Healthcare organizations are focused on providing the best possible care while managing resources effectively during the best of times. Part of that process is limiting readmissions, where patients return to the hospital after being discharged. Understanding what might cause a readmission is crucial during crises like COVID-19, since the patient population is not just limited to those suffering from the virus.
Right now, hospitals and health systems are under tremendous strain for resources across every aspect, be it shortages in personal protective equipment (PPE), ventilators, beds or staff hours. Being able to understand what resources are needed for non-COVID patients helps the health systems have a better window into where they might need to request additional materials and manpower support.
A Modern Analytics Solution for Hospital Readmissions
Qlik, Snowflake and DataRobot have come together to create a modern analytics platform that enables the real-time analytics needed to predict patient readmittance, which, in turn, helps plan for COVID-19 surge capacity. It’s a combination of a cloud data platform, enterprise AI and machine learning for predictive modeling and actionable business intelligence. A full video demo of the solution can be found here: https://youtu.be/9wbddnaFtpk.
Cloud data platform – Executing analytics against an online transactional processing system (OLTP), especially an electronic medical records system, isn’t best practice. This is especially true when considering machine learning predictive modeling. Also, OLTP systems don’t always keep historical data, which is very relevant to best predicting what conditions factor into readmittance. Predictive analytics that leverage machine learning need a scalable data warehouse like Snowflake to incorporate the historical data with the agility to keep it refreshed with real-time data.
Building a predictive model – There are hundreds of parameters that could factor into readmission. To understand the underlying issues, you need a predictive model like the ones possible with DataRobot, the leader in enterprise AI and machine learning. With the click of a button, DataRobot dynamically generated and tested out 83 different enterprise modeling approaches to find the best model, all without code. That model was then deployed with one click directly from DataRobot into Qlik to power the analytics needed to assess current and future needs.
Analytics that creates actionable intelligence with machine learning – With Qlik reading the live data from Snowflake and executing the predictive model from DataRobot right within the Qlik application, healthcare decision-makers have an up-to-date window into their current state of care, while also getting a data-driven sense of the strategies they need to execute to best serve their entire patient population. As analytics isn't a side hustle for clinicians, this solution can be embedded directly into their existing workflow where they can take action.
NHS Tackles Hospital Readmissions Amongst COVID-19 Surge
“There are so many areas where data science can help enable more effective care, from live and capacity demand management, to predicting length of stay, to alignment on discharge and lower care demands for patients exiting acute care. For example, being able to understand our current patient population’s risk for readmittance is crucial to effectively executing unscheduled demand forecasting to manage an influx of crisis related patients,” said Rob O’Neill, Head of Information for University Hospitals of Morecambe Bay NHS. “Combining data science and analytics through an integrated platform of Qlik and DataRobot will help us more confidently understand our current needs, and predict what resources we will need to deliver complete care to our entire patient population.”
The solution of Qlik, Snowflake and DataRobot enables organizations like the NHS to drill down into specific modalities and departments to get a clear understanding of the where/how/why of readmittance trends. For example, providers can often recommend a wide array of options post-discharge, ranging from home healthcare services to temporary placement in a skilled nursing facility. These services may be critical to prevent readmission, but to conserve resources it's important to target them appropriately. Below is an exploration of readmittance of patients for a selected hospital within a health system followed by a view into the subset of patients who are currently in the systems’ ICU and have been readmitted in the past for two selected conditions.
We can see there is a very high readmittance rate for this
population. Now leveraging real-time data from Snowflake and the predictive
model from DataRobot, we can cross-correlate directly in Qlik to understand and
predict much more clearly how to plan around current care needs, capacity and
This visibility gives front line caregivers both the targeted population they need to focus on for potential readmittance issues, but also the underlying reasons related to each patient to even further focus the care plan.It's also worth noting that healthcare payers are keenly interested in preventing readmissions to improve patient experience and reduce costs. They can use these targeted predictions and visualizations to provide targeted follow-up care and care management.
The COVID-19 pandemic and its hourly changing conditions have put a premium on healthcare systems being able to make decisions in real-time while also predicting as much as possible what resources they will need for likely surges. Qlik, Snowflake, and DataRobot are bringing together a real-time data warehouse, machine learning predictive modeling and modern business intelligence to help make readmittance data part of the solution for COVID-19 related care. To view a full demo video of the solution, go to https://youtu.be/9wbddnaFtpk.