A Disease Trajectory Representation Framework With Risk-Aware Pseudotime Analysis for Electronic Health Records: Application to Heart Failure Risk Stratification
Ein Rahmenwerk zur Krankheitsverlaufsdarstellung mit risikoadaptiver Pseudotime-Analyse für elektronische Gesundheitsakten: Anwendung auf die Herzinsuffizienz-Risikostratifizierung
JMIR Medical Informatics · 2026-11-10 · 14 · e95929
DOI: 10.2196/95929 ↗Auf einen Blick
Das Rahmenwerk stellte longitudinale Krankheitsverläufe kompakt und interpretierbar dar. Es erreichte eine OOF-AUPRC von 0,667 und eine AUC von 0,888.
Fragestellung
Soll eine interpretierbare Verlaufsdarstellung aus EHR-Daten die Risikostratifizierung für Herzinsuffizienz verbessern?
Methode
Longitudinale ICD-Verläufe mit Node2Vec-Embeddings und IG-gewichteten geometrischen Merkmalen; Bewertung per 10-fold cross-validation gegen Aggregation, sparse ICD one-hot encoding und LSTM.
Ergebnisse
OOF-AUPRC 0,667 und AUC 0,888. Gegenüber sparse ICD one-hot encoding etwa 75 % weniger Merkmale bei vergleichbarer Vorhersageleistung. Kombination mit sparse ICD one-hot verbesserte LR und XGBoost.
Schlussfolgerung der Autor:innen
Das Rahmenwerk liefert eine kompakte, interpretierbare Darstellung longitudinaler Krankheitsverläufe bei vergleichbarer Vorhersageleistung. Es unterstützt die Darstellung, Visualisierung und Risikostratifizierung von EHR-Verläufen.
Kernaussagen
- OOF-AUPRC 0,667; AUC 0,888
- Etwa 75 % weniger Merkmale als sparse ICD one-hot encoding
- Risikoadaptive Pseudotime und IG×PPMI dienten der Interpretation
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
At a glance
Journal article in JMIR Medical Informatics, published online on 2026-11-10. Written by Jhen-Li Huang and 2 co-authors. Institution: Department of Computer Science and Engineering, National Taiwan Ocean University, Keelung, Taiwan. Major MEDLINE topics: Electronic Health Records, Heart Failure. 39 references.
Topics: Herzinsuffizienz
Abstract (original language)
Background
Heart failure develops through complex longitudinal interactions among multiple chronic diseases, making longitudinal disease trajectories an important source of clinical information. Longitudinal disease trajectories contain rich structural information that reflects disease evolution and comorbidity interactions. However, this information is often lost when electronic health record (EHR) data are summarized using conventional pooling strategies or sparse International Classification of Diseases (ICD) representations.
Objective
This study aimed to develop an interpretable trajectory representation that preserves structural characteristics of longitudinal disease evolution for heart failure risk stratification using EHRs.
Methods
Longitudinal ICD trajectories were represented using Node2Vec embeddings and summarized with information gain (IG)–weighted geometric features, including historical means, directional shifts, dispersion, and deviation relative to high-risk disease representations. The resulting maximum IG-weighted deviation geometric (mIGwDG) representation was evaluated using 10-fold cross-validation against conventional embedding aggregation strategies, sparse ICD one-hot encoding, and a long short-term memory (LSTM) model. To facilitate interpretation of longitudinal disease evolution, we further developed a risk-aware pseudotime framework to organize patient trajectories along a model-inferred risk continuum and used a framework combining IG with the positive pointwise mutual information (PPMI) framework to characterize clinically relevant comorbidity patterns.
Results
The proposed framework achieved an out-of-fold (OOF) area under the precision-recall curve (AUPRC) of 0.667 and an area under the curve (AUC) of 0.888, outperforming conventional embedding aggregation methods. Compared with sparse ICD one-hot encoding, the proposed framework reduced feature dimensionality by approximately 75% while maintaining comparable predictive performance. Combining mIGwDG with sparse ICD one-hot features further improved both logistic regression (LR) and extreme gradient boosting (XGBoost), suggesting that the proposed representation captures complementary longitudinal disease trajectory information. In addition, the risk-aware pseudotime framework organized heterogeneous patient trajectories along a model-inferred risk continuum, while IG×PPMI analysis highlighted clinically relevant comorbidity patterns that supported the interpretation of longitudinal disease organization.
Conclusions
The proposed framework provides a compact and interpretable representation of longitudinal disease trajectories while maintaining comparable predictive performance. By combining geometric trajectory characterization with risk-aware pseudotime visualization, the framework facilitates the representation of longitudinal EHRs, the visualization of disease evolution, and risk stratification.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Computer Science and Engineering, National Taiwan Ocean University, Keelung, Taiwan.
- Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan.
ORCID profiles: Jhen-Li Huang, Cing-Han Yang, Tun-Wen Pai
Cite
APA
Huang, J. L., Yang, C. H., & Pai, T. W. (2026). A Disease Trajectory Representation Framework With Risk-Aware Pseudotime Analysis for Electronic Health Records: Application to Heart Failure Risk Stratification. JMIR Medical Informatics, 14, e95929. https://doi.org/10.2196/95929
Vancouver
Huang JL, Yang CH, Pai TW. A Disease Trajectory Representation Framework With Risk-Aware Pseudotime Analysis for Electronic Health Records: Application to Heart Failure Risk Stratification. JMIR Medical Informatics. 2026;14:e95929. doi:10.2196/95929
BibTeX
@article{Huang2026,
author = {Huang, Jhen-Li and Yang, Cing-Han and Pai, Tun-Wen},
title = {A Disease Trajectory Representation Framework With Risk-Aware Pseudotime Analysis for Electronic Health Records: Application to Heart Failure Risk Stratification},
journal = {JMIR Medical Informatics},
year = {2026},
volume = {14},
pages = {e95929},
doi = {10.2196/95929}
}
EUVIMED