Using Retrieval-Augmented Generation to Capture Molecularly-Driven Treatment Relationships for Precision Oncology.

Modern generative artificial intelligence techniques like retrieval-augmented generation (RAG) may be applied in support of precision oncology treatment discussions. Experts routinely review published literature for evidence and recommendations of treatments in a labor-intensive process. A RAG pipeline may help reduce this effort by providing chunks of text from these publications to an off-the-shelf large language model (LLM), allowing it to answer related questions without any fine-tuning. This potential application is demonstrated by retrieving treatment relationships from a trusted data source (OncoKB) and reproducing over 80% of them by asking simple questions to an untrained Llama 2 model with access to relevant abstracts.

Poly (ADP-ribose) Polymerase Inhibitor Resistance Driven by Emergence of Polyclonal Mutations With Convergent Evolution: A Molecular Tumor Board Discussion.

Polyclonal convergent evolution to PARPi resistance in a patient with metastatic breast cancer with gPALB2.

Neoadjuvant nivolumab or nivolumab plus LAG-3 inhibitor relatlimab in resectable esophageal/gastroesophageal junction cancer: a phase Ib trial and ctDNA analyses.

Gastroesophageal cancer dynamics and drivers of clinical responses with immune checkpoint inhibitors (ICI) remain poorly understood. Potential synergistic activity of dual programmed cell death protein 1 (PD-1) and lymphocyte-activation gene 3 (LAG-3) inhibition may help improve immunotherapy responses for these tumors. We report a phase Ib trial that evaluated neoadjuvant nivolumab (Arm A, n = 16) or nivolumab-relatlimab (Arm B, n = 16) in combination with chemoradiotherapy in 32 patients with resectable stage II/stage III gastroesophageal cancer together with an in-depth evaluation of pathological, molecular and functional immune responses. Primary endpoint was safety; the secondary endpoint was feasibility; exploratory endpoints included pathological complete (pCR) and major pathological response (MPR), recurrence-free survival (RFS) and overall survival (OS). The study met its primary safety endpoint in Arm A, although Arm B required modification to mitigate toxicity. pCR and MPR rates were 40% and 53.5% for Arm A and 21.4% and 57.1% for Arm B. Most common adverse events were fatigue, nausea, thrombocytopenia and dermatitis. Overall, 2-year RFS and OS rates were 72.5% and 82.6%, respectively. Higher baseline programmed cell death ligand 1 (PD-L1) and LAG-3 expression were associated with deeper pathological responses. Exploratory analyses of circulating tumor DNA (ctDNA) showed that patients with undetectable ctDNA post-ICI induction, preoperatively and postoperatively had a significantly longer RFS and OS; ctDNA clearance was reflective of neoantigen-specific T cell responses. Our findings provide insights into the safety profile of combined PD-1 and LAG-3 blockade in gastroesophageal cancer and highlight the potential of ctDNA analysis to dynamically assess systemic tumor burden during neoadjuvant ICI that may open a therapeutic window for future intervention. ClinicalTrials.gov registration: NCT03044613 .

Early detection of ovarian cancer using cell-free DNA fragmentomes and protein biomarkers.

Ovarian cancer is a leading cause of death for women worldwide in part due to ineffective screening methods. In this study, we used whole-genome cell-free DNA (cfDNA) fragmentome and protein biomarker (CA-125 and HE4) analyses to evaluate 591 women with ovarian cancer, benign adnexal masses, or without ovarian lesions. Using a machine learning model with the combined features, we detected ovarian cancer with specificity >99% and sensitivity of 72%, 69%, 87%, and 100% for stages I-IV, respectively. At the same specificity, CA-125 alone detected 34%, 62%, 63%, and 100% of ovarian cancers for stages I-IV. Our approach differentiated benign masses from ovarian cancers with high accuracy (AUC=0.88, 95% CI=0.83-0.92). These results were validated in an independent population. These findings show that integrated cfDNA fragmentome and protein analyses detect ovarian cancers with high performance, enabling a new accessible approach for noninvasive ovarian cancer screening and diagnostic evaluation.

Trainee-Led Quality Improvement Project to Improve Fertility Preservation Counseling for Patients With Cancer.

PURPOSE: Oncofertility counseling regarding the reproductive risks associated with cancer therapy is essential for quality cancer care. We aimed to increase the rate of oncofertility counseling for patients of reproductive age (18-40 years) with cancer who were initiating systemic therapy at the Johns Hopkins Cancer Center from a baseline rate of 37% (25 of 68, June 2019-January 2020) to 70% by February 2021. METHODS: We formed an interprofessional, multidisciplinary team as part of the ASCO Quality Training Program. We obtained data from the electronic medical record and verified data with patients by phone. We surveyed patients, oncologists, and fertility specialists to identify barriers. After considering a prioritization matrix, we implemented Plan-Do-Study-Act (PDSA) cycles. RESULTS: We identified the following improvement opportunities: (1) oncologist self-reported lack of knowledge about counseling and local fertility preservation options and (2) lack of a standardized referral mechanism to fertility services. During the first PDSA cycle (February 2020-August 2020, disrupted by COVID-19), we introduced the initiative to increase oncofertility counseling at faculty meetings. From September 2020 to November 2020, we implemented a second PDSA cycle: (1) educating and presenting the initiative at Oncology Grand Rounds, (2) distributing informative pamphlets to oncologists and patients, and (3) implementing an electronic medical record order set. In the third PDSA cycle (December 2020-February 2021), we redesigned the order set to add information (eg, contact information for fertility coordinator) to the patient after-visit summary. Postimplementation (September 2020-February 2021), counseling rates increased from 37% to 81% (38 of 47). CONCLUSION: We demonstrate how a trainee-led, patient-centered initiative improved oncofertility care. Ongoing work focuses on ensuring sustainability and assessing the quality of counseling.

White blood cell and cell-free DNA analyses for detection of residual disease in gastric cancer.

Liquid biopsies are providing new opportunities for detection of residual disease in cell-free DNA (cfDNA) after surgery but may be confounded through identification of alterations arising from clonal hematopoiesis. Here, we identify circulating tumor-derived DNA (ctDNA) alterations through ultrasensitive targeted sequencing analyses of matched cfDNA and white blood cells from the same patient. We apply this approach to analyze samples from patients in the CRITICS trial, a phase III randomized controlled study of perioperative treatment in patients with operable gastric cancer. After filtering alterations from matched white blood cells, the presence of ctDNA predicts recurrence when analyzed within nine weeks after preoperative treatment and after surgery in patients eligible for multimodal treatment. These analyses provide a facile method for distinguishing ctDNA from other cfDNA alterations and highlight the utility of ctDNA as a predictive biomarker of patient outcome to perioperative cancer therapy and surgical resection in patients with gastric cancer.