INTRODUCTION: Obstructive sleep apnoea (OSA) is a serious but underdiagnosed condition. Demand for the gold standard diagnostic polysomnogram (PSG) far exceeds its availability. More efficient diagnostic methods are needed, even in tertiary settings. Machine learning (ML) models have strengths in disease prediction and early diagnosis. We explored the use of ML with oximetry, demographic and anthropometric data to diagnose OSA. METHODS: A total of 2,996 patients were included for modelling and divided into test and training sets. Seven commonly used supervised learning algorithms were trained with the data. Sensitivity (recall), specificity, positive predictive value (PPV) (precision), negative predictive value, area under the receiver operating characteristic curve (AUC) and F1 measure were reported for each model. RESULTS: In the best performing four-class model (neural network model predicting no, mild, moderate or severe OSA), a prediction of moderate and/or severe disease had a combined PPV of 94%; one out of 335 patients had no OSA and 19 had mild OSA. In the best performing two-class model (logistic regression model predicting no-mild vs. moderate-severe OSA), the PPV for moderate-severe OSA was 92%; two out of 350 patients had no OSA and 26 had mild OSA. CONCLUSION Our study showed that the prediction of moderate-severe OSA in a tertiary setting with an ML approach is a viable option to facilitate early identification of OSA. Prospective studies with home-based oximeters and analysis of other oximetry variables are the next steps towards formal implementation.
Humans ; Oximetry/methods* ; Sleep Apnea, Obstructive/diagnosis* ; Male ; Female ; Middle Aged ; Machine Learning ; Polysomnography ; Adult ; Anthropometry ; ROC Curve ; Aged ; Algorithms ; Predictive Value of Tests ; Sensitivity and Specificity ; Neural Networks, Computer ; Demography

OBJECTIVE: To investigate the anthropometric parameters that can accurately predict the diameter of the hamstring tendon graft, and to examine the correlation between disease etiology, duration, and graft diameter. METHODS: A retrospective analysis was conducted on data from 166 patients who underwent anterior cruciate ligament reconstruction using hamstring tendon autografts (semitendinosus and gracilis tendon) between January 2013 and December 2023. The cohort conprised 135 males and 31 females;the age ranged from 14 to 62 years old with an average of (28.87±10.46) years old. Pearson correlation coefficients, partial correlation coefficients, and stepwise multiple linear regression analysis were utilized to elucidate the relationship between the outcome variable (diameter of hamstring tendon grafts) and predictive variables (e.g., height). RESULTS: Correlation analysis revealed significant associations between the diameter of hamstring tendon grafts and height (r=0.379, P<0.001), weight (r=0.225, P=0.002), male gender (r=0.302, P<0.001), age(r=-0.218, P=0.002), and sports injury etiology (r=0.167, P=0.016). No significant correlations were found with surgical side, body mass index (BMI), or injury duration (P>0.05). Stepwise multiple linear regression analysis using a backward elimination method indicated that height was the sole significant predictive variable (R²=0.144, P<0.001), with the optimal predictive equation being:Graft size =2.636+0.029×Height (cm). Partial correlation analysis, after controlling for height, showed no significant association between age, gender, weight, and injury etiology with graft diameter. CONCLUSION Height is an effective predictive factor for the diameter of autologous hamstring tendon grafts. Factors such as gender, age, surgical side, body weight, and BMI are not influential to the diameter of the hamstring tendon grafts. Under the condition of the same height, there is no significant difference in the influence of these factors on the graft diameter. Preoperative physical activity level and the duration of injury do not significantly affect the diameter of the hamstring tendon grafts obtained during surgery. It is recommended to use the formula 'Graft Diameter=2.636 + 0.029 × Height (cm)' for preoperative prediction.
Humans ; Male ; Female ; Adult ; Middle Aged ; Retrospective Studies ; Adolescent ; Young Adult ; Transplantation, Autologous ; Anthropometry ; Anterior Cruciate Ligament Reconstruction ; Tendons/anatomy & histology* ; Autografts ; Hamstring Tendons/transplantation* ; Quadriceps Muscle/surgery*

BACKGROUND: The creatinine (Cre) concentration in urine is used as an adjustment factor in chemical exposure and nutritional intake assessments. Because Cre excretion varies by sex, age, race, and anthropometric measurements such as height and weight, developing a method suitable for estimating one-day Cre excretion is necessary. Accordingly, this study aimed to develop a predictive equation for individual one-day Cre excretion in Japanese school children. METHODS: Urine samples were collected from 113 boys and 91 girls (aged 6-12 years) from the Aichi Prefecture, Japan, who were free from diseases affecting the renal, muscle, or nervous systems. Urinary concentrations and one-day excreted amounts of Cre were measured and compared with the values obtained using previously reported equations or a fixed value, totaling 11 methods. Subsequently, we developed a new equation using machine learning and multiple regression analyses. Additionally, the estimated one-day sodium excretion value calculated using this equation was compared with the measured value. RESULTS: Among the 11 methods to predict Cre excretion, 7 overestimated-5 of which showed a positive trend bias with larger differences at higher average concentrations-and 3 underestimated-2 of which showed a negative trend bias with larger differences at lower average concentrations. A new machine learning model using sex, age, and body surface area (calculated from height and weight) yielded the most accurate prediction. Multiple regression analysis, which demonstrated the most accurate prediction, used sex, age, and body surface area as independent variables with or without the first void Cre concentration divided by urination duration from the previous night's urination to the first void. Moreover, the difference in one-day sodium excretion from first-void urine predicted using our newly developed Cre equation increased as the measured values increased. CONCLUSIONS: Our study suggests that the estimation of one-day Cre excretion based on sex, age, and body surface area is most appropriate for Japanese schoolchildren, particularly in assessing their chemical exposure and dietary nutrient intake. TRIAL REGISTRATION Trial registration is not applicable as this observational study did not involve any intervention or randomization requiring registration in a clinical trials registry.
Humans ; Child ; Female ; Male ; Japan ; Creatinine/urine* ; Anthropometry ; East Asian People

OBJECTIVE: To investigate a new noninvasive diagnostic model for nonalcoholic fatty liver disease (NAFLD) based on features of tongue images. METHODS: Healthy controls and volunteers confirmed to have NAFLD by liver ultrasound were recruited from China-Japan Friendship Hospital between September 2018 and May 2019, then the anthropometric indexes and sampled tongue images were measured. The tongue images were labeled by features, based on a brief protocol, without knowing any other clinical data, after a series of corrections and data cleaning. The algorithm was trained on images using labels and several anthropometric indexes for inputs, utilizing machine learning technology. Finally, a logistic regression algorithm and a decision tree model were constructed as 2 diagnostic models for NAFLD. RESULTS: A total of 720 subjects were enrolled in this study, including 432 patients with NAFLD and 288 healthy volunteers. Of them, 482 were randomly allocated into the training set and 238 into the validation set. The diagnostic model based on logistic regression exhibited excellent performance: in validation set, it achieved an accuracy of 86.98%, sensitivity of 91.43%, and specificity of 80.61%; with an area under the curve (AUC) of 0.93 [95% confidence interval (CI) 0.68-0.98]. The decision tree model achieved an accuracy of 81.09%, sensitivity of 91.43%, and specificity of 66.33%; with an AUC of 0.89 (95% CI 0.66-0.92) in validation set. CONCLUSIONS The features of tongue images were associated with NAFLD. Both the 2 diagnostic models, which would be convenient, noninvasive, lightweight, rapid, and inexpensive technical references for early screening, can accurately distinguish NAFLD and are worth further study.
Humans ; Non-alcoholic Fatty Liver Disease/diagnostic imaging* ; Ultrasonography ; Anthropometry ; Algorithms ; China

Objective: To determine a normative value for the nasopharyngeal depth from the anterior nasal spine (ND-ANS) among normal adult Filipinos using Computed Tomography scans. Methods: Design: Cross-sectional study. Setting: Tertiary National University Hospital. Participants: Of 516 adult patients that underwent facial, neck and temporal bone CT scans in our hospital between January 1 to June 30, 2019, 100 cases were randomized to be included in the study and 91 CT scans were analyzed. Results: The mean nasopharyngeal depth from the anterior nasal spine among Filipino adults is 7.17 ± 0.42. There was a significant difference between sexes with a mean measurement of 7.23 cm ± 0.44 in males and 7.09 ± 0.37 cm in females. There was no statistically significant difference in mean nasopharyngeal depth across age groups. Conclusion A statistically significant difference was observed between sexes in our study sample. Our study provides initial normative values of nasopharyngeal depth among adult Filipinos, and additional studies may use this as a basis for further research.
Nasopharynx ; Adult ; Anthropometry

Background: Access to nutritious food among the nutritionally at risk preschool children remains a challenge even in urban households in the Philippines. Objectives: This study determined if the daily consumption of rice-soy meals for 120 days improved the anthropometric status of preschool children enrolled in selected child development centers in low-income barangay in Taguig City. Specifically, it determined if the proportion of underweight preschool children decreased at endline and if there was an increase in the weight of preschool children at endline. Methodology: The study used the before and after study design. The Dietary Supplementation Program was implemented by the LGU’s day care teachers. An NGO supplied the rice-soy meal packs. The children were fed with different variants of rice-soy meal pack containing 23 essential micronutrients. Anthropometric measurements were taken before and after 120 days. Data were subjected to Mc Nemar’s test to determine changes in the children’s nutritional status. Results: A total of 538 children were enrolled in the DSP. Results of Mc Nemar's test showed that there was a significant improvement in the nutritional status (weight-for-age) of underweight preschool children (p=0.0000001) while the paired t-test showed that the increase in the weight of preschool children after the 120 day-dietary supplementation program was extremely statistically significant (p<0.001). Conclusion The daily feeding improved the weight of the undernourished children but overweight children maintained their overweight status at endline. The DSP Guidelines should include feeding mechanism for overweight children. The DSP complementary components should also be assessed in improving household food security.
Anthropometry

Virility and sexual pleasure have long been associated with penile size and this, in turn, has typically been linked to some anthropometric measurements, such as foot size or height, leading to various misconceptions from both men and women. Our intention is to estimate penile size parameters in Argentina and evaluate the correlation between penile size and certain anthropometric measurements. This is a cross-sectional, descriptive, multicenter, and observational study. Male patients who underwent a urological procedure were included in four hospitals located in different regions of the country. Different anthropometric measurements were obtained: height, weight, penile circumference, flaccid and stretched length, and foot length. A total of 800 patients were evaluated. Mean left foot was 26.4 cm. Mean flaccid penile length was 11.4 (95% confidence interval [CI]: 8-14) cm, and mean penile circumference was 10.1 (95% CI: 8-12) cm. Finally, mean stretched penis was 15.2 (95% CI: 11-18.5) cm. We can confirm that estimates of the average penile measurements in Argentina are flaccid penis length of 11.4 cm, penile circumference of 10.1 cm, and stretching the penis to the maximum in flaccidity of 15.2 cm. Correlations between flaccid penis length, stretched out, penile circumference, height, weight, and length of the left foot were evaluated, finding low or no correlation between those mentioned, except for flaccid and stretched length.
Humans ; Male ; Female ; Prospective Studies ; Cross-Sectional Studies ; Anthropometry ; Penis ; Body Height ; Reference Values

BACKGROUND: There is no normative craniofacial anthropometric data for the Kenyan-African population. The purpose of this investigation was to determine normative anthropometric craniofacial measurements and proportional relationships for Kenyans of African descent and to compare the data with African Americans (AA), North American Whites (NAW), and neoclassical canons. METHODS: Twenty-five direct facial anthropometric measurements, and 4 angular measurements, were taken on 72 Kenyan-African participants (age range 18–30 years) recruited at the University of Nairobi in Kenya. The data were compared with AA and NAW populations, and neoclassical canons. Descriptive statistics of the variables were computed for the study population. RESULTS: Significant differences between both Kenyan males and females were detected in forehead height (~ 5 mm greater for males, ~ 4.5 mm for females), nasal height (reduced by ~ 4 mm in males, ~ 3 mm in females), nasal width (8–9 mm greater), upper lip height (> 3 mm), and eye width (greater by ~ 3 mm) compared to NAW subjects. All vertical measurements obtained were significantly different compared with NAW. Differences were observed in comparison with AA subjects, but less marked. Mouth width was similar in all groups. Angular measurements were variable. Neoclassical canons did not apply to the Kenyan population. CONCLUSIONS: Anthropometric measurements of NAW showed clear differences when compared with the Kenyan population, and variations exist with comparative AA data. The anthropometric data in terms of linear measurements, angular measurements, and proportional values described may serve as a database for facial analysis in the Kenyan-African population.
African Americans ; Anthropometry ; Female ; Forehead ; Humans ; Kenya ; Lip ; Male ; Mouth

OBJECTIVE: The aim of this study was to determine whether low calf circumference (CC) could predict nutritional risk and the cutoff values of CC for predicting nutritional risk in hospitalized patients aged ⪖ 80 years. METHODS: A total of 1,234 consecutive patients aged ⪖ 80 years were enrolled in this study. On admission, demographic data, CC, and laboratory parameters were obtained. Patients with Nutritional Risk Screening 2002 (NRS-2002) total score ⪖ 3 were considered as having nutritional risk. RESULTS: CC values were significantly lower in patients with nutritional risk compared to those in patients without nutritional risk [27.00 (24.50-31.00) vs. 31.00 (29.00-33.50], P < 0.001]. CC was negatively correlated with age and nutritional risk scores. Logistic regression analysis of nutritional risk revealed that body mass index, albumin level, hemoglobin level, cerebral infarction, neoplasms, and CC (OR, 0.897; 95% confidence interval, 0.856-0.941; P < 0.001) were independent impact factors of nutritional risk. Nutritional risk scores increased with a decrease in CC. In men, the best CC cutoff value for predicting nutritional risk according to the NRS-2002 was 29.75 cm. In women, the cutoff value was 28.25 cm. CONCLUSION CC is a simple, noninvasive, and valid anthropometric measure to predict nutritional risk for hospitalized patients aged ⪖ 80 years.
Aged, 80 and over ; Anthropometry ; methods ; China ; Female ; Hospitalization ; statistics & numerical data ; Humans ; Leg ; anatomy & histology ; Male ; Nutritional Status ; Risk Assessment ; methods

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