{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,20]],"date-time":"2026-11-20T02:36:58Z","timestamp":1795142218581,"version":"4.10.3"},"reference-count":40,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"unspecified","delay-in-days":10,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100007452","name":"\u201dWu Jieping Medical Foundation","doi-asserted-by":"crossref","award":["320.6750.2025-9-21"],"award-info":[{"award-number":["320.6750.2025-9-21"]}],"id":[{"id":"10.13039\/100007452","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["bmjpo"],"accepted":{"date-parts":[[2026,4,17]]},"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:p>The neonatal intensive care unit (NICU) generates vast amounts of high-throughput, multimodal monitoring data, offering unprecedented potential for identifying early signs of clinical deterioration in high-risk neonates. However, the traditional threshold-based alarm systems are plagued by high false alarm rates and alarm fatigue, failing to harness this data complexity. This narrative review examines the role of machine learning (ML) in transforming early warning systems (EWSs) by effectively analysing these complex data streams. We first characterise the diverse sources\u2014including physiological waveforms, neuromonitoring signals, electronic health records and emerging behavioural data\u2014and inherent challenges (eg, noise, heterogeneity, label scarcity) of NICU data. We then detail key ML technologies, from preprocessing and feature engineering to core algorithms like deep learning models (recurrent neural networks, convolutional neural networks, Transformers) and multimodal fusion strategies, emphasising their application in handling time-series data. The review catalogues empirical evidence of ML-driven EWS for critical conditions such as sepsis, necrotising enterocolitis, neurological injury and cardiorespiratory instability, highlighting performance improvements over conventional methods. Finally, we discuss the significant technical, clinical integration and ethical challenges that impede widespread adoption and outline future directions, including federated learning, digital twins and cloud-edge architectures. The integration of ML-based insights promises to shift neonatal care from a reactive to a proactive, personalised paradigm, ultimately aiming to improve outcomes for vulnerable infants.<\/jats:p>","DOI":"10.1136\/bmjpo-2026-004705","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:40:24Z","timestamp":1781196024000},"page":"e004705","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":2,"title":["High-throughput analysis of multimodal monitoring data: the role of machine learning in early warning systems for high-risk neonates"],"prefix":"10.1136","volume":"10","author":[{"given":"Huiyi","family":"Huo","sequence":"first","affiliation":[{"name":"Department of Neonatology, The First People\u2019s Hospital of Foshan (Foshan Hospital Affiliated to Southern University of Science and Technology), School of Medicine, Southern University of Science and Technology, Foshan, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxue","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Neonatology, The First People\u2019s Hospital of Foshan (Foshan Hospital Affiliated to Southern University of Science and Technology), School of Medicine, Southern University of Science and Technology, Foshan, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Neonatology, The First People\u2019s Hospital of Foshan (Foshan Hospital Affiliated to Southern University of Science and Technology), School of Medicine, Southern University of Science and Technology, Foshan, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Neonatology, The First People\u2019s Hospital of Foshan (Foshan Hospital Affiliated to Southern University of Science and Technology), School of Medicine, Southern University of Science and Technology, Foshan, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinjuan","family":"Pei","sequence":"additional","affiliation":[{"name":"Department of Neonatology, The First People\u2019s Hospital of Foshan (Foshan Hospital Affiliated to Southern University of Science and Technology), School of Medicine, Southern University of Science and Technology, Foshan, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7356-1888","authenticated-orcid":false,"given":"Chao","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Stomatology, The Eighth Affiliated Hospital of Southern Medical University (The First People's Hospital of Shunde), Foshan, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"key":"2026061109401333000_10.1.e004705.1","doi-asserted-by":"crossref","first-page":"106401","DOI":"10.1016\/j.earlhumdev.2025.106401","article-title":"Gut microbiota as a risk and protective factor in neonatal necrotizing enterocolitis: An integrative review","volume":"211","author":"Onofre","year":"2025","journal-title":"Early Hum Dev"},{"key":"2026061109401333000_10.1.e004705.2","doi-asserted-by":"crossref","first-page":"105366","DOI":"10.1016\/j.ijmedinf.2024.105366","article-title":"Early detection of late-onset neonatal sepsis from noninvasive biosignals using deep learning: A multicenter prospective development and validation study","volume":"184","author":"Kallonen","year":"2024","journal-title":"Int J Med Inform"},{"key":"2026061109401333000_10.1.e004705.3","doi-asserted-by":"crossref","first-page":"108658","DOI":"10.1016\/j.compbiomed.2024.108658","article-title":"Machine learning model with output correction: Towards reliable bradycardia detection in neonates","volume":"177","author":"Rahman","year":"2024","journal-title":"Comput Biol Med"},{"key":"2026061109401333000_10.1.e004705.4","doi-asserted-by":"crossref","first-page":"2056","DOI":"10.1038\/s41390-024-03604-7","article-title":"Early prediction of mortality and morbidities in VLBW preterm neonates using machine learning","volume":"97","author":"Shu","year":"2025","journal-title":"Pediatr Res"},{"key":"2026061109401333000_10.1.e004705.5","doi-asserted-by":"crossref","DOI":"10.1186\/s13054-025-05553-x","article-title":"Development and validation of a dynamic early warning system with time-varying machine learning models for predicting hemodynamic instability in critical care: a multicohort study","volume":"29","author":"Chiang","year":"2025","journal-title":"Crit Care"},{"key":"2026061109401333000_10.1.e004705.6","doi-asserted-by":"crossref","first-page":"101690","DOI":"10.1016\/j.siny.2025.101690","article-title":"A systematic review on the use of artificial intelligence in the neonatal intensive care unit: far beyond the potential impact","volume":"31","author":"Millana","year":"2026","journal-title":"Semin Fetal Neonatal Med"},{"key":"2026061109401333000_10.1.e004705.7","doi-asserted-by":"crossref","DOI":"10.3390\/s23094487","article-title":"Respiratory Rate Extraction from Neonatal Near-Infrared Spectroscopy Signals","volume":"23","author":"Hakimi","year":"2023","journal-title":"Sensors (Basel)"},{"key":"2026061109401333000_10.1.e004705.8","doi-asserted-by":"crossref","first-page":"104315","DOI":"10.1016\/j.braindev.2024.104315","article-title":"Which aEEG patterns could predict neurodevelopmental outcome in preterm neonates? - A systematic review","volume":"47","author":"Santos","year":"2025","journal-title":"Brain Dev"},{"key":"2026061109401333000_10.1.e004705.9","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1038\/jp.2017.14","article-title":"Predictive value of amplitude-integrated EEG (aEEG) after rescue hypothermic neuroprotection for hypoxic ischemic encephalopathy: a meta-analysis","volume":"37","author":"Chandrasekaran","year":"2017","journal-title":"J Perinatol"},{"key":"2026061109401333000_10.1.e004705.10","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1002\/ped4.70025","article-title":"The utility of C-reactive protein in neonatal early-onset sepsis screening: A territory-wide cohort analysis","volume":"9","author":"Wang","year":"2025","journal-title":"Pediatr Investig"},{"key":"2026061109401333000_10.1.e004705.11","doi-asserted-by":"crossref","first-page":"102724","DOI":"10.1016\/j.artmed.2023.102724","article-title":"Human vs machine towards neonatal pain assessment: A comprehensive analysis of the facial features extracted by health professionals, parents, and convolutional neural networks","volume":"147","author":"Carlini","year":"2024","journal-title":"Artif Intell Med"},{"key":"2026061109401333000_10.1.e004705.12","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2013.2240452"},{"key":"2026061109401333000_10.1.e004705.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinph.2017.08.036"},{"key":"2026061109401333000_10.1.e004705.14","doi-asserted-by":"crossref","first-page":"1387","DOI":"10.1007\/s10877-023-00975-w","article-title":"Missing data imputation techniques for wireless continuous vital signs monitoring","volume":"37","author":"van Rossum","year":"2023","journal-title":"J Clin Monit Comput"},{"key":"2026061109401333000_10.1.e004705.15","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/JBHI.2016.2636665","article-title":"Deep Learning for Health Informatics","volume":"21","author":"Ravi","year":"2017","journal-title":"IEEE J Biomed Health Inform"},{"key":"2026061109401333000_10.1.e004705.16","doi-asserted-by":"crossref","DOI":"10.3346\/jkms.2025.40.e208","article-title":"Predicting the Need for Cardiopulmonary Resuscitation in Preterm Infants in the Delivery Room Using Machine Learning Models: Analysis of a Korean Neonatal Network Database","volume":"40","author":"Kim","year":"2025","journal-title":"J Korean Med Sci"},{"key":"2026061109401333000_10.1.e004705.17","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-025-89905-1","article-title":"Predicting preterm birth using machine learning methods","volume":"15","author":"Kloska","year":"2025","journal-title":"Sci Rep"},{"key":"2026061109401333000_10.1.e004705.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2017.09.017"},{"key":"2026061109401333000_10.1.e004705.19","doi-asserted-by":"crossref","DOI":"10.3390\/bioengineering11010089","article-title":"ECG Forecasting System Based on Long Short-Term Memory","volume":"11","author":"Zacarias","year":"2024","journal-title":"Bioengineering (Basel)"},{"key":"2026061109401333000_10.1.e004705.20","doi-asserted-by":"crossref","first-page":"3422","DOI":"10.1109\/JBHI.2024.3390606","article-title":"Understanding the Role of Self-Attention in a Transformer Model for the Discrimination of SCD From MCI Using Resting-State EEG","volume":"28","author":"Sibilano","year":"2024","journal-title":"IEEE J Biomed Health Inform"},{"key":"2026061109401333000_10.1.e004705.21","doi-asserted-by":"crossref","DOI":"10.3390\/ijms231911880","article-title":"Data Integration-Possibilities of Molecular and Clinical Data Fusion on the Example of Thyroid Cancer Diagnostics","volume":"23","author":"P\u0142uciennik","year":"2022","journal-title":"Int J Mol Sci"},{"key":"2026061109401333000_10.1.e004705.22","article-title":"Influence of early through late fusion on pancreas segmentation from imperfectly registered multimodal magnetic resonance imaging","volume":"12","author":"Remedios","year":"2025","journal-title":"J Med Imaging (Bellingham)"},{"key":"2026061109401333000_10.1.e004705.23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"2026061109401333000_10.1.e004705.24","doi-asserted-by":"crossref","first-page":"104138","DOI":"10.1016\/j.medengphy.2024.104138","article-title":"Advanced hybrid attention-based deep learning network with heuristic algorithm for adaptive CT and PET image fusion in lung cancer detection","volume":"126","author":"Shyamala Bharathi","year":"2024","journal-title":"Med Eng Phys"},{"key":"2026061109401333000_10.1.e004705.25","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0317396","article-title":"Addressing imbalanced data classification with Cluster-Based Reduced Noise SMOTE","volume":"20","author":"Hemmatian","year":"2025","journal-title":"PLoS One"},{"key":"2026061109401333000_10.1.e004705.26","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1037\/met0000586","article-title":"Everything has its price: Foundations of cost-sensitive machine learning and its application in psychology","volume":"30","author":"Sterner","year":"2025","journal-title":"Psychol Methods"},{"key":"2026061109401333000_10.1.e004705.27","doi-asserted-by":"crossref","DOI":"10.2196\/32903","article-title":"Strategies to Address the Lack of Labeled Data for Supervised Machine Learning Training With Electronic Health Records: Case Study for the Extraction of Symptoms From Clinical Notes","volume":"10","author":"Humbert-Droz","year":"2022","journal-title":"JMIR Med Inform"},{"key":"2026061109401333000_10.1.e004705.28","doi-asserted-by":"crossref","first-page":"1606571","DOI":"10.3389\/fped.2025.1606571","article-title":"Ultrasound combined with serological markers for predicting neonatal necrotizing enterocolitis: a machine learning approach","volume":"13","author":"Yang","year":"2025","journal-title":"Front Pediatr"},{"key":"2026061109401333000_10.1.e004705.29","doi-asserted-by":"crossref","unstructured":"Hossain MI , Zamzmi G , Mouton P , et al . Explainable ai (xai) for neonatal pain assessment via influence function modification. 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); Orlando, FL, USA, 2024:1\u20135. doi:10.1109\/EMBC53108.2024.10782892","DOI":"10.1109\/EMBC53108.2024.10782892"},{"key":"2026061109401333000_10.1.e004705.30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpeds.2011.06.044"},{"key":"2026061109401333000_10.1.e004705.31","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0212665","article-title":"Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data","volume":"14","author":"Masino","year":"2019","journal-title":"PLoS One"},{"key":"2026061109401333000_10.1.e004705.32","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1055\/a-2685-2169","article-title":"Clinical Impact of the PDA and Its Management on Outcomes of Preterm Infants with NEC: A Review","volume":"43","author":"Gunasekaran","year":"2026","journal-title":"Am J Perinatol"},{"key":"2026061109401333000_10.1.e004705.33","first-page":"1452","article-title":"Using Vital Signs for the Early Prediction of Necrotizing Enterocolitis in Preterm Neonates with Machine Learning","volume":"11","author":"Verhoeven","year":"2024","journal-title":"Children (Basel)"},{"key":"2026061109401333000_10.1.e004705.34","doi-asserted-by":"crossref","first-page":"51050","DOI":"10.1109\/ACCESS.2021.3069191","article-title":"Multimodal AI System for the Rapid Diagnosis and Surgical Prediction of Necrotizing Enterocolitis","volume":"9","author":"Gao","year":"2021","journal-title":"IEEE Access"},{"key":"2026061109401333000_10.1.e004705.35","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1038\/s41597-023-02002-8","article-title":"Neonatal EEG graded for severity of background abnormalities in hypoxic-ischaemic encephalopathy","volume":"10","author":"O\u2019Toole","year":"2023","journal-title":"Sci Data"},{"key":"2026061109401333000_10.1.e004705.36","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.compbiomed.2015.05.017","article-title":"Multimodal predictor of neurodevelopmental outcome in newborns with hypoxic-ischaemic encephalopathy","volume":"63","author":"Temko","year":"2015","journal-title":"Comput Biol Med"},{"key":"2026061109401333000_10.1.e004705.37","unstructured":"Thornber K . Machine Learning Advances Prognosis in Hypoxic-Ischemic Encephalopathy. Neurology (ECronicon) 2024."},{"key":"2026061109401333000_10.1.e004705.38","doi-asserted-by":"crossref","unstructured":"Kloonen RMJS , Varisco G , de Kort E , et al . Predicting CPAP failure after less invasive surfactant administration (LISA) in preterm infants by machine learning model on vital parameter data: a pilot study. Physiol Meas 2023;44. doi:10.1088\/1361-6579\/ad0ab6","DOI":"10.1088\/1361-6579\/ad0ab6"},{"key":"2026061109401333000_10.1.e004705.39","doi-asserted-by":"crossref","DOI":"10.1007\/s00431-025-06073-0","article-title":"A machine learning approach to predict mortality and neonatal persistent pulmonary hypertension in newborns with congenital diaphragmatic hernia. A retrospective observational cohort study","volume":"184","author":"Conte","year":"2025","journal-title":"Eur J Pediatr"},{"key":"2026061109401333000_10.1.e004705.40","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMc2029240"}],"container-title":["BMJ Paediatrics Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjpo-2026-004705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:40:30Z","timestamp":1781196030000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjpaedsopen.bmj.com\/lookup\/doi\/10.1136\/bmjpo-2026-004705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,6,11]]},"published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1136\/bmjpo-2026-004705"],"URL":"https:\/\/doi.org\/10.1136\/bmjpo-2026-004705","relation":{},"ISSN":["2399-9772"],"issn-type":[{"value":"2399-9772","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}