JMIR Medical Informatics最新文献

{"title":"Prediction of In-Hospital Cardiac Arrest in the Intensive Care Unit: Machine Learning-Based Multimodal Approach.","authors":"Hsin-Ying Lee, Po-Chih Kuo, Frank Qian, Chien-Hung Li, Jiun-Ruey Hu, Wan-Ting Hsu, Hong-Jie Jhou, Po-Huang Chen, Cho-Hao Lee, Chin-Hua Su, Po-Chun Liao, I-Ju Wu, Chien-Chang Lee","doi":"10.2196/49142","DOIUrl":"10.2196/49142","url":null,"abstract":"<p><strong>Background: </strong>Early identification of impending in-hospital cardiac arrest (IHCA) improves clinical outcomes but remains elusive for practicing clinicians.</p><p><strong>Objective: </strong>We aimed to develop a multimodal machine learning algorithm based on ensemble techniques to predict the occurrence of IHCA.</p><p><strong>Methods: </strong>Our model was developed by the Multiparameter Intelligent Monitoring of Intensive Care (MIMIC)-IV database and validated in the Electronic Intensive Care Unit Collaborative Research Database (eICU-CRD). Baseline features consisting of patient demographics, presenting illness, and comorbidities were collected to train a random forest model. Next, vital signs were extracted to train a long short-term memory model. A support vector machine algorithm then stacked the results to form the final prediction model.</p><p><strong>Results: </strong>Of 23,909 patients in the MIMIC-IV database and 10,049 patients in the eICU-CRD database, 452 and 85 patients, respectively, had IHCA. At 13 hours in advance of an IHCA event, our algorithm had already demonstrated an area under the receiver operating characteristic curve of 0.85 (95% CI 0.815-0.885) in the MIMIC-IV database. External validation with the eICU-CRD and National Taiwan University Hospital databases also presented satisfactory results, showing area under the receiver operating characteristic curve values of 0.81 (95% CI 0.763-0.851) and 0.945 (95% CI 0.934-0.956), respectively.</p><p><strong>Conclusions: </strong>Using only vital signs and information available in the electronic medical record, our model demonstrates it is possible to detect a trajectory of clinical deterioration up to 13 hours in advance. This predictive tool, which has undergone external validation, could forewarn and help clinicians identify patients in need of assessment to improve their overall prognosis.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e49142"},"PeriodicalIF":3.1,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11287234/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141763012","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":"Construction of a Multi-Label Classifier for Extracting Multiple Incident Factors From Medication Incident Reports in Residential Care Facilities: Natural Language Processing Approach.","authors":"Hayato Kizaki, Hiroki Satoh, Sayaka Ebara, Satoshi Watabe, Yasufumi Sawada, Shungo Imai, Satoko Hori","doi":"10.2196/58141","DOIUrl":"10.2196/58141","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Medication safety in residential care facilities is a critical concern, particularly when nonmedical staff provide medication assistance. The complex nature of medication-related incidents in these settings, coupled with the psychological impact on health care providers, underscores the need for effective incident analysis and preventive strategies. A thorough understanding of the root causes, typically through incident-report analysis, is essential for mitigating medication-related incidents.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;We aimed to develop and evaluate a multilabel classifier using natural language processing to identify factors contributing to medication-related incidents using incident report descriptions from residential care facilities, with a focus on incidents involving nonmedical staff.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We analyzed 2143 incident reports, comprising 7121 sentences, from residential care facilities in Japan between April 1, 2015, and March 31, 2016. The incident factors were annotated using sentences based on an established organizational factor model and previous research findings. The following 9 factors were defined: procedure adherence, medicine, resident, resident family, nonmedical staff, medical staff, team, environment, and organizational management. To assess the label criteria, 2 researchers with relevant medical knowledge annotated a subset of 50 reports; the interannotator agreement was measured using Cohen κ. The entire data set was subsequently annotated by 1 researcher. Multiple labels were assigned to each sentence. A multilabel classifier was developed using deep learning models, including 2 Bidirectional Encoder Representations From Transformers (BERT)-type models (Tohoku-BERT and a University of Tokyo Hospital BERT pretrained with Japanese clinical text: UTH-BERT) and an Efficiently Learning Encoder That Classifies Token Replacements Accurately (ELECTRA), pretrained on Japanese text. Both sentence- and report-level training were performed; the performance was evaluated by the F&lt;sub&gt;1&lt;/sub&gt;-score and exact match accuracy through 5-fold cross-validation.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Among all 7121 sentences, 1167, 694, 2455, 23, 1905, 46, 195, 1104, and 195 included \"procedure adherence,\" \"medicine,\" \"resident,\" \"resident family,\" \"nonmedical staff,\" \"medical staff,\" \"team,\" \"environment,\" and \"organizational management,\" respectively. Owing to limited labels, \"resident family\" and \"medical staff\" were omitted from the model development process. The interannotator agreement values were higher than 0.6 for each label. A total of 10, 278, and 1855 reports contained no, 1, and multiple labels, respectively. The models trained using the report data outperformed those trained using sentences, with macro F&lt;sub&gt;1&lt;/sub&gt;-scores of 0.744, 0.675, and 0.735 for Tohoku-BERT, UTH-BERT, and ELECTRA, respectively. The report-trained models also demonstrated better exact match accuracy","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e58141"},"PeriodicalIF":3.1,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11303886/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141749839","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":"Distributed Statistical Analyses: A Scoping Review and Examples of Operational Frameworks Adapted to Health Analytics.","authors":"Félix Camirand Lemyre, Simon Lévesque, Marie-Pier Domingue, Klaus Herrmann, Jean-François Ethier","doi":"10.2196/53622","DOIUrl":"https://doi.org/10.2196/53622","url":null,"abstract":"<p><strong>Background: </strong>Data from multiple organizations are crucial for advancing learning health systems. However, ethical, legal, and social concerns may restrict the use of standard statistical methods that rely on pooling data. Although distributed algorithms offer alternatives, they may not always be suitable for health frameworks.</p><p><strong>Objective: </strong>This paper aims to support researchers and data custodians in three ways: (1) providing a concise overview of the literature on statistical inference methods for horizontally partitioned data; (2) describing the methods applicable to generalized linear models (GLM) and assessing their underlying distributional assumptions; (3) adapting existing methods to make them fully usable in health settings.</p><p><strong>Methods: </strong>A scoping review methodology was employed for the literature mapping, from which methods presenting a methodological framework for GLM analyses with horizontally partitioned data were identified and assessed from the perspective of applicability in health settings. Statistical theory was used to adapt methods and to derive the properties of the resulting estimators.</p><p><strong>Results: </strong>From the review, 41 articles were selected, and six approaches were extracted for conducting standard GLM-based statistical analysis. However, these approaches assumed evenly and identically distributed data across nodes. Consequently, statistical procedures were derived to accommodate uneven node sample sizes and heterogeneous data distributions across nodes. Workflows and detailed algorithms were developed to highlight information-sharing requirements and operational complexity.</p><p><strong>Conclusions: </strong>This paper contributes to the field of health analytics by providing an overview of the methods that can be used with horizontally partitioned data, by adapting these methods to the context of heterogeneous health data and by clarifying the workflows and quantities exchanged by the methods discussed. Further analysis of the confidentiality preserved by these methods is needed to fully understand the risk associated with the sharing of summary statistics.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141728335","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 Information and Communication Technology Maturity Assessment at Primary Health Care Services Across 9 Provinces in Indonesia: Evaluation Study.","authors":"Dewi Nur Aisyah, Agus Heri Setiawan, Alfiano Fawwaz Lokopessy, Nadia Faradiba, Setiaji Setiaji, Logan Manikam, Zisis Kozlakidis","doi":"10.2196/55959","DOIUrl":"10.2196/55959","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Indonesia has rapidly embraced digital health, particularly during the COVID-19 pandemic, with over 15 million daily health application users. To advance its digital health vision, the government is prioritizing the development of health data and application systems into an integrated health care technology ecosystem. This initiative involves all levels of health care, from primary to tertiary, across all provinces. In particular, it aims to enhance primary health care services (as the main interface with the general population) and contribute to Indonesia's digital health transformation.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study assesses the information and communication technology (ICT) maturity in Indonesian health care services to advance digital health initiatives. ICT maturity assessment tools, specifically designed for middle-income countries, were used to evaluate digital health capabilities in 9 provinces across 5 Indonesian islands.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A cross-sectional survey was conducted from February to March 2022, in 9 provinces across Indonesia, representing the country's diverse conditions on its major islands. Respondents included staff from public health centers (Puskesmas), primary care clinics (Klinik Pratama), and district health offices (Dinas Kesehatan Kabupaten/Kota). The survey used adapted ICT maturity assessment questionnaires, covering human resources, software and system, hardware, and infrastructure. It was administered electronically and involved 121 public health centers, 49 primary care clinics, and 67 IT staff from district health offices. Focus group discussions were held to delve deeper into the assessment results and gain more descriptive insights.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;In this study, 237 participants represented 3 distinct categories: 121 public health centers, 67 district health offices, and 49 primary clinics. These instances were selected from a sample of 9 of the 34 provinces in Indonesia. Collected data from interviews and focus group discussions were transformed into scores on a scale of 1 to 5, with 1 indicating low ICT readiness and 5 indicating high ICT readiness. On average, the breakdown of ICT maturity scores was as follows: 2.71 for human resources' capability in ICT use and system management, 2.83 for software and information systems, 2.59 for hardware, and 2.84 for infrastructure, resulting in an overall average score of 2.74. According to the ICT maturity level pyramid, the ICT maturity of health care providers in Indonesia fell between the basic and good levels. The need to pursue best practices also emerged strongly. Further analysis of the ICT maturity scores, when examined by province, revealed regional variations.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The maturity of ICT use is influenced by several critical components. Enhancing human resources, ensuring infrastructure, the availability of supportive hardware, and optimizing informa","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e55959"},"PeriodicalIF":3.1,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11269960/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141735796","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":"Data Lake, Data Warehouse, Datamart, and Feature Store: Their Contributions to the Complete Data Reuse Pipeline","authors":"Antoine Lamer, Chloé Saint-Dizier, Nicolas Paris, Emmanuel Chazard","doi":"10.2196/54590","DOIUrl":"https://doi.org/10.2196/54590","url":null,"abstract":"The growing adoption and utilization of health information technology has generated a wealth of clinical data in electronic format, offering opportunities for data reuse beyond direct patient care. However, as data are distributed across multiple software, it becomes challenging to cross-reference information between sources due to differences in formats, vocabularies, technologies, and the absence of common identifiers among software. To address these challenges, hospitals have adopted data warehouses to consolidate and standardize these data for research. Additionally, as a complement or alternative, data lakes store both source data and metadata in a detailed and unprocessed format, empowering exploration, manipulation, and adaptation of the data to meet specific analytical needs. Subsequently, datamarts are utilized to further refine data into usable information tailored to specific research questions. However, for efficient analysis, a feature store is essential to pivot and denormalize the data, simplifying queries. In conclusion, while data warehouses are crucial, data lakes, datamarts and feature stores play essential and complementary roles in facilitating data reuse for research and analysis in healthcare.","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"66 1","pages":""},"PeriodicalIF":3.2,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141719754","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":"Evaluating Large Language Models for Automated Reporting and Data Systems Categorization: Cross-Sectional Study.","authors":"Qingxia Wu, Qingxia Wu, Huali Li, Yan Wang, Yan Bai, Yaping Wu, Xuan Yu, Xiaodong Li, Pei Dong, Jon Xue, Dinggang Shen, Meiyun Wang","doi":"10.2196/55799","DOIUrl":"10.2196/55799","url":null,"abstract":"<p><strong>Background: </strong>Large language models show promise for improving radiology workflows, but their performance on structured radiological tasks such as Reporting and Data Systems (RADS) categorization remains unexplored.</p><p><strong>Objective: </strong>This study aims to evaluate 3 large language model chatbots-Claude-2, GPT-3.5, and GPT-4-on assigning RADS categories to radiology reports and assess the impact of different prompting strategies.</p><p><strong>Methods: </strong>This cross-sectional study compared 3 chatbots using 30 radiology reports (10 per RADS criteria), using a 3-level prompting strategy: zero-shot, few-shot, and guideline PDF-informed prompts. The cases were grounded in Liver Imaging Reporting & Data System (LI-RADS) version 2018, Lung CT (computed tomography) Screening Reporting & Data System (Lung-RADS) version 2022, and Ovarian-Adnexal Reporting & Data System (O-RADS) magnetic resonance imaging, meticulously prepared by board-certified radiologists. Each report underwent 6 assessments. Two blinded reviewers assessed the chatbots' response at patient-level RADS categorization and overall ratings. The agreement across repetitions was assessed using Fleiss κ.</p><p><strong>Results: </strong>Claude-2 achieved the highest accuracy in overall ratings with few-shot prompts and guideline PDFs (prompt-2), attaining 57% (17/30) average accuracy over 6 runs and 50% (15/30) accuracy with k-pass voting. Without prompt engineering, all chatbots performed poorly. The introduction of a structured exemplar prompt (prompt-1) increased the accuracy of overall ratings for all chatbots. Providing prompt-2 further improved Claude-2's performance, an enhancement not replicated by GPT-4. The interrun agreement was substantial for Claude-2 (k=0.66 for overall rating and k=0.69 for RADS categorization), fair for GPT-4 (k=0.39 for both), and fair for GPT-3.5 (k=0.21 for overall rating and k=0.39 for RADS categorization). All chatbots showed significantly higher accuracy with LI-RADS version 2018 than with Lung-RADS version 2022 and O-RADS (P<.05); with prompt-2, Claude-2 achieved the highest overall rating accuracy of 75% (45/60) in LI-RADS version 2018.</p><p><strong>Conclusions: </strong>When equipped with structured prompts and guideline PDFs, Claude-2 demonstrated potential in assigning RADS categories to radiology cases according to established criteria such as LI-RADS version 2018. However, the current generation of chatbots lags in accurately categorizing cases based on more recent RADS criteria.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e55799"},"PeriodicalIF":3.1,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11292156/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141629385","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":"Diagnostic Accuracy of Artificial Intelligence in Endoscopy: Umbrella Review","authors":"Bowen Zha, Angshu Cai, Guiqi Wang","doi":"10.2196/56361","DOIUrl":"https://doi.org/10.2196/56361","url":null,"abstract":"Background: Some research has already reported the diagnostic value of artificial intelligence (AI) in different endoscopy outcomes. However, the evidence is confusing and of varying quality. Objective: To comprehensively evaluate the credibility of the evidence of the diagnostic accuracy of artificial intelligence in endoscopy. Methods: Before the study began, the protocol was registered in the International prospective register of systematic reviews (CRD42023483073). Firstly, two researchers searched PubMed, Web of Science, Embase, and Cochrane Library using comprehensive search terms. The deadline is November 2023. Then, researchers conduct screening research and extract information. We use A Measurement Tool to Assess Systematic Reviews 2 (AMSTAR2) to evaluate the quality of the article. We choose the research with higher quality evaluation for the same outcome for further analysis. In order to ensure the reliability of the conclusion, we have calculated each outcome again. Finally, the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) is used to evaluate the credibility of the outcome. Results: A total of 21 studies were included for analysis. Through AMSTAR2, it was found that eight research methodologies were of moderate quality, while other studies were regarded as low or critical low. The sensitivity and specificity of 17 different outcomes were analyzed. There are four different outcomes related to the esophagus, stomach, and colorectal, respectively. Two outcomes are associated with capsule endoscopy and laryngoscope, respectively. While the other is related to ultrasonic endoscopy. In terms of sensitivity, gastroesophageal reflux disease has the highest accuracy rate, reaching 97%, while the invasion depth of colon neoplasia has the lowest accuracy rate, only 71%. On the other hand, the specificity of colorectal cancer is the highest, reaching 98%, while the gastrointestinal stromal tumor has the lowest, only 80%. The GRADE evaluation suggests that the reliability of most outcomes are evaluated as low or very low. Conclusions: AI shows the value of diagnosis in endoscopy, especially in esophageal and colorectal diseases. These findings provide a theoretical basis for the development and evaluation of the use of AI-assisted systems, which are aimed at assisting endoscopists to carry out examinations to improve human health. However, it is worth noting further high-quality research is needed in the future.","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"90 1","pages":""},"PeriodicalIF":3.2,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141719753","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":"Integrating Clinical Data and Medical Imaging in Lung Cancer: Feasibility Study Using the Observational Medical Outcomes Partnership Common Data Model Extension.","authors":"Hyerim Ji, Seok Kim, Leonard Sunwoo, Sowon Jang, Ho-Young Lee, Sooyoung Yoo","doi":"10.2196/59187","DOIUrl":"10.2196/59187","url":null,"abstract":"<p><strong>Background: </strong>Digital transformation, particularly the integration of medical imaging with clinical data, is vital in personalized medicine. The Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) standardizes health data. However, integrating medical imaging remains a challenge.</p><p><strong>Objective: </strong>This study proposes a method for combining medical imaging data with the OMOP CDM to improve multimodal research.</p><p><strong>Methods: </strong>Our approach included the analysis and selection of digital imaging and communications in medicine header tags, validation of data formats, and alignment according to the OMOP CDM framework. The Fast Healthcare Interoperability Resources ImagingStudy profile guided our consistency in column naming and definitions. Imaging Common Data Model (I-CDM), constructed using the entity-attribute-value model, facilitates scalable and efficient medical imaging data management. For patients with lung cancer diagnosed between 2010 and 2017, we introduced 4 new tables-IMAGING_STUDY, IMAGING_SERIES, IMAGING_ANNOTATION, and FILEPATH-to standardize various imaging-related data and link to clinical data.</p><p><strong>Results: </strong>This framework underscores the effectiveness of I-CDM in enhancing our understanding of lung cancer diagnostics and treatment strategies. The implementation of the I-CDM tables enabled the structured organization of a comprehensive data set, including 282,098 IMAGING_STUDY, 5,674,425 IMAGING_SERIES, and 48,536 IMAGING_ANNOTATION records, illustrating the extensive scope and depth of the approach. A scenario-based analysis using actual data from patients with lung cancer underscored the feasibility of our approach. A data quality check applying 44 specific rules confirmed the high integrity of the constructed data set, with all checks successfully passed, underscoring the reliability of our findings.</p><p><strong>Conclusions: </strong>These findings indicate that I-CDM can improve the integration and analysis of medical imaging and clinical data. By addressing the challenges in data standardization and management, our approach contributes toward enhancing diagnostics and treatment strategies. Future research should expand the application of I-CDM to diverse disease populations and explore its wide-ranging utility for medical conditions.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e59187"},"PeriodicalIF":3.1,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11282389/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141602289","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":"Time Series AI Model for Acute Kidney Injury Detection Based on a Multicenter Distributed Research Network: Development and Verification Study","authors":"Suncheol Heo, Eun-Ae Kang, Jae Yong Yu, Hae Reong Kim, Suehyun Lee, Kwangsoo Kim, Yul Hwangbo, Rae Woong Park, Hyunah Shin, Kyeongmin Ryu, Chungsoo Kim, Hyojung Jung, Yebin Chegal, Jae-Hyun Lee, Yu Rang Park","doi":"10.2196/47693","DOIUrl":"https://doi.org/10.2196/47693","url":null,"abstract":"Background: Acute kidney injury (AKI) is a marker of clinical deterioration and renal toxicity. While there are many studies offering prediction models for the early detection of AKI, those predicting AKI occurrence using distributed research network (DRN)-based time series data are rare. Objective: In this study, we aimed to detect the early occurrence of AKI by applying the interpretable LSTM-based model on a hospital EHR-based time series in patients who took nephrotoxic drugs using a DRN Methods: We conducted a multi-institutional retrospective cohort study of data from six hospitals using a DRN. For each institution, a patient-based dataset was constructed using five drugs for AKI, and the interpretable multi-variable long short-term memory (IMV-LSTM) model was used for training. This study employed propensity score matching to mitigate differences in demographics and clinical characteristics. Additionally, the temporal attention values of the AKI prediction model's contribution variables were demonstrated for each institution and drug, with differences in highly important feature distributions between the case and control data confirmed using one-way analysis of variance. Results: This study analyzed 8,643 and 31,012 patients with and without AKI, respectively, across six hospitals. When analyzing the distribution of AKI onset, vancomycin showed an earlier onset (median: 12 days), and acyclovir was the slowest compared to the other drugs (median: 23 days). Our temporal deep learning model for AKI prediction performed well for most drugs. Acyclovir had the highest average area under the receiver operating characteristic curve score per drug (0.94), followed by acetaminophen (0.93), vancomycin (0.92), naproxen (0.90), and celecoxib (0.89). Based on the temporal attention values of the variables in the AKI prediction model, verified lymphocytes and calcium had the highest attention, whereas lymphocytes, albumin, and hemoglobin tended to decrease over time, and urine pH and prothrombin time tended to increase. Conclusions: Early surveillance of AKI outbreaks can be achieved by applying the IMV-LSTM based on time series data through hospital electronic health records (EHR)-based DRNs. This approach can help identify risk factors and enable early detection of adverse drug reactions when prescribing drugs that cause renal toxicity before AKI occurs.","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"6 1","pages":""},"PeriodicalIF":3.2,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141569919","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":"Privacy-Preserving Prediction of Postoperative Mortality in Multi-Institutional Data: Development and Usability Study.","authors":"Jungyo Suh, Garam Lee, Jung Woo Kim, Junbum Shin, Yi-Jun Kim, Sang-Wook Lee, Sulgi Kim","doi":"10.2196/56893","DOIUrl":"10.2196/56893","url":null,"abstract":"<p><strong>Background: </strong>To circumvent regulatory barriers that limit medical data exchange due to personal information security concerns, we use homomorphic encryption (HE) technology, enabling computation on encrypted data and enhancing privacy.</p><p><strong>Objective: </strong>This study explores whether using HE to integrate encrypted multi-institutional data enhances predictive power in research, focusing on the integration feasibility across institutions and determining the optimal size of hospital data sets for improved prediction models.</p><p><strong>Methods: </strong>We used data from 341,007 individuals aged 18 years and older who underwent noncardiac surgeries across 3 medical institutions. The study focused on predicting in-hospital mortality within 30 days postoperatively, using secure logistic regression based on HE as the prediction model. We compared the predictive performance of this model using plaintext data from a single institution against a model using encrypted data from multiple institutions.</p><p><strong>Results: </strong>The predictive model using encrypted data from all 3 institutions exhibited the best performance based on area under the receiver operating characteristic curve (0.941); the model combining Asan Medical Center (AMC) and Seoul National University Hospital (SNUH) data exhibited the best predictive performance based on area under the precision-recall curve (0.132). Both Ewha Womans University Medical Center and SNUH demonstrated improvement in predictive power for their own institutions upon their respective data's addition to the AMC data.</p><p><strong>Conclusions: </strong>Prediction models using multi-institutional data sets processed with HE outperformed those using single-institution data sets, especially when our model adaptation approach was applied, which was further validated on a smaller host hospital with a limited data set.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"12 ","pages":"e56893"},"PeriodicalIF":3.1,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11259763/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141539029","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}