Health equity assessment of machine learning performance (HEAL): a framework and dermatology AI model case study.

Background: Artificial intelligence (AI) has repeatedly been shown to encode historical inequities in healthcare. We aimed to develop a framework to quantitatively assess the performance equity of health AI technologies and to illustrate its utility via a case study. Methods: Here, we propose a methodology to assess whether health AI technologies prioritise performance for patient populations experiencing worse outcomes, that is complementary to existing fairness metrics. We developed the Health Equity Assessment of machine Learning performance (HEAL) framework designed to quantitatively assess the performance equity of health AI technologies via a four-step interdisciplinary process to understand and quantify domain-specific criteria, and the resulting HEAL metric. As an illustrative case study (analysis conducted between October 2022 and January 2023), we applied the HEAL framework to a dermatology AI model. A set of 5420 teledermatology cases (store-and-forward cases from patients of 20 years or older, submitted from primary care providers in the USA and skin cancer clinics in Australia), enriched for diversity in age, sex and race/ethnicity, was used to retrospectively evaluate the AI model's HEAL metric, defined as the likelihood that the AI model performs better for subpopulations with worse average health outcomes as compared to others. The likelihood that AI performance was anticorrelated to pre-existing health outcomes was estimated using bootstrap methods as the probability that the negated Spearman's rank correlation coefficient (i.e., "R") was greater than zero. Positive values of R suggest that subpopulations with poorer health outcomes have better AI model performance. Thus, the HEAL metric, defined as p (R >0), measures how likely the AI technology is to prioritise performance for subpopulations with worse average health outcomes as compared to others (presented as a percentage below). Health outcomes were quantified as disability-adjusted life years (DALYs) when grouping by sex and age, and years of life lost (YLLs) when grouping by race/ethnicity. AI performance was measured as top-3 agreement with the reference diagnosis from a panel of 3 dermatologists per case. Findings: Across all dermatologic conditions, the HEAL metric was 80.5% for prioritizing AI performance of racial/ethnic subpopulations based on YLLs, and 92.1% and 0.0% respectively for prioritizing AI performance of sex and age subpopulations based on DALYs. Certain dermatologic conditions were significantly associated with greater AI model performance compared to a reference category of less common conditions. For skin cancer conditions, the HEAL metric was 73.8% for prioritizing AI performance of age subpopulations based on DALYs. Interpretation: Analysis using the proposed HEAL framework showed that the dermatology AI model prioritised performance for race/ethnicity, sex (all conditions) and age (cancer conditions) subpopulations with respect to pre-existing health disparities. More work is needed to investigate ways of promoting equitable AI performance across age for non-cancer conditions and to better understand how AI models can contribute towards improving equity in health outcomes. Funding: Google LLC.

Does your dermatology classifier know what it doesn't know? Detecting the long-tail of unseen conditions.

Supervised deep learning models have proven to be highly effective in classification of dermatological conditions. These models rely on the availability of abundant labeled training examples. However, in the real-world, many dermatological conditions are individually too infrequent for per-condition classification with supervised learning. Although individually infrequent, these conditions may collectively be common and therefore are clinically significant in aggregate. To prevent models from generating erroneous outputs on such examples, there remains a considerable unmet need for deep learning systems that can better detect such infrequent conditions. These infrequent 'outlier' conditions are seen very rarely (or not at all) during training. In this paper, we frame this task as an out-of-distribution (OOD) detection problem. We set up a benchmark ensuring that outlier conditions are disjoint between the model training, validation, and test sets. Unlike traditional OOD detection benchmarks where the task is to detect dataset distribution shift, we aim at the more challenging task of detecting subtle differences resulting from a different pathology or condition. We propose a novel hierarchical outlier detection (HOD) loss, which assigns multiple abstention classes corresponding to each training outlier class and jointly performs a coarse classification of inliers vs. outliers, along with fine-grained classification of the individual classes. We demonstrate that the proposed HOD loss based approach outperforms leading methods that leverage outlier data during training. Further, performance is significantly boosted by using recent representation learning methods (BiT, SimCLR, MICLe). Further, we explore ensembling strategies for OOD detection and propose a diverse ensemble selection process for the best result. We also perform a subgroup analysis over conditions of varying risk levels and different skin types to investigate how OOD performance changes over each subgroup and demonstrate the gains of our framework in comparison to baseline. Furthermore, we go beyond traditional performance metrics and introduce a cost matrix for model trust analysis to approximate downstream clinical impact. We use this cost matrix to compare the proposed method against the baseline, thereby making a stronger case for its effectiveness in real-world scenarios.

Development and Assessment of an Artificial Intelligence-Based Tool for Skin Condition Diagnosis by Primary Care Physicians and Nurse Practitioners in Teledermatology Practices.

Importance: Most dermatologic cases are initially evaluated by nondermatologists such as primary care physicians (PCPs) or nurse practitioners (NPs). Objective: To evaluate an artificial intelligence (AI)-based tool that assists with diagnoses of dermatologic conditions. Design, Setting, and Participants: This multiple-reader, multiple-case diagnostic study developed an AI-based tool and evaluated its utility. Primary care physicians and NPs retrospectively reviewed an enriched set of cases representing 120 different skin conditions. Randomization was used to ensure each clinician reviewed each case either with or without AI assistance; each clinician alternated between batches of 50 cases in each modality. The reviews occurred from February 21 to April 28, 2020. Data were analyzed from May 26, 2020, to January 27, 2021. Exposures: An AI-based assistive tool for interpreting clinical images and associated medical history. Main Outcomes and Measures: The primary analysis evaluated agreement with reference diagnoses provided by a panel of 3 dermatologists for PCPs and NPs. Secondary analyses included diagnostic accuracy for biopsy-confirmed cases, biopsy and referral rates, review time, and diagnostic confidence. Results: Forty board-certified clinicians, including 20 PCPs (14 women [70.0%]; mean experience, 11.3 [range, 2-32] years) and 20 NPs (18 women [90.0%]; mean experience, 13.1 [range, 2-34] years) reviewed 1048 retrospective cases (672 female [64.2%]; median age, 43 [interquartile range, 30-56] years; 41 920 total reviews) from a teledermatology practice serving 11 sites and provided 0 to 5 differential diagnoses per case (mean [SD], 1.6 [0.7]). The PCPs were located across 12 states, and the NPs practiced in primary care without physician supervision across 9 states. The NPs had a mean of 13.1 (range, 2-34) years of experience and practiced in primary care without physician supervision across 9 states. Artificial intelligence assistance was significantly associated with higher agreement with reference diagnoses. For PCPs, the increase in diagnostic agreement was 10% (95% CI, 8%-11%; P < .001), from 48% to 58%; for NPs, the increase was 12% (95% CI, 10%-14%; P < .001), from 46% to 58%. In secondary analyses, agreement with biopsy-obtained diagnosis categories of maglignant, precancerous, or benign increased by 3% (95% CI, -1% to 7%) for PCPs and by 8% (95% CI, 3%-13%) for NPs. Rates of desire for biopsies decreased by 1% (95% CI, 0-3%) for PCPs and 2% (95% CI, 1%-3%) for NPs; the rate of desire for referrals decreased by 3% (95% CI, 1%-4%) for PCPs and NPs. Diagnostic agreement on cases not indicated for a dermatologist referral increased by 10% (95% CI, 8%-12%) for PCPs and 12% (95% CI, 10%-14%) for NPs, and median review time increased slightly by 5 (95% CI, 0-8) seconds for PCPs and 7 (95% CI, 5-10) seconds for NPs per case. Conclusions and Relevance: Artificial intelligence assistance was associated with improved diagnoses by PCPs and NPs for 1 in every 8 to 10 cases, indicating potential for improving the quality of dermatologic care.

A deep learning system for differential diagnosis of skin diseases.

Skin conditions affect 1.9 billion people. Because of a shortage of dermatologists, most cases are seen instead by general practitioners with lower diagnostic accuracy. We present a deep learning system (DLS) to provide a differential diagnosis of skin conditions using 16,114 de-identified cases (photographs and clinical data) from a teledermatology practice serving 17 sites. The DLS distinguishes between 26 common skin conditions, representing 80% of cases seen in primary care, while also providing a secondary prediction covering 419 skin conditions. On 963 validation cases, where a rotating panel of three board-certified dermatologists defined the reference standard, the DLS was non-inferior to six other dermatologists and superior to six primary care physicians (PCPs) and six nurse practitioners (NPs) (top-1 accuracy: 0.66 DLS, 0.63 dermatologists, 0.44 PCPs and 0.40 NPs). These results highlight the potential of the DLS to assist general practitioners in diagnosing skin conditions.

Automated audiometry using apple iOS-based application technology.

OBJECTIVE: The aim of this study is to determine the feasibility of an Apple iOS-based automated hearing testing application and to compare its accuracy with conventional audiometry. STUDY DESIGN: Prospective diagnostic study. Setting Academic medical center. SUBJECTS AND METHODS: An iOS-based software application was developed to perform automated pure-tone hearing testing on the iPhone, iPod touch, and iPad. To assess for device variations and compatibility, preliminary work was performed to compare the standardized sound output (dB) of various Apple device and headset combinations. Forty-two subjects underwent automated iOS-based hearing testing in a sound booth, automated iOS-based hearing testing in a quiet room, and conventional manual audiometry. RESULTS: The maximum difference in sound intensity between various Apple device and headset combinations was 4 dB. On average, 96% (95% confidence interval [CI], 91%-100%) of the threshold values obtained using the automated test in a sound booth were within 10 dB of the corresponding threshold values obtained using conventional audiometry. When the automated test was performed in a quiet room, 94% (95% CI, 87%-100%) of the threshold values were within 10 dB of the threshold values obtained using conventional audiometry. Under standardized testing conditions, 90% of the subjects preferred iOS-based audiometry as opposed to conventional audiometry. CONCLUSION: Apple iOS-based devices provide a platform for automated air conduction audiometry without requiring extra equipment and yield hearing test results that approach those of conventional audiometry.