دورية أكاديمية
Towards Predicting Length of Stay and Identification of Cohort Risk Factors Using Self-Attention-Based Transformers and Association Mining: COVID-19 as a Phenotype.
العنوان: | Towards Predicting Length of Stay and Identification of Cohort Risk Factors Using Self-Attention-Based Transformers and Association Mining: COVID-19 as a Phenotype. |
---|---|
المؤلفون: | Alam F; Department of Computer Science & Engineering, Oakland University, 115 Library Drive, Rochester, MI 48309, USA., Ananbeh O; Department of Computer Science & Engineering, Oakland University, 115 Library Drive, Rochester, MI 48309, USA., Malik KM; Department of Computer Science & Engineering, Oakland University, 115 Library Drive, Rochester, MI 48309, USA., Odayani AA; Infection Control Center of Excellence Prince Sultan Military Medical City, Riyadh 12233, Saudi Arabia., Hussain IB; Infection Control Center of Excellence Prince Sultan Military Medical City, Riyadh 12233, Saudi Arabia., Kaabia N; Infection Control Center of Excellence Prince Sultan Military Medical City, Riyadh 12233, Saudi Arabia., Aidaroos AA; Infection Control Center of Excellence Prince Sultan Military Medical City, Riyadh 12233, Saudi Arabia., Saudagar AKJ; Information Systems Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi Arabia. |
المصدر: | Diagnostics (Basel, Switzerland) [Diagnostics (Basel)] 2023 May 17; Vol. 13 (10). Date of Electronic Publication: 2023 May 17. |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: MDPI AG Country of Publication: Switzerland NLM ID: 101658402 Publication Model: Electronic Cited Medium: Print ISSN: 2075-4418 (Print) Linking ISSN: 20754418 NLM ISO Abbreviation: Diagnostics (Basel) Subsets: PubMed not MEDLINE |
أسماء مطبوعة: | Original Publication: Basel, Switzerland : MDPI AG, [2011]- |
مستخلص: | Predicting length of stay (LoS) and understanding its underlying factors is essential to minimizing the risk of hospital-acquired conditions, improving financial, operational, and clinical outcomes, and better managing future pandemics. The purpose of this study was to forecast patients' LoS using a deep learning model and to analyze cohorts of risk factors reducing or prolonging LoS. We employed various preprocessing techniques, SMOTE-N to balance data, and a TabTransformer model to forecast LoS. Finally, the Apriori algorithm was applied to analyze cohorts of risk factors influencing hospital LoS. The TabTransformer outperformed the base machine learning models in terms of F1 score (0.92), precision (0.83), recall (0.93), and accuracy (0.73) for the discharged dataset and F1 score (0.84), precision (0.75), recall (0.98), and accuracy (0.77) for the deceased dataset. The association mining algorithm was able to identify significant risk factors/indicators belonging to laboratory, X-ray, and clinical data, such as elevated LDH and D-dimer levels, lymphocyte count, and comorbidities such as hypertension and diabetes. It also reveals what treatments have reduced the symptoms of COVID-19 patients, leading to a reduction in LoS, particularly when no vaccines or medication, such as Paxlovid, were available. |
References: | BMC Infect Dis. 2021 Jul 22;21(1):700. (PMID: 34294037) Front Cell Infect Microbiol. 2022 Feb 25;11:777070. (PMID: 35282595) Eur J Clin Invest. 2021 Mar;51(3):e13406. (PMID: 33043432) Int J Lab Hematol. 2020 Dec;42(6):761-765. (PMID: 32779838) JAMA Netw Open. 2021 Jan 4;4(1):e2034266. (PMID: 33464319) Jt Comm J Qual Patient Saf. 2011 May;37(5):217-27. (PMID: 21618898) PLoS One. 2021 Oct 28;16(10):e0258351. (PMID: 34710097) Sci Data. 2016 May 24;3:160035. (PMID: 27219127) BMJ. 2022 Jun 15;377:o1431. (PMID: 35705219) NPJ Digit Med. 2018 May 8;1:18. (PMID: 31304302) J Hosp Med. 2016 Nov;11(11):757-762. (PMID: 27352032) J Biomed Inform. 2021 Jun;118:103778. (PMID: 33872817) Med Biol Eng Comput. 2021 Mar;59(3):483-496. (PMID: 33544271) |
معلومات مُعتمدة: | 959 Deputyship for Research & Innovation, Ministry of Education in Saudi Arabia |
فهرسة مساهمة: | Keywords: COVID-19; association mining; clinical informatics; deep learning; machine learning; transformer |
تواريخ الأحداث: | Date Created: 20230527 Latest Revision: 20230530 |
رمز التحديث: | 20240628 |
مُعرف محوري في PubMed: | PMC10216944 |
DOI: | 10.3390/diagnostics13101760 |
PMID: | 37238244 |
قاعدة البيانات: | MEDLINE |
تدمد: | 2075-4418 |
---|---|
DOI: | 10.3390/diagnostics13101760 |