Prediction and Classification of COVID-19 Admissions to Intensive Care Units (ICU) Using Weighted Radial Kernel SVM Coupled with Recursive Feature Elimination (RFE).

Healthcare systems have been under immense pressure since the beginning of the COVID-19 pandemic; hence, studies on using machine learning (ML) methods for classifying ICU admissions and resource allocation are urgently needed. We investigated whether ML can propose a useful classification model for predicting the ICU admissions of COVID-19 patients. In this retrospective study, the clinical characteristics and laboratory findings of 100 patients with laboratory-confirmed COVID-19 tests were retrieved between May 2020 and January 2021. Based on patients' demographic and clinical data, we analyzed the capability of the proposed weighted radial kernel support vector machine (SVM), coupled with (RFE). The proposed method is compared with other reference methods such as linear discriminant analysis (LDA) and kernel-based SVM variants including the linear, polynomial, and radial kernels coupled with REF for predicting ICU admissions of COVID-19 patients. An initial performance assessment indicated that the SVM with weighted radial kernels coupled with REF outperformed the other classification methods in discriminating between ICU and non-ICU admissions in COVID-19 patients. Furthermore, applying the Recursive Feature Elimination (RFE) with weighted radial kernel SVM identified a significant set of variables that can predict and statistically distinguish ICU from non-ICU COVID-19 patients. The patients' weight, PCR Ct Value, CCL19, INF-ß, BLC, INR, PT, PTT, CKMB, HB, platelets, RBC, urea, creatinine and albumin results were found to be the significant predicting features. We believe that weighted radial kernel SVM can be used as an assisting ML approach to guide hospital decision makers in resource allocation and mobilization between intensive care and isolation units. We model the data retrospectively on a selected subset of patient-derived variables based on previous knowledge of ICU admission and this needs to be trained in order to forecast prospectively.

Recall of Prior Knowledge in Medical Microbiology Among Medical Interns: A Multicenter Cross-Sectional Assessment in Saudi Arabia.

Background: Retention of basic biomedical sciences knowledge is of great importance in medical practice. This study aimed to provide some insights into medical interns' ability to recall theoretical knowledge of medical microbiology and to explore factors that affect its retention. Methods: In this cross-sectional study conducted between January and March 2019, an anonymized questionnaire with 10 validated multiple-choice questions about medical microbiology was distributed as hard copies to test the ability to recall knowledge of Saudi medical interns in three tertiary training hospitals in Riyadh, Saudi Arabia. Results: A total of 300 medical interns [164 females (54.7%) and 136 males (45.3%)], in three major tertiary medical care centers in Riyadh, Saudi Arabia, voluntarily participated in the study. Almost a third of participants, 107 (36.4%), graduated from medical schools adopting a traditional curriculum, whereas 184 (63.6%) graduated from medical schools adopting problem-based learning (PBL) instructional approach. The overall mean score out of 10 marks was 3.9±1.8 with almost 82% failures scoring less than six marks. Both total and pass/fail grades were significantly associated with interns who graduated from private colleges. Scores were not significantly associated with any of the investigated parameters except type of college (governmental vs private) with a p-value of 0.049. Conclusion: The current study revealed an overall poor recall of knowledge in microbiology among interns. Our findings suggest a need for a careful revision of curriculum to correct deficiencies, particularly in teaching medical microbiology. Integration of basic sciences is required as well as aligning teaching of basic medical sciences with clinical skills.