Modeling of diagnosis for metabolic syndrome by integrating symptoms into physiochemical indexes.

BACKGROUND: Metabolic syndrome (MS) is a major global health concern comprising a cluster of co-occurring conditions that increase the risk of heart disease, stroke and type 2 diabetes. MS is usually diagnosed using a combination of physiochemical indexes (such as BMI, abdominal circumference and blood pressure) but largely ignores clinical symptoms when investigating prevention and treatment of the disease. Exploring predictors of MS using multiple diagnostic indicators may improve early diagnosis and treatment of MS. Traditional Chinese medicine (TCM) attaches importance to the etiology of disease symptoms and indications using four diagnostic methods, which have long been used to treat metabolic disease. Therefore, in this study, we aimed to develop predictive indicators for MS using both physiochemical indexes and TCM methods. METHODS: Clinical information (including both physiochemical and TCM indexes) was obtained from a cohort of 586 individuals across 4 hospitals in China, comprising 136 healthy controls and 450 MS cases. Using this cohort, we compared three classic machine learning methods: decision tree (DT), support vector machine (SVM) and random forest (RF) towards MS diagnosis using physiochemical and TCM indexes, with the best model selected by comparing the accuracy, specificity and sensitivity of the three models. In parallel, the best proportional partition of the training data to the test data was confirmed by observing the changes in evaluation indexes using each model. Next, three subsets containing different categories of variables (including both TCM and physicochemical indexes combined - termed the "fused indexes", only physicochemical indexes, and TCM indexes only) were compared and analyzed using the best performing model and optimum training to test data proportion. Next, the best subset was selected through comprehensive comparative analysis, and then the important prediction variables were selected according to their weight. RESULTS: When comparing the three models, we found that the RF model had the highest average accuracy (average 0.942, 95%CI [0.925, 0.958]) and sensitivity (average 0.993, 95%CI [0.990, 0.996]). Besides, when the training set accounted for 80% of the cohort data, the specificity got the best value and the accuracy and sensitivity were also very high in RF model. In view of the performance of the three different subsets, the prediction accuracy and sensitivity of models analyzing the fused indexes and only physicochemical indexes remained at a high level. Further, the mean value of specificity of the model using fused indexes was 0.916, which was significantly higher than the model with only physicochemical indexes (average 0.822) and the model with only TCM indexes (average 0.403). Based on the RF model and data allocation ratio (8:2), we further extracted the top 20 most significant variables from the fused indexes, which included 14 physicochemical indexes and 6 TCM indexes including wiry pulse, chest tightness, spontaneous perspiration, greasy tongue coating etc. CONCLUSION: Compared with SVM and DT models, the RF model showed the best performance, especially when the ratio of the training set to test set is 8:2. Compared with single predictive indexes, the model constructed by combining physiochemical indexes with TCM indexes (i.e. the fused indexes) exhibited better predictive ability. In addition to common physicochemical indexes, some TCM indexes, such as wiry pulse, chest tightness, spontaneous perspiration, greasy tongue coating, can also improve diagnosis of MS.

[Effect of Paidu Baoshen Pill on renal fibrosis in 5/6 nephrectomized rats].

OBJECTIVE: To observe the anti-renal fibrosis effect of Paidu Baoshen Pill (PBP) on 5/6 nephrectomized rats and to explore its mechanism. METHODS: Totally 50 SD male healthy rats were randomly divided into the normal control group (n = 10), the sham-operation group (n = 10), and the nephrectomy model group (n = 30) according to the proportion of 1:1:3. Rats in the sham-operation group had their renal capsule isolated without nephrectomy. Rats in the nephrectomy model group had their kidneys 5/6 nephrectomized. Then 24 h urine was collected and 24 h urinary protein (24 h UP) detected. Serum blood urea nitrogen (BUN) and serum creatitine (SCr) were also tested. According to the SCr level 30 rats of the model group were further randomly divided into the model group, the PBP group, and the Niaoduqing Granule (NG) group, 10 in each group. Rats in the PBP group and the NG group were respectively administered with PBP (at the daily dose of 1.0 g/kg) and NG (at the daily dose of 3.33 g/kg) by gastrogavage (they were dissolved in distilled water). At the same time, 2 mL distilled water was administered by gastrogavage to rats in the normal control group, the sham-operation group, and the nephrectomy model group, once daily for 4 successive weeks. Mental conditions, activities, hair color, shape of stool, and the body weight were observed during administration. After 4 weeks, urine was collected to detect 24 h UP. Blood was sampled to detect SCr, BUN, transforming growth factor ß1 (TGF-ß1), type III procollagen (PC III), collagen type IV (Col IV), laminin (LN), and fibronectin (FN). After rats were killed, their left remnant renal tissues were collected for pathological examinations. The protein expression quantity of TGF-ß1 and FN was detected by immunohistochemical method. mRNA expression levels of TGF-ß1 and FN were detected using real time fluorescent quantitative PCR. RESULTS: There was no statistical difference in the above indices between the normal control group and the sham-operation group (P > 0.05). Compared with the sham-operation group, rats' general condition was poorer in the model group, their body weight grew slower, and 24 h UP increased; serum levels of BUN, SCr, TGF-ß1, PC III, Col IV, LN, and FN increased; the residual renal pathological lesion was serious; expression levels of TGF-ß1, TGF-ß1, mRNA, FN, and FN mRNA increased in the renal tissue (all P < 0.01). Compared with the model group, rats' general condition was better, their body weight grew faster, 24 h UP reduced (P < 0.05), blood levels of BUN and SCr decreased significantly (P < 0.01), serum levels of TGF-ß1, PC III, CoL IV, LN, and FN decreased (P < 0.05, P < 0.01); the residual renal pathological lesion was attenuated in the PBP group and the NG group; expression levels of TGF-ß1, TGF-ß1, mRNA, FN, and FN mRNA decreased (P < 0.01). Compared with the NG group, blood levels of SCr and FN, and expression levels of FN and FN mRNA decreased more in the PBP group (P < 0.05). CONCLUSIONS: PBP had the effect of anti-renal fibro- sis in 5/6 nephrectomized rats. Down-regulating expression levels of TGF-ß1, and FN from gene transcription and protein translation levels might be one of its mechanisms.

[Effect of paidu baoshen pill in retarding the progression of chronic renal failure].

OBJECTIVE: To assess the impact of Paidu Baoshen Pill (PBP, modified Dahuang Zhechong Pill), in retarding the procession of chronic renal failure (CRF) of stage II-III. METHODS: The 283 patients of CRF stage II-III were randomly assigned to two groups, 151 patients in the treatment group treated with oral administration of PBP 3 g twice a day, and 132 patients in the control group with oxidative amylase aldehyde enveloped capsule 5-10 capsules thrice a day after meal. The course for both groups was 2 months, and the changes after 1 or 2 courses treatment in scoring of quality of life (QOL) and clinical symptoms, also in laboratory indexes including serum levels of creatinine (Cr), urea nitrogen (UN), and intrinsic creatinine clearance rate were observed. RESULTS: The total effective rate was 70. 86% (107/151 cases) in the treatment group and 44.70% (59/132 cases) in the control group, showing significant difference between them (X2 = 18.69, P < 0.01). Significant differences between groups were also shown in comparisons of scores of QOL and clinical symptoms after treatment. Inter-group comparison showed no difference in all the three indexes detected before treatment, but they did show statistical significance respectively after 1 and 2 courses of treatment (P < 0.05 and P < 0.01). CONCLUSION: PBP could effectively retard the progression of chronic renal failure and significantly improve the QOL of patients.