Skip to main content

All Content

Search Tips
Published Date
Original Publication Date
Original Publication Date
PSNet Publication Date
Narrow Results By
PSNet Original Content
Commonly Searched Resource Types
1 - 15 of 15
Wang L, Goh KH, Yeow A, et al. J Med Internet Res. 2022;24:e23355.
Alert fatigue is an increasingly recognized patient safety concern. This retrospective study examined the association between habit and dismissal of indwelling catheter alerts among physicians at one hospital in Singapore. Findings indicate that physicians dismissed 92% of all alerts and that 73% of alerts were dismissed in 3 seconds or less. The study also concluded that a physician’s prior dismissal of alerts increases the likelihood of dismissing future alerts (habitual dismissal), raising concerns that physicians may be missing important alerts.
Leviatan I, Oberman B, Zimlichman E, et al. J Am Med Inform Assoc. 2021;28:1074-1080.
Human factors, such as cognitive load, are main contributors to prescribing errors. This study assessed the relationship between medication prescribing errors and a physician’s workload, successive work shifts, and prescribing experience. The researchers reviewed presumed medication errors flagged by a computerized decision support system (CDSS) in acute care settings (excluding intensive care units) and found that longer hours and less experience in prescribing specific medications increased the risk of prescribing errors.
Segal G, Segev A, Brom A, et al. J Am Med Inform Assoc. 2019;26:1560-1565.
Alerts designed to prevent inappropriate prescribing of medications are frequently overridden and contribute to alert fatigue. This study describes the use of machine learning to improve the clinical relevance of medication error alerts in the inpatient setting.
Shimizu T, Nemoto T, Tokuda Y. Int J Med Inform. 2018;109:1-4.
This retrospective study found that clinicians who had access to a commercial clinical decision support tool made fewer diagnostic errors than clinicians who did not have access to the tool. The authors conclude that online clinical decision support from this platform improved diagnosis.
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.
Prgomet M, Li L, Niazkhani Z, et al. J Am Med Inform Assoc. 2017;24:413-422.
While prior research has shown that computerized provider order entry and clinical decision support systems have the potential to improve patient safety, less is known about the impact of such systems in intensive care units. In this systematic review and meta-analysis, investigators found an 85% decrease in prescribing errors and a 12% reduction in ICU mortality rates in critical care units that converted from paper orders to commercially available computerized provider order entry systems.
HIM J. 2015;44.
This quality improvement study to enhance the safety of chemotherapy was conducted at a tertiary care hospital in Pakistan. Investigators found that standardized chemotherapy orders within a computerized provider order entry system were associated with fewer medication errors as well as improved dispensing efficiency compared with the older, paper-based order system.
Lee JH, Han H, Ock M, et al. Int J Med Inform. 2014;83.
This before-and-after study found that clinical decision support reduced medication errors (greater than maximum dose) for five high-alert medications. Changes in order patterns emerged following the alerts, but the authors did not identify patient harm associated with the system. This work supports the use of clinical decision support for high-risk medications.
Hsu C-C, Chou C-Y, Chou C-L, et al. PLoS One. 2014;9:e114359.
Clinicians may prescribe split pills for many different reasons, including dosing flexibility and patient affordability; however, this practice presents potential hazards. Splitting medications that are formulated to be extended-release or enteric-coated can lead to possibly dangerous changes in the drug's functionality. This study discusses the introduction of a clinical decision support warning that created a "hard stop" for any time an outpatient clinician attempted to prescribe a split pill for these special formulation medications. The study site was an academic medical center in Taiwan that performs more than 2.5 million ambulatory visits per year. The intervention resulted in a sharp decline in inappropriate medication splitting from a rate of approximately 0.61% to below 0.2%, where it has remained for at least 10 consecutive months. The use of a hard stop order can be controversial, as this method has resulted in unintended consequences in the past. A prior AHRQ WebM&M perspective discussed some of the tensions related to implementing medication decision support systems.
Ahn EK, Cho S-Y, Shin D, et al. Healthc Inform Res. 2014;20:280-7.
Alert fatigue is a well-described limitation of clinical decision support systems. This qualitative study found alert overrides occurred most frequently in the emergency department, and the most common reason reported was that the alert was clinically irrelevant, emphasizing the need to tailor alerting systems for different clinical settings.
Kadmon G, Bron-Harlev E, Nahum E, et al. Pediatrics. 2009;124:935-940.
Hospitalized children are particularly vulnerable to medication errors due to the complexity of weight-based dosing and the resulting potential for calculation errors. Computerized provider order entry (CPOE) has been widely advocated as a means of preventing such errors. In this study, implementation of a CPOE system did not initially reduce adverse drug events in a pediatric intensive care unit. However, when a decision support system for calculating weight-based dosages was added to the CPOE system, medication errors declined significantly. A 2008 Sentinel Event Alert published by The Joint Commission highlighted the prevalence of pediatric medication errors and recommended potential solutions.