Ferrying Oncologists Across the Chasm of Interpreting Biomarker Testing Reports: Systematic Support Needed to Improve Care and Decrease Disparities

Generative Artificial Intelligence in Anatomic Pathology

CONTEXT.—

Generative artificial intelligence (AI) has emerged as a transformative force in various fields, including anatomic pathology, where it offers the potential to significantly enhance diagnostic accuracy, workflow efficiency, and research capabilities.

OBJECTIVE.—

To explore the applications, benefits, and challenges of generative AI in anatomic pathology, with a focus on its impact on diagnostic processes, workflow efficiency, education, and research.

DATA SOURCES.—

A comprehensive review of current literature and recent advancements in the application of generative AI within anatomic pathology, categorized into unimodal and multimodal applications, and evaluated for clinical utility, ethical considerations, and future potential.

CONCLUSIONS.—

Generative AI demonstrates significant promise in various domains of anatomic pathology, including diagnostic accuracy enhanced through AI-driven image analysis, virtual staining, and synthetic data generation; workflow efficiency, with potential for improvement by automating routine tasks, quality control, and reflex testing; education and research, facilitated by AI-generated educational content, synthetic histology images, and advanced data analysis methods; and clinical integration, with preliminary surveys indicating cautious optimism for nondiagnostic AI tasks and growing engagement in academic settings. Ethical and practical challenges require rigorous validation, prompt engineering, federated learning, and synthetic data generation to help ensure trustworthy, reliable, and unbiased AI applications. Generative AI can potentially revolutionize anatomic pathology, enhancing diagnostic accuracy, improving workflow efficiency, and advancing education and research. Successful integration into clinical practice will require continued interdisciplinary collaboration, careful validation, and adherence to ethical standards to ensure the benefits of AI are realized while maintaining the highest standards of patient care.

Emerging molecular testing paradigms in non-small cell lung cancer management-current perspectives and recommendations

Advances in molecular testing and precision oncology have transformed the clinical management of lung cancer, especially non-small cell lung cancer, enhancing diagnosis, treatment, and outcomes. Practical guidelines offer insights into selecting appropriate biomarkers and assays, emphasizing the importance of comprehensive testing. However, real-world data reveal the underutilization of biomarker testing and consequently targeted therapies. Molecular testing often occurs late in diagnosis or not at all in clinical practice, leading to delayed or inadequate treatment. Enhancing precision requires adherence to best practices by all health care professionals involved, which can ultimately improve lung cancer patient outcomes. The future of precision oncology for lung cancer will likely involve a more personalized approach, starting increasingly from earlier disease settings, with novel and more complex targeted therapies, immunotherapies, and combination regimens, and relying on liquid biopsies, muti-detection advanced genomic technologies and data integration, with artificial intelligence as a central orchestrator. This review presents the currently known actionable mutations in lung cancer and new upcoming ones that are likely to enter clinical practice soon and provides an overview of established and emerging concepts in testing methodologies. Challenges are discussed and best practice recommendations are made that are relevant today, will continue to be relevant in the future, and are likely to be relevant for other cancer types too.

Additional reporting of diffuse and homogeneous ROS-1 SP384 immunoreactivity enhances prediction of ROS1 fusion-positive non-small cell lung cancer

OBJECTIVES

ROS-1 immunohistochemistry (IHC) is a common method for screening ROS1 fusion in the clinical management of non-small cell lung cancer. The interpretation criteria for ROS-1 SP384 IHC, however, remain unestablished.

METHODS

Sixty-five non-small cell lung cancer cases underwent AmoyDx ROS1 fusion real-time polymerase chain reaction (PCR) study and ROS-1 SP384 IHC tests, which were retrieved for analysis. ROS-1 IHC tests were interpreted based on the established classifiers as well as the presence of diffuse homogeneous immunoreactivity. The diagnostic accuracies of these ROS-1 IHC interpretation methods were evaluated by comparing them with the ROS1 real-time PCR results.

RESULTS

Previous ROS-1 IHC classifiers demonstrated high sensitivity for positive ROS1 real-time PCR results (100%), but they showed low specificities (25%-50%) and overall accuracies (58%-72%). In contrast, the diffuse homogeneous ROS-1 immunoreactivity predicted positive ROS1 real-time PCR results with much higher specificity (94%) and overall accuracy (95%), albeit with a slightly lower sensitivity (97%). Some cases that showed discrepancy between diffuse homogeneous ROS-1 immunoreactivity and real-time PCR results involved rare ROS1::LDLR fusion and suboptimal IHC staining.

CONCLUSIONS

A 3-tier reporting system for ROS-1 SP384 IHC testing combining previous interpretation criteria and diffuse and homogeneous immunoreactivity may better predict ROS1 fusion status without decreasing specificity.

Electronic Medical Record-Based Nudge Intervention to Increase Comprehensive Molecular Genotyping in Patients With Metastatic Non-Small Cell Lung Cancer: Results From a Prospective Clinical Trial

PURPOSE

Less than half of the patients with newly diagnosed metastatic non-small cell lung cancer (NSCLC) undergo comprehensive molecular testing. We designed an electronic medical record (EMR)-based "nudge intervention" to prompt plasma-based molecular testing at the time of initial medical oncology consultation.

METHODS

A nonrandomized prospective trial was conducted at the University of Pennsylvania's academic practice and two affiliated community practices. Molecular genotyping was performed by tissue- and/or plasma-based next generation sequencing methods. Comprehensive testing was defined as testing for EGFR, ALK, BRAF, ROS1, MET, RET, KRAS, and NTRK. Guideline-concordant treatment was defined as the use of the appropriate first-line (1L) therapy as per the National Comprehensive Cancer Network (NCCN) guidelines. Proportion of patients with comprehensive molecular genotyping results available at any time, molecular results available before 1L therapy, and guideline-concordant 1L treatment were compared between the preintervention and postintervention cohorts using Fisher's exact test or Pearson's chi-squared test.

RESULTS

Five hundred and thirty-three patients were included, 376 in the preintervention cohort and 157 in the postintervention cohort. After implementation of the EMR-based nudge, a higher proportion of patients underwent comprehensive molecular testing in the postintervention versus the preintervention cohort (100% v 88%, P = <.001), had results of comprehensive molecular testing available before initiating 1L treatment (97.3% v 91.6%, P = .026), and received NCCN guideline-concordant care (89.8% v 78.2%, P = .035).

CONCLUSION

Across three practice sites in a large health system, implementation of a provider team-focused EMR-based nudge intervention was feasible, and led to a higher number of patients with NSCLC undergoing comprehensive molecular genotyping. These findings demonstrate that behavioral nudges can promote molecular testing and should be studied further as a tool to improve guideline-concordant care in both community and academic sites.

The Impact of Prior Single-Gene Testing on Comprehensive Genomic Profiling Results for Patients with Non-Small Cell Lung Cancer

INTRODUCTION

Tissue-based broad molecular profiling of guideline-recommended biomarkers is advised for the therapeutic management of patients with non-small cell lung cancer (NSCLC). However, practice variation can affect whether all indicated biomarkers are tested. We aimed to evaluate the impact of common single-gene testing (SGT) on subsequent comprehensive genomic profiling (CGP) test outcomes and results in NSCLC.

METHODS

Oncologists who ordered SGT for guideline-recommended biomarkers in NSCLC patients were prospectively contacted (May-December 2022) and offered CGP (DNA and RNA sequencing), either following receipt of negative SGT findings, or instead of SGT for each patient. We describe SGT patterns and compare CGP completion rates, turnaround time, and recommended biomarker detection for NSCLC patients with and without prior negative SGT results.

RESULTS

Oncologists in > 80 community practices ordered CGP for 561 NSCLC patients; 135 patients (27%) first had negative results from 30 different SGT combinations; 84% included ALK, EGFR and PD-L1, while only 3% of orders included all available SGTs for guideline-recommended genes. Among patients with negative SGT results, CGP was attempted using the same tissue specimen 90% of the time. There were also significantly more CGP order cancellations due to tissue insufficiency (17% vs. 7%), DNA sequencing failures (13% vs. 8%), and turnaround time > 14 days (62% vs. 29%) than among patients who only had CGP. Forty-six percent of patients with negative prior SGT had positive CGP results for recommended biomarkers, including targetable genomic variants in genes beyond ALK and EGFR, such as ERBB2, KRAS (non-G12C), MET (exon 14 skipping), NTRK2/3, and RET .

CONCLUSION

For patients with NSCLC, initial use of SGT increases subsequent CGP test cancellations, turnaround time, and the likelihood of incomplete molecular profiling for guideline-recommended biomarkers due to tissue insufficiency.

Interpreting and integrating genomic tests results in clinical cancer care: Overview and practical guidance

The last decade has seen rapid progress in the use of genomic tests, including gene panels, whole-exome sequencing, and whole-genome sequencing, in research and clinical cancer care. These advances have created expansive opportunities to characterize the molecular attributes of cancer, revealing a subset of cancer-associated aberrations called driver mutations. The identification of these driver mutations can unearth vulnerabilities of cancer cells to targeted therapeutics, which has led to the development and approval of novel diagnostics and personalized interventions in various malignancies. The applications of this modern approach, often referred to as precision oncology or precision cancer medicine, are already becoming a staple in cancer care and will expand exponentially over the coming years. Although genomic tests can lead to better outcomes by informing cancer risk, prognosis, and therapeutic selection, they remain underutilized in routine cancer care. A contributing factor is a lack of understanding of their clinical utility and the difficulty of results interpretation by the broad oncology community. Practical guidelines on how to interpret and integrate genomic information in the clinical setting, addressed to clinicians without expertise in cancer genomics, are currently limited. Building upon the genomic foundations of cancer and the concept of precision oncology, the authors have developed practical guidance to aid the interpretation of genomic test results that help inform clinical decision making for patients with cancer. They also discuss the challenges that prevent the wider implementation of precision oncology.

Large Language Models in Oncology: Revolution or Cause for Concern?

The technological capability of artificial intelligence (AI) continues to advance with great strength. Recently, the release of large language models has taken the world by storm with concurrent excitement and concern. As a consequence of their impressive ability and versatility, their provide a potential opportunity for implementation in oncology. Areas of possible application include supporting clinical decision making, education, and contributing to cancer research. Despite the promises that these novel systems can offer, several limitations and barriers challenge their implementation. It is imperative that concerns, such as accountability, data inaccuracy, and data protection, are addressed prior to their integration in oncology. As the progression of artificial intelligence systems continues, new ethical and practical dilemmas will also be approached; thus, the evaluation of these limitations and concerns will be dynamic in nature. This review offers a comprehensive overview of the potential application of large language models in oncology, as well as concerns surrounding their implementation in cancer care.

ChatGPT-A promising generative AI tool and its implications for cancer care

PLAIN LANGUAGE SUMMARY

Since its launch, ChatGPT has taken the internet by storm and has the potential to be used broadly in the health care system, particularly in a setting such as medical oncology. ChatGPT is well suited to review and extract key content from records of patients with cancer, interpret next-generation sequencing reports, and offer a list of potential clinical trial options.