Liquid biopsies offer minimally invasive diagnosis and monitoring of cancer disease. This biosource is often analyzed using sequencing, which generates highly complex data that can be used using machine learning tools. Nevertheless, validating the clinical applications of such methods is challenging. It requires: (a) using data from many patients; (b) verifying potential bias concerning sample collection; and (c) adding interpretability to the model. In this work, we have used RNA sequencing data of tumor-educated platelets (TEPs) and performed a binary classification (cancer vs. no-cancer). First, we compiled a large-scale dataset with more than a thousand donors. Further, we used different convolutional neural networks (CNNs) and boosting methods to evaluate the classifier performance. We have obtained an impressive result of 0.96 area under the curve. We then identified different clusters of splice variants using expert knowledge from the Kyoto Encyclopedia of Genes and Genomes (KEGG). Employing boosting algorithms, we identified the features with the highest predictive power. Finally, we tested the robustness of the models using test data from novel hospitals. Notably, we did not observe any decrease in model performance. Our work proves the great potential of using TEP data for cancer patient classification and opens the avenue for profound cancer diagnostics.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10136732 | PMC |
http://dx.doi.org/10.3390/cancers15082336 | DOI Listing |
JTO Clin Res Rep
January 2025
Institut de Cancérologie de l'Ouest, 44805 Saint-Herblain, France.
Introduction: In a phase 1 study, bintrafusp alfa was found to have an encouraging clinical activity in patients with previously treated advanced NSCLC. This study evaluated the safety and efficacy of bintrafusp alfa with chemotherapy in patients with stage IV NSCLC regardless of the programmed death-ligand 1 (PD-L1) expression status.
Methods: In this open-label, phase 1b/2 study (NCT03840915), eligible patients were assigned to one of four cohorts.
Breast Cancer (Dove Med Press)
December 2024
Department of Breast Surgical Oncology, Montefiore Einstein Comprehensive Cancer Center, Bronx, NY, USA.
Early detection is a relative newcomer in medicine, with its efficacy relying not only on therapy but also on the availability of evidence supporting the advantage of treatment at an earlier stage. Late 19th century histologic evidence that cancer begins as a single primary focus and Halsted's centrifugal theory of stepwise spread (breast, regional nodes, and systemic distribution) provided the rationale for both en bloc surgery and the lifesaving benefit of early detection. Clinicians soon noticed exceptions to this ordered timeline, and pathologists identified histological features that questioned its primacy; however, Bernard Fisher spearheaded the initial challenge.
View Article and Find Full Text PDFThe purpose of this review was to analyze the most perspective methods for risk stratification of malignant transformation of pancreatic intraductal papillary mucinous neoplasms (IPMN). Advisability of humoral predictors (tumor markers, inflammatory markers, circulating leptin and branched-chain amino acids, etc.) is in identifying prognostic signs suitable for risk stratification of IPMN malignant transformation and, therefore, determining treatment strategy for a particular patient.
View Article and Find Full Text PDFInt J Nanomedicine
December 2024
Department of Obstetrics and Gynecology, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, 430071, People's Republic of China.
Purpose: Fetal nucleated red blood cells (fNRBCs) in the peripheral blood of pregnant women contain comprehensive fetal genetic information, making them an ideal target for non-invasive prenatal diagnosis (NIPD). However, challenges in identifying, enriching, and detecting fNRBCs limit their diagnostic potential.
Methods: To overcome these obstacles, we developed a novel biomimetic chip, replicating the micro-nano structure of red rose petals on polydimethylsiloxane (PDMS).
Front Oncol
December 2024
Analysis of Circulating Tumor Cells, Laboratory of Analytical Chemistry, Department of Chemistry, University of Athens, Athens, Greece.
Introduction: Detection of mutations in primary tumors and liquid biopsy samples is of increasing importance for treatment decisions and therapy resistance in many types of cancer. The aim of the present study was to directly compare the efficacy of a relatively inexpensive ultrasensitive real-time PCR with the well-established and highly sensitive technology of ddPCR for the detection of the three most common hotspot mutations of , in exons 9 and 20, that are all of clinical importance in various types of cancer.
Patients And Methods: We analyzed 42 gDNAs from primary tumors (FFPEs), 29 plasma-cfDNA samples, and 29 paired CTC-derived gDNAs, all from patients with ER+ metastatic breast cancer, and plasma from 10 healthy donors.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!