Automated AI labeling of optic nerve head enables insights into cross-ancestry glaucoma risk and genetic discovery in >280,000 images from UKB and CLSA.

Cupping of the optic nerve head, a highly heritable trait, is a hallmark of glaucomatous optic neuropathy. Two key parameters are vertical cup-to-disc ratio (VCDR) and vertical disc diameter (VDD). However, manual assessment often suffers from poor accuracy and is time intensive. Here, we show convolutional neural network models can accurately estimate VCDR and VDD for 282,100 images from both UK Biobank and an independent study (Canadian Longitudinal Study on Aging), enabling cross-ancestry epidemiological studies and new genetic discovery for these optic nerve head parameters. Using the AI approach, we perform a systematic comparison of the distribution of VCDR and VDD and compare these with intraocular pressure and glaucoma diagnoses across various genetically determined ancestries, which provides an explanation for the high rates of normal tension glaucoma in East Asia. We then used the large number of AI gradings to conduct a more powerful genome-wide association study (GWAS) of optic nerve head parameters. Using the AI-based gradings increased estimates of heritability by ∼50% for VCDR and VDD. Our GWAS identified more than 200 loci associated with both VCDR and VDD (double the number of loci from previous studies) and uncovered dozens of biological pathways; many of the loci we discovered also confer risk for glaucoma.

Verifying explainability of a deep learning tissue classifier trained on RNA-seq data.

For complex machine learning (ML) algorithms to gain widespread acceptance in decision making, we must be able to identify the features driving the predictions. Explainability models allow transparency of ML algorithms, however their reliability within high-dimensional data is unclear. To test the reliability of the explainability model SHapley Additive exPlanations (SHAP), we developed a convolutional neural network to predict tissue classification from Genotype-Tissue Expression (GTEx) RNA-seq data representing 16,651 samples from 47 tissues. Our classifier achieved an average F1 score of 96.1% on held-out GTEx samples. Using SHAP values, we identified the 2423 most discriminatory genes, of which 98.6% were also identified by differential expression analysis across all tissues. The SHAP genes reflected expected biological processes involved in tissue differentiation and function. Moreover, SHAP genes clustered tissue types with superior performance when compared to all genes, genes detected by differential expression analysis, or random genes. We demonstrate the utility and reliability of SHAP to explain a deep learning model and highlight the strengths of applying ML to transcriptome data.

Web Application for the Automated Extraction of Diagnosis and Site From Pathology Reports for Keratinocyte Cancers.

PURPOSE: Keratinocyte cancers are exceedingly common in high-risk populations, but accurate measures of incidence are seldom derived because the burden of manually reviewing pathology reports to extract relevant diagnostic information is excessive. Thus, we sought to develop supervised learning algorithms for classifying basal and squamous cell carcinomas and other diagnoses, as well as disease site, and incorporate these into a Web application capable of processing large numbers of pathology reports. METHODS: Participants in the QSkin study were recruited in 2011 and comprised men and women age 40-69 years at baseline (N = 43,794) who were randomly selected from a population register in Queensland, Australia. Histologic data were manually extracted from free-text pathology reports for participants with histologically confirmed keratinocyte cancers for whom a pathology report was available (n = 25,786 reports). This provided a training data set for the development of algorithms capable of deriving diagnosis and site from free-text pathology reports. We calculated agreement statistics between algorithm-derived classifications and 3 independent validation data sets of manually abstracted pathology reports. RESULTS: The agreement for classifications of basal cell carcinoma (κ = 0.97 and κ = 0.96) and squamous cell carcinoma (κ = 0.93 for both) was almost perfect in 2 validation data sets but was slightly lower for a third (κ = 0.82 and κ = 0.90, respectively). Agreement for total counts of specific diagnoses was also high (κ > 0.8). Similar levels of agreement between algorithm-derived and manually extracted data were observed for classifications of keratoacanthoma and intraepidermal carcinoma. CONCLUSION: Supervised learning methods were used to develop a Web application capable of accurately and rapidly classifying large numbers of pathology reports for keratinocyte cancers and related diagnoses. Such tools may provide the means to accurately measure subtype-specific skin cancer incidence.