8th ACM IKDD CODS and 26th COMAD | 2021
Wound and Episode Level Readmission Risk or Weeks to Readmit: Why do patients get readmitted? How long does it take for a patient to get readmitted?
Abstract
The Affordable care Act of 2010 had introduced the readmission reduction program in 2012 to reduce avoidable readmissions to control rising healthcare costs. Wound care impacts 15% [16] of Medicare beneficiaries, making it one of the major contributors of medicare health care cost. Health plans have been exploring proactive health care services that can prevent wound recurrences and readmissions from controlling wound care costs. With the rising costs of the Wound care industry, it has become of paramount importance to reduce wound recurrences & patient readmissions. What factors are responsible for a Wound to recur, which ultimately leads to hospitalization or readmission? Is there a way to identify the patients at risk of readmission before the occurrence using data-driven analysis? Patient readmission risk management has become critical for patients suffering from chronic wounds such as diabetic ulcers, pressure ulcers, and vascular ulcers. Understanding the risk & the factors that cause patient readmission can help care providers and patients avoid wound recurrences. Our work focuses on identifying patients who are at high risk of readmission and determining the time period within which a patient might get readmitted. Frequent readmissions add financial stress to the patient & Health plan and deteriorate the patient’s quality of life. Having this information can allow a provider to set up preventive measures that can delay, if not prevent, patients’ readmission. On a combined wound & episode-level dataset of patient’s wound care information, our extended autoprognosis achieves a recall of 0.92 and a precision of 0.92 for predicting a patient’s readmission risk. For new patient class, precision and recall are as high as 0.91 and 0.98, respectively. We can also predict the amount of time (in weeks) it might take after a patient’s discharge event for a readmission event to occur through our model with a mean absolute error of 2.3 weeks.