Development of a Pan-Cancer Screening Model Based on Blood Biomarkers (PanCanBlood)

Establishment of a Pan-Cancer Screening Model Based on Blood Biomarkers

This study aims to develop a pan-cancer screening model using routine blood biomarkers (including complete blood count, biochemical tests, coagulation panel, and tumor markers). The study is retrospective, collecting data from approximately 10,000,000 cancer patients diagnosed at multiple centers in China between January 2006 and September 2025. All patients have confirmed pathological diagnosis and complete blood test records. A Mixture of Experts (MoE) machine learning model will be built to predict the presence of various cancers (e.g., gastric, colorectal, liver, lung, ovarian cancer). The goal is to establish a low-cost, non-invasive screening tool suitable for large-scale population screening.

Study Overview

• Status: Active, not recruiting
• Conditions: Neoplasms
• Intervention / Treatment: Other: No intervention

Detailed Description

Background: Cancer is a leading cause of death worldwide. Early detection improves survival, but current screening methods (e.g., endoscopy, imaging) are invasive, costly, or not widely accessible. Blood-based biomarkers offer a non-invasive, repeatable, and cost-effective alternative.

Objective: Primary: To establish a pan-cancer screening model based on blood biomarkers. Secondary: To combine multiple blood markers for identifying high-risk populations. Exploratory: To develop a cost-effective, scalable screening technology.

Study Design: This is a multicenter, retrospective study. Data will be collected from 15 participating hospitals in China, including Zhejiang Cancer Hospital, Tongling People's Hospital, Pingyang People's Hospital, Fenghua People's Hospital, Shaoxing Central Hospital, Bingqi General Hospital, the Second Affiliated Hospital of Jiaxing University, Taizhou Hospital of Zhejiang Province affiliated to Wenzhou Medical University, Affiliated Jinhua Hospital, Zhejiang University School of Medicine, Yunnan Cancer Hospital, Xianju People's Hospital, Longhua Hospital, Shanghai University of Traditional Chinese Medicine, No.9 Hospital Ningbo, Norinco General Hospital, Quzhou Kecheng People's Hospital.

Participants: Approximately 10,000,000 patients aged 18-80 years with pathologically confirmed cancer (including respiratory, digestive, urogenital, nervous, endocrine, and soft tissue malignancies). Exclusion criteria: presence of non-cancer organic diseases, hematologic disorders, immunodeficiency (e.g., AIDS), or incomplete data.

Data collection: Blood biomarkers including complete blood count, biochemical tests (liver/kidney function, glucose, lipids), coagulation (PT, APTT, TT, fibrinogen), and tumor markers (e.g., CEA, CA19-9, AFP, CA125, etc.) along with clinical data (age, sex, height, weight, diagnosis) will be extracted from medical records.

Statistical analysis: A Mixture of Experts (MoE) architecture with deep residual networks, attention-based gating, and feature interaction (FM + deep neural networks) will be used. Multi-task learning, Focal Loss for class imbalance, and adaptive sample weighting will be applied. Model performance will be evaluated for sensitivity, specificity, and AUC.

Ethics: Approved by the Ethics Committee of Zhejiang Cancer Hospital (IRB-2025-1319[IIT]). Because this is a retrospective study using de-identified data, the committee approved a waiver of informed consent for patients without prior general consent, in accordance with Chinese regulations and the Declaration of Helsinki. Data will be encrypted and stored securely for 15 years after study completion.

Dissemination: Results will be published in peer-reviewed journals and presented at conferences.

• Study Type: Observational
• Enrollment (Estimated): 10000000

Contacts and Locations

Study Locations

• China
  • Zhejiang
    • Hangzhou, Zhejiang, China, 310022
      • Zhejiang Cancer Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

The study population consists of two groups: (1) patients with pathologically confirmed cancer (including gastric, colorectal, liver, lung, ovarian, and other solid tumors) and (2) non-cancer controls (individuals undergoing routine health checkups without cancer or other major organic diseases). All participants are aged 18-80 years. Data are retrospectively collected from medical records across multiple centers in China.

Description

Inclusion Criteria:

• Pathologically confirmed cancer patients (for case group) OR individuals without cancer (for control group)
• Age between 18 and 80 years
• Complete clinical data and blood test results (complete blood count, biochemistry, coagulation panel, tumor markers) available
• No history of other organic diseases (excluding cancer)

Exclusion Criteria:

• Presence of organic diseases other than cancer (e.g., severe heart, liver, kidney disease)
• Hematologic disorders or immunodeficiency diseases (e.g., AIDS)
• Incomplete data or missing timeline records

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
All Participants; All enrolled individuals (cancer patients and non-cancer controls) with retrospective blood biomarker data.	Other: No intervention; This is an observational, retrospective study with no assigned interventions. Data are collected from existing medical records, including routine blood biomarkers (complete blood count, biochemistry, coagulation panel, tumor markers). No experimental drugs, devices, or procedures are administered. Only de-identified historical data are used for model development.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Area under the ROC curve (AUC)	AUC of the MoE model for discriminating cancer from non-cancer controls.	At study completion, approximately December 2030
Sensitivity of the model	True positive rate of the pan-cancer screening model.	At study completion, approximately December 2030
Specificity of the model	True negative rate of the pan-cancer screening model.	At study completion, approximately December 2030

Collaborators and Investigators

• Sponsor: Zhejiang Cancer Hospital
• Investigators: Principal Investigator: Xiangdong Cheng, MD, PhD, Zhejiang Cancer Hospital

Study record dates

Study Major Dates

• Study Start (Actual): October 22, 2025
• Primary Completion (Estimated): July 31, 2027
• Study Completion (Estimated): December 31, 2030

Study Registration Dates

• First Submitted: April 14, 2026
• First Submitted That Met QC Criteria: April 22, 2026
• First Posted (Actual): April 28, 2026

Study Record Updates

• Last Update Posted (Actual): April 28, 2026
• Last Update Submitted That Met QC Criteria: April 22, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: machine learning; early detection; blood biomarkers; pan-cancer
• Additional Relevant MeSH Terms: Neoplasms
• Other Study ID Numbers: IRB-2025-1319[IIT]

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Data sharing is not permitted due to ethical and privacy restrictions.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No