Ethnic diversity in treatment response for colorectal cancer: proof of concept for radiomics-driven enrichment trials

Artificial intelligence in immunotherapy PET/SPECT imaging

OBJECTIVE

Immunotherapy has dramatically altered the therapeutic landscape for oncology, but more research is needed to identify patients who are likely to achieve durable clinical benefit and those who may develop unacceptable side effects. We investigated the role of artificial intelligence in PET/SPECT-guided approaches for immunotherapy-treated patients.

METHODS

We performed a scoping review of MEDLINE, CENTRAL, and Embase databases using key terms related to immunotherapy, PET/SPECT imaging, and AI/radiomics through October 12, 2022.

RESULTS

Of the 217 studies identified in our literature search, 24 relevant articles were selected. The median (interquartile range) sample size of included patient cohorts was 63 (157). Primary tumors of interest were lung (n = 14/24, 58.3%), lymphoma (n = 4/24, 16.7%), or melanoma (n = 4/24, 16.7%). A total of 28 treatment regimens were employed, including anti-PD-(L)1 (n = 13/28, 46.4%) and anti-CTLA-4 (n = 4/28, 14.3%) monoclonal antibodies. Predictive models were built from imaging features using univariate radiomics (n = 7/24, 29.2%), radiomics (n = 12/24, 50.0%), or deep learning (n = 5/24, 20.8%) and were most often used to prognosticate (n = 6/24, 25.0%) or describe tumor phenotype (n = 5/24, 20.8%). Eighteen studies (75.0%) performed AI model validation.

CONCLUSION

Preliminary results suggest broad potential for the application of AI-guided immunotherapy management after further validation of models on large, prospective, multicenter cohorts.

CLINICAL RELEVANCE STATEMENT

This scoping review describes how artificial intelligence models are built to make predictions based on medical imaging and explores their application specifically in the PET and SPECT examination of immunotherapy-treated cancers.

KEY POINTS

• Immunotherapy has drastically altered the cancer treatment landscape but is known to precipitate response patterns that are not accurately accounted for by traditional imaging methods. • There is an unmet need for better tools to not only facilitate in-treatment evaluation but also to predict, a priori, which patients are likely to achieve a good response with a certain treatment as well as those who are likely to develop side effects. • Artificial intelligence applied to PET/SPECT imaging of immunotherapy-treated patients is mainly used to make predictions about prognosis or tumor phenotype and is built from baseline, pre-treatment images. Further testing is required before a true transition to clinical application can be realized.

Prevalence and predictors for cisplatin-induced toxicities in Zimbabwean women with cervical cancer

Aim: To describe treatment-induced toxicities (TITs) and associated factors in Zimbabwean cancer patients receiving cisplatin.Methods: In total, 252 Zimbabwean women with cervical cancer, receiving cisplatin were followed up over 12 months for TITs and disease status.Results: Peripheral neuropathy (70%) and ototoxicity (53%) were most prevalent. Advanced disease (OR = 1.3; 95% CI = 1.1-1.5; p = 0.02), pain comedications (OR = 1.3; 95% CI = 1.1-1.5; p = 0.03), alcohol (OR = 2.8; 95% CI = 1.1-7.5; p = 0.04) and comorbidities (OR = 1.2; 95% CI = 1.1-1.4; p = 0.04) increased peripheral neuropathy and ototoxicity risk. Older age increased risk of disease progression (OR = 1.9; 95% CI = 1.4-3.0; p = 0.033).Conclusion: High peripheral neuropathy and ototoxicity prevalence were observed, which are not routinely monitored in Zimbabwe. There is a need for capacity building to incorporate comprehensive TIT testing and optimize cancer care in Zimbabwe.

RAS/RAF/MAPK Pathway Mutations as Predictive Biomarkers in Middle Eastern Colorectal Cancer: A Systematic Review

Background

This review article aims to investigate the prevalence and spectrum of rat sarcoma (RAS) and V-Raf Murine Sarcoma Viral Oncogene Homolog B (BRAF) mutations, and their connection with geographical location, clinicopathological features, and other relevant factors in colorectal cancer (CRC) patients in the Middle East.

Methods

A systematic literature review, employing the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, was conducted to investigate the association between the frequency of relevant mutations and the descriptive clinicopathological characteristics of CRC patients. Multiple electronic databases, including PubMed, Science Direct, Web of Science, Scopus, and Google Scholar, were searched to analyze the relevant literature.

Results

A total of 19 eligible studies comprising 2960 patients with CRC were included in this review. A comprehensive analysis of the collected literature data as well as descriptive and methodological insights is provided. Men were predominant in reviewed studies for the region, accounting for 58.6%. Overall, RAS mutation prevalence was 38.1%. Kirsten RAS Viral Oncogene Homolog (KRAS) mutations were the most common, accounting for 37.1% of cases and distributed among different exons, with the G12D mutation being the most frequent in exon 2 (23.2%) followed by G12V (13.7%), G13D (10.1%), G12C (5.1%), G12A (5.04%), and G12S (3.6%). Neuroblastoma RAS Viral Oncogene Homolog (NRAS) mutations were identified in 3.3% of tumor samples, with the most common mutation site located in exons 2, 3, and 4, and codon 61 being the most common location for the region. The total mutation frequency in the BRAF gene was 2.6%, with the V600E mutation being the most common.

Conclusion

The distribution patterns of RAS and BRAF mutations among CRC patients exhibit notable variations across diverse ethnic groups. Our study sheds light on this phenomenon by demonstrating a higher prevalence of KRAS mutations in CRC patients from the Middle East, as compared with those from other regions. The identification of these mutations and geographical differences is important for personalized treatment planning and could potentially aid in the development of novel targeted therapies. The distinct distribution patterns of RAS and BRAF mutations among CRC patients across different ethnic groups, as well as the regional variability in mutation prevalence, highlight the need for further research in this area.

Racial disparities in colorectal cancer clinicopathological and molecular tumor characteristics: a systematic review

PURPOSE

African Americans have the highest colorectal cancer (CRC) mortality of all racial groups in the USA, which may relate to differences in healthcare access or advanced stage at diagnosis. Recent evidence indicates that differences in tumor characteristics may also underlie disparities in mortality. To highlight recent findings and areas for investigation, we completed the first systematic review of racial disparities in CRC tumor prognostic markers, including clinicopathological markers, microsatellite instability (MSI), oncogene mutations, and novel markers, including cancer stem cells and immune markers.

METHODS

Relevant studies were identified via PubMed, limited to original research published within the last 10 years. Ninety-six articles were identified that compared the prevalence of mortality-related CRC tumor characteristics in African Americans (or other African ancestry populations) to White cases.

RESULTS

Tumors from African ancestry cases are approximately 10% more likely to contain mutations in KRAS, which confer elevated mortality and resistance to epidermal growth factor receptor inhibition. Conversely, African Americans have approximately 50% lower odds for BRAF-mutant tumors, which occur less frequently but have similar effects on mortality and therapeutic resistance. There is less consistent evidence supporting disparities in mutations for other oncogenes, including PIK3CA, TP53, APC, NRAS, HER2, and PTEN, although higher rates of PIK3CA mutations and lower prevalence of MSI status for African ancestry cases are supported by recent evidence. Although emerging evidence suggests that immune markers reflecting anti-tumor immunity in the tumor microenvironment may be lower for African American cases, there is insufficient evidence to evaluate disparities in other novel markers, cancer stem cells, microRNAs, and the consensus molecular subtypes.

CONCLUSION

Higher rates of KRAS-mutant tumors in in African Americans may contribute to disparities in CRC mortality. Additional work is required to understand whether emerging markers, including immune cells, underlie the elevated CRC mortality observed for African Americans.