PurposePhenotype information is crucial for the interpretation of genomic variants. So far it has only been accessible for bioinformatics workflows after encoding into clinical terms by expert dysmorphologists.MethodsHere, we introduce an approach driven by artificial intelligence that uses portrait photographs for the interpretation of clinical exome data. We measured the value added by computer-assisted image analysis to the diagnostic yield on a cohort consisting of 679 individuals with 105 different monogenic disorders. For each case in the cohort we compiled frontal photos, clinical features, and the disease-causing variants, and simulated multiple exomes of different ethnic backgrounds.ResultsThe additional use of similarity scores from computer-assisted analysis of frontal photos improved the top 1 accuracy rate by more than 20–89% and the top 10 accuracy rate by more than 5–99% for the disease-causing gene.ConclusionImage analysis by deep-learning algorithms can be used to quantify the phenotypic similarity (PP4 criterion of the American College of Medical Genetics and Genomics guidelines) and to advance the performance of bioinformatics pipelines for exome analysis.

Germline mutations in BRCA1 and BRCA2 (BRCA1/2) genes are present in about 50% of cases of hereditary breast cancer. Proteins encoded by these genes are key players in DNA repair by homologous recombination (HR). Advances in next generation sequencing and gene panels for breast cancer testing have generated a large amount of data on gene variants implicated in hereditary breast cancer, particularly in genes such as PALB2, ATM, CHEK2, RAD51, MSH2, and BARD1. These genes are involved in DNA repair. Most of these variants have been reported for Caucasian, Jewish, and Asian population, with few reports for other communities, like those in Latin American (LA) countries. We reviewed 81 studies from 11 LA countries published between 2000 and 2019 but most of these studies focused on BRCA1/2 genes. In addition to these genes, breast cancer-related variants have been reported for PALB2, ATM, CHEK2, BARD1, MLH1, BRIP1, MSH2, NBN, MSH6, and PMS2 genes. Some of these variants are unique to LA populations. This analysis may contribute to enhance breast cancer variant characterization, and thus to find therapies and implement precision medicine for LA communities.

PURPOSE The pilot-phase report of the Joven & Fuerte prospective cohort broadly characterizes and assesses the needs of Mexican young women with breast cancer (YWBC). PATIENTS AND METHODS Women age ≤ 40 years with nonmetastatic primary breast cancer were consecutively accrued from 2 hospitals. Data were collected at the first/baseline oncology visit and 2 years later using a sociodemographic survey, European Organisation for Research and Treatment of Cancer Quality-of-Life (QOL) Questionnaire Core 30 (QLQ-C30) and Breast Cancer–Specific QOL Questionnaire (QLQ-BR23), Hospital Anxiety and Depression Scale (HADS), Female Sexual Functioning Index (FSFI), Sexual Satisfaction Inventory, and patients’ medical records. Pearson χ2 and 2-sided t tests were used for statistical analysis. An unadjusted P value < .05 was considered significant. RESULTS Ninety patients were included, all with government health care coverage. Most had low monthly household incomes (98%) and at least a high school education (59%). There was a considerable prevalence of unpartnered patients (36%) and unmet parity (25%). Patients’ most common initial symptom was a palpable mass (84%), and they were most frequently diagnosed with stage III disease (48%), with 51% having had a physician visit ≤ 3 months since detection but 39% receiving diagnosis > 12 months later. At baseline, 66% of patients were overweight/obese, and this proportion had significantly increased by 2 years ( P < .001). Compared with baseline, global QLQ-C30 had improved significantly by 2 years ( P = .004), as had HADS-Anxiety ( P < .001). However, both at baseline and at 2 years, nearly half of patients exhibited FSFI sexual dysfunction. CONCLUSION These preliminary findings demonstrate that YWBC in Mexico have particular sociodemographic and clinicopathologic characteristics, reinforcing the necessity to further describe and explore the needs of these young patients, because they may better represent the understudied and economically vulnerable population of YWBC in limited-resource settings.