Search

Context.— Prostate cancer is a common malignancy, and accurate diagnosis typically requires histologic review of multiple prostate core biopsies per patient. As pathology volumes and complexity increase, new tools to improve the efficiency of everyday practice are keenly needed. Deep learning has shown promise in pathology diagnostics, but most studies silo the efforts of pathologists from the application of deep learning algorithms. Very few hybrid pathologist–deep learning approaches have been explored, and these typically require complete review of histologic slides by both the pathologist and the deep learning system. Objective.— To develop a novel and efficient hybrid human–machine learning approach to screen prostate biopsies. Design.— We developed an algorithm to determine the 20 regions of interest with the highest probability of malignancy for each prostate biopsy; presenting these regions to a pathologist for manual screening limited the initial review by a pathologist to approximately 2% of the tissue area of each sample. We evaluated this approach by using 100 biopsies (29 malignant, 60 benign, 11 other) that were reviewed by 4 pathologists (3 urologic pathologists, 1 general pathologist) using a custom-designed graphical user interface. Results.— Malignant biopsies were correctly identified as needing comprehensive review with high sensitivity (mean, 99.2% among all pathologists); conversely, most benign prostate biopsies (mean, 72.1%) were correctly identified as needing no further review. Conclusions.— This novel hybrid system has the potential to efficiently triage out most benign prostate core biopsies, conserving time for the pathologist to dedicate to detailed evaluation of malignant biopsies.

Context.—In 2008, the Joint Commission (JC) implemented a standard mandating formal monitoring of physician professional performance as part of the process of granting and maintaining practice privileges.Objective.—To create a pathology-specific management tool to aid pathologists in constructing a professional practice-monitoring program, thereby meeting the JC mandate.Design.—A total of 105 College of American Pathologists (CAP)–defined metrics were created. Metrics were based on the job descriptions of pathologists' duties in the laboratory, and metric development was aided by experience from the Q-Probes and Q-Tracks programs. The program was offered in a Web-based format, allowing secure data entry, customization of metrics, and central data collection for future benchmarking.Results.—The program was live for 3 years, with 347 pathologists subscribed from 61 practices (median, 4 per institution; range, 1–35). Subscribers used 93 of the CAP-defined metrics and created 109 custom metrics. The median number of CAP-defined metrics used per pathologist was 5 (range, 1–43), and the median custom-defined metrics per pathologist was 2 (range, 1–5). Most frequently, 1 to 3 metrics were monitored (42.7%), with 20% each following 4 to 6 metrics, 5 to 9 metrics, or greater than 10 metrics. Anatomic pathology metrics were used more commonly than clinical pathology metrics. Owing to low registration, the program was discontinued in 2016.Conclusions.—Through careful vetting of metrics it was possible to develop a pathologist-specific management tool to address the JC mandate. While this initial product failed, valuable metrics were developed and implementation knowledge was gained that may be used to address new regulatory requirements for emerging value-based payment systems.

Context.—Assessment of customer satisfaction is a vital component of the laboratory quality improvement program.Objective.—To survey the level of physician satisfaction with hospital clinical laboratory services.Design.—Participating institutions provided demographic information and survey results of physician satisfaction, with specific features of clinical laboratory services individually rated on a scale of 5 (excellent) to 1 (poor).Results.—Eighty-one institutions submitted 2425 surveys. The median overall satisfaction score was 4.2 (10th percentile, 3.6; 90th percentile, 4.6). Of the 16 surveyed areas receiving the highest percentage of excellent/good ratings (combined scores of 4 and 5), quality of results was highest along with test menu adequacy, staff courtesy, and overall satisfaction. Of the 4 categories receiving the lowest percentage values of excellent/good ratings, 3 were related to turnaround time for inpatient “STAT” (tests performed immediately), outpatient STAT, and esoteric tests. The fourth was a new category presented in this survey: ease of electronic order entry. Here, 11.4% (241 of 2121) of physicians assigned below-average (2) or poor (1) scores. The 5 categories deemed most important to physicians included quality of results, turnaround times for inpatient STAT, routine, and outpatient STAT tests, and clinical report format. Overall satisfaction as measured by physician willingness to recommend their laboratory to another physician remains high at 94.5% (2160 of 2286 respondents).Conclusions.—There is a continued trend of high physician satisfaction and loyalty with clinical laboratory services. Physician dissatisfaction with ease of electronic order entry represents a new challenge. Test turnaround times are persistent areas of dissatisfaction, representing areas for improvement.