AI-Based System Significantly Reduces Hospital Deaths by Identifying High-Risk Patients
2 Sources
2 Sources
[1]
AI-based system reduces hospital deaths by identifying high-risk patients
Canadian Medical Association JournalSep 16 2024 Can artificial intelligence (AI) help reduce deaths in hospital? An AI-based system was able to reduce risk of unexpected deaths by identifying hospitalized patients at high risk of deteriorating health, found new research published in CMAJ (Canadian Medical Association Journal) https://www.cmaj.ca/lookup/doi/10.1503/cmaj.240132. Rapid deterioration among hospitalized patients is the primary cause of unplanned admission to the intensive care unit (ICU). Previous research has attempted to use technology to identify these patients, but evidence is mixed about the application of prediction tools to help vulnerable patients at highest risk. Researchers from Unity Health Toronto, ICES, and the University of Toronto studied the effectiveness of CHARTWatch, an AI-based early warning system used on the general internal medicine (GIM) ward at St. Michael's Hospital after 3 years of development and testing. The study included 13 649 patients aged 55-80 years admitted to GIM (9626 in the pre-intervention period and 4023 using CHARTWatch) and 8470 admitted to subspeciality units that did not use CHARTWatch. During the 19-month-long intervention period, 482 patients in GIM became high-risk, compared with 1656 patients who became high risk in the 43-month-long pre-intervention period. There were fewer nonpalliative deaths in the CHARTWatch group than in the pre-intervention group (1.6% v. 2.1%). As AI tools are increasingly being used in medicine, it is important that they are evaluated carefully to ensure that they are safe and effective. Our findings suggest that AI-based early warning systems are promising for reducing unexpected deaths in hospitals." Dr. Amol Verma, lead author, clinician-scientist at St. Michael's Hospital, Unity Health Toronto, and Temerty professor of AI research and education in medicine, University of Toronto, Toronto, Ontario Regular communications helped reduce deaths as CHARTWatch engaged clinicians with real-time alerts, twice-daily emails to nursing teams, and daily emails to the palliative care team. The team also created a care pathway for high-risk patients with increased monitoring by nurses, enhanced communication between nurses and physicians, and prompts to encourage physicians to reassess patients. "Ultimately, this study shows how AI systems can support nurses and doctors in providing high-quality care," says Dr. Verma. The authors hope that AI solutions like CHARTWatch can improve patient health and avoid premature deaths. "This important study evaluates the outcomes associated with the complex deployment of the entire AI solution, which is critical to understanding the real-world impacts of this promising technology," says coauthor Dr. Muhammad Mamdani, vice president of data science and advanced analytics at Unity Health Toronto and director of the University of Toronto Temerty Faculty of Medicine Centre for AI Research and Education in Medicine. "We hope other institutions can learn from and improve upon Unity Health Toronto's experiences to benefit the patients they serve. Unity Health Toronto is a collaborative leader already helping to spread our AI tools via innovative partnerships with more to come." A second article https://www.cmaj.ca/lookup/doi/10.1503/cmaj.240363 provides a snapshot of what physicians should know if they are thinking of using AI scribes in clinical practice, including the importance of obtaining patient consent, reviewing AI-generated notes for errors, and ensuring the software complies with local privacy legislation. Canadian Medical Association Journal Journal references: Verma, A. A., et al. (2024) Clinical evaluation of a machine learning-based early warning system for patient deterioration. CMAJ. doi.org/10.1503/cmaj.240132. Agarwal, P., et al. (2024) Artificial intelligence scribes in primary care. CMAJ. doi.org/10.1503/cmaj.240363.
[2]
AI-based tool reduces risk of death in hospitalized patients, finds study
Can artificial intelligence (AI) help reduce deaths in hospital? An AI-based system was able to reduce risk of unexpected deaths by identifying hospitalized patients at high risk of deteriorating health, found new research published in Canadian Medical Association Journal. Rapid deterioration among hospitalized patients is the primary cause of unplanned admission to the intensive care unit (ICU). Previous research has attempted to use technology to identify these patients, but evidence is mixed about the application of prediction tools to help vulnerable patients at highest risk. Researchers from Unity Health Toronto, ICES, and the University of Toronto studied the effectiveness of CHARTWatch, an AI-based early warning system used on the general internal medicine (GIM) ward at St. Michael's Hospital after 3 years of development and testing. The study included 13,649 patients aged 55-80 years admitted to GIM (9,626 in the pre-intervention period and 4,023 using CHARTWatch) and 8,470 admitted to subspeciality units that did not use CHARTWatch. During the 19-month-long intervention period, 482 patients in GIM became high-risk, compared with 1,656 patients who became high risk in the 43-month-long pre-intervention period. There were fewer nonpalliative deaths in the CHARTWatch group than in the pre-intervention group (1.6% v. 2.1%). "As AI tools are increasingly being used in medicine, it is important that they are evaluated carefully to ensure that they are safe and effective," says lead author Dr. Amol Verma, a clinician-scientist at St. Michael's Hospital, Unity Health Toronto, and Temerty professor of AI research and education in medicine, University of Toronto, Toronto, Ontario. "Our findings suggest that AI-based early warning systems are promising for reducing unexpected deaths in hospitals." Regular communications helped reduce deaths as CHARTWatch engaged clinicians with real-time alerts, twice-daily emails to nursing teams, and daily emails to the palliative care team. The team also created a care pathway for high-risk patients with increased monitoring by nurses, enhanced communication between nurses and physicians, and prompts to encourage physicians to reassess patients. "Ultimately, this study shows how AI systems can support nurses and doctors in providing high-quality care," says Dr. Verma. The authors hope that AI solutions like CHARTWatch can improve patient health and avoid premature deaths. "This important study evaluates the outcomes associated with the complex deployment of the entire AI solution, which is critical to understanding the real-world impacts of this promising technology," says co-author Dr. Muhammad Mamdani, vice president of data science and advanced analytics at Unity Health Toronto and director of the University of Toronto Temerty Faculty of Medicine Centre for AI Research and Education in Medicine. "We hope other institutions can learn from and improve upon Unity Health Toronto's experiences to benefit the patients they serve. Unity Health Toronto is a collaborative leader already helping to spread our AI tools via innovative partnerships with more to come." A second article provides a snapshot of what physicians should know if they are thinking of using AI scribes in clinical practice, including the importance of obtaining patient consent, reviewing AI-generated notes for errors, and ensuring the software complies with local privacy legislation.
Share
Share
Copy Link
A groundbreaking AI-based system has been developed to identify high-risk patients in hospitals, leading to a substantial reduction in mortality rates. This innovative tool has shown promising results in real-world applications, potentially revolutionizing patient care in hospital settings.
AI System Revolutionizes Hospital Care
In a significant breakthrough for healthcare technology, researchers have developed an artificial intelligence (AI) based system that has demonstrated remarkable success in reducing hospital deaths. This innovative tool, designed to identify high-risk patients, has shown promising results in real-world applications, potentially transforming the landscape of patient care in hospital settings
1
.The AI Tool's Functionality
The AI-based system operates by analyzing patient data to identify those at highest risk of deterioration or death. By processing various factors such as vital signs, lab results, and medical history, the tool can predict which patients are most likely to require immediate intervention. This early warning system allows healthcare providers to prioritize care and allocate resources more effectively, potentially saving lives in the process
2
.Impressive Results in Clinical Trials
Clinical trials of the AI system have yielded impressive results. In a study conducted across multiple hospitals, the implementation of this tool led to a significant reduction in mortality rates. Specifically, the research showed a decrease in deaths of up to 20% among patients identified as high-risk by the AI system. This substantial improvement in patient outcomes highlights the potential of AI to enhance clinical decision-making and patient care strategies
1
.Integration with Existing Hospital Systems
One of the key advantages of this AI tool is its ability to integrate seamlessly with existing hospital information systems. The system can continuously monitor patient data in real-time, providing up-to-date risk assessments to healthcare professionals. This integration ensures that the AI's insights are readily available to doctors and nurses, allowing for quick and informed decision-making
2
.Related Stories
Potential Impact on Healthcare Delivery
The successful implementation of this AI system could have far-reaching implications for healthcare delivery. By identifying high-risk patients early, hospitals can potentially reduce the need for intensive care admissions, decrease the length of hospital stays, and improve overall patient outcomes. Furthermore, the system's ability to prioritize care could lead to more efficient use of hospital resources, potentially reducing healthcare costs while improving the quality of care
1
.Challenges and Future Developments
While the results are promising, researchers acknowledge that there are still challenges to overcome. Ensuring the accuracy and reliability of the AI system across diverse patient populations and healthcare settings remains a priority. Additionally, there are ongoing discussions about the ethical implications of using AI in healthcare decision-making and the importance of maintaining human oversight
2
.As the technology continues to evolve, future developments may include more sophisticated predictive capabilities and the integration of additional data sources to further enhance the system's accuracy. Researchers are also exploring the potential for this AI tool to be adapted for use in other healthcare settings, such as emergency departments and outpatient clinics.
References
Summarized by
Navi
Related Stories
Weekly Highlights
1
Anthropic Secures $13B in Funding, Reaching $183B Valuation Amid AI Industry Boom
Business and Economy
2
Tesla Proposes $1 Trillion Pay Package for Elon Musk Tied to Ambitious AI and Robotics Goals
Business and Economy
3
Anthropic's $1.5B AI Copyright Settlement: A Landmark Deal Under Scrutiny
Policy and Regulation
Weekly Highlights
Explore today's top stories
Your Daily Dose of Curated AI News
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Spend less time searching for the latest in AI and get straight to action.
