Predicting Postoperative Pain and Opioid Use with Machine Learning Applied to Longitudinal Electronic Health Record and Wearable Data
Vorhersage von postoperativen Schmerzen und Opioidgebrauch mit Machine Learning auf Basis longitudinaler EHR- und Wearable-Daten
Applied Clinical Informatics · 01.05.2024 · 15 (03) · 569-582
DOI: 10.1055/a-2321-0397 ↗Auf einen Blick
In einer Kohorte von etwa 347 Personen sagte ein Machine-Learning-Modell akute postoperative Schmerzen und chronischen Opioidgebrauch vorher. Wearable-Daten waren dabei wichtige Prädiktoren.
Fragestellung
Lassen sich mit präoperativen EHR- und Wearable-Daten postoperative akute Schmerzen und chronischer Opioidgebrauch vorhersagen?
Methode
Etwa 347 Teilnehmende des All of Us Research Program mit 8 chirurgischen Eingriffen; 4 Machine-Learning-Modelle; SHAP zur Identifikation relevanter Prädiktoren.
Ergebnisse
Das Stacking-Ensemble erreichte die höchste Genauigkeit für akute Schmerzen (0,68) und chronischen Opioidgebrauch (0,89). AUC für starke Schmerzen vs. andere Schmerzen: 0,88.
Schlussfolgerung der Autor:innen
Die SHAP-Analyse individueller Risikofaktoren für starke Schmerzen kann die Anpassung von Schmerztherapieplänen unterstützen. Eine genaue präoperative Vorhersage des chronischen Opioidgebrauchs kann Risiken mindern.
Kernaussagen
- Stacking-Ensemble mit Genauigkeit 0,68 für akute Schmerzen
- Genauigkeit 0,89 für chronischen Opioidgebrauch
- Wearable-Daten spielten für beide Endpunkte eine wichtige Rolle
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Applied Clinical Informatics, erschienen am 01.05.2024. Verfasst von Nidhi Soley und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Computational Medicine, Whiting School of Engineering, Johns Hopkins University, Baltimore, Maryland, United States. Hauptthemen laut MEDLINE: Postoperative Pain, Machine Learning, Electronic Health Records, Wearable Electronic Devices. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, NHGRI NIH HHS, National Human Genome Research Institute.
Themen: Schmerzmanagement, Künstliche Intelligenz in der Pflege
Abstract (Originalsprache)
Background
Managing acute postoperative pain and minimizing chronic opioid use are crucial for patient recovery and long-term well-being.
Objectives
This study explored using preoperative electronic health record (EHR) and wearable device data for machine-learning models that predict postoperative acute pain and chronic opioid use.
Methods
The study cohort consisted of approximately 347 All of Us Research Program participants who underwent one of eight surgical procedures and shared EHR and wearable device data. We developed four machine learning models and used the Shapley additive explanations (SHAP) technique to identify the most relevant predictors of acute pain and chronic opioid use.
Results
The stacking ensemble model achieved the highest accuracy in predicting acute pain (0.68) and chronic opioid use (0.89). The area under the curve score for severe pain versus other pain was highest (0.88) when predicting acute postoperative pain. Values of logistic regression, random forest, extreme gradient boosting, and stacking ensemble ranged from 0.74 to 0.90 when predicting postoperative chronic opioid use. Variables from wearable devices played a prominent role in predicting both outcomes.
Conclusion
SHAP detection of individual risk factors for severe pain can help health care providers tailor pain management plans. Accurate prediction of postoperative chronic opioid use before surgery can help mitigate the risk for the outcomes we studied. Prediction can also reduce the chances of opioid overuse and dependence. Such mitigation can promote safer and more effective pain control for patients during their recovery.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Institute for Computational Medicine, Whiting School of Engineering, Johns Hopkins University, Baltimore, Maryland, United States.
- Department of Biomedical Engineering, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States.
- Department of Psychiatry and Behavioral Sciences, Johns Hopkins University, School of Medicine, Baltimore, Maryland, United States.
- Armstrong Institute for Patient Safety and Quality, Johns Hopkins University, School of Medicine, Baltimore, Maryland, United States.
- Department of Anesthesia and Critical Care Medicine, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States.
- Department of General Internal Medicine, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States.
Förderung
- NIH HHS
- NHGRI NIH HHS
- National Human Genome Research Institute
Zitieren
APA
Soley, N., Speed, T. J., Xie, A., & Taylor, C. O. (2024). Predicting Postoperative Pain and Opioid Use with Machine Learning Applied to Longitudinal Electronic Health Record and Wearable Data. Applied Clinical Informatics, 15(03), 569-582. https://doi.org/10.1055/a-2321-0397
Vancouver
Soley N, Speed TJ, Xie A, Taylor CO. Predicting Postoperative Pain and Opioid Use with Machine Learning Applied to Longitudinal Electronic Health Record and Wearable Data. Applied Clinical Informatics. 2024;15(03):569-582. doi:10.1055/a-2321-0397
BibTeX
@article{Soley2024,
author = {Soley, Nidhi and Speed, Traci J and Xie, Anping and Taylor, Casey Overby},
title = {Predicting Postoperative Pain and Opioid Use with Machine Learning Applied to Longitudinal Electronic Health Record and Wearable Data},
journal = {Applied Clinical Informatics},
year = {2024},
volume = {15},
number = {03},
pages = {569--582},
doi = {10.1055/a-2321-0397}
}
EUVIMED