Prediction of Sudden Death Due to COVID-19 Using Machine Learning Models

The early classification of COVID-19 patients severity can help save lives by giving to doctors valuable instructions and guidelines for the cases that may need more attention to survive. This paper aims to classify cases depending on their severity into three classes: "survivor”, "sudden death” and "death” using electronic health records (HER). The first class represents positive cases discharged from the hospital after being treated for COVID-19. While the second and the third classes are describing the level of cases severity based on the interval of death. We called the highest severity class "sudden death” to identify critical cases with a high risk of death in the first two days of admission, while the "death” class includes severe cases with an interval of death beyond two days. The sudden death class represents the biggest challenge for this classification as the number of samples representing this case is very small. This paper presents a triage system for COVID-19 cases using four machine learning algorithms (KNN, Logistic Regression, SVM, and Decision tree). The best classification results were obtained using Logistic Regression and SVM models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Jordanian nurses' attitudes toward using electronic health records during COVID-19 pandemic.

Electronic health records (EHRs) have proven their effectiveness during the coronavirus disease (COVID-19) pandemic. However, successful implementation of EHRs requires assessing nurses' attitudes as they are considered the first line in providing direct care for patients. This study assessed Jordanian nurses' attitudes and examined factors that affect nurses' attitudes toward using EHRs. A cross-sectional, correlational design was used. A convenient sample of 130 nurses was recruited from three major public hospitals in Jordan. All Participants completed the Nurses' attitudes Towards Computerization (NATC) Questionnaire. The overall nurses' attitude was positive; the mean was 61.85 (SD = 10.97). Findings revealed no significant relationship between nurses' attitudes toward using EHRs and nurses' age, gender, education level, previous computer skills experience, years of work experience, and years of dealing with EHRs. However, the work unit was found to have a significant correlation with nurses' attitudes toward using EHRs. Therefore, nurse administrators should arrange for the conduct of educational workshops and continuous training programs considering the needs of the nurses.

Outpatient and inpatient anticoagulation therapy and the risk for hospital admission and death among COVID-19 patients.

BACKGROUND: Coronavirus disease 2019 (COVID-19) is associated with a hypercoagulable state. Limited data exist informing the relationship between anticoagulation therapy and risk for COVID-19 related hospitalization and mortality. METHODS: We evaluated all patients over the age of 18 diagnosed with COVID-19 in a prospective cohort study from March 4th to August 27th, 2020 among 12 hospitals and 60 clinics of M Health Fairview system (USA). We investigated the relationship between (1) 90-day anticoagulation therapy among outpatients before COVID-19 diagnosis and the risk for hospitalization and mortality and (2) Inpatient anticoagulation therapy and mortality risk. FINDINGS: Of 6195 patients, 598 were immediately hospitalized and 5597 were treated as outpatients. The overall case-fatality rate was 2•8% (n = 175 deaths). Among the patients who were hospitalized, the inpatient mortality was 13%. Among the 5597 COVID-19 patients initially treated as outpatients, 160 (2.9%) were on anticoagulation and 331 were eventually hospitalized (5.9%). In a multivariable analysis, outpatient anticoagulation use was associated with a 43% reduction in risk for hospital admission, HR (95% CI = 0.57, 0.38-0.86), p = 0.007, but was not associated with mortality, HR (95% CI=0.88, 0.50 - 1.52), p = 0.64. Inpatients who were not on anticoagulation (before or after hospitalization) had an increased risk for mortality, HR (95% CI = 2.26, 1.17-4.37), p = 0.015. INTERPRETATION: Outpatients with COVID-19 who were on outpatient anticoagulation at the time of diagnosis experienced a 43% reduced risk of hospitalization. Failure to initiate anticoagulation upon hospitalization or maintaining outpatient anticoagulation in hospitalized COVID-19 patients was associated with increased mortality risk. FUNDING: No funding was obtained for this study.