{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T00:08:08Z","timestamp":1775434088455,"version":"3.50.1"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"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. Med."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Radiographically confirmed pneumonia within 90\u202fdays of chemotherapy initiation is a frequent and clinically important complication in patients with non-Hodgkin lymphoma, yet interpretable tools for early individualized risk estimation are limited.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objective<\/jats:title><jats:p>To develop and internally validate an interpretable machine-learning model that predicts the 90-day risk of radiographically confirmed pneumonia after chemotherapy initiation in non-Hodgkin lymphoma.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We retrospectively analyzed 205 chemotherapy-treated NHL patients. A two-step feature selection (LASSO followed by random-forest\u2013based recursive feature elimination) identified four predictors: high-grade malignancy, drinking (alcohol use), estimated glomerular filtration rate (eGFR), and smoking. Five algorithms were trained and compared under a stratified 70\/30 split (training <jats:italic>n<\/jats:italic>\u202f=\u202f145; internal hold-out test set <jats:italic>n<\/jats:italic>\u202f=\u202f60) with leakage-safe preprocessing (within-fold kNN imputation, SMOTE, and scaling). The gradient boosting machine (GBM) performed best and was interpreted using SHAP. A web-based prototype was implemented for research use only.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>On the internal hold-out test set (<jats:italic>n<\/jats:italic>\u202f=\u202f60), the GBM achieved an AUC of 0.855 (95% CI 0.746\u20130.964), an F1 score of 0.679, and a Brier score of 0.155. SHAP identified reduced eGFR, smoking, drinking, and high-grade malignancy as influential contributors; case-level waterfall and force plots enhanced transparency. These estimates reflect internal validation only and were obtained without systematic microbiological confirmation or standardized radiologic rescoring. Accordingly, performance may be optimistic, and real-world use is not advised pending temporal and multicenter external validation (with potential recalibration) and prospective evaluation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The interpretable GBM model demonstrated promising discrimination and calibration on an internal hold-out test set; however, clinical deployment requires temporal and multicenter external validation (as well as prospective assessment with potential recalibration). The accompanying web calculator is a research-only prototype and is not intended for clinical decision-making until such validation is completed.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1674896","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T05:29:44Z","timestamp":1758518984000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Interpretable machine learning model to predict 90-day radiographically confirmed pneumonia after chemotherapy initiation in non-Hodgkin lymphoma: development and internal validation of a single-center cohort"],"prefix":"10.3389","volume":"12","author":[{"given":"Zhanna","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manqi","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panruo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingling","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangmin","family":"Tong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gongqiang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global Cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA A Cancer J Clinicians"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3322\/caac.21166","article-title":"Cancer statistics, 2013","volume":"63","author":"Siegel","year":"2013","journal-title":"CA A Cancer J Clinicians"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1056\/NEJMoa011795","article-title":"CHOP chemotherapy plus rituximab compared with CHOP alone in elderly patients with diffuse large-B-cell lymphoma","volume":"346","author":"Coiffier","year":"2002","journal-title":"N Engl J Med"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"860526","DOI":"10.3389\/fcimb.2022.860526","article-title":"Increased cytokine levels assist in the diagnosis of respiratory bacterial infections or concurrent Bacteremia in patients with non-Hodgkin\u2019s lymphoma","volume":"12","author":"Zhang","year":"2022","journal-title":"Front Cell Infect Microbiol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"S318","DOI":"10.1093\/mmy\/myy138","article-title":"A clinical approach to respiratory disease in patients with hematological malignancy, with a focus on respiratory infection","volume":"57","author":"Periselneris","year":"2019","journal-title":"Med Mycol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"2373","DOI":"10.1007\/s00277-018-3448-9","article-title":"Characteristics of pulmonary complications in non-Hodgkin\u2019s lymphoma patients treated with rituximab-containing chemotherapy and impact on survival","volume":"97","author":"Keefer","year":"2018","journal-title":"Ann Hematol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1038\/s41375-019-0388-x","article-title":"Infections associated with immunotherapeutic and molecular targeted agents in hematology and oncology. A position paper by the European conference on infections in Leukemia (ECIL)","volume":"33","author":"Maschmeyer","year":"2019","journal-title":"Leukemia"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.880144","article-title":"Meta-analysis of risk factors and incidence of interstitial pneumonia with CHOP-like regimens for non-Hodgkin lymphoma","volume":"12","author":"Yang","year":"2022","journal-title":"Front Oncol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"v111","DOI":"10.1093\/annonc\/mdw325","article-title":"Management of febrile neutropaenia: ESMO clinical practice guidelines","volume":"27","author":"Klastersky","year":"2016","journal-title":"Ann Oncol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"3038","DOI":"10.1200\/JCO.2000.18.16.3038","article-title":"The multinational association for supportive care in cancer risk index: a multinational scoring system for identifying low-risk febrile neutropenic cancer patients","volume":"18","author":"Klastersky","year":"2000","journal-title":"J Clin Oncol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1200\/JCO.1992.10.2.316","article-title":"Risk assessment in cancer patients with fever and neutropenia: a prospective, two-center validation of a prediction rule","volume":"10","author":"Talcott","year":"1992","journal-title":"J Clin Oncol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1200\/JCO.2014.57.2347","article-title":"Prediction of serious complications in patients with seemingly stable febrile neutropenia: validation of the clinical index of stable febrile neutropenia in a prospective cohort of patients from the FINITE study","volume":"33","author":"Carmona-Bayonas","year":"2015","journal-title":"J Clin Oncol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"9048","DOI":"10.1038\/s41598-021-88207-6","article-title":"Usefulness analysis of the 2018 ASCO\/IDSA guideline for outpatient management of fever and neutropenia in adults treated for malignancy","volume":"11","author":"Hwang","year":"2021","journal-title":"Sci Rep"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1016\/j.jinf.2019.04.002","article-title":"Development and internal validation of a model for predicting 60-day risk of invasive mould disease in patients with haematological malignancies","volume":"78","author":"Stanzani","year":"2019","journal-title":"J Infect"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"e75531","DOI":"10.1371\/journal.pone.0075531","article-title":"A risk prediction score for invasive Mold disease in patients with Hematological malignancies","volume":"8","author":"Stanzani","year":"2013","journal-title":"PLoS One"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1186\/s13027-021-00413-z","article-title":"Infectious diseases as a cause of death among cancer patients: a trend analysis and population-based study of outcome in the United States based on the surveillance, epidemiology, and end results database","volume":"16","author":"Elhadi","year":"2021","journal-title":"Infect Agents Cancer"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"150618124156002","DOI":"10.1513\/AnnalsATS.201501-046OC","article-title":"Sepsis-associated outcomes in critically ill patients with malignancies","volume":"12","author":"Torres","year":"2015","journal-title":"Ann Am Thorac Soc"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1443","DOI":"10.1200\/JCO.2017.77.6211","article-title":"Outpatient management of fever and neutropenia in adults treated for malignancy: American Society of Clinical Oncology and Infectious Diseases Society of America clinical practice guideline update","volume":"36","author":"Taplitz","year":"2018","journal-title":"J Clin Oncol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"13015","DOI":"10.1038\/s41598-025-97685-x","article-title":"An integrated approach of feature selection and machine learning for early detection of breast cancer","volume":"15","author":"Zhu","year":"2025","journal-title":"Sci Rep"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e32662","DOI":"10.2196\/32662","article-title":"Machine learning\u2013based hospital discharge prediction for patients with cardiovascular diseases: development and usability study","volume":"9","author":"Ahn","year":"2021","journal-title":"JMIR Med Inform"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-025-00825-9","article-title":"A comparative study of imputation techniques for missing values in healthcare diagnostic datasets","author":"Joel","year":"2025","journal-title":"Int J Data Sci Anal"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"3786","DOI":"10.1093\/bioinformatics\/btz134","article-title":"Missing value estimation methods for DNA methylation data","volume":"35","author":"Di Lena","year":"2019","journal-title":"Bioinformatics"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1037\/0033-2909.112.1.155","article-title":"A power primer","volume":"112","author":"Cohen","year":"1992","journal-title":"Psychol Bull"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"3083","DOI":"10.1002\/sim.3697","article-title":"Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples","volume":"28","author":"Austin","year":"2009","journal-title":"Stat Med"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1214\/09-STS313","article-title":"Matching methods for causal inference: a review and a look forward","volume":"25","author":"Stuart","year":"2010","journal-title":"Stat Sci"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"597","DOI":"10.2147\/CIA.S406735","article-title":"Lasso-based machine learning algorithm for predicting postoperative lung complications in elderly: a single-center retrospective study from China","volume":"18","author":"Liu","year":"2023","journal-title":"Clin Interv Aging"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"e13907","DOI":"10.1111\/1440-1681.13907","article-title":"Establishment of diagnostic model and identification of diagnostic markers between liver cancer and cirrhosis based on multi-chip and machine learning","volume":"51","author":"Yang","year":"2024","journal-title":"Clin Exp Pharma Physio"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"104151","DOI":"10.1016\/j.compbiomed.2020.104151","article-title":"Machine learning model for predicting malaria using clinical information","volume":"129","author":"Lee","year":"2021","journal-title":"Comput Biol Med"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"2000","DOI":"10.3390\/healthcare11142000","article-title":"Application of SHAP for explainable machine learning on age-based subgrouping mammography questionnaire data for positive mammography prediction and risk factor identification","volume":"11","author":"Sun","year":"2023","journal-title":"Healthcare"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"106036","DOI":"10.1016\/j.ijmedinf.2025.106036","article-title":"Development and validation of a machine learning-based clinical prediction model for monitoring liver injury in patients with pan-cancer receiving immunotherapy","volume":"203","author":"Wang","year":"2025","journal-title":"Int J Med Inform"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"e0271185","DOI":"10.1371\/journal.pone.0271185","article-title":"moreThanANOVA: a user-friendly shiny\/R application for exploring and comparing data with interactive visualization","volume":"17","author":"Jiang","year":"2022","journal-title":"PLoS One"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"102617","DOI":"10.1016\/j.eclinm.2024.102617","article-title":"Development and validation of an early diagnosis model for bone metastasis in non-small cell lung cancer based on serological characteristics of the bone metastasis mechanism","volume":"72","author":"Teng","year":"2024","journal-title":"eClinicalMedicine"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"e45","DOI":"10.1164\/rccm.201908-1581ST","article-title":"Diagnosis and treatment of adults with community-acquired pneumonia. An official clinical practice guideline of the American Thoracic Society and Infectious Diseases Society of America","volume":"200","author":"Metlay","year":"2019","journal-title":"Am J Respir Crit Care Med"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1403392","DOI":"10.3389\/fonc.2024.1403392","article-title":"Construction of a risk prediction model for lung infection after chemotherapy in lung cancer patients based on the machine learning algorithm","volume":"14","author":"Sun","year":"2024","journal-title":"Front Oncol"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1063610","DOI":"10.3389\/fninf.2022.1063610","article-title":"Machine learning-based infection prediction model for newly diagnosed multiple myeloma patients","volume":"16","author":"Peng","year":"2023","journal-title":"Front Neuroinform"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1186\/s12885-020-07254-w","article-title":"Prophylactic antibiotic treatment with TMP-SMX decreased the incidence of interstitial pneumonia in patients with B-cell lymphoma on chemotherapy","volume":"20","author":"Li","year":"2020","journal-title":"BMC Cancer"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"2869","DOI":"10.1007\/s00277-025-06296-z","article-title":"Incidence and risk factors of severe infections in diffuse large B-cell lymphoma patients undergoing immunochemotherapy","volume":"104","author":"Zhao","year":"2025","journal-title":"Ann Hematol"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"4395","DOI":"10.1038\/s41598-017-04495-x","article-title":"Infection is an independent predictor of death in diffuse large B cell lymphoma","volume":"7","author":"Dendle","year":"2017","journal-title":"Sci Rep"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"955535","DOI":"10.3389\/fonc.2022.955535","article-title":"Post-chemotherapy pneumonia in Chinese patients with diffuse large B-cell lymphoma: outcomes and predictive model","volume":"12","author":"Zhao","year":"2022","journal-title":"Front Oncol"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"11931","DOI":"10.21037\/apm-21-3280","article-title":"Incidence and risk factors of pneumonia in diffuse large B-cell lymphoma patients receiving first line R-CHOP\/R-CHOP-like immunochemotherapy: a retrospective study of 287 patients in single center","volume":"10","author":"Wang","year":"2021","journal-title":"Ann Palliat Med"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"e022344","DOI":"10.1136\/bmjopen-2018-022344","article-title":"Alcohol and the risk of pneumonia: a systematic review and meta-analysis","volume":"8","author":"Simou","year":"2018","journal-title":"BMJ Open"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/s12288-016-0730-7","article-title":"Validation of MASCC score for risk stratification in patients of Hematological disorders with febrile neutropenia","volume":"33","author":"Taj","year":"2017","journal-title":"Indian J Hematol Blood Transfus"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1007\/s00520-025-09562-y","article-title":"Clinical prediction models for febrile neutropenia and its outcomes: a systematic review","volume":"33","author":"Sheehy","year":"2025","journal-title":"Support Care Cancer"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1186\/s40001-024-01940-2","article-title":"Personalized prediction of mortality in patients with acute ischemic stroke using explainable artificial intelligence","volume":"29","author":"Xu","year":"2024","journal-title":"Eur J Med Res"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1674896\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T05:29:45Z","timestamp":1758518985000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1674896\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":44,"alternative-id":["10.3389\/fmed.2025.1674896"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1674896","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"article-number":"1674896"}}