🛰️ Daily AI Frontier
‹ back to 2026-08-07

Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering

Research Medical/Healthcare AI

Ranking

Overall 64
Content 75
Popularity 39

Observed public metrics from 1 member.

Representative image for Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering

Merged summary

TL;DR - An arXiv preprint presenting nMAS, a multi-agent LLM pipeline that automates evidence-linked, rubric-grounded feature engineering from EHR data for heart-failure phenotyping. It matters because feature engineering consumes 39–45% of data scientists' workload, and this approach adds auditability and provenance that rule-based or plain-LLM methods lack.

  • Evaluated on 500 dummy patient records spanning nine EHR source tables; produced 132 structured features and 70 rubric-scored aggregated features, checked for structural integrity, rubric compliance, and provenance, with a restricted LLM performing the audit.
  • Adding aggregated features raised held-out AUROC from 0.895 → 0.963 (HFrEF) and 0.870 → 0.910 (HFpEF).
  • An independent LLM rubric assessment of evidence support and methodological soundness scored the features at 81.5% of maximum points.
  • Limitations stated by the authors: single-institution cohort and dummy records only; external validation still needed.

Sources (1)

Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering

arXiv cs.AI Soorya Ram Shimgekar, Michelle Hu, Dorisa Shehi, Daniel Kang, Roy Ka-Wei Lee, Koustuv Saha, Christian Poellabauer, Christopher Lee, Sajeev Singh, Piyum Zonooz, Navin Kumar, Zeeshan Ahmed, Priyadarshini Kachroo 2026-08-06 arXiv:2608.06366
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-08-31 14:25:44.766782 UTC

TL;DR - An arXiv preprint presenting nMAS, a multi-agent LLM pipeline that automates evidence-linked, rubric-grounded feature engineering from EHR data for heart-failure phenotyping. It matters because feature engineering consumes 39–45% of data scientists' workload, and this approach adds auditability and provenance that rule-based or plain-LLM methods lack.

  • Evaluated on 500 dummy patient records spanning nine EHR source tables; produced 132 structured features and 70 rubric-scored aggregated features, checked for structural integrity, rubric compliance, and provenance, with a restricted LLM performing the audit.
  • Adding aggregated features raised held-out AUROC from 0.895 → 0.963 (HFrEF) and 0.870 → 0.910 (HFpEF).
  • An independent LLM rubric assessment of evidence support and methodological soundness scored the features at 81.5% of maximum points.
  • Limitations stated by the authors: single-institution cohort and dummy records only; external validation still needed.
item →