METHODS: Permission to use and translate the original RAC-Q into the Malay language was obtained. The RAC-Q was then translated into the Malay language following the 10 steps proposed for the translation of a patient-reported outcome questionnaire. A pretest was conducted based on 30 inpatients to assess the appropriateness and clarity of the finalized translated questionnaire. A cross-sectional study was performed based on 138 inpatients from six adult wards of a teaching hospital so as to validate the translated questionnaire. The data were analyzed using R software version 4.1.3 (R Core Team, Vienna, Austria, 2020). The results were presented descriptively as numbers and percentages or means and standard deviations. A confirmatory factor analysis was performed using robust estimators.
RESULTS: The analysis showed that the measurement model of the RAC-Q Malay version (RAC-QM) fits well based on several fit indices: a standardized factor loading range from 0.40 to 0.73, comparative fit index (CFI) of 0.917, Tucker-Lewis fit index (TLI) of 0.904, root mean square error of approximation (RMSEA) of 0.06, and a standardized root mean square residual (SRMR) of 0.073. It has good reliability, with a Cronbach's alpha of 0.857 and a composite ratio of 0.857.
CONCLUSION: The RAC-QM demonstrated good psychometric properties and is valid and reliable based on the confirmatory analysis, and it can thus be used as a tool for evaluating the level of compassionate care in Malaysia.
METHODS: Anonymised data consisting of 44 independent predictor variables from 355 adults diagnosed with COVID-19, at a UK hospital, was manually extracted from electronic patient records for retrospective, case-control analysis. Primary outcomes included inpatient mortality, required ventilatory support, and duration of inpatient treatment. Pulmonary embolism sequala was the only secondary outcome. After balancing data, key variables were feature selected for each outcome using random forests. Predictive models were then learned and constructed using Bayesian networks.
RESULTS: The proposed probabilistic models were able to predict, using feature selected risk factors, the probability of the mentioned outcomes. Overall, our findings demonstrate reliable, multivariable, quantitative predictive models for four outcomes, which utilise readily available clinical information for COVID-19 adult inpatients. Further research is required to externally validate our models and demonstrate their utility as risk stratification and clinical decision-making tools.