دورية أكاديمية
Deep learning-based prediction of heart failure rehospitalization during 6, 12, 24-month follow-ups in patients with acute myocardial infarction.
| العنوان: | Deep learning-based prediction of heart failure rehospitalization during 6, 12, 24-month follow-ups in patients with acute myocardial infarction. |
|---|---|
| المؤلفون: | Bat-Erdene BI; Department of Computer Science, 34933Chungbuk National University, Cheongju, South Korea., Zheng H; Department of Computer Science, 34933Chungbuk National University, Cheongju, South Korea., Son SH; Department of Computer Science, 34933Chungbuk National University, Cheongju, South Korea., Lee JY; Department of Computer Science, 34933Chungbuk National University, Cheongju, South Korea. |
| المصدر: | Health informatics journal [Health Informatics J] 2022 Apr-Jun; Vol. 28 (2), pp. 14604582221101529. |
| نوع المنشور: | Journal Article; Research Support, Non-U.S. Gov't |
| اللغة: | English |
| بيانات الدورية: | Publisher: SAGE Publications Country of Publication: England NLM ID: 100883604 Publication Model: Print Cited Medium: Internet ISSN: 1741-2811 (Electronic) Linking ISSN: 14604582 NLM ISO Abbreviation: Health Informatics J Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: London : SAGE Publications Original Publication: Sheffield, UK : Sheffield Academic Press, [1997- |
| مواضيع طبية MeSH: | Deep Learning* , Heart Failure*/diagnosis , Heart Failure*/therapy , Myocardial Infarction*/diagnosis , Myocardial Infarction*/therapy, Follow-Up Studies ; Humans ; Patient Readmission |
| مستخلص: | Heart failure is a clinical syndrome that occurs when the heart is too weak or stiff and cannot pump enough blood that our body needs. It is one of the most expensive diseases due to frequent hospitalizations and emergency room visits. Reducing unnecessary rehospitalizations is also an important and challenging task that has the potential of saving healthcare costs, enabling discharge planning, and identifying patients at high risk. Therefore, this paper proposes a deep learning-based prediction model of heart failure rehospitalization during 6, 12, 24-month follow-ups after hospital discharge in patients with acute myocardial infarction (AMI). We used the Korea Acute Myocardial Infarction-National Institutes of Health (KAMIR-NIH) registry which included 13,104 patient records and 551 features. The proposed deep learning-based rehospitalization prediction model outperformed traditional machine learning algorithms such as logistic regression, support vector machine, AdaBoost, gradient boosting machine, and random forest. The performance of the proposed model was accuracy, the area under the curve, precision, recall, specificity, and F1 score of 99.37%, 99.90%, 96.86%, 98.61%, 99.49%, and 97.73%, respectively. This study showed the potential of a deep learning-based model for cardiology, which can be used for decision-making and medical diagnosis tool of heart failure rehospitalization in patients with AMI. |
| فهرسة مساهمة: | Keywords: acute myocardial infarction; decision support system; heart failure; hospital readmission; medical diagnosis; rehospitalization |
| تواريخ الأحداث: | Date Created: 20220519 Date Completed: 20220523 Latest Revision: 20220621 |
| رمز التحديث: | 20231215 |
| DOI: | 10.1177/14604582221101529 |
| PMID: | 35587458 |
| قاعدة البيانات: | MEDLINE |
Full Text Finder | تدمد: | 1741-2811 |
|---|---|
| DOI: | 10.1177/14604582221101529 |