BMC Medical Informatics and Decision Making最新文献

{"title":"Improving event prediction using general practitioner clinical judgement in a digital risk stratification model: a pilot study.","authors":"Emma Parry, Kamran Ahmed, Elizabeth Guest, Vijay Klaire, Abdool Koodaruth, Prasadika Labutale, Dawn Matthews, Jonathan Lampitt, Alan Nevill, Gillian Pickavance, Mona Sidhu, Kate Warren, Baldev M Singh","doi":"10.1186/s12911-024-02797-5","DOIUrl":"10.1186/s12911-024-02797-5","url":null,"abstract":"<p><strong>Background: </strong>Numerous tools based on electronic health record (EHR) data that predict risk of unscheduled care and mortality exist. These are often criticised due to lack of external validation, potential for low predictive ability and the use of thresholds that can lead to large numbers being escalated for assessment that would not have an adverse outcome leading to unsuccessful active case management. Evidence supports the importance of clinical judgement in risk prediction particularly when ruling out disease. The aim of this pilot study was to explore performance analysis of a digitally driven risk stratification model combined with GP clinical judgement to identify patients with escalating urgent care and mortality events.</p><p><strong>Methods: </strong>Clinically risk stratified cohort study of 6 GP practices in a deprived, multi-ethnic UK city. Initial digital driven risk stratification into Escalated and Non-escalated groups used 7 risk factors. The Escalated group underwent stratification using GP global clinical judgement (GCJ) into Concern and No concern groupings.</p><p><strong>Results: </strong>3968 out of 31,392 patients were data stratified into the Escalated group and further categorised into No concern (n = 3450 (10.9%)) or Concern (n = 518 (1.7%)) by GPs. The 30-day combined event rate (unscheduled care or death) per 1,000 was 19.0 in the whole population, 67.8 in the Escalated group and 168.0 in the Concern group (p < 0.001). The de-escalation effect of GP assessment into No Concern versus Concern was strongly negatively predictive (OR 0.25 (95%CI 0.19-0.33; p < 0.001)). The whole population ROC for the global approach (Non-escalated, GP No Concern, GP Concern) was 0.614 (0.592-0.637), p < 0.001, and the increase in the ROC area under the curve for 30-day events was all focused here (+ 0.4% (0.3-0.6%, p < 0.001), translating into a specific ROC c-statistic for GP GCJ of 0.603 ((0.565-0.642), p < 0.001).</p><p><strong>Conclusions: </strong>The digital only component of the model performed well but adding GP clinical judgement significantly improved risk prediction, particularly by adding negative predictive value.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"382"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11654091/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142852954","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":"An explainable analysis of diabetes mellitus using statistical and artificial intelligence techniques.","authors":"William Hoyos, Kenia Hoyos, Rander Ruiz, Jose Aguilar","doi":"10.1186/s12911-024-02810-x","DOIUrl":"10.1186/s12911-024-02810-x","url":null,"abstract":"<p><strong>Background: </strong>Diabetes mellitus (DM) is a chronic disease prevalent worldwide, requiring a multifaceted analytical approach to improve early detection and subsequent mitigation of morbidity and mortality rates. This research aimed to develop an explainable analysis of DM by combining sociodemographic and clinical data with statistical and artificial intelligence (AI) techniques.</p><p><strong>Methods: </strong>Leveraging a small dataset that includes sociodemographic and clinical profiles of diabetic and non-diabetic individuals, we employed a diverse set of statistical and AI models for predictive purposes and assessment of DM risk factors. The statistical tests used were Student's t-test and Chi-square, while the AI techniques were fuzzy cognitive maps (FCM), artificial neural networks (ANN), support vector machines (SVM), and XGBoost.</p><p><strong>Results: </strong>Our statistical models facilitated an in-depth exploration of variable associations, while the resulting AI models demonstrated exceptional efficacy in DM classification. In particular, the XGBoost model showed superior performance in accuracy, sensitivity and specificity with values of 1 for each of these metrics. On the other hand, the FCM stood out for its explainability capabilities by allowing an analysis of the variables involved in the prediction using scenario-based simulations.</p><p><strong>Conclusions: </strong>An integrated analysis of DM using a variety of methodologies is critical for timely detection of the disease and informed clinical decision-making.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"383"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11654128/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142853023","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":"The social experience of uncertainty: a qualitative analysis of emergency department care for suspected pneumonia for the design of decision support.","authors":"Peter Taber, Charlene Weir, Susan L Zickmund, Elizabeth Rutter, Jorie Butler, Barbara E Jones","doi":"10.1186/s12911-024-02805-8","DOIUrl":"10.1186/s12911-024-02805-8","url":null,"abstract":"<p><strong>Background: </strong>This study sought to understand the process of clinical decision-making for suspected pneumonia by emergency departments (ED) providers in Veterans Affairs (VA) Medical Centers. The long-term goal of this work is to create clinical decision support tools to reduce unwarranted variation in diagnosis and treatment of suspected pneumonia.</p><p><strong>Methods: </strong>Semi-structured qualitative interviews were conducted with 16 ED clinicians from 9 VA facilities demonstrating variation in antibiotic and hospitalization decisions. Interviews of ED providers focused on understanding decision making for provider-selected pneumonia cases and providers' organizational contexts.</p><p><strong>Results: </strong>Thematic analysis identified four salient themes: i) ED decision-making for suspected pneumonia is a social process; ii) the \"diagnosis drives treatment\" paradigm is poorly suited to pneumonia decision-making in the ED; iii) The unpredictability of the ED requires deliberate and effortful information management by providers in CAP decision-making; and iv) the emotional stakes and high uncertainty of pneumonia care drive conservative decision making.</p><p><strong>Conclusions: </strong>Ensuring CDS reflects the realities of clinical work as a socially organized process with high uncertainty may ultimately improve communication between ED and admitting providers, continuity of care and patient outcomes.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"386"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11657753/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142853030","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":"Challenges and solutions in implementing electronic prescribing in Iran's health system: a qualitative study.","authors":"Neda Borhani Moghani, Elahe Hooshmand, Marzie Zarqi, Marziyhe Meraji","doi":"10.1186/s12911-024-02737-3","DOIUrl":"10.1186/s12911-024-02737-3","url":null,"abstract":"<p><strong>Background: </strong>The use of electronic prescribing is recognized as a strategic tool for improving healthcare. Given the nationwide implementation of electronic prescribing systems initiated in 2020, this study aims to explore the challenges and solutions for implementing electronic prescribing in Iran's health system as a developing country.</p><p><strong>Methods: </strong>This qualitative study was conducted through interviews with physicians, pharmacy staff, and electronic prescribing representatives in 2023. Initially, three in-depth interviews were conducted to develop the interview questions, resulting in three separate interview guides for each participant group (supplementary file no.1). Participants were purposively selected, including 12 physicians, 15 electronic prescribing representatives, and 9 pharmacy staff members. Interviews continued until data saturation was reached. The interviews were recorded, transcribed, and analyzed using Inductive content analysis with MAXQDA version 10 software. To identify challenges, sessions were held, and a final list of challenges was categorized. In the final stage, expert panels including 3 researchers, 4 e-prescribing representatives, and 3 insurance experts were formed to propose solutions.</p><p><strong>Result: </strong>The challenges identified in this study were categorized into two main domains: \"Organizational Challenges\" and \"Systemic Challenges.\" Organizational challenges included issues related to insurance (16 cases), patient referrals (4 cases), stakeholder education and communication (6 cases), and supervision (8 cases). Systemic challenges included infrastructure problems (18 cases), user interface (UI) issues (14 cases), and database issues (10 cases). The primary challenges in implementing electronic prescribing were system downtime and sluggishness, internet connectivity issues, and the existence of multiple insurance systems. Expert panel discussions resulted in proposed solutions, including the uniform design of software by the Ministry of Health, the establishment of an integrated electronic referral system, conducting practical training sessions for physicians, and implementing electronic signatures.</p><p><strong>Conclusion: </strong>Electronic prescribing in Iran is still in its early stages and will inevitably face challenges and problems. Continuous monitoring of electronic prescribing systems is essential to address implementation issues promptly. Issues related to training insurance monitoring the user interface and database infrastructure were challenging. Overall, improvements in infrastructure, integration of insurance systems, implementation of electronic signatures, adherence to electronic prescribing standards, and provision of practical training are recommended.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"393"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11657228/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142851898","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":"Target informed client recruitment for efficient federated learning in healthcare.","authors":"Vincent Scheltjens, Lyse Naomi Wamba Momo, Wouter Verbeke, Bart De Moor","doi":"10.1186/s12911-024-02798-4","DOIUrl":"10.1186/s12911-024-02798-4","url":null,"abstract":"<p><strong>Background: </strong>Modern machine learning and deep learning methods have been widely incorporated in decision making processes in healthcare in the form of decision support mechanisms. In healthcare, data are abundant but typically not centrally available and, therefore, require some form of aggregation to facilitate training procedures. Aggregating sensitive data poses a significant privacy risk, which is why, both in Europe and the United States, legal frameworks regulate the treatment of such data. Whilst these measures protect the individual behind the data, they pose a significant challenge that results in extensive legal administration related to data sharing efforts. Federated learning (FL) offers a way to mitigate these challenges by allowing to learn models in distributed fashion, eliminating the need to aggregate data for the purpose of training. However, FL comes with a new set of challenges related to communication overhead, client selection and efficiency of the FL training procedure, among others.</p><p><strong>Methods: </strong>In this work, we extend on a previously proposed client recruitment approach by incorporating knowledge on the local hardware such that it becomes possible to recruit a subset of clients for the federation based on the construct of client-level representativeness, which is expressed in terms of the local target distribution divergence, sample size, and the underlying hardware.</p><p><strong>Results: </strong>We show that, for prominent, medical regression and classification tasks, the recruitment approach yields results that are on par, or better, compared to the central and federated approaches. The proposed approach requires a mere fraction of the data for training and reduces the training time by a factor of 3-4. In addition, we show that excluded clients can still significantly benefit from the resulting federated model through local fine-tuning.</p><p><strong>Conclusions: </strong>By expressing the representativeness of clients in function of the deviation in the local target distribution, the sample size and efficiency of the underlying hardware, we are able to define a recruitment approach that yields a subset of clients for the federation resulting in significantly reduced training time, without harming predictive performance, whilst improving the privacy preserving characteristics compared to the standard FL and central approaches.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"380"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11653562/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142853028","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":"Development and evaluation of a shared decision-making system for choosing the type of bariatric surgery.","authors":"Sahar Darnahal, Rita Rezaee, Somayyeh Zakerabasali","doi":"10.1186/s12911-024-02796-6","DOIUrl":"10.1186/s12911-024-02796-6","url":null,"abstract":"<p><strong>Introduction: </strong>Obesity is a multifactorial disease resulting from various environmental, genetic, and metabolic factors, affecting a large portion of the population. One of the most effective treatments for severe obesity is bariatric surgery. This research aims to develop a shared decision-making system that facilitates the selection of the appropriate type of bariatric surgery.</p><p><strong>Method: </strong>In this research, we designed and developed a prototype of a shared decision-making system to aid in choosing the type of bariatric surgery through three steps: a) identifying data requirements from a literature review, b) designing interfaces and prototyping, and c) conducting a usability evaluation.</p><p><strong>Results: </strong>Through a literature review of articles, books, and interviews with ten selected patients, the necessary clinical data and educational topics were identified and confirmed by nine surgeons. A prototype was developed using the web application \"Figma.\" We also analyzed the prototype using heuristic evaluation; \"helping users understand and recover from errors\" and \"confidentiality\" had the highest degrees of problem severity, with scores of 3.3 and 3.5, respectively.</p><p><strong>Conclusion: </strong>The developed prototype demonstrated an acceptable level of usability. This system can facilitate shared decision-making and help structure education for patients seeking bariatric surgery.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"385"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11657857/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142852895","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":"Continuous prediction for tumor mutation burden based on transcriptional data in gastrointestinal cancers.","authors":"Beibei Hu, Guohui Yin, Jialin Zhu, Yi Bai, Xuren Sun","doi":"10.1186/s12911-024-02794-8","DOIUrl":"10.1186/s12911-024-02794-8","url":null,"abstract":"<p><strong>Background: </strong>Tumor mutation burden (TMB) has been considered a biomarker for utilization of immune checkpoint inhibitors(ICIs), but whole exome sequencing(WES) and cancer gene panel(CGP) based on next generation sequencing for TMB detection are costly. Here, we use transcriptome data of TCGA to construct a model for TMB prediction in gastrointestinal tumors.</p><p><strong>Methods: </strong>Transcriptome data, somatic mutation data and clinical data of four gastrointestinal tumors from TCGA, including esophageal cancer (ESCA), stomach adenocarcinoma (STAD), colon adenocarcinoma (COAD) and rectal adenocarcinoma (READ). Using R, we performed visual analysis of somatic mutation data, differentially expressed genes (DEGs) function enrichment analysis, gene set enrichment analysis (GSEA), and estimated TMB value in clinic. Finally, a deep neural network (DNN) model was constructed for TMB prediction.</p><p><strong>Results: </strong>Visualization of somatic mutation data summarized the classification of mutation, frequency of each mutation type, and top-mutated genes. GSEA showed the enrichment of CD4⁺/CD8⁺ T cells in the high TMB group and the activation of tumor suppressing pathways. Single-sample GSEA (ssGSEA) manifested that the high-TMB group had higher level of multiple immune cells infiltration. In addition, distribution of TMB was related to clinical parameters. Like age, M stage, N stage, AJCC stage, and overall survival(OS). After model optimization using genetic algorithm, in the training set, validation set, and testing set, the Pearson relevance coefficient r between predicted values and actual values reaches 0.98, 0.82, and 0.92, respectively; the coefficient of determination R2 is 0.95, 0.82, and 0.7, respectively.</p><p><strong>Conclusion: </strong>TMB correlates with clinicopathological parameters in gastrointestinal carcinoma, and patients with high TMB have higher levels of immune infiltration. In addition, the DNN model based on 31 genes predicts TMB of gastrointestinal tumors in a high accuracy.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"384"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11654420/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142852894","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":"Early prediction of mortality upon intensive care unit admission.","authors":"Yu-Chang Yeh, Yu-Ting Kuo, Kuang-Cheng Kuo, Yi-Wei Cheng, Ding-Shan Liu, Feipei Lai, Lu-Cheng Kuo, Tai-Ju Lee, Wing-Sum Chan, Ching-Tang Chiu, Ming-Tao Tsai, Anne Chao, Nai-Kuan Chou, Chong-Jen Yu, Shih-Chi Ku","doi":"10.1186/s12911-024-02807-6","DOIUrl":"10.1186/s12911-024-02807-6","url":null,"abstract":"<p><strong>Background: </strong>We aimed to develop and validate models for predicting intensive care unit (ICU) mortality of critically ill adult patients as early as upon ICU admission.</p><p><strong>Methods: </strong>Combined data of 79,657 admissions from two teaching hospitals' ICU databases were used to train and validate the machine learning models to predict ICU mortality upon ICU admission and at 24 h after ICU admission by using logistic regression, gradient boosted trees (GBT), and deep learning algorithms.</p><p><strong>Results: </strong>In the testing dataset for the admission models, the ICU mortality rate was 7%, and 38.4% of patients were discharged alive or dead within 1 day of ICU admission. The area under the receiver operating characteristic curve (0.856, 95% CI 0.845-0.867) and area under the precision-recall curve (0.331, 95% CI 0.323-0.339) were the highest for the admission GBT model. The ICU mortality rate was 17.4% in the 24-hour testing dataset, and the performance was the highest for the 24-hour GBT model.</p><p><strong>Conclusion: </strong>The ADM models can provide crucial information on ICU mortality as early as upon ICU admission. 24 H models can be used to improve the prediction of ICU mortality for patients discharged more than 1 day after ICU admission.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"394"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11656927/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142852906","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":"Predicting blood transfusion demand in intensive care patients after surgery by comparative analysis of temporally extended data selection.","authors":"Seyedmostafa Sheikhalishahi, Sebastian Goss, Lea K Seidlmayer, Sarra Zaghdoudi, Ludwig C Hinske, Mathias Kaspar","doi":"10.1186/s12911-024-02800-z","DOIUrl":"10.1186/s12911-024-02800-z","url":null,"abstract":"<p><strong>Background: </strong>Blood transfusion (BT) is a critical aspect of medical care for surgical patients in the Intensive Care Unit (ICU). Timely and accurate identification of BT needs can enhance patient outcomes and healthcare resource management.</p><p><strong>Methods: </strong>This study aims to determine whether a machine learning (ML) model can be trained to predict the need for blood transfusion (BT) in patients on the ICU after a wide range of surgeries, utilizing only data from the ICU.</p><p><strong>Results: </strong>This retrospective study analyzed data from 9,118 surgical ICU patients from the Amsterdam University Medical Centers database (UMCdb). The study included a primary analysis using data from 6 h before ICU admission up to 1, 2, 3, and 6 h after admission, and a secondary analysis using only the data from 6 h before ICU admission and only the data from the first hour after admission. The model integrated 32 relevant clinical variables and compared the performance of XGBoost and logistic regression (LR) algorithms.</p><p><strong>Conclusions: </strong>The model demonstrated an effective BT prediction, with XGBoost outperforming LR, particularly for a 12-hour prediction window. Notable differences in patient characteristics were observed among those who received BT and those who did not receive BT. The study establishes the feasibility of using ML for the prediction of BT in surgical ICU patients. It underlines the potential of ML models as decision support tools in healthcare, enabling early identification of BT needs.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"397"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11657635/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142853025","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":"Screening for undiagnosed atrial fibrillation using an electronic health record‒based clinical prediction model: clinical pilot implementation initiative.","authors":"Randall W Grout, Mohammad Ateya, Baely DiRenzo, Sara Hart, Chase King, Joshua Rajkumar, Susan Sporrer, Asad Torabi, Todd A Walroth, Richard J Kovacs","doi":"10.1186/s12911-024-02773-z","DOIUrl":"10.1186/s12911-024-02773-z","url":null,"abstract":"<p><strong>Background: </strong>Atrial fibrillation (AF) is a major risk factor for ischemic stroke, and early AF diagnosis may reduce associated morbidity and mortality. A 10-variable predictive model (UNAFIED) was previously developed to estimate patients' 2-year AF risk. This study evaluated a clinical workflow incorporating UNAFIED for screening, education, and follow-up evaluation of patients visiting a cardiology clinic who may be at an elevated risk of developing AF within 2 years.</p><p><strong>Methods: </strong>Patients were included if they were aged ≥ 40 years with a scheduled in-person visit at the Eskenazi Health Cardiology Clinic between October 25, 2021, and August 10, 2022. Clinical decision support identified patients with an elevated AF risk. Initial screening with 1-lead electrocardiogram devices was offered, and routine clinical practice for diagnosis and management was followed. Physicians were surveyed on their use of the workflow, attitudes toward implementation, and perceived impact on patient care.</p><p><strong>Results: </strong>A total of 2827 patients had a clinic visit during the study period, of whom 1395 were eligible to be screened because they were classified as \"elevated risk\" by the UNAFIED predictive model. AF or atrial flutter diagnosis was newly documented for 29 patients during the study period. Of the newly diagnosed patients, 13 began anticoagulant therapy to mitigate stroke risk. Physicians (n = 13) who used the workflow most clinic days were more likely to indicate that it was easy to use, was not time-consuming, and improved patient care compared with physicians who only used the workflow occasionally.</p><p><strong>Conclusions: </strong>To our knowledge, this study is the first of its kind to demonstrate clinical application of an electronic health record-based AF predictive model. The newly documented diagnoses, however, did not solely result from implementation of UNAFIED. This non-invasive, inexpensive approach could be adopted by other sites wishing to proactively screen patients at elevated risk for AF. Other sites should verify the model's performance in their own settings and ensure compliance with evolving regulatory requirements where applicable.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"24 1","pages":"388"},"PeriodicalIF":3.3,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11657685/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142853027","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}