AI assistance improved radiologists' performance in distinguishing COVID-19 from pneumonia of other etiology on chest CT. Key Results: An AI model had higher test accuracy (96% vs 85%, p<0.001), sensitivity (95% vs 79%, p<0.001), and specificity (96% vs 88%, p=0.002) than radiologists. In an independent test set, our AI model achieved an accuracy of 87%, sensitivity of 89% and specificity of 86%. With AI assistance, the radiologists achieved a higher average accuracy (90% vs 85%, p<0.001), sensitivity (88% vs 79%, p<0.001) and specificity (91% vs 88%, p=0.001). AbstractBackground: COVID-19 and pneumonia of other etiology share similar CT characteristics, contributing to the challenges in differentiating them with high accuracy.Purpose: To establish and evaluate an artificial intelligence (AI) system in differentiating COVID-19 and other pneumonia on chest CT and assess radiologist performance without and with AI assistance.Methods: 521 patients with positive RT-PCR for COVID-19 and abnormal chest CT findings were retrospectively identified from ten hospitals from January 2020 to April 2020. 665 patients with non-COVID-19 pneumonia and definite evidence of pneumonia on chest CT were retrospectively selected from three hospitals between 2017 and 2019. To classify COVID-19 versus other pneumonia for each patient, abnormal CT slices were input into the EfficientNet B4 deep neural network architecture after lung segmentation, followed by two-layer fully-connected neural network to pool slices together.Our final cohort of 1,186 patients (132,583 CT slices) was divided into training, validation and test sets in a 7:2:1 and equal ratio. Independent testing was performed by evaluating model performance on separate hospitals. Studies were blindly reviewed by six radiologists without and then with AI assistance.Results: Our final model achieved a test accuracy of 96% (95% CI: 90-98%), sensitivity 95% (95% CI: 83-100%) and specificity of 96% (95% CI: 88-99%) with Receiver Operating Characteristic (ROC) AUC of 0.95 and Precision-Recall (PR) AUC of 0.90. On independent testing, our model achieved an accuracy of 87% (95% CI: 82-90%), sensitivity of 89% (95% CI: 81-94%) and specificity of 86% (95% CI: 80-90%) with ROC AUC of 0.90 and PR AUC of 0.87. Assisted by the models' probabilities, the radiologists achieved a higher average test accuracy (90% vs. 85%, ∆=5, p<0.001), sensitivity (88% vs. 79%, ∆=9, p<0.001) and specificity (91% vs. 88%, ∆=3, p=0.001).

Key Points Question Were the Liaison Committee on Medical Education 2009 diversity accreditation guidelines associated with decreased underrepresentation of minorities in medicine? Findings In this cross-sectional study of self-reported race/ethnicity of US medical school matriculants from 2002 to 2017, numbers and proportions of black, Hispanic, and American Indian or Alaska Native medical school matriculants increased, but at a rate slower than their age-matched counterparts in the US population, resulting in increased underrepresentation. Meaning This study suggests that while absolute numbers of physicians from minority racial/ethnic groups have increased over time, the physician workforce still does not represent the demographic characteristics of the US population.

ObjectiveTo evaluate trends in racial, ethnic, and sex representation at US medical schools across 16 specialties: internal medicine, pediatrics, surgery, psychiatry, radiology, anesthesiology, obstetrics and gynecology, neurology, family practice, pathology, emergency medicine, orthopedic surgery, ophthalmology, otolaryngology, physical medicine and rehabilitation, and dermatology. Using a novel, Census-derived statistical measure of diversity, the S-score, we quantified the degree of underrepresentation for racial minority groups and female faculty by rank for assistant, associate, and full professors from 1990–2016.MethodsThis longitudinal study of faculty diversity uses data obtained from the American Association of Medical Colleges (AAMC) Faculty Roster from US allopathic medical schools. The proportion of professors of racial minority groups and female faculty by rank was compared to the US population based on data from the US Census Bureau. The Roster includes data on 52,939 clinical medical faculty in 1990, and 129,545 in 2016, at the assistant professor level or higher.The primary measure used in this study was the S-score, a measure of representation based on the probability of the observed frequency of faculty from a racial/ethnic group and sex, given the racial and ethnic distribution of the US. Pearson correlations and 95% confidence intervals for S-score with time were used to measure trends.ResultsBlacks and Hispanics showed statistically significant trends (p<0.05) towards increasing underrepresentation in most specialties and are more underrepresented in 2016 than in 1990 across all ranks and specialties analyzed, except for Black females in obstetrics & gynecology. White females were also underrepresented in many specialties and in a subset of specialties trended toward greater underrepresentation.ConclusionsCurrent efforts to improve faculty diversity are inadequate in generating an academic physician workforce that represents the diversity of the US. More aggressive measures for faculty recruitment, retention, and promotion are necessary to reach equity in academia and healthcare.

No abstract

Examination of ancestry-informative genetic markers shows that Puerto Rican and Mexican populations have shown strong assortative mating that continues to this day.