Skip to main content

All Content

Search Tips
Save
Selection
Format
Download
Published Date
Original Publication Date
Original Publication Date
PSNet Publication Date
Narrow Results By
PSNet Original Content
Commonly Searched Resource Types
1 - 7 of 7
Mamede S, de Carvalho-Filho MA, de Faria RMD, et al. BMJ Qual Saf. 2020;29:550-559.
There is uncertainty about the effectiveness of cognitive debiasing in reducing bias that can contribute to diagnostic error. Instead of focusing on the process of reasoning, this study examined whether an intervention directed at refining knowledge of a cluster of related disease can ‘immunize’ physicians against bias. Ninety-one internal medicine residents in Brazil were randomized to one of two sets of vignettes (reflecting diseases associated with either chronic diarrhea or jaundice) and compared/contrasted alternative diagnoses. After residents encountered one case of a disease, non-immunized residents twice as likely to give that incorrect diagnosis to a different (but similar) disease, resulting in a 40% decrease in diagnostic accuracy between immunized and non-immunized physicians.
Tschandl P, Codella N, Akay BN, et al. Lancet Oncol. 2019;20:938-947.
Machine learning may have the potential to improve clinical decision-making and diagnosis. In this study, machine-learning algorithms generally performed better than human experts in accurately diagnosing 7 types of pigmented skin lesions and the top 3 algorithms performed better than the 27 physicians.
Bejnordi BE, Veta M, van Diest PJ, et al. JAMA. 2017;318:2199-2210.
Diagnostic error is a growing area of focus within patient safety. Artificial intelligence has the potential to improve the diagnostic process, both in terms of accuracy and efficiency. In this study, investigators compared the use of automated deep learning algorithms for detecting metastatic disease in stained tissue sections of lymph nodes of women with breast cancer to pathologists' diagnoses. The algorithms were developed by researchers as part of a competition and their performance was assessed on a test set of 129 slides, 49 with metastatic disease and 80 without. A panel of 11 pathologists evaluated the same slides with a 2-hour time limit and one pathologist evaluated the slides without any time constraints. The authors conclude that some of the algorithms demonstrated better diagnostic performance than the pathologists did, but they suggest that further testing in a clinical setting is warranted. An accompanying editorial discusses the potential of artificial intelligence in health care.
Carlotti APCP, Bachette LG, Carmona F, et al. Am J Clin Pathol. 2016;146:701-708.
This autopsy study demonstrated significant discrepancies between clinical and postmortem diagnoses among children who died in the intensive care unit. These results demonstrate the importance of autopsy as an educational tool for clinical teams to improve patient outcomes.
Plebani M, ed. Clinica Chimica Acta. 2009;404(1):1-86.
This collection of papers presented at an international conference on laboratory medicine focuses on efforts to reduce medical errors in laboratory practice, especially those concerning diagnostic mistakes.
Pinto Carvalho FL, Cordeiro JA, Cury PM. Pathol Int. 2008;58.
This study discovered that autopsy-detected diagnostic errors occurred in 10% of cases examined, leading the authors to advocate for autopsy as an important learning strategy for clinicians. A past AHRQ WebM&M commentary discusses a case of a missed diagnosis that was discovered at autopsy.