2026 ASH®
Annual Meeting & Exposition December 12-15, 2026 ▪ New Orleans, Louisiana

Paper Details

Abstracts, authors, affiliations, and disclosures.

Sunday, December 13, 2026
06:00 p.m. - 08:00 p.m.
MCCNO - Hall F
Access, Representation, Population Health, Technology and Procedures, Molecular Testing, Omics Technologies, Bioinformatics, Clinical Procedures, Computational Biology, Emerging Technologies, Profiling, Treatment Considerations, Combination Therapy, Drug Development, Therapy Sequence, Biological Therapies, Antibody Therapy, Transplantation, Monoclonal Antibody Therapy, Non-Biological Therapies, Chemotherapy, Adverse Events, Artificial Intelligence (AI), Machine Learning, Biological Processes, Apoptosis, Pathogenesis, Genomics, Immune Mechanism, Molecular Biology, Clinical Practice (Health Services and Quality), Clinical Guidelines, Patient Safety, Quality Improvement, Diseases, Bleeding and Clotting, Thromboembolism, Thrombotic Disorders, Myeloid Malignancies, Acute Myeloid Malignancies, Chronic Myeloid Malignancies, Research, AML, Translational Research, MPN, Clinical Research, Clinical Trials, Epidemiology, Health Outcomes Research, Patient-Reported Outcomes, Real-World Evidence, Registries, Study Population, Human, Adult, Pregnant, Young Adult
PAPER

3789 A machine learning-based signature for precise diagnosis and leukemic transformation prediction in essential thrombocythemia.

Qianqian Liu, Sun Ting, PhD2, Anqi Zhang3, Renchi Yang4, Lei Zhang, MD5
1 State Key Laboratory of Experimental Hematology, National Clinical Research Center for Blood Diseases, Haihe Laboratory of Cell Ecosystem, Tianjin Key Laboratory of Gene Therapy for Blood Diseases, CAMS Key Laboratory of Gene Therapy for Blood Diseases, Institute of Hematology & Blood Diseases Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin, China
2 State Key Laboratory of Experimental Hematology, National Clinical Research Center for Blood Diseases, Haihe Laboratory of Cell Ecosystem, Tianjin Key Laboratory of Gene Therapy for Blood Diseases, CAMS Key Laboratory of Gene Therapy for Blood Diseases, Institute of Hematology & Blood Diseases Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin, China
3 State Key Laboratory of Experimental Hematology, National Clinical Research Center for Blood Diseases, Haihe Laboratory of Cell Ecosystem, Tianjin Key Laboratory of Gene Therapy for Blood Diseases, CAMS Key Laboratory of Gene Therapy for Blood Diseases, Institute of Hematology & Blood Diseases Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin, China
4 State Key Laboratory of Experimental Hematology, National Clinical Research Center for Blood Diseases, Haihe Laboratory of Cell Ecosystem, Tianjin Key Laboratory of Gene Therapy for Blood Diseases, CAMS Key Laboratory of Gene Therapy for Blood Diseases, Institute of Hematology & Blood Diseases Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin, China
5 State Key Laboratory of Experimental Hematology, National Clinical Research Center for Blood Diseases, Haihe Laboratory of Cell Ecosystem, Tianjin Key Laboratory of Gene Therapy for Blood Diseases, CAMS Key Laboratory of Gene Therapy for Blood Diseases, Institute of Hematology & Blood Diseases Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin, China

Background:Essential thrombocythemia (ET) is a chronic myeloproliferative neoplasm characterized by megakaryocyte hyperplasia and thrombocytosis. Although the median survival of ET patients is approximately 18 years, an estimated 3% transforms into acute myeloid leukemia (AML), which carries a dismal prognosis.

Aims: To identify a protein signature for precise diagnosis and leukemic transformation prediction in ET.

Methods: The 4D direct DIA method was utilized for proteomic analyses. Differentially expressed proteins (DEPs) were identified between 11 patients with ET and 7 healthy donors (HDs), among which proteins associated with immune-inflammatory pathways were then screened.Machine learning approaches, including the least absolute shrinkage and selection operator (LASSO), Support Vector Machine (SVM) and random forest (RF), were used to select core proteins. Model performance and the core proteins' potential for predicting leukemic transformation were evaluated by the area under the receiver operating characteristic curve (AUC).

Results: To specifically capture proteins indicative of ET-driven progression rather than general AML features, we first defined the ET-specific proteome against HDs. Compared to HDs, patients with ET exhibited significant alterations in 194 proteins (139 upregulated, 55 downregulated), which were enriched in pathways related to platelet activation and aggregation, neutrophil degranulation, and integrin signaling pathways. Cross-referencing the DEPs with known immune-inflammatory gene sets yielded 24 key candidate proteins. Using three machine learning algorithms(LASSO regression, SVM, and RF), three core proteins were identified: VASP, TFRC, and EMP3. These three core proteins were demonstrated excellent diagnostic performance in distinguishing ET and HDs (AUC > 0.9). Then we analyzed the BM proteomic sequencing data from 11 patients with ET and 6 patients with post-ET leukemic transformation. Decreased EMP3 expression was observed in transformed cases. Based on the three core proteins, we developed a model for predicting the risk of leukemic transformation in ET (AUC: 0.909, 95% CI: 0.724– 1.000). 

Conclusions: This study reports a three-protein signature (EMP3, VASP, TFRC) that offers clues to the pathogenesis of ET, while also serving as a tool for precise diagnosis and leukemic transformation prediction.

Qianqian Liu: No relevant conflicts of interest to declare.