IMPORTANCE For prostate cancer, Gleason grading of the biopsy specimen plays a pivotal role in determining case management. However, Gleason grading is associated with substantial interobserver variability, resulting in a need for decision support tools to improve the reproducibility of Gleason grading in routine clinical practice. OBJECTIVE To evaluate the ability of a deep learning system (DLS) to grade diagnostic prostate biopsy specimens. DESIGN, SETTING, AND PARTICIPANTS The DLS was evaluated using 752 deidentified digitized images of formalin-fixed paraffin-embedded prostate needle core biopsy specimens obtained from 3 institutions in the United States, including 1 institution not used for DLS development. To obtain the Gleason grade group (GG), each specimen was first reviewed by 2 expert urologic subspecialists from a multi-institutional panel of 6 individuals (years of experience: mean, 25 years; range, 18-34 years). A third subspecialist reviewed discordant cases to arrive at a majority opinion. To reduce diagnostic uncertainty, all subspecialists had access to an immunohistochemical-stained section and 3 histologic sections for every biopsied specimen. Their review was conducted from December 2018 to June 2019. MAIN OUTCOMES AND MEASURES The frequency of the exact agreement of the DLS with the majority opinion of the subspecialists in categorizing each tumor-containing specimen as 1 of 5 categories: nontumor, GG1, GG2, GG3, or GG4-5. For comparison, the rate of agreement of 19 general pathologists' opinions with the subspecialists' majority opinions was also evaluated. RESULTS For grading tumor-containing biopsy specimens in the validation set (n = 498), the rate of agreement with subspecialists was significantly higher for the DLS (71.7%; 95% CI, 67.9%-75.3%) than for general pathologists (58.0%; 95% CI, 54.5%-61.4%) (P < .001). In subanalyses of biopsy specimens from an external validation set (n = 322), the Gleason grading performance of the DLS remained similar. For distinguishing nontumor from tumor-containing biopsy specimens (n = 752), the rate of agreement with subspecialists was 94.3% (95% CI, 92.4%-95.9%) for the DLS and similar at 94.7% (95% CI, 92.8%-96.3%) for general pathologists (P = .58). CONCLUSIONS AND RELEVANCE In this study, the DLS showed higher proficiency than general pathologists at Gleason grading prostate needle core biopsy specimens and generalized to an independent institution. Future research is necessary to evaluate the potential utility of using the DLS as a decision support tool in clinical workflows and to improve the quality of prostate cancer grading for therapy decisions.

IMPORTANCE Coronary computed tomography angiography (CCTA) is a new approach for the diagnosis of anatomical coronary artery disease (CAD), but it is unclear how CCTA performs compared with the standard approach of functional stress testing.OBJECTIVE To compare the clinical effectiveness of CCTA with that of functional stress testing for patients with suspected CAD.DATA SOURCES A systematic literature search was conducted in PubMed and MEDLINE for English-language randomized clinical trials of CCTA published from January 1, 2000, to July 10, 2016.STUDY SELECTION Researchers selected randomized clinical trials that compared a primary strategy of CCTA with that of functional stress testing for patients with suspected CAD and reported data on patient clinical events and changes in therapy. DATA EXTRACTION AND SYNTHESISTwo reviewers independently extracted data from and assessed the quality of the trials. This analysis followed the PRISMA statement for reporting systematic reviews and meta-analyses and used the Cochrane Collaboration's tool for assessing risk of bias in randomized trials. The Mantel-Haenszel method was used to conduct the primary analysis. Summary relative risks were calculated with a random-effects model. MAIN OUTCOMES AND MEASURESThe outcomes of interest were all-cause mortality, cardiac hospitalization, myocardial infarction, invasive coronary angiography, coronary revascularization, new CAD diagnoses, and change in prescription for aspirin and statins.RESULTS Thirteen trials were included, with 10 315 patients in the CCTA arm and 9777 patients in the functional stress testing arm who were followed up for a mean duration of 18 months. There were no statistically significant differences between CCTA and functional stress testing in death (1.0% vs 1.1%; risk ratio [RR], 0.93; 95% CI, 0.71-1.21) or cardiac hospitalization (2.7% vs 2.7%; RR, 0.98; 95% CI, 0.79-1.21), but CCTA was associated with a reduction in the incidence of myocardial infarction (0.7% vs 1.1%; RR, 0.71; 95% CI, 0.53-0.96). Patients undergoing CCTA were significantly more likely to undergo invasive coronary angiography (11.7% vs 9.1%; RR, 1.33; 95% CI, 1.12-1.59) and revascularization (7.2% vs 4.5%; RR, 1.86; 95% CI, 1.43-2.43). They were also more likely to receive a diagnosis of new CAD and to have initiated aspirin or statin therapy. CONCLUSIONS AND RELEVANCECompared with functional stress testing, CCTA is associated with a reduced incidence of myocardial infarction but an increased incidence of invasive coronary angiography, revascularization, CAD diagnoses, and new prescriptions for aspirin and statins. Despite these differences, CCTA is not associated with a reduction in mortality or cardiac hospitalizations.

To determine the relationship between Type A behavior pattern and angiographically documented coronary atherosclerosis (CAD), we analyzed risk factor, behavioral, and angiographic data collected on 2,289 patients undergoing diagnostic coronary angiography at Duke University Medical Center between 1974 and 1980. Multivariable analyses using ordinal logistic regression techniques showed that Type A behavior as assessed by the structured interview (SI) is significantly associated with CAD severity after age, sex, hyperlipidemia, smoking, hypertension, and their various significant interactions were controlled for. This relationship, however, is dependent upon age. Among patients aged 45 or younger, Type A's had more severe CAD than did Type B's; among patients aged 46-54, CAD severity was similar between Type A's and B's; and among patients 55 and older, there was a trend toward more severe CAD among Type B's than among Type A's. These Type A-CAD relationships did not appear to be the result of various factors relating to the selection of patients for angiography. Type A behavior as assessed by the Jenkins Activity Survey was unrelated to CAD severity. These findings suggest that SI-determined Type A behavior is associated with more severe CAD among younger patients referred for diagnostic coronary angiography. The reversal of the Type A-CAD relationship among older patients may be due to survival effects. Inadequate sample sizes, use of assessment tools other than the SI, and failure to consider the Type A by age interaction could account for failures to find a Type A-CAD relationship in other studies. We conclude that the present findings are consistent with the hypothesis that Type A behavior is involved in the pathogenesis of CAD, but only in younger age groups. The Type A effect in the present data is small relative to that of both smoking and hyperlipidemia, however, and future research should focus more specifically on the hostility and anger components of Type A behavior, particularly in younger samples.

No abstract