Printer Friendly

Modification of the Integrated Sasang Constitutional Diagnostic Model.

1. Introduction

In recent years, the interest in and use of constitutional health care services have been reported to increase consistently. According to a survey by the Korea Institute of Oriental Medicine (KIOM), the percentage of constitutional health services in total traditional medical services reached 30.7% in 2015, which is approximately 7% higher than the corresponding value of 23.8% in 2004 [1].

Sasang constitutional medicine is a personalized medicine that diagnoses the patient's constitution as one of the four Sasang constitutional (SC) types (Tae-Yang: TY, Tae-Eum: TE, So-Yang: SY, and So-Eum: SE) and treats him/her differently depending on the constitution. Therefore, a precise diagnosis of constitution is central to producing consistent results when various experts diagnose the constitution of a single person.

From 2007 to 2011, KIOM collected face, body, voice, and questionnaire data from 2,773 subjects who were diagnosed in terms of constitutional prescriptions by Sasang constitutional experts in 23 oriental medical clinics. Based on these data, an objective and comprehensive Sasang constitutional diagnostic model, which has addressed the existing problems, was proposed in 2012 [2].

Based on this model, many studies on the relationship between Sasang constitution and disease have been conducted. For example, the SY and TE types are independent risk factors for nonalcoholic fatty liver disease [3] regardless of obesity level, TE is a strong risk factor for type 2 diabetes [4], and metabolic syndrome increases the risk of cardiovascular disease in certain physical conditions, such as the SY type [5]. Additionally, physiological characteristics may differ across Sasang types: the SY type has a higher value of total nasal resistance compared to the TE and SE types [6], and the TE type may tolerate psychological or oxidative stress better than the other types [7]. Other studies on constitution-specific physiology, such as comparisons of gut microbiota among Sasang constitutional types [8], have also been conducted using a constitutional diagnostic model.

As increasingly more researchers use the diagnostic model developed by KIOM, multiple issues have also been raised.

Firstly, the ratio of predicted SC types should be the same as the proportions of actual SC types. In the existing model, the predicted proportion of the TE type is much higher than the actual one, which, we believe, is due to the fact that the proportion of TE type is the highest.

Secondly, the multicollinearity problem results from the fact that the explanatory variables of the diagnostic model are highly correlated, making the regression coefficient estimates unreliable.

Finally, in the existing diagnostic model, it was assumed that all individual diagnostic components equally contribute to the diagnosis of the SC types, which turns out to be somewhat unreasonable.

Therefore, in this paper, we propose a novel modified model to solve the problems of the previous diagnostic model, and we compare the revised model with the previous model in terms of various aspects.

2. Methods

2.1. Participants and Data Acquisition. Using the same standard operating procedure used in the previous study, we collected more face, body shape, voice, and questionnaire data from the subjects than the previous study. A total of 3,849 patients, ranging from teenagers to people in their eighties, were recruited from 23 sites (oriental medical clinics) between November 2006 and August 2012. This process was approved by the KIOM Institutional Review Board (I-0910/02-001) and we obtained written informed consent from the subjects. As in the previous study [2], several patients were excluded for a variety of reasons, such as a small number of TY-type subjects, subjects below the age of 15 having growth spurts, or improper data (Table 1). Table 2 shows the distribution of subjects by age group.

In comparison with the previous study, the data for one year (August 2011 to August 2012) have been added, and the data extraction algorithm has been enhanced to increase the usage.

2.2. Candidate Feature Variables

2.2.1. Facial Images. A total of 57 facial feature points, including 13 newly added points over the previous study, were extracted using an automatic feature extraction algorithm (Figure 1). However, the feature points of the upper eyelid line, which require a high-resolution image, were excluded for more efficient implementation. Facial candidate feature variables using the extracted points are described in Table 3.

2.2.2. Body Shape. In contrast to the previous study, we excluded both BMI and body weight and reconstructed the model with the remaining variables. The reason for this exclusion is that there is a prejudice to diagnose as a TE type if the BMI and body weight are high and to diagnose as an SE type if BMI and body weight are low. Moreover, in the literature, it is noted that the body shape of the TE type is tall and large rather than obese, and the body shape of the SE type is short and small rather than slender [9].

2.2.3. Voice. Vocal features were extracted using a C++ program combined with the hidden Markov model toolkit [10]. Input vocal signals were divided into multiple windows corresponding to the reference time duration for feature extraction. The window size was 46.4 ms and was mapped to 211 samples at a 44.1 kHz sampling frequency.

The voice signal used was a recording of five vowels and one sentence repeated twice. Unlike the previous study [2], feature extraction was performed only from the sentence, excluding the vowels. Generally, the sentence was more suitable than the vowels because of the unchanged voice information for characterizing an individual. The accuracy and repeatability of the Sasang constitution diagnosis were better in the case of using only the sentence compared to the case of using both the vowels and the sentence [11].

A description of vocal features is provided in Table 4. The harmonic-to-noise ratio (HNR) and the cepstral peak prominence (CPP) are newly added features not found in our previous study [2].

The HNR is a measure that quantifies the amount of additive noise in the voice signal. It is widely used to characterize healthy and disordered voices. The CPP is known to be an accurate predictor and a more reliable measure of dysphonia than other vocal features, such as jitter, shimmer, and HNR [12].

2.2.4. Questionnaire. Binary variables were constructed using the response categories of the questions in the questionnaire, which consisted of multiple-choice questions in Supplementary Table S1 in Supplementary Material available online at https://doi.org/10.1155/2017/9180159. The procedure of generating questionnaire continuous variables is summarized in Supplementary Figure S1.

2.2.5. Compensating for Age Differences. As in previous study, because the candidate feature variables may have shown age-specific trends, a process to eliminate the effect of age was considered by normalizing each candidate feature variable with moving average and standard deviation of the variable for the given age [2].

2.3. Model for Sasang Constitutional Diagnosis

2.3.1. Individual Diagnostic Models. The regression coefficients of the explanatory variables used in the previous individual models were estimated using ordinary least squares (OLS). However, the OLS estimator may be acquired with a large variance of the coefficients and be inestimable if the dimension of explanatory variables is too high or each of them is highly intercorrelated. These problems are referred to as overfitting and multicollinearity, respectively. One well-known solution to these problems is the least absolute shrinkage and selection operator (LASSO), which shrinks the variance of the coefficients and makes other coefficients zero [13]. Coefficients were estimated using the glmnet package implemented in the R software. The tuning parameter [lambda] was selected from the result of 10-fold cross-validation using the mean square error (MSE) to measure the risk of loss. The decision rule is to choose log(A) that gives the minimum mean cross-validated error.

In the questionnaire model, we calculated questionnaire continuous variables with binary variables using LASSO (Supplementary Table S5) and then we constructed questionnaire model with continuous variables using OLS because the dimension of explanatory variables is low and each of them is not highly intercorrelated.

In addition, because the ratio of SC types is not uniform, the tendency in the previous model was to classify the TE type as the highest ratio. As a result, the sensitivity of TE type was high, but the sensitivity of other SC types was significantly low.

Sensitivity was low, particularly in the male SY type and female SE type. To compensate for this problem, weighting by SC types was added to the model by considering the ratios of SC types.

In the previous model, the training and test sets were separated based on the data collection year. However, there was a problem that the two groups are heterogeneous, which came from the effect of differences due to the collection year. In the present model, the complete set was randomly divided into a training set and a test set at a ratio of 7: 3 considering SC type and age.

The results of estimated coefficients for face, voice, body shape, and questionnaire continuous features for each SC type are shown in Supplementary Tables S2, S3, S4, and S6, respectively.

2.3.2. Integrating Diagnostic Models from Four Diagnostic Components. Let [[pi].sub.ij] be the estimated probability of the ith subject in category j for each individual diagnostic model, where j = 1,2, and 3 indicate TE, SE, and SY type, respectively.

In the previous study, the importance of each individual diagnostic model was also considered through multiplying the weights by [[pi].sub.ij]. The integrated estimated probability of an SC type j for the ith subject, denoted as [TSCORE.sub.ij], can be defined by the sum of [([[pi].sub.ij]).sub.r] with weight [w.sub.r]:

[TSCORE.sub.ij] = [4.summation over (r=1)] [w.sub.r] ([[pi].sub.ij]).sub.r], (1)

where r indicates each individual diagnostic component; r = 1, 2, 3, and 4 represent face, body shape, questionnaire, and voice, respectively.

In this study, we constructed a model with explanatory variables as [([[pi].sub.ij]).sub.r] of individual diagnosis models. This scheme can be regarded as weighting by a methodical and rigorous method, unlike the case of the previous study, in which arbitrary weights were set.

In addition, compared to the previous weight [w.sub.r] assigned to each individual diagnostic component, the weight [w.sub.jr] of this study was obtained considering each component and SC type as shown in Supplementary Table S7:

[TSCORE.sub.ij] = [4.summation over (r=1)] [w.sub.jr] ([[pi].sub.ij]).sub.r], (2)

Finally, the predicted SC type for the ith subject was determined in the same way as in the previous study.

Predicted [SC.sub.i] = argmax ([TSCORE.sub.i1], [TSCORE.sub.i2], [TSCORE.sub.i3)],

where the numbers of the subscripts indicate the TE, SE, and SY types.

3. Results

The predicted results of the proposed integrated diagnostic model are shown in Table 5. Relative to the predictions of the previous integrated diagnostic models, the accuracy in the test set is improved by approximately 10% on average. Moreover, the sensitivities of the male SY type (36.4% [right arrow] 62.0%) and the female SE type (43.7% [right arrow] 64.5%), which were low in the previous model, were significantly improved, while the sensitivity of the TE type and that of the female SY type were somewhat lowered.

Table 6 shows the results of applying a cutoff to the predicted results of the proposed integrated diagnostic model. To extract more typical SC-type predictions, the reference value for the cutoff criterion was changed to the maximum value minus the second highest value from the maximum value among the three probability values of the SC types, which was proposed in the previous study. This change was determined after implementing various cutoff value transformations.

Comparing the performances before and after the cutoff, the sensitivities and accuracies of each SC type were improved by approximately 7% on average. In particular, the sensitivity of the female SE type improved significantly.

This result alone does not make the comparison with the previous model justified due to the fact that it is not a comparison for the same test set. In this study, the number of data cases is greater and the complete dataset is divided into the training set and test set at random. To make an accurate comparison of the present model with the previous one, an additional comparison was performed with only the common part of the data that were included in finding both models among the test sets used in this model (Table 7).

A comparison of the two results shows that the sensitivities of the previous model are greater for the male TE type and the female SY type, but the sensitivities and accuracies of the other SC types are higher than average by more than 10%.

Although the result of the previous study has an advantage because some training data from the previous study are included in the test set of this study, it is notable that the overall performance of the proposed model is significantly improved.

4. Discussion and Conclusions

Relative to the previous studies, the diagnostic performance is significantly improved because of the reasonable considerations of various methodological approaches and the increased number of data cases and variables used to construct the model.

Although the previous diagnostic model offers the same accuracy as the overall model, the sensitivity for the TE type, which has the highest ratio among the SC types, is the highest, whereas the sensitivities for the SE and SY types are significantly lower. This result occurs because the estimation of the regression coefficient of the model is focused on reducing the error for the TE type. Therefore, to improve the performance for the SE and SY constitutional types, although the diagnostic performance for the TE type is somewhat degraded, the regression coefficients of the model are estimated with equal weight by training the model with different weights for each SC type based on their proportions. The TE type, which was frequently predicted in the previous model, was confirmed to have inferior performance, but the performance associated with the other SC types was improved.

As the regression coefficients are difficult to analyze individually because the model consists of multiple explanatory variables, the explanatory variables used in this model are highly correlated because the calculated variables are from similar positions on the body.

In general, the width of a confidence interval of an estimated regression coefficient increases when multicollinearity occurs. The fact that the confidence interval is wide implies that the estimated regression coefficient value is not actually confirmed but is highly likely to differ from the true value of the regression coefficient. Therefore, the influence of the variable cannot be explained correctly, and, as a result, the reliability of the model itself deteriorates.

Among the methods that can solve the multicollinearity problem, LASSO, as used in this study, can reduce multicollinearity without the modification of explanatory variables. Although the resolution of multicollinearity does not lead to improved accuracy, the results suggest that the reliability of the regression coefficient is satisfiable and that stable results will be obtained when new data are analyzed using the model.

In the previous study, the training and test sets were classified based on the data collection year, but the proportions of SC types and age may be heterogeneous in the training and test sets. Therefore, considering the proportions of SC types and age, it is reasonable and well reflective of the characteristics of the entire dataset to obtain both the training set and the test set from the complete dataset.

In traditional medicine in Asia, including Chinese medicine, facial, body shape, voice, and pulse information, as well as ordinary symptoms, are combined in the process of diagnosis for prescription decisions. In particular, many studies on the relationship between Prakriti (Ayurveda constitution) and various objective biological parameters have been actively conducted in the field of Ayurveda, and, at the same time, efforts are being made to propose a standard protocol for the objective and reliable diagnosis of Prakriti [14]. We believe that the proposed method is the most advanced tool to support the ability of Asian doctors to diagnose in an objective and scientific way. The improvement of this algorithm is expected to contribute not only to the scientific development of Sasang constitutional medicine in Korea but also to that of other traditional medical diagnosis methods.

https://doi.org/10.1155/2017/9180159

Conflicts of Interest

The authors declare that there are no conflicts of interest regarding the publication of this article.

Acknowledgments

This research was supported by the Bio & Medical Technology Development Program of the NRF funded by the Korean government, MSIP (NRF-2015M3A9B6027138).

References

[1] J. Y. Kim and D. D. Pham, "Sasang constitutional medicine as a holistic tailored medicine," Evidence-Based Complementary and Alternative Medicine, vol. 6, supplement 1, pp. 11-19, 2009.

[2] J.-H. Do, E. Jang, B. Ku, J.-S. Jang, H. Kim, and J. Y. Kim, "Development of an integrated Sasang constitution diagnosis method using face, body shape, voice, and questionnaire information," BMC Complementary and Alternative Medicine, vol. 12, pp. 85-93, 2012.

[3] S. K. Lee, D. W. Yoon, S. W. Lee, J. Y. Kim, J. K. Kim, and C. Shin, "Non-alcoholic fatty liver disease among sasang constitutional types: a population-based study in Korea," BMC Complementary and Alternative Medicine, vol. 15, no. 1, article no. 399, 2015.

[4] N. H. Cho, J. Y. Kim, S. S. Kim, S. K. Lee, and C. Shin, "Predicting type 2 diabetes using Sasang constitutional medicine," Journal of Diabetes Investigation, vol. 5, no. 5, pp. 525-532, 2014.

[5] N. H. Cho, J. Y. Kim, S. S. Kim, and C. Shin, "The relationship of metabolic syndrome and constitutional medicine for the prediction of cardiovascular disease," Diabetes & Metabolic Syndrome: Clinical Research & Reviews, vol. 7, no. 4, pp. 226-232, 2013.

[6] D. W. Yoon, S. K. Lee, H. Yi et al., "Total nasal resistance among Sasang constitutional types: a population-based study in Korea," BMC Complementary and Alternative Medicine, vol. 13, 2013.

[7] H. G. Kim, Y. J. Kim, Y. C. Ahn, and C. G. Son, "Serum levels of stress hormones and oxidative stress biomarkers differ according to sasang constitutional type," Evidence-Based Complementary and Alternative Medicine, vol. 2015, Article ID 737631, 2015.

[8] B.-S. Kim, H. S. Bae, C.-Y. Lim et al., "Comparison of gut microbiota between sasang constitutions," Evidence-Based Complementary and Alternative Medicine, vol. 2013, Article ID 171643, 2013.

[9] H. Chae and Y. Kown, "Best-fit index for describing physical perspectives in Sasang typology," Integrative Medicine Research, vol. 4, no. 1, pp. 20-28, 2015.

[10] S. Young, G. Evermann, T. Hain et al., The HTK Book, 2002, http://htk.eng.cam.ac.uk/.

[11] J.-S. Jang, Y.-S. Kim, B. Ku, and J. Y. Kim, "Recent progress in voice-based sasang constitutional medicine: Improving stability of diagnosis," Evidence-Based Complementary and Alternative Medicine, vol. 2013, Article ID 920384, 2013.

[12] Y. D. Heman-Ackah, R. J. Heuer, D. D. Michael et al., "Cepstral peak prominence: A more reliable measure of dysphonia," Annals of Otology, Rhinology & Laryngology, vol. 112, no. 4, pp. 324-333, 2003.

[13] R. Tibshirani, "Regression shrinkage and selection via the lasso," Journal of the Royal Statistical Society: Series B (Statistical Methodological), vol. 58, no. 1, pp. 267-288, 1996.

[14] S. Bhalerao and K. Patwardhan, "Prakriti-based research: Good reporting practices," Journal of Ayurveda and Integrative Medicine, vol. 7, no. 1, pp. 69-72, 2016.

Jiho Nam, (1) Jun-Su Jang, (2) Honggie Kim, (3) Jong Yeol Kim, (2) and Jun-Hyeong Do (2)

(1) Medizen Humancare Inc., 20F Keungil Tower, 223 Teheran-ro, Seoul, Republic of Korea

(2) KM Fundamental Research Division, Korea Institute of Oriental Medicine, 1672 Yuseong-daero, Daejeon, Republic of Korea

(3) Department of Information and Statistics, Chungnam National University, 99 Daehak-ro, Daejeon, Republic of Korea

Correspondence should be addressed to Jong Yeol Kim; ssmed@kiom.re.kr and Jun-Hyeong Do; jhdo@kiom.re.kr

Received 26 June 2017; Accepted 17 October 2017; Published 27 November 2017

Academic Editor: Bhushan Patwardhan

Caption: Figure 1: Feature points extracted automatically from facial images. * Added feature point.
Table 1: The number of excluded and included data cases for each
individual diagnostic model.

Reason for exclusion       Face    Body shape   Voice   Questionnaire
(total number of
subjects: 3,849)

Not collected initially     182        0         592         624

TY constitution             76         76        73           73

Below 15 years of age       96        107        79           79

Data extraction errors     1,343      429        388         150
and missing cases

Final number of subjects   2,152     3,237      2,717       2,923

Common samples after integrating th1,891 (male: 657; female: 1,234)

Table 2: Distribution of subjects by age group.

          Face          Body shape    Voice         Questionnaire
Age
group     M *    F **   M      F      M      F      M      F

10s        32     29     50     41     45     40     46     41
20s        89    162    120    234     97    198     98     214
30s       131    273    186    375    159    326    165     346
40s       161    317    245    453    202    381    214     416
50s       169    317    264    464    219    375    240     412
60s-      171    301    299    506    244    431    267     464

Total     2,152         3,237         2,717         2,923

                        Common samples

Age              TE     SE            SY
group     M      F      M      F      M      F

10s        10     14     13     6      6      8
20s        23     45     27     50     25     48
30s        46     66     35     81     32     93
40s        58    109     42     73     41     95
50s        61     99     34     72     49    105
60s-       66    128     22     68     67     74

Total                   1,891

* M: male; ** F: female.

Table 3: Candidate facial feature variables.

                             Size-related variables

Face        (i) Width        FD_43_143, FD_53_53, FD_94_194,
shape                        FDH_33_133

            (ii) Depth       PDH_44_53, PDH_12.36, PDH_14.36,
                             PDH_21_36

            (iii) Height     FDV_47_52, FDV_47_50, FDV_10_21,
                             FDV_52_50, FDV_81_50, PDV_6_12,
                             PDV_6_32, PDVJ0_32, PDVJ2_32, PDV_21_32,
                             PDV_25_32

            (iv) Area        FArea02, FArea03, FArea02/FArea03

Forehead    Height           FDV_47_10, PDV_6_9, PDV_61O

            (i) Width        FDH_18_25, FDH_118_125, FDH_18_118,
                             FDH_25_25, FDH_21_121

Eye         (ii) Height      FD_17_26, FD_117_26

            (iii) Distance   FD_17_25, FD_117_25, FD_18_25,
                             FD_118_125

            (i) Width        FDH_36_136, PDH_12_14, PDL_14_12_21

Nose        (ii) Height      FDV_52_81, PDVJ2 J4, PDV_14_21,
                             PDV_12_21, PD_12_21

            (iii) Depth      PDH_41_21

            (iv) Area        FArea_52_36_136, PArea_12_14_21

Mouth       (i) Width        PDL_22_21_32, PDL_25_21_32

            (ii) Height      FDV_80_50

            (i) Depth        PDH_32_36

Chin        (ii) Height      PDV_32_36

            (iii) Distance   PD_32_36

                             Shape-related variables

Face        (i) Angle        FA_53_94, FAs_153_L94, FA_94_43,
shape                        FAs_194_143, FA_53_94_43, FA_8_5_43,
                             FA_118_125_143, FA_18_17_43,
                             FA_118_17_43, FA_7_25_43, FA_117_25_43,
                             FA_8_5_94, FA_18_43_50, FA_18_94_50

            (ii) Ratio       FHD_33_133_43_143, FDD_53_153_43_143,
                             FDD_94_194_43_43, FHD_33_133_53_153,
                             FVV_47_52_52_81, FVV_47_52_52_50,
                             FVV_47_52_81_50, FVV_52_81_81_50,
                             PVV_6_0_0.33, PVV_12_14_4_32,
                             PVV_12_14_32, FVD_52_50_53_153,
                             FVD_52_81_53_153, FVD_81_50_94_194

Forehead    (i) Angle        Pai_7_6, Pai_9_7, Pai_71_72, Pai_72_73,
                             PA_6_7_9

            (ii) Ratio       PDD_77_9_6_9

            (iii) Depth      PDH_6_7, PDH_9_12

            (iv) Distance    PD_7_77, PDV_6_7, PDV_7_9, PDV_9_2,
                             PA_9_2, PA_10_12

Eye         (i) Angle        FA_18_17_25, FA_118_17_25, FAi.25_7, FA
                             is_125_117, Fais_18_17, Fai_118_17,
                             Fais_18_25, FAi.118_125

            (ii) Ratio       FDH_17_26_18_25, FDH_117_126_118_25,
                             FDH_52_50_18_18, FDD_17_26_52_81,
                             FDD_17_26_52_50,
                             (FDH_18_25+FDH_118_125)/2/FDH_18_118,
                             (FDH_18_25 + FDH_118_125)/2/FD_53_153,
                             (FDH_18_25+FDH_118_125)/2/FDH.33_33,
                             FHD_18_118_53_153, FHD_25_125_53_153

Nose        (i) Angle        PAi_14_12, PA_14_21, PA_12_14_21,
                             Pai_13_84, PA_87_88, PA_87_21

            (ii) Ratio       FHD_36_136_53_153, FVH 52_81_36_136

Mouth       Ratio            FVV_80_50_52_50, FVV_80_50_81_50

Chin        Angle            PA_32_33, PA_33_36, PA_32_33_36

Note. FD([n.sub.1], [n.sub.2]) [or PD([n.sub.1], [n.sub.2])]:
distance between points [n.sub.1] and [n.sub.2] in a frontal
(or profile) image; FDH([n.sub.1], [n.sub.2]) [or PDH([n.sub.1],
[n.sub.2])]: horizontal distance between [n.sub.1] and [n.sub.2]
in a frontal (or profile) image; FDV([n.sub.1], [n.sub.2])
[or PDV([n.sub.1], [n.sub.2])]: vertical distance between [n.sub.1]
and [n.sub.2] in a frontal (or profile) image; FA([n.sub.1], [n.sub.2])
[or PA([n.sub.1], [n.sub.2])]: angle between the line through two
points [n.sub.1] and [n.sub.2] and a horizontal line in a frontal
(or profile) image; FA([n.sub.1], [n.sub.2], [n.sub.3]) [or
PA([n.sub.1], [n.sub.2], [n.sub.3])]: angle between three points,
[n.sub.1], [n.sub.2], and [n.sub.3], in a frontal (or profile) image;
PAR([n.sub.1], [n.sub.2], [n.sub.3]): area of the triangle formed by
three points, [n.sub.1], [n.sub.2], and [n.sub.3], in a profile image;
FHD [n.sub.1] [n.sub.2] [n.sub.3] [n.sub.4] [or PHD [n.sub.1]
[n.sub.2] [n.sub.3] [n.sub.4]] = FDH [n.sub.1] [n.sub.2]/FD
[n.sub.3] [n.sub.4] [or PDH [n.sub.1] [n.sub.2]/PD [n.sub.3]
[n.sub.4]]; FDH [n.sub.1] [n.sub.2] [n.sub.3] [n.sub.4] [or PDH
[n.sub.1] [n.sub.2] [n.sub.3] [n.sub.4]] = FD [n.sub.1] [n.sub.2]/FDH
[n.sub.3] [n.sub.4] [or PD [n.sub.1] [n.sub.2]/PDH [n.sub.3]
[n.sub.4]]; FDD [n.sub.1] [n.sub.2] [n.sub.3] [n.sub.4] [or PDD
[n.sub.1] [n.sub.2] [n.sub.3] [n.sub.4]] = FD [n.sub.1] [n.sub.2]/FD
[n.sub.3] [n.sub.4] [or PD [n.sub.1] [n.sub.2]/PD [n.sub.3]
[n.sub.4]]; FVD [n.sub.1] [n.sub.2] [n.sub.3] [n.sub.4] [or PVD
[n.sub.1] [n.sub.2] [n.sub.3][n.sub.4]] = FDV [n.sub.1]
[n.sub.2]/FD [n.sub.3] [n.sub.4] [or PDV [n.sub.1] [n.sub.2]/PD
[n.sub.3] [n.sub.4]]; FVV [n.sub.1] [n.sub.2] [n.sub.3] [n.sub.4]
[or PVV [n.sub.1] [n.sub.2] [n.sub.3] [n.sub.4]] = FDV [n.sub.1]
[n.sub.2]/FDV [n.sub.3] [n.sub.4] [or PDV [n.sub.1] [n.sub.2]/PDV
[n.sub.3] [n.sub.4]]; FVH [n.sub.1] [n.sub.2] [n.sub.3] [n.sub.4]
[or PVH [n.sub.1] [n.sub.2] [n.sub.3] [n.sub.4]] = FDV [n.sub.1]
[n.sub.2]/FDH [n.sub.3] [n.sub.4] [or PDV [n.sub.1] [n.sub.2]/PDH
[n.sub.3] [n.sub.4].

Table 4: Description of sentence features.

Sentence feature *   Description

sF0, sFCV            Average pitch frequency and coefficient of
                     variation of the pitch

sF10, sF50, sF90     10th, 50th, and 90th percentiles of pitch
                     distribution

sFHL                 Ratio of(sF90-sF50) to (sF50-sF10)

sDT                  Duration time of a sentence reading

sHNR                 HNR

sCPP                 CPP

sMFCC1-12            12 Mel-frequency cepstral coefficients

Table 5: Diagnostic results of the proposed integrated diagnostic model.

                               Male

                     Predicted SC type        Sensitivity

                 TE     SE     SY     Total

Training set
True SC type

TE               144    14     30     188        76.6%
SE               14     81     26     121        66.9%
SY               29     28     92     149        61.7%
Total            187    123    148    458

Accuracy                       69.2%

Test set
True SC type

TE               64     4      8      76         84.2%
SE               8      35     9      52         67.3%
SY               22     5      44     71         62.0%
Total            94     44     61     199

Accuracy                       71.9%

                              Female

                     Predicted SC type        Sensitivity

                 TE     SE     SY     Total

Training set
True SC type

TE               233    32     66     321        69.5%
SE               33     146    63     242        60.3%
SY               65     65     168    298        56.4%
Total            321    321    297    861

Accuracy                       62.4%

Test set
True SC type

TE               104    12     25     141         73.8%
SE               12     69     26     107         64.5%
SY               25     28     72     125         57.6%
Total            141    109    123    373

Accuracy                       65.7%

Table 6: Diagnosis results of proposed integrated diagnosis
model using a cutoff.

                              Male

                         Predicted SC type      Sensitivity

                 TE      SE      SY     Total

Training set
True SC type
TE                131      9      19     159       82.4%
SE                10      71      17     98        72.4%
SY                19      15      68     102       66.7%

Total             160     95     104     359

Accuracy                   5     75.2%

Test set
True SC type
TE                58       3      3      64        90.6%
SE                 4      29      5      38        76.3%
SY                15       4      38     57        66.7%

Total             77      36      46     159

Accuracy

                                 Female

                         Predicted SC type      Sensitivity

                 TE      SE      SY     Total

Training set
True SC type
TE                181     15      39     235       77.0%
SE                19      110     28     157       70.1%
SY                39      40     114     193       59.1%

Total             239     165    181     585

Accuracy                         69.2%

Test set
True SC type
TE                89      11      14     114       78.1%
SE                 8      58      9      75        77.3%
SY                12      14      49     75        65.3%

Total             109     83      72     264

Accuracy                         74.2%

Table 7: Comparison of diagnosis results of the set of common
data between the test set of the proposed integrated diagnosis
model and the full set of the previous integrated diagnosis model.

                                  Male

                        Predicted SC type      Sensitivity

                 TE     SE     SY     Total

Proposed integrated diagnosis model

True SC type
TE               36     2      5      43       83.7%
SE               3      21     8      32       65.6%
SY               14     4      24     42       57.1%

Total            53     27     37     117

Accuracy                              69.2%

Previous integrated diagnosis model

True SC type

TE               38     3      2      43       88.4%
SE               9      15     8      32       46.9%
SY               15     7      20     42       47.6%

Total            62     25     30     117
                                      62.4%

                               Female

                        Predicted SC type      Sensitivity

                 TE     SE     SY     Total

Proposed integrated diagnosis model

True SC type
TE               68     9      16     93       73.1%
SE               7      46     15     68       67.6%
SY               13     21     47     81       58.0%

Total            88     76     78     242

Accuracy                       66.5%

Previous integrated diagnosis model

True SC type

TE               62     6      25     93       66.7%
SE               10     27     31     68       39.7%
SY               18     10     53     81       65.4%

Total            90     43     109    242
                               58.7%
COPYRIGHT 2017 Hindawi Limited
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2017 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Title Annotation:Research Article
Author:Nam, Jiho; Jang, Jun-Su; Kim, Honggie; Kim, Jong Yeol; Do, Jun-Hyeong
Publication:Evidence - Based Complementary and Alternative Medicine
Date:Jan 1, 2017
Words:5242
Previous Article:Effect of Tai Chi Training on Dual-Tasking Performance That Involves Stepping Down among Stroke Survivors: A Pilot Study.
Next Article:A Review of Black Salve: Cancer Specificity, Cure, and Cosmesis.
Topics:

Terms of use | Privacy policy | Copyright © 2021 Farlex, Inc. | Feedback | For webmasters |