By Abhishek Vadlakonda |
February 28, 2019
Healthcare organizations collect data on patient health, diseases, claims, lab test details etc and save them as Electronic Health Records (EHR). EHRs help clinicians understand the patient’s medical history and their ongoing conditions.
While most organizations use this data to understand things like how many patients were admitted in the last month or how many surgical infections occurred in the last quarter of the total surgeries performed etc., this is descriptive analytics. While this information is good for understanding and helps in hospital operations allowing doctors to know about their patients’ health history, it does not give any forecasting or trends analysis.
This is where the need for predictive analytics comes in. Predictive analytics has the capability to predict the course of future events using historical data. To predict future events, predictive analytics requires a huge amount of real-time data to build models and generate an accurate, detailed and precise trend of events.
A recent study observed that out of all organizations which implement clinical predictive analytics, 82% cite improved patient care, 63% cite reduced readmission rates and 62% cite improved overall health outcomes. One predictive analytics tool developed at a leading clinic cut the time between initial symptoms and treatment by half. It also reduced manual screening hours by 72%, allowing nurses to focus on other care duties without putting patients at risk.
Predictive analytics has a wide array of applications in the healthcare sector, the following are some of them:
Chronic disease management and population health management
An organization can predict the chances of occurrence of chronic diseases with the help of predictive analytics and help patients be cautious to avoid health problems that are costly and difficult to treat. Based on patient EHR, lab tests data, claims data and other data points with the help of predictive analytics, hospitals can create RISK SCORES for patients. This in turn helps warning patients with chronic diseases.
Avoiding 30-day hospital readmissions
Predictive analytics can help hospitals by predicting when a patient’s risk factors indicate a high likelihood for readmission within the 30-day window. Predictive analytics tools that identify patients with factors that produce a high impact on the likelihood of readmission can give hospitals an extra indication of when to focus resources on follow-up and how to design discharge planning protocols to prevent speedy returns to the hospital.
Effective Care management of in-patients
In-patients face numerous risks of infection, sepsis and sudden deterioration in the disease condition. With the help of predictive analytics, hospitals can predict these cases and help doctors with the course of action. At an Alabama hospital, it was found that combining predictive analytics and clinical decision support (CDS) tools could reduce sepsis mortality by more than half. The analytics-driven strategy exceeded the accuracy of existing gold-standard tools.
Supply chain management at hospitals
The supply chain is a major cost center for organizations. By optimizing the supply chain, organizations can cut unnecessary expenditures and increase efficiency. Predictive analytics tools are in high demand in hospitals which are aiming to gain more actionable insights and in turn improve the efficiency of the supply chain. According to a 2017 health report, only 17% of hospitals currently use automated or data-driven solutions to manage their supply chains. In addition, another study found that using analytical tools to monitor the supply chain and make proactive, data-driven decisions about spending could save hospitals almost $10 million per year.
Developing new therapies and precision medicine:
Predictive analytics are becoming a supplement to traditional clinical trials and helping in developing new therapies and precision medicine. “In silico” testing (performed on a computer or via computer simulation) is a way to reduce the need to recruit patients for complex and costly clinical trials while speeding up the evaluation of new therapies.
FDA Commissioner Scott Gottlieb, MD, after the passage of the 21st Century Cures Act said “FDA’s Center for Drug Evaluation and Research (CDER) is currently using modeling and simulation to predict clinical outcomes, inform clinical trial designs, support evidence of effectiveness, optimize dosing, predict product safety, and evaluate potential adverse event mechanisms”. In silico models are being used to create control groups for trials related to degenerative conditions such as Parkinson’s disease, Huntington’s disease, and Alzheimer’s, the FDA added.
Predictive analytics and clinical decision support tools can therefore play key roles in translating new drugs into precision therapies.