Deep learning-based identification of patients at increased risk of cancer using routine laboratory markers

2024-10-25

arXiv.org

AI Summary

This study addresses the high cost and limited accessibility of cancer screening in asymptomatic populations by proposing a multi-cancer risk stratification method leveraging routine blood tests—specifically complete blood count (CBC) and comprehensive metabolic panel (CMP). A deep neural network is employed to build an end-to-end predictive model, systematically demonstrating for the first time that low-cost, widely available laboratory biomarkers can effectively identify early-stage risk for colorectal cancer (AUC = 0.76), hepatocellular carcinoma (AUC = 0.85), and lung cancer (AUC = 0.78). Innovatively, the work establishes a real-world clinically aligned risk stratification paradigm, enabling both individualized pre-screening triage and regional population-level health management. The findings provide an evidence-based, implementation-ready technical pathway to achieve broad-coverage, low-burden cancer early detection using existing clinical laboratory infrastructure.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Metareasoning and Metaheuristics
• Computer Vision: Multi-modal Vision

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Early screening for cancer has proven to improve the survival rate and spare patients from intensive and costly treatments due to late diagnosis. Cancer screening in the healthy population involves an initial risk stratification step to determine the screening method and frequency, primarily to optimize resource allocation by targeting screening towards individuals who draw most benefit. For most screening programs, age and clinical risk factors such as family history are part of the initial risk stratification algorithm. In this paper, we focus on developing a blood marker-based risk stratification approach, which could be used to identify patients with elevated cancer risk to be encouraged for taking a diagnostic test or participate in a screening program. We demonstrate that the combination of simple, widely available blood tests, such as complete blood count and complete metabolic panel, could potentially be used to identify patients at risk for colorectal, liver, and lung cancers with areas under the ROC curve of 0.76, 0.85, 0.78, respectively. Furthermore, we hypothesize that such an approach could not only be used as pre-screening risk assessment for individuals but also as population health management tool, for example to better interrogate the cancer risk in certain sub-populations.

Problem

• Cancer Screening
• Early Detection
• Risk Stratification

Innovation

• Advanced Computer Technology
• Cancer Risk Prediction
• Personalized Health Management