SALT LAKE CITY – Researchers at Intermountain Healthcare have developed a clinical decision support app that more quickly identifies when heart failure becomes advanced and a patient’s care needs have changed. “We found that clinical decision support can facilitate the early identification of patients needing advanced heart failure therapy and that its use was associated with significantly more patients visiting specialized heart facilities and longer survival,” said R. Scot Evans, lead author of a study on the app that was published in the Journal of Cardiac Failure recently. Using the app during the study, researchers found that it led to significantly improved detection of disease advancements and more intervention patients were alive after 30, 90 and 180 days compared to a control group. “The sooner advanced heart failure is diagnosed and patients begin to receive advanced, specialized treatment, the better they tend to do,” wrote Evans. When computer monitoring indicates a patient likely has advanced heart failure, the app automatically sends a secure email to the patient’s doctors, and includes the recommended therapy and all the relevant information that triggered the alert. It also provides a link to a secure Intermountain web-based page that provides further information, and lists phone numbers and links so doctors can easily connect the patients with advanced heart failure specialists.
BOSTON and TOKYO – Partners Connected Health and Hitachi are working together to develop artificial intelligence technology which can accurately predict the risk of hospital readmissions within 30 days for patients with heart failure.
“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,” said Dr. Kamal Jethwani, senior director, Partners Connected Health Innovation, in a statement. “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.”
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 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.
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, a remote monitoring and education program designed to improve the management of heart failure patients at risk for hospitalization.
Hitachi’s new AI technology uses deep learning to construct the prediction model. The company developed the technology for risk prediction with analyzing the results presented by deep learning and extracting the several dozens of actionable factors for each patient from the vast amount of data collected from heart failure patients. Through a standard statistical approach based on this risk prediction model, the extracted factors were used to calculate the risk of hospital readmission, and the relevance of the factors was calculated. Thus, this explainable AI technology can enhance prediction accuracy and the quality of medical decision-making.
Hitachi and the Partners Connected Health Innovation team will jointly conduct a prospective study, which evaluates the prediction program by clinicians, and study how to integrate this within clinical workflows.
SHAANXI, China – Scientists at several universities have developed a paper strip test that will allow heart failure patients to monitor their disease at home.
The fluorescent strip works with a smartphone-based reader (the UC-LFS platform) to identify the two antigens responsible for indicating progressive heart failure. A study on the platform was successful.
“The developed UC-LFS platform is demonstrated to be highly sensitive and specific for sample-to-answer prognosis of heart failure, which holds great potential for risk assessment and health monitoring of post-treatment patients at home,” said Feng Xu, one of the authors of a recently published paper on the study, in a statement.
The test uses 10 microliters of sample blood. Patients can use an accompanying app to analyze the information and send results to their physician.
“Comparing the results from (the U.S. Food & Drug Administration)-approved clinical methods, we obtained a good linear correlation, indicating the practical reliability and stability of our developed UC-LFS platform,” said Xu.