# How Compliant is Sepsis Treatment? An Expert-Guided Neuro-symbolic Pipeline for Generating Clinical Compliance Insights

arXiv: https://arxiv.org/abs/2608.13617 · HTML: https://mlsanity.com/paper/2608.13617/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 29 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Builds on (most cited first, 7 of 7)

- [ClinicalGPT: Large Language Models Finetuned with Diverse Medical Data and Comprehensive Evaluation](https://mlsanity.com/paper/2306.09968/) (2023)
- [An Extensive Data Processing Pipeline for MIMIC-IV](https://mlsanity.com/paper/2204.13841/) (2022)
- [Neuro-symbolic representation learning on biological knowledge graphs](https://mlsanity.com/paper/1612.04256/) (2016)
- [CHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models](https://mlsanity.com/paper/2302.12343/) (2023)
- [K-Diag: Knowledge-enhanced Disease Diagnosis in Radiographic Imaging](https://mlsanity.com/paper/2302.11557/) (2023)
- [Neurosymbolic AI for Reasoning on Biomedical Knowledge Graphs](https://mlsanity.com/paper/2307.08411/) (2023)
- [CLIN-LLM: A Safety-Constrained Hybrid Framework for Clinical Diagnosis and Treatment Generation](https://mlsanity.com/paper/2510.22609/) (2025)

## Abstract (arXiv)

Verifying whether clinical care follows evidence-based protocols is a natural neuro-symbolic problem, yet the safety-critical setting defeats either paradigm alone. We present an expert-guided pipeline that constrains a large language model strictly to semantic normalization, mapping messy drug and microbiology strings onto a fixed clinical vocabulary, while a Sugeno fuzzy inference system reasons over the normalized events. The fuzzy layer encodes eight Surviving Sepsis Campaign bundle rules and replaces binary judgments with graded scores in [0,1]. Applied to 2,438 MIMIC-IV v3.1 sepsis episodes, it surfaces antibiotic timing as the most critical breakdown (mean 0.24, 13% within one hour), Hour-1 underperformance (mean 36.7%), a 51% elevated-lactate drop-off, and descriptive differences in ICU stay across compliance groups (3.8 versus 5.1 days).