Patient Trajectory

Patient trajectory analysis focuses on modeling the temporal evolution of a patient's health status using longitudinal data from electronic health records (EHRs), aiming to improve prediction of clinical outcomes and personalize care. Current research emphasizes the use of deep learning models, including recurrent neural networks, transformers, and neural ordinary differential equations, to handle the complexities of irregular and multimodal EHR data, often incorporating techniques like contrastive learning and adversarial training to mitigate biases. These advancements enable more accurate risk prediction, improved patient stratification for targeted interventions, and the development of interpretable models that provide valuable insights for clinicians and researchers.

Papers

October 31, 2024

Topology-Aware Graph Augmentation for Predicting Clinical Trajectories in Neurocognitive Disorders
Qianqian Wang, Wei Wang, Yuqi Fang, Hong-Jun Li, Andrea Bozoki, Mingxia Liu
Brain Network Cognitive Impairment Patient Trajectory Brain Network Analysis

October 29, 2024

Individualised recovery trajectories of patients with impeded mobility, using distance between probability distributions of learnt graphs
Chuqiao Zhang, Crina Grosan, Dalia Chakrabarty
Graph Drawing Distance Matter Prompt Recovery Mobility Management Optimal Behavior Physical Rehabilitation Probability Distribution Patient Trajectory

October 4, 2024

Stabilized Neural Prediction of Potential Outcomes in Continuous Time
Konstantin Hess, Stefan Feuerriegel
Time Varying Continuous Time Patient Trajectory Inverse Propensity Weighting Stable Neural Network

September 19, 2024

SeqRisk: Transformer-augmented latent variable model for improved survival prediction with longitudinal data
Mine Öğretir, Miika Koskinen, Juha Sinisalo, Risto Renkonen, Harri Lähdesmäki
Latent Variable Model Survival Prediction Longitudinal Data Patient Trajectory Variational Recurrent

September 10, 2024

Developing the Temporal Graph Convolutional Neural Network Model to Predict Hip Replacement using Electronic Health Records
Zoe Hancox, Sarah R. Kingsbury, Andrew Clegg, Philip G. Conaghan, Samuel D. Relton
Electronic Health Record Temporal Graph Patient Trajectory Total Knee Arthroplasty Hip Fracture

August 25, 2024

Prediction of COPD Using Machine Learning, Clinical Summary Notes, and Vital Signs
Negar Orangi-Fard
Machine Learning Human Prediction Vital Sign Patient Trajectory Chronic Obstructive Pulmonary Disease

July 28, 2024

Learning to Select the Best Forecasting Tasks for Clinical Outcome Prediction
Yuan Xue, Nan Du, Anne Mottram, Martin Seneviratne, Andrew M. Dai
LeArning Abstract Medical Information Mart for Intensive Patient Representation Forecasting Task Patient Trajectory Clinical Outcome Prediction

July 20, 2024

Mapping Patient Trajectories: Understanding and Visualizing Sepsis Prognostic Pathways from Patients Clinical Narratives
Sudeshna Jana, Tirthankar Dasgupta, Lipika Dey
Human Understanding Clinical Narrative Sepsis Prediction Patient Trajectory Patient Subgroup

July 12, 2024

Towards Personalised Patient Risk Prediction Using Temporal Hospital Data Trajectories
Thea Barnes, Enrico Werner, Jeffrey N. Clark, Raul Santos-Rodriguez
Risk Prediction Early Warning Patient Trajectory Hospital Mortality Prediction

May 21, 2024

A machine learning framework for interpretable predictions in patient pathways: The case of predicting ICU admission for patients with symptoms of sepsis
Sandra Zilker, Sven Weinzierl, Mathias Kraus, Patrick Zschech, Martin Matzner
Patient Friendly Language Outcome Prediction Clinical Decision Support Patient Trajectory Standard Sepsis Interpretable Prediction Patient Pathway

April 16, 2024

Data-driven subgrouping of patient trajectories with chronic diseases: Evidence from low back pain
Christof Naumzik, Alice Kongsted, Werner Vach, Stefan Feuerriegel
Evidence Piece Clinical Data Longitudinal Study Patient Trajectory Markov Model Chronic Disease Subgroup Analysis

April 10, 2024

Global Contrastive Training for Multimodal Electronic Health Records with Language Supervision
Yingbo Ma, Suraj Kolla, Zhenhong Hu, Dhruv Kaliraman, Victoria Nolan, Ziyuan Guan, Yuanfang Ren, Brooke Armfield, Tezcan Ozrazgat-Baslanti, Jeremy A. Balch, Tyler J. Loftus, Parisa Rashidi, Azra Bihorac, Benjamin Shickel
Contrastive Learning Multimodal Data Electronic Health Record Language Supervision Patient Trajectory EHR Datasets Multimodal Electronic Health Record

March 6, 2024

Temporal Cross-Attention for Dynamic Embedding and Tokenization of Multimodal Electronic Health Records
Yingbo Ma, Suraj Kolla, Dhruv Kaliraman, Victoria Nolan, Zhenhong Hu, Ziyuan Guan, Yuanfang Ren, Brooke Armfield, Tezcan Ozrazgat-Baslanti, Tyler J. Loftus, Parisa Rashidi, Azra Bihorac, Benjamin Shickel
Cross Attention Patient Trajectory Dynamic Embeddings Multimodal Electronic Health Record

December 10, 2023

Temporal Supervised Contrastive Learning for Modeling Patient Risk Progression
Shahriar Noroozizadeh, Jeremy C. Weiss, George H. Chen
Contrastive Learning Tabular Data Supervised Contrastive Learning Patient Trajectory ADNI Dataset

November 29, 2023

TimelyGPT: Extrapolatable Transformer Pre-training for Long-term Time-Series Forecasting in Healthcare
Ziyang Song, Qincheng Lu, Hao Xu, He Zhu, David L. Buckeridge, Yue Li
Temporal Dependency Generative Pre Trained Transformer Large Scale Pre Trained Model Patient Trajectory Transformer Length Extrapolation

November 15, 2023

Approaching adverse event detection utilizing transformers on clinical time-series
Helge Fredriksen, Per Joel Burman, Ashenafi Woldaregay, Karl Øyvind Mikalsen, Ståle Nymo
Anomaly Detection Transformer Megatron Decepticons Vital Sign Patient Trajectory Clinical Time Series Adverse Event Patient Phenotype

October 19, 2023

On existence, uniqueness and scalability of adversarial robustness measures for AI classifiers
Illia Horenko
Adversarial Robustness Adversarial Perturbation Potential Scalability Machine Learning Classifier Patient Trajectory

March 21, 2023

Dynamic Healthcare Embeddings for Improving Patient Care
Hankyu Jang, Sulyun Lee, D. M. Hasibul Hasan, Philip M. Polgreen, Sriram V. Pemmaraju, Bijaya Adhikari
Word Embeddings Patient Trajectory Dynamic Embeddings Healthcare Prediction Heterogeneous Dynamic Healthcare Prediction Task

November 14, 2022

Learning predictive checklists from continuous medical data
Yukti Makhija, Edward De Brouwer, Rahul G. Krishnan
LeArning Abstract Patient Trajectory Assessment Checklist Predictive Checklist

September 9, 2022

Modelling Patient Trajectories Using Multimodal Information
João Figueira Silva, Sérgio Matos
Multimodal Information Medical Information Mart for Intensive Clinical Data Patient Trajectory

Patient Trajectory

Papers

Topology-Aware Graph Augmentation for Predicting Clinical Trajectories in Neurocognitive Disorders

Individualised recovery trajectories of patients with impeded mobility, using distance between probability distributions of learnt graphs

Stabilized Neural Prediction of Potential Outcomes in Continuous Time

SeqRisk: Transformer-augmented latent variable model for improved survival prediction with longitudinal data

Developing the Temporal Graph Convolutional Neural Network Model to Predict Hip Replacement using Electronic Health Records

Prediction of COPD Using Machine Learning, Clinical Summary Notes, and Vital Signs

Learning to Select the Best Forecasting Tasks for Clinical Outcome Prediction

Mapping Patient Trajectories: Understanding and Visualizing Sepsis Prognostic Pathways from Patients Clinical Narratives

Towards Personalised Patient Risk Prediction Using Temporal Hospital Data Trajectories

A machine learning framework for interpretable predictions in patient pathways: The case of predicting ICU admission for patients with symptoms of sepsis

Data-driven subgrouping of patient trajectories with chronic diseases: Evidence from low back pain

Global Contrastive Training for Multimodal Electronic Health Records with Language Supervision

Temporal Cross-Attention for Dynamic Embedding and Tokenization of Multimodal Electronic Health Records

Temporal Supervised Contrastive Learning for Modeling Patient Risk Progression

TimelyGPT: Extrapolatable Transformer Pre-training for Long-term Time-Series Forecasting in Healthcare

Approaching adverse event detection utilizing transformers on clinical time-series

On existence, uniqueness and scalability of adversarial robustness measures for AI classifiers

Dynamic Healthcare Embeddings for Improving Patient Care

Learning predictive checklists from continuous medical data

Modelling Patient Trajectories Using Multimodal Information