I recently watched a report on the BBC discussing the potential for artificial intelligence in the NHS. The potential benefits of AI and digital technology are clear, but how close are we to seeing broad adoption and material improvements to efficiency, cost and health outcomes as a result?
At Hitachi, we have an insatiable thirst for innovation which drives benefit to society... but realising our objectives is often more complicated and slower than necessary.
To overcome these challenges we need to improve the capacity for innovation in the NHS, embed a culture of co-creation and establish mechanisms to accelerate progress - only then will be break the deadlock and unlock the benefits technology can deliver.
Hitachi, Ltd. (TSE: 6501, Hitachi) today announced the development of artificial intelligence (AI) technology by Hitachi, in collaboration with Partners Connected Health, which can predict with high accuracy, the risk of hospital readmissions within 30 days for patients with heart failure. The AI technology helps select appropriate patients to participate in a readmission prevention program following hospital discharge, and can explain the reason why patients were identified as being at high risk. The 30-day readmission rate is regarded as one of the important indicators in hospital management, and can carry significant penalties for hospitals via the US Centers for Medicare and Medicaid (CMS) as part of the Affordable Care Act. This technology is an example of explainable AI, a new term currently defined as enabling machines to explain their decisions and actions to human users, and enabling them to understand, appropriately trust and effectively manage AI tools, while maintaining a high level of prediction accuracy. "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 Kamal Jethwani, MD, MPH, Senior Director, Partners Connected Health Innovation. "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." As part of the study, the Partners Connected Health Innovation team simulated the readmission prediction program among heart failure patients participating in the Partners Connected Cardiac Care Program (CCCP), a remote monitoring and education program designed to improve the management of heart failure patients at risk for hospitalization. These results were compared to data from approximately 12,000 heart failure patients hospitalized and discharged from the Partners HealthCare hospital network in 2014 and 2015. The analysis showed the prediction algorithm achieved a high accuracy of approximately AUC 0.71, and can significantly reduce the number of patient readmissions. (AUC, area under the curve, is a measure of prediction model performance with an ideal value range from 0 to 1.) As a result, approximately an additional US $7,000 savings per patient per year among the cohort of CCCP patients can be expected.