Choudhury A, Asan O. JMIR Med Inform. 2020;8:e18599.
This systematic review explored how artificial intelligence (AI) based on machine learning algorithms and natural language processing is used to address and report patient safety outcomes. The review suggests that AI-enabled decision support systems can improve error detection, patient stratification, and drug management, but that additional evidence is needed to understand how well AI can predict safety outcomes.
Härkänen M, Turunen H, Vehviläinen-Julkunen K. J Patient Saf. 2020;16.
This study compared medication errors detected using incident reports, the Global Trigger Tool method, and direct observations of patient records. Incident reports and the Global Trigger Tool more commonly identified medication errors likely to cause harm. Omission errors were commonly identified by all three methods, but identification of other errors varied. For example, incident reports most commonly identified wrong dose and wrong time errors. The contributing factors also varied by method, but in general, communication issues and human factors were the most common contributors.
This commentary explores two scientific cultures in modern medicine. A ‘traditional culture’ leaves error control up to individuals and groups of healthcare practitioners; the author describes how this culture leads to an overconfidence among practitioners about personal abilities to reduce errors. In contrast, a ‘modern scientific culture’ considers errors as inevitable and pervasive throughout medicine and beyond individuals or groups to control. The author describes the competing priorities of these cultures, and suggests that error control efforts in medicine will be more successful if there is a paradigm shift towards a more ‘modern’ attitude.
Please select your preferred way to submit a case. Note that even if you have an account, you can still choose to submit a case as a guest. And if you do choose to submit as a logged-in user, your name will not be publicly associated with the case. Learn more information here.