Lowering Cancer-Specific Mortality Rates Using Protein Biomarkers
Mostafizi, B.; Rudsari Khosfekr, H.; Irajizad, E.
Show abstract
BackgroundLate-stage diagnosis remains a significant contributor to cancer mortality worldwide. Protein biomarkers have emerged as critical tools in both early detection and monitoring. This study investigates whether specific protein biomarkers can be leveraged not only to detect cancers at earlier stages but to reverse tumor progression toward more treatable stages, ultimately reducing mortality. MethodsWe evaluated 39 protein biomarkers across eight prevalent cancer types: breast, colorectal, esophageal, liver, lung, ovarian, pancreatic, and stomach. Biomarker performance was assessed using receiver operating characteristic (ROC) curve analysis to calculate the area under the curve (AUC) and sensitivities at 90% specificity across cancer stages I through III. The highest-performing biomarkers were subsequently used to estimate potential stage-shift effects and the corresponding reduction in mortality. ResultsSpecific protein biomarkers demonstrated high predictive accuracy and strong potential for stage shifting across multiple cancers, which in turn may help reduce mortality. In breast cancer, a combination of prolactin and IL-8 achieved a 48.2% stage shift, translating into a 33.7% reduction in mortality. For colorectal cancer, integrating OPN and IL-8 led to a 68.7% stage shift, contributing to a 26.8% reduction in mortality. In esophageal cancer, OPN, HGF, and GDF15 shifted 65.4% of late-stage cases into earlier stages, resulting in a 12.4% mortality reduction. For liver cancer, Endoglin, HGF, and OPN together shifted 63% of late-stage cases to earlier stages, yielding a 4.4% reduction in mortality. In lung cancer, prolactin showed notable performance, shifting 65.1% of late-stage cancers to early stage, contributing to a 19% mortality reduction. Ovarian cancer demonstrated the greatest benefit, where prolactin and CA-125 shifted 79.1% of late-stage cancers to earlier stages, leading to a 50.3% decrease in projected deaths. In pancreatic cancer, TIMP-2 and CA19-9 shifted 81.1% of cases to earlier stages, helping lower mortality by 9.3%. Finally, in stomach cancer, OPN shifted 63.1% of late-stage cases to earlier stages, reducing mortality by 16.4%. ConclusionsProtein biomarkers offer a promising path not only for early detection but also for mortality reduction. This study highlights the potential of biomarker-driven strategies to reduce cancer mortality through stage regression, particularly in common and lethal cancers. ImpactThese findings underscore the potential for integrating biomarker-guided interventions into cancer care, offering a new paradigm in personalized oncology focused on shifting the stage landscape toward improved survival.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Predicting cancer origins with a DNA methylation-based deep neural network model 94%
- Pixelwise H-score: a novel digital image analysis based-metric to quantify membrane biomarker expression from immunohistochemistry images 93%
- Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images 92%
Similar papers in this journal
- Deep plasma proteomics identifies and validates an eight-protein biomarker panel that separate benign from malignant tumors in ovarian cancer 92%
- Machine learning models predict long COVID outcomes based on baseline clinical and immunologic factors 90%
- Subpopulation-specific Machine Learning Prognosis for Underrepresented Patients with Double Prioritized Bias Correction 90%
Similar papers in this journal
- Novel ratio-metric features enable the identification of new driver genes across cancer types 93%
- Identification of patients at risk for pancreatic cancer in a 3-year timeframe based on machine learning algorithms 92%
- Uncovering Hidden Cancer Self-Dependencies through Analysis of shRNA-Level Dependency Scores 92%
Similar papers in this journal
- A prospective validation of nomograms based on BC-116 and BC-106 urine peptide biomarker panels for bladder cancer diagnostics and monitoring 91%
- Frequent post-treatment monitoring of colorectal cancer using individualized ctDNA validated by multi-regional molecular profiling 91%
- Inequalities in the decline and recovery of pathological cancer diagnoses during the first six months of the COVID-19 pandemic: a population-based study 91%
Similar papers in this journal
- Prelude to Malignancy: A Gene Expression Signature in Normal Mammary Gland from Breast Cancer Patients Suggests Pre-tumorous Alterations and Is Associated with Adverse Outcomes 91%
- Novel mammogram-based measures improve breast cancer risk prediction beyond an established mammographic density measure 91%
- Prediction of Colorectal Cancer Risk Based on Profiling with Common Genetic Variants 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.