{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T06:05:30Z","timestamp":1790661930301,"version":"4.1.0"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"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>Acute leukemias require rapid subtype identification to guide timely treatment. Differentiation of acute lymphoblastic leukemia (ALL), acute monocytic leukemia (AMoL\/M5), and acute promyelocytic leukemia (APL\/M3) often relies on specialized tests that may not be immediately available. This study evaluated differentiation only among patients already confirmed to have one of these three diagnoses, rather than screening an unselected population with suspected acute leukemia.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This multicenter retrospective study included 9,398 newly diagnosed, previously untreated patients with established APL\/M3, AMoL\/M5, or ALL between May 2019 and May 2025 at four tertiary hospitals in China. Relapse, remission, follow-up, and non-initial disease episodes were excluded. Twenty-four routine hematological parameters were evaluated. One center served as the development cohort with five-fold stratified cross-validation, while three independent centers were reserved for external validation. Ten machine-learning algorithms were compared. Performance was assessed using AUC, sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and F1 score. SHapley Additive exPlanations (SHAP) supported feature selection and interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>An 18-feature random forest model achieved a development-stage cross-validated AUC of 0.93 and external AUCs of 0.89, 0.87, and 0.90. Overall sensitivity, specificity, PPV, NPV, accuracy, and F1 score were 0.78, 0.90, 0.81, 0.91, 0.81, and 0.79, respectively. SHAP identified leukocyte, erythrocyte, and platelet indices as the most important features. A Streamlit application was developed for clinical evaluation. Using a development-derived APL alert threshold of 0.0966, APL sensitivity was 99.02% in development and 96.32%\u201397.94% across external cohorts, with PPVs of 54.34% and 35.58%\u201384.25%, respectively. External validation showed center-specific calibration shifts, indicating that predicted probabilities should not be interpreted as universally calibrated absolute diagnostic probabilities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Among patients already confirmed to have APL\/M3, AMoL\/M5, or ALL, this explainable model enabled low-cost preliminary differentiation using routine hematological data. It may support subtype prioritization and confirmatory testing but cannot replace standard diagnostics, identify other diagnoses, or screen unselected patients. Prospective multinational and workflow-based validation is required before routine implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1939329","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T05:51:09Z","timestamp":1790661069000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multicenter validation of an explainable machine-learning model for APL, AMoL, and ALL"],"prefix":"10.3389","volume":"16","author":[{"given":"Xuanxuan","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Clinical Laboratory, The First Affiliated Hospital of Anhui Medical University","place":["Hefei, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixiang","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, The Affiliated Guangdong Second Provincial General Hospital of Jinan University","place":["Guangzhou, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, The First Affiliated Hospital of Anhui Medical University","place":["Hefei, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Tongling People\u2019s Hospital","place":["Tongling, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Wanbei Coal Electric Group General Hospital","place":["Suzhou, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, The First Affiliated Hospital of Anhui Medical University","place":["Hefei, Anhui, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1002\/ajh.27625","article-title":"Acute myeloid leukemia: 2025 update on diagnosis, risk-stratification, and management","volume":"100","author":"Shimony","year":"2025","journal-title":"Am J Hematol"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.hoc.2017.08.006","article-title":"Acute leukemia","volume":"31","author":"Rose-Inman","year":"2017","journal-title":"Hematol Oncol Clin North Am"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(18)31694-5","article-title":"Forecasting life expectancy, years of life lost, and all-cause and cause-specific mortality for 250 causes of death: reference and alternative scenarios for 2016-40 for 195 countries and territories","volume":"392","author":"Foreman","year":"2018","journal-title":"Lancet"},{"key":"B4","volume-title":"SEER Cancer Stat Facts: Acute Lymphocytic Leukemia","year":"2024"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1155\/2012\/129707","article-title":"The experience in nicaragua: childhood leukemia in low income countries-the main cause of late diagnosis may be \"medical delay","volume":"2012","author":"De Angelis","year":"2012","journal-title":"Int J Pediatr"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.pathol.2021.02.001","article-title":"Diagnosis of rare subtypes of acute myeloid leukaemia and related neoplasms","volume":"53","author":"George","year":"2021","journal-title":"Pathology"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s10552-007-9097-2","article-title":"Patterns of leukemia incidence in the United States by subtype and demographic characteristics, 1997-2002","volume":"19","author":"Yamamoto","year":"2008","journal-title":"Cancer Causes Control"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1097\/moh.0000000000000221","article-title":"What's new in the pathogenesis of the coagulopathy in acute promyelocytic leukemia","volume":"23","author":"Mantha","year":"2016","journal-title":"Curr Opin Hematol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2016-09-736686","article-title":"Long-term outcome of acute promyelocytic leukemia treated with all-trans-retinoic acid, arsenic trioxide, and gemtuzumab","volume":"129","author":"Abaza","year":"2017","journal-title":"Blood"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3324\/haematol.2021.280093","article-title":"A risk score based on real-world data to predict early death in acute promyelocytic leukemia","volume":"107","author":"\u00d6sterroos","year":"2022","journal-title":"Haematologica"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1307315","article-title":"Risk stratification for early mortality in newly diagnosed acute promyelocytic leukemia: a multicenter, non-selected, retrospective cohort study","volume":"14","author":"Kim","year":"2024","journal-title":"Front Oncol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1188\/10.cjon.747-759","article-title":"Acute promyelocytic leukemia: an overview with implications for oncology nurses","volume":"14","author":"Walker","year":"2010","journal-title":"Clin J Oncol Nurs"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2017-12-778472","article-title":"Treatment strategies for adolescent and young adult patients with acute myeloid leukemia","volume":"132","author":"O'Dwyer","year":"2018","journal-title":"Blood"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2014-10-551507","article-title":"How I treat hyperleukocytosis in acute myeloid leukemia","volume":"125","author":"R\u00f6llig","year":"2015","journal-title":"Blood"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0085554","article-title":"Survival of adults with acute lymphoblastic leukemia in Germany and the United States","volume":"9","author":"Pulte","year":"2014","journal-title":"PloS One"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/s1470-2045(10)70114-5","article-title":"Glucocorticoid use in acute lymphoblastic leukaemia","volume":"11","author":"Inaba","year":"2010","journal-title":"Lancet Oncol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2016-08-733196","article-title":"Diagnosis and management of AML in adults: 2017 ELN recommendations from an international expert panel","volume":"129","author":"D\u00f6hner","year":"2017","journal-title":"Blood"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3324\/haematol.2022.280406","article-title":"Diagnosis of acute promyelocytic leukemia based on routine biological parameters using machine learning","volume":"107","author":"Cheli","year":"2022","journal-title":"Haematologica"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2016-09-741355","article-title":"Comprehensive analysis of a myeloperoxidase-negative acute promyelocytic leukemia","volume":"129","author":"Heiblig","year":"2017","journal-title":"Blood"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/s2589-7500(24)00044-x","article-title":"Evaluation of a machine-learning model based on laboratory parameters for the prediction of acute leukaemia subtypes: a multicentre model development and validation study in France","volume":"6","author":"Alcazer","year":"2024","journal-title":"Lancet Digit Health"},{"key":"B21","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":"B22","doi-asserted-by":"publisher","DOI":"10.1111\/jebm.70005","article-title":"Towards diagnostic intelligent systems in leukemia detection and classification: a systematic review and meta-analysis","volume":"18","author":"Aria","year":"2025","journal-title":"J Evid Based Med"},{"key":"B23","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.cell.2020.03.022","article-title":"How machine learning will transform biomedicine","volume":"181","author":"Goecks","year":"2020","journal-title":"Cell"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2022.101431","article-title":"A novel machine learning model and a public online prediction platform for prediction of post-ERCP-cholecystitis (PEC)","volume":"48","author":"Zhang","year":"2022","journal-title":"EClinicalMedicine"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2023.102409","article-title":"Identification and validation of an explainable prediction model of acute kidney injury with prognostic implications in critically ill children: a prospective multicenter cohort study","volume":"68","author":"Hu","year":"2024","journal-title":"EClinicalMedicine"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1939329\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T05:51:16Z","timestamp":1790661076000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1939329\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":25,"alternative-id":["10.3389\/fonc.2026.1939329"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1939329","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]},"article-number":"1939329"}}