Objective: The study aims to investigate the factors causing the difference of stroke patients' in-hospital cost and study these factors on health outcome in terms of mortality.
Methods: Eight hundred and sixty-two in-patients with stroke in a tertiary hospital in China from 2017 to 2019 were included in the database. Descriptive statistics indexes were used to describe patients' in-hospital cost and mortality. Based on Elixhauser coding algorithms, multiple linear regression and logistic regressions (LRs) were used to evaluate the impact of factors identified from univariate analysis on in-hospital cost and mortality, respectively. In addition to LRs, a comparison study was then carried out with random forest, gradient boosting decision tree and artificial neural network.
Results: Factors affecting both cost and mortality are age, discharged day-of-week, length of stay, stroke subtype, other neurological disorders, renal failure, fluid and electrolyte disorders and total number of comorbidities.
Conclusion: With the increase of age, the mortality rate of in-patients (except for the juvenile) with stroke increases and the cost of hospitalization decreases. Intracerebral haemorrhage is the most devastating stroke for its highest mortality in short length of stay. Medical services should focus on these specific comorbidities.
Keywords: comorbidities; in-hospital cost; mortality; regression analysis; stroke.
© 2020 John Wiley & Sons Ltd.