Real-World Outcomes of an Automated Physician Support System for Genome-Driven Oncology

Molecular tumour boards - current and future considerations for precision oncology

Over the past 15 years, rapid progress has been made in developmental therapeutics, especially regarding the use of matched targeted therapies against specific oncogenic molecular alterations across cancer types. Molecular tumour boards (MTBs) are panels of expert physicians, scientists, health-care providers and patient advocates who review and interpret molecular-profiling results for individual patients with cancer and match each patient to available therapies, which can include investigational drugs. Interpretation of the molecular alterations found in each patient is a complicated task that requires an understanding of their contextual functional effects and their correlations with sensitivity or resistance to specific treatments. The criteria for determining the actionability of molecular alterations and selecting matched treatments are constantly evolving. Therefore, MTBs have an increasingly necessary role in optimizing the allocation of biomarker-directed therapies and the implementation of precision oncology. Ultimately, increased MTB availability, accessibility and performance are likely to improve patient care. The challenges faced by MTBs are increasing, owing to the plethora of identifiable molecular alterations and immune markers in tumours of individual patients and their evolving clinical significance as more and more data on patient outcomes and results from clinical trials become available. Beyond next-generation sequencing, broader biomarker analyses can provide useful information. However, greater funding, resources and expertise are needed to ensure the sustainability of MTBs and expand their outreach to underserved populations. Harmonization between practice and policy will be required to optimally implement precision oncology. Herein, we discuss the evolving role of MTBs and current and future considerations for their use in precision oncology.

Broad spectrum of regorafenib activity on mutant KIT and absence of clonal selection in gastrointestinal stromal tumor (GIST): correlative analysis from the GRID trial

BACKGROUND

In the phase 3 GRID trial, regorafenib improved progression-free survival (PFS) independent of KIT mutations in exons 9 and 11. In this retrospective, exploratory analysis of the GRID trial, we investigated whether a more comprehensive KIT mutation analysis could identify mutations that impact treatment outcome with regorafenib and a regorafenib-induced mutation pattern.

METHODS

Archived tumor samples, collected at any time prior to enrollment in GRID, were analyzed by Sanger sequencing (n = 102) and next-generation sequencing (FoundationONE; n = 47). Plasma samples collected at baseline were analyzed by BEAMing (n = 163) and SafeSEQ (n = 96).

RESULTS

In archived tumor samples, 67% (68/102) had a KIT mutation; 61% (62/102) had primary KIT mutations (exons 9 and 11) and 12% (12/102) had secondary mutations (exons 13, 14, 17, and 18). At baseline, 81% of samples (78/96) had KIT mutations by SafeSEQ, including the M541L polymorphism (sole event in 6 patients). Coexisting mutations in other oncogenes were rare, as were mutations in PDGFR, KRAS, and BRAF. Regorafenib showed PFS benefit across all primary and secondary KIT mutational subgroups examined. Available patient-matched samples taken at baseline and end of treatment (n = 41; SafeSEQ), revealed heterogeneous KIT mutational changes with no specific mutation pattern emerging upon regorafenib treatment.

CONCLUSION

These data support the results of the GRID trial, and suggest that patients may benefit from regorafenib in the presence of KIT mutations and without the selection of particular mutation patterns that confer resistance. The study was not powered to address biomarker-related questions, and the results are exploratory and hypothesis-generating.

Machine learning applications for therapeutic tasks with genomics data

Thanks to the increasing availability of genomics and other biomedical data, many machine learning algorithms have been proposed for a wide range of therapeutic discovery and development tasks. In this survey, we review the literature on machine learning applications for genomics through the lens of therapeutic development. We investigate the interplay among genomics, compounds, proteins, electronic health records, cellular images, and clinical texts. We identify 22 machine learning in genomics applications that span the whole therapeutics pipeline, from discovering novel targets, personalizing medicine, developing gene-editing tools, all the way to facilitating clinical trials and post-market studies. We also pinpoint seven key challenges in this field with potentials for expansion and impact. This survey examines recent research at the intersection of machine learning, genomics, and therapeutic development.

Implementation of a Molecular Tumor Registry to Support the Adoption of Precision Oncology Within an Academic Medical Center: The Duke University Experience

Comprehensive genomic profiling to inform targeted therapy selection is a central part of oncology care. However, the volume and complexity of alterations uncovered through genomic profiling make it difficult for oncologists to choose the most appropriate therapy for their patients. Here, we present a solution to this problem, The Molecular Registry of Tumors (MRT) and our Molecular Tumor Board (MTB).

PATIENTS AND METHODS

MRT is an internally developed system that aggregates and normalizes genomic profiling results from multiple sources. MRT serves as the foundation for our MTB, a team that reviews genomic results for all Duke University Health System cancer patients, provides notifications for targeted therapies, matches patients to biomarker-driven trials, and monitors the molecular landscape of tumors at our institution.

RESULTS

Among 215 patients reviewed by our MTB over a 6-month period, we identified 176 alterations associated with therapeutic sensitivity, 15 resistance alterations, and 51 alterations with potential germline implications. Of reviewed patients, 17% were subsequently treated with a targeted therapy. For 12 molecular therapies approved during the course of this work, we identified between two and 71 patients who could qualify for treatment based on retrospective MRT data. An analysis of 14 biomarker-driven clinical trials found that MRT successfully identified 42% of patients who ultimately enrolled. Finally, an analysis of 4,130 comprehensive genomic profiles from 3,771 patients revealed that the frequency of clinically significant therapeutic alterations varied from approximately 20% to 70% depending on the tumor type and sequencing test used.

CONCLUSION

With robust informatics tools, such as MRT, and the right MTB structure, a precision cancer medicine program can be developed, which provides great benefit to providers and patients with cancer.

Early Detection of Pancreatic Cancer: Applying Artificial Intelligence to Electronic Health Records

ABSTRACT

The potential of artificial intelligence (AI) applied to clinical data from electronic health records (EHRs) to improve early detection for pancreatic and other cancers remains underexplored. The Kenner Family Research Fund, in collaboration with the Cancer Biomarker Research Group at the National Cancer Institute, organized the workshop entitled: "Early Detection of Pancreatic Cancer: Opportunities and Challenges in Utilizing Electronic Health Records (EHR)" in March 2021. The workshop included a select group of panelists with expertise in pancreatic cancer, EHR data mining, and AI-based modeling. This review article reflects the findings from the workshop and assesses the feasibility of AI-based data extraction and modeling applied to EHRs. It highlights the increasing role of data sharing networks and common data models in improving the secondary use of EHR data. Current efforts using EHR data for AI-based modeling to enhance early detection of pancreatic cancer show promise. Specific challenges (biology, limited data, standards, compatibility, legal, quality, AI chasm, incentives) are identified, with mitigation strategies summarized and next steps identified.