Search

BackgroundRapidly and efficiently identifying critically ill infants for WGS is a costly and challenging task currently performed by scarce, highly trained experts, and is a major bottleneck for application of WGS in the NICU. Automated means to prioritize patients for WGS are thus badly needed.MethodsInstitutional databases of Electronic Health Records (EHRs) are logical starting points for identifying patients with undiagnosed Mendelian diseases. We have developed automated means to prioritize patients for Rapid and Whole Genome Sequencing (rWGS and WGS) directly from clinical notes. Our approach combines a Clinical Natural Language Processing (CNLP) workflow with a machine learning-based prioritization tool we call the Mendelian Phenotype Search Engine (MPSE).ResultsMPSE accurately and robustly identified NICU patients selected for WGS by clinical experts from Rady Children’s Hospital in San Diego (AUC 0.86) and the University of Utah (AUC 0.85). In addition to effectively identifying patients for WGS, MPSE scores also strongly prioritize diagnostic cases over non-diagnostic cases, with projected diagnostic yields exceeding 50% throughout the first and second quartiles of score-ranked patients.ConclusionsOur results indicate that an entirely automated pipeline for selecting acutely ill infants in neonatal intensive care units (NICU) for WGS can meet or exceed diagnostic yields obtained through current selection procedures, which require time-consuming manual review of clinical notes and histories by specialized personnel.

Introduction: Use of upfront chemotherapy or novel hormonal therapy (NHT) in patients (pts) with mCSPC has been approved based on improved outcomes. Baseline clinical and genomic correlates associated with inferior outcomes on intensified therapy would help identify pts at high risk for early progression or death, may improve patient counselling and guide drug development. Methods: In this IRB-approved study, pt-level data were collected retrospectively. Eligibility: mCSPC pts undergoing ADT plus NHT or docetaxel with available pre-treatment tumor comprehensive genomic profiling from a CLIA-certified lab. Study endpoint: progression-free survival (PFS) per PCWG-2, is defined as PSA, or radiographic, or clinical progression or death whichever occurred first. Variants of unknown significance and mutated genes present in ≤5% pts were excluded. Cox proportional hazards was used to evaluate the relationship between PFS and age at diagnosis, Gleason score, volume of disease (per CHAARTED), presence of visceral mets, PSA at baseline and genomic alterations. Significance was pre-set at p ≤ 0.05. Results: 106 pts with mCSPC were included: median follow-up was 20 months. Median age at diagnosis was 62 yrs (58 - 68); 85 pts (80%) had a Gleason score ≥8; 67 pts (63%) had de-novo metastatic disease; 69 pts (56%) had high-volume disease; and 20 (19%) had visceral metastases at time of diagnosis of metastatic disease. Most frequently mutated genes: TP53 (28%, n=30), TMPRSS2 (27%, n=29), and PTEN (21%, n=22). See table for COX regression results. Conclusion: In this real-world cohort of mCSPC pts undergoing intensified ADT we identify clinical and genomic markers that are significantly associated with a an inferior PFS. These hypothesis-generating data need external validation. Hazard Ratio (95% CI) P Age 0.98 (0.94-1.02) 0.40 De Novo 1.28 (0.61-2.62) 0.52 Gleason Score ≥8 2.61 (0.98-6.93) 0.05 Log-PSA at Baseline 1.17 (1.03-1.33) 0.02 High Vol of Disease 2.47 (1.23-4.99) 0.01 Visceral Mets 1.25 (0.54-3.92) 0.60 Mutated Genes MYC 5.17 (1.39-19.27) 0.01 KDM6A 0.97 (0.20-4.52) 0.97 RB1 3.14 (0.97-10.17) 0.06 PTEN 1.07 (0.48-2.36) 0.87 TMPRSS2 1.09 (0.55-2.14) 0.81 TP53 0.89 (0.47-1.74) 0.74 Citation Format: Nicolas Sayegh, Bennet Peterson, Nishita Tripathi, Beverly Chigarira, Haoran Li, Kamal Kant Sahu, Deepika Sirohi, Roberto Nussenzveig, Benjamin L. Maughan, Neeraj Agarwal, Umang Swami. Clinical and genomic correlates of survival outcomes in patients (pts) with metastatic castration-sensitive prostate cancer (mCSPC) receiving intensified androgen deprivation therapy (ADT) in a real-world population [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 5142.