Neural networks and hospital length of stay: an application to support healthcare management with national benchmarks and thresholds

Translational artificial intelligence-led optimization and realization of estimated discharge with a supportive weekend interprofessional flow team (TAILORED-SWIFT)

Weekend discharges occur less frequently than discharges on weekdays, contributing to hospital congestion. Artificial intelligence algorithms have previously been derived to predict which patients are nearing discharge based upon ward round notes. In this implementation study, such an artificial intelligence algorithm was coupled with a multidisciplinary discharge facilitation team on weekend shifts. This approach was implemented in a tertiary hospital, and then compared to a historical cohort from the same time the previous year. There were 3990 patients included in the study. There was a significant increase in the proportion of inpatients who received weekend discharges in the intervention group compared to the control group (median 18%, IQR 18-20%, vs median 14%, IQR 12% to 17%, P = 0.031). There was a corresponding higher absolute number of weekend discharges during the intervention period compared to the control period (P = 0.025). The studied intervention was associated with an increase in weekend discharges and economic analyses support this approach as being cost-effective. Further studies are required to examine the generalizability of this approach to other centers.

Implementation of Lean Management Tools Using an Example of Analysis of Prolonged Stays of Patients in a Multi-Specialist Hospital in Poland

Healthcare institutions in Poland constantly encounter challenges related both to the quality of provided services and to the pressures associated with treatment effectiveness and economic efficiency. The implemented solutions have a goal of improving the service quality of lowering the continuously increasing operational costs. The aim of this paper is to present the application of Lean Management (LM) tools in a Polish hospital, which allowed for the identification of prolonged stays as one of the main issues affecting the service costs and the deteriorating financial results of the hospital. The study was conducted in the neurology department and involved an analysis of data for the whole of 2019 and the first half of 2022. In addition, surveys were conducted among the medical staff to help identify the main causes of prolonged stays. Methods of data analysis and feasible solutions were developed in order to improve the economic efficiency of the unit. The analysis shows that the application of LM tools may contribute to improvement in the functioning of hospitals and that further studies should focus on the development of the method to evaluate efficiency of the implemented solutions intended at shortening the hospital stays of the patients.

Study of Hospitalization Costs in Patients with Cerebral Ischemia Based on E-CHAID Algorithm

Background. The aging of the population has led to a rapid increase in the prevalence of most neurological diseases between 1990 and 2016, with a growth rate of up to 117%, which has put enormous pressure on medical insurance funds. As one of the core diseases of disease diagnosis grouping, the hospitalization cost composition and grouping research of patients with cerebral ischemic disease can help to determine scientific payment standards and reduce the economic burden of patients. Aim. We aimed to understand the cost composition and influencing factors of hospitalized patients with cerebral ischemic diseases and to identify a reasonable cost grouping scheme. Methods. The data come from the homepage of medical records of inpatients with cerebral ischemia in a tertiary hospital in Sichuan Province from 2018 to 2020. After cleaning the data, a total of 5,204 pieces of data were obtained. Nonparametric tests and gamma regression models were used to explore the influencing factors of hospitalization costs. Taking the influencing factors as the predictor variables and the hospitalization cost as the target variable, the exhaustive Chi-squared automatic interaction detector (E-CHAID) algorithm was used to form the costs grouping, and the payment standard of the hospitalization cost for each group was determined. The rationality of cost grouping was evaluated by coefficient of variation (CV) and Kruskal–Wallis H test. Results. From 2018 to 2020, the average hospital stay of 5,204 inpatients with cerebral ischemic disease was 10.70 days, and the average hospitalization cost was 17,206.09 RMB yuan. Among the hospitalization costs, diagnosis costs and drug costs accounted for the highest proportion, accounting for 41.18% and 22.38%, respectively, in 2020. Gender, age, admission route, comorbidities and complications, super length of stay (>30 days), and discharge mode had significant effects on hospitalization costs (P < 0.05). Patients were divided into 10 cost groups, and the grouping nodes included comorbidities and complications, discharge mode, age, gender, and admission route. The CV of 9 of the 10 cost groups is less than or equal to 1. The Kruskal–Wallis H test showed that the difference between groups was statistically significant (P < 0.05). Conclusion. The cost grouping of patients with cerebral ischemic diseases based on the E-CHAID algorithm is reasonable. This study examined the effects of super length of stay (>30 days), comorbidities and complications, and age on hospitalization cost in patients with cerebral ischemic disease. This study can provide a theoretical basis for advancing the China Healthcare Security Diagnosis Related Groups (CHS-DRG) grouping program and medical expense payment, thereby reducing the disease burden of patients.