jmn4(1)_preneonates | Neural Press

How to cite this paper

Syed Taimoor Hussain Shah, Syed Adil Hussain Shah, Konstantinos Panagiotopoulos, Janet Pigueiras-del-Real, Kainat Qayyum, Syed Baqir Hussain Shah, Shahzad Ahmad Qureshi, Angelo Di Terlizzi, Giacomo Di Benedetto & Marco Agostino Deriu (2025). Artificial intelligence coupled with the Internet of Things targeting neurodevelopmental challenges in preterm neonates. Journal of Multiscale Neuroscience 4(1), 32-56. https://doi.org/10.56280

Authors Affiliation

Politecnico di Torino, Department of Mechanical and Aerospace Engineering, PolitoBioMed Lab, Corso Duca degli Abruzzi 24, Torino, 10129, Italy

GPI SpA, Department of Research and Development (R&D), Via Ragazzi del '99, Trento 38123, Italy

University of Cádiz, Department of Condensed Matter Physics, Cádiz 11510, Spain

Tianjin Polytechnic University, School of Artificial Intelligence, Binshui West Road No. 399, Tianjin 300387, PR China

COMSATS University Islamabad (CUI), Wah Campus, Department of Computer Science, Grand Trunk Road, Wah 47040, Pakistan

Pakistan Institute of Engineering and Applied Sciences (PIEAS), Department of Computer and Information Sciences, Islamabad 45650, Pakistan

7HC SRL, Rome 00198, Italy

Received 7 February 2025

Accepted: 19 February 2025

Online Published: 12 March 2025

ORIGINAL RESEARCH Artificial intelligence coupled with the Internet of Things targeting

neurodevelopmental challenges in preterm neonates

Publication: Journal of Multiscale Neuroscience DOI: https://doi.org/10.56280

Abstract

Preterm neonates face significant neurological risks due to incomplete brain development at birth. The third trimester is critical for brain maturation, and premature birth disrupts essential developmental processes, leading to long-term cognitive, motor, and sensory impairments. Key vulnerabilities include cortical underdevelopment, white matter damage, and immature neurotransmission, contributing to neurodevelopmental disorders such as cerebral palsy, attention deficits, and learning difficulties. While advances in Neonatal Intensive Care Units (NICUs) have improved survival rates, early detection and continuous monitoring of complications remain challenging. The integration of Internet of Things (IoT) technology in neonatal care presents a transformative approach, enabling real-time physiological monitoring, predictive analytics, and automated alerts for timely interventions. IoT-driven neonatal monitoring systems enhance clinical decision-making, reduce caregiver burden, and improve patient outcomes. In parallel, Artificial Intelligence (AI) is revolutionizing neonatal healthcare by processing multimodal data, including clinical records, physiological signals, and imaging to provide real-time insights, predictive diagnostics, and risk assessments. Machine learning (ML) and deep learning (DL) techniques aid in disease prediction, anomaly detection, and precision diagnostics, significantly enhancing neonatal monitoring. However, challenges such as AI interpretability, data security, and integration into clinical workflows must be addressed to ensure adoption. Explainable-AI (XAI) tools such as SHAP, LIME, and Grad-CAM are crucial in making AI-driven decisions more transparent and actionable. The future of neonatal AI lies in developing multimodal frameworks that integrate physiological signals and facial, vocal, and motion data for comprehensive neonatal health monitoring. Addressing the technical and ethical challenges associated with AI and IoT adoption will be critical to fully realizing their potential in neonatal care and improving outcomes for preterm infants.

Keywords: Preterm neonates, brain development, neurodevelopmental disorders, neonatal intensive care unit, Internet of Things, artificial intelligence, machine learning, deep learning, explainable-AI, predictive analytics

Conflict of Interest

The authorS declare no conflict of interest

This is an open access article distributed under the terms and conditions of the CC BY 4.0 license.

Disclaimer: The statements, opinions, and data in the Journal of Multiscale Neuroscience are solely those of the individual authors and contributors, not those of the Neural Press™ or the editors(s).

References:

Abbasi, H., Mollet, S.R., Williams, S.A., Lim, L. & Battin, M.R. et al. (2023) Deep-learning for automated markerless

tracking of infants' general movements. International Journal of Information Technology 15, 4073–4083.

Abduhari, E.S., Shaik, T.C., Adidul, A.B., Ladja, J.H. & Saliddin, E.S. et al. (2025) Access control mechanisms and

their role in preventing unauthorized data access: A comparative analysis of RBAC, MFA, and strong passwords.

Natural Sciences Engineering and Technology Journal 5, 418–430

Brett, C. & Robinowitz, D. (2023) Physiology and development of the term and preterm neonate. In J. Lerman (ed.) Neonatal Anesthesia. Cham: Springer International Publishing, Switzerland.

Chandrasekaran, A., Amboiram, P., Balakrishnan, U., Abiramalatha, T. & Rao, G. et al. (2021) Disposable low- cost cardboard incubator for thermoregulation of stable preterm infant – a randomized controlled non-inferiority trial. eClinicalMedicine 31, 100664.

Colom, M. & Rohloff, P. (2018) Cultural considerations for informed consent in paediatric research in low/middle income countries: a scoping review. BMJ Paediatrics Open 2, e000298.

De Paula Fiod Costa, H. & De Paula Fiod Costa, E. (2022) Neonatal complications of prematurity. In, R.A. Moreira de

Sá and E.B. da Fonseca (eds) Perinatology: Evidence-Based Best Practices in Perinatal Medicine. Cham, Springer

International Publishing.