Quantifying Symptom Causality in Clinical Decision Making: An Exploration Using CausaLM

Alexander Romanus; Mehul Shetty; Connor Jordan

cs.LGMar 25, 2025

Quantifying Symptom Causality in Clinical Decision Making: An Exploration Using CausaLM

Authors: Alexander Romanus, Mehul Shetty, Connor Jordan

Abstract

Current machine learning approaches to medical diagnosis often rely on correlational patterns between symptoms and diseases, risking misdiagnoses when symptoms are ambiguous or common across multiple conditions. In this work, we move beyond correlation to investigate the causal influence of key symptoms-specifically "chest pain" on diagnostic predictions. Leveraging the CausaLM framework, we generate counterfactual text representations in which target concepts are effectively "forgotten" enabling a principled estimation of the causal effect of that concept on a model's predicted disease distribution. By employing Textual Representation-based Average Treatment Effect (TReATE), we quantify how the presence or absence of a symptom shapes the model's diagnostic outcomes, and contrast these findings against correlation-based baselines such as CONEXP. Our results offer deeper insight into the decision-making behavior of clinical NLP models and have the potential to inform more trustworthy, interpretable, and causally-grounded decision support tools in medical practice.

Figures & tables

Figure 1: Three causal graphs relating the concepts of symptoms, clinical notes, their representations and distribution output.

Disease	TReATE
Bronchitis	0.2708
Anemia	0.2076
PSVT	0.1339
Myasthenia gravis	0.1214
Acute dystonic reactions	0.0693
…	…

Table 1: TReATE Values

Disease	CONEXP
Bronchitis	0.082
PSVT	0.079
Myocarditis	0.063
…	…
Allergic sinusitis	-0.022
Acute laryngytis	-0.0256

Table 2: CONEXP Values

Clinical Decision-Making

Clinical decision-making studies how evidence, patient preferences, risks, and resource constraints can guide diagnosis, treatment, and care.

See all 130 papers

When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models
Mar 24, 2026Jianxin Lin, Chunzheng Zhu, Peter J. Kneuertz +2Medical VLMs Causal Reasoning in Language Models
The Ohio State University · Hunan University · Amazon
CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation
Apr 12, 2026Elahe Khatibi, Ziyu Wang, Ankita Sharma +4Electrocardiogram Classification Causal Reasoning in Language Models
University of California, Irvine; Irvine, California, United States · Arizona State University; Tempe, Arizona, United States · California State University, Dominguez Hills; Carson, California, United States
Is a 9B Decision Foundation Model Needed for Symptom-to-Disease Classification? Fine-Tuning Clef-Flash Against TF-IDF Baselines
Oct 10, 2026S. M. Mahbub Uddin AhmedMedical Diagnosis Clinical Decision-Making
Department of Computer Science and Engineering, United International University

Mar 24, 2026J/K move · Enter open · S save

When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models

Jianxin Lin, Chunzheng Zhu, Peter J. Kneuertz, Yunfei Bai+1

The Ohio State University · Hunan University · Amazon

Medical VLMs Causal Reasoning in Language Models VLM Hallucination Mitigation Counterfactual Reasoning in Language Models

Open paper AskPDF arXiv

Vision-Language Models (VLMs) have enabled interpretable medical diagnosis by integrating visual perception with linguistic reasoning. Yet, existing medical chain-of-thought (CoT) models lack explicit mechanisms to represent and enforce causal reasoning, leaving them vulnerable to spurious correlations and limiting their clinical reliability. We pinpoint three core challenges in medical CoT reasoning: how to adaptively trigger causal correction, construct high-quality causal-spurious contrastive samples, and maintain causal consistency across reasoning trajectories. To address these challenges, we propose MedCausalX, an end-to-end framework explicitly models causal reasoning chains in medical VLMs. We first introduce the CRMed dataset providing fine-grained anatomical annotations, structured causal reasoning chains, and counterfactual variants that guide the learning of causal relationships beyond superficial correlations. Building upon CRMed, MedCausalX employs a two-stage adaptive reflection architecture equipped with

\langle

causal

\rangle

and

\langle

verify

\rangle

tokens, enabling the model to autonomously determine when and how to perform causal analysis and verification. Finally, a trajectory-level causal correction objective optimized through error-attributed reinforcement learning refines the reasoning chain, allowing the model to distinguish genuine causal dependencies from shortcut associations. Extensive experiments on multiple benchmarks show that MedCausalX consistently outperforms state-of-the-art methods, improving diagnostic consistency by +5.4 points, reducing hallucination by over 10 points, and attaining top spatial grounding IoU, thereby setting a new standard for causally grounded medical reasoning. The code and dataset are available at https://github.com/zhcz328/MedCausalX.

Abstract

Clinical Decision-Making

Explore similar work

When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models

CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation

Is a 9B Decision Foundation Model Needed for Symptom-to-Disease Classification? Fine-Tuning Clef-Flash Against TF-IDF Baselines