THANK YOU FOR SUBSCRIBING
Clinical variation management is vital in improving patient outcomes, reducing healthcare costs and handling financial risks. Its large scale application could address the enormous cost spent on procedures that don’t improve patient outcomes. Reducing clinical variation requires an analysis of massive amounts of data spread across multiple systems. Conventional analytics applications are not apt candidates for this task, but artificial intelligence is. AI with a vast amount of computational power can rapidly develop and measure adherence to highly sophisticated care process models. Flager hospitals have successfully employed an AI solution to improve care paths for pneumonia and sepsis and are on track to apply the same technology to more conditions over the coming months.
The initial step was challenging and included pulling out data from electronic health record (EHR), enterprise data warehouse, and surgical, financial and corporate performance systems. Then the data was brought to the clinical variation management application. Understanding which variables are essential to the task was challenging. The variables include costs, length of stay (LOS), duration of the encounter, actions such as medication orders, and vital signs. The AI solution used machine learning to understand the structure of data and patterns that unveiled the best pneumonia treatment approaches. The program then showed the direct variable costs, the average length of stay, readmission rates, and mortality rates along with the statistical significance of the data.
Even without a data scientist on board hospitals can improve patient safety and outcomes, increase efficiency, and boost bottom lines. As hospitals move toward clinical risk variation must be managed, and AI solution will be the perfect way to accomplish that goal with less cost. There is a positive response primarily due to the use of hospital data with the AI program, instead of data from scientific studies. As a result, the physicians are becoming confident that the results were based on data for patients like theirs. Following the successful pilot, Flager used the AI solution to improve its sepsis COPD, and heart failure care paths.