Skip to content

Construction of a Multimodal Model for Early Diagnosis of Hematological Malignancies Driven by Routine Blood Test Data

Construction of a Multimodal Model for Early Diagnosis of Hematological Malignancies Driven by Routine Blood Test Data

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600122303
Enrollment
Unknown
Registered
2026-04-11
Start date
2026-04-30
Completion date
Unknown
Last updated
2026-04-14

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Hematological malignancies

Interventions

Gold Standard:Bone marrow aspiration examination
Index test:The diagnostic test to be evaluated in this study is a blood routine data-driven multimodal model for the early diagnosis of hematologic neoplasms. This model takes relevant indicators of c
2.Original data/images of white blood cell scatter plots
3.Original data/images of reticulocyte scatter plots. 4.As an integrated diagnostic test method, this multimodal model realizes the early diagnostic evaluation of hematologic neoplasms by integrating

Sponsors

West China Hospital of Sichuan University
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: Inclusion Criteria Case Group: 1.Aged >=18 years;Definite diagnosis of hematologic neoplasms in line with clinical gold standards; 2.Complete data of complete blood cell analysis before diagnosis (without any targeted treatment received), 3.Including numerical parameters and original data/images of white blood cell and reticulocyte scatter plots. Control Group: 1.Aged >=18 years; 2.Underwent examinations such as bone marrow aspiration due to suspected hematologic neoplasms, and malignant hematologic diseases were definitively ruled out by gold standards; 3.Complete routine blood numerical parameters and data of white blood cell and reticulocyte scatter plots before bone marrow aspiration.

Exclusion criteria

Exclusion criteria: Exclusion Criteria 1.Severe missing or poor quality of routine blood numerical parameters or scatter plot data that renders them unfit for research analysis; 2.Having received treatments that may significantly affect routine blood test results (e.g., chemotherapy, radiotherapy, targeted therapy, stem cell transplantation) prior to the diagnosis of hematologic neoplasms; 3.Combined with known severe non-hematological infections (such as sepsis), severe renal failure, bone marrow metastasis of solid tumors, pregnancy, and other diseases or conditions that significantly interfere with blood routine and scatter plot manifestations.

Design outcomes

Primary

MeasureTime frame
Complete blood count numerical parameters (DIFF);White blood cell scatter plot raw data (WBC);Accuracy;Precision;Recall (Sensitivity);Specificity;

Countries

China

Contacts

Public ContactZheng Qin

West China Hospital of Sichuan University

zhengqinhx@scu.edu.cn+86 189 8060 6750

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Apr 17, 2026