Research Brief: Healthcare Systems
Project Brief
Type of Research: Healthcare Systems
Motivation for Research: Despite several improvements in various domains of healthcare systems, inability to reduce patients’ readmission rates is still a major problem faced by healthcare providers. Readmissions basically lead to the use of healthcare resources by the same person twice instead of being utilized by another patient. Furthermore, readmission rate is used as a potential measure of healthcare quality. The high readmission rates may be due to a poor quality of care provided. Thus, having a high readmission rate could tarnish the reputation of the healthcare facilities as well as reduce their reimbursements from the insurance companies. The goal of this research is to quantify the risk of hospital readmissions by analyzing significant factors in patients.
Research Approach
In this research, a data analysis and predictive modeling approach is adopted to identify the predictors of readmissions using a big dataset of hospitalized patients. We analyze a total of 22,388 records for specific group of patients in a one-year period. Our analysis shows a total readmission rate of 5.58% in the dataset. We have analyzed readmission rates based on various factors such as patient’s age, gender, claim type, line of business, and whether the patient was categorized under outpatient or professional subcategories.
We have currently identified the number of readmissions occurring throughout the course of one year. The next step of our analysis would be to bifurcate these readmissions into the time interval of that they occur to find the respective readmission rates. The main focus of our analysis would be the 30-days readmissions as it is the time frame considered by Centers for Medicare and Medicaid Services. We are also interested to analyze the significant factors for readmissions occurring within 7 and 15 days of prior discharge. Additionally, our data shows that significant number of readmissions occur within 90 days of the index admission discharge. Hence, we would like to analyze the significant factors for readmissions occurring within 45, 60, and 90 days of time-interval. Finally, we will develop a predictive model for each of the time frames. We believe this could help in identifying the significant factors that cause readmission in each time interval.
Key Findings
- The readmission rate is higher for male patients compared to female patients.
- Patients between 21 to 40 years had the highest readmission rate (i.e., 13%) followed by the age group of younger than 20 years, which had 7% readmission rate.
- Our primary analysis presented differences in the readmission rate based on where the patient was treated.