Applied Clinical Informatics最新文献

{"title":"Health Consumers' Use and Perceptions of Health Information from Generative Artificial Intelligence Chatbots: A Scoping Review.","authors":"John Robert Bautista, Drew Herbert, Matthew Farmer, Ryan Q De Torres, Gil P Soriano, Charlene E Ronquillo","doi":"10.1055/a-2647-1210","DOIUrl":"10.1055/a-2647-1210","url":null,"abstract":"<p><p>Health consumers can use generative artificial intelligence (GenAI) chatbots to seek health information. As GenAI chatbots continue to improve and be adopted, it is crucial to examine how health information generated by such tools is used and perceived by health consumers.To conduct a scoping review of health consumers' use and perceptions of health information from GenAI chatbots.Arksey and O'Malley's five-step protocol was used to guide the scoping review. Following PRISMA guidelines, relevant empirical papers published on or after January 1, 2019, were retrieved between February and July 2024. Thematic and content analyses were performed.We retrieved 3,840 titles and reviewed 12 papers that included 13 studies (quantitative = 5, qualitative = 4, and mixed = 4). ChatGPT was used in 11 studies, while two studies used GPT-3. Most were conducted in the United States (<i>n</i> = 4). The studies involve general and specific (e.g., medical imaging, psychological health, and vaccination) health topics. One study explicitly used a theory. Eight studies were rated with excellent quality. Studies were categorized as user experience studies (<i>n</i> = 4), consumer surveys (<i>n</i> = 1), and evaluation studies (<i>n</i> = 8). Five studies examined health consumers' use of health information from GenAI chatbots. Perceptions focused on: (1) accuracy, reliability, or quality; (2) readability; (3) trust or trustworthiness; (4) privacy, confidentiality, security, or safety; (5) usefulness; (6) accessibility; (7) emotional appeal; (8) attitude; and (9) effectiveness.Although health consumers can use GenAI chatbots to obtain accessible, readable, and useful health information, negative perceptions of their accuracy, trustworthiness, effectiveness, and safety serve as barriers that must be addressed to mitigate health-related risks, improve health beliefs, and achieve positive health outcomes. More theory-based studies are needed to better understand how exposure to health information from GenAI chatbots affects health beliefs and outcomes.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":" ","pages":"892-902"},"PeriodicalIF":2.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12390362/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144555497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mobile Admission Process and Administrative Turnaround Time for Hospitalization of Outpatients: A Retrospective Study.","authors":"Ho Sub Chung, Myeong Namgung, Sung Jin Bae, Yunhyung Choi, Dong Hoon Lee, Chan Woong Kim, Sunho Kim, Kwang Yul Jung","doi":"10.1055/a-2576-7110","DOIUrl":"10.1055/a-2576-7110","url":null,"abstract":"<p><p>This study compared the time efficiency of the hospital admission process using personal mobile devices to traditional walk-in methods, thereby assessing the effectiveness of the mobile admission process.This retrospective study was conducted at Chung-Ang University Gwangmyeong Hospital in South Korea (August 2022-January 2023). Turnaround times for the walk-in and mobile admission processes were compared. Patients were divided into mobile and walk-in groups based on their admission process. Collected timestamp data were extracted by examining patients' electronic medical record log time or caregivers' electronic signatures on consent forms. Time intervals between timestamp data were calculated and compared.We enrolled 4,344 patients to compare the turnaround time and demographics of the mobile (<i>n</i> = 1,336) and walk-in (<i>n</i> = 3,008) admission processes. The former had a significantly shorter mean turnaround time (13.4 minutes) than the latter (22.2 minutes). Female patients, younger patients, and those admitted to surgery departments were more likely to use the mobile process. Older patients were less likely to undergo mobile admissions. A linear regression analysis revealed that these factors significantly affected the usability of the mobile device admission process.Compared with the traditional walk-in admission process, the mobile admission process can reduce task completion time.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":" ","pages":"769-776"},"PeriodicalIF":2.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12352987/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144052994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical Decision Support Enhanced by User Acceptance Testing to Promote Situational Awareness for Pediatric Patients with a Difficult Airway.","authors":"Megan Dahl, Sarah Thompson, Jerry Chih, Swaminathan Kandaswamy, Evan Orenstein, Justin B Long","doi":"10.1055/a-2632-9337","DOIUrl":"10.1055/a-2632-9337","url":null,"abstract":"<p><p>Children with a difficult airway are at high risk of decompensation in the setting of respiratory distress. Situational awareness among all team members, and a shared plan in case of an emergency, can reduce the chance of catastrophic outcomes.This study aimed to improve difficult airway situational awareness while minimizing alert burden in a quaternary care pediatric healthcare system through the application of clinical decision support (CDS).Three iterative designs were developed and implemented from 2015 through 2023. We measured interruptive alert burden and performed observations between each implementation to estimate point prevalence among hospitalized patients with a difficult airway of three desired behaviors: presence of a difficult airway sign at the head of the bed, orders placed for appropriate equipment nearby, and primary nurse awareness of the difficult airway.Over the course of the redesign, the alert burden decreased from 12,316 firings per month to 125 firings per month from the first alert to the second redesign and final iteration. There was a statistically significant increase in the proportion of difficult airway patients with orders for appropriate equipment from 51.4 to 83.9% (<i>p</i> < 0.001). There was no significant change in difficult airway sign placement (71.4-87.1%, <i>p</i> = 0.29) or observed nurse awareness of difficult airway status of the patient (80.0-87.1%, <i>p</i> = 0.447). The greatest improvements in alert burden and rates of desired user action occurred after redesigning based on usability testing.CDS redesign using popular frameworks alone reduced alert burden without significantly worsening situational awareness. Redesign through guerilla in situ usability testing led to much more substantial reductions in alert burden and greater improvements in desired user action.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":" ","pages":"855-862"},"PeriodicalIF":2.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12349968/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144286934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transitioning Ineffective Medications on Hold Alert from Interruptive to Noninterruptive Alert to Decrease Alert Burden.","authors":"Lindsey A Knake, Joshua M Kettelkamp, Alison Bronson, Nathan Meyer, Kenneth Hacker, James M Blum","doi":"10.1055/a-2632-0605","DOIUrl":"10.1055/a-2632-0605","url":null,"abstract":"<p><p>Interruptive clinical decision support (CDS) alerts are intended to improve patient care, but can contribute to alert fatigue, diminishing their effectiveness. The alert demonstrated minimal clinical effect while contributing significantly to alert fatigue.This study aims to evaluate if transitioning a high-firing medication on hold alert from interruptive to noninterruptive would change provider practices.The alert was triggered when at least two medications were held for >48 hours. A pre-post intervention cohort study was conducted to evaluate transitioning the medication on hold alert from interruptive to noninterruptive. A comparison was made to evaluate provider practices in resuming medications during the 6 months before and after transitioning the alert. Data were extracted from the medication administration record and the institutional risk reporting system.After transitioning to a noninterruptive alert, the number of actions taken by clicking on the alert decreased from 33,632 (3.0 clicks per hospital encounter) to 305 (0.02 clicks per hospital encounter) in a 6-month period. There was no significant change in the median hold duration of medications that were on hold for greater than 48 hours (81.5 hours and 85.6 hours in the pre- and postintervention cohorts, respectively [<i>p</i>-value = 0.22]). There was no change in the most frequent medications that were held until patient discharge, and there was no increased reporting of medication-on-hold safety events.The initial interruptive medication on hold alert was not effective and contributed to a high volume of alerts in our institution. Transitioning the medications on hold alert from an interruptive to a noninterruptive alert reduced potential alert fatigue without significantly impacting clinical outcomes. These findings highlight the need for careful evaluation of CDS alerts to balance clinical utility and provider alert burden. Alerts that do not affect the desired clinical outcome should be redesigned or retired.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":" ","pages":"848-854"},"PeriodicalIF":2.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12349967/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144310652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ambient Artificial Intelligence Scribes in Oncology: Adoption, Feasibility, Acceptability, and Appropriateness.","authors":"Abigail E Baldwin-Medsker, Susan Chimonas, Suryan P Goyal, Adam J Watson, Maclain R Damstrom, Gilad J Kuperman, Tiffany Traina, Benjamin R Roman, Peter D Stetson, Allison Lipitz-Snyderman","doi":"10.1055/a-2662-0740","DOIUrl":"10.1055/a-2662-0740","url":null,"abstract":"<p><p>Hospitals are looking to AI and other innovative applications to help alleviate provider burden and dissatisfaction associated with clinical documentation in oncology. Ambient artificial intelligence (AI) scribes are a promising technology to address these issues. However, they generally have not been optimized for oncology. This study aimed to evaluate an ambient AI scribe application with oncology providers to determine opportunities and potential challenges.This prospective pilot study of a scribe application was conducted over 4 months at a high-volume cancer center in New York City. Qualitative (interviews) and quantitative (surveys and utilization) data were collected to assess adoption, feasibility, acceptability, and appropriateness. The analysis included descriptive statistics and thematic content analysis.Thirty-one providers were included across oncology specialties. Twenty-five providers used the application at least once; of these, 18 completed a survey and 21 completed an interview. Providers used the application in 620 (13.9%) out of 4,449 in-person outpatient visits. Out of 18 survey respondents, 17 (94%) indicated they used the AI-drafted content at least sometimes, demonstrating feasibility. For acceptability, 11 (61%) indicated a moderate, strong, or very strong desire for continued access to the technology. All providers interviewed advocated for continued investment in ambient technology. Metrics around appropriateness showed variability based on its accuracy in capturing complex clinical scenarios and in the types of patients the technology was used with. For example, providers used the technology for 21.1% of new visits but only 12.2% of follow-up visits.This study demonstrated the potential for ambient AI scribes to be useful in oncology. Future research should evaluate the use of this technology at scale as it may realize workflow efficiencies and improve the clinical documentation process.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":"16 4","pages":"995-1004"},"PeriodicalIF":2.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12408117/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144993980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Disappearing Text as a Clinical Decision Support Layer: A Case Series.","authors":"Jared Silberlust, William Small, Darhsi Shah, Eesha Chakravartty, Katherine Moawad, Andrew Moawad, Paul Testa, Jonah Feldman","doi":"10.1055/a-2675-3510","DOIUrl":"10.1055/a-2675-3510","url":null,"abstract":"<p><p>This case series aims to evaluate several applications of inline disappearing text (DT) clinical decision support (CDS) tools within clinician documentation.DT blocks were created to prompt documentation for perioperative anticoagulation planning (scenario 1), predischarge intravenous antibiotic planning (scenario 2), and advanced care planning (ACP; scenario 3). In scenario 1, DT was the only intervention. In scenario 2, DT was paired with a documentation SmartList. In scenario 3, DT was paired with a documentation SmartList and an OurPractice advisory. The number of documented perioperative anticoagulation plans, predischarge intravenous antibiotic plans, and ACP notes was measured pre- and postintervention and compared using chi-square analyses.In scenario 1, there was no statistically significant change in the percentage of perioperative anticoagulation plans documented at 0 to 24 and 24 to 48 hours before surgery. In scenario 2, documentation of antibiotic contingency planning in patients expected to be discharged within 24 hours increased from 60% (54/90 notes) to 93% (1,850/1,994 notes) <i>X</i> ² (1, <i>n</i> = 2,084) = 113.1, <i>p</i> < 0.001. In scenario 3, ACP note documentation by discharge in patients with a positive mandatory surprise question increased from 43% (821/1,909 encounters) to 52% (975/1,874 encounters) <i>X</i> ² (1, <i>n</i> = 3,783) = 30.5, <i>p</i> < 0.001.Utilizing DT in conjunction with other forms of CDS was associated with an improvement of documentation quality in predischarge IV antibiotics and ACP. A sociotechnical analysis explores how interactions between technology, people, workflow, and culture could contextualize how utilizing DT with other forms of CDS was more effective than DT alone.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":" ","pages":"1114-1120"},"PeriodicalIF":2.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12443503/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144790507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Challenges and Opportunities for Health Information Systems in Primary Care Clinics: A Mixed-Method Study among Health Workers in Manila, Philippines.","authors":"Ma Sergia Fatima Sucaldito, Rahul Malhotra, Lia Palileo-Villanueva, John Jefferson Besa, Precious Angelica Echague, Mary John Saquilayan, Jessa Mae Banzuela, Kian Mendoza, Anton Elepaño, Lijing L Yan, Truls Østbye","doi":"10.1055/a-2595-2824","DOIUrl":"10.1055/a-2595-2824","url":null,"abstract":"<p><p>Globally, health information system (HIS) development projects face challenges regarding technology infrastructure, financing, user resistance, and interoperability. While these challenges are well-described in literature, most studies on HIS digitalization focus on the development of national and hospital HISs, with little focus on HISs in primary care. We described the HISs of two primary care clinics in Manila, Philippines in terms of data management procedures, governance, training and equipment, information culture, and health worker data skills, and investigated health workers' experiences during digitalization.This convergent mixed-methods descriptive study included two clinics: a nongovernmental organization (NGO)-operated clinic and a government-operated public health center (PHC). We surveyed eight health workers in the NGO clinic and six in PHC using the Performance of Routine Information System Management (PRISM) Community HIS evaluation tools from the World Health Organization and MEASURE Evaluation and conducted in-depth interviews among the same participants to explore their HIS experiences.Respondents in both clinics provided low scores on governance, indicating deficiencies in HIS strategy and documentation. PHC scored higher on data management, training, and equipment compared with the NGO clinic, whereas information culture scores were similar. Survey results reflected differences in IT infrastructure and services, stemming from PHC's larger size and funding. Interviews corroborated the survey results, highlighting barriers such as inadequate training and resources and the critical roles of internal communication and joint data stewardship, as described by the Filipino term \"damayan,\" which means working together in times of adversity. Additionally, interviews revealed expected benefits from digitalization, negative impact on workflow, and limited communication with external organizations.The findings highlight critical areas for enhancing HIS implementation and digitalization in primary care clinics in the Philippines. Addressing governance gaps, resource deficiencies, and communication barriers can improve HIS performance and help build digital resilience.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":"16 4","pages":"1077-1085"},"PeriodicalIF":2.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12431810/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145056125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semantic Relations: Extending SNOMED CT and Solor.","authors":"Melissa P Resnick, James Hitt, Wilmon McCray, Kendria Hall, Frank LeHouillier, Steven H Brown, Keith E Campbell, Diane Montella, Jonathan Nebeker, Peter L Elkin","doi":"10.1055/a-2606-9411","DOIUrl":"10.1055/a-2606-9411","url":null,"abstract":"<p><p>Terminologies, such as Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) and Solor, assist with knowledge representation and management, data integration, and triggering clinical decision support (CDS) rules. Semantic relations in these terminologies provide explicit meaning in compositional expressions, which assist with many of the above-listed activities.The aims of this research are to: (1) identify semantic relations that are not fully present in SNOMED CT and Solor and (2) use these identified semantic relations with terms that are currently present in SNOMED CT and Solor to form triples.We identified relations that were not fully present in either SNOMED CT or Solor and were important for VA Knowledge Artifacts (KNARTS). These terms and the relations were formed into triples. The relations, terms, classifications, and sentences were used to implement the relations in the High Definition-Natural Language Processing (HD-NLP) program.There are a total of 38 semantic relations. These had use cases built for each and were implemented in the Solor HD-NLP server for tagging of KNARTS.These new SNOMED CT and Solor semantic relations will give clinicians the ability to add more detail and meaning to their clinical notes. This can improve our ability to trigger CDS rules, leading to improved CDS provided to clinicians during patient care.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":"16 4","pages":"1263-1270"},"PeriodicalIF":2.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12494445/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145226120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EHR Use in Inpatient Physicians: Patterns and Predictors.","authors":"Gabrielle Safian, Kaiyu Tio, Kevin Tang, Shitij Arora, Sunit Jariwala","doi":"10.1055/a-2615-4085","DOIUrl":"10.1055/a-2615-4085","url":null,"abstract":"<p><p>Electronic health record (EHR) systems have become integral to hospital-based care, with studies showing physicians spending significant time interfacing with these systems. While EHR interactions are necessary for patient care, understanding usage patterns can identify opportunities for system optimization and workflow improvement. Previous studies have focused on outpatient settings, making this study among the first to comprehensively analyze inpatient EHR interaction patterns.This study aims to characterize EHR utilization patterns among inpatient physicians and analyze how these patterns vary by physician characteristics, including gender, specialty, and years of experience. This analysis aims to identify opportunities for targeted EHR optimization and workflow enhancement strategies.We analyzed nine key EHR interaction metrics from Epic Signal across 1,787 inpatient physicians during February 2024. Metrics included time spent in various EHR activities, patient volume, secure message usage, and specific feature utilization. Multivariate regression models were then generated for each outcome metric.Female physicians spent more time per patient in the EHR (21.74 vs. 15.62 minutes, <i>p</i> < 0.001) and utilized secure messaging features more frequently (messages sent: 0.82 vs. 0.06 per day, <i>p</i> < 0.001). Internal Medicine/Pediatrics demonstrated higher EHR interaction times across multiple metrics compared to Surgical Specialists, even after adjusting for patient load (51.93 vs. 8.37 minutes per day, <i>p</i> < 0.001). Years since graduation showed significant negative correlations with most EHR interaction metrics (<i>r</i> = -0.11 to -0.27, <i>p</i> < 0.001).This analysis reveals significant variation in EHR utilization patterns across physician demographics and specialties. These findings can inform targeted interventions to optimize EHR workflows and support efficient system usage while maintaining documentation quality and patient care standards.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":"16 4","pages":"1271-1280"},"PeriodicalIF":2.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12494415/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145226142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Challenges with Implementing Predictive Models for Inpatient Hypoglycemic Events in Clinical Decision Support.","authors":"Sarah Stern, Richa Bundy, Lauren Witek, Adam Moses, Christopher Kelly, Matthew Gorris, Cynthia Burns, Ajay Dharod","doi":"10.1055/a-2617-6522","DOIUrl":"10.1055/a-2617-6522","url":null,"abstract":"<p><p>Inpatient hypoglycemia is associated with increased length of stay and mortality. There have been several models developed to predict a patient's risk of inpatient hypoglycemia.This study aimed to describe the barriers to implementing a model that we developed to predict inpatient hypoglycemic events informing a clinical decision support tool.A logistic regression model was trained on inpatient hospitalizations of diabetic patients receiving insulin at Atrium Health Wake Forest Baptist Medical Center, an academic medical center in the Southeastern United States, from January 2020 to December 2021. The model was developed to predict a hypoglycemic event (glucose < 70 mg/dL) within 24 hours of a patient's first borderline-low glucose measurement (70-90 mg/dL).The model area under the curve was 0.69 on the validation dataset; however, we chose not to implement the model in clinical practice.We decided not to implement our predictive model into clinical decision support due to a variety of factors including limitations in the predictiveness of the model and several contextual factors. Through this work we learned that it is not always feasible to use predictive analytics in clinical decision support, especially when attempting to predict low incidence events for which some important predictors are not documented in the electronic health record in a structured way.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":" ","pages":"1319-1324"},"PeriodicalIF":2.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12513774/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144121220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}