ACuTE Patient State

ACuTE (Acute patient state) research focuses on improving the understanding and management of critical patient conditions by analyzing complex, high-dimensional clinical data. Current efforts involve developing advanced algorithms, such as self-supervised learning methods and 3D convolutional neural networks, to identify distinct physiological states from time-series data and medical images (e.g., for stroke lesion segmentation). These advancements aim to enhance diagnostic accuracy, personalize treatment strategies, and improve risk prediction, particularly in areas like traumatic brain injury and oncology, leveraging both structured and unstructured clinical data (e.g., through natural language processing). The ultimate goal is to facilitate more timely and effective interventions for acutely ill patients.

Papers

November 14, 2023

GPT-4V(ision) Unsuitable for Clinical Care and Education: A Clinician-Evaluated Assessment
Senthujan Senkaiahliyan, Augustin Toma, Jun Ma, An-Wen Chan, Andrew Ha, Kevin R. An, Hrishikesh Suresh, Barry Rubin, Bo Wang
Medical Image Large Multimodal Model Education Domain Imaging Modality Clinical Assessment ACuTE Patient State

March 23, 2023

Identifying TBI Physiological States by Clustering Multivariate Clinical Time-Series Data
Hamid Ghaderi, Brandon Foreman, Amin Nayebi, Sindhu Tipirneni, Chandan K. Reddy, Vignesh Subbian
Multivariate Time Series Data Dynamic Clustering Traumatic Brain Injury Physiological State ACuTE Patient State

January 17, 2023

Acute ischemic stroke lesion segmentation in non-contrast CT images using 3D convolutional neural networks
A. V. Dobshik, S. K. Verbitskiy, I. A. Pestunov, K. M. Sherman, Yu. N. Sinyavskiy, A. A. Tulupov, V. B. Berikov
3D Convolutional 3D Brain Non Contrast Volumetric Segmentation Ischemic Stroke Ischemic Stroke Lesion Segmentation ACuTE Patient State

September 28, 2022

Natural Language Processing Methods to Identify Oncology Patients at High Risk for Acute Care with Clinical Notes
Claudio Fanconi, Marieke van Buchem, Tina Hernandez-Boussard
Natural Language Processing Natural Language Processing Model Clinical Note Risk Prediction Cancer Patient Structured Clinical High Risk ACuTE Patient State

April 11, 2022

ACuTE: Automatic Curriculum Transfer from Simple to Complex Environments
Yash Shukla, Christopher Thierauf, Ramtin Hosseini, Gyan Tatiya, Jivko Sinapov
Reinforcement Learning Complex Environment Robot Simulation Curriculum Generation ACuTE Patient State

ACuTE Patient State

Papers

GPT-4V(ision) Unsuitable for Clinical Care and Education: A Clinician-Evaluated Assessment

Identifying TBI Physiological States by Clustering Multivariate Clinical Time-Series Data

Acute ischemic stroke lesion segmentation in non-contrast CT images using 3D convolutional neural networks

Natural Language Processing Methods to Identify Oncology Patients at High Risk for Acute Care with Clinical Notes

ACuTE: Automatic Curriculum Transfer from Simple to Complex Environments