{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T07:49:39Z","timestamp":1793346579229,"version":"4.5.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Cancer"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Acute promyelocytic leukemia (APL), a high-risk subtype of acute myeloid leukemia, necessitates rapid diagnosis upon hospital admission to mitigate early mortality. Current diagnosing approaches relying on time-consuming genetic testing or morphological expertise are particularly challenging in resource-limited settings. Herein, this study introduces a novel machine learning approach leveraging routine lab data to enable immediate APL suspicion, offering a new diagnostic possibility for under-resourced hospitals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We developed a two-stage machine learning model using multi-center retrospective data. The cohort included 94 confirmed APL patients (2020\u20132024) from three tertiary hospitals, with an external validation set (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009541) from an independent center. Using four VGG-16 networks, we extracted APL-specific 3D scatterplot features from DIFF and WNB channels of routine blood tests. These features were then fed into an optimized random forest classifier-scatterplot (RFC-S) model, refined via recursive feature elimination and threshold tuning.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The RFC-S model achieved near-perfect discrimination, with an AUC of 0.9893 in the test set and 0.9979 in external validation. It maintained 98.15% sensitivity and 95.52% specificity\u2014outperforming conventional methods. SHAP analysis confirmed that key scattergram-derived features (e.g.,\n                      <jats:italic>N_APL_Ratio_YZ<\/jats:italic>\n                      ) drove predictions. Critically, the model requires no additional tests, making it deployable even in low-resource clinics.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The RFC-S model represents an innovative approach to APL screening by combining deep learning-derived scattergram features with routine blood parameters. This two-stage methodology achieves high diagnostic accuracy (AUC\u2009&gt;\u20090.98) while maintaining computational efficiency. Importantly, the model\u2019s ability to utilize existing laboratory data without requiring additional tests makes it particularly valuable for resource-constrained settings where access to genetic testing or hematological expertise may be limited. Our findings suggest this approach could serve as a practical tool for early APL identification, potentially reducing diagnostic delays in diverse clinical environments.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12885-025-15034-7","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T07:30:22Z","timestamp":1762500622000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Development of a screening model for APL using cell population data and deep learning-extracted WBC scattergram features"],"prefix":"10.1186","volume":"25","author":[{"given":"Qi","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbo","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingxian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimin","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donglan","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huihui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yushuai","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,7]]},"reference":[{"key":"15034_CR1","doi-asserted-by":"publisher","first-page":"1136","DOI":"10.1056\/NEJMra1406184","volume":"373","author":"H D\u00f6hner","year":"2015","unstructured":"D\u00f6hner H, Weisdorf DJ, Bloomfield CD. Acute myeloid leukemia. N Engl J Med. 2015;373:1136\u201352.","journal-title":"N Engl J Med"},{"key":"15034_CR2","doi-asserted-by":"crossref","unstructured":"Li W. The 5(th) Edition of the World Health Organization Classification of Hematolymphoid Tumors. In: Li W. Leukemia. Brisbane (AU): Exon Publications Copyright: The Authors.; The authors confirm that the materials included in this chapter do not violate copyright laws. Where relevant, appropriate permissions have been obtained from the original copyright holder(s) and all original sources have been appropriately acknowledged or referenced. 2022.","DOI":"10.36255\/exon-publications-leukemia-who-5th-edition-hematolymphoid-tumors"},{"key":"15034_CR3","doi-asserted-by":"publisher","first-page":"1431","DOI":"10.3324\/haematol.10874","volume":"92","author":"RH J\u00e1como","year":"2007","unstructured":"J\u00e1como RH, Melo RA, Souto FR, de Mattos ER, de Oliveira CT, Fagundes EM, et al. Clinical features and outcomes of 134 Brazilians with acute promyelocytic leukemia who received ATRA and anthracyclines. Haematologica. 2007;92:1431\u20132.","journal-title":"Haematologica"},{"key":"15034_CR4","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1182\/blood-2015-04-637678","volume":"127","author":"J Liu","year":"2016","unstructured":"Liu J, Zhu HH, Jiang H, Jiang Q, Huang XJ. Varying responses of PML-RARA with different genetic mutations to arsenic trioxide. Blood. 2016;127:243\u201350.","journal-title":"Blood"},{"key":"15034_CR5","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1056\/NEJMoa1300874","volume":"369","author":"F Lo-Coco","year":"2013","unstructured":"Lo-Coco F, Avvisati G, Vignetti M, Thiede C, Orlando SM, Iacobelli S, et al. Retinoic acid and arsenic trioxide for acute promyelocytic leukemia. N Engl J Med. 2013;369:111\u201321.","journal-title":"N Engl J Med"},{"key":"15034_CR6","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1515\/bchm3.1990.371.1.465","volume":"371","author":"C Franck","year":"1990","unstructured":"Franck C, Byrjalsen I. Fractionation of elastase-type enzyme activity in biological fluids using a centrifugal analyser. Biol Chem Hoppe-Seyler. 1990;371:465\u20139.","journal-title":"Biol Chem Hoppe-Seyler"},{"key":"15034_CR7","doi-asserted-by":"publisher","first-page":"1128","DOI":"10.1038\/leu.2011.78","volume":"25","author":"S Lehmann","year":"2011","unstructured":"Lehmann S, Ravn A, Carlsson L, Antunovic P, Deneberg S, M\u00f6llg\u00e5rd L, et al. Continuing high early death rate in acute promyelocytic leukemia: a population-based report from the Swedish adult acute leukemia registry. Leukemia. 2011;25:1128\u201334.","journal-title":"Leukemia"},{"key":"15034_CR8","doi-asserted-by":"publisher","first-page":"1528","DOI":"10.3324\/haematol.2021.280093","volume":"107","author":"A \u00d6sterroos","year":"2022","unstructured":"\u00d6sterroos A, Maia T, Eriksson A, J\u00e4dersten M, Lazarevic V, Wennstr\u00f6m L, et al. A risk score based on real-world data to predict early death in acute promyelocytic leukemia. Haematologica. 2022;107:1528\u201337.","journal-title":"Haematologica"},{"key":"15034_CR9","doi-asserted-by":"crossref","unstructured":"Tajvidi Asr R, Rahimi M, Hossein Pourasad M, Zayer S, Momenzadeh M, Ghaderzadeh M. Hematology and hematopathology insights powered by machine learning: shaping the future of blood disorder management. Iran J Blood Cancer. 2024;16(4):9-19.","DOI":"10.61186\/ijbc.16.4.9"},{"key":"15034_CR10","doi-asserted-by":"crossref","unstructured":"Ghaderzadeh M, Shalchian A, Irajian G, Sadeghsalehi H, Sabet B. Artificial intelligence in drug discovery and development against antimicrobial resistance: A narrative review. Iran J Med Microbiol. 2024;18(3):135-47.","DOI":"10.30699\/ijmm.18.3.135"},{"key":"15034_CR11","doi-asserted-by":"publisher","first-page":"5113","DOI":"10.1002\/int.22753","volume":"37","author":"M Ghaderzadeh","year":"2022","unstructured":"Ghaderzadeh M, Aria M, Hosseini A, Asadi F, Bashash D, Abolghasemi H. A fast and efficient CNN model for B-ALL diagnosis and its subtypes classification using peripheral blood smear images. Int J Intell Syst. 2022;37:5113\u201333.","journal-title":"Int J Intell Syst"},{"key":"15034_CR12","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1182\/blood-2011-04-346437","volume":"118","author":"JH Park","year":"2011","unstructured":"Park JH, Qiao B, Panageas KS, Schymura MJ, Jurcic JG, Rosenblat TL, et al. Early death rate in acute promyelocytic leukemia remains high despite all-trans retinoic acid. Blood. 2011;118:1248\u201354.","journal-title":"Blood"},{"key":"15034_CR13","doi-asserted-by":"publisher","first-page":"e323","DOI":"10.1016\/S2589-7500(24)00044-X","volume":"6","author":"V Alcazer","year":"2024","unstructured":"Alcazer V, Le Meur G, Roccon M, Barriere S, Le Calvez B, Badaoui B, et al. 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. Lancet Digit Health. 2024;6:e323\u201333.","journal-title":"Lancet Digit Health"},{"key":"15034_CR14","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.tranon.2019.09.009","volume":"13","author":"RZ Haider","year":"2020","unstructured":"Haider RZ, Ujjan IU, Shamsi TS. Cell population data-driven acute promyelocytic leukemia flagging through artificial neural network predictive modeling. Transl Oncol. 2020;13:11\u20136.","journal-title":"Transl Oncol"},{"key":"15034_CR15","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12010138","author":"RZ Haider","year":"2022","unstructured":"Haider RZ, Ujjan IU, Khan NA, Urrechaga E, Shamsi TS. Beyond the in-practice CBC: the research CBC parameters-driven machine learning predictive modeling for early differentiation among leukemias. Diagnostics (Basel). 2022. https:\/\/doi.org\/10.3390\/diagnostics12010138.","journal-title":"Diagnostics (Basel)"},{"key":"15034_CR16","doi-asserted-by":"publisher","first-page":"2986","DOI":"10.1002\/cncr.34890","volume":"129","author":"H Liao","year":"2023","unstructured":"Liao H, Xu Y, Meng Q, Mao Z, Qiao Y, Liu Y, et al. A convolutional neural network-based, quantitative complete blood count scattergram-mapping framework promptly screens acute promyelocytic leukemia with high sensitivity. Cancer. 2023;129:2986\u201398.","journal-title":"Cancer"},{"key":"15034_CR17","doi-asserted-by":"publisher","first-page":"2391","DOI":"10.1182\/blood-2016-03-643544","volume":"127","author":"DA Arber","year":"2016","unstructured":"Arber DA, Orazi A, Hasserjian R, Thiele J, Borowitz MJ, Le Beau MM, et al. The 2016 revision to the World Health Organization classification of myeloid neoplasms and acute leukemia. Blood. 2016;127:2391\u2013405.","journal-title":"Blood"},{"key":"15034_CR18","doi-asserted-by":"publisher","first-page":"1466","DOI":"10.3324\/haematol.2022.280406","volume":"107","author":"E Cheli","year":"2022","unstructured":"Cheli E, Chevalier S, Kosmider O, Eveillard M, Chapuis N, Plesa A, et al. Diagnosis of acute promyelocytic leukemia based on routine biological parameters using machine learning. Haematologica. 2022;107:1466\u20139.","journal-title":"Haematologica"},{"key":"15034_CR19","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1186\/s12885-022-10059-8","volume":"22","author":"J Zhu","year":"2022","unstructured":"Zhu J, Lemaire P, Mathis S, Ronez E, Clauser S, Jondeau K, et al. Machine learning-based improvement of MDS-CBC score brings platelets into the limelight to optimize smear review in the hematology laboratory. BMC Cancer. 2022;22:972.","journal-title":"BMC Cancer"},{"key":"15034_CR20","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1111\/ijlh.13777","volume":"44","author":"SM Hwang","year":"2022","unstructured":"Hwang SM, Nam Y. Complete blood count and cell population data parameters from the Abbott Alinity HQ analyzer are useful in differentiating myelodysplastic syndromes from other forms of cytopenia. Int J Lab Hematol. 2022;44:468\u201376.","journal-title":"Int J Lab Hematol"},{"key":"15034_CR21","doi-asserted-by":"publisher","first-page":"1808","DOI":"10.1515\/cclm-2019-0380","volume":"57","author":"PJ Vinholt","year":"2019","unstructured":"Vinholt PJ. The role of platelets in bleeding in patients with thrombocytopenia and hematological disease. Clin Chem Lab Med. 2019;57:1808\u201317.","journal-title":"Clin Chem Lab Med"},{"key":"15034_CR22","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1002\/ajh.23643","volume":"89","author":"PW Raess","year":"2014","unstructured":"Raess PW, van de Geijn GJ, Njo TL, Klop B, Sukhachev D, Wertheim G, et al. Automated screening for myelodysplastic syndromes through analysis of complete blood count and cell population data parameters. Am J Hematol. 2014;89:369\u201374.","journal-title":"Am J Hematol"},{"key":"15034_CR23","doi-asserted-by":"publisher","first-page":"1935","DOI":"10.1182\/blood-2012-08-449918","volume":"121","author":"EM Rego","year":"2013","unstructured":"Rego EM, Kim HT, Ruiz-Arg\u00fcelles GJ, Undurraga MS, Uriarte Mdel R, Jacomo RH, et al. Improving acute promyelocytic leukemia (APL) outcome in developing countries through networking, results of the international consortium on APL. Blood. 2013;121:1935\u201343.","journal-title":"Blood"}],"container-title":["BMC Cancer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12885-025-15034-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12885-025-15034-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12885-025-15034-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T07:30:23Z","timestamp":1762500623000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmccancer.biomedcentral.com\/articles\/10.1186\/s12885-025-15034-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,7]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["15034"],"URL":"https:\/\/doi.org\/10.1186\/s12885-025-15034-7","relation":{},"ISSN":["1471-2407"],"issn-type":[{"value":"1471-2407","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,7]]},"assertion":[{"value":"15 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by the institutional review board of Shanghai Jiaotong University School of Medicine Ruijin Hospital (ethics approval number 2021 (72)). Informed consent was waived because the research utilized only de-identified residual samples obtained during routine clinical testing, and the study posed no additional risk to patients.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not available.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1725"}}