{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T05:15:53Z","timestamp":1783228553196,"version":"3.54.6"},"reference-count":34,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000061","name":"National Institutes of Health (NIH) Fogarty International Center","doi-asserted-by":"publisher","award":["R21TW012211"],"award-info":[{"award-number":["R21TW012211"]}],"id":[{"id":"10.13039\/100000061","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000060","name":"NIH National Institute of Allergy and Infectious Diseases","doi-asserted-by":"crossref","award":["2R25AI140490"],"award-info":[{"award-number":["2R25AI140490"]}],"id":[{"id":"10.13039\/100000060","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pediatric Reports"],"abstract":"<jats:p>Background: Sepsis is a leading cause of pediatric mortality worldwide, disproportionately affecting children in low- and middle-income countries (LMICs). However, timely recognition of potential sepsis and access to healthcare resources needed to diagnose pediatric sepsis according to international guidelines are challenging in LMICs. This exploratory study aimed to develop machine learning (ML) models to detect pediatric sepsis and septic shock using a simplified set of clinical data contextualized for practical use in resource-limited settings. Methods: This was a secondary analysis of an observational study of 100 children with potential sepsis admitted to a non-profit referral hospital in Dhaka, Bangladesh. The outcomes were sepsis as defined by a Phoenix Sepsis Score (PSS) \u2265 2 and septic shock (sepsis plus PSS cardiovascular sub-score \u2265 1). Models were trained using either clinical + laboratory variables or clinical-only variables. A single 24 h worst-value assessment window was derived per patient; stratified 5-fold cross-validation was used to maintain class proportions across the training and test folds. Model performance was assessed using area under the precision\u2013recall curve (AUPRC) and area under the receiver operating characteristic curve (AUROC) with 95% confidence intervals (CIs) derived from a 2000-resample patient-level bootstrap of out-of-fold classifications. Logistic regression coefficients were used to assess feature contributions. Results: For sepsis classification, the non-laboratory model achieved an AUPRC of 0.942 (95% CI: 0.884\u20130.979) and an AUROC of 0.945 (95% CI: 0.890\u20130.983), with comparable performance from the clinical + laboratory model (AUPRC 0.941, 95% CI: 0.880\u20130.981; AUROC 0.945, 95% CI: 0.881\u20130.986). For septic shock, AUROCs of 0.870 (95% CI: 0.761\u20130.952) and 0.878 (95% CI: 0.758\u20130.967) were observed. However, these estimates should be interpreted cautiously, given the low prevalence (23%) and absence of external validation. SpO2:FiO2 ratio, GCS, and systolic blood pressure were consistently strong predictors across models. Conclusions: ML models using pragmatic clinical variables demonstrate preliminary diagnostic performance, with the non-laboratory model showing discrimination comparable to models incorporating laboratory data. Logistic regression demonstrated the most stable performance and may represent an early proof of concept for assistive diagnostic support. However, these models are not clinically usable without external validation. These findings are hypothesis-generating; external validation in larger, independent cohorts is essential before any clinical use, particularly for septic shock.<\/jats:p>","DOI":"10.3390\/pediatric18040088","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T11:39:11Z","timestamp":1783078751000},"page":"88","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Utilizing Machine Learning for Diagnostic Assistance of Pediatric Sepsis and Septic Shock in Resource-Limited Settings"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1098-8133","authenticated-orcid":false,"given":"Kaden","family":"Bunch","sequence":"first","affiliation":[{"name":"Warren Alpert Medical School of Brown University, Providence, RI 02903, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1732-4242","authenticated-orcid":false,"given":"Shamsun Nahar","family":"Shaima","sequence":"additional","affiliation":[{"name":"International Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b), Dhaka 1000, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0907-7875","authenticated-orcid":false,"given":"Gazi Md. Salahuddin","family":"Mamun","sequence":"additional","affiliation":[{"name":"International Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b), Dhaka 1000, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2235-4248","authenticated-orcid":false,"given":"Sai Gopal","family":"Jarabana","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Warren Alpert Medical School of Brown University, Providence, RI 02903, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2860-9104","authenticated-orcid":false,"given":"Monique","family":"Gainey","sequence":"additional","affiliation":[{"name":"Virginia Tech Carilion School of Medicine, Roanoke, VA 24016, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7375-5269","authenticated-orcid":false,"given":"Abu Sayem Mirza Md. Hasibur","family":"Rahman","sequence":"additional","affiliation":[{"name":"International Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b), Dhaka 1000, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alicia","family":"Genisca","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Warren Alpert Medical School of Brown University, Providence, RI 02903, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1832-3479","authenticated-orcid":false,"given":"Atin","family":"Jindal","sequence":"additional","affiliation":[{"name":"Division of Hospital Medicine, Brown University Health System, Providence, RI 02903, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6866-1193","authenticated-orcid":false,"given":"Nidhi","family":"Kadakia","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Yale School of Medicine, New Haven, CT 06510, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Monira","family":"Sarmin","sequence":"additional","affiliation":[{"name":"International Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b), Dhaka 1000, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farzana","family":"Afroze","sequence":"additional","affiliation":[{"name":"International Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b), Dhaka 1000, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam C.","family":"Levine","sequence":"additional","affiliation":[{"name":"Warren Alpert Medical School of Brown University, Providence, RI 02903, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9958-3071","authenticated-orcid":false,"given":"Mohammod Jobayer","family":"Chisti","sequence":"additional","affiliation":[{"name":"International Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b), Dhaka 1000, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephanie Chow","family":"Garbern","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Warren Alpert Medical School of Brown University, Providence, RI 02903, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.jiac.2023.11.016","article-title":"Predicting mortality in pediatric sepsis: A nationwide data analysis using a pediatric sepsis surveillance method","volume":"30","author":"Miura","year":"2024","journal-title":"J. Infect. Chemother."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"37","DOI":"10.14238\/pi63.1.2023.37-44","article-title":"The clinical and biomarker approach to predict sepsis mortality in pediatric patients","volume":"63","author":"Yuniar","year":"2023","journal-title":"Paediatr. Indones."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1001\/jamapediatrics.2018.4839","article-title":"Global Case-Fatality Rates in Pediatric Severe Sepsis and Septic Shock: A Systematic Review and Meta-analysis","volume":"173","author":"Tan","year":"2019","journal-title":"JAMA Pediatr."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Rusmawatiningtyas, D., Rahmawati, A., Makrufardi, F., Mardhiah, N., Murni, I.K., Uiterwaal, C.S.P.M., Savitri, A.I., and Kumara, I.F. (2021). Factors associated with mortality of pediatric sepsis patients at the pediatric intensive care unit in a low-resource setting. BMC Pediatr., 21.","DOI":"10.1186\/s12887-021-02945-0"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1097\/01.ccm.0000910364.77758.1a","article-title":"1157: Early Intervention in the Critical Care Resuscitation Unit and Mortality Among Patients with Sepsis","volume":"51","author":"Emamian","year":"2023","journal-title":"Crit. Care Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1001\/jama.2024.0179","article-title":"International Consensus Criteria for Pediatric Sepsis and Septic Shock","volume":"331","author":"Schlapbach","year":"2024","journal-title":"JAMA"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e9993","DOI":"10.7717\/peerj.9993","article-title":"Comparison of pediatric scoring systems for mortality in septic patients and the impact of missing information on their predictive power: A retrospective analysis","volume":"8","author":"Niederwanger","year":"2020","journal-title":"PeerJ"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1016\/j.pedneo.2021.09.006","article-title":"Accuracy of SIRS, age-adapted pSOFA, and quick SOFA scoring systems for predicting outcomes in paediatric patients with sepsis: A meta-analysis","volume":"63","author":"Sun","year":"2022","journal-title":"Pediatr. Neonatol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1001\/jama.2024.8202","article-title":"Development and Validation of the Phoenix Criteria for Pediatric Sepsis and Septic Shock","volume":"331","author":"Bennett","year":"2024","journal-title":"JAMA"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Chilinda, G.K., Gadama, L.A., and Stones, W. (2018). Point-of-care umbilical arterial lactate and newborn outcomes in a low resource setting: Cohort study. BMC Res. Notes, 11.","DOI":"10.1186\/s13104-018-3598-9"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1016\/j.hoc.2015.11.012","article-title":"Improving Laboratory and Clinical Hematology Services in Resource Limited Settings","volume":"30","author":"Allen","year":"2016","journal-title":"Hematol.\/Oncol. Clin. N. Am."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2175","DOI":"10.1001\/jama.2018.6413","article-title":"qSOFA Score for Patients With Sepsis in Low- and Middle-Income Countries","volume":"319","author":"Adhikari","year":"2018","journal-title":"JAMA"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.euroneuro.2024.08.005","article-title":"The challenges of using machine learning models in psychiatric research and clinical practice","volume":"88","author":"Ostojic","year":"2024","journal-title":"Eur. Neuropsychopharmacol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1177\/10547738231183207","article-title":"Predicting the Onset of Sepsis Using Vital Signs Data: A Machine Learning Approach","volume":"32","author":"Tran","year":"2023","journal-title":"Clin. Nurs. Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1007\/s00134-019-05872-y","article-title":"Machine learning for the prediction of sepsis: A systematic review and meta-analysis of diagnostic test accuracy","volume":"46","author":"Fleuren","year":"2020","journal-title":"Intensive Care Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1097\/01.PCC.0000149131.72248.E6","article-title":"International pediatric sepsis consensus conference: Definitions for sepsis and organ dysfunction in pediatrics","volume":"6","author":"Goldstein","year":"2005","journal-title":"Pediatr. Crit. Care Med."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Garbern, S.C., Mamun, G.M.S., Shaima, S.N., Hakim, N., Wegerich, S., Alla, S., Sarmin, M., Afroze, F., Sekaric, J., and Genisca, A. (2024). A novel digital health approach to improving global pediatric sepsis care in Bangladesh using wearable technology and machine learning. PLoS Digit. Health, 3.","DOI":"10.1371\/journal.pdig.0000634"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Shi, X., Wang, X., Yang, H., Fan, X., Liu, G., Song, Y., Peng, Q., Wang, Q., Sun, X., and Ma, W. (2025). Accurate prediction of sepsis from pediatric emergency department to PICU using a machine-learning model. Front. Pediatr., 13.","DOI":"10.3389\/fped.2025.1610187"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1093\/jamiaopen\/ooaa006","article-title":"Machine learning for early detection of sepsis: An internal and temporal validation study","volume":"3","author":"Bedoya","year":"2020","journal-title":"JAMIA Open"},{"key":"ref_20","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019, January 4\u20138). Optuna: A Next-generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330701"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1186\/cc3045","article-title":"Statistics review 14: Logistic regression","volume":"9","author":"Bewick","year":"2005","journal-title":"Crit. Care"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/s10994-024-06723-8","article-title":"Resolving power: A general approach to compare the distinguishing ability of threshold-free evaluation metrics","volume":"114","author":"Beam","year":"2023","journal-title":"Mach. Learn."},{"key":"ref_24","unstructured":"Bunch, K. (2026, June 27). Pediatric Sepsis ML\u2014Analysis Pipeline. Available online: https:\/\/github.com\/kadenbunch\/pediatric-sepsis-ml."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1186\/s13054-022-03977-3","article-title":"Machine learning derivation of four computable 24-h pediatric sepsis phenotypes to facilitate enrollment in early personalized anti-inflammatory clinical trials","volume":"26","author":"Qin","year":"2022","journal-title":"Crit. Care"},{"key":"ref_26","unstructured":"Velez, T., Wang, T., Koutroulis, I., Chamberlain, J., Uppal, A., Yohannes, S., Tschampel, T., and Apostolova, E. (2019). Identification of Pediatric Sepsis Subphenotypes for Enhanced Machine Learning Predictive Performance: A Latent Profile Analysis. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/s12950-024-00379-w","article-title":"Pediatric sepsis inflammatory blood biomarkers that correlate with clinical variables and severity of illness scores","volume":"21","author":"Leonard","year":"2024","journal-title":"J. Inflamm."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e055658","DOI":"10.1136\/bmjopen-2021-055658","article-title":"Global eHealth capacity: Secondary analysis of WHO data on eHealth and implications for kidney care delivery in low-resource settings","volume":"12","author":"Okpechi","year":"2022","journal-title":"BMJ Open"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"20552076231203660","DOI":"10.1177\/20552076231203660","article-title":"An electronic health record system implementation in a resource limited country\u2014Lessons learned","volume":"9","author":"Ali","year":"2023","journal-title":"Digit. Health"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e44","DOI":"10.2196\/medinform.8131","article-title":"Open-Source Electronic Health Record Systems for Low-Resource Settings: Systematic Review","volume":"5","author":"Syzdykova","year":"2017","journal-title":"JMIR Med. Inform."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1161\/CIRCOUTCOMES.120.007031","article-title":"Use of Mobile Health Applications in Low-Income Populations","volume":"13","author":"Liu","year":"2020","journal-title":"Circ. Cardiovasc. Qual. Outcomes"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1080\/03091902.2016.1256081","article-title":"E-health in low to middle income countries","volume":"40","author":"Clifford","year":"2016","journal-title":"J. Med. Eng. Technol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e1684","DOI":"10.1016\/S2214-109X(23)00380-7","article-title":"Pulse oximetry to detect paediatric hypoxaemia-the fifth vital sign","volume":"11","author":"Heather","year":"2023","journal-title":"Lancet. Glob. Health"},{"key":"ref_34","unstructured":"Adam Levine, A.J. (2026, June 27). Remote Electronic Monitoring and Decision-support for ImprovEd Sepsis care (REMEDIES). Available online: https:\/\/osf.io\/bju56."}],"container-title":["Pediatric Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2036-7503\/18\/4\/88\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T04:27:54Z","timestamp":1783225674000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2036-7503\/18\/4\/88"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,3]]},"references-count":34,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["pediatric18040088"],"URL":"https:\/\/doi.org\/10.3390\/pediatric18040088","relation":{},"ISSN":["2036-7503"],"issn-type":[{"value":"2036-7503","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,3]]}}}