Predictive Modeling of COVID-19 Readmissions: Insights from Machine Learning and Deep Learning Approaches.

This project employs artificial intelligence, including machine learning and deep learning, to assess COVID-19 readmission risk in Malaysia. It offers tools to mitigate healthcare resource strain and enhance patient outcomes. This study outlines a methodology for classifying COVID-19 readmissions. It starts with dataset description and pre-processing, while the data balancing was computed through Random Oversampling, Borderline SMOTE, and Adaptive Synthetic Sampling. Nine machine learning and ten deep learning techniques are applied, with five-fold cross-validation for evaluation. Optuna is used for hyperparameter selection, while the consistency in training hyperparameters is maintained. Evaluation metrics encompass accuracy, AUC, and training/inference times. Results were based on stratified five-fold cross-validation and different data-balancing methods. Notably, CatBoost consistently excelled in accuracy and AUC across all tables. Using ROS, CatBoost achieved the highest accuracy (0.9882 ± 0.0020) with an AUC of 1.0000 ± 0.0000. CatBoost maintained its superiority in BSMOTE and ADASYN as well. Deep learning approaches performed well, with SAINT leading in ROS and TabNet leading in BSMOTE and ADASYN. Decision Tree ensembles like Random Forest and XGBoost consistently showed strong performance.

Propagation of a hospital-associated cluster of COVID-19 in Malaysia.

BACKGROUND: Hospitals are vulnerable to COVID-19 outbreaks. Intrahospital transmission of the disease is a threat to the healthcare systems as it increases morbidity and mortality among patients. It is imperative to deepen our understanding of transmission events in hospital-associated cases of COVID-19 for timely implementation of infection prevention and control measures in the hospital in avoiding future outbreaks. We examined the use of epidemiological case investigation combined with whole genome sequencing of cases to investigate and manage a hospital-associated cluster of COVID-19 cases. METHODS: An epidemiological investigation was conducted in a University Hospital in Malaysia from 23 March to 22 April 2020. Contact tracing, risk assessment, testing, symptom surveillance, and outbreak management were conducted following the diagnosis of a healthcare worker with SARS-CoV-2 by real-time PCR. These findings were complemented by whole genome sequencing analysis of a subset of positive cases. RESULTS: The index case was symptomatic but did not fulfill the initial epidemiological criteria for routine screening. Contact tracing suggested epidemiological linkages of 38 cases with COVID-19. Phylogenetic analysis excluded four of these cases. This cluster included 34 cases comprising ten healthcare worker-cases, nine patient-cases, and 15 community-cases. The epidemic curve demonstrated initial intrahospital transmission that propagated into the community. The estimated median incubation period was 4.7 days (95% CI: 3.5-6.4), and the serial interval was 5.3 days (95% CI: 4.3-6.5). CONCLUSION: The study demonstrated the contribution of integrating epidemiological investigation and whole genome sequencing in understanding disease transmission in the hospital setting. Contact tracing, risk assessment, testing, and symptom surveillance remain imperative in resource-limited settings to identify and isolate cases, thereby controlling COVID-19 outbreaks. The use of whole genome sequencing complements field investigation findings in clarifying transmission networks. The safety of a hospital population during this COVID-19 pandemic may be secured with a multidisciplinary approach, good infection control measures, effective preparedness and response plan, and individual-level compliance among the hospital population.

Case report : Actinomyces naeslundii complicating preterm labour in a trisomy-21 pregnancy.

Preterm birth is a global concern with considerable morbidity and mortality. Intrapartum infection is a known cause of preterm birth and Actinomyces infection is one of the infections contributing to preterm birth. We report a case of preterm birth of a trisomy-21 neonate to a mother with positive Actinomyces naeslundii from an intra-operative placental swab sample and discussed the relationship of this bacteria and preterm delivery, and the role of postpartum antibiotics use in this case.