BACKGROUND: Sarcopenia is an age-related progressive skeletal muscle disorder involving the loss of muscle mass or strength and physiological function. Efficient and precise AI algorithms may play a significant role in the diagnosis of sarcopenia. In this study, we aimed to develop a machine learning model for sarcopenia diagnosis using clinical characteristics and laboratory indicators of aging cohorts. METHODS: We developed models of sarcopenia using the baseline data from the West China Health and Aging Trend (WCHAT) study. For external validation, we used the Xiamen Aging Trend (XMAT) cohort. We compared the support vector machine (SVM), random forest (RF), eXtreme Gradient Boosting (XGB), and Wide and Deep (W&D) models. The area under the receiver operating curve (AUC) and accuracy (ACC) were used to evaluate the diagnostic efficiency of the models. RESULTS: The WCHAT cohort, which included a total of 4057 participants for the training and testing datasets, and the XMAT cohort, which consisted of 553 participants for the external validation dataset, were enrolled in this study. Among the four models, W&D had the best performance (AUC = 0.916 ± 0.006, ACC = 0.882 ± 0.006), followed by SVM (AUC =0.907 ± 0.004, ACC = 0.877 ± 0.006), XGB (AUC = 0.877 ± 0.005, ACC = 0.868 ± 0.005), and RF (AUC = 0.843 ± 0.031, ACC = 0.836 ± 0.024) in the training dataset. Meanwhile, in the testing dataset, the diagnostic efficiency of the models from large to small was W&D (AUC = 0.881, ACC = 0.862), XGB (AUC = 0.858, ACC = 0.861), RF (AUC = 0.843, ACC = 0.836), and SVM (AUC = 0.829, ACC = 0.857). In the external validation dataset, the performance of W&D (AUC = 0.970, ACC = 0.911) was the best among the four models, followed by RF (AUC = 0.830, ACC = 0.769), SVM (AUC = 0.766, ACC = 0.738), and XGB (AUC = 0.722, ACC = 0.749). CONCLUSIONS: The W&D model not only had excellent diagnostic performance for sarcopenia but also showed good economic efficiency and timeliness. It could be widely used in primary health care institutions or developing areas with an aging population. TRIAL REGISTRATION Chictr.org, ChiCTR 1800018895.
Humans ; Aged ; Sarcopenia/diagnosis* ; Deep Learning ; Aging ; Algorithms ; Biomarkers

OBJECTIVES: Patients with head and neck cancer (HNC) have a high risk of sarcopenia, which is associated with poor prognosis. Skeletal-muscle area and index at the third lumbar (L3) vertebra level (L3MA and L3MI) are recommended for the detection of sarcopenia. However, L3 level is not included in many imaging protocols and there are no data for optimal levels and cutoffs for the diagnosis of sarcopenia in head and neck computed tomography (HNCT) scans. Our aim was to assess the relationship between cervical paravertebral muscle values and L3MI and to investigate optimal level to diagnose sarcopenia on HNCTs. METHODS: Patients with HNC (n=159) who underwent positron emission tomography-CT for tumor staging were retrospectively analyzed. On CT images, paravertebral and sternocleidomastoid muscle areas at second (C2), third (C3), and fourth (C4) cervical vertebrae levels (C2MA, C3MA, C4MA, SCMA) and L3MA were measured. Cross-sectional areas were normalized for stature (muscle area/height square) and muscle index (C2MI, C3MI, C4MI, SCMI, L3MI) values were obtained. Spearman correlation and linear regression analyses were used for assessing correlations. To calculate the diagnostic performance of SCMI, C2MI, C3MI, and C4MI for the diagnosis of sarcopenia with respect to the cutoffs of L3MI, receiver operating characteristic (ROC) analysis was used. RESULTS: Males had significantly higher muscle areas than females. Although C2MI, C3MI, C4MI, and SCMI values all showed very strong and significant correlation with L3MI (P<0.001). According to the ROC analysis, the best discriminative for sarcopenia was C3MI in males (area under curve [AUC], 0.967) and SCMI in females (AUC, 0.898). CONCLUSION: C2MI, C3MI, C4MI, and SCMI values can be used as alternatives for the diagnosis of sarcopenia in routine HNCT examinations.
Body Mass Index ; Cervical Vertebrae ; Diagnosis ; Electrons ; Female ; Head and Neck Neoplasms ; Head ; Humans ; Image Processing, Computer-Assisted ; Linear Models ; Male ; Neck ; Neoplasm Staging ; Prognosis ; Retrospective Studies ; ROC Curve ; Sarcopenia ; Spine

BACKGROUND: We determined the prevalence of sarcopenia according to fracture site and evaluated the associated risk factors in female patients with osteoporotic fractures. METHODS: A total of 108 patients aged 50 years or older with an osteoporotic fracture (hip, spine, or wrist) were enrolled in this retrospective observational study. A diagnosis of sarcopenia was confirmed using whole-body densitometry for skeletal muscle mass measurement. Logistic regression analysis was used to analyze the risk factors for sarcopenia. RESULTS: Of 108 female patients treated for osteoporotic fractures between January 2016 and June 2017, sarcopenia was diagnosed in 39 (36.1%). Of these, 41.5% (17/41) had hip fractures, 35% (14/40) had spine fractures, and 29.6% (8/27) had distal radius fractures. Body mass index (BMI; P=0.036) and prevalence of chronic kidney disease (CKD; P=0.046) and rheumatoid arthritis (P=0.051) were significantly different between the groups. In multivariable analysis, BMI (odds ratio [OR], 0.76; 95% confidence interval [CI], 0.55–1.05, P=0.098) and CKD (OR 2.51; 95% CI, 0.38–16.2; P=0.233) were associated with an increased risk of sarcopenia; however, this was not statistically significant. CONCLUSIONS: This study evaluated the prevalence of sarcopenia according to the fracture site and identified associated risk factors in patients with osteoporotic fractures. A longterm, observational study with a larger population is needed to validate our results.
Arthritis, Rheumatoid ; Body Mass Index ; Densitometry ; Diagnosis ; Female ; Hip Fractures ; Humans ; Logistic Models ; Muscle, Skeletal ; Observational Study ; Osteoporosis ; Osteoporotic Fractures ; Prevalence ; Radius Fractures ; Renal Insufficiency, Chronic ; Retrospective Studies ; Risk Factors ; Sarcopenia ; Spine

BACKGROUND: We sought to develop a novel index based on the skeletal muscle mass that reflects the change of quality of life (QOL), and is the most appropriate index for the body composition of the elderly in Korea. Whether lower extremity skeletal muscle mass index (LESMI) is an appropriate novel new index to diagnose patients with sarcopenia was also evaluated. A cut-off value for each index was reported to facilitate the diagnosis of patients with sarcopenia in a Korean population. METHODS: We used the 5th Korean National Health and Nutrition Examination Survey data from 2010. We analyzed 409 elderly patients, including 231 men and 178 women, aged ≥65 years. Patients were diagnosed by calculating their skeletal muscle index based on the skeletal muscle mass measured using dual energy X-ray absorptiometry. Obesity and osteoporosis were used to screen data and EuroQOL-5 dimension as a health questionnaire. RESULTS: The prevalence of sarcopenia in each index was obtained based on its cut-off value for diagnosing sarcopenia. There was a significant difference between the obesity rate of elderly patients diagnosed with sarcopenia and those who were not based on each index. There was no significant difference in the prevalence of osteoporosis between the groups. Sarcopenia diagnosis based on the LESMI was significantly correlated with QOL. CONCLUSIONS: LESMI, a novel index based on skeletal muscle mass, reflects changes in QOL and is appropriate for the body composition of elderly people in Korea.
Absorptiometry, Photon ; Aged ; Body Composition ; Diagnosis ; Female ; Humans ; Korea ; Lower Extremity ; Male ; Muscle, Skeletal ; Nutrition Surveys ; Obesity ; Osteoporosis ; Prevalence ; Quality of Life ; Sarcopenia

Sarcopenia was listed in the International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) as M62.84, on October 1, 2016. Sarcopenia is primarily associated with metabolic diseases, such as diabetes, obesity, and cachexia, as well as chronic renal failure, congestive heart failure, and chronic obstructive pulmonary disease. Sarcopenia is also significantly associated with osteoporosis in elderly populations and the combined disease is defined as osteosarcopenia. Several studies have confirmed that sarcopenia and osteoporosis (osteosarcopenia) share common risk factors and biological pathways. Osteosarcopenia is associated with significant physical disability, representing a significant threat to the loss of independence in later life. However, the pathophysiology and diagnosis of osteosarcopenia are not fully defined. Additionally, pharmacologic and hormonal treatments for sarcopenia are undergoing clinical trials. This review summarizes the epidemiology, pathophysiology, diagnosis, and treatment of osteosarcopenia, and includes Korean data.
Aged ; Cachexia ; Diagnosis ; Epidemiology ; Heart Failure ; Humans ; International Classification of Diseases ; Kidney Failure, Chronic ; Korea ; Metabolic Diseases ; Obesity ; Osteoporosis ; Pulmonary Disease, Chronic Obstructive ; Risk Factors ; Sarcopenia

OBJECTIVES: This study evaluated the relationship between the skeletal muscle mass (SMM), obtained by predictive equations, and the body composition, nutritional aspects, functionality and physical performance in elderly people. METHODS: The sample consisted of adults aged 65 years or over from the cross-sectional study of the Brazilian Elderly Frailty Study Network, in Cuiabá, Mato Grosso State, Brazil. The anthropometric parameters, instrumental activities of daily living (IADL), Short Physical Performance Battery (SPPB), and handgrip strength (HGS) were evaluated. The SMM was estimated by 2 predictive anthropometric equations. RESULTS: Both SMM equations correlated with age, anthropometric indices, SPPB, IADL, and HGS. However, only HGS and neck circumference strongly correlated in both equations, being higher in SMM II. CONCLUSIONS: It seems that both equations are sensitive to obtain the SMM, contributing to the diagnosis of sarcopenia, nutritional status, and a physical performance condition.
Activities of Daily Living ; Adult ; Aged ; Body Composition ; Brazil ; Cross-Sectional Studies ; Diagnosis ; Humans ; Muscle, Skeletal ; Neck ; Nutritional Status ; Sarcopenia

BACKGROUND: The aim of this study was to determine the accuracy and error range of hand grip strength measurement using various methods. METHODS: Methods used for measurement of hand grip strength in 34 epidemiologic studies on sarcopenia were analyzed. Maximum grip strength was measured in a sitting position with the elbow flexed at 90 degrees, the shoulder in 0 degrees flexion, and the wrist in neutral position (0 degrees). Maximum grip strength in standing position was measured with the shoulder in 180 degrees flexion, the elbow fully extended, and the wrist in neutral position (0 degrees). Three measurements were taken on each side at 30 sec intervals. The uncertainty of measurement was calculated. RESULTS: The combined uncertainty in sitting position on the right and left sides was 1.14% and 0.38%, respectively, and the combined uncertainty in standing position on the right and left sides was 0.35 and 1.20, respectively. The expanded uncertainty in sitting position on the right and left sides was 2.28 and 0.79, respectively, and the expanded uncertainty in standing position on the right and left sides was 0.71 and 2.41, respectively (k=2). CONCLUSIONS: Uncertainty of hand grip strength measurement was identified in this study, and a significant difference was observed between measurement. For more precise diagnosis of sarcopenia, dynamometers need to be corrected to overcome uncertainty.
Diagnosis ; Elbow ; Epidemiologic Studies ; Hand Strength* ; Hand* ; Humans ; Posture ; Sarcopenia* ; Shoulder ; Uncertainty* ; Wrist

The prevalence of chronic diseases including osteoporosis and sarcopenia increases as the population ages. Osteoporosis and sarcopenia are commonly associated with genetics, mechanical factors, and hormonal factors and primarily associated with aging. Many older populations, particularly those with frailty, are likely to have concurrent osteoporosis and sarcopenia, further increasing their risk of disease-related complications. Because bones and muscles are closely interconnected by anatomy, metabolic profile, and chemical components, a diagnosis should be considered for both sarcopenia and osteoporosis, which may be treated with optimal therapeutic interventions eliciting pleiotropic effects on both bones and muscles. Exercise training has been recommended as a promising therapeutic strategy to encounter the loss of bone and muscle mass due to osteosarcopenia. To stimulate the osteogenic effects for bone mass accretion, bone tissues must be exposed to mechanical load exceeding those experienced during daily living activities. Of the several exercise training programs, resistance exercise (RE) is known to be highly beneficial for the preservation of bone and muscle mass. This review summarizes the mechanisms of RE for the preservation of bone and muscle mass and supports the clinical evidences for the use of RE as a therapeutic option in osteosarcopenia.
Activities of Daily Living ; Aging ; Bone and Bones ; Bone Density ; Chronic Disease ; Diagnosis ; Education ; Genetics ; Metabolome ; Muscle Strength ; Muscles ; Osteoporosis ; Prevalence ; Sarcopenia

BACKGROUND: This study evaluated the prevalence of osteosarcopenia, as well as the relationship between one-year mortality and osteosarcopenia, as defined by criteria of the Asian Working Group on Sarcopenia in patients age 60 or older with hip fracture. METHODS: A total of 324 patients age 60 years or older with hip fracture were enrolled in this retrospective observational study. The main outcome measure was the prevalence of osteosarcopenia, as well as the relationship between osteosarcopenia and 1-year mortality. The diagnosis of sarcopenia was carried out according to the Asian Working Group on Sarcopenia. Whole body densitometry analysis was used for skeletal muscle mass measurement and muscle strength were evaluated by handgrip testing. Mortality was assessed at the end of 1-year. Cox regression analysis was utilized to analyze the risk factor of osteosarcopenia. RESULTS: Of 324 patients with hip fracture, 93 (28.7%) were diagnosed with osteosarcopenia. In total, 9.0% died during the one-year follow-up. A one-year mortality of osteosarcopenia (15.1%) was higher than that of other groups (normal: 7.8%, osteoporosis only: 5.1%, sarcopenia only: 10.3%). Osteosarcopenia had a 1.8 times higher mortality rate than non-osteosarcopenia. CONCLUSION: The present study demonstrates that the prevalence of osteosarcopenia is not rare, and has a higher mortality rate than the non-osteosarcopenia group at the 1-year follow-up period. This is the first study evaluating the relationship between mortality and osteosarcopenia in patients with hip fracture.
Asian Continental Ancestry Group ; Densitometry ; Diagnosis ; Follow-Up Studies ; Hip ; Humans ; Mortality ; Muscle Strength ; Muscle, Skeletal ; Observational Study ; Osteoporosis ; Outcome Assessment (Health Care) ; Prevalence ; Retrospective Studies ; Risk Factors ; Sarcopenia

OBJECTIVE: Body composition is measured using bioelectrical impedance analysis (BIA), and correlation between the result of BIA and cognitive function is analyzed. METHODS: A total of 118 elderly (46 male, 72 female) were recruited. They were divided into three groups; normal (n=33), mild cognitive impairment (n=42), and Alzheimer's dementia (n=43) according to the diagnostic criteria. Skeletal muscle mass, body fat mass, and fat-free mass were measured using a BIA device, and were converted to the ratio of body weight. All participants underwent Korean version of Mini-Mental State Examination (MMSE-K). RESULTS: In pearson correlation analysis, skeletal muscle percentage (SMP) and fat-free mass percentage (FFMP) were positively correlated with MMSE-K score (r=0.309, p=0.001; r=0.245, p=0.008), and body fat percentage was negatively correlated (r=−0.258, p=0.005). In multiple regression analysis, SMP (β=2.012, t=4.457, p < 0.001) and FFMP (β=−1.733, t=−3.838, p < 0.001) were selected as the best predictors of changes in MMSE-K score (R2=0.198). CONCLUSION: Reduced skeletal muscle and increased body fat correlate with decreased cognitive function, suggesting the need for prevention of frailty and early diagnosis of cognitive impairment.
Adipose Tissue ; Aged ; Body Composition* ; Body Weight ; Cognition Disorders ; Cognition* ; Dementia ; Early Diagnosis ; Electric Impedance* ; Humans ; Male ; Mild Cognitive Impairment ; Muscle, Skeletal ; Sarcopenia