and evaluated their performance via three prominent LLMs: GPT-4o, Claude 3.5 Sonnet, and gpt-oss-120b. Additionally, we employed three diverse medical corpora: i2b2-2014, i2b2-2012, and MedTxt-CR. Accuracy was assessed via precision, recall, and the F1 score, with evaluation methods aligned with those used in relevant shared tasks to ensure the comparability of the results.</div></div><div><h3>Results</h3><div>Our findings indicate that adding detailed annotation guidelines to few-shot prompts improves the recall and F1 score in most cases.</div></div><div><h3>Conclusion</h3><div>Including annotation guidelines in prompts enhances the performance of LLMs in NER tasks, making this a practical approach for developing accurate NLP systems in resource-constrained environments. Although annotation guidelines are essential for evaluation and example creation, their integration into LLM prompts can further optimize few-shot learning, especially within specialized domains such as medical NLP.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"208 ","pages":"Article 106230"},"PeriodicalIF":4.1,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145821980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development and validation of a bleeding risk model for off-pump coronary artery bypass grafting: a multi-center retrospective cohort study 非体外循环冠状动脉旁路移植术出血风险模型的建立和验证：一项多中心回顾性队列研究

IF 4.1 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2025-12-16 DOI: 10.1016/j.ijmedinf.2025.106226

Zi Wang , Runhua Ma , Qiming Wang , Fan Yang , Xiaotong Xia , Xiaoyu Li , Qing Xu , Yao yao , Hongyi Wu , Chunsheng Wang , Qianzhou Lv

Background

Perioperative bleeding is a major challenge in coronary artery bypass grafting (CABG). Existing bleeding risk models often lack specificity for off-pump CABG (OPCABG) patients.

Objective

This study aims to develop and validate a novel perioperative bleeding prediction model tailored for OPCABG patients.

Methods

This retrospective, multi-center cohort study was conducted using both internal and external validation cohorts. Fourteen different models, including Binary Logistic Regression, Random Forest, Decision Tree, Extra Trees, Adaptive Boosting, Extreme Gradient Boosting, Categorical Boosting, Gradient Boosting, Naive Bayes, Artificial Neural Network, Light Gradient Boosting Machine, K-nearest Neighbors, Support Vector Machine, and LogitBoost, were applied for model development. SHapley Additive exPlanations (SHAP) were used to interpret feature importance and the model’s outputs.

Results

The final model, CABG Bleeding Risk of 10 Variables (CABG-BR10), was built using Random Rorest. This model identified 10 key variables: antiplatelet drug discontinuation, N-terminal pro B-type natriuretic peptide, activated partial thromboplastin time, hemoglobin, urea, cardiac troponin T, estimated glomerular filtration rate, total bilirubin, fibrinogen, and international normalized ratio. In the internal and external validation cohorts, the model demonstrated solid performance with Receiver Operating Characteristic − Area Under the Curve values of 0.90 and 0.87, and Precision-Recall − Area Under the Curve values of 0.70 and 0.67, respectively. SHAP analysis identified key predictors of bleeding risk, and an online tool was developed to facilitate bleeding risk assessment.

Conclusion

The CABG-BR10 model accurately predicts perioperative bleeding risk in OPCABG patients, outperforming traditional scoring systems and providing interpretable, clinically relevant insights into bleeding risk factors.

背景：围手术期出血是冠状动脉旁路移植术（CABG）的主要挑战。现有的出血风险模型对非体外循环CABG （OPCABG）患者往往缺乏特异性。目的建立并验证一种适合OPCABG患者的围手术期出血预测模型。方法采用内部和外部验证队列进行回顾性、多中心队列研究。采用了二元逻辑回归、随机森林、决策树、额外树、自适应增强、极端梯度增强、分类增强、梯度增强、朴素贝叶斯、人工神经网络、轻梯度增强机、k近邻、支持向量机和LogitBoost等14种不同的模型进行模型开发。SHapley加性解释（SHAP）用于解释特征的重要性和模型的输出。结果采用随机抽样方法建立CABG- br10 （CABG- br10）模型。该模型确定了10个关键变量：抗血小板药物停药、n端前b型利钠肽、活化部分凝血活蛋白时间、血红蛋白、尿素、心肌肌钙蛋白T、估计肾小球滤过率、总胆红素、纤维蛋白原和国际标准化比率。在内部和外部验证队列中，该模型表现出良好的性能，接收者工作特征-曲线下面积值分别为0.90和0.87，精确召回率-曲线下面积值分别为0.70和0.67。SHAP分析确定了出血风险的关键预测因素，并开发了一个在线工具来促进出血风险评估。结论CABG-BR10模型可准确预测OPCABG患者围手术期出血风险，优于传统评分系统，为出血危险因素提供可解释的、临床相关的见解。

{"title":"Development and validation of a bleeding risk model for off-pump coronary artery bypass grafting: a multi-center retrospective cohort study","authors":"Zi Wang , Runhua Ma , Qiming Wang , Fan Yang , Xiaotong Xia , Xiaoyu Li , Qing Xu , Yao yao , Hongyi Wu , Chunsheng Wang , Qianzhou Lv","doi":"10.1016/j.ijmedinf.2025.106226","DOIUrl":"10.1016/j.ijmedinf.2025.106226","url":null,"abstract":"<div><h3>Background</h3><div>Perioperative bleeding is a major challenge in coronary artery bypass grafting (CABG). Existing bleeding risk models often lack specificity for off-pump CABG (OPCABG) patients.</div></div><div><h3>Objective</h3><div>This study aims to develop and validate a novel perioperative bleeding prediction model tailored for OPCABG patients.</div></div><div><h3>Methods</h3><div>This retrospective, multi-center cohort study was conducted using both internal and external validation cohorts. Fourteen different models, including Binary Logistic Regression, Random Forest, Decision Tree, Extra Trees, Adaptive Boosting, Extreme Gradient Boosting, Categorical Boosting, Gradient Boosting, Naive Bayes, Artificial Neural Network, Light Gradient Boosting Machine, K-nearest Neighbors, Support Vector Machine, and LogitBoost, were applied for model development. SHapley Additive exPlanations (SHAP) were used to interpret feature importance and the model’s outputs.</div></div><div><h3>Results</h3><div>The final model, CABG Bleeding Risk of 10 Variables (CABG-BR10), was built using Random Rorest. This model identified 10 key variables: antiplatelet drug discontinuation, N-terminal pro B-type natriuretic peptide, activated partial thromboplastin time, hemoglobin, urea, cardiac troponin T, estimated glomerular filtration rate, total bilirubin, fibrinogen, and international normalized ratio. In the internal and external validation cohorts, the model demonstrated solid performance with Receiver Operating Characteristic − Area Under the Curve values of 0.90 and 0.87, and Precision-Recall − Area Under the Curve values of 0.70 and 0.67, respectively. SHAP analysis identified key predictors of bleeding risk, and an online tool was developed to facilitate bleeding risk assessment.</div></div><div><h3>Conclusion</h3><div>The CABG-BR10 model accurately predicts perioperative bleeding risk in OPCABG patients, outperforming traditional scoring systems and providing interpretable, clinically relevant insights into bleeding risk factors.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"208 ","pages":"Article 106226"},"PeriodicalIF":4.1,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145799858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predictive modeling of hospital emergency department demand using artificial intelligence: A systematic review 基于人工智能的医院急诊科需求预测建模：系统综述。

IF 4.1 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2025-12-13 DOI: 10.1016/j.ijmedinf.2025.106215

Jorge Blanco , Marina Ferreras , Oscar Cosido

Background

Accurately forecasting patient arrivals in hospital emergency departments (EDs) is critical for hospital capacity and planning and clinical decision-making. Artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), has shown promising performance over traditional time series approaches. However, the extent to which these models are validated and generalizable remains uncertain.

Objective

To systematically review the literature on predictive models for hospital ED demand forecasting, focusing on algorithms used, internal and external variables, validation strategies and limitations pre- and post-pandemic developments.

Methods

A systematic literature review (SLR) was conducted following PRISMA guidelines. Five databases (PubMed, IEEE, Springer, ScienceDirect, ACM) were searched for peer-reviewed articles published between January 2019 and July 2025. Eligible studies applied predictive algorithms – excluding those focused on COVID-19 – to forecast ED visits. Extracted data included modeling approaches, feature types, evaluation metrics, and validation methods.

Results

Eleven studies met the inclusion criteria. Classical models such as ARIMA and SARIMA remain in use, but ML (e.g., XGBoost, Random Forest) and DL (e.g., LSTM, CNN) showed higher predictive accuracy, especially with high-dimensional, nonlinear data. Incorporating external variables—such as weather (temperature, humidity, wind), air quality, and calendar events—consistently improved performance. Common metrics included Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE), with MAPE ranging from 3 % to 18 %. Few studies performed external validation, and only a minority employed explainable AI methods (e.g., SHAP) to address interpretability.

Conclusions

AI-based models offer strong potential for ED demand forecasting, particularly when integrating environmental and temporal features. However, limited external validation and lack of interpretability remain significant barriers to clinical adoption. Future research should prioritize multicenter validation, standardized evaluation, and explainable AI to support reliable, transparent, and scalable use in hospital emergency departments.

背景：准确预测医院急诊科（EDs）的患者到达对医院容量、规划和临床决策至关重要。人工智能（AI），特别是机器学习（ML）和深度学习（DL），已经比传统的时间序列方法表现出了很好的表现。然而，这些模型被验证和推广的程度仍然不确定。目的：系统回顾有关医院急诊科需求预测预测模型的文献，重点关注所使用的算法、内部和外部变量、验证策略以及大流行前后发展的局限性。方法：根据PRISMA指南进行系统文献回顾（SLR）。五个数据库（PubMed， IEEE， b施普林格，ScienceDirect， ACM）检索了2019年1月至2025年7月之间发表的同行评议文章。符合条件的研究应用了预测算法（不包括那些关注COVID-19的研究）来预测急诊科就诊。提取的数据包括建模方法、特征类型、评估指标和验证方法。结果：11项研究符合纳入标准。经典模型如ARIMA和SARIMA仍在使用，但ML（如XGBoost、Random Forest）和DL（如LSTM、CNN）显示出更高的预测精度，特别是在高维、非线性数据下。结合外部变量—例如天气（温度、湿度、风）、空气质量和日历事件—可以持续提高性能。常用指标包括平均绝对误差（MAE）、均方根误差（RMSE）和平均绝对百分比误差（MAPE）， MAPE的范围从3%到18%。很少有研究进行外部验证，只有少数研究采用可解释的AI方法（例如，SHAP）来解决可解释性问题。结论：基于人工智能的模型为ED需求预测提供了强大的潜力，特别是在整合环境和时间特征时。然而，有限的外部验证和缺乏可解释性仍然是临床采用的重大障碍。未来的研究应优先考虑多中心验证、标准化评估和可解释的人工智能，以支持在医院急诊科可靠、透明和可扩展的使用。

{"title":"Predictive modeling of hospital emergency department demand using artificial intelligence: A systematic review","authors":"Jorge Blanco , Marina Ferreras , Oscar Cosido","doi":"10.1016/j.ijmedinf.2025.106215","DOIUrl":"10.1016/j.ijmedinf.2025.106215","url":null,"abstract":"<div><h3>Background</h3><div>Accurately forecasting patient arrivals in hospital emergency departments (EDs) is critical for hospital capacity and planning and clinical decision-making. Artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), has shown promising performance over traditional time series approaches. However, the extent to which these models are validated and generalizable remains uncertain.</div></div><div><h3>Objective</h3><div>To systematically review the literature on predictive models for hospital ED demand forecasting, focusing on algorithms used, internal and external variables, validation strategies and limitations pre- and post-pandemic developments.</div></div><div><h3>Methods</h3><div>A systematic literature review (SLR) was conducted following PRISMA guidelines. Five databases (PubMed, IEEE, Springer, ScienceDirect, ACM) were searched for peer-reviewed articles published between January 2019 and July 2025. Eligible studies applied predictive algorithms – excluding those focused on COVID-19 – to forecast ED visits. Extracted data included modeling approaches, feature types, evaluation metrics, and validation methods.</div></div><div><h3>Results</h3><div>Eleven studies met the inclusion criteria. Classical models such as ARIMA and SARIMA remain in use, but ML (e.g., XGBoost, Random Forest) and DL (e.g., LSTM, CNN) showed higher predictive accuracy, especially with high-dimensional, nonlinear data. Incorporating external variables—such as weather (temperature, humidity, wind), air quality, and calendar events—consistently improved performance. Common metrics included Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE), with MAPE ranging from 3 % to 18 %. Few studies performed external validation, and only a minority employed explainable AI methods (e.g., SHAP) to address interpretability.</div></div><div><h3>Conclusions</h3><div>AI-based models offer strong potential for ED demand forecasting, particularly when integrating environmental and temporal features. However, limited external validation and lack of interpretability remain significant barriers to clinical adoption. Future research should prioritize multicenter validation, standardized evaluation, and explainable AI to support reliable, transparent, and scalable use in hospital emergency departments.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"207 ","pages":"Article 106215"},"PeriodicalIF":4.1,"publicationDate":"2025-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145769787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0