Application of machine learning for lung cancer survival prognostication-A systematic review and meta-analysis.

Introduction: Machine learning (ML) techniques have gained increasing attention in the field of healthcare, including predicting outcomes in patients with lung cancer. ML has the potential to enhance prognostication in lung cancer patients and improve clinical decision-making. In this systematic review and meta-analysis, we aimed to evaluate the performance of ML models compared to logistic regression (LR) models in predicting overall survival in patients with lung cancer. Methods: We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. A comprehensive search was conducted in Medline, Embase, and Cochrane databases using a predefined search query. Two independent reviewers screened abstracts and conflicts were resolved by a third reviewer. Inclusion and exclusion criteria were applied to select eligible studies. Risk of bias assessment was performed using predefined criteria. Data extraction was conducted using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) checklist. Meta-analytic analysis was performed to compare the discriminative ability of ML and LR models. Results: The literature search resulted in 3,635 studies, and 12 studies with a total of 211,068 patients were included in the analysis. Six studies reported confidence intervals and were included in the meta-analysis. The performance of ML models varied across studies, with C-statistics ranging from 0.60 to 0.85. The pooled analysis showed that ML models had higher discriminative ability compared to LR models, with a weighted average C-statistic of 0.78 for ML models compared to 0.70 for LR models. Conclusion: Machine learning models show promise in predicting overall survival in patients with lung cancer, with superior discriminative ability compared to logistic regression models. However, further validation and standardization of ML models are needed before their widespread implementation in clinical practice. Future research should focus on addressing the limitations of the current literature, such as potential bias and heterogeneity among studies, to improve the accuracy and generalizability of ML models for predicting outcomes in patients with lung cancer. Further research and development of ML models in this field may lead to improved patient outcomes and personalized treatment strategies.

Evaluation of the Quality and Comprehensiveness of YouTube Videos Discussing Pancreatic Cancer.

Pancreatic cancer is one of the most lethal diseases worldwide and incidence continues to rise, resulting in increased deaths each year. In the modern era, patients often turn to online sources like YouTube for information regarding their disease, which may be subject to a high degree of bias and misinformation; previous analyses have demonstrated low quality of other cancer-related YouTube videos. Thus, we sought to determine if patients can rely on educational YouTube videos for accurate and comprehensive information about pancreatic cancer diagnosis and treatment. We designed a search query and inclusion/exclusion criteria based on published studies evaluating YouTube user tendencies, which were used to identify videos most likely watched by patients. Videos were evaluated based on two well-known criteria, the DISCERN and JAMA tools, as well as a tool published by Sahin et al. to evaluate the comprehensiveness of YouTube videos. Statistical analyses were performed using Chi-square analysis to compare categorical variables. We used linear regression to assess for correlations between quantitative variables. Kruskal-Wallis and independent samples t-test were used to compare means between groups. We assessed inter-rater reliability using Cronbach's alpha. After the initial search query, 39 videos were retrieved that met inclusion criteria. The comprehensiveness and quality of these materials was generally low to moderate, with only 7 videos being considered comprehensive. Pearson's R demonstrated strong correlations between video length and both comprehensiveness and quality. Higher-quality videos also tended to be newer. YouTube videos regarding pancreatic cancer are generally of low to moderate quality and lack comprehensiveness, which could affect patients' perceptions of their disease or understanding of treatment options. These videos, which have collectively been viewed over 6 million times, should be subject to some form of expert review before upload, and producers of this content should consider citing the sources used in the video.

Melanoma Treatments and Mortality Rate Trends in the US, 1975 to 2019.

Importance: Melanoma accounts for most of the deaths due to skin cancer. In the past decade, effective US Food and Drug Administration (FDA)-approved therapies for melanoma have emerged. Objective: To review changes in the long-term melanoma mortality rate (MMR) trends in the US and determine whether they have any temporal association with the FDA approval of new agents. Design, Setting, and Participants: This cross-sectional study used population data from the Surveillance, Epidemiology, and End Results (SEER) database and retrospectively reviewed the age-adjusted MMR trends in adult patients (aged ≥18 years) from 1975 to 2019 in the US population. The timeline of the FDA approvals for melanoma treatment was also reviewed. Data were analyzed from March 15 to August 15, 2022. Exposures: Outcomes were assessed in association with FDA approval of drugs for the treatment of melanoma. Main Outcomes and Measures: Mortality rates are from the SEER database, reported per 100 000 population and age-adjusted to the 2000 US standard population. The annual percent change (APC) has been used to report long-term trends. Results: After the introduction of newer treatments in 2011 (most after 2013), a significant reduction in MMR was seen from 2013 to 2017 in the US for the first time in the past 40 years. Rates increased from 1975 to 1988 (APC, 1.65% [95% CI, 1.30%-2.00%]; P < .001). No statistically significant change in MMR was seen from 1988 to 2013 (APC, 0.01% [95% CI, -1.10% to 0.12%]; P = .85). The MMR decreased significantly from 2013 to 2017 (APC, -6.28% [95% CI, -8.52% to -3.97%]; P < .001). Conclusions and Relevance: These findings suggest a benefit associated with the availability of effective therapies in the past decade and further suggest that the use of new pharmacological therapies is associated with decreased MMR in the US population. These data are very encouraging and support the continued development of such therapies. Additionally, the accessibility of these treatments and the associated health care costs need to be addressed.

Clinical Evaluation of Avelumab in the Treatment of Advanced Urothelial Carcinoma: Focus on Patient Selection and Outcomes.

BACKGROUND: First-line therapy for treatment of advanced urothelial carcinoma includes combination platinum-based chemotherapies, though resistance and long-term toxicity concerns to these regimens cause limitations in progression-free survival and overall survival. Maintenance treatment with an alternative agent such as the PD-L1 inhibitor, avelumab (Bavencio®), after initial chemotherapy has been shown to prolong overall survival. The aim of this review is to provide a landscape clinical use of avelumab in the treatment of advanced urothelial carcinoma with a focus on patient selection and outcomes. METHODS: This review includes the most up to date phases and results from clinical trials published in peer-reviewed journals. RESULTS: Three studies were included, one phase 1B trial, one phase 1B trial with 2 year follow-up, and one phase 3 trial. Patients receiving avelumab maintenance therapy at 10 mg/kg IV every two weeks had an overall better performance status, though those with an increased ECOG-PS, increased Bellmunt risk score, or failure of ≥3 chemotherapies had poorer responses. Patients over the age of 65 had a higher ORR (18-25%) compared to younger patients (13-14%). Patients with PD-L1 positive tumors had a significantly increased CR median ORR (13.8%), median PFS (5.7 months), and median 12-month OS rate (79.1%) compared to control subjects receiving best supportive care (1.2%, 2.1 months, 60.4%, respectively). TRAEs were seen in 86.7% of patients, with 32.4% of patients experiencing a ≥grade 3 AE. The most common AE was IRR (32.4%, ≥grade 3 1.01%) and irAE 25.6% of any grade, including various rashes and pruritus AEs, immune-related thyroid disorders, and immune related hepatitis. There were 3 reported treatment-related deaths (0.05%). Ongoing phases of one of the trials is investigating the use of docetaxel and avelumab together after failure of one chemotherapy. CONCLUSION: Avelumab as a maintenance therapy after platinum-based chemotherapy failure or in platinum-ineligible patients with advanced or metastatic urothelial carcinoma is an effective option with increased ORR, PFS, and OS with a similar safety profile to other chemotherapies. Ongoing studies currently in recruitment and active clinical trials will yield valuable insights into optimizing avelumab therapy in conjunction with chemotherapies and/or immunotherapies, better characterization of response for PD-L1 positive tumors, and a clearer insight into clinically validated prognostic factors to improve patient outcomes.

Subclonal landscape of cancer drives resistance to immune therapy.

Tumor mutation burden (TMB) is often used as a biomarker for immunogenicity and prerequisite for immune checkpoint inhibitor (ICI) therapy. However, it is becoming increasingly evident that not all tumors with high TMB respond to ICIs as expected. It has been shown that the ability of T-cells to infiltrate the tumor microenvironment and elicit a specific immune response is dependent not only on the TMB, but also on intra-tumor heterogeneity and the fraction of low-frequency subclonal mutations that make up the tumor. High intra-tumor heterogeneity leads to inefficient recognition of tumor neoantigens by T-cells due to their diluted frequency and spatial heterogeneity. Clinical studies have shown that tumors with a high degree of intra-tumor heterogeneity respond poorly to ICI therapy, and previous cytotoxic treatment may increase the intra-tumor heterogeneity and render second-line ICI therapy less effective. This paper reviews the role of ICI therapy when following chemotherapy or radiation to determine if they may be better suited as first-line therapy in patients with high TMB, low intra-tumor heterogeneity, and high PD-1, PD-L1, or CTLA-4 expression.

Homologous recombination proficiency in ovarian and breast cancer patients.

Homologous recombination and DNA repair are important for genome maintenance. Genetic variations in essential homologous recombination genes, including BRCA1 and BRCA2 results in homologous recombination deficiency (HRD) and can be a target for therapeutic strategies including poly (ADP-ribose) polymerase inhibitors (PARPi). However, response is limited in patients who are not HRD, highlighting the need for reliable and robust HRD testing. This manuscript will review BRCA1/2 function and homologous recombination proficiency in respect to breast and ovarian cancer. The current standard testing methods for HRD will be discussed as well as trials leading to approval of PARPi's. Finally, standard of care treatment and synthetic lethality will be reviewed.

Chimeric Antigen Receptor T-Cell Therapy: Reach to Solid Tumor Experience.

Chimeric antigen receptor (CAR) modified T-cell therapy, a unique platform technology highlighting precision medicine through utilization of molecular biology and cell-based therapeutics has shown unprecedented rates in patients with hematological malignancies such as acute lymphocyte leukemia, non-Hodgkin's lymphoma and multiple myeloma (MM). With the approval of CD19-targeted CAR T-cells by the Food and Drug Administration in acute lymphoblastic leukemia (ALL) and NHL, this technology is positioned for aggressive expansion to combination therapeutic opportunities and proof of principle towards utility in other malignant disorders. However, despite the impressive results seen with hematological malignancies, CAR T-cells have shown limited efficacy in solid tumors with several unsuccessful preclinical studies. Regardless, these attempts have provided us with a better understanding of the imminent challenges specific to solid tumors even if they have not so far led to expanded clinical treatment opportunities outside ALL/NHL/MM. This review summarizes our current understanding of CAR T-cell mechanism of action, while presenting the major limitations of CAR T-cell derived treatments in solid tumors. We further discuss recent findings and present new potential strategies to overcome the challenges facing solid tumor targeting by CAR T-cell platforms.