-Author name in bold denotes the presenting author
-Asterisk * with author name denotes a Non-ASH member
Clinically Relevant Abstract denotes an abstract that is clinically relevant.

PhD Trainee denotes that this is a recommended PHD Trainee Session.

Ticketed Session denotes that this is a ticketed session.

901 Interpretable Artificial Intelligence (AI) Differentiates Prefibrotic Primary Myelofibrosis (prePMF) from Essential Thrombocythemia (ET): A Multi-Center Study of a New Clinical Decision Support Tool

Program: Oral and Poster Abstracts
Type: Oral
Session: 803. Emerging Tools, Techniques and Artificial Intelligence in Hematology: Image-Based Machine Learning in Hematology
Hematology Disease Topics & Pathways:
Research, artificial intelligence (AI), adult, Translational Research, MPN, Clinical Research, health outcomes research, Chronic Myeloid Malignancies, Diseases, computational biology, Myeloid Malignancies, Technology and Procedures, Study Population, Human, machine learning, Pathology
Monday, December 11, 2023: 2:45 PM

Andrew Srisuwananukorn, MD1, Giuseppe Gaetano Loscocco2*, Andrew T. Kuykendall, MD3, James M Dolezal, MD4, Raffaella Santi, MD5*, Ling Zhang, MD6, Avani M Singh, MD7*, Paola Guglielmelli, MD, PhD8, Alessandro Maria Vannucchi9, Douglas Tremblay, MD10, Alexander T Pearson, MD, PhD11*, Mohamed E. Salama, MD12,13* and Ronald Hoffman, MD14

1Division of Hematology, Department of Internal Medicine, The Ohio State University Comprehensive Cancer Center, Columbus, OH
2Centro Ricerca e Innovazione Malattie Mieloproliferative (CRIMM), AOU Careggi, Florence, ITA
3Moffitt Cancer Center, Tampa, FL
4Department of Medicine, University of Chicago Comprehensive Cancer Center, Chicago
5Pathology Section, Department of Health Sciences, University of Florence, Florence, Italy
6Department of Pathology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL
7Department of Hematology Oncology, H. Lee Moffitt Cancer Center & Research Institute, Tampa
8Centro Ricerca e Innovazione Malattie Mieloproliferative (CRIMM), AOU Careggi, Florence, Italy
9CRIMM, Center for Research and Innovation of Myeloproliferative Neoplasms, Azienda Ospedaliero-Universitaria Careggi, Firenze, Italy
10Department of Hematology and Medical Oncology, Mount Sinai School of Medicine, New York, NY
11Department of Medicine, University of Chicago Comprehensive Cancer Center, Chicago, IL
12Department of Pathology, University of Texas Health Science Center, San Antonio
13Sonic Healthcare USA, Austin, TX
14Department of Medicine, Division of Hematology and Medical Oncology, Icahn School of Medicine at Mount Sinai, New York, NY


Overlapping clinical, molecular, and histopathological characteristics pose challenges in differentiating prePMF from ET. The median overall survival, however, significantly differs between prePMF and ET (11.9 vs 22.2 years, Jeryczynski, 2017). The difference in survival highlights the need to distinguish between these two myeloproliferative neoplasms (MPNs) to select disease-specific therapeutic options. This area of unmet need often requires expert assessment at high-volume academic institutions to render a definitive diagnosis. Our aim in this study is to develop and validate a biologically-motivated AI algorithm to rapidly, accurately, and inexpensively diagnose prePMF and ET directly from diagnostic bone marrow (BM) biopsy digital whole-slide images (WSI).


Patients with a clinical/histopathological diagnosis of prePMF or ET as determined by the International Consensus Classification of Myeloid Neoplasms were identified at the University of Florence, Italy (Florence) between 06/2007 and 05/2023 and Moffitt Cancer Center, Tampa, FL (Moffitt) between 01/2013 and 01/2022. Diagnostic H&E-stained BM biopsy slides were digitized using Aperio AT2 slide scanners (Leica Biosystems, Deer Park, IL) at each institution. The training cohort comprised of 200 (100 prePMF / 100 ET) patients from Florence, and the external test cohort entailed 26 (6 prePMF / 20 ET) patients from Moffitt.

In total, the resultant model was trained on 32,226 patient-derived WSI. Our chosen pretrained neural network, RetCCL, was previously trained on 32,000 diagnostic WSIs to potentially represent a histologically-informed model (Wang, 2023). BM WSI were tessellated into representative image tiles extracted at 10x magnification (302 microns per image dimensions) for model training. Finally, a prediction upon each patient’s WSI was calculated by attention-based multiple instance learning, which is a method that automatically assigns a numeric weight to an image portion representing its relative importance to the classification task.

Model performance was assessed utilizing the area under the receiver operator curve (AUC). The cutoff threshold for diagnosis classification was determined by maximizing Youden’s Index. For qualitative assessment, attention scores were plotted as a heatmap across the BM WSI and reviewed for morphological features by an expert hematopathologist.

Custom scripts were written using our open-source AI framework, Slideflow (Dolezal, 2021). Model development was performed on the Minerva High Performance Computer at Mount Sinai Hospital. Evaluation time upon a single WSI was estimated using a consumer-grade computer with an NVIDIA RTX 3080 graphics processing unit.


Within the training cohort, 5-fold cross validation resulted in a mean AUC of 0.90 and standard deviation of 0.04. A final locked model re-trained on the entire training cohort resulted in an AUC of 0.90 upon evaluation of the test cohort (Figure 1). We optimized the classification threshold to balance sensitivity and specificity; the final diagnostic classification accuracy on the test cohort was 92.3% with a sensitivity and specificity for prePMF diagnosis of 66.6% and 100%, respectively. Upon review of the slides with highest prediction value per class, attention heatmaps highlighted the model’s reliance on areas of cellular marrow without reliance on image artifacts or background (Figure 2). Using affordable consumer-grade hardware, evaluation upon a previously unseen WSI was completed in approximately 6.1 seconds (4.9 for preprocessing and 1.2 for evaluation).


We developed a novel AI model with high accuracy for distinguishing between prePMF and ET in distinct clinical cohorts. To our knowledge, this study represents the largest image-based AI study within MPNs with external validation. Our proposed model may assist clinicians in appropriately identifying patient cohorts who would benefit from disease-specific therapies or enrollment onto clinical trials. We imagine that a potential high-speed, low-cost algorithm may reliably distinguish prePMF from ET patients with high specificity which can be democratized to the MPN clinical community in routine practice and drive clinical trial accrual for biologically rational novel therapeutics.

Disclosures: Kuykendall: Protagonist Therapeutics, Inc.: Consultancy, Research Funding; Prelude: Research Funding; Morphosys: Consultancy, Research Funding; BMS: Consultancy, Research Funding; Blueprint: Consultancy, Research Funding, Speakers Bureau; CTI: Consultancy; Incyte: Consultancy; AbbVie: Consultancy; Novartis: Consultancy; GSK: Consultancy; Sierra Oncology: Research Funding; Imago: Consultancy. Guglielmelli: GSK: Speakers Bureau; Novartis: Other: Other member of advisory board, speaker at meeting, Speakers Bureau; Abbvie: Other: Other member of advisory board, speaker at meeting, Speakers Bureau. Vannucchi: Abbvie: Honoraria; Roche: Honoraria; AOP: Honoraria; Novartis: Honoraria; BMS: Honoraria; GSK: Honoraria; Incyte: Honoraria. Tremblay: CTI Biopharma: Consultancy, Research Funding; Novartis: Consultancy; AbbVie: Consultancy; Sierra Oncology: Consultancy; GSK: Consultancy; Cogent Biosciences: Consultancy; Astellas Pharma: Research Funding; Gilead: Research Funding. Salama: Sonic Healthcare USA: Current Employment. Hoffman: Dompe: Patents & Royalties; Kartos Abbvie: Research Funding; TD2: Research Funding; Summitomo: Research Funding; Silence Therapeutics: Consultancy; Dexcel Pharma: Research Funding; Karyopharm: Research Funding; Curis: Research Funding; Cellinkos: Consultancy; Protagonist Therapeutics: Consultancy.

Previous Abstract | Next Abstract >>
*signifies non-member of ASH