New AI Tool Developed to Reduce Death Risk in Hospitalized Patients

The AI tool, called CHARTWatch, acts as an early warning mechanism to alert healthcare providers, allowing them to take timely actions that improve patient outcomes.

A team of researchers, including an Indian-origin scientist, has developed an AI tool designed to reduce the risk of unexpected deaths in hospitals by identifying patients at high risk of health deterioration.

The AI tool, called CHARTWatch, acts as an early warning mechanism to alert healthcare providers, allowing them to take timely actions that improve patient outcomes.

The study, published in the Canadian Medical Association Journal (CMAJ), evaluated the system’s impact on preventing unplanned admissions to the intensive care unit (ICU).

Lead author Dr Amol Verma, a clinician-scientist at St Michael's Hospital, Unity Health Toronto, explained, “As AI tools are increasingly being used in medicine, it is important that they are evaluated carefully to ensure they are safe and effective. Our findings suggest that AI-based early warning systems are promising for reducing unexpected deaths in hospitals."

The study analyzed 13,649 patients aged 55-80 admitted to the general internal medicine (GIM) unit. CHARTWatch was used for 4,023 patients, while 9,626 were monitored before its implementation. Another 8,470 patients in subspecialty units did not use the AI tool.

Results showed a reduction in deaths, attributed to regular communication facilitated by CHARTWatch, which provided real-time alerts, emails to nursing teams twice a day, and daily notifications to the palliative care team.

The AI system also helped create a specific care pathway for high-risk patients, prompting increased monitoring by nurses and enhanced communication between medical staff.

Co-author Dr Muhammad Mamdani from the University of Toronto highlighted the importance of assessing real-world outcomes from the AI system, stating, “Understanding the real-world impacts of this promising technology is important."

The researchers believe CHARTWatch has the potential to support nurses and doctors in delivering high-quality care and preventing unexpected patient deaths.

AI Tools Enhancing Patient Care

Recently, a study revealed that AI technology can detect lung nodules leading to lung cancer nearly 3 years before symptoms.

A new study presented at the 2024 World Conference on Lung Cancer reveals the potential of AI-powered chest X-ray interpretation to detect lung nodules that could develop into early-stage lung cancer nearly three years before symptoms appear or an official diagnosis is made.

The research conducted at Phrapokklao Hospital’s Cancer Centre of Excellence in Bangkok, Thailand, used the Qure.ai chest X-ray AI solution, qXR, to analyze patient data.

Likewise, a 28-year-old man suffering from acute pulmonary thromboembolism (PE) due to a blood clot in his leg was successfully treated using an advanced AI tool.

Pulmonary thromboembolism is a severe condition that occurs when a blood clot travels through the bloodstream and becomes lodged in the lungs, potentially leading to life-threatening complications.

After seeking treatment at other hospitals without success, he was brought to Sir Gangaram Hospital, where he was treated by Dr VS Bedi, chairman of vascular surgery.