PANDIA: Infant Pain Assessment Performance Metrics

Performance analysis data for the PANDIA AI system, which assesses pain in infants aged 0–3 months. The dataset likely contains evaluation metrics from a study involving 2,847 infants across four datasets. The system was developed by Oussama El Othmani and results were published in 2026.

Use Cases

• Benchmarking edge-deployed AI models based on reported accuracy and parameter count.
• Analyzing clinician acceptance rates for AI explanations based on the reported 92.1% acceptance metric.
• Studying federated learning performance for multi-site clinical collaboration as described in the system.
• Evaluating meta-learning adaptation for personalized assessment with minimal per-patient data.

Strengths

• Evaluation involves 2,847 infants, providing a substantial sample size.
• System achieved 87.3% accuracy and a 12.4% improvement over baselines.
• Model has fewer than 30M parameters, suitable for edge deployment.
• Code, models, and pipelines are fully publicly available.

Limitations

• Dataset heterogeneity across collection sites is noted as a limitation.
• Validation design is retrospective, requiring prospective clinical trials.
• Row count and column-level documentation are unknown, limiting suitability assessment.

Provenance

Source

Oussama El Othmani

Collection Method

Likely derived from the evaluation of the PANDIA AI system on four infant pain datasets.

Freshness

Last updated 2026-05-26 17:32:11