The continuing efforts to reduce hospital readmission rates in the US have largely been driven by the great understanding of readmission rates among individuals and the associated costs to the health system. Patients with serious and chronic illnesses are treated in the hospital and then discharged. Unfortunately, according to multiple studies, up to 25% of these patients will be readmitted within 30 days to be treated again, often with less favourable outcomes. With a focus on value-based care, providers are trying to prevent unnecessary readmissions and improve patient care outcomes. Readmission can be significantly reduced by taking steps while the patient is still hospitalized, defining different actions during discharge, and taking steps post discharge to ensure compliance with home care regimens.
Readmissions risk prediction can require data about the specific patient’s recent care, their current condition, treatment, their home life and other risk factors from electronic medical records. AI models can use this information to provide a proactive assessment of their risk and notify clinicians while the patient is still hospitalized. AI can provide the reasons that will lead to readmission and also provide recommendations for the types of treatments that are most likely to be successful given the patient’s history. The reason codes are valuable to clinicians because they can pinpoint areas to focus on when developing a care plan for the patient and prevent unnecessary and costly tests.
This solution can be leveraged beyond predicting readmissions to offer personalized treatment suggestions, further ensuring patients stay out of the hospital after undergoing surgery. This app demoed using public data AI, can also be leveraged to offer personalized treatment recommendations for patients during their hospital stay.
The Hospital Readmission App demonstrates the use of machine learning models by business users in the context of hospital readmissions. Based on patient data, users can view predictions of patient readmission, forecast readmission rates, and identify relevant readmission factors. This solution helps identify patients at the highest risk for readmission can reduce quality gaps when coupled with patient-centred interventions
This solution is powered by the H2O AI Cloud Driverless AI AutoML, H2O-3, and H2O.ai Wave. The data science approaches include genetic algorithm, advanced feature engineering, GLM, GBM, XGBoost, ensemble stacking, and Shapley value estimation, among others.