← Back to all news
arXiv Machine Learning

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

The paper investigates the causal impact of the symptom "chest pain" on medical diagnosis predictions, moving beyond traditional correlation-based methods. Using the CausaLM framework, the authors generate counterfactual text representations that effectively remove the symptom, allowing for a principled estimation of its causal effect on disease predictions. They apply Textual Representation-based Average Treatment Effect (TReATE) to quantify how the presence or absence of chest pain shapes diagnostic outcomes, and compare these results to correlation-based baselines such as CONEXP, providing deeper insight into the decision-making behavior of clinical NLP models.

Related stories

arXiv AI
Sep 2

Medical Causal Hypothesis Verification with Large Language Models

The paper "Medical Causal Hypothesis Verification with Large Language Models" reports a small-scale study evaluating eight LLMs on 17 medical causal hypotheses. The authors introduce an evaluation framework and annotate 1,067 evidence points across six criteria, using nine metrics to assess performance. Results show that while LLMs have strong recall, they frequently fail to provide valid scientific articles, evidence, or reject unsupported hypotheses, revealing a critical limitation for their use in healthcare.

By Safiyyah Ahmed, Abrar Ansari, Md Aminul Islam, Elena Zheleva
llms
More like this →
arXiv Machine Learning
Aug 5

Causal Inference with Unstructured Outcomes

arXiv:2608. 03085v1 Announce Type: cross Abstract: Causal inference has traditionally centered on scalar outcomes: whether a patient recovers, how much a worker earns, or how many visits a website receives.

By Kevin Christian Wibisono, Yixin Wang
More like this →
arXiv Machine Learning
Oct 16

Supervised Learning Objectives for High-Dimensional Treatment Effects

The paper proposes supervised learning objectives for estimating causal effects of high‑dimensional treatments, such as text or continuous variables, by recasting causal inference as a learning problem under realizability and no unobserved confounding. It shows that causal error can be decomposed into moment‑balancing errors of increasing order and designs objectives that directly improve causal estimation by exploiting the structure of conditional outcomes. The authors also demonstrate how to project high‑dimensional treatment effects onto coarser attributes, enabling a single model to answer multiple causal questions without extra attribute‑specific training, and validate their approach empirically across continuous, discrete, and text treatments.

By Nikita Dhawan, Arnav Paruthi, Andrew Kim, Lovedeep Gondara, Jekaterina Novikova, Chris J. Maddison
More like this →
arXiv Machine Learning
Oct 7

Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence

The paper introduces BAR, a Budget‑Aware LLM Reasoning framework that enhances post‑discharge risk prediction by integrating external medical knowledge graphs (KGs). BAR refines KGs into disease‑specific evidence graphs with support scores and provenance, then uses an LLM to plan, navigate, and verify evidence within a patient‑specific budget. Experiments on MIMIC‑III and MIMIC‑IV across eight diseases show BAR improves AUPRC by 3.4 points, raises citation precision from 59.8% to 77.9%, and uses only 62‑65% of the allotted budget.

By Chen Chen, Dongjie Wang, Mei Liu, Zijun Yao
llms
More like this →