Patient Level Prediction

Patient-level prediction in healthcare aims to leverage diverse data sources, including electronic health records, medical images, and even patient narratives, to create accurate predictions of individual patient outcomes, such as disease risk, treatment response, or length of stay. Current research emphasizes the use of machine learning, particularly deep learning models and graph neural networks, often incorporating multi-task learning and pre-training techniques to improve prediction accuracy and generalizability across diverse patient populations. These advancements hold significant promise for improving clinical decision-making, optimizing resource allocation, and ultimately enhancing patient care by enabling earlier interventions and more personalized treatment strategies.

Papers

October 21, 2024

A Framework for Evaluating Predictive Models Using Synthetic Image Covariates and Longitudinal Data
Simon Deltadahl, Andreu Vall, Vijay Ivaturi, Niklas Korsbo
New Framework Synthetic Image Predictive Model Optical Coherence Tomography Relevant Covariates Longitudinal Data Longitudinal Analysis Synthetic Health Data Patient Level Prediction

May 5, 2024

Enabling Patient-side Disease Prediction via the Integration of Patient Narratives
Zhixiang Su, Yinan Zhang, Jiazheng Jing, Jie Xiao, Zhiqi Shen
Disease Prediction Clinical Narrative Patient Level Prediction

May 25, 2023

Patient Outcome Predictions Improve Operations at a Large Hospital Network
Liangyuan Na, Kimberly Villalobos Carballo, Jean Pauphilet, Ali Haddad-Sisakht, Daniel Kombert, Melissa Boisjoli-Langlois, Andrew Castiglione, Maram Khalifa, Pooja Hebbal, Barry Stein, Dimitris Bertsimas
Economic Operation Discharge Summary Patient Outcome Prediction Patient Level Prediction

March 23, 2022

Unsupervised Pre-Training on Patient Population Graphs for Patient-Level Predictions
Chantal Pellegrini, Anees Kazi, Nassir Navab
Pre Training Graph Transformer Unsupervised Pre Training Patient Outcome Prediction Population Graph Patient Level Prediction

February 25, 2022

Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation
Di Wu, Jie Yang, Mohamad Sawan
Knowledge Distillation Seizure Detection Patient Specific Seizure Prediction Patient Level Prediction

December 1, 2021

Multi-task fusion for improving mammography screening data classification
Maria Wimmer, Gert Sluiter, David Major, Dimitrios Lenis, Astrid Berg, Theresa Neubauer, Katja Bühler
Deep Learning Model Task Specific Model Mammography Report Multi Branch Multi Task Fusion Patient Level Prediction

Patient Level Prediction

Papers

A Framework for Evaluating Predictive Models Using Synthetic Image Covariates and Longitudinal Data

Enabling Patient-side Disease Prediction via the Integration of Patient Narratives

Patient Outcome Predictions Improve Operations at a Large Hospital Network

Unsupervised Pre-Training on Patient Population Graphs for Patient-Level Predictions

Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation

Multi-task fusion for improving mammography screening data classification