Delayed referrals from primary care providers to specialty care can lead to delayed diagnoses and patient harm. This retrospective analysis examined differences in timely versus delayed referrals for urgent skin cancer evaluations at one institution. Among 320 referrals occurring in 2018, 38% of evaluations occurred 31 days or more after the referral and nearly 11% of referrals were never completed. Delayed referrals were more common among patients who did not speak English and racial/ethnic minorities.

Providers’ gender, racial, and ethnic bias can adversely affect patient safety and lead to poor outcomes. This study investigated white patients’ physiological responses to treatment provided by either a woman or Black physician. Despite patients’ positive overt attitudes to Black or woman physicians, they were less physiologically responsive to placebo treatment provided by women or Black physicians, suggesting additional implications for health inequities.

Incomplete or delayed referrals from primary care providers to specialty care can cause diagnostic delays and patient harm. A systems engineering analysis was conducted to identify vulnerabilities in the referral process and develop a framework to close the loop between primary and specialty care. Low reliability processes, such as workarounds, were identified and human factors approaches were recommended to improve successful referral rates.

Radiofrequency identification (RFID) technology has been most commonly used in perioperative settings to improve patient safety. This study explored whether RFID technology can improve process measures in laboratory settings, such as order tracking, specimen processing, and test result communication. Findings indicate that RFID-tracked orders were more likely to have completed testing process milestones and were completed more quickly.

Adverse events associated with pharmacy compounding (e.g., parenteral nutrition, sterile compounding) are well-documented. This survey of state medical and osteopathic boards gathered information about compounding-associated adverse events in physician offices and use of compounding standards. Findings indicate that the incidence of in-office compounding-related adverse events is low and that the majority of respondents had not incorporated compounding standards into their regulations.

This study explored the use of artificial intelligence (AI)-based support in clinical decision-making in dermatology. The authors propose a framework for future research on image-based diagnostics to improve AI use in clinical practice.

Researchers in this study used semi-structured interviews to explore how patients perceive the use of direct-to-patient and clinician decision-support artificial intelligence (AI) tools for skin cancer screening. Common perceived benefits included increased diagnostic speed and health care access, while increased anxiety was a common risk. Patients perceived more accurate diagnoses (69%) and less accurate diagnoses (85%) to be both the greatest strength and weakness of these tools. The vast majority of patients (94%) expressed the importance of a symbiotic relationship between patients, physicians and AI tools. The related commentary discusses the importance of including the patient perspective in the development and implementation of AI tools in healthcare.

Delays in cancer diagnosis can lead to adverse patient outcomes. This systematic review examined whether smartphone-based apps can assist patients in assessing skin cancer risk and whether they should seek medical attention for suspicious lesions. The review included nine studies evaluating six different smartphone apps; reported sensitivity and specificity varied widely across studies. The authors note limitations of the included studies, such as failure to recruit a population representative of the general population. Findings are consistent with earlier studies reporting poor performance of smartphone apps for melanoma detection. Although these apps are intended to reduce delays in diagnosis, the authors conclude they can’t be relied upon for detection of all cases of skin cancer.

Advanced computing holds promise for reducing missed diagnoses of cancer. This metanalysis found that computer-aided diagnosis effectively detects melanoma; however, studies were low in quality. The authors suggest that these systems may help assist dermatologists in overcoming the limitations of human cognition for performing repetitive tasks.

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.

Cognitive shortcuts, or heuristics, are often used by experts to make decisions. This two-part review examines how heuristics affect diagnosis in dermatology. The first article discusses the strengths and weaknesses in visual diagnosis behaviors. The second recommends techniques for improving decision making and self-awareness of thought processes to avoid diagnostic error in dermatology practice.

A key component of resident education is learning from mistakes in real time to improve practice. An open and psychologically safe clinical learning environment enables residents and the health care workforce to develop the skills required to manage such situations appropriately.

Diagnostic errors among physician extenders are understudied, especially in subspecialty settings. In this study, physician assistants working in dermatology clinics performed more biopsies and diagnosed fewer skin cancers and melanoma than board-certified dermatologists. The authors were unable to assess how often either clinician type missed diagnoses of skin cancer.

This analysis of Medicare prescription data found that dermatologists' opioid prescribing varies widely, with the highest prescribing rates in surgical settings. The authors suggest that dermatologists should prescribe nonopioid medications in the postoperative setting.

This retrospective examination of closed malpractice claims against dermatologists identified procedural errors and missed diagnoses as the most frequent types of claims. As with malpractice claims across other specialties, most were dismissed or withdrawn.