EUVIMEDEUVIMED entdecken
Crossref

Predicting Acute Exacerbation Phenotype in Chronic Obstructive Pulmonary Disease Patients Using VGG-16 Deep Learning

Vorhersage des akuten Exazerbationsphänotyps bei COPD-Patient:innen mit VGG-16 Deep Learning

Shengchuan Feng, Ran Zhang, Wenxiu Zhang, Yuqiong Yang, Aiqi Song, Jiawei Chen, Fengyan Wang, Jiaxuan Xu, Cuixia Liang, Xiaoyun Liang, Rongchang Chen, Zhenyu Liang

Respiration · 24.07.2024 · 1-14

DOI: 10.1159/000540383 ↗

Auf einen Blick

Eine retrospektive Studie mit 219 COPD-Patient:innen entwickelte ein DL-Modell aus HRCT-Daten zur Vorhersage von AECOPD. Das beste Modell erreichte in der Validierung eine AUC von 0,932.

Fragestellung

Kann ein auf HRCT basierendes Deep-Learning-Modell den akuten Exazerbationsphänotyp bei COPD vorhersagen?

Methode

Retrospektive Studie bei 219 COPD-Patient:innen mit inspiratorischen und exspiratorischen HRCT-Scans; 69 QCT-Parameter und 2.000 DL-Features; logistische Regression; externe Validierung mit 29 Patient:innen.

Ergebnisse

Das Modell 7-B mit klinischen Merkmalen, QCT-Parametern und DL-Features erzielte die beste Leistung: AUC 0,979 in der Testkohorte und 0,932 in der externen Validierung. Weitere Modelle lagen niedriger.

Schlussfolgerung der Autor:innen

DL-Features aus HRCT-Scans können den akuten Exazerbationsphänotyp bei COPD-Patient:innen wirksam vorhersagen.

Kernaussagen

  • Retrospektive Analyse von 219 COPD-Patient:innen
  • Bestes Modell: AUC 0,979 im Test, 0,932 extern
  • DL-Features aus HRCT waren prädiktiv für AECOPD

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 Respiration, online erschienen am 24.07.2024. Verfasst von Shengchuan Feng und 11 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, National Center for Respiratory Medicine, Dep…. Hauptthemen laut MEDLINE: Pulmonary Disease, Chronic Obstructive, Deep Learning. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 33 Literaturangaben.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Exacerbations of chronic obstructive pulmonary disease (COPD) have a significant impact on hospitalizations, morbidity, and mortality of patients. This study aimed to develop a model for predicting acute exacerbation in COPD patients (AECOPD) based on deep-learning (DL) features.

Methods

We performed a retrospective study on 219 patients with COPD who underwent inspiratory and expiratory HRCT scans. By recording the acute respiratory events of the previous year, these patients were further divided into non-AECOPD group and AECOPD group according to the presence of acute exacerbation events. Sixty-nine quantitative CT (QCT) parameters of emphysema and airway were calculated by NeuLungCARE software, and 2,000 DL features were extracted by VGG-16 method. The logistic regression method was employed to identify AECOPD patients, and 29 patients of external validation cohort were used to access the robustness of the results.

Results

The model 3-B achieved an area under the receiver operating characteristic curve (AUC) of 0.933 and 0.865 in the testing cohort and external validation cohort, respectively. Model 3-I obtained AUC of 0.895 in the testing cohort and AUC of 0.774 in the external validation cohort. Model 7-B combined clinical characteristics, QCT parameters, and DL features achieved the best performance with an AUC of 0.979 in the testing cohort and demonstrating robust predictability with an AUC of 0.932 in the external validation cohort. Likewise, model 7-I achieved an AUC of 0.938 and 0.872 in the testing cohort and external validation cohort, respectively.

Conclusions

DL features extracted from HRCT scans can effectively predict acute exacerbation phenotype in COPD patients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pulmonary Disease, Chronic ObstructiveDeep LearningHumansMaleFemaleRetrospective StudiesAgedMiddle AgedTomography, X-Ray ComputedDisease ProgressionPhenotypeROC Curve

Stichwörter der Autor:innen

Acute exacerbationChronic obstructive pulmonary diseaseHigh-resolution computed tomographyQuantitative computed tomographyVGG-16

Autor:innen und Institutionen

  • State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, National Center for Respiratory Medicine, Department of Respiratory Medicine, Guangzhou Institute of Respiratory He…
  • Neusoft Medical Systems Co., Ltd., Shenyang, China.
  • Institute of Research and Clinical Innovations, Neusoft Medical Systems Co., Ltd., Shanghai, China.
  • Nanshan School, Guangzhou Medical University, Guangzhou, China.
  • First Clinical School, Guangzhou Medical University, Guangzhou, China.

Zitieren

APA

Feng, S., Zhang, R., Zhang, W., Yang, Y., Song, A., Chen, J., Wang, F., Xu, J., Liang, C., Liang, X., Chen, R., & Liang, Z. (2024). Predicting Acute Exacerbation Phenotype in Chronic Obstructive Pulmonary Disease Patients Using VGG-16 Deep Learning. Respiration, 1-14. https://doi.org/10.1159/000540383

Vancouver

Feng S, Zhang R, Zhang W, Yang Y, Song A, Chen J, et al. Predicting Acute Exacerbation Phenotype in Chronic Obstructive Pulmonary Disease Patients Using VGG-16 Deep Learning. Respiration. 2024:1-14. doi:10.1159/000540383

BibTeX
@article{Feng2024,
  author = {Feng, Shengchuan and Zhang, Ran and Zhang, Wenxiu and Yang, Yuqiong and Song, Aiqi and Chen, Jiawei and Wang, Fengyan and Xu, Jiaxuan and Liang, Cuixia and Liang, Xiaoyun and Chen, Rongchang and Liang, Zhenyu},
  title = {Predicting Acute Exacerbation Phenotype in Chronic Obstructive Pulmonary Disease Patients Using VGG-16 Deep Learning},
  journal = {Respiration},
  year = {2024},
  pages = {1--14},
  doi = {10.1159/000540383}
}
Kostenlos starten →