Establishment Of Prognosis Prediction Model For Tuberculosis And Diabetes Comorbidity/association Of Vitamin D And Its Metabolic Pathway Genes With Insulin Resistance And Tuberculosis And Diabetes Comorbidity

Recently,there are more and more evidence having proved that the relationship between diabetes and tuberculosis,which issues a new challenge to the prevention of diabetes and tuberculosis.Clinical trial and epidemiology have demonstrated that diabetes and tuberculosis are bidirectional relationship disease,in which mycobacterium tuberculosis may cause the variations of blood glucose,resulting in the blood glucose variability,increasing the risk of metabolic disease and type 2 diabetes.While,Diabetic patients may have a higher risk of latent tuberculosis infection or even active tuberculosis infection due to persistent hyperglycemia,insufficient insulin secretion or insulin resistance,and excessive accumulation of glycation end products in the circulation.Vitamin D deficiency is the global issues.Vitamin D deficiency not only increases the risk and severity of diabetes,but also positively correlates with the risk of tuberculosis.Previous studies have reported that vitamin D plays an important role in the regulation of insulin and the insulin signaling pathway.Vitamin D binds to its receptor and activates the L-type calcium ion channel on the β-cell,which promotes the release of insulin and islet receptor substrate tyrosine phosphorylates and starts islet signaling.Vitamin D deficiency leads to closure of calcium channels or blockage of phosphorylation of insulin receptor substrates and affects islet signaling.Recent years,the immunomodulatory effects of vitamin D on the innate and adaptive immune systems have been widely recognized.When the body infection due to Mtb,vitamin D activates the innate immune system to interfere with the proliferation of Mtb in macrophages.Vitamin D binds to Toll-like receptors,it activates α-hydroxylase and induces the expression of antimicrobial peptides.In turn,this process inhibits and kills Mtb.In summary,vitamin D deficiency may not only impair the secretory function of islets,but also reduce the body’s immune response to Mycobacterium tuberculosis,which may increase the risk of diabetes and tuberculosis comorbidity in the target population.CYP24A1,CYP2R1,CYP27B1,DHCR7,and VDR genes in the vitamin D metabolic pathway are key genes for vitamin D metabolism,transport,and function.Previous studies have shown that their epigenetic changes and abnormal gene expression may increase the incidence of tuberculosis or type 2 diabetes.However,there are many controversies due to ethnic factors,age,and research design issues.At present,the prognosis of TB-DM is not very clear,and how to use a convenient and economical method to establish an early explainable and accurate prediction model is still controversial.additionally,the relationship between insulin and vitamin D in TBDM patients is unclear.Finally,there is no report on the association between DNA promoter methylation of key genes in the vitamin D metabolic pathway and TB-DM.This study intends to use machine learning methods to establish an explainable prediction model based on clinically relevant variables in real-world research,to assist physicians to predict the prognosis of TB-DM patients in an economical and convenient way.Furthermore,we use both real-world research and the public database—National Health and Nutrition Examination Survey(NHANES)to explore the role and correlation of insulin and vitamin D on the pathophysiology of TB-DM.Based on the case-control study,we further analyzed the DNA methylation level of the key gene promoter region in the vitamin D metabolic pathway related to the risk of TB-DM,so as to provide more evidence and information for the prevention of tuberculosis and diabetes complications.Part one Explainable Machine Learning for Early Predicting Treatment Failure Risk among Patients with TB-diabetes Comorbidity: a cross-sectional studyObject Hyperglycemia in patients with tuberculosis has been proved to increase the risk of mortality and unfavorable treatment outcome.The present study aims to assess the treatment outcome of patients with diabetes and tuberculosis(TB-DM)at an early stage using machine learning based on electronic medical record(EMR).Methods A total of 429 patients were included at Chongqing Public Health Medical Center.The 69 variables included in the study were regarded as candidate predictors.The random-forest-based Boruta algorithm was employed to select the essential variables,and four models with a 5-fold cross-validation scheme were used for modeling and model evaluation.Furthermore,we adopted SHapley additive explanations to interpret results from the tree-based model.Results 9 features out of 69 candidate features were chosen as predictors.Among these predictors,type of resistance was the most important feature,followed by activated partial throm-boplastic time(APTT),thrombin time(TT),platelet distribution width(PDW),and prothrombin time(PT).All the models we established performed above AUC 0.7 with good predictive performance.XGBoost,the optimal performance model,predicts the risk of treatment failure in the test set with an AUC 0.9218,accuracy of 0.8438,a sensitivity of 0.7111,and a specificity of 0.9167,respectively.Conclusions This study suggests that machine learning approaches can help clinicians identify patients with TB-DM at higher risk of treatment failure at an early stage based on EMR.The application of convenient and economy EMR based on machine learning provides new insight into TB-DM treatment strategies in low and middle-income countries.Part two Association of insulin resistance with CT features in patients with tuberculosis and diabetes mellitusObject The purpose of this study was to investigate the association of the triglyceride glucose(Ty G)index,a surrogate marker of insulin resistance(IR)with a high sensitivity of 96.5% and a specificity of 85.0% for the diagnosis of IR,with computed tomography(CT)features in patients with tuberculosis and diabetes mellitus.Methods A total of 247 subjects were enrolled From July,2020 to May,2021.The basic clinical features and CT features were analyzed.In addition,multivariate logistic regression analysis models were employed to evaluate the association of the Ty G indicator with CT features in participants.Results In the quartile groups of Ty G index,air bronchial sign detection rate was 11.7%,14.5%,23.2%,and 44.1%;large segmented leafy shadow detection rate was 27.9%,40.6%,46.4%,and 66.2%;thick-walled cavity was found in 38.2%,43.4%,57.9%,and 69.1%;the rate of multiple cavities was 17.6%,27.5%,36.2%,52.9%;the rate of lymph node enlargement was 22.1%,17.4%,28.9%,and 38.2%,respectively.In addition,the positive relation with the Ty G index and the prevalence of abnormal CT signs was observed in the fully adjusted model: Ty G,per one-unit increase: air bronchial sign: adjusted odds ratio(AOR)3.92,95% CI 1-15.35,P = 0.049;multiple cavities: AOR 4.1,95% CI 1.26-13.31,P = 0.019;thick-walled cavity: AOR 2.89,95% CI 1.05-8.03,P = 0.041.In quartile of Ty G index,compared with patients in quartile 1,the AOR(95% CI)values for air bronchial sign in quartile 4 was 8.1(1.7-44),P = 0.011;multiple cavities was 7.1(1.7-32),P = 0.008;thick-walled cavity was 7.8(1.9-34.7),P = 0.005.Conclusions The present study showed that an increased Ty G index was positively related to the severity of patients with T2DM-PTB.Part three Association between vitamin D and insulin resistance in adults with latent tuberculosis infectionObject Evidence demonstrated that vitamin D insufficiency was involved in insulin resistance(IR)pathogenesis and associated with tuberculosis.However,the association of vitamin D and IR in patients with latent tuberculosis infection(LTBI)remains unclear.This study aims to evaluate the association between vitamin D and insulin resistance in US adults with LTBI.Method National Health and Nutrition Examination Survey(NHANES)participants ≥ 20 years during the years 2011–2012 with positive Quanti FERON(?)-TB Gold-In-Tube(QFT)or tuberculin skin testing(TST)were enrolled in present study.Participants with LTBI were divided into 2 groups:(1)vitamin D insufficiency group(n = 267),and(2)vitamin D sufficiency group(n = 437).Results Weighted analysis of all the population in the study showed that serum 25(OH)D inversely correlated with HOMA-IR(r =-0.14,P = 0.008).The vitamin D insufficiency group had higher fasting insulin(17.5(1.38)vs.15.29(3.1),respectively,P = 0.0013)and HOMA-IR(5.0(0.4)vs.4.5(1),respectively,P = 0.013)than the vitamin D sufficiency group.In adjusted analysis,vitamin D levels was independently associated with insulin resistance(adjusted OR [a OR] 2.74;95% CI,1.01-7.48,p = 0.0489).Conclusions Taken together,our study suggested that serum 25(OH)D concentrations were inversely and independently associated with HOMA-IR in LTBI.Part four Association between promoter methylation of vitamin D metabolic pathway genes and tuberculosis and diabetes comorbidity in a Chinese Han population: A case-control studyObject Deficiency vitamin D and hyperglycemia could be related to weakened innate immune response and aggravate the progression of tuberculosis(TB).This study hypothesized that DNA promoter methylation of the pivotal genes in the vitamin D metabolic pathway might be related to insulin resistance and diabetes and tuberculosis co-morbidity(TB-DM)susceptibility.Methods: A total of 50 TB-DM and 50 healthy subjects(HS)were included in the present study.Targeted bisulfite sequencing was applied to detect the methylation of the promoter regions of candidate genes in the vitamin D metabolic pathway(CYP24A1,CYP27B1,CYP2R1,DHCR7,and VDR)in whole blood.Results: The overall methylation level of candidate genes in this study was lower in patients with TB-DM than HS,except for CYP2R1.The results of the ROC demonstrated that the potential of CYP24A1,CYP27B1,DHCR7,and VDR promoter methylation as a biomarker for diagnosing TB-DM,with all the AUC above 0.7.In subgroup analysis,we found lower circulating vitamin D is related to a low level of CYP24A1,CYP27B1,and DHCR7 promoter methylation in patients with TB-DM.With decreasing methylation level,risk of TB-DM was significantly decreased(odds ratio,95% CI 0.343,0.144-0.821 for CYP24A1;0.461,0.275-0.773 for CYP27B1;0.09,0.015-0.530 for DHCR7;0.006,0.0003-0.115 for VDR).Besides,our results revealed that there was a significant correlation between DNA promoter methylation of selected genes in the vitamin D metabolic pathway and platelet indices in TB-DM.However,there was no correlation between DNA methylation of the four genes and insulin resistance,fasting glucose and Hb A1 c.Conclusions Our results could suggest that the selected genes in the vitamin D metabolic pathway may be involved in the pathological process of TB-DM,but independent of the process of hyperglycemia to impaired immune responses to Mtb.