EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Metabolic phenotyping with computed tomography deep learning for metabolic syndrome, osteoporosis and sarcopenia predicts mortality in adults

Sang Wouk Cho, Seungjin Baek iD, Sookyeong Han, Chang Oh Kim, Hyeon Chang Kim, Yumie Rhee, Namki Hong iD

Journal of Cachexia, Sarcopenia and Muscle · 2024-08 · 15 (4) · 1418-1429

DOI: 10.1002/jcsm.13487 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Cachexia, Sarcopenia and Muscle, online erschienen am 22.04.2024. Verfasst von Sang Wouk Cho und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Internal Medicine, Endocrine Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea. Hauptthemen laut MEDLINE: Sarcopenia, Metabolic Syndrome, Deep Learning, Tomography, X-Ray Computed. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Health and Welfare, Republic of Korea, Ministry of Science and ICT, South Korea, Research of Korea Centers for Disease Control and Prevention.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Computed tomography (CT) body compositions reflect age‐related metabolic derangements. We aimed to develop a multi‐outcome deep learning model using CT multi‐level body composition parameters to detect metabolic syndrome (MS), osteoporosis and sarcopenia by identifying metabolic clusters simultaneously. We also investigated the prognostic value of metabolic phenotyping by CT model for long‐term mortality.

Methods

The derivation set ( n = 516; 75% train set, 25% internal test set) was constructed using age‐ and sex‐stratified random sampling from two community‐based cohorts. Data from participants in the individual health assessment programme ( n = 380) were used as the external test set 1. Semi‐automatic quantification of body compositions at multiple levels of abdominal CT scans was performed to train a multi‐layer perceptron (MLP)‐based multi‐label classification model. External test set 2 to test the prognostic value of the model output for mortality was built using data from individuals who underwent abdominal CT in a tertiary‐level institution ( n = 10 141).

Results

The mean ages of the derivation and external sets were 62.8 and 59.7 years, respectively, without difference in sex distribution (women 50%) or body mass index (BMI; 23.9 kg/m 2 ). Skeletal muscle density (SMD) and bone density (BD) showed a more linear decrement across age than skeletal muscle area. Alternatively, an increase in visceral fat area (VFA) was observed in both men and women. Hierarchical clustering based on multi‐level CT body composition parameters revealed three distinctive phenotype clusters: normal, MS and osteosarcopenia clusters. The L3 CT‐parameter‐based model, with or without clinical variables (age, sex and BMI), outperformed clinical model predictions of all outcomes (area under the receiver operating characteristic curve: MS, 0.76 vs. 0.55; osteoporosis, 0.90 vs. 0.79; sarcopenia, 0.85 vs. 0.81 in external test set 1; P < 0.05 for all). VFA contributed the most to the MS predictions, whereas SMD, BD and subcutaneous fat area were features of high importance for detecting osteoporosis and sarcopenia. In external test set 2 (mean age 63.5 years, women 79%; median follow‐up 4.9 years), a total of 907 individuals (8.9%) died during follow‐up. Among model‐predicted metabolic phenotypes, sarcopenia alone (adjusted hazard ratio [aHR] 1.55), MS + sarcopenia (aHR 1.65), osteoporosis + sarcopenia (aHR 1.83) and all three combined (aHR 1.87) remained robust predictors of mortality after adjustment for age, sex and comorbidities.

Conclusions

A CT body composition‐based MLP model detected MS, osteoporosis and sarcopenia simultaneously in community‐dwelling and hospitalized adults. Metabolic phenotypes predicted by the CT MLP model were associated with long‐term mortality, independent of covariates.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SarcopeniaMetabolic SyndromeDeep LearningTomography, X-Ray ComputedOsteoporosisPhenotypeHumansFemaleMaleMiddle AgedAgedPrognosisBody CompositionAdult

Stichwörter der Autor:innen

computed tomographymetabolic syndromemulti‐layer perceptronosteoporosissarcopenia

Autor:innen und Institutionen

  • Department of Internal Medicine, Endocrine Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea.
  • Institue for Innovation in Digital Healthcare (IIDH), Yonsei University Health System, Seoul, South Korea.
  • Division of Geriatric Medicine, Department of Internal Medicine, Yonsei University College of Medicine, Seoul, South Korea.
  • Department of Preventive Medicine, Yonsei University College of Medicine, Seoul, South Korea.

ORCID-Profile: Seungjin Baek, Namki Hong

Förderung

  • Ministry of Health and Welfare, Republic of Korea
  • Ministry of Science and ICT, South Korea
  • Research of Korea Centers for Disease Control and Prevention
  • Hanmi Pharmaceutical Co., Ltd

Zitieren

APA

Cho, S. W., Baek, S., Han, S., Kim, C. O., Kim, H. C., Rhee, Y., & Hong, N. (2024). Metabolic phenotyping with computed tomography deep learning for metabolic syndrome, osteoporosis and sarcopenia predicts mortality in adults. Journal of Cachexia, Sarcopenia and Muscle, 15(4), 1418-1429. https://doi.org/10.1002/jcsm.13487

Vancouver

Cho SW, Baek S, Han S, Kim CO, Kim HC, Rhee Y, et al. Metabolic phenotyping with computed tomography deep learning for metabolic syndrome, osteoporosis and sarcopenia predicts mortality in adults. Journal of Cachexia, Sarcopenia and Muscle. 2024;15(4):1418-1429. doi:10.1002/jcsm.13487

BibTeX
@article{Cho2024,
  author = {Cho, Sang Wouk and Baek, Seungjin and Han, Sookyeong and Kim, Chang Oh and Kim, Hyeon Chang and Rhee, Yumie and Hong, Namki},
  title = {Metabolic phenotyping with computed tomography deep learning for metabolic syndrome, osteoporosis and sarcopenia predicts mortality in adults},
  journal = {Journal of Cachexia, Sarcopenia and Muscle},
  year = {2024},
  volume = {15},
  number = {4},
  pages = {1418--1429},
  doi = {10.1002/jcsm.13487}
}
Kostenlos starten →