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

arXiv: https://arxiv.org/abs/2608.06366 · HTML: https://mlsanity.com/paper/2608.06366/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 47 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III](https://mlsanity.com/paper/1907.08322/) (2019)
- [Agentic AI framework for End-to-End Medical Data Inference](https://mlsanity.com/paper/2507.18115/) (2025)
- [One VLM, Two Roles: Stage-Wise Routing and Specialty-Level Deployment for Clinical Workflows](https://mlsanity.com/paper/2508.16839/) (2025)
- [An Information Extraction Approach to Prescreen Heart Failure Patients for Clinical Trials](https://mlsanity.com/paper/1609.01594/) (2016)
- [Automatic Construction of Clinical Scoring Systems with LLM Agents](https://mlsanity.com/paper/2601.22324/) (2026)

## Abstract (arXiv)

Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists' workload. This is especially pronounced in heart failure, which affects an estimated 6.7 million U.S. adults and requires integrating fragmented EHR data with disease-specific, guideline-based clinical reasoning. Existing rule-based and large language model (LLM)-based approaches offer only partial automation with limited maintainability and evidence traceability. We developed the Nimblemind Multi-Agent System (nMAS), an evidence-linked, rubric-grounded pipeline for automated heart-failure feature engineering, and evaluated it on 500 dummy patient records from nine EHR source tables. nMAS generated 132 structured and 70 rubric-scored aggregated features, verified for structural integrity, rubric compliance, and provenance, and audited by a restricted LLM. Adding the aggregated features improved held-out AUROC from 0.895 to 0.963 for HFrEF and 0.870 to 0.910 for HFpEF phenotyping, and an independent LLM-based rubric assessment of evidence support and methodological soundness scored the features at 81.5% of maximum points. These results demonstrate the feasibility of automated, auditable feature engineering for complex cardiovascular EHR data, though evaluation was limited to a single-institution cohort and external validation is needed.