Development of an Artificial Intelligence–Guided Citizen-Centric Predictive Model for the Uptake of Maternal Health Services Among Pregnant Women Living in Urban Slum Settings in India: Protocol for a Cross-sectional Study With a Mixed Methods Design
Bibliographic record
Abstract
BACKGROUND: Pregnant women are considered a "high-risk" group with limited access to health facilities in urban slums in India. Barriers to using health services appropriately may lead to maternal and child mortality, morbidity, low birth weight, and children with stunted growth. With the increase in the use of artificial intelligence (AI) and machine learning in the health sector, we plan to develop a predictive model that can enable substantial uptake of maternal health services and improvements in adverse pregnancy health care outcomes from early diagnostics to treatment in urban slum settings. OBJECTIVE: The objective of our study is to develop and evaluate the AI-guided citizen-centric platform that will support the uptake of maternal health services among pregnant women seeking antenatal care living in urban slum settings. METHODS: We will conduct a cross-sectional study using a mixed methods approach to enroll 225 pregnant women aged 18-44 years, living in the urban slums of Delhi for more than 6 months, seeking antenatal care, and who have smartphones. Quantitative and qualitative data will be collected using an Open Data Kit Android-based tool. Variables gathered will include sociodemographics, clinical history, pregnancy history, dietary history, COVID-19 history, health care facility data, socioeconomic status, and pregnancy outcomes. All data gathered will be aggregated into a common database. We will use AI to predict the early at-risk pregnancy outcomes (in terms of the type of delivery method, term, and related complications) depending on the needs of the beneficiaries translating into effective service-delivery improvements in enhancing the use of maternal health services among pregnant women seeking antenatal care. The proposed research will help policy makers to prioritize resource planning, resource allocation, and the development of programs and policies to enhance maternal health outcomes. The academic research study has received ethical approval from the University Research Ethics Committee of Dehradun Institute of Technology (DIT) University, Dehradun, India. RESULTS: The study was approved by the University Research Ethics Committee of DIT University, Dehradun, on July 4, 2021. Enrollment of the eligible participants will begin by April 2022 followed by the development of the predictive model by October 2022 till January 2023. The proposed AI-guided citizen-centric tool will be designed, developed, implemented, and evaluated using principles of human-centered design that will help to predict early at-risk pregnancy outcomes. CONCLUSIONS: The proposed internet-enabled AI-guided prediction model will help identify the potential risk associated with pregnancies and enhance the uptake of maternal health services among those seeking antenatal care for safer deliveries. We will explore the scalability of the proposed platform up to different geographic locations for adoption for similar and other health conditions. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/35452.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.027 | 0.028 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.004 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.011 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".