An agentic AI- and n8n automation-powered maternal care framework with predictive pregnancy monitoring and continuous learning.
- 1School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India.
- 2Department of Electrical and Electronic Engineering, UCSI University, Kuala Lumpur, Malaysia.
Abstract
Conventional maternal remote patient monitoring has relied upon using immutable ranges for detection of conditions on maternal telemetry. However, this has created extreme alert fatigue in clinicians. The newly proposed Agentic AI Maternal Triage Framework combines patient-reported outcome data with quantitative telemetry values to deliver real-time, context-aware decisions regarding risk stratification to both the clinician and patient. The triage workloads are processed in an orchestrated manner via n8n, utilizing light gradient boosting machine models to determine the likelihood that the maternal telemetry is showing that the patient is developing cardiovascular or metabolic risks. The models produce continuous risk scores that are consumed by a retrieval-augmented generation-powered Google Gemini large language model to yield structured triaged outputs. The triage outputs are delivered to a conversational agent for low-risk patients and a physician for high-risk patients using a triage model of escalation. To allow for continued learning, expert validation is captured via stateless webhooks. In the simulation-based evaluation, the predictive models achieved classification metrics above 99.8%; however, these results reflect the controlled synthetic data-generating environment and do not establish clinical validity. The framework therefore represents a technical proof of concept for integrating predictive modeling, retrieval-grounded generative reasoning, context-aware routing, and human-in-the-loop feedback, with external clinical validation required before real-world deployment.
Related
- Continuous glucose monitoring after discontinuation of incretin-based obesity pharmacotherapy: indirect evidence and a research framework for metabolic stability and weight maintenance
- Explainable machine learning framework with Granger-based temporal predictive validation for monitoring fiscal risk in national health insurance expenditure
- A Secure IoT-Blockchain Framework for Vaccine Cold-Chain Monitoring With Predictive Analytics.
- Camus: a video-based framework for continuous behavioral monitoring in the mouse home-cage
- Low-voltage, ultra-broadband wearable MEMS ultrasound: a frequency-merged, wafer-scale framework for continuous in vivo cardiovascular imaging and monitoring.
BibTeX
@article{thippa2026agentic,
title = {{An agentic AI- and n8n automation-powered maternal care framework with predictive pregnancy monitoring and continuous learning.}},
author = {Subhash Thippa and Nagesparan Ainarappan and R Suganya},
journal = {Frontiers in digital health},
year = {2026},
month = oct,
doi = {10.3389/fdgth.2026.1840650},
url = {https://europepmc.org/article/MED/42898328},
note = {CC BY},
}
RIS
TY - JOUR
TI - An agentic AI- and n8n automation-powered maternal care framework with predictive pregnancy monitoring and continuous learning.
AU - Subhash Thippa
AU - Nagesparan Ainarappan
AU - R Suganya
PY - 2026
DA - 2026/10/05
JO - Frontiers in digital health
DO - 10.3389/fdgth.2026.1840650
UR - https://europepmc.org/article/MED/42898328
AB - Conventional maternal remote patient monitoring has relied upon using immutable ranges for detection of conditions on maternal telemetry. However, this has created extreme alert fatigue in clinicians. The newly proposed Agentic AI Maternal Triage Framework combines patient-reported outcome data with quantitative telemetry values to deliver real-time, context-aware decisions regarding risk stratification to both the clinician and patient. The triage workloads are processed in an orchestrated manner via n8n, utilizing light gradient boosting machine models to determine the likelihood that the maternal telemetry is showing that the patient is developing cardiovascular or metabolic risks. The models produce continuous risk scores that are consumed by a retrieval-augmented generation-powered Google Gemini large language model to yield structured triaged outputs. The triage outputs are delivered to a conversational agent for low-risk patients and a physician for high-risk patients using a triage model of escalation. To allow for continued learning, expert validation is captured via stateless webhooks. In the simulation-based evaluation, the predictive models achieved classification metrics above 99.8%; however, these results reflect the controlled synthetic data-generating environment and do not establish clinical validity. The framework therefore represents a technical proof of concept for integrating predictive modeling, retrieval-grounded generative reasoning, context-aware routing, and human-in-the-loop feedback, with external clinical validation required before real-world deployment.
SN - 2673-253X
ER -