We have hit a wall in predicting re-admissions using traditional clinical methods.

Using big data to keep heart failure patients out of hospital

The Ted Rogers Centre for Heart Research at the Peter Munk Cardiac Centre (PMCC) at Toronto General Hospital awarded its first-ever $1-million innovation grants to world-first projects working to alleviate the massive burden of heart failure on patients, loved ones and healthcare systems.

Dr. Douglas Lee, Ted Rogers Chair in Heart Function Outcomes and cardiologist at the PMCC, will lead the first funded project, creating a new machine learning model to predict prognoses of patients with heart failure, preventing unnecessary admissions to hospital.

The project marks a significant step forward in advancing solutions for a disease affecting more than a million Canadians, and costing the healthcare system $3 billion each year.

Heart failure is a leading cause of hospital readmissions that bear a substantial burden on the healthcare systems of most countries. In general, the disease is treated reactively: a patient experiences symptoms, heads to the emergency department and is admitted to hospital.

“We have hit a wall in predicting readmissions using traditional clinical methods,” says Dr. Lee. “As it stands, without the right tools in place, low-risk patients may be unnecessarily admitted while high-risk patients could be inadvertently discharged home.”

To better predict outcomes and improve care, the team will develop a new algorithm based on an array of information that includes biomarkers, physiologic data, blood samples and a patient’s own reported symptoms. Combined with evolving technology such as remote patient monitoring and machine learning, the aim is to develop a complete, integrated model to predict heart failure readmissions.