PMID- 37270917
OWN - NLM
STAT- MEDLINE
DCOM- 20230606
LR  - 20230607
IS  - 1598-6357 (Electronic)
IS  - 1011-8934 (Print)
IS  - 1011-8934 (Linking)
VI  - 38
IP  - 21
DP  - 2023 May 29
TI  - A Prediction Model for Osteoporosis Risk Using a Machine-Learning Approach and 
      Its Validation in a Large Cohort.
PG  - e162
LID - 10.3346/jkms.2023.38.e162 [doi]
LID - e162
AB  - BACKGROUND: Osteoporosis develops in the elderly due to decreased bone mineral 
      density (BMD), potentially increasing bone fracture risk. However, the BMD is not 
      regularly measured in a clinical setting. This study aimed to develop a good 
      prediction model for the osteoporosis risk using a machine learning (ML) approach 
      in adults over 40 years in the Ansan/Anseong cohort and the association of 
      predicted osteoporosis risk with a fracture in the Health Examinees (HEXA) 
      cohort. METHODS: The 109 demographic, anthropometric, biochemical, genetic, 
      nutrient, and lifestyle variables of 8,842 participants were manually selected in 
      an Ansan/Anseong cohort and included in the ML algorithm. The polygenic risk 
      score (PRS) of osteoporosis was generated with a genome-wide association study 
      and added for the genetic impact of osteoporosis. Osteoporosis was defined with < 
      -2.5 T scores of the tibia or radius compared to people in their 20s-30s. They 
      were divided randomly into the training (n = 7,074) and test (n = 1,768) 
      sets-Pearson's correlation between the predicted osteoporosis risk and fracture 
      in the HEXA cohort. RESULTS: XGBoost, deep neural network, and random forest 
      generated the prediction model with a high area under the curve (AUC, 0.86) of 
      the receiver operating characteristic (ROC) with 10, 15, and 20 features; the 
      prediction model by XGBoost had the highest AUC of ROC, high accuracy and k-fold 
      values (> 0.85) in 15 features among seven ML approaches. The model included the 
      genetic factor, genders, number of children and breastfed children, age, 
      residence area, education, seasons to measure, height, smoking status, hormone 
      replacement therapy, serum albumin, hip circumferences, vitamin B6 intake, and 
      body weight. The prediction models for women alone were similar to those for both 
      genders, with lower accuracy. When the prediction model was applied to the HEXA 
      study, the correlation between the fracture incidence and predicted osteoporosis 
      risk was significant but weak (r = 0.173, P < 0.001). CONCLUSION: The prediction 
      model for osteoporosis risk generated by XGBoost can be applied to estimate 
      osteoporosis risk. The biomarkers can be considered for enhancing the prevention, 
      detection, and early therapy of osteoporosis risk in Asians.
CI  - (c) 2023 The Korean Academy of Medical Sciences.
FAU - Wu, Xuangao
AU  - Wu X
AUID- ORCID: 0000-0002-6293-7363
AD  - Department of Bioconvergence, Hoseo University, Asan, Korea.
FAU - Park, Sunmin
AU  - Park S
AUID- ORCID: 0000-0002-6092-8340
AD  - Department of Bioconvergence, Hoseo University, Asan, Korea.
AD  - Department of Food and Nutrition, Obesity/Diabetes Research Center, Hoseo 
      University, Asan, Korea. smpark@hoseo.edu.
LA  - eng
GR  - RS-2023-00208567/National Research Foundation of Korea/Korea
PT  - Journal Article
DEP - 20230529
PL  - Korea (South)
TA  - J Korean Med Sci
JT  - Journal of Korean medical science
JID - 8703518
SB  - IM
MH  - Adult
MH  - Child
MH  - Humans
MH  - Female
MH  - Male
MH  - Aged
MH  - Bone Density
MH  - Genome-Wide Association Study
MH  - *Osteoporosis/diagnosis/epidemiology/complications
MH  - *Fractures, Bone/diagnosis/epidemiology/etiology
MH  - Machine Learning
PMC - PMC10226854
OTO - NOTNLM
OT  - Deep Neural Network
OT  - Genetic Risk Scores
OT  - Hormone Replacement Therapy
OT  - Machine Learning
OT  - Nutrient Intake
OT  - Osteoporosis
OT  - XGboost
COIS- The authors have no potential conflicts of interest to disclose.
EDAT- 2023/06/05 00:42
MHDA- 2023/06/06 06:42
PMCR- 2023/05/29
CRDT- 2023/06/04 18:03
PHST- 2022/11/13 00:00 [received]
PHST- 2023/02/15 00:00 [accepted]
PHST- 2023/06/06 06:42 [medline]
PHST- 2023/06/05 00:42 [pubmed]
PHST- 2023/06/04 18:03 [entrez]
PHST- 2023/05/29 00:00 [pmc-release]
AID - 38.e162 [pii]
AID - 10.3346/jkms.2023.38.e162 [doi]
PST - epublish
SO  - J Korean Med Sci. 2023 May 29;38(21):e162. doi: 10.3346/jkms.2023.38.e162.