Hitachi, in collaboration with Partners Connected Health (PCH), has developed artificial intelligence (AI) technology which can predict the risk of 30-day hospital readmissions for heart failure patients.

The technology helps select appropriate patients to participate in a readmission prevention programme following hospital discharge. It uses deep learning to construct this prediction model and can explain the reason why patients were identified as being at high risk.

“Traditional machine learning can help us predict events, but as end-users, we can’t tell why the machine is predicting something a certain way,” said Senior Director at Partners Connected Health Innovation, Kamal Jethwani, MD, MPH.

“With this innovation, doctors and nurses using the algorithm will be able to tell exactly why a certain patient is at high risk for hospital admission, and what they can do about it. We want to enable our providers to act on this information, which is a step beyond the state-of-the-art today, in terms of machine learning algorithms,” continued Jethwani.

PCH simulated the readmission prediction programme among heart failure patients participating in the Partners Connected Cardiac Care Programme (CCCP), a remote monitoring and education programme designed to improve the management of heart failure patients at risk for hospitalisation.

The results were compared to data from approximately 12,000 heart failure patients hospitalised and discharged from the Partners HealthCare hospital network in 2014 and 2015. The analysis found that the prediction algorithm achieved a high accuracy, helping to reduce the number of patient readmissions.

The two companies said they will jointly conduct a prospective study, which evaluates the prediction programme by clinicians, and study how to integrate this within clinical workflows.

By using this new AI technology, Hitachi will provide solutions for the medical field, including solutions for insurance and pharmaceutical companies, emergency services, and other healthcare services where prediction-based on medical data can be utilised.

For more information contact, like us on Facebook or tweet us @eHealthNewsZA.