{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T03:40:03Z","timestamp":1792813203125,"version":"4.5.0"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003196","name":"Ministero della Salute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003196","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Recently, artificial intelligence (AI) has become a valuable tool for diagnosing and predicting outcomes in blood disorders. Whole Slide Imaging (WSI) of bone marrow biopsies (BMBs) offers detailed, high-resolution views of cells and tissues; its adoption may improve the resources dedicated to the interpretation of BMB with suspected early myeloproliferative neoplasms (MPNs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We collected a retrospective dataset of H&amp;amp;E-stained BMBs from 88 patients diagnosed with MPN, divided into three groups: 19 with prefibrotic primary myelofibrosis (pre-PMF), 30 with polycythemia vera (PV), and 39 with essential thrombocythemia (ET). Using AI, we framed this as a three-class classification problem. For each whole slide image, we automatically calculated cellularity and cell density. We extracted morphological features related to megakaryocytes\u2014area, perimeter, and circularity\u2014and summarized them for each patient using statistics like mean, standard deviation, skewness, kurtosis, and entropy. This resulted in 17 features combining nuclear morphology, cell density statistics, and cellularity. After selecting significant features with the Kruskal-Wallis test, we trained a Support Vector Machine (SVM) classifier with 5-fold cross-validation to predict MPN subtypes. We then tested the model on 13 patients with a diagnosis of MPN not otherwise specified (MPN-NOS) to assess its capacity to correctly characterize the diagnosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The model achieved a mean multiclass Area Under the Curve (AUC) of 0.70 \u00b1 0.01 and an accuracy of 0.60 \u00b1 0.03. When tested on the 13 patients with MPN not otherwise specified (MPN-NOS), the model agreed with pathologists\u2019 biopsy classifications 61.5% of the time and with clinical follow-up evaluations 50% of the time.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study represents a first step toward the development of automated tools to support MPN diagnosis, providing potential assistance to haematologists and pathologists in the clinical management of patients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2025.1741610","type":"journal-article","created":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T05:40:31Z","timestamp":1769406031000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Predicting modelling for early diagnosis in early myeloproliferative neoplasms, not otherwise specified. Evidence from a machine learning study"],"prefix":"10.3389","volume":"15","author":[{"given":"Anna","family":"Scattone","sequence":"first","affiliation":[{"name":"Pathology Department, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Lupo","sequence":"additional","affiliation":[{"name":"Biostatistics and Bioinformatics Laboratory, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Concetta","family":"Saponaro","sequence":"additional","affiliation":[{"name":"Pathology Department, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Margherita","family":"Sonnessa","sequence":"additional","affiliation":[{"name":"Pathology Department, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Ditonno","sequence":"additional","affiliation":[{"name":"Hematology and Cell Therapy Unit, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d, Viale Orazio Flacco","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samantha","family":"Bove","sequence":"additional","affiliation":[{"name":"Biostatistics and Bioinformatics Laboratory, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annarita","family":"Fanizzi","sequence":"additional","affiliation":[{"name":"Biostatistics and Bioinformatics Laboratory, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Accogli","sequence":"additional","affiliation":[{"name":"Biostatistics and Bioinformatics Laboratory, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rossana","family":"Daprile","sequence":"additional","affiliation":[{"name":"Pathology Department, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco Alfredo","family":"Zito","sequence":"additional","affiliation":[{"name":"Pathology Department, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria Colomba","family":"Comes","sequence":"additional","affiliation":[{"name":"Biostatistics and Bioinformatics Laboratory, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raffaella","family":"Massafra","sequence":"additional","affiliation":[{"name":"Biostatistics and Bioinformatics Laboratory, IRCCS Istituto Tumori \u201cGiovanni Paolo II\u201d","place":["Bari, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/s41408-018-0054-y","article-title":"The 2016 WHO classification and diagnostic criteria for myeloproliferative neoplasms: document summary and in-depth discussion","volume":"8","author":"Barbui","year":"2018","journal-title":"Blood Cancer J"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2014-05-578435","article-title":"Clinical effect of driver mutations of JAK2, CALR, or MPL in primary myelofibrosis","volume":"124","author":"Rumi","year":"2014","journal-title":"Blood"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1038\/s41375-024-02425-1","article-title":"Characterization of myeloproliferative neoplasms based on genetics only and prognostication of transformation to blast phase","volume":"38","author":"Walter","year":"2024","journal-title":"Leukemia"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2016-03-643544","article-title":"The 2016 revision to the World Health Organization classification of myeloid neoplasms and acute leukemia","volume":"127","author":"Arber","year":"2016","journal-title":"Blood"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1038\/s41375-022-01613-1","article-title":"The 5th edition of the world health organization classification of haematolymphoid tumours: myeloid and histiocytic\/dendritic neoplasms","volume":"36","author":"Khoury","year":"2022","journal-title":"Leukemia"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1182\/blood.2022015850","article-title":"International Consensus Classification of Myeloid Neoplasms and Acute Leukemias: integrating morphologic, clinical, and genomic data","volume":"140","author":"Arber","year":"2022","journal-title":"Blood"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1002\/ajh.24657","article-title":"Impact of the 2016 revised WHO criteria for myeloproliferative neoplasms, unclassifiable: Comparison with the 2008 version","volume":"92","author":"Iurlo","year":"2017","journal-title":"Am J Hematol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2015-07-661983","article-title":"Presence of atypical thrombopoietin receptor (MPL) mutations in triple-negative essential thrombocythemia patients","volume":"127","author":"Cabagnols","year":"2016","journal-title":"Blood"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1182\/bloodadvances.2020002230","article-title":"Artificial intelligence\u2013based morphological fingerprinting of megakaryocytes: a new tool for assessing disease in MPN patients","volume":"4","author":"Sirinukunwattana","year":"2020","journal-title":"Blood Adv"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e48307","DOI":"10.7759\/cureus.48307","article-title":"Artificial intelligence applications for biomedical cancer research: A review","volume":"15","author":"Weerarathna","year":"2023","journal-title":"Cureus"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3390\/cancers16091687","article-title":"Development of an artificial-intelligence-based tool for automated assessment of cellularity in bone marrow biopsies in ph-negative myeloproliferative neoplasms","volume":"16","author":"D\u2019Abbronzo","year":"2024","journal-title":"Cancers (Basel)"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1177\/0300985813503570","article-title":"Whole-slide imaging and automated image analysis","volume":"51","author":"Webster","year":"2014","journal-title":"Vet Pathol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13061123","article-title":"Applications of artificial intelligence in philadelphia-negative myeloproliferative neoplasms","volume":"13","author":"Elsayed","year":"2023","journal-title":"Diagnostics"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2023-173877","article-title":"Interpretable artificial intelligence (AI) differentiates prefibrotic primary myelofibrosis (prePMF) from essential thrombocythemia (ET): A multi-center study of a new clinical decision support tool","volume":"142","author":"Srisuwananukorn","year":"2023","journal-title":"Blood"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3324\/haematol.2024.286123","article-title":"Artificial intelligence-based quantitative bone marrow pathology analysis for myeloproliferative neoplasms","volume":"110","author":"Yu","year":"2025","journal-title":"Haematologica"},{"key":"B16","article-title":"European consensus on grading bone marrow fibrosis and assessment of cellularity","volume":"90","author":"Thiele","year":"2005","journal-title":"Haematologica"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2020.00480","article-title":"MarrowQuant across aging and aplasia: A digital pathology workflow for quantification of bone marrow compartments in histological sections","volume":"11","author":"Tratwal","year":"2020","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B18","doi-asserted-by":"publisher","first-page":"16878","DOI":"10.1038\/s41598-017-17204-5","article-title":"QuPath: Open source software for digital pathology image analysis","volume":"7","author":"Bankhead","year":"2017","journal-title":"Sci Rep"},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.1002\/9781119398929","volume-title":"Bone Marrow Pathology","author":"Bain","year":"2019"},{"key":"B20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/9780470479216.corpsy0491","article-title":"Kruskal-wallis test","volume-title":"The Corsini Encyclopedia of Psychology","author":"McKight","year":"2010"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009715923555","article-title":"A tutorial on support vector machines for pattern recognition","volume":"2","author":"Burges","year":"1998","journal-title":"Data Min Knowl Discov"},{"key":"B22","doi-asserted-by":"crossref","DOI":"10.1109\/IJCNN.2008.4633979","article-title":"Multi-class AUC metrics and weighted alternatives","author":"Van Calster","year":"2008"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1002\/ajh.24320","article-title":"Refining prognostication of thrombosis inET","volume":"91","author":"Barbui","year":"2016","journal-title":"Am J Hematol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1038\/s41375-018-0077-1","article-title":"Philadelphia chromosome-negative classical myeloproliferative neoplasms: revised management recommendations from European LeukemiaNet","volume":"32","author":"Barbui","year":"2018","journal-title":"Leukemia"},{"key":"B25","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1159\/000101706","article-title":"Classification of ph-negative chronic myeloproliferative disorders \u2013 morphology as the yardstick of classification","volume":"74","author":"Kvasnicka","year":"2007","journal-title":"Pathobiology"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1038\/modpathol.2017.2","article-title":"Erratum: The myeloproliferative neoplasms, unclassifiable: clinical and pathological considerations","volume":"30","author":"Gianelli","year":"2017","journal-title":"Modern Pathol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1093\/ajcp\/aqae033","article-title":"Predictors of clinical outcome in myeloproliferative neoplasm, unclassifiable: A Bone Marrow Pathology Group study","volume":"162","author":"Crane","year":"2024","journal-title":"Am J Clin Pathol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1111\/bjh.17375","article-title":"Clinicopathological characterisation of myeloproliferative neoplasm-unclassifiable (MPN-U): a retrospective analysis from a large UK tertiary referral centre","volume":"193","author":"Deschamps","year":"2021","journal-title":"Br J Haematol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1741610\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T05:40:32Z","timestamp":1769406032000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1741610\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,26]]},"references-count":28,"alternative-id":["10.3389\/fonc.2025.1741610"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1741610","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,26]]},"article-number":"1741610"}}