AI Paper Atlas

Research map / Large language models / AI and society

Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors' Reasoning with Deep Reinforcement Learning

Arsene Fansi Tchango, Rishab Goel, Julien Martel, Zhi Wen, Gaetan Marceau Caron, Joumana Ghosn

NeurIPS 2022 · Large language models › AI and society · approach: AI for health and public decisions

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Train to predict the differential instead of only the ground truth pathologyCASANDE · DDXPlus testDDF1: 30.84 -> 94.24Improved
Use CASANDE instead of Diaformer when trained with differentialCASANDE · DDXPlus testDDF1: 83.3 -> 94.24Improved
Use CASANDE instead of the best baseline when trained with differentialCASANDE · DDXPlus testDSHM: 69.43 -> 73.88Improved
Use CASANDE instead of AARLCCASANDE · DDXPlus testPER: 54.55 -> 98.39Improved
Use CASANDE instead of BASD, which has shorter interactionsCASANDE · DDXPlus testinteraction length: 17.86 -> 19.71Hurt
Train AARLC with differential versus withoutAARLC · DDXPlus testPER: 32.78 -> 54.55Improved
Train BASD with differential versus withoutBASD · DDXPlus testPER: 88.45 -> 88.18No clear effect
Add all rewards but remove classification reward R_Cl (ablation)CASANDE · DDXPlus validationDSHM: 73.55 -> 74.19Improved
Add exploration, confirmation and severity rewards (ablation)CASANDE · DDXPlus validationDDF1: 93.11 -> 94.26Improved
Add only classification reward R_Cl (ablation)CASANDE · DDXPlus validationDDF1: 93.11 -> 93.48No clear effect
Add exploration and confirmation rewards (ablation)CASANDE · DDXPlus validationinteraction length: 17.56 -> 19.71Mixed
Add severity reward R_Sev (ablation)CASANDE · DDXPlus validationDSHMImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy