What is the clinical evidence from this study?

Study design: Observational. Population: Cancer (n=5376). Intervention: AI-based cancer risk assessment (CRA) model. Primary outcome: Model performance (Area Under the Curve) for cancer detection.

What question did this study set out to answer?

To develop an AI-based cancer risk assessment model utilizing routine laboratory tests to improve early cancer detection.

April 5, 2026

Abstract 5103: AI-empowered cancer risk assessment model based on routine laboratory tests for enriching individuals at high risk of cancer

Key Result

An AI-based cancer risk assessment model using routine laboratory tests achieved a validation AUC of 0.802 and enriched cancer prevalence from 26.0% to 38.2% among predicted positive individuals.

Key Points

To develop an AI-based cancer risk assessment model utilizing routine laboratory tests to improve early cancer detection.
Retrospective analysis of laboratory data from 5,376 individuals (1,399 with cancer, 3,977 without) across two hospitals.
Gradient boosting framework used to calculate cancer risk assessment (CRA) scores from 43 features.
Evaluation of the CRA model's performance through AUC, sensitivity, and specificity metrics.
CRA model achieved AUCs of 0.738 in training and 0.802 in validation cohorts.
Sensitivity reached 87.5% and 90.0% at specificities of 50.0% and 47.2%, respectively.
Cancer prevalence in CRA-positive individuals increased from 26.0% to 38.2%.
In the subgroup with CRA > 0.88, 65.4% were cancer patients, with higher advanced disease stages.
Population simulation showed cancer incidence increased to 1.5%, reducing false positives by 33.3% and halving screening costs.

Study Design

Type

Observational (n=5,376)

Multicenter

Yes

Structured PICO

Does an AI-based cancer risk assessment model using routine laboratory tests improve cancer detection and screening cost-effectiveness?

Population

5,376 individuals (1,399 cancer; 3,977 non-cancer) across two hospitals

Intervention

AI-based cancer risk assessment (CRA) model using 43 features from routine laboratory tests (complete blood count, urinalysis, and biochemical panels)

Outcome

Diagnostic performance (AUC, sensitivity, specificity) of the CRA model for cancer detection

An AI-based cancer risk assessment model using routine laboratory tests can effectively enrich high-risk individuals, potentially halving screening costs when used before multi-cancer early detection tests.

Abstract

Abstract Background: Early cancer detection improves survival, yet population-wide screening remains costly and logistically challenging. Traditional cancer risk models, such as lifestyle-based assessments and polygenic risk scores, offer limited sensitivity. In contrast, routine laboratory tests (complete blood count, urinalysis, and biochemical panels) are already widely performed in primary care and may harbor latent cancer signals. We developed an AI-based cancer risk assessment (CRA) model using these existing data to enrich cancer cases and improve the cost-effectiveness of downstream multi-cancer early detection (MCED) tests. Methods: Routine laboratory data from 5, 376 individuals (1, 399 cancer; 3, 977 non-cancer) across two hospitals were retrospectively collected and split into training and validation cohorts. A total of 43 features were selected to calculate CRA scores using a gradient boosting framework. All participants also underwent OncoSeek testing, a validated MCED assay combining multiple protein tumor markers with clinical data, applied to CRA-positive individuals. Results: The CRA model achieved AUCs of 0. 738 and 0. 802, with sensitivities of 87. 5% and 90. 0% at specificities of 50. 0% and 47. 2% in the training and validation cohorts. Among individuals predicted positive (CRA 0. 4, n = 3241), cancer prevalence increased from 26. 0% to 38. 2% (1. 5-fold enrichment). In this enriched group, OncoSeek achieved 37. 0% sensitivity at 97. 3% specificity, and 56. 6% sensitivity when restricted to its covered 14 cancer types. Furthermore, within the high-risk subgroup (CRA 0. 88, n = 231), 65. 4% were cancer patients, with a higher proportion of advanced disease (Stage IV: 42. 2%) than the overall cohort (25. 0%), indicating potential to flag patients needing prompt diagnostic evaluation. A population-level simulation in 1 million adults ≥50 years (incidence = 0. 9%) showed that adding CRA before OncoSeek increased cancer incidence to 1. 5% (1. 7-fold), reduced false positives by 33. 3%, and halved total screening cost (80. 0 M → 40. 5 M), lowering cost per detected case by 44. 1%, demonstrating improved efficiency and cost-effectiveness. Conclusion: The AI-based CRA model, leveraging routine primary care data, provides substantially higher sensitivity and broader applicability than polygenic risk scores. Beyond enriching cancer incidence for screening, CRA can also flag individuals with strong cancer signals who may require prompt diagnostic evaluation in EMR system. When integrated as a front-end enrichment step before MCED testing, this approach effectively filters out low-risk individuals, reduces unnecessary downstream testing, and halves screening costs with only a modest (∼9%) sensitivity reduction. The combined CRA + MCED framework offers a scalable and economically sustainable pathway for precision population-level cancer early detection. Citation Format: Mao Mao, Yi Luan, Yong Shen, Shiyong Li, Shibin Long, Wei Wu. AI-empowered cancer risk assessment model based on routine laboratory tests for enriching individuals at high risk of cancer abstract. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts) ; 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86 (7 Suppl): Abstract nr 5103.

Bookmark