EUVIMEDEUVIMED entdecken
Open Access

Interpretable Deep-Learning Approaches for Osteoporosis Risk Screening and Individualized Feature Analysis Using Large Population-Based Data: Model Development and Performance Evaluation

Bogyeong Suh iD, Heejin Yu iD, Hyeyeon Kim iD, Sanghwa Lee iD, Sunghye Kong iD, Jin-Woo Kim iD, Jongeun Choi iD

Journal of Medical Internet Research · 2023

DOI: 10.2196/40179 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Internet Research, 2023. Verfasst von Bogyeong Suh und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Yonsei University, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Osteoporosis. Die Arbeit wurde bisher 56-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Osteoporosis is one of the diseases that requires early screening and detection for its management. Common clinical tools and machine-learning (ML) models for screening osteoporosis have been developed, but they show limitations such as low accuracy. Moreover, these methods are confined to limited risk factors and lack individualized explanation.

Objective

The aim of this study was to develop an interpretable deep-learning (DL) model for osteoporosis risk screening with clinical features. Clinical interpretation with individual explanations of feature contributions is provided using an explainable artificial intelligence (XAI) technique.

Methods

We used two separate data sets: the National Health and Nutrition Examination Survey data sets from the United States (NHANES) and South Korea (KNHANES) with 8274 and 8680 respondents, respectively. The study population was classified according to the T-score of bone mineral density at the femoral neck or total femur. A DL model for osteoporosis diagnosis was trained on the data sets and significant risk factors were investigated with local interpretable model-agnostic explanations (LIME). The performance of the DL model was compared with that of ML models and conventional clinical tools. Additionally, contribution ranking of risk factors and individualized explanation of feature contribution were examined.

Results

Our DL model showed area under the curve (AUC) values of 0.851 (95% CI 0.844-0.858) and 0.922 (95% CI 0.916-0.928) for the femoral neck and total femur bone mineral density, respectively, using the NHANES data set. The corresponding AUC values for the KNHANES data set were 0.827 (95% CI 0.821-0.833) and 0.912 (95% CI 0.898-0.927), respectively. Through the LIME method, significant features were induced, and each feature’s integrated contribution and interpretation for individual risk were determined.

Conclusions

The developed DL model significantly outperforms conventional ML models and clinical tools. Our XAI model produces high-ranked features along with the integrated contributions of each feature, which facilitates the interpretation of individual risk. In summary, our interpretable model for osteoporosis risk screening outperformed state-of-the-art methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningOsteoporosisHumansArtificial IntelligenceNutrition SurveysOxidesCalcium Compounds

Stichwörter der Autor:innen

artificial intelligencedeep learningmachine learningosteoporosisrisk factorsscreening

Substanzen

limeOxidesCalcium Compounds

Autor:innen und Institutionen

  • School of Mechanical Engineering, Yonsei University, Seoul, Republic of Korea.
  • Department of Family Medicine, School of Medicine, Ewha Womans University, Seoul, Republic of Korea.
  • Department of Internal Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea.
  • Department of Oral and Maxillofacial Surgery, School of Medicine, Ewha Womans University, Seoul, Republic of Korea.

ORCID-Profile: Bogyeong Suh, Heejin Yu, Hyeyeon Kim, Sanghwa Lee, Sunghye Kong, Jin-Woo Kim, Jongeun Choi

Zitieren

APA

Suh, B., Yu, H., Kim, H., Lee, S., Kong, S., Kim, J. W., & Choi, J. (2023). Interpretable Deep-Learning Approaches for Osteoporosis Risk Screening and Individualized Feature Analysis Using Large Population-Based Data: Model Development and Performance Evaluation. Journal of Medical Internet Research. https://doi.org/10.2196/40179

Vancouver

Suh B, Yu H, Kim H, Lee S, Kong S, Kim JW, et al. Interpretable Deep-Learning Approaches for Osteoporosis Risk Screening and Individualized Feature Analysis Using Large Population-Based Data: Model Development and Performance Evaluation. Journal of Medical Internet Research. 2023. doi:10.2196/40179

BibTeX
@article{Suh2023,
  author = {Suh, Bogyeong and Yu, Heejin and Kim, Hyeyeon and Lee, Sanghwa and Kong, Sunghye and Kim, Jin-Woo and Choi, Jongeun},
  title = {Interpretable Deep-Learning Approaches for Osteoporosis Risk Screening and Individualized Feature Analysis Using Large Population-Based Data: Model Development and Performance Evaluation},
  journal = {Journal of Medical Internet Research},
  year = {2023},
  doi = {10.2196/40179}
}
Kostenlos starten →