EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Evaluating the Role of Order and Time Information for Classifying Sequences of Healthcare Events Derived from Claims Data

Corentin Faujour, Stéphane Bouee, Corinne Emery, Anne-Sophie Jannot

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260305 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Corentin Faujour und 3 weiteren Autor:innen. Beteiligte Einrichtung: CEMKA, Bourg-La-Reine, France. Hauptthemen laut MEDLINE: Neural Networks, Computer, Amyotrophic Lateral Sclerosis, Insurance Claim Review. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sequences of healthcare events from claims data are increasingly used for predictive modeling. Despite the rise in popularity of neural networks, the benefit of modeling event order and timing remains underexplored. We simulated patient trajectories using parameters estimated from claims data including 22,000 amyotrophic lateral sclerosis (ALS) cases and 22,000 age and gender-matched controls. The simulation reproduced irregular event timing and condition-related activity that increased near an incident diagnosis. We compared three model families for population classification: frequency-based models, sequential models (long short-term memory and Transformer architectures) capturing event order, and sequential models incorporating temporal information. Performance was evaluated using the area under the ROC curve (AUC) at multiple time points before diagnosis. Sequential models outperformed frequency-based baselines by about +0.06 AUC on average, confirming the benefit of modeling event order. Adding time information provided no noticeable improvement, and results were stable across different time encoding and scaling methods. These findings suggest that, in claims-based classification tasks, event order captures most of the useful temporal signal, while explicit time encoding offers limited additional benefit under similar conditions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerAmyotrophic Lateral SclerosisInsurance Claim ReviewHumansClassification AlgorithmsLong Short Term MemoryPredictive Learning ModelsComputer SimulationPrediction AlgorithmsFemale

Stichwörter der Autor:innen

Claims DataHealthcare Event SequencesNeural NetworksSequence ClassificationTemporal Features

Autor:innen und Institutionen

  • CEMKA, Bourg-La-Reine, France.
  • Université Paris Cité, Inria, Inserm, HeKA, F-75015 Paris, France.
  • French National Rare Disease Registry (BNDMR), Greater Paris University Hospitals (AP-HP), Université Paris Cité, Paris, France.

Zitieren

APA

Faujour, C., Bouee, S., Emery, C., & Jannot, A. S. (2026). Evaluating the Role of Order and Time Information for Classifying Sequences of Healthcare Events Derived from Claims Data. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260305

Vancouver

Faujour C, Bouee S, Emery C, Jannot AS. Evaluating the Role of Order and Time Information for Classifying Sequences of Healthcare Events Derived from Claims Data. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260305

BibTeX
@article{Faujour2026,
  author = {Faujour, Corentin and Bouee, Stéphane and Emery, Corinne and Jannot, Anne-Sophie},
  title = {Evaluating the Role of Order and Time Information for Classifying Sequences of Healthcare Events Derived from Claims Data},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260305}
}
Kostenlos starten →