{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T23:46:12Z","timestamp":1792107972342,"version":"4.4.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"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":["Pediatr Res"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>This study aimed to address the critical gap in the limited application of machine learning (ML) for identifying developmental delays in low-resource settings by developing models to predict off-track development in infants aged 0 to 6 months and identify key predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A cross-sectional study involving 1,995 singleton infants aged 0 to 6 months was conducted in Kaloleni and Rabai sub-counties, Kilifi, Kenya, between March 2023 and March 2024. Development was assessed using the World Health Organization\u2019s Indicators of Infant and Young Child Development tool, with Development-for-Age Z-scores used to classify infants as on- or off-track. Ridge logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost) models were trained using sociodemographic, psychosocial, clinical\/biological, nutritional, and health-related predictors. Performance was evaluated using area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. SHapley Additive exPlanations enhanced model interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Approximately 10.4% of infants were developmentally off-track. Ridge LR, RF, and XGBoost showed similar performance, with AUCs of 76.6%, 75.8%, and 76.1%, respectively. Limited psychosocial stimulation and increasing infant age were the strongest predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study highlights the burden of developmental delays in low-resource settings. ML models<\/jats:p>\n                    <jats:p>show promise for early risk prediction and targeted intervention, though further validation is<\/jats:p>\n                    <jats:p>recommended.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Impact<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>Early intervention programs are proven to enhance optimal childhood development, yet the vital step of early identification of developmental delays is often overlooked.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>While machine learning is increasingly used to predict or identify health outcomes, its application in identifying developmental outcomes, particularly in low-resource settings, remains limited.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>This study contributes to the literature by applying machine learning to identify infants who are developmentally off-track and highlights key predictors. Limited psychosocial stimulation and increasing infant age were the strongest predictors, alongside low socioeconomic status, maternal mental health challenges, limited healthcare access, and nutritional and biological risks.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1038\/s41390-026-04761-7","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T10:46:51Z","timestamp":1769770011000},"page":"1100-1108","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting off-track development in infants aged 0\u20136 months in low-resource settings using machine learning"],"prefix":"10.1038","volume":"100","author":[{"given":"Faith Neema","family":"Benson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rachel","family":"Odhiambo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony K.","family":"Ngugi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Willie","family":"Brink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akbar K.","family":"Waljee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheryl A.","family":"Moyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Agoi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amina","family":"Abubakar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"4761_CR1","doi-asserted-by":"publisher","first-page":"e001302","DOI":"10.1136\/bmjgh-2018-001302","volume":"4","author":"L Richter","year":"2019","unstructured":"Richter, L. et al. Early childhood development: an imperative for action and measurement at scale. BMJ Glob. Health 4, e001302 (2019).","journal-title":"BMJ Glob. Health"},{"key":"4761_CR2","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1146\/annurev.psych.54.111301.145442","volume":"54","author":"DH Arnold","year":"2003","unstructured":"Arnold, D. H. & Doctoroff, G. L. The early education of socioeconomically disadvantaged children. Annu. Rev. Psychol. 54, 517\u2013545 (2003).","journal-title":"Annu. Rev. Psychol."},{"key":"4761_CR3","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1111\/j.1440-1754.2010.01817.x","volume":"46","author":"S Maggi","year":"2010","unstructured":"Maggi, S., Irwin, L. J., Siddiqi, A. & Hertzman, C. The social determinants of early child development: an overview. J. Paediatr. Child Health 46, 627\u2013635 (2010).","journal-title":"J. Paediatr. Child Health"},{"key":"4761_CR4","doi-asserted-by":"crossref","unstructured":"Raikes, A., Yoshikawa, H., Britto, P. R. & Iruka, I. Children, Youth and Developmental Science in the 2015-2030 Global Sustainable Development Goals. Social Policy Report. Volume 30, Number 3. Society for Research in Child Development (2017).","DOI":"10.1002\/j.2379-3988.2017.tb00088.x"},{"key":"4761_CR5","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/S0140-6736(16)31389-7","volume":"389","author":"MM Black","year":"2017","unstructured":"Black, M. M. et al. Early childhood development coming of age: science through the life course.  lancet 389, 77\u201390 (2017).","journal-title":"lancet"},{"key":"4761_CR6","doi-asserted-by":"publisher","first-page":"977453","DOI":"10.3389\/fpubh.2022.977453","volume":"10","author":"BO Olusanya","year":"2022","unstructured":"Olusanya, B. O., Kancherla, V., Shaheen, A., Ogbo, F. A. & Davis, A. C. Global and regional prevalence of disabilities among children and adolescents: analysis of findings from global health databases. Front. Public Health 10, 977453 (2022).","journal-title":"Front. Public Health"},{"key":"4761_CR7","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1093\/nsr\/nwt032","volume":"1","author":"J Fan","year":"2014","unstructured":"Fan, J., Han, F. & Liu, H. Challenges of big data analysis. Natl. Sci. Rev. 1, 293\u2013314 (2014).","journal-title":"Natl. Sci. Rev."},{"key":"4761_CR8","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1038\/nmeth.4642","volume":"15","author":"H Ij","year":"2018","unstructured":"Ij, H. Statistics versus machine learning. Nat. Methods 15, 233 (2018).","journal-title":"Nat. Methods"},{"key":"4761_CR9","doi-asserted-by":"crossref","unstructured":"Ahsan, M. M., Luna, S. A. & Siddique, Z. Machine-learning-based disease diagnosis: A comprehensive review. In Healthcare. 10, 541 (2022).","DOI":"10.3390\/healthcare10030541"},{"key":"4761_CR10","doi-asserted-by":"crossref","unstructured":"Okwi, P. O. et al. Spatial determinants of poverty in rural Kenya. Proc Natl Acad Sci USA. 104, 16769\u201316774 (2007).","DOI":"10.1073\/pnas.0611107104"},{"key":"4761_CR11","unstructured":"Kenya National Bureau of Statistics & ICF Macro. Kenya: Demographic and Health Survey 2008\u201309. Calverton, MD: KNBS & ICF Macro (2010). Available from: http:\/\/dhsprogram.com\/pubs\/pdf\/FR229\/FR229.pdf."},{"key":"4761_CR12","doi-asserted-by":"crossref","unstructured":"Ngugi, A. K. et al. Cohort profile: the Kaloleni\/Rabai community health and demographic surveillance system. Int. J. Epidemiol. 49, 758\u2013759e (2020).","DOI":"10.1093\/ije\/dyz252"},{"key":"4761_CR13","doi-asserted-by":"publisher","first-page":"6117","DOI":"10.3390\/ijerph18116117","volume":"18","author":"M Gladstone","year":"2021","unstructured":"Gladstone, M. et al. Validation of the infant and young child development (IYCD) indicators in three countries: Brazil, Malawi and Pakistan. Int. J. Environ. Res. public health 18, 6117 (2021).","journal-title":"Int. J. Environ. Res. public health"},{"key":"4761_CR14","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1046\/j.1525-1497.2001.016009606.x","volume":"16","author":"K Kroenke","year":"2001","unstructured":"Kroenke, K., Spitzer, R. L. & Williams, J. B. The PHQ-9: validity of a brief depression severity measure. J. Gen. Intern. Med. 16, 606\u2013613 (2001).","journal-title":"J. Gen. Intern. Med."},{"key":"4761_CR15","doi-asserted-by":"publisher","first-page":"1989","DOI":"10.1016\/j.procs.2020.04.213","volume":"171","author":"P Kumar","year":"2020","unstructured":"Kumar, P., Garg, S. & Garg, A. Assessment of anxiety, depression and stress using machine learning models. Procedia Comput. Sci. 171, 1989\u20131998 (2020).","journal-title":"Procedia Comput. Sci."},{"key":"4761_CR16","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1016\/S0022-3476(86)80853-8","volume":"108","author":"WK Frankenburg","year":"1986","unstructured":"Frankenburg, W. K. & Coons, C. E. Home Screening Questionnaire: its validity in assessing home environment.  J. Pediatr. 108, 624\u2013626 (1986).","journal-title":"J. Pediatr."},{"key":"4761_CR17","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1016\/j.earlhumdev.2008.02.003","volume":"84","author":"A Abubakar","year":"2008","unstructured":"Abubakar, A. et al. Socioeconomic status, anthropometric status, and psychomotor development of Kenyan children from resource-limited settings: a path-analytic study. Early Hum. Dev. 84, 613\u2013621 (2008).","journal-title":"Early Hum. Dev."},{"key":"4761_CR18","first-page":"57","volume":"17","author":"MF Sanner","year":"1999","unstructured":"Sanner, M. F. Python: a programming language for software integration and development. J. Mol. Graph Model 17, 57\u201361 (1999).","journal-title":"J. Mol. Graph Model"},{"key":"4761_CR19","doi-asserted-by":"publisher","first-page":"1920","DOI":"10.1161\/CIRCULATIONAHA.115.001593","volume":"132","author":"RC Deo","year":"2015","unstructured":"Deo, R. C. Machine learning in medicine. Circulation 132, 1920\u20131930 (2015).","journal-title":"Circulation"},{"key":"4761_CR20","doi-asserted-by":"crossref","unstructured":"Bohr, A. & Memarzadeh, K. In Artificial Intelligence in healthcare 25-60 (Elsevier, (2020).","DOI":"10.1016\/B978-0-12-818438-7.00002-2"},{"key":"4761_CR21","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1002\/sim.7992","volume":"38","author":"RD Riley","year":"2019","unstructured":"Riley, R. D. et al. Minimum sample size for developing a multivariable prediction model: PART II-binary and time-to-event outcomes. Stat. Med. 38, 1276\u20131296 (2019).","journal-title":"Stat. Med."},{"key":"4761_CR22","first-page":"545","volume":"6","author":"I Ivanov","year":"2023","unstructured":"Ivanov, I., Toleva, B. & Hooper, V. J. A fast and effective approach for classification medical data sets. Int. J. Innov. Res. Sci. Stud. 6, 545\u2013552 (2023).","journal-title":"Int. J. Innov. Res. Sci. Stud."},{"key":"4761_CR23","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1016\/j.procs.2022.12.067","volume":"215","author":"SM Shrestha","year":"2022","unstructured":"Shrestha, S. M. & Shakya, A. A customer churn prediction model using XGBoost for the telecommunication industry in Nepal. Procedia Comput. Sci. 215, 652\u2013661 (2022).","journal-title":"Procedia Comput. Sci."},{"key":"4761_CR24","doi-asserted-by":"crossref","unstructured":"Berrar, D. Cross\u2011validation. Encyclopedia of Bioinformatics and Computational Biology 542\u2013545 (Academic Press, 2019).","DOI":"10.1016\/B978-0-12-809633-8.20349-X"},{"key":"4761_CR25","doi-asserted-by":"crossref","unstructured":"Kuhn, M. & Johnson, K. Applied predictive modeling Vol. 26 (Springer, 2013).","DOI":"10.1007\/978-1-4614-6849-3"},{"key":"4761_CR26","doi-asserted-by":"publisher","unstructured":"Elshawi, R., Maher, M. & Sakr, S. Automated machine learning: state-of-the-art and open challenges. arXiv preprint. https:\/\/doi.org\/10.48550\/arXiv.1906.02287 (2019).","DOI":"10.48550\/arXiv.1906.02287"},{"key":"4761_CR27","doi-asserted-by":"publisher","unstructured":"Lundberg, S. M., Erion, G. G. & Lee, S.-I. Consistent individualized feature attribution for tree ensembles. arXiv preprint. https:\/\/doi.org\/10.48550\/arXiv.1802.03888 (2018).","DOI":"10.48550\/arXiv.1802.03888"},{"key":"4761_CR28","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1007\/s11277-021-09158-9","volume":"123","author":"D Tripathi","year":"2022","unstructured":"Tripathi, D., Shukla, A. K., Reddy, B. R., Bopche, G. S. & Chandramohan, D. Credit scoring models using ensemble learning and classification approaches: a comprehensive survey. Wirel. Personal. Commun. 123, 785\u2013812 (2022).","journal-title":"Wirel. Personal. Commun."},{"key":"4761_CR29","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1002\/bimj.200410135","volume":"47","author":"R Fluss","year":"2005","unstructured":"Fluss, R., Faraggi, D. & Reiser, B. Estimation of the Youden Index and its associated cutoff point. Biom. J. 47, 458\u2013472 (2005).","journal-title":"Biom. J."},{"key":"4761_CR30","first-page":"627","volume":"4","author":"K Hajian-Tilaki","year":"2013","unstructured":"Hajian-Tilaki, K. Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Casp. J. Intern. Med. 4, 627 (2013).","journal-title":"Casp. J. Intern. Med."},{"key":"4761_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12887-019-1769-z","volume":"19","author":"G Namazzi","year":"2019","unstructured":"Namazzi, G. et al. Prevalence and associated factors of neurodevelopmental disability among infants in eastern Uganda: a population based study. BMC Pediatr. 19, 1\u201310 (2019).","journal-title":"BMC Pediatr."},{"key":"4761_CR32","doi-asserted-by":"publisher","first-page":"e002117","DOI":"10.1136\/bmjpo-2023-002117","volume":"7","author":"G Segre","year":"2023","unstructured":"Segre, G. et al. Early detection of neurodevelopmental disorders in African children living in informal settlements in Nairobi. BMJ Paediatr. Open 7, e002117 (2023).","journal-title":"BMJ Paediatr. Open"},{"key":"4761_CR33","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1097\/JTO.0b013e3181ec173d","volume":"5","author":"JN Mandrekar","year":"2010","unstructured":"Mandrekar, J. N. Receiver operating characteristic curve in diagnostic test assessment. J. Thorac. Oncol. 5, 1315\u20131316 (2010).","journal-title":"J. Thorac. Oncol."},{"key":"4761_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12887-014-0308-1","volume":"14","author":"FA Camargo-Figuera","year":"2014","unstructured":"Camargo-Figuera, F. A., Barros, A. J., Santos, I. S., Matijasevich, A. & Barros, F. C. Early life determinants of low IQ at age 6 in children from the 2004 Pelotas Birth Cohort: a predictive approach. BMC Pediatr. 14, 1\u201312 (2014).","journal-title":"BMC Pediatr."},{"key":"4761_CR35","doi-asserted-by":"publisher","first-page":"1634","DOI":"10.1038\/s41390-023-02914-6","volume":"95","author":"AK Bowe","year":"2024","unstructured":"Bowe, A. K., Lightbody, G., O\u2019Boyle, D. S., Staines, A. & Murray, D. M. Predicting low cognitive ability at age 5 years using perinatal data and machine learning. Pediatr. Res. 95, 1634\u20131643 (2024).","journal-title":"Pediatr. Res."},{"key":"4761_CR36","doi-asserted-by":"publisher","first-page":"e2349111","DOI":"10.1001\/jamanetworkopen.2023.49111","volume":"6","author":"AK Bowe","year":"2023","unstructured":"Bowe, A. K., Lightbody, G., Staines, A., Murray, D. M. & Norman, M. Prediction of 2-year cognitive outcomes in very preterm infants using machine learning methods. JAMA Netw. Open 6, e2349111 (2023).","journal-title":"JAMA Netw. Open"},{"key":"4761_CR37","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1037\/0012-1649.39.5.924","volume":"39","author":"GW Evans","year":"2003","unstructured":"Evans, G. W. A multimethodological analysis of cumulative risk and allostatic load among rural children. Dev. Psychol. 39, 924 (2003).","journal-title":"Dev. Psychol."},{"key":"4761_CR38","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-021-11147-3","volume":"21","author":"B Koshy","year":"2021","unstructured":"Koshy, B. et al. Developmental trends in early childhood and their predictors from an Indian birth cohort. BMC Public Health 21, 1083 (2021).","journal-title":"BMC Public Health"},{"key":"4761_CR39","doi-asserted-by":"publisher","first-page":"1329","DOI":"10.3390\/children12101329","volume":"12","author":"BM Bondo","year":"2025","unstructured":"Bondo, B. M. et al. Factors associated with being on track for early childhood development in kinshasa: a community-based cross-sectional study. Children 12, 1329 (2025).","journal-title":"Children"}],"container-title":["Pediatric Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41390-026-04761-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41390-026-04761-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41390-026-04761-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T22:57:21Z","timestamp":1792105041000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41390-026-04761-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,30]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["4761"],"URL":"https:\/\/doi.org\/10.1038\/s41390-026-04761-7","relation":{},"ISSN":["0031-3998","1530-0447"],"issn-type":[{"value":"0031-3998","type":"print"},{"value":"1530-0447","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,30]]},"assertion":[{"value":"23 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"The primary project was approved by the Aga Khan University, Nairobi Institutional Scientific and Ethics Review Committee (Ref: 2022\/ISERC_75(V2)). Permission to conduct the study in Kenya was granted by the National Commission for Science, Technology, and Innovation (Ref: 2322698). A local permit to conduct the study was granted by the research office in Kilifi (Ref: KLF\/DOH\/RESEARCH\/VOL.1\/004). All participants provided written informed consent for their participation.","order":2,"name":"Ethics","label":"Ethics approval","group":{"name":"EthicsHeading","label":"Ethics"}}]}}