Readmission Prediction

Readmission prediction focuses on identifying patients at high risk of re-hospitalization shortly after discharge, aiming to improve patient outcomes and resource allocation. Current research emphasizes the development of sophisticated machine learning models, including graph neural networks, transformers, and large language models, to analyze diverse data sources such as electronic health records (EHRs), including both structured and unstructured data (e.g., clinical notes, vital signs). These models are evaluated using metrics like AUC and recall, with a growing emphasis on explainability and model portability across different healthcare institutions. Improved accuracy in readmission prediction can lead to more effective interventions and ultimately reduce healthcare costs and improve patient safety.

Papers

October 23, 2024

Predicting 30-Day Hospital Readmission in Medicare Patients: Insights from an LSTM Deep Learning Model
Xintao Li, Sibei Liu, Dezhi Yu, Yang Zhang, Xiaoyu Liu
Human Prediction DCU Insight AQ LSTM Network Patient Friendly Language Patient Data LSTM Model Readmission Prediction Hospital Readmission

August 27, 2024

Evaluating the Predictive Features of Person-Centric Knowledge Graph Embeddings: Unfolding Ablation Studies
Christos Theodoropoulos, Natasha Mulligan, Joao Bettencourt-Silva
Graph Neural Network Knowledge Graph Embeddings Ablation Study Predictive Feature Entity Centric Knowledge Readmission Prediction

July 15, 2024

Static and multivariate-temporal attentive fusion transformer for readmission risk prediction
Zhe Sun, Runzhi Li, Jing Wang, Gang Chen, Siyu Yan, Lihong Ma
Temporal Fusion Transformer Readmission Prediction

March 12, 2024

Enhancing Readmission Prediction with Deep Learning: Extracting Biomedical Concepts from Clinical Texts
Rasoul Samani, Mohammad Dehghani, Fahime Shahrokh
Deep Learning Clinical Text Biomedical Concept Readmission Prediction Hospital Readmission Unplanned Readmission Patient Readmission

September 25, 2023

Explainable Machine Learning for ICU Readmission Prediction
Alex G. C. de Sá, Daniel Gould, Anna Fedyukova, Mitchell Nicholas, Lucy Dockrell, Calvin Fletcher, David Pilcher, Daniel Capurro, David B. Ascher, Khaled El-Khawas, Douglas E. V. Pires
Intensive Care Unit Explainable Machine Learning Intensive Care Readmission Prediction Unplanned Readmission Patient Readmission

September 20, 2023

CPLLM: Clinical Prediction with Large Language Models
Ofir Ben Shoham, Nadav Rappoport
Large Language Model Diagnosis Prediction Clinical Prediction Readmission Prediction Hospital Readmission Prediction

May 14, 2023

Predicting Unplanned Readmissions in the Intensive Care Unit: A Multimodality Evaluation
Eitam Sheetrit, Menachem Brief, Oren Elisha
Intensive Care Unit Multimodal Evaluation Readmission Prediction Hospital Readmission Unplanned Readmission

November 13, 2022

Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction
Grace Yang, Ming Cao, Lavender Y. Jiang, Xujin C. Liu, Alexander T. M. Cheung, Hannah Weiss, David Kurland, Kyunghyun Cho, Eric K. Oermann
Language Model XGBoost Model Readmission Prediction Sensitivity Score Lexical Sensitivity Traditional Evaluation Metric

July 26, 2022

When BERT Fails -- The Limits of EHR Classification
Augusto Garcia-Agundez, Carsten Eickhoff
Transformer Megatron Decepticons Electronic Health Record Ticket BERT Continuum Limit Text Representation Prediction Accuracy Clinical Decision Support Readmission Prediction

July 6, 2022

Distillation to Enhance the Portability of Risk Models Across Institutions with Large Patient Claims Database
Steve Nyemba, Chao Yan, Ziqi Zhang, Amol Rajmane, Pablo Meyer, Prithwish Chakraborty, Bradley Malin
Machine Learning Mutual Distillation Clinical Decision Support Risk Model Readmission Prediction

April 14, 2022

Multimodal spatiotemporal graph neural networks for improved prediction of 30-day all-cause hospital readmission
Siyi Tang, Amara Tariq, Jared Dunnmon, Umesh Sharma, Praneetha Elugunti, Daniel Rubin, Bhavik N. Patel, Imon Banerjee
Neural Network Graph Learning Deep Learning Based Better Prediction Medical Multimodal Readmission Prediction Hospital Readmission

December 19, 2021

Predicting Patient Readmission Risk from Medical Text via Knowledge Graph Enhanced Multiview Graph Convolution
Qiuhao Lu, Thien Huu Nguyen, Dejing Dou
Knowledge Graph Electronic Health Record Medical Text Discharge Summary Readmission Prediction

Readmission Prediction

Papers

Predicting 30-Day Hospital Readmission in Medicare Patients: Insights from an LSTM Deep Learning Model

Evaluating the Predictive Features of Person-Centric Knowledge Graph Embeddings: Unfolding Ablation Studies

Static and multivariate-temporal attentive fusion transformer for readmission risk prediction

Enhancing Readmission Prediction with Deep Learning: Extracting Biomedical Concepts from Clinical Texts

Explainable Machine Learning for ICU Readmission Prediction

CPLLM: Clinical Prediction with Large Language Models

Predicting Unplanned Readmissions in the Intensive Care Unit: A Multimodality Evaluation

Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction

When BERT Fails -- The Limits of EHR Classification

Distillation to Enhance the Portability of Risk Models Across Institutions with Large Patient Claims Database

Multimodal spatiotemporal graph neural networks for improved prediction of 30-day all-cause hospital readmission

Predicting Patient Readmission Risk from Medical Text via Knowledge Graph Enhanced Multiview Graph Convolution