Artificial intelligence modelling to assess the risk of cardiovascular disease in oncology patients.

Aims: There are no comprehensive machine learning (ML) tools used by oncologists to assist with risk identification and referrals to cardio-oncology. This study applies ML algorithms to identify oncology patients at risk for cardiovascular disease for referrals to cardio-oncology and to generate risk scores to support quality of care. Methods and results: De-identified patient data were obtained from Vanderbilt University Medical Center. Patients with breast, kidney, and B-cell lymphoma cancers were targeted. Additionally, the study included patients who received immunotherapy drugs for treatment of melanoma, lung cancer, or kidney cancer. Random forest (RF) and artificial neural network (ANN) ML models were applied to analyse each cohort: A total of 20 023 records were analysed (breast cancer, 6299; B-cell lymphoma, 9227; kidney cancer, 2047; and immunotherapy for three covered cancers, 2450). Data were divided randomly into training (80%) and test (20%) data sets. Random forest and ANN performed over 90% for accuracy and area under the curve (AUC). All ANN models performed better than RF models and produced accurate referrals. Conclusion: Predictive models are ready for translation into oncology practice to identify and care for patients who are at risk of cardiovascular disease. The models are being integrated with electronic health record application as a report of patients who should be referred to cardio-oncology for monitoring and/or tailored treatments. Models operationally support cardio-oncology practice. Limited validation identified 86% of the lymphoma and 58% of the kidney cancer patients with major risk for cardiotoxicity who were not referred to cardio-oncology.

The Association between a Decrease in On-Treatment Neutrophil-to-Eosinophil Ratio (NER) at Week 6 after Ipilimumab Plus Nivolumab Initiation and Improved Clinical Outcomes in Metastatic Renal Cell Carcinoma.

A lower baseline neutrophil-to-eosinophil ratio (NER) has been associated with improved responses to immune checkpoint inhibitors (ICI)-treated metastatic renal cell carcinoma (mRCC). This study investigated the decrease in NER at week 6 after ipilimumab/nivolumab (ipi/nivo) initiation and treatment responses in mRCC. A retrospective study of ipi/nivo-treated mRCC at two US academic cancer centers was conducted. A landmark analysis at week 6 was performed to assess the association between the change in NER and clinical responses (progression-free survival (PFS)/overall survival (OS)). Week 6 NER was modeled as a continuous variable, after log transformation (Ln NER), and a categorical variable by percent change. There were 150 mRCC patients included: 78% had clear cell histology, and 78% were IMDC intermediate/poor risk. In multivariable regression analysis, every decrease of 1 unit of Ln NER at week 6 was associated with improved PFS (adjusted hazard ratio (AHR): 0.78, p-value:0.005) and OS (AHR: 0.67, p-value: 0.002). When NER was modeled by percent change, decreased NER > 50% was associated with improved PFS (AHR: 0.55, p-value: 0.03) and OS (AHR: 0.37, p-value: 0.02). The decrease in week 6 NER was associated with improved PFS/OS in ipi/nivo-treated mRCC. Prospective studies are warranted to validate NER change as a biomarker to predict ICI responses.

Comprehensive review of chromophobe renal cell carcinoma.

Chromophobe renal cell carcinoma (chRCC) is the third most common type of RCC with distinct biology compared to other kidney cancer subtypes. The heterogeneity between the RCC subtypes is associated with noticeable differences in tumor aggressiveness and risk for the development of metastatic disease. ChRCC is characterized by chromosomal aneuploidy, TP53, PTEN, and mitochondrial gene mutations. Though the therapeutic landscape of clear cell RCC (ccRCC) has significantly evolved over the past decade, limited progress has been seen in chRCC due to its infrequent incidence. In fact, the therapeutic approach for chRCC is often extrapolated from ccRCC treatments or studies that combine several forms of nccRCC subtypes. In the new era of genetic profiling of tumors and targeted therapeutics, this review describes the epidemiology, pathology, molecular characteristics, and current management with ongoing clinical trials for chRCC.

Fibroblast Growth Factor Receptor (FGFR) Inhibitors in Urothelial Cancer.

Dysregulated fibroblast growth factor receptor (FGFR) signaling is associated with several cancers, including urothelial carcinoma. Preclinical studies with FGFR inhibitors have shown significant antitumor activity, which has led to clinical evaluation of multiple FGFR inhibitors. Recently, erdafitinib was approved by the U.S. Food and Drug Administration for advanced urothelial carcinoma with FGFR gene alterations as the first molecularly targeted therapy. Additional ongoing clinical trials with other types of FGFR inhibitors have shown encouraging results. This review summarizes the oncogenic signaling of FGFR alterations, completed and ongoing clinical trials of FGFR inhibitors, and resistance patterns. IMPLICATIONS FOR PRACTICE: Dysregulated fibroblast growth factor receptor (FGFR) signaling is associated with several cancers, including urothelial carcinoma. Preclinical studies with FGFR inhibitors have shown significant antitumor activity, which has led to clinical evaluation of multiple FGFR inhibitors. Most recently, erdafitinib was approved by the U.S. Food and Drug Administration for advanced urothelial carcinoma with FGFR gene alterations as the first molecularly targeted therapy. Additional ongoing clinical trials with other types of FGFR inhibitors have shown encouraging results. This review summarizes the oncogenic signaling of FGFR alterations, completed and ongoing clinical trials of FGFR inhibitors, and resistance patterns.