1.Prevalence of Periodontitis in Erectile Dysfunction Patients
Hirzi Kamaludin ; Jamie Chin Kok Kwong ; Lili Zuryani Marmuji ; Khamiza Zainol Abidin
Archives of Orofacial Sciences 2022;17(SUPP 1):73-84
		                        		
		                        			ABSTRACT
		                        			Erectile dysfunction (ED) and periodontitis have common risk factors, such as diabetes mellitus 
and tobacco smoking. Multiple reports are available in regard to the association between ED and 
chronic periodontitis (CP). The study aimed to determine the association of ED and CP in selected 
Malaysian population. In this study, 74 patients (mean age = 52.4 ± 10.9 years old) diagnosed with 
ED, from scores via the International Index of Erectile Function (IIEF-5) questionnaire, were included. 
ED severity was classified as mild, mild to moderate, moderate, and severe. Periodontal condition was 
recorded using basic periodontal examination (BPE) method, of which scores of 0, 1, 2, and 3 were 
associated with having no periodontitis while a score of 4 was considered to have periodontitis. There 
are 40 (54.1%) subjects found to have periodontitis and the association of ED and periodontitis showed 
a moderate positive degree of correlation, ρ = 0.487 (p < 0.001). The percentage of subjects having 
periodontitis indicated an increasing trend with the severity of ED; from 19.0% (mild ED), 54.2% 
(mild to moderate ED), 75.0% (moderate ED), to 84.6% (severe ED). A greater degree of correlation 
was noted between dental scaling experience and ED, ρ = 0.635 (p < 0.001). Binomial logistic regression 
had shown no other co-morbidities and factors were affecting this relation. There seemed to be an 
association between ED and periodontitis existing in these selected Malaysian populations.
		                        		
		                        		
		                        		
		                        			Erectile Dysfunction
		                        			;
		                        		
		                        			 Chronic Periodontitis
		                        			;
		                        		
		                        			 Malaysia--ethnology
		                        			
		                        		
		                        	
2.Polymorphisms of the Vitamin D Receptor Gene and Sex-Differential Associations with Lipid Profiles in Chinese Han Adults.
Yan Mei CHEN ; Ping XU ; Zhou Tian WANG ; Yu Mei ZHU ; Chun Mei GONG ; Chang Hua HUANG ; Xiao Li LIU ; Ji Chang ZHOU
Biomedical and Environmental Sciences 2022;35(2):115-125
		                        		
		                        			OBJECTIVE:
		                        			To explore the association of single nucleotide polymorphisms (SNPs) of the vitamin D receptor gene ( VDR) with circulating lipids considering gender differences.
		                        		
		                        			METHODS:
		                        			Of the Han Chinese adults recruited from a health examination center for inclusion in the study, the circulating lipids, 25-hydroxyvitamin D (25OHD), and other parameters were measured. The VDR SNPs of Cdx2 (rs11568820), Fok1 (rs2228570), Apa1 (rs7975232), and Taq1 (rs731236) were genotyped with a qPCR test using blood DNA samples, and their associations with lipids were analyzed using logistic regression.
		                        		
		                        			RESULTS:
		                        			In the female participants ( n = 236 with dyslipidemia and 888 without dyslipidemia), multiple genotype models of Fok1 indicated a positive correlation of B (not A) alleles with LDLC level ( P < 0.05). In the male participants ( n = 299 with dyslipidemia and 564 without dyslipidemia), the recessive model of Cdx2 and the additive and recessive models of Fok1 differed ( P < 0.05) between the HDLC-classified subgroups, respectively, and Fok1 BB and Cdx2 TT presented interactions with 25OHD in the negative associations with HDLC ( P < 0.05).
		                        		
		                        			CONCLUSION
		                        			In the Chinese Han adults included in the study, the Fok1 B-allele of VDR was associated with higher LDLC in females, and the Fok1 B-allele and the Cdx2 T-allele of VDR were associated with lower HDLC in males. The interaction of VD and Fok1 BB or Cdx2 TT in males synergistically decreased HDLC levels.
		                        		
		                        		
		                        		
		                        			Adult
		                        			;
		                        		
		                        			Alleles
		                        			;
		                        		
		                        			Asians/genetics*
		                        			;
		                        		
		                        			China/ethnology*
		                        			;
		                        		
		                        			Dyslipidemias/genetics*
		                        			;
		                        		
		                        			Female
		                        			;
		                        		
		                        			Genetic Predisposition to Disease/genetics*
		                        			;
		                        		
		                        			Genotype
		                        			;
		                        		
		                        			Humans
		                        			;
		                        		
		                        			Lipids/blood*
		                        			;
		                        		
		                        			Male
		                        			;
		                        		
		                        			Middle Aged
		                        			;
		                        		
		                        			Polymorphism, Single Nucleotide
		                        			;
		                        		
		                        			Receptors, Calcitriol/genetics*
		                        			;
		                        		
		                        			Sex Factors
		                        			;
		                        		
		                        			Vitamin D/blood*
		                        			
		                        		
		                        	
3.Differences of body composition and physical strength among Japanese and Thai older adults living in Chiang Mai, Thailand: an inter-ethnic cross-sectional study.
Takeshi YODA ; Bumnet SAENGRUT ; Kensaku MIYAMOTO ; Rujee RATTANASATHIEN ; Tatsuya SAITO ; Yasuko ISHIMOTO ; Kanlaya CHUNJAI ; Rujirat PUDWAN ; Kawin SIRIMUENGMOON ; Hironobu KATSUYAMA
Environmental Health and Preventive Medicine 2021;26(1):97-97
		                        		
		                        			BACKGROUND:
		                        			The number of adults aged over 65 years is rapidly increasing in several Southeast Asian countries. Muscle mass decreases with age, leading to sarcopenia. The primary objective of this study was to determine whether differences exist in the body composition and physical strength, according to ethnicity, among community-dwelling Japanese and Thai older adults living in Chiang Mai Province, Thailand.
		                        		
		                        			METHODS:
		                        			A survey was conducted in February and March 2019. Japanese and Thai adults aged ≥ 60 years living in Chiang Mai Province were recruited through community clubs. Participants completed a self-administered questionnaire that enabled collection of data on age, sex, educational background, marital status, annual income, current medical conditions, smoking and alcohol consumption, and exercise habits. Measurements were collected on height, weight, body composition, blood pressure, hand grip, and walking speed for 6 m. Body composition was measured using a standing-posture 8-electrode multifrequency bioimpedance analysis analyzer. Hand grip of each hand was measured with the patient in the standing position using a digital grip dynamometer. Multivariable logistic regression was used to determine factors associated with skeletal muscle mass index (SMI).
		                        		
		                        			RESULTS:
		                        			Of the total 119 participants, 47 were Japanese (26 men, 21 women) and 72 were Thai (16 men, 56 women). The prevalence of a low SMI was 3/26 (12%), 1/21 (5%), 6/16 (38%), and 5/56 (9%) among Japanese men, Japanese women, Thai men, and Thai women, respectively. The prevalence of low muscle strength was 2/26 (8%), 2/21 (10%), 3/16 (19%), and 13/56 (23%) among Japanese men, Japanese women, Thai men, and Thai women, respectively. There were significant differences between ethnic groups in body mass index for both sexes, percentage body fat in women, SMI in men, and average grip strength in men. Ethnic group, sex, age, and body mass index were independent predictors of SMI.
		                        		
		                        			CONCLUSIONS
		                        			Ethnicity had a clinically important effect on body composition and physical strength among older Japanese and Thai adults living in a similar environment.
		                        		
		                        		
		                        		
		                        			Aged
		                        			;
		                        		
		                        			Aging/physiology*
		                        			;
		                        		
		                        			Asians/ethnology*
		                        			;
		                        		
		                        			Body Composition
		                        			;
		                        		
		                        			Body Mass Index
		                        			;
		                        		
		                        			Cross-Sectional Studies
		                        			;
		                        		
		                        			Electric Impedance
		                        			;
		                        		
		                        			Ethnicity
		                        			;
		                        		
		                        			Female
		                        			;
		                        		
		                        			Hand Strength
		                        			;
		                        		
		                        			Humans
		                        			;
		                        		
		                        			Independent Living
		                        			;
		                        		
		                        			Male
		                        			;
		                        		
		                        			Middle Aged
		                        			;
		                        		
		                        			Muscle Strength
		                        			;
		                        		
		                        			Thailand/ethnology*
		                        			;
		                        		
		                        			Walking Speed
		                        			
		                        		
		                        	
4.Assessment of Prognostic Factors of Racial Disparities in Testicular Germ Cell Tumor Survival in the United States (1992-2015).
Jing WU ; Yi Bing JI ; Bi Wei TANG ; Matthew BROWN ; Bao Hua WANG ; Chen Lei DU ; Jian Shu DU ; Xue Mei WANG ; Li Jun CAI ; Guo Yi WU ; Yan ZHOU
Biomedical and Environmental Sciences 2021;34(2):152-162
		                        		
		                        			Objective:
		                        			Testicular germ cell tumors (TGCT) are the most common cancer among men aged 15 to 39 years. Previous studies have considered factors related to TGCT survival rate and race/ethnicity, but histological type of the diagnosed cancer has not yet been thoroughly assessed.
		                        		
		                        			Methods:
		                        			The data came from 42,854 eligible patients from 1992 to 2015 in the Surveillance Epidemiology and End Results 18. Frequencies and column percent by seminoma and nonseminoma subtypes were determined for each covariates. We used Cox proportional hazard regression to assess the impact of multiple factors on post-diagnostic mortality of TGCT.
		                        		
		                        			Results:
		                        			Black males were diagnosed at a later stage, more commonly with local or distant metastases. The incidence of TGCT in black non-seminoma tumors increased most significantly. The difference in survival rates between different ethnic and histological subtypes, overall survival (OS) in patients with non-seminoma was significantly worse than in patients with seminoma. The most important quantitative predictor of death was the stage at the time of diagnosis, and older diagnostic age is also important factor affecting mortality.
		                        		
		                        			Conclusion
		                        			Histological type of testicular germ cell tumor is an important factor in determining the prognosis of testicular cancer in males of different ethnic groups.
		                        		
		                        		
		                        		
		                        			Adult
		                        			;
		                        		
		                        			Health Status Disparities
		                        			;
		                        		
		                        			Humans
		                        			;
		                        		
		                        			Male
		                        			;
		                        		
		                        			Neoplasms, Germ Cell and Embryonal/pathology*
		                        			;
		                        		
		                        			Prognosis
		                        			;
		                        		
		                        			Risk Factors
		                        			;
		                        		
		                        			SEER Program/statistics & numerical data*
		                        			;
		                        		
		                        			Seminoma/pathology*
		                        			;
		                        		
		                        			Survival Rate/trends*
		                        			;
		                        		
		                        			Testicular Neoplasms/pathology*
		                        			;
		                        		
		                        			United States/ethnology*
		                        			
		                        		
		                        	
5.Physical Activity and Sedentary Behaviors among Chinese Children: Recent Trends and Correlates.
Xi YANG ; Alice Waiyi LEUNG ; Russell JAGO ; Shi Cheng YU ; Wen Hua ZHAO
Biomedical and Environmental Sciences 2021;34(6):425-438
		                        		
		                        			Objective:
		                        			This study was aimed at examining the trends and correlates of physical activity (PA) and sedentary behaviors among Chinese children.
		                        		
		                        			Methods:
		                        			A total of 4,341 subjects (6,936 observations) aged 6-17 years who participated in the China Health and Nutrition Survey (2004-2015) were included. Of the subjects, 41% participated in the survey twice or more. Random-effects ordinal regression models and repeated-measures mixed-effects models were used to examine the PA trends. Quantile regression models were applied to examine the factors influencing PA and sedentary behaviors.
		                        		
		                        			Results:
		                        			From 2004 to 2015, the prevalence of physical inactivity among Chinese children aged 6-17 years increased by 5.5% [odds ratio ( 
		                        		
		                        			Conclusions
		                        			A declining PA trend among Chinese children aged 6-17 years was observed from 2004 to 2015, and certain subgroups and geographical areas are at higher risk of physical inactivity.
		                        		
		                        		
		                        		
		                        			Adolescent
		                        			;
		                        		
		                        			Asian Continental Ancestry Group/statistics & numerical data*
		                        			;
		                        		
		                        			Child
		                        			;
		                        		
		                        			Child Behavior/ethnology*
		                        			;
		                        		
		                        			China/epidemiology*
		                        			;
		                        		
		                        			Exercise
		                        			;
		                        		
		                        			Female
		                        			;
		                        		
		                        			Humans
		                        			;
		                        		
		                        			Male
		                        			;
		                        		
		                        			Nutrition Surveys
		                        			;
		                        		
		                        			Regression Analysis
		                        			;
		                        		
		                        			Sedentary Behavior/ethnology*
		                        			
		                        		
		                        	
6.Determinants of alcohol consumption and marijuana use among young adults in the Republic of Palau.
Mizuki SATA ; Renzhe CUI ; Chifa CHIANG ; Singeru Travis SINGEO ; Berry Moon WATSON ; Hiroshi YATSUYA ; Kaori HONJO ; Takashi MITA ; Everlynn Joy TEMENGIL ; Sherilynn MADRAISAU ; Kazumasa YAMAGISHI ; Atsuko AOYAMA ; Hiroyasu ISO
Environmental Health and Preventive Medicine 2021;26(1):12-12
		                        		
		                        			BACKGROUND:
		                        			This study aimed to describe the status of alcohol consumption and drug use among young adults as well as their determinants.
		                        		
		                        			METHODS:
		                        			We conducted a cross-sectional study of 356 young adults (aged 18 to 24 years) living in Palau in 2013. The prevalence of self-reported alcohol and marijuana usage were compared within and between sexes, age groups, ethnicities, and education levels.
		                        		
		                        			RESULTS:
		                        			The proportion of current drinking was higher in people aged 21-24 than in those aged 18-20 (73.2% vs. 60.9%, p = 0.09 in men and 48.3% vs. 30.0%, p = 0.02 in women), while that of marijuana use did not differ between the age groups. The proportions of current drinking and marijuana use were higher in Palauan than in other ethnicities (current drinking: 70.6% vs. 40.6%, p = 0.005 in men and 38.8% vs. 16.6%, p = 0.04 in women; lifetime marijuana use: 80.0% vs. 52.9%, p = 0.02 in men and 56.1% vs. 30.6%, p = 0.09 in women). The proportion of frequent (3 times or more) marijuana users was higher for the lower educated than for the higher educated (62.5% vs. 32.1%, p < 0.001 in men and 33.9% vs. 24.4%, p = 0.12 in women).
		                        		
		                        			CONCLUSIONS
		                        			Sex, age, ethnicity, and education were significant determinants of alcohol and marijuana use.
		                        		
		                        		
		                        		
		                        			Age Factors
		                        			;
		                        		
		                        			Alcohol Drinking/ethnology*
		                        			;
		                        		
		                        			Cross-Sectional Studies
		                        			;
		                        		
		                        			Educational Status
		                        			;
		                        		
		                        			Female
		                        			;
		                        		
		                        			Humans
		                        			;
		                        		
		                        			Male
		                        			;
		                        		
		                        			Marijuana Use/ethnology*
		                        			;
		                        		
		                        			Palau/epidemiology*
		                        			;
		                        		
		                        			Prevalence
		                        			;
		                        		
		                        			Sex Factors
		                        			;
		                        		
		                        			Young Adult
		                        			
		                        		
		                        	
7.Dose-dependent Cardiac Dysfunction and Structural Damage in Rats after Shortwave Radiation.
Jing ZHANG ; Chao YU ; Bin Wei YAO ; Hui WANG ; Li ZHAO ; Xin Ping XU ; Ji DONG ; Hao Yu WANG ; Yan Hui HAO ; Rui Yun PENG
Biomedical and Environmental Sciences 2020;33(8):603-613
		                        		
		                        			Objective:
		                        			To detect the effects of shortwave radiation on dose-dependent cardiac structure and function in rats after radiation and to elucidate the mechanism of shortwave radiation induced cardiac injury to identify sensitive indicators and prophylactic treatment.
		                        		
		                        			Methods:
		                        			One hundred Wistar rats were either exposed to 27 MHz continuous shortwave at a power density of 5, 10, and 30 mW/cm for 6 min or undergone sham exposure for the control (the rats had to be placed in the exposure system with the same schedules as the exposed animals, but with an inactive antenna). The Ca , glutamic oxaloacetic transaminase (AST), creatine kinase (CK) and lactate dehydrogenase (LDH) content in the peripheral serum of the rats were detected by an automatic blood biochemical analyser. The electrocardiogram (ECG) of standard lead II was recorded by a multi-channel physiological recording and analysis system. The cardiac structure of rats was observed by light and electron microscopy.
		                        		
		                        			Results:
		                        			The results showed that the 5, 10, and 30 mW/cm shortwave radiation caused a significant increased in the levels of Ca , AST, CK, and LDH in the peripheral serum of rats. The cardiac structure was damaged by radiation and showed a disordered arrangement of myocardial fibres, the cavitation and swelling of myocardial mitochondria. These injuries were most significant 7 d after radiation and were not restored until 28 d after radiation.
		                        		
		                        			Conclusion
		                        			Shortwave radiation of 5, 10, and 30 mW/cm can damage rat cardiac function, including damage to the tissue structure and ultrastructure, especially at the level of the myocardial fibres and mitochondria. Shortwave radiation at 5, 10, and 30 mW/cm induced damage to rat heart function and structure with a dose-effect relationship, i.e., the greater the radiation dose was, the more significant the damage was.
		                        		
		                        		
		                        		
		                        			Animals
		                        			;
		                        		
		                        			Dose-Response Relationship, Radiation
		                        			;
		                        		
		                        			Heart
		                        			;
		                        		
		                        			radiation effects
		                        			;
		                        		
		                        			Heart Diseases
		                        			;
		                        		
		                        			ethnology
		                        			;
		                        		
		                        			pathology
		                        			;
		                        		
		                        			physiopathology
		                        			;
		                        		
		                        			Male
		                        			;
		                        		
		                        			Myocardium
		                        			;
		                        		
		                        			pathology
		                        			;
		                        		
		                        			Radio Waves
		                        			;
		                        		
		                        			adverse effects
		                        			;
		                        		
		                        			Random Allocation
		                        			;
		                        		
		                        			Rats
		                        			;
		                        		
		                        			Rats, Wistar
		                        			
		                        		
		                        	
8.Relationship between sleep duration and TV time with cardiometabolic risk in adolescents.
Ana Paula SEHN ; Anelise Reis GAYA ; Arieli Fernandes DIAS ; Caroline BRAND ; Jorge MOTA ; Karin Allor PFEIFFER ; Javier Brazo SAYAVERA ; Jane Dagmar Pollo RENNER ; Cézane Priscila REUTER
Environmental Health and Preventive Medicine 2020;25(1):42-42
		                        		
		                        			OBJECTIVE:
		                        			To verify the association between sleep duration and television time with cardiometabolic risk and the moderating role of age, gender, and skin color/ethnicity in this relationship among adolescents.
		                        		
		                        			METHODS:
		                        			Cross-sectional study with 1411 adolescents (800 girls) aged 10 to 17 years. Television time, sleep duration, age, gender, and skin color/ethnicity were obtained by self-reported questionnaire. Cardiometabolic risk was evaluated using the continuous metabolic risk score, by the sum of the standard z-score values for each risk factor: high-density lipoprotein cholesterol, triglycerides, glycemia, cardiorespiratory fitness, systolic blood pressure, and waist circumference. Generalized linear regression models were used.
		                        		
		                        			RESULTS:
		                        			There was an association between television time and cardiometabolic risk (β, 0.002; 95% CI, 0.001; 0.003). Short sleep duration (β, 0.422; 95% CI, 0.012; 0.833) was positively associated with cardiometabolic risk. Additionally, age moderated the relationship between television time and cardiometabolic risk (β, - 0.009; 95% CI, - 0.002; - 0.001), suggesting that this relationship was stronger at ages 11 and 13 years (β, 0.004; 95% CI, 0.001; 0.006) compared to 13 to 15 years (β, 0.002; 95% CI, 0.001; 0.004). No association was found in older adolescents (β, 0.001; 95% CI, - 0.002; 0.002).
		                        		
		                        			CONCLUSIONS
		                        			Television time and sleep duration are associated with cardiometabolic risk; adolescents with short sleep have higher cardiometabolic risk. In addition, age plays a moderating role in the relationship between TV time and cardiometabolic risk, indicating that in younger adolescents the relationship is stronger compared to older ones.
		                        		
		                        		
		                        		
		                        			Age Factors
		                        			;
		                        		
		                        			Brazil
		                        			;
		                        		
		                        			epidemiology
		                        			;
		                        		
		                        			Cardiovascular Diseases
		                        			;
		                        		
		                        			epidemiology
		                        			;
		                        		
		                        			ethnology
		                        			;
		                        		
		                        			etiology
		                        			;
		                        		
		                        			Cross-Sectional Studies
		                        			;
		                        		
		                        			Metabolic Syndrome
		                        			;
		                        		
		                        			epidemiology
		                        			;
		                        		
		                        			ethnology
		                        			;
		                        		
		                        			etiology
		                        			;
		                        		
		                        			Prevalence
		                        			;
		                        		
		                        			Risk Factors
		                        			;
		                        		
		                        			Sedentary Behavior
		                        			;
		                        		
		                        			ethnology
		                        			;
		                        		
		                        			Sex Factors
		                        			;
		                        		
		                        			Sleep
		                        			;
		                        		
		                        			Television
		                        			;
		                        		
		                        			statistics & numerical data
		                        			
		                        		
		                        	
9.Combined Effects of A Body Shape Index and Serum C-reactive Protein on Ischemic Stroke Incidence among Mongolians in China.
Guang Li WANG ; Rui ZHANG ; Yi Ting ZHOU ; Ai Li WANG ; Tian XU ; Ming Zhi ZHANG ; Hong Mei LI ; Yong Hong ZHANG
Biomedical and Environmental Sciences 2019;32(3):169-176
		                        		
		                        			OBJECTIVE:
		                        			We aimed to evaluate the combined effects of a high body shape index (ABSI) and a high serum C-reactive protein (CRP) level on the incidence of ischemic stroke in a Mongolian population in China.
		                        		
		                        			METHODS:
		                        			A prospective cohort study was conducted among 2,589 participants from June 2002 to July 2012 in Inner Mongolia, China. The participants were categorized into 4 groups according to their level of ABSI and CRP. Cox proportional hazards models were used to assess the hazard ratios (HRs) and 95% confidence intervals (CIs) for ischemic stroke among all groups.
		                        		
		                        			RESULTS:
		                        			The multivariate adjusted HRs (95% CI) of ischemic stroke for high ABSI and high CRP level were 1.46 (0.89-2.39) and 1.63 (0.95-2.79), respectively. Compared with the low ABSI/low CRP level group, the multivariate adjusted HRs (95% CI) of ischemic stroke in the low ABSI/high CRP, high ABSI/low CRP, and high ABSI/high CRP groups were 1.04 (0.46-2.35), 1.06 (0.58-1.95) and 2.52 (1.27-5.00), respectively. The HR of ischemic stroke for the high ABSI/high CRP level group was the highest and most statistically significant.
		                        		
		                        			CONCLUSION
		                        			We found that participants with simultaneously high ABSI and high CRP levels had the highest risk of ischemic stroke in the Mongolian population. Our findings suggest that the combination of high ABSI and high CRP levels may increase the risk of ischemic stroke.
		                        		
		                        		
		                        		
		                        			Adult
		                        			;
		                        		
		                        			Aged
		                        			;
		                        		
		                        			Anthropometry
		                        			;
		                        		
		                        			Brain Ischemia
		                        			;
		                        		
		                        			epidemiology
		                        			;
		                        		
		                        			etiology
		                        			;
		                        		
		                        			C-Reactive Protein
		                        			;
		                        		
		                        			metabolism
		                        			;
		                        		
		                        			China
		                        			;
		                        		
		                        			epidemiology
		                        			;
		                        		
		                        			Female
		                        			;
		                        		
		                        			Humans
		                        			;
		                        		
		                        			Incidence
		                        			;
		                        		
		                        			Male
		                        			;
		                        		
		                        			Middle Aged
		                        			;
		                        		
		                        			Mongolia
		                        			;
		                        		
		                        			ethnology
		                        			;
		                        		
		                        			Proportional Hazards Models
		                        			;
		                        		
		                        			Prospective Studies
		                        			;
		                        		
		                        			Risk Factors
		                        			;
		                        		
		                        			Stroke
		                        			;
		                        		
		                        			epidemiology
		                        			;
		                        		
		                        			etiology
		                        			
		                        		
		                        	
10.Regression Algorithm of Bone Age Estimation of Knee-joint Based on Principal Component Analysis and Support Vector Machine.
Yi Yang LEI ; Yu Shu SHEN ; Ya Hui WANG ; Hu ZHAO
Journal of Forensic Medicine 2019;35(2):194-199
		                        		
		                        			
		                        			Objective To establish a regression algorithm model that applies to bone age estimation of Xinjiang Uygur adolescents with machine learning methods such as histogram of oriented gradient (HOG), local binary patterns (LBP), support vector machine (SVM), principal component analysis (PCA). Methods DR images of knee-joints from 275 male and 225 female subjects aged 12.0-<19.0 years old were collected, PCA method was used to reduce the dimensionality of the HOG and LBP features, and support vector regression (SVR) was used to establish a knee-joint bone age estimation algorithm model. Stratified random sampling method was used to select 215 male samples, 180 female samples for the model training set. K-fold cross validation method was used to optimize parameters of the model. The remaining samples as the independent test set was used to compare the sample's true age and model estimated age, and had an accuracy rate in the statistical error range of ±0.8 and ±1.0 years, respectively. Then the mean absolute error (MAE) and root mean square error (RMSE) were calculated. Results The accuracy rate of male in the statistical error range of ±0.8 and ±1.0 year was 80.67%, 89.33%, respectively. The MAE and RMSE were 0.486 and 0.606 years, respectively. The accuracy rate of female in the statistical error range of ±0.8 and ±1.0 years was 80.19%, 90.45%, respectively. The MAE and RMSE were 0.485 and 0.590 years, respectively. Conclusion Establishment of prediction model for bone age estimation by feature dimension reduction of HOG and LBP in DR images of knee-joint based on PCA and SVM has relatively high accuracy.
		                        		
		                        		
		                        		
		                        			Adolescent
		                        			;
		                        		
		                        			Adult
		                        			;
		                        		
		                        			Age Determination by Skeleton/methods*
		                        			;
		                        		
		                        			Algorithms
		                        			;
		                        		
		                        			Asian People/ethnology*
		                        			;
		                        		
		                        			China
		                        			;
		                        		
		                        			Female
		                        			;
		                        		
		                        			Humans
		                        			;
		                        		
		                        			Image Processing, Computer-Assisted
		                        			;
		                        		
		                        			Knee Joint/diagnostic imaging*
		                        			;
		                        		
		                        			Machine Learning
		                        			;
		                        		
		                        			Male
		                        			;
		                        		
		                        			Principal Component Analysis
		                        			;
		                        		
		                        			Support Vector Machine
		                        			;
		                        		
		                        			Young Adult
		                        			
		                        		
		                        	
            

Result Analysis
Print
Save
E-mail