Article Summary

Vicky R. Bowden, DNSc, RN, and Bernice D. Mowery, PhD, RN

Knowledge-to-Action

Five Ways Artificial Intelligence Impacts Pediatric Health Care

Beth Kaylor

A

rtificial intelligence (AI) is reshaping pediatric health care, offering innovative solutions to enhance clinical decision-making, early disease detection, and patient monitoring. These

advancements can potentially improve patient outcomes while optimizing workflow efficiency. This article explores five key applications of AI in pediatrics that have shown promise in transforming patient care.

Five Key Applications of AI

These AI applications were selected based on their demonstrated impact on pediatric health care, their ability to enhance patient care and nursing efficiency, and their potential for widespread adoption in clinical practice. Each application addresses a critical aspect of pediatric health care, from improving diagnosis and treatment to optimizing workflows and expanding access to care. Table 1 summarizes these applications, including their clinical benefits and implementation challenges.

Sepsis Detection and Management

Sepsis remains a leading cause of morbidity and mortality among children, necessitating rapid identification and intervention to improve survival outcomes. Traditional screening methods, such as the Systemic Inflammatory Response Syndrome (SIRS) criteria, have been widely used; however, their low sensitivity (ability to identify those with sepsis) and specificity (ability to identify those without sepsis) in children often lead to overdiagnosis and treatment delays (Goldstein et al., 2005). SIRS criteria may not effectively differentiate between infectious and non-infectious inflammatory

Beth Kaylor, RN, CAPS, CSPO, is a Health Technology Consultant and Founder of AI in Nursing, Chattanooga, TN.

© 2025 Jannetti Publications, Inc.

Kaylor, B. (2025). Five ways artificial intelligence impacts pediatric health care. Pediatric Nursing, 51(4), 203206. https://doi.org/10.62116/PNJ.2025.51.4.203

responses in children, underscoring the need for pediatric-specific sepsis definitions to guide clinical decision-making (Fleischmann-Struzek et al., 2018; Weiss et al., 2020).

Recent advancements in sepsis detection have focused on integrating biomarker-based risk stratification and machine learning (ML)-driven models to improve early detection and clinical outcomes (Bignami et al., 2025). ML is a type of AI that uses algorithms to learn from data and make predictions without explicit programming. AI- and ML-powered algorithms can analyze trends in vital signs, laboratory markers, and electronic health records (EHRs) to identify sepsis risk earlier than conventional methods (Fleischmann-Struzek et al., 2018). Standardizing evidence-based pediatric sepsis criteria remains essential for enhancing diagnostic precision and patient care.

AI-driven early warning systems for sepsis have demonstrated the ability to expedite key interventions, including antibiotic administration, fluid resuscitation, and escalation of care, significantly reducing time to treatment (Di Sarno et al., 2024). These systems offer valuable decision support for pediatric nurses during rapid assessment and triage. Despite these advancements, important challenges persist. Many sepsis prediction models have been trained primarily on adult datasets, necessitating rigorous validation in pediatric cohorts to minimize bias and improve reliability (Fleischmann-Struzek et al., 2018).

In the Knowledge-to-Action column, nurse experts share practical information to better understand scholarly activities for research, evidence-based practice, quality improvement, and implementation of science processes. Look for Knowledge-to-Action in each issue of Pediatric Nursing.

PEDIATRIC NURSING/July-August 2025/Vol. 51/No. 4 203

Table 1.

Key Artificial Intelligence (AI) Application in Pediatric Health Care

AI Application	Use Case	Clinical Benefits	Implementation Challenges
Sepsis detection and management	Early identification using AI-based predictive models	Faster diagnosis, improved survival rates	Data accuracy, need for pediatric-specific validation
Remote monitoring and wearables	AI-integrated sensors track vital signs, detect early deterioration	Non-invasive monitoring, reduced hospital visits	Device accessibility, data privacy concerns
Autism screening	AI-based behavioral, neuroimaging, and eyetracking models for autism spectrum disorder detection	Early intervention, objective diagnosis	Bias in AI models, need for broader dataset representation
Clinical decision support	AI-driven alerts and risk stratification tools for pediatric conditions	Reduced diagnostic errors, optimized treatment plans	Integration into workflow, alert fatigue
Support for non-specialized pediatric care	AI-assisted guidance for nurses in general hospitals or rural areas	Improved care in underserved areas, reduced disparities	Implementation costs, training requirements

The successful integration of AI-based clinical decision support (CDS) systems requires active clinician engagement, seamless EHR integration, and ongoing monitoring to mitigate alert fatigue and ensure responsible AI-assisted decision-making at the bedside (Ramgopal et al., 2022). For frontline pediatric nurses, balancing AI-generated alerts with clinical judgment remains essential. Continued validation across diverse health care settings and standardization efforts are critical to establish AI as a reliable, evidence-based tool that enhances rather than replaces clinical expertise.

Remote Monitoring and Wearables

Advancements in AI and wearable technologies are transforming pediatric health care by enabling continuous, non-invasive monitoring of vital signs and early disease detection both inside and outside of health care settings. AI-integrated remote monitoring devices provide real-time assessment at home of physiological parameters, reducing hospital visits and enabling earlier intervention when abnormalities are detected (Krbec et al., 2024). AI-driven wearable sensors can help detect cardiorespiratory instability before clinical deterioration occurs. Compared to traditional monitoring techniques, AI enhances the early identification of respiratory distress, apnea, and vital sign fluctuations both within and outside of the hospital environment (Krbec et al., 2024). These innovations are particularly beneficial in neonatal intensive care units and resource-limited settings, where early detection can significantly impact survival rates.

Beyond neonatal care, AI-powered remote monitoring is gaining traction in pediatric psychiatry. Wearable biosensors and mobile applications can passively monitor physiological signals, such as heart rate variability and sleep patterns, which may serve as indicators of mental health conditions (Welch et al., 2022). By providing continuous, objective data, these AI-enhanced tools support early identification and intervention for anxiety and depression in children and adolescents.

AI-driven wearables are also being integrated into postoperative care, allowing for early detection of surgical complications through ML-based analysis of postoperative vital signs. This can predict complications such as infection, dehydration, or cardiovascular distress, reducing hospital readmissions and improving recovery outcomes (Ghomrawi et al., 2023).

As AI-powered wearable technologies evolve, further research is needed to validate their accuracy, integrate them effectively into clinical workflows, and ensure equitable access for pediatric patients. Addressing ethical considerations such as data privacy will be critical for their successful implementation in pediatric health care.

Autism Screening

Autism spectrum disorder (ASD) affects social communication, behavior, and sensory processing in children. Early diagnosis is essential for improving longterm outcomes, yet traditional screening methods rely on observations and questionnaires, which can be subjective and time-consuming (Farooq et al., 2023). AI-driven models offer a more objective, data-driven ap proach. They analyze behavioral, linguistic, and physiological data to detect early markers of ASD and can identify subtle behavioral patterns that may be difficult for human observers to recognize.

204 PEDIATRIC NURSING/July-August 2025/Vol. 51/No. 4

AI-powered eye-tracking technologies are emerging as another promising tool for early ASD detection. Children with ASD exhibit distinct gaze patterns, such as reduced eye contact and altered social attention (Cilia et al., 2021). ML models can analyze eye-tracking data in real-time, providing scalable, noninvasive, and costeffective screening tools for primary care settings or telehealth platforms (Meng et al., 2023).

As AI technologies evolve, pediatric nurses play a crucial role in advocating for safe, ethical implementation while leveraging AI as a supportive tool to enhance, not replace, clinical expertise.

Despite its potential, AI-based ASD detection faces significant challenges. Model bias, data limitations, and clinical validation remain key concerns. Most AI models are trained on datasets that may not fully represent diverse pediatric populations, raising issues of generalizability and equity in diagnosis (Farooq et al., 2023). Addressing these challenges through diverse data collection, rigorous validation, and ethical AI implementation will be essential for ensuring AI’s role in improving ASD screening and early intervention.

Clinical Decision Support

Clinical decision support systems play a vital role in pediatric care by providing real-time recommendations, risk stratification, and diagnostic insights. AI-driven CDS enhances traditional systems by offering more personalized and adaptive decision-making (Ramgopal et al., 2022). One study found that AI-based systems outperformed traditional early warning scores by reducing false positives and improving early warning detection for conditions such as sepsis, respiratory distress, and acute kidney injury (Rust et al., 2023). Additionally, AIenhanced CDS has been successfully implemented in pediatric emergency departments, reducing diagnostic errors and improving workflow efficiency (Di Sarno et al., 2024).

Beyond acute care, AI-enhanced CDS systems support the management of chronic pediatric conditions such as asthma. A randomized trial found that an AI-assisted CDS tool for childhood asthma management improved adherence to clinical guidelines, reduced exacerbations, and increased provider confidence in treatment plans (Seol et al., 2021). Despite these advancements, successful implementation requires seamless integration into clinical workflows while minimizing alert fatigue. Ensuring that AI-based tools complement, rather than overwhelm clinicians, is essential for optimizing their effectiveness and adoption in pediatric health care (Ramgopal et al., 2022).

Support for Non-Specialized Pediatric Care

Many pediatric conditions require specialized knowledge that non-pediatric health care providers may lack. AI-driven tools help bridge this gap by equipping general health care professionals with advanced decision support, predictive analytics, and remote monitoring capabilities. These innovations are particularly valuable in rural hospitals, general emergency departments, and community clinics, where access to pediatric specialists is often limited.

AI-driven sepsis prediction models can improve early detection rates, particularly in hospitals with limited pediatric expertise, where timely recognition and intervention are critical. These tools provide essential decision support, allowing non-specialist providers to identify sepsis risk earlier and initiate appropriate interventions (Bignami et al., 2025).

Beyond decision support, AI enhances remote monitoring and telehealth services in underserved areas. AIpowered remote monitoring devices continuously track vital signs and detect early warning signs of deterioration, reducing hospital visits, and providing a safety net for children in regions with limited pediatric resources. Adding a virtual nurse to the health care team can reduce the additional staff burden often associated with remote patient monitoring, though this addition may impact the overall cost of care. To maximize AI’s impact, efforts should focus on expanding access to AI-driven tools, ensuring adequate training for health care professionals, and validating AI models across diverse pediatric populations to ensure equitable and reliable implementation.

Implications for Pediatric Nursing Practice

As AI continues to evolve in health care, its role in nursing practice is becoming increasingly significant. AI-driven tools can enhance nursing practice by addressing daily workflow challenges, supporting clinical decision-making, and enhancing chronic disease management.

For pediatric nurses, the adoption of AI applications offers several key advantages.

· Enhanced assessment capabilities: AI-powered tools can detect subtle clinical changes before visible symptoms appear, allowing for earlier intervention.

· Workflow optimization: Automated documentation, predictive alerts, and AI-assisted decision support can reduce administrative burdens, allowing nurses to focus more on direct patient care.

· Support for evidence-based practice: AI helps standardize care protocols, ensuring consistent application of best practices, which can be particularly beneficial for novice nurses.

· Extended reach in resource-limited settings: AIenhanced telehealth platforms extend pediatric nursing expertise to underserved areas, improving access to care.

· Continuous professional development: AI-based simulation and learning systems provide ongoing education and skills reinforcement.

Conclusion

PEDIATRIC NURSING/July-August 2025/Vol. 51/No. 4 205

Artificial intelligence is rapidly transforming pediatric nursing by enhancing clinical decision-making, improving early detection, and optimizing patient management. These advancements enhance diagnostic precision and help alleviate the workload burden on health care providers. However, successful integration into practice requires rigorous clinical validation, continuous education for health care professionals, and thoughtful implementation to ensure equitable access.

Ethical considerations, such as data privacy, algorithm bias, and transparency, must be prioritized to support responsible AI adoption. As these technologies evolve, pediatric nurses play a crucial role in advocating for safe, ethical implementation while leveraging AI as a supportive tool to enhance, not replace, clinical expertise. By staying informed, actively engaging with emerging research, and shaping AI integration within pediatric health care, nurses can help ensure these technologies drive improved patient outcomes and contribute to a more sustainable, effective health care system.

References

Bignami, E.G., Berdini, M., Panizzi, M., Domenichetti, T., Bezzi, F., Allai, S., Damiano, T., & Bellini, V. (2025). Artificial intelligence in sepsis management: An overview for clinicians. Journal of

Clinical Medicine, 14(1), 286. https://doi.org/10.3390/jcm1401

0286

Cilia, F., Carette, R., Elbattah, M., Dequen, G., Guérin, J.L., Bosche, J., Vandromme, L., & Le Driant, B. (2021). Computer-aided screening of autism spectrum disorder: Eye-tracking study using data visualization and deep learning. JMIR Human Factors, 8(4), e27706. https://doi.org/10.2196/27706

Di Sarno, L., Caroselli, A., Tonin, G., Graglia, B., Pansini, V., Causio, F.A., Gatto, A., & Chiaretti, A. (2024). Artificial intelligence in pediatric emergency medicine: Applications, challenges, and future perspectives. Biomedicines, 12(6), 1220. https://doi.org/10.33

90/biomedicines12061220

Farooq, M.S., Tehseen, R., Sabir, M., & Atal, Z. (2023). Detection of autism spectrum disorder (ASD) in children and adults using machine learning. Scientific Reports, 13(1), 1-13. https://doi. org/10.1038/s41598-023-35910-1

Fleischmann-Struzek, C., Goldfarb, D.M., Schlattmann, P., Schlapbach, L.J., Reinhart, K., & Kissoon, N. (2018). The global burden of paediatric and neonatal sepsis: A systematic review.

The Lancet Respiratory Medicine, 6(3), 223-230. https://doi.org/

10.1016/S2213-2600(18)30063-8

Ghomrawi, H.M.K., O’Brien, M.K., Carter, M., Macaluso, R., Khazanchi, R., Fanton, M., DeBoer, C., Linton, S.C., Zeineddin, S., Pitt, J.B., Bouchard, M., Figueroa, A., Kwon, S., Holl, J.L., Jayaraman, A., & Abdullah, F. (2023). Applying machine learning to consumer wearable data for the early detection of complica-

tions after pediatric appendectomy. Nature Partner Journal

Digital Medicine, 6(1), 1-12. https://doi.org/10.1038/s41746-023-

00890-z

Goldstein, B., Giroir, B., & Randolph, A. (2005). International pediatric sepsis consensus conference: Definitions for sepsis and organ dysfunction in pediatrics. Pediatric Critical Care Medicine, 6(1), 2-8. https://doi.org/10.1097/01.PCC.0000149131.72248.E6

Krbec, B.A., Zhang, X., Chityat, I., Brady-Mine, A., Linton, E., Copeland, D., Anthony, B.W., Edelman, E.R., & Davis, J.M. (2024). Emerging innovations in neonatal monitoring: A comprehensive review of progress and potential for non-contact technologies. Frontiers in Pediatrics, 12. https://doi.org/10.3389/ fped.2024.1442753

Meng, F., Li, F., Wu, S., Yang, T., Xiao, Z., Zhang, Y., Liu, Z., Lu, J., & Luo, X. (2023). Machine learning-based early diagnosis of autism according to eye movements of real and artificial faces scanning.

Frontiers in Neuroscience, 17, Article 1170951. https://doi.org/

10.3389/fnins.2023.1170951

Ramgopal, S., Sanchez-Pinto, L.N., Horvat, C.M., Carroll, M.S., Luo, Y., & Florin, T.A. (2022). Artificial intelligence-based clinical decision support in pediatrics. Pediatric Research, 93(2), 334-341. https://doi.org/10.1038/s41390-022-02226-1

Rust, L.O.H., Gorham, T.J., Bambach, S., Bode, R.S., Maa, T., Hoffman, J.M., & Rust, S.W. (2023). The Deterioration Risk Index: Developing and piloting a machine learning algorithm to reduce pediatric inpatient deterioration. Pediatric Critical Care Medicine,

24(4), 322-333. https://doi.org/10.1097/PCC.0000000000003

186

Seol, H.Y., Shrestha, P., Muth, J.F., Wi, I., Sohn, S., Ryu, E., Park, M., Ihrke, K., Moon, S., King, K., Wheeler, P., Borah, B., Moriarty, J., Rosedahl, J., Liu, H., McWilliams, D.B., & Juhn, Y.J. (2021). Artificial intelligence-assisted clinical decision support for childhood asthma management: A randomized clinical trial. PLOS One, 16(8), e0255261. https://doi.org/10.1371/journal.pone.

0255261

Weiss, S.L., Peters, M.J., Alhazzani, W., Agus, M.S.D., Flori, H.R., Inwald, D.P., Nadel, S., Schlapbach, L.J., Tasker, R.C., Argent, A.C., Brierley, J., Carcillo, J., Carrol, E.D., Carroll, C.L., Cheifetz,

I.M., Choong, K., Cies, J.J., Cruz, A.T., De Luca, D., ... Tissieres, P. (2020). Surviving sepsis campaign international guidelines for the management of septic shock and sepsis-associated organ dysfunction in children. Pediatric Critical Care Medicine, 21(2), e52-e106. https://doi.org/10.1097/PCC.0000000000002198

Welch, V., Wy, T.J., Ligezka, A., Hassett, L.C., Croarkin, P.E., Athreya, A.P., & Romanowicz, M. (2022). The role of artificial intelligence in child and adolescent psychiatry: A scoping review of mobile and wearable technologies. Child and Adolescent Psychiatry and Mental Health, 17(1), 102. https://doi.org/10.2196/33560

206 July-August 2025/Vol. 51/No. 4

Kaylor, B. (2025).  Pediatric Nursing, 51 (4), 203-206. doi: 10.62116/PNJ.2025.51.4.203. PEDIATRIC NURSING/