Artificial intelligence–enabled nursing surveillance for pediatric cancer immunotherapy: integrating biomarkers, patient-reported outcomes, and long-term toxicity management
- 1Department of Pediatrics, The First People’s Hospital of Guangyuan , , ,
- 2Department of Gynecology, The First People’s Hospital of Guangyuan , , ,
Abstract
Pediatric cancer immunotherapy has expanded from anti-GD2 antibodies and bispecific T-cell engagers to immune checkpoint inhibitors and chimeric antigen receptor T-cell therapy. These treatments can produce rapid, nonlinear, and partially overlapping toxicities, including cytokine release syndrome, immune effector cell-associated neurotoxicity syndrome, infection, prolonged cytopenia, B-cell aplasia, and organ-specific immune-related adverse events. Nurses provide the highest-frequency clinical observations across inpatient, ambulatory, and home settings, yet conventional monitoring often fragments laboratory data, vital signs, neurologic findings, caregiver observations, and patient-reported outcomes. Artificial intelligence (AI) offers a means to fuse these longitudinal signals into individualized risk trajectories. The clinically relevant mechanism, however, is not autonomous prediction; it is a nurse-in-the-loop system in which AI improves temporal sensitivity and prioritization, while nurses verify signal quality, interpret age- and development-specific context, reconcile child–caregiver discordance, activate protocol-based escalation, and maintain accountability. This Mini Review examines how biomarkers, continuous physiological monitoring, electronic patient-reported outcomes, and caregiver-reported behavioral changes can support AI-enabled nursing surveillance during acute immunotoxicity and long-term survivorship. We propose a three-layer framework linking immune-toxicity biology, a multimodal digital phenotype, and nursing counter-regulation. We also discuss workflow integration, alert fatigue, model drift, bias, privacy, and the need for prospective pediatric validation. AI should augment not replace specialist pediatric oncology nursing judgment and should be evaluated by whether it improves timely intervention, symptom burden, family experience, and long-term safety.
Related
- Toward Precision Colorectal Cancer Screening: Integrating Clinical Risk Stratification, Molecular Biomarkers, and Artificial Intelligence
- Single-cell RNA sequencing combined with artificial intelligence to uncover immunotherapy biomarkers and decipher drug resistance mechanisms in glioblastoma.
- Multimodal biomarkers for early detection and immunotherapy assessment in hepatocellular carcinoma: integrating liquid biopsy, AI-based imaging and tumor immune profiling.
- Vulnerable Coronary Plaques on CT Angiography: Imaging Biomarkers, Artificial Intelligence, and Emerging Technologies for Risk Stratification
- From Pattern Recognition to Decision Guidance: Artificial Intelligence in Interstitial Lung Disease Diagnosis and Surveillance
BibTeX
@article{peng2026artificial,
title = {{Artificial intelligence–enabled nursing surveillance for pediatric cancer immunotherapy: integrating biomarkers, patient-reported outcomes, and long-term toxicity management}},
author = {Yi Peng and Qiong Kou and Sihong Guo and Jia Xu and Lijuan Wang and Xiaoyan Chen},
journal = {Frontiers in medicine},
year = {2026},
month = oct,
doi = {10.3389/fmed.2026.1976674},
url = {https://europepmc.org/article/PMC/PMC13720359},
note = {CC BY},
}
RIS
TY - JOUR
TI - Artificial intelligence–enabled nursing surveillance for pediatric cancer immunotherapy: integrating biomarkers, patient-reported outcomes, and long-term toxicity management
AU - Yi Peng
AU - Qiong Kou
AU - Sihong Guo
AU - Jia Xu
AU - Lijuan Wang
AU - Xiaoyan Chen
PY - 2026
DA - 2026/10/16
JO - Frontiers in medicine
DO - 10.3389/fmed.2026.1976674
UR - https://europepmc.org/article/PMC/PMC13720359
AB - Pediatric cancer immunotherapy has expanded from anti-GD2 antibodies and bispecific T-cell engagers to immune checkpoint inhibitors and chimeric antigen receptor T-cell therapy. These treatments can produce rapid, nonlinear, and partially overlapping toxicities, including cytokine release syndrome, immune effector cell-associated neurotoxicity syndrome, infection, prolonged cytopenia, B-cell aplasia, and organ-specific immune-related adverse events. Nurses provide the highest-frequency clinical observations across inpatient, ambulatory, and home settings, yet conventional monitoring often fragments laboratory data, vital signs, neurologic findings, caregiver observations, and patient-reported outcomes. Artificial intelligence (AI) offers a means to fuse these longitudinal signals into individualized risk trajectories. The clinically relevant mechanism, however, is not autonomous prediction; it is a nurse-in-the-loop system in which AI improves temporal sensitivity and prioritization, while nurses verify signal quality, interpret age- and development-specific context, reconcile child–caregiver discordance, activate protocol-based escalation, and maintain accountability. This Mini Review examines how biomarkers, continuous physiological monitoring, electronic patient-reported outcomes, and caregiver-reported behavioral changes can support AI-enabled nursing surveillance during acute immunotoxicity and long-term survivorship. We propose a three-layer framework linking immune-toxicity biology, a multimodal digital phenotype, and nursing counter-regulation. We also discuss workflow integration, alert fatigue, model drift, bias, privacy, and the need for prospective pediatric validation. AI should augment not replace specialist pediatric oncology nursing judgment and should be evaluated by whether it improves timely intervention, symptom burden, family experience, and long-term safety.
SN - 2296-858X
ER -