A study in JAMA Network Open evaluated the effectiveness of early warning scores (EWS) in detecting clinical deterioration in hospitalized patients, analyzing data from 362,926 encounters across seven hospitals. The research compared three AI-based scores—eCARTv5, Rothman Index, and Epic Deterioration Index—with three traditional scores—Modified Early Warning Score, National Early Warning Score, and NEWS2—focusing on their ability to predict transfers to ICU or death within 24 hours. Results indicated that eCARTv5 had the highest predictive accuracy, with an AUROC of 0.895, while the EDI score underperformed significantly with an AUROC of 0.808. The findings underscore notable differences in the predictive power of these scores, particularly in identifying at-risk patients.

AI Outshines Traditional Scores in Predicting Patient Deterioration JAMA Network Open

For cybersecurity professionals dealing with the stress of post-incident recovery, it is critical for organizations to implement supportive measures aimed at mental health and well-being. Recognizing the intense scrutiny and accountability these teams face, organizations can introduce initiatives such as mental health resources, manageable workloads, and a culture that emphasizes the importance of psychological safety. By prioritizing the mental health of cybersecurity staff, companies can not only help mitigate burnout but also enhance the overall security posture and effectiveness of their teams.

Cybersecurity Professionals Face Rising Burnout Amidst Crisis Accountability BankInfoSecurity

Harvard Medical School (HMS) is incorporating artificial intelligence into its curriculum to better prepare future doctors amid evolving medical challenges. Following the introduction of ChatGPT in late 2022, HMS recognizes the need for a shift in medical training, comparable to the impact of the internet in the 1990s. Dean Bernard Chang highlights the implementation of a one-month introductory AI course for all incoming Health Sciences and Technology (HST) students, which will cover both the applications and limitations of AI in healthcare. Additionally, a new PhD program in AI in Medicine has drawn significant interest, indicating a rising demand for expertise in this field. HMS is also offering Dean’s Innovation Awards to support AI-driven projects.

Harvard Medical School Embraces AI to Revolutionize Medical Education Harvard Medical School

Healthcare organizations are increasingly vulnerable to cyber threats, with a recent report indicating that 92% of U.S. healthcare entities faced cyberattacks in the past year, primarily through damaging supply chain intrusions. These attacks frequently disrupt essential services and supplies, impacting patient care directly; 82% of affected organizations reported significant interruptions, and 28% noted an increase in patient fatalities linked to such breaches. The findings underscore the need for healthcare entities to enhance their cybersecurity measures, particularly concerning third-party vendor management, to mitigate the risks associated with these supply chain vulnerabilities.

Healthcare Cyberattacks Surge: Supply Chain Threats Endanger Patient Care Cyber Magazine