EUVIMEDEUVIMED entdecken
BeobachtungsstudieOpen Access

Nursing Process Data for Health Care Cost Prediction Using Machine Learning: Longitudinal Study

Pflegeprozessdaten zur Vorhersage von Gesundheitskosten mit Machine Learning: Längsschnittstudie

María Consuelo Company-Sancho, Víctor M González-Chordá, María Isabel Orts-Cortés

JMIR Nursing · 04.09.2026 · 9 · e93638-e93638

DOI: 10.2196/93638 ↗

Auf einen Blick

Die Einbeziehung strukturierter Pflegeprozessdaten führte in ML-Modellen zur Vorhersage von Gesundheitskosten zu kleinen Leistungszuwächsen. Der Effekt war insgesamt begrenzt.

Fragestellung

Welchen Einfluss hat die Integration von Pflegeprozessdaten auf ML-basierte Modelle zur Vorhersage individueller Gesundheitskosten im Vergleich zu Modellen ohne diese Daten?

Methode

Retrospektive Beobachtungsstudie in einer populationsbasierten Kohorte mit 1.691.075 Personen ≤15 Jahre; Modelle mit neuronalen Netzen und XGBoost, Ensemble; Testset mit R².

Ergebnisse

Mit Pflegevariablen stieg R² für die Gesamtkosten im Ensemble von 0,5023 auf 0,5058. Bei Krankenhauskosten und Arzneimittelkosten zeigten sich ebenfalls Verbesserungen; 789 Variablen wurden per Autoencoder auf 16 latente Dimensionen reduziert.

Schlussfolgerung der Autor:innen

Die Integration strukturierter Pflegeprozessdaten ist mit kleinen zusätzlichen Verbesserungen ML-basierter Vorhersagemodelle verbunden und ergänzt soziodemografische, klinische und Morbiditätsvariablen.

Kernaussagen

  • Gesamtkosten: R² 0,5023 ohne vs. 0,5058 mit Pflegevariablen
  • Verbesserungen auch bei Krankenhaus- und Arzneimittelkosten
  • 789 Pflegevariablen auf 16 latente Dimensionen reduziert

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Beobachtungsstudie in der Zeitschrift JMIR Nursing, online erschienen am 04.09.2026. Verfasst von María Consuelo Company-Sancho und 2 weiteren Autor:innen. Beteiligte Einrichtung: Health Promotion Service, Directorate General for Public Health, Canary Islands Health Service, Las Palmas de Gran Canaria, Canary Islands, Spain. Hauptthemen laut MEDLINE: Machine Learning, Health Care Costs. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Machine learning (ML) has been demonstrated to enhance health care cost prediction by handling high-dimensional data and identifying complex patterns. However, current risk-adjustment models rarely incorporate structured nursing information derived from the nursing process. This information captures care needs and human responses to health problems.

Objective

This study aimed to evaluate the impact of integrating nursing process data into ML-based predictive models of individual health care costs, including cost component analyses, compared with models based solely on sociodemographic, clinical, and morbidity-related variables.

Methods

A retrospective observational study was conducted using a population-based cohort of 1,691,075 individuals aged 15 years or younger who were registered with the Canary Islands Health Service. Predictors were derived from data available up to 2017 and included sociodemographic and clinical variables, Adjusted Morbidity Groups, health care use, and structured nursing records (Functional Health Patterns [FHP], North American Nursing Diagnosis Association [NANDA], Nursing Outcomes Classification [NOC], and Nursing Interventions Classification [NIC]). Predictive models were developed using feedforward neural networks and extreme gradient boosting; predictions were combined using an ensemble approach. An autoencoder was applied as a dimensionality-reduction technique for the nursing variables. Model performance with and without nursing variables was compared on total cost and individual cost components, and the coefficient of determination ( R ²) was used on the test set.

Results

Including the nursing methodology yielded small numerical increases in predictive performance. With respect to total cost, the ensemble model improved the R ² from 0.5023 to 0.5058 when the nursing variables were added. Although directionally consistent, these gains were limited in magnitude. In the component-level analyses, performance gains were observed in hospital care ( R ²=0.2396) and pharmaceutical costs ( R ²=0.6631). Reducing 789 nursing variables to 16 latent dimensions using an autoencoder substantially simplified the feature space, with predictive performance remaining broadly comparable but without a substantial additional gain.

Conclusions

Integrating structured information from the nursing process is associated with small incremental improvements in ML-based predictive models and complements commonly used sociodemographic, clinical, and morbidity variables. The systematic incorporation of nursing data into predictive tools may contribute to more accurate health care cost prediction and support more holistic, person-centered approaches.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningHealth Care CostsHumansRetrospective StudiesLongitudinal StudiesFemaleMaleAdolescentPredictive Learning ModelsPrediction AlgorithmsAdultClassification Algorithms

Stichwörter der Autor:innen

health care costsmachine learningnursing diagnosisnursing processpredictive modelingrisk adjustmentstandardized nursing terminology

Autor:innen und Institutionen

  • Health Promotion Service, Directorate General for Public Health, Canary Islands Health Service, Las Palmas de Gran Canaria, Canary Islands, Spain.
  • Nursing and Healthcare Research Unit (Investén-isciii), Research Network on Chronicity, Primary Care and Health Promotion (RICAPPS), Carlos III Health Institute, Madrid, Spain.
  • Nursing and Healthcare Research Unit (Investén-isciii), CIBER of Frailty and Healthy Ageing (CIBERFES), Carlos III Health Institute, Madrid, Spain.
  • Nursing Research Group GIENF-241, Nursing Department, Universitat Jaume I, Castellón de la Plana, Castellón, 12071, Spain, 34 964 387744.
  • Department of Nursing (BALMIS), Institute for Health and Biomedical Research (ISABIAL, Group 23), University of Alicante, Alicante, Spain.

Zitieren

APA

Company-Sancho, M. C., González-Chordá, V. M., & Orts-Cortés, M. I. (2026). Nursing Process Data for Health Care Cost Prediction Using Machine Learning: Longitudinal Study. JMIR Nursing, 9, e93638-e93638. https://doi.org/10.2196/93638

Vancouver

Company-Sancho MC, González-Chordá VM, Orts-Cortés MI. Nursing Process Data for Health Care Cost Prediction Using Machine Learning: Longitudinal Study. JMIR Nursing. 2026;9:e93638-e93638. doi:10.2196/93638

BibTeX
@article{CompanySancho2026,
  author = {Company-Sancho, María Consuelo and González-Chordá, Víctor M and Orts-Cortés, María Isabel},
  title = {Nursing Process Data for Health Care Cost Prediction Using Machine Learning: Longitudinal Study},
  journal = {JMIR Nursing},
  year = {2026},
  volume = {9},
  pages = {e93638--e93638},
  doi = {10.2196/93638}
}
Kostenlos starten →