98%
921
2 minutes
20
Cancer causes over 10 million deaths annually worldwide, with 40.5% of Americans expected to be diagnosed in their lifetime. Early detection is critical; for liver cancer, survival rates improve from 4 to 37% when caught early. However, predicting time to first cancer diagnosis is challenging due to its complex and multifactorial nature. We developed predictive models using the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial for training and the UK Biobank for evaluation to estimate time-to-first cancer diagnosis for high-incidence cancers, including lung, liver, and bladder cancers. Utilizing Cox proportional hazards models with elastic net regularization, survival decision trees, and random survival forests, we used 46 sex-agnostic demographic, clinical, and behavioral features. The Cox model achieved a C-index of 0.813 for lung cancer, surpassing non-parametric machine learning methods in accuracy and interpretability. Cancer-specific models consistently outperformed non-specific cancer models, as shown by time-dependent AUC analyses. Scaled Cox coefficients revealed novel insights, including BMI's inverse association with lung cancer risk. Our findings offer interpretable, accurate tools for personalized cancer risk assessment, improving early detection and bridging computational advances with clinical practice.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12241622 | PMC |
http://dx.doi.org/10.1038/s41598-025-08790-w | DOI Listing |
Public Health
September 2025
Department of Public Health, Erasmus MC University Medical Center, Rotterdam, the Netherlands.
Objectives: Participation rates in fecal immunochemical test (FIT)-based colorectal cancer (CRC) screening differ across socio-demographic subgroups. The largest health gains could be achieved in subgroups with low participation rates and high risk of CRC. We investigated the CRC risk within different socio-demographic subgroups with low participation in the Dutch CRC screening program.
View Article and Find Full Text PDFBiomaterials
August 2025
Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA, 90095, USA. Electronic address:
Wearable bioelectronics have transformed modern biomedical applications by enabling seamless integration with biological tissues, providing continuous, comprehensive, and personalized healthcare. Skin cancer, particularly melanoma, poses a significant clinical challenge due to its high metastatic potential and associated mortality. Traditional diagnostic approaches face limitations in accuracy, accessibility, and reproducibility, while existing treatments are often constrained by systemic toxicity and therapeutic resistance.
View Article and Find Full Text PDFTurk J Pediatr
September 2025
Department of Pediatric Hematology and Oncology, the Affiliated Hospital of Qingdao University, Qingdao, Shandong, China.
Background: The expression and clinical correlation of BRAFV600E mutation and programmed cell death-1 ligand 1 (PD-L1) in children with Langerhans cell histiocytosis (LCH) have been reported, but the conclusions of previous studies are inconsistent. In addition, it has been reported that elevated cathepsin S (CTSS) expression is associated with various cancers. However, there is currently no research on the correlation between CTSS and LCH.
View Article and Find Full Text PDFTurk J Pediatr
September 2025
Department of Pediatric Hematology, Faculty of Medicine, Dokuz Eylül University, İzmir, Türkiye.
Backround: Leukemia is the most common childhood malignancy and often presents with nonspecific symptoms, which may lead to delays in diagnosis. Early recognition of clinical signs and laboratory abnormalities is essential to ensure timely referral and improve outcomes. This study assesses the clinical and laboratory characteristics of pediatric patients with acute and relapsed leukemia, points out key considerations during diagnosis, and investigates potential factors contributing to delayed diagnosis.
View Article and Find Full Text PDFAm J Clin Hypn
September 2025
Higher Institute of Nursing and Health Technology, Rabat, Morocco.
Gestational trophoblastic tumors (GTTs) encompass a spectrum of neoplastic conditions, including invasive mole, choriocarcinoma, placental site trophoblastic tumor, and epithelioid trophoblastic tumor. Invasive mole, which frequently develops following a complete hydatidiform mole, represents the most common form. A cancer diagnosis constitutes a profoundly destabilizing experience, often resulting in considerable psychological distress.
View Article and Find Full Text PDF