A deep learning model predicts the presence of diverse cancer types using circulating tumor cells.

Circulating tumor cells (CTCs) are cancer cells that detach from the primary tumor and intravasate into the bloodstream. Thus, non-invasive liquid biopsies are being used to analyze CTC-expressed genes to identify potential cancer biomarkers. In this regard, several studies have used gene expression changes in blood to predict the presence of CTC and, consequently, cancer. However, the CTC mRNA data has not been used to develop a generic approach that indicates the presence of multiple cancer types. In this study, we developed such a generic approach. Briefly, we designed two computational workflows, one using the raw mRNA data and deep learning (DL) and the other exploiting five hub gene ranking algorithms (Degree, Maximum Neighborhood Component, Betweenness Centrality, Closeness Centrality, and Stress Centrality) with machine learning (ML). Both workflows aim to determine the top genes that best distinguish cancer types based on the CTC mRNA data. We demonstrate that our automated, robust DL framework (DNNraw) more accurately indicates the presence of multiple cancer types using the CTC gene expression data than multiple ML approaches. The DL approach achieved average precision of 0.9652, recall of 0.9640, f1-score of 0.9638 and overall accuracy of 0.9640. Furthermore, since we designed multiple approaches, we also provide a bioinformatics analysis of the gene commonly identified as top-ranked by the different methods. To our knowledge, this is the first study wherein a generic approach has been developed to predict the presence of multiple cancer types using raw CTC mRNA data, as opposed to other models that require a feature selection step.

Thirty-Day Mortality After Curative and Palliative Anti-Cancer Treatment: Data Interpretation and Lessons for Clinical Implementation.

PURPOSE: Despite advancements in cancer therapeutics, mortality and morbidity due to anti-cancer treatments still occur but are not frequently reported. We aimed to report the 30-day mortality and morbidity of all curative and palliative anti-cancer treatments. PATIENTS AND METHODS: Adults with solid and hematological malignancies from two large cancer centers in Saudi Arabia, irrespective of the cancer stage and treatment type, were included in this retrospective observational study. RESULTS: Between December 1, 2019 and February 29, 2020, 1694 patients from King Abdullah Medical City in Makkah and King Fahad Medical City in Riyadh were included in the study. Among them, 77.5% were younger than 65 years of age; 72.8% were female; the prevalence of obesity, diabetes, and hypertension was 35%, 34%, and 28%, respectively; and 66.5% of patients had breast and gastrointestinal cancers. Fifty-nine (3.5%) patients died within 30 days of receiving anti-cancer treatment. Of them, 9 (0.3%) were treated with curative intent, and 50 (3%) were treated with palliative intent. CONCLUSION: Our results emphasize the need to address preventable metabolic changes and implement innovative, predictive, preventive, and personalized medicine (PPPM) approaches focusing on patient profiles. Reporting the 30-day outcomes of all anti-cancer treatments will also allow the identification of factors underlying mortality and morbidity and lead to an improvement in oncological outcomes via innovative programs designed to improve clinical decision-making.