Patient Similarity

Patient similarity research aims to identify and quantify relationships between patients based on their medical data, enabling personalized medicine and improved healthcare outcomes. Current approaches leverage diverse data sources and employ machine learning techniques, including graph neural networks, variational autoencoders, and sparse coding methods, often within a framework of graph embedding or low-rank approximations to handle the inherent sparsity and complexity of healthcare data. These methods are being refined to improve accuracy in patient similarity searches, clustering, and predictive modeling tasks, ultimately leading to more effective diagnosis, treatment, and resource allocation. The resulting patient profiles and similarity measures are crucial for developing more precise and efficient healthcare strategies.

Papers

September 20, 2024

A Generative Framework for Predictive Modeling of Multiple Chronic Conditions Using Graph Variational Autoencoder and Bandit-Optimized Graph Neural Network
Julian Carvajal Rico, Adel Alaeddini, Syed Hasib Akhter Faruqui, Susan P Fisher-Hoch, Joseph B Mccormick
Graph Neural Network Predictive Model Generative Framework Variational Graph Predictive Healthcare Patient Similarity

December 21, 2023

WellFactor: Patient Profiling using Integrative Embedding of Healthcare Data
Dongjin Choi, Andy Xiang, Ozgur Ozturk, Deep Shrestha, Barry Drake, Hamid Haidarian, Faizan Javed, Haesun Park
Healthcare Data Latent Embeddings Structured Clinical Patient Similarity

November 24, 2023

AdaMedGraph: Adaboosting Graph Neural Networks for Personalized Medicine
Jie Lian, Xufang Luo, Caihua Shan, Dongqi Han, Varut Vardhanabhuti, Dongsheng Li
Graph Neural Network High Dimensional Feature Personalized Medicine Clinical Prediction Task Patient Similarity

September 8, 2023

PRISM: Leveraging Prototype Patient Representations with Feature-Missing-Aware Calibration for EHR Data Sparsity Mitigation
Yinghao Zhu, Zixiang Wang, Long He, Shiyun Xie, Xiaochen Zheng, Liantao Ma, Chengwei Pan
Electronic Health Record Imputation Method Patient Representation Instance Selection Feature Calibration Patient Similarity

July 22, 2023

Contrastive Self-Supervised Learning Based Approach for Patient Similarity: A Case Study on Atrial Fibrillation Detection from PPG Signal
Subangkar Karmaker Shanto, Shoumik Saha, Atif Hasan Rahman, Mohammad Mehedy Masud, Mohammed Eunus Ali
Contrastive Learning Self Supervised Case Study PPG Signal Physiological Time Series Data Similar Embeddings Atrial Fibrillation Detection Patient Similarity

September 1, 2022

Self-supervised Representation Learning on Electronic Health Records with Graph Kernel Infomax
Hao-Ren Yao, Nairen Cao, Katina Russell, Der-Chen Chang, Ophir Frieder, Jeremy Fineman
Graph Representation Electronic Health Record Self Supervised Representation Learning Graph Kernel Patient Similarity

February 3, 2022

SparGE: Sparse Coding-based Patient Similarity Learning via Low-rank Constraints and Graph Embedding
Xian Wei, See Kiong Ng, Tongtong Zhang, Yingjie Liu
Graph Drawing Many Sparse Similarity Measure Healthcare Datasets Low Rank Constraint Sparse Coding Patient Similarity

Patient Similarity

Papers

A Generative Framework for Predictive Modeling of Multiple Chronic Conditions Using Graph Variational Autoencoder and Bandit-Optimized Graph Neural Network

WellFactor: Patient Profiling using Integrative Embedding of Healthcare Data

AdaMedGraph: Adaboosting Graph Neural Networks for Personalized Medicine

PRISM: Leveraging Prototype Patient Representations with Feature-Missing-Aware Calibration for EHR Data Sparsity Mitigation

Contrastive Self-Supervised Learning Based Approach for Patient Similarity: A Case Study on Atrial Fibrillation Detection from PPG Signal

Self-supervised Representation Learning on Electronic Health Records with Graph Kernel Infomax

SparGE: Sparse Coding-based Patient Similarity Learning via Low-rank Constraints and Graph Embedding