Perspective on AI-Driven High-Risk Pregnancy Prediction and Safeguards

A 2026 perspective article by Qingqing Ji synthesizes evidence on AI-based obstetric risk prediction, prenatal screening impacts, and digital health governance principles. The 18.2 KB document examines how risk labeling can increase anxiety and discrimination, proposing integrated safeguards for future deployments.

Use Cases

• Analyze the discussion of AI-based obstetric risk prediction tools and their reliance on clinical records and physiologic signals.
• Extract proposed safeguards like transparent model documentation and continuous fairness monitoring for text-based policy analysis.
• Identify discrimination pathways such as biased data labels and defensive clinical escalation for equity-focused research.

Strengths

• Authored by a named researcher (Qingqing Ji) and published in 2026.
• Released under a permissive CC BY 4.0 license for reuse.
• Synthesizes evidence from three distinct domains: AI prediction, prenatal screening, and digital health governance.

Limitations

• The 18.2 KB file is a perspective article, not a structured dataset, limiting quantitative analysis.
• The synthesis is described as non-systematic, which may not represent a complete evidence review.
• No primary data, columns, or sample records are provided for model training or validation.

Provenance

Source

figshare

Collection Method

Targeted, non-systematic narrative synthesis by the author.

Time Range

null

Freshness

null

Geography

null