Sasang Constitution Types Research Articles

Realtime Analysis of Sasang Constitution Types from Facial Features Using Computer Vision and Machine Learning

Realtime Analysis of Sasang Constitution Types from Facial Features Using Computer Vision and Machine Learning

Compound-level identification of sasang constitution type-specific personalized herbal medicine using data science approach

IntroductionSasang Constitutional Medicine (SCM) is a type of traditional Korean medicine where patients are classified as one of four Sasang constitution types (Sasang type) and medications consisting of medicinal herbs are prescribed according to the Sasang type. Despite the importance of personalized medicine, the operation mechanism is largely unknown. To gain a better understanding, we investigated the compound information that composes Sasang type-specific personalized herbal medicines on both multivariate and univariate levels. MethodsFive machine learning classifiers including extremely randomized trees (ERT) were trained to investigate whether the Sasang type can be explained by compound information at the multivariate level. Hierarchical clustering was conducted to determine whether compounds are processed distributedly or specifically. Taxonomic and biosynthetic analyses were conducted on these compounds. A univariate level statistical test was conducted to provide more robust Sasang type-specific compound information. ResultsUsing the trained ERT classifier, sixty important compounds were extracted. The sixty compounds were clustered into three groups, corresponding to each Sasang type-prominent compounds, suggesting that most compounds have specific preference for the Sasang type. Structural and biosynthetic characteristics of these Sasang type-prominent compounds were determined based on taxonomy and pathway analyses. Fourteen compounds showed statistically significant relevance with the Sasang type. Additionally, we predicted the Sasang type of unknown herbs, which were confirmed by their biological effects in functional assays. ConclusionThis study investigated the personalized herbal medicines of the SCM using compound information. This study provided information on the chemical characteristics of the compounds that are essential for classifying the Sasang type of medicinal herbs, as well as predictions regarding the Sasang type of the commonly used but unidentified medicinal herbs.

Sasang Constitution Type Combined with General Obesity May Act as a Risk Factor for Prediabetes Mellitus.

Sasang constitutional medicine is a traditional customized medicine in Korea that classifies people into four types: Taeeumin (TE), Taeyangin (TY), Soeumin (SE), and Soyangin (SY). This study explored whether Sasang constitution (SC) types combined with general obesity could be risk factors for prediabetes mellitus (pre-DM). This study was cross-sectional and was conducted from November 2007 to July 2011 in 23 Korean medical clinics. In total, 2185 eligible subjects participated. A t test, one-way ANOVA with Scheffé's post hoc analysis, the chi-square test and multinomial logistic regression were used. Significance was indicated by p < 0.05. The numbers of participants with normal fasting plasma glucose (FPG) levels and pre-DM were 405 (75.3%) and 133 (24.7%) in the SE, 516 (70.3%) and 218 (29.7%) in the SY, and 590 (64.6%) and 323 (35.4%) in the TE (p < 0.001) groups, respectively. There was a significant difference in the proportion of each SC type among people with pre-DM and normal FPG levels in the normal BMI group. The odds ratios (ORs) of the TE type were significantly different from those of the SE type in the crude and Model 1. The distribution of the normal FPG and pre-DM individuals between the obese and normal BMI groups only for the SY type was significantly different. The SY type combined with general obesity had a higher OR (1.846, 95% CI 1.286-2.649) than that combined with normal BMI among participants with pre-DM, and this higher OR remained after adjusting for covariates (OR, 1.604, 95% CI, 1.093-2.354). This study revealed that the TE type might be a risk factor for pre-DM in the normal BMI group, and the SY type with general obesity could be a risk factor for pre-DM compared with the SY type with normal BMI. Accordingly, SC and BMI should be considered when managing pre-DM. To clarify the risk of SC and BMI, further study including epigenetic factors is needed.

Individual Differences in the Association of Lifestyle with Cardiometabolic Risk in Middle-Aged Koreans Based on Traditional Korean Medicine.

Cardiometabolic (CM) risk differs in morbidity and disease progression depending on lifestyle and individual characteristics. This cross-sectional study aimed to analyze the association between CM risk and lifestyle and examine whether this association varies based on Sasang constitution (SC), a Korean medicine classification. Data were analyzed from 1996 individuals participating in the Korean Medicine Daejeon Citizen Cohort study. Individuals with CM risk had two to five CM risk factors. Lifestyle factors included physical activity, sleep duration, and eating index. SC types were Taeeum-in (TE) and non-TE. We estimated the odds ratio (OR) and 95% confidence interval for CM risk based on SC and lifestyle factors. Among the participants, 33.9% had a CM risk, and the TE and non-TE groups were 26.2% and 7.7%, respectively. In the TE group, CM risk was associated with low physical activity (OR, 1.63) and moderate eating index (OR, 1.41). In the non-TE group, CM risk was associated with ≥8 h of sleep (OR, 1.87) and marginally associated with ≤6 h of sleep. In the TE group alone, CM risk was significantly associated with lifestyle patterns that combined the three lifestyle factors and was approximately two-fold higher in patterns involving less physical activity. The effects of lifestyle on CM risk differed across SC types. To decrease the burden of cardiovascular diseases in middle-aged adults, we recommend an individualized management strategy of healthy lifestyle interventions for cardiovascular risks.

Metabolic Syndrome Prediction Models Using Machine Learning and Sasang Constitution Type.

Background Machine learning may be a useful tool for predicting metabolic syndrome (MetS), and previous studies also suggest that the risk of MetS differs according to Sasang constitution type. The present study investigated the development of MetS prediction models utilizing machine learning methods and whether the incorporation of Sasang constitution type could improve the performance of those prediction models. Methods Participants visiting a medical center for a health check-up were recruited in 2005 and 2006. Six kinds of machine learning were utilized (K-nearest neighbor, naive Bayes, random forest, decision tree, multilayer perceptron, and support vector machine), as was conventional logistic regression. Machine learning-derived MetS prediction models with and without the incorporation of Sasang constitution type were compared to investigate whether the former would predict MetS with higher sensitivity. Age, sex, education level, marital status, body mass index, stress, physical activity, alcohol consumption, and smoking were included as potentially predictive factors. Results A total of 750/2,871 participants had MetS. Among the six types of machine learning methods investigated, multiplayer perceptron and support vector machine exhibited the same performance as the conventional regression method, based on the areas under the receiver operating characteristic curves. The naive-Bayes method exhibited the highest sensitivity (0.49), which was higher than that of the conventional regression method (0.39). The incorporation of Sasang constitution type improved the sensitivity of all of the machine learning methods investigated except for the K-nearest neighbor method. Conclusion Machine learning-derived models may be useful for MetS prediction, and the incorporation of Sasang constitution type may increase the sensitivity of such models.

Machine learning-based prediction of Sasang constitution types using comprehensive clinical information and identification of key features for diagnosis

BackgroundDespite the importance of accurate Sasang type diagnosis, a unique form of Korean medicine, there have been concerns about consistency among diagnoses. We investigate a data-driven integrative diagnostic model by applying machine learning to a multicenter clinical dataset with comprehensive features. MethodsExtremely randomized trees (ERT), support vector machines, multinomial logistic regression, and K-nearest neighbor were applied, and performances were evaluated by cross-validation. The feature importance of the classifier was analyzed to understand which information is crucial in diagnosis. ResultsThe ERT classifier showed the highest performance, with an overall f1 score of 0.60±0.060. The feature classes of body measurement, personality, general information, and cold–heat were more decisive than others in classifying Sasang types. Costal angle was the most informative feature. In pairwise classification, we found Sasang type-dependent distinctions that body measurement features played a key role in TE-SE and TE-SY datasets, while personality and cold–heat features showed importance in SE-SY dataset. ConclusionCurrent study investigated a comprehensive diagnostic model for Sasang type using machine learning and achieved better performance than previous studies. This study helps data-driven decision making in clinics by revealing key features contributing to the Sasang type diagnosis.

Predictive Models for Sasang Constitution Types Using Genetic Factors

Predictive Models for Sasang Constitution Types Using Genetic Factors

Effect of Lifestyle Factors on Hypertension by Constitution Type: A Large Community-Based Study

Background. The risk of hypertension differs according to lifestyle factors and individual constitution types. The aim of this study was to investigate the effect of lifestyle factors on hypertension and to assess whether those effects differ according to the constitution types. Methods. A total of 5,793 men and women were recruited between 2012 and 2014. Odds ratios for hypertension associated with constitution types and lifestyle factors were estimated. Lifestyle factors included smoking status, body mass index, alcohol consumption, physical activity, and sleep quality. Constitution types were estimated based on the Sasang constitutional medicine as the TE type, SE type, and SY type. Results. The risk of hypertension was significantly higher for SY (odds ratio 1.25 (95% confidence interval 1.03 to 1.52) and TE types (1.38 (1.10 to 1.74)) than the SE type even with adjustment of health behaviors. Compared with individuals who had an unhealthy lifestyle, those with healthy lifestyle scores showed significantly lower risk of hypertension in only SY (odds ratio 0.62 (95% confidence interval 0.48 to 0.81)) and TE types (0.69 (0.58 to 0.81)). The difference in risk for hypertension among constitution types was decreased with a healthy lifestyle (1.34 in SY and 2.35 in TE types, as compared with the SE type) versus an unhealthy lifestyle (2.21 in SY and 3.64 in TE types, as compared with the SE type). Conclusion. The risk of hypertension was different by Sasang constitution types. The impact of lifestyle factors differed according to Sasang constitution types, and the difference in risk of hypertension among constitution types was decreased with a healthy lifestyle.

Daily-life screening of hypertension using facial imaging and a preliminary study across Sasang Constitution types

Daily-life screening of hypertension using facial imaging and a preliminary study across Sasang Constitution types

Metabolite Markers for Characterizing Sasang Constitution Type through GC-MS and 1H NMR-Based Metabolomics Study.

Sasang constitutional medicine classifies human beings into four types based on their physical and psychological characteristics. Despite its potential value in achieving personalized medicine, the diagnosis of sasang constitution (SC) type is complex and subjective. In this study, gas chromatography–mass spectrometry and 1H nuclear magnetic resonance–based metabolic analyses were conducted to find maker metabolites in serum and urine according to different SC types. Although some samples were overlapped on orthogonal projection to latent structure discriminant analysis score plots, serum samples showed separation between different SC types. Levels of lactate, glutamate, triglyceride, and fatty acids in serum and glycolic acid in urine of Tae-Eum type were higher than those of So-Eum and So-Yang type. Fatty acids, triglyceride, and lactate levels were found to be metabolites related to body mass index, indicating that marker metabolites for the diagnosis of SC type could be associated with obese. However, Tae-Eum type showed higher lactate levels in serum than So-Yang type for both normal weight and overweight groups, suggesting that the contents of serum lactate might be dependent on the SC type regardless of body weight. These results suggest that metabolomics analysis could be used to determine SC type.

Genetic and Environmental Overlaps Among Sasang Constitution Types: A Multivariate Twin Study.

According to the Sasang theory, humans can be categorized into one of the four Sasang constitution (SC) types. The four SC types are Tae-Yang (TY), Tae-Eum (TE), So-Yang (SY), and So-Eum (SE), which are determined mainly on the basis of anthropometric characteristics, personality, and the balance of the physiological functions of the major organ systems. There is a growing recognition in the complementary and alternative medicine area that SC types have the potential to be a useful scientific tool for the prevention, diagnosis, and treatment of diseases (Cooper, Evidence Based Complementary and Alternative Medicine, Vol. 6 (Suppl. 1), 2009, pp. 1-3). The main purposes of the present study are to estimate genetic and environmental influences on SC types, and to explore genetic and environmental correlations that affect phenotypic associations among the SC types. In total, 1,742 (365 monozygotic male, 173 dizygotic male, 675 monozygotic female, 271 dizygotic female, and 258 opposite-sex dizygotic) twins (mean age = 19.1 ± 3.1 year) completed a Sasang questionnaire. Univariate and multivariate model-fitting analyses were performed. Total (additive and non-additive) genetic influences were 71% for males and 81% for females in TE, 70% for males and 71% for females in SE, and 47% for both sexes in SY. Non-additive genetic effects were substantial, and shared environmental influences were negligible in most SC types. Multivariate model-fitting analysis revealed that non-additive genetic and individual-specific environmental correlations between TE and SE were -0.92 (95% CI [-0.89, -0.93]) and -0.62 (95% CI [-0.57, -0.68]), respectively. The corresponding estimates were -0.55 (95% CI [-0.48, -0.61]) and -0.44 (95% CI [-0.37, -0.51]) between TE and SY and 0.19 (95% CI [0.09, 0.29]) and -0.40 (95% CI [-0.32, -0.47]) between SE and SY. These results suggest that the phenotypic associations among SC types may be mediated by pleiotropic mechanism of genes.

Can We Determine Sasang Constitutional Body Type Merely by Facial Inspection?

This study aimed to assess the inter-observer concordance rate of anthroscopic examination on facial features among experts in Sasang constitutional medicine (SCM) in order to evaluate the presence of statistical differences in facial structural characteristics among different body types of Sasang constitution (SC), and to develop an objective method for facial analysis for diagnosing SC types to prevent SCM experts from misdiagnosis by their perceptional errors about faces. This was a double-blinded cross-sectional study conducted on 174 people's faces. Ten SCM experts participated in this study. Frontal and lateral photographs of subjects were standardized and displayed to 10 SCM experts for diagnosing the SC type by anthroscopic examination alone (experiment 1). The subjects' faces were analyzed by photogrammetric method to investigate the presence of any typical structural characteristics of the faces to differentiate SC type (experiment 2). Comparing subjects' SC type with anthroscopic diagnosis by 10 SCM experts, the inter-observer concordance rates were measured (experiment 1). Using photogrammetric facial analysis, a multinomial logistic model was made for analyzing the correlation of SC type and subjects' facial structural configuration (experiment 2). The inter-observer concordance rate of anthroscopic examination was 2.9% in experiment 1. Using a multinomial logistic fitting model, the predicted probability for determining SC type was 52.8-57.6% in experiment 2 (p < 0.05). Prototype composite faces were also created from photographs of subjects who received the same SC type from the SCM experts. As SC type cannot be precisely diagnosed using anthroscopic examination alone, SCM needs a definitive objective and scientific diagnosing method to be a scientifically verified alternative medicine and be globalized in future.

대학생활스트레스와 정신건강의 영향관계에 대한 사상체질 간 다집단 분석

대학생활스트레스와 정신건강의 영향관계에 대한 사상체질 간 다집단 분석

Changes in Body Water Caused by Sleep Deprivation in Taeeum and Soyang Types in Sasang Medicine: Prospective Intervention Study.

Background There is a negative relationship between sleep deprivation and health. However, no study has investigated the effect of sleep deprivation on individuals with different body composition. The aim of this study was to determine the differential effect of sleep deprivation in individuals with different body compositions (fluid) according to Soyang type (SY) and Taeeum type (TE). Methods Sixty-two cognitively normal, middle-aged people with normal sleep patterns were recruited from the local population. The duration of participants' sleep was restricted to 4 h/day during the intervention phase. To examine the physiological changes brought on by sleep deprivation and recovery, 10 ml of venous blood was obtained. Results Total Body Water (TBW) and Extracellular Water (ECW) were significantly different between the groups in the intervention phase. Physiological parameters also varied from the beginning of the resting phase to the end of the experiment. Potassium levels changed more in SY than TE individuals. Conclusion Participants responded differently to the same amount of sleep deprivation depending on their Sasang constitution types. This study indicated that SY individuals were more sensitive to sleep deprivation and were slower to recover from the effects of sleep deprivation than TE individuals.

한국인과 연길 거주 조선족의 체질별 체형 비교 연구(Propensity Score Matching을 활용하여)

Objectives The body shape was a key information for diagnosing the Sasang constitution (SC) in Sasang constitutional medicine. The aim of this study was to compare the body shapes and mainly focusing on the Korean and Chinese-KoreanMethods We calculated the propensity score for each SC type in males and females separately, and compared body shape including 8 circumference and 5 width between Korean and Chinese-Korean according to the sex and SC.Results Koreans have larger trunk and hip area compared to Chinese-Koreans, while Chinese-Koreans have larger abdomen compared with Koreans. Most variables were significantly different among SC types, for both Korean and Chinese-Korean. Especially, the Taeumin (TE) type has the largest body shape compared with the other SC types, it was similar between Korean and Chinese-Korean.Conclusions This study showed that the TE type has the largest body shape, followed by Soyangin (SY) and Soeumin (SE) in order, for both Korean and Chinese-Korean respectively. These results suggests that the body shape of Chinese-Korean is similar with Korean based on SC type.

Sasang Constitution May Play a Key Role in Increasing the Number of Sub-Elements of Metabolic Syndrome.

Metabolic syndrome (MS), a representative cluster of chronic diseases, is defined by the presence of three or more of the following five elements: high blood glucose, high blood pressure, low high-density lipoprotein (HDL)cholesterol, high serum triglyceride levels, and abdominal obesity. Recently, innate factors have been continuously demonstrated as important risk factors for increasing the number of MS sub-elements. Sasang constitutional medicine (SCM) is a traditional Korean medicine in which each Sasang constitution (SC) type has a different susceptibility to pathology and diseases. The aim of this study is to determine whether the SC could be an independent risk factor for single and multiple MS sub-elements. Twenty-four Korean medical clinics joined the study, and 3334 participants aged 20-80 years were recruited. Clinical data related to MS and general characteristics were obtained. The chi-square test and a one-way analysis of variance were conducted, and the odds ratios (ORs) with 95% confidence intervals (CIs) were generated through multinomial logistic regression according to the SC. The prevalence of single and multiple MS sub-elements was significantly different according to SC. The ORs of the Tae-Eumin (TE) type were significantly high for abdominal obesity, diabetes mellitus, hypertriglyceridemia, low HDL cholesterol, and hypertension. The ORs for the So-Yangin type were also high in hypertriglyceridemia and low HDL cholesterol compared with the So-Eumin type, even after being adjusted for sex, age, body mass index, and eating habits. As the numbers of MS sub-elements increased, the ORs of the TE type also increased. This study showed that the SC types may be risk factors for not only single MS sub-elements but also multiple MS sub-elements and that the TE type's risk degree is associated with an increase in the number of MS sub-elements.

Sasang constitution may act as a risk factor for prehypertension.

BackgroundPrehypertension (pre-HTN), similar to hypertension, has been associated with an elevated risk of cardiovascular disease. The aim of this study was to determine whether the Sasang constitution (SC) types could also be independent risk factors for pre-HTN.MethodsA total of 2,806 eligible subjects, older than 20 years old from 25 medical clinics, participated. Clinical data, including the blood pressure, age, height, weight, and data from blood tests, were collected. One-way ANOVA with Scheffé’s post-hoc analysis and the chi-square test were used, according to the SC and sex. Logistic regression was used to generate the odds ratios (ORs) and 95 % confidence interval (CI) for pre-HTN.ResultsThe pre-HTN prevalence rates of the Soeumin type, Soyangin type and Tae-eumin type were 59.4 %, 60.1 % and 74.9 %, respectively, in men (p < 0.001) and 41.7 %, 44.4 % and 58.3 % in women (p < 0.001). The Soyangin type was not more associated with increased ORs than the Soeumin type in any of the subjects with pre-HTN. Even after adjusting for sex, BMI, FBG, TC, TGs, HDL, and LDL, the Tae-eumin type in men was associated with increased ORs of pre-HTN compared with the Soeumin type (OR 1.57, 95 % CI 1.03–2.39), but the Tae-eumin type in women was not associated with pre-HTN.ConclusionsThis study suggested that the Tae-eumin type combined with sex might be significantly and independently associated with pre-HTN, especially high pre-HTN.

Constitutional multicenter bank linked to Sasang constitutional phenotypic data.

BackgroundBiobanks are more important in medical area because they can give researchers data for demonstrating and validating their research. In this study, we developed a biobank called the Korea Constitutional Multicenter Bank (KCMB) based on Sasang Constitutional Medicine (SCM). The aim of the KCMB was a foundation to providing the scientific basis of SCM.MethodsThe KCMB has been constructed since 2006 in 24 Korean medical clinics with collection of questionnaire data, physical measurements and biological information comprised the results from blood test and DNA analyses. All participants were prescribed Sasang Constitution (SC)-specific herbal remedies for the treatment, and showed improvement of original symptoms as confirmed by Korean medicine doctor. Collected data went through de-identification process using the electronic case report form system. For calculation of several SC type specific tendencies, we used the direct standardization and Chi-square tests.ResultsThe KCMB collected clinical information from 3,711 study participants (1,353 men and 2,358 women) aged more than 10 years. The mean age (± standard deviation) was 47.1 (±16.6) and 47.7 (±15.8) years for men and women respectively. After applying the direct standardization, the estimated constitutional distributions for the SC types were as follows: 39.2% for Tae-eumin(TE), 27.1% for Soeumin(SE), 33.7% for Soyangyin(SY), and non-zero but below 0.1% for Taeyangyin(TY). The estimated distribution of TE was about 10% less, while that of SY and SE were slightly more than the distribution reported by Jema Lee established the SCM. Based on the participants’ medical history within the KCMB, each SC type had notably different frequencies for some diseases such as hypertension, diabetes, hyperlipidemia, stroke, and obesity (P < 0.001).ConclusionsThe KCMB may serve to verify and validate SCM theories and practices. It may also provide new insights into SCM mechanisms. The results from many studies using the KCMB data are of great importance and value for making decisions in healthcare policy and developing novel therapies.

Can the Mahalanobis Taguchi system be applied to Sasang constitution classifications by using body shape information?

The Mahalanobis Taguchi system (MTS) is a predictive and diagnostic statistical method for classifying normal and abnormal data in multivariate cases. The objective was to apply the MTS to predict Sasang constitution (SC) by using body measurements for classification of SC type. After surveying nine Oriental medical clinics, TY type (N = 9) participants of low proportion were excluded. Therefore, 511 subjects were recruited and body shape information was collected. The classifications for both sexes were analyzed using the MTS. The classification rates of SC type for the Taeeumin (TE) and Soeumin (SE) types in male and female subjects were 81.15 and 74.54%, respectively. However, the SE type and Soyangin (SY) type were indistinguishable. This study shows that an analysis using the MTS based on body shape information, may be highly useful for classifications of the SE and TE types, but should not be used to distinguish the SE and SY types.

Constitution-specific features of perspiration and skin visco-elasticity in SCM

BackgroundHuman skin properties have been used as an important diagnostic component in traditional medicine as they change with health conditions. Sasang constitutional medicine (SCM) puts emphasis on the recognition of the constitution-specific skin features prior to the diagnostic decision of health. In this work, in search of skin-characteristics effectively reflecting SCM features, we compared several skin properties such as perspiration, visco-elasticity, elasticity, and elasticity hysteresis, in several candidate body parts.MethodsWe conducted a clinical study in which a total of 111 healthy females aged 50 – 70 years participated with their Sasang constitution (SC) types determined objectively by the Sasang constitutional analytic tool. Perspiration on the skin surface was estimated by using a capacitance sensor to measure the amount of moisture on the palm, forehead, and philtrum before and after a heating stimulus. We acquired the visco-elasticity, elasticity, and elasticity hysteresis at the forearm by Dermalab’s elasticity sensing device. An analysis of covariance (ANCOVA) was conducted to evaluate the effect of SC on the nine skin features acquired.ResultsThe visco-elasticity of the forearm of the Soeum-in (SE) group was significantly lower than that of the Taeeum-in (TE) group (F = 68.867, p < 0.001), whereas the elasticity hysteresis of the SE group was higher than that of the TE group (F = 10.364, p < 0.01). The TE group had more perspiration on the forehead than the SE group (F = 9.050, p < 0.01). The SE group had a large perspiration difference between the philtrum and the forehead compared with the TE group (F = 7.892, p < 0.01).ConclusionsWe found four significant skin features that reflect the inherent constitutional attributes of the TE and SE groups in accordance with SCM literature; the visco-elasticity, elasticity hysteresis, perspiration on the forehead and philtrum. Our findings are based on a novel interpretation of the SCM literature and will contribute to developing the constitutional health status evaluation system in SCM.