The Roles of Comprehensive Genomic Profiling, Next-Generation Sequencing, and AI in the Oncology Treatment Landscape
The genetic changes or alterations that cause cancer can be a result of germline mutations or somatic mutations, where the alteration is from acquired genetic damage. Advancements in science and technology bring the ability to incorporate genetic testing for oncology biomarkers into clinical care, with the goal of improved patient outcomes. In a recent Medicare-proposed local coverage determination, biomarkers for oncology were broken down into four functional types: (1) Diagnostic biomarkers detect or confirm the presence of a disease or condition; (2) Prognostic biomarkers provide information about the likely course of a disease process and potential patient outcomes if left untreated; (3) Predictive biomarkers forecast a patient’s response to and/or the benefit of a specific treatment; and (4) Therapeutic biomarkers identify potential targets for a medical intervention (eg, targeted drug therapy).
In this issue, we will be focusing on the utilization of predictive biomarker testing as it pertains to the use of genomic testing in advanced solid tumors. For patients with advanced/metastatic solid tumors (mostly stage IV disease), comprehensive genomic profiling (CGP) via next-generation sequencing (NGS) panels are highly utilized by oncologists to complete guideline-recommended tumor genetic testing. However, while genomic testing of an advanced solid tumor can forecast a patient’s response and/ or benefit to a specific treatment, there is a perception that comprehensive genomic testing can also lead to off-label drug use and associated costs or harm. Off-label utilization is a key barrier to health plan coverage for such testing, despite lack of studies reporting such behavior following genetic testing. Wiedower et al (page 37) present the results of a study analyzing the observed frequency of real-world off-label therapy usage patterns following CGP via next-generation sequencing in an oncology care setting and in a compassionate care setting. In addition to looking at overall off-label therapy usage patterns, they evaluate whether prescribing patterns differ between these two care settings.
In another featured article, Biancalana and Pandey (page 56) discuss the use of artificial intelligence (AI) in oncology. AI technology in cancer care has the potential to improve the accuracy and speed of diagnosis, aid clinical decision-making, and lead to better health outcomes. In addition, AI-guided clinical care has the potential to play an important role in reducing health disparities, particularly in low-resource settings. Biancalana and Pandey point out that with the shortfall of physicians projected to worsen in the coming decade, AI, and its manifestations in both machine learning and deep learning, are poised to unburden physicians from many laborious and repetitive tasks in diagnostic analyses, while also providing insight into prospective therapeutic options. However, as with any new technology, there are wins and challenges to deliver on the promise of personalized cancer through guided intelligence. Thus, while insights from AI will undoubtedly revolutionize health care, it is essential to understand its limitations relative to the expertise of the physicians who can assess the utility and applicability of these insights for a particular patient.
Finally, our supplement report presents the proceeding of the NGS Institute’s (NGSi) report on NGS testing in non–small cell lung cancer (NSCLC). The report summarizes the discussions of the NGSi NSCLC subcommittee, a group of various stakeholders convened to examine the current state of NGS biomarker testing in NSCLC (page 27). The views expressed and documented in this report are those of the participants based upon their experience and expertise in NGS/biomarker testing from the perspective of the patient and clinical outcomes. While other groups have similar ongoing efforts focused on the standard of practice, it is not the intent of this group to duplicate ongoing efforts but rather to add value and possibly establish partnerships to improve utilization.
As always, let us know any concerns, comments, questions, or suggestions you may have. And if you’d like to submit your data for publication, please visit jcponline.com. Hope to see you at the Clinical Pathways Congress in Boston, October 6-8.
