# DiagnoLLM: A Hybrid Bayesian Neural Language Framework for Interpretable Disease Diagnosis

arXiv: https://arxiv.org/abs/2511.05810 · HTML: https://mlsanity.com/paper/2511.05810/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 49 references that are in the map.
- First posted on arXiv 8 Nov 2025.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [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)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks](https://mlsanity.com/paper/2206.06565/) (2022)
- [JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation](https://mlsanity.com/paper/2509.22548/) (2025)
- [VisRL: Intention-Driven Visual Perception via Reinforced Reasoning](https://mlsanity.com/paper/2503.07523/) (2025)
- [BALF: Simple and Efficient Blur Aware Local Feature Detector](https://mlsanity.com/paper/2211.14731/) (2022)
- [Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models](https://mlsanity.com/paper/2505.16122/) (2025)
- [NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoning](https://mlsanity.com/paper/2404.00459/) (2024)
- [Understanding the Dynamics of DNNs Using Graph Modularity](https://mlsanity.com/paper/2111.12485/) (2021)
- [Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information](https://mlsanity.com/paper/2410.04463/) (2024)
- [FlowMalTrans: Unsupervised Binary Code Translation for Malware Detection Using Flow-Adapter Architecture](https://mlsanity.com/paper/2508.20212/) (2025)
- [LUNA: Language Understanding with Number Augmentations on Transformers via Number Plugins and Pre-training](https://mlsanity.com/paper/2212.02691/) (2022)
- [scInterpreter: Training Large Language Models to Interpret scRNA-seq Data for Cell Type Annotation](https://mlsanity.com/paper/2402.12405/) (2024)
- [Application of Deep Learning on Single-Cell RNA-sequencing Data Analysis: A Review](https://mlsanity.com/paper/2210.05677/) (2022)
- [DISPROTBENCH: Uncovering the Functional Limits of Protein Structure Prediction Models in Intrinsically Disordered Regions](https://mlsanity.com/paper/2507.02883/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Deterministic Evidence Layer for Vision-Language Autism Screening from Naturalistic Home Video](https://mlsanity.com/paper/2610.09217/) (2026)

## Abstract (arXiv)

Building trustworthy clinical AI systems requires not only accurate predictions but also transparent, biologically grounded explanations. We present textttDiagnoLLM, a hybrid framework that integrates Bayesian deconvolution, eQTL-guided deep learning, and LLM-based narrative generation for interpretable disease diagnosis. DiagnoLLM begins with GP-unmix, a Gaussian Process-based hierarchical model that infers cell-type-specific gene expression profiles from bulk and single-cell RNA-seq data while modeling biological uncertainty. These features, combined with regulatory priors from eQTL analysis, power a neural classifier that achieves high predictive performance in Alzheimer's Disease (AD) detection (88.0% accuracy). To support human understanding and trust, we introduce an LLM-based reasoning module that translates model outputs into audience-specific diagnostic reports, grounded in clinical features, attribution signals, and domain knowledge. Human evaluations confirm that these reports are accurate, actionable, and appropriately tailored for both physicians and patients. Our findings show that LLMs, when deployed as post-hoc reasoners rather than end-to-end predictors, can serve as effective communicators within hybrid diagnostic pipelines.