Construction of artificial neural network diagnostic model and analysis of immune infiltration for periodontitis

Abstract

Background: Periodontitis is a chronic inflammatory disease leading to tooth loss in severe cases, and early diagnosis is essential for periodontitis prevention. This study aimed to construct a diagnostic model for periodontitis using a random forest algorithm and an artificial neural network (ANN).Methods: Gene expression data of two large cohorts of patients with periodontitis, GSE10334 and GSE16134, were downloaded from the Gene Expression Omnibus database. We screened for differentially expressed genes in the GSE10334 cohort, identified key periodontitis biomarkers using a Random Forest algorithm, and constructed a classification artificial neural network model, using receiver operating characteristic curves to evaluate its diagnostic utility. Furthermore, patients with periodontitis were classified using a consensus clustering algorithm. The immune infiltration landscape was assessed using CIBERSOFT and single-sample Gene Set Enrichment Analysis.Results: A total of 153 differentially expressed genes were identified, of which 42 were downregulated. We utilized 13 key biomarkers to establish a periodontitis diagnostic model. The model had good predictive performance, with an area under the receiver operative characteristic curve (AUC) of 0.945. The independent cohort (GSE16134) was used to further validate the model’s accuracy, showing an area under the receiver operative characteristic curve of 0.900. The proportion of plasma cells was highest in samples from patients with period ontitis, and 13 biomarkers were closely related to immunity. Two molecular subgroups were defined in periodontitis, with one cluster suggesting elevated levels of immune infiltration and immune function.Conclusion: We successfully identified key biomarkers of periodontitis using machine learning and developed a satisfactory diagnostic model. Our model may provide a valuable reference for the prevention and early detection of periodontitis.

Pediatric Crohn's disease diagnosis aid via genomic analysis and machine learning

“…However, very little is known about the role of the other 5 identified genes in CD at present. It is reported that the expression levels of RGS13 in colon tissues associate with endoscopic remission after vedolizumab in IBD patients ( 45 ). FOLH1 can increase folic acid levels, which may promote proliferation of inflammatory cells ( 46 ).…”

Construction of predictive model of interstitial fibrosis and tubular atrophy after kidney transplantation with machine learning algorithms

“…However, on how to construct a low-dimensional diagnostic model based on high-dimensional data that still performs stably in the validation set remains a research challenge. The key benefits of random forest (RF) are its accuracy and resistance to overfitting, which makes it a good choice of machine learning algorithms (Wu et al, 2022), and it has also shown consistent diagnostic efficacy in previous studies (Sun et al, 2022;Wu et al, 2022;Xiang et al, 2022).…”

Construction of Predictive Model of Interstitial Fibrosis and Tubular Atrophy (IFTA) After Kidney Transplantation with Machine Learning Algorithm

“…Gini coe cient method was used to calculate the dimensional signi cance value for screening the important genes as the candidate genes for IFTA diagnosis. The IFTA candidate genes for ANN model development was de ned from the top 15 DEGs with signi cance value greater than 2, which is a acceptable screening index in RF and has been used in similar studies (12,15).…”

“…The key bene ts of Random Forest (RF) are its accuracy and resistance to over tting, which makes it a good choices of machine learning algorithms (12). The use of Arti cial Neural Networks (ANNs) allows for the creation of nonlinear models, and make it is possible to detect nonlinear relationships and all potential interactions among predictor variables (13).It has been reported that RF and ANN can be used in conjunction to make e cient diagnoses in a wide range of diseases, such as Alzheimer"s disease, heart failure and periodontitis (12,14,15).…”