AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

INSPECT: A Multimodal Dataset for Pulmonary Embolism Diagnosis and Prognosis

Shih-Cheng Huang, Zepeng Huo, Ethan Steinberg, Chia-Chun Chiang, Matthew P. Lungren, Curtis Langlotz, Serena Yeung, Nigam Shah, Jason Alan Fries

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Medical vision-language models · 9 citations (OpenAlex)

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
add EHR models to CT model by late fusionCT LRCN · INSPECT PE diagnosisAUROC: 0.721 -> 0.771Improved
add CT model to EHR MOTOR by late fusionMOTOR · INSPECT PE diagnosisAUROC: 0.677 -> 0.761Improved
add CT model to MOTOR by late fusionMOTOR · INSPECT mortality 6mAUROC: 0.901 -> 0.903No clear effect
add CT model to MOTOR by late fusionMOTOR · INSPECT re-admission 12mAUROC: 0.767 -> 0.764No clear effect
add CT model to EHR models by late fusionMOTOR+GBT · INSPECT pulmonary hypertension 12mAUROC: 0.849 -> 0.843Hurt
add CT model to MOTOR by late fusionMOTOR · INSPECT mortality 1mAUROC: 0.923 -> 0.924No clear effect
use CT instead of EHR for prognosissingle-modality models · INSPECT mortality 1mAUROC: 0.923 -> 0.794Hurt
use EHR instead of CT for diagnosissingle-modality models · INSPECT PE diagnosisAUROC: 0.721 -> 0.677Hurt

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