Expression of Salivary miRNAs, Clinical, and Demographic Features in the Early Detection of Gastric Cancer: A Statistical and Machine Learning Analysis.
{"title":"Expression of Salivary miRNAs, Clinical, and Demographic Features in the Early Detection of Gastric Cancer: A Statistical and Machine Learning Analysis.","authors":"Maryam Koopaie, Sasan Arian-Kia, Soheila Manifar, Mahnaz Fatahzadeh, Sajad Kolahdooz, Mansour Davoudi","doi":"10.1007/s12029-024-01136-1","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>Gastric cancer ranks as one of the top five deadliest cancers worldwide and is often diagnosed at late stages. Analysis of saliva may provide a non-invasive approach for detection of malignancies in organs associated with the oral cavity. This research aims to analyze salivary microRNA expression together with clinical and demographic features with the aim of diagnosing gastric cancer.</p><p><strong>Materials: </strong>The study included 19 patients with early-stage gastric cancer and 19 healthy controls. Saliva samples were collected and processed for RNA isolation. Salivary expression of miR-223-3p and miR-21-5p were measured using quantitative reverse-transcription polymerase chain reaction (RT-qPCR). Receiver operating characteristic (ROC) curves were generated to evaluate the accuracy of diagnostic models. Machine learning algorithms, multiple logistic regression, and principal component analysis (PCA) were used to assess the predictive power of miRNAs in conjunction with clinical-demographic features.</p><p><strong>Results: </strong>Significant upregulation of miR-223-3p and downregulation of miR-21-5p in saliva were observed in patients with gastric cancer. The area under ROC curve (AUC) values for salivary miR-21-5p, salivary miR-223-3p, and their multiple logistic regression were determined to be 0.723, 0.791, and 0.850, respectively. The AUC for multiple logistic regression model was 0.919. The PCA model led to the highest diagnostic odds ratio (DOR) of 134.33 (sensitivity = 0.785, specificity = 1.00, AUC = 903). Application of machine learning methods, and in particular a random forest algorithm, showed high accuracy in diagnosing patients with gastric cancer (sensitivity = 1.00, specificity = 0.857, AUC = 0.93).</p><p><strong>Conclusion: </strong>The application of validated salivary diagnostics in clinical practice could help facilitate earlier diagnosis of gastric cancer and improve medical outcome. Expression of miR-21 and miR-223-3p in saliva together with clinical and demographic features, appears promising in screening for GC.</p>","PeriodicalId":15895,"journal":{"name":"Journal of Gastrointestinal Cancer","volume":"56 1","pages":"15"},"PeriodicalIF":1.6000,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Gastrointestinal Cancer","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s12029-024-01136-1","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Objective: Gastric cancer ranks as one of the top five deadliest cancers worldwide and is often diagnosed at late stages. Analysis of saliva may provide a non-invasive approach for detection of malignancies in organs associated with the oral cavity. This research aims to analyze salivary microRNA expression together with clinical and demographic features with the aim of diagnosing gastric cancer.
Materials: The study included 19 patients with early-stage gastric cancer and 19 healthy controls. Saliva samples were collected and processed for RNA isolation. Salivary expression of miR-223-3p and miR-21-5p were measured using quantitative reverse-transcription polymerase chain reaction (RT-qPCR). Receiver operating characteristic (ROC) curves were generated to evaluate the accuracy of diagnostic models. Machine learning algorithms, multiple logistic regression, and principal component analysis (PCA) were used to assess the predictive power of miRNAs in conjunction with clinical-demographic features.
Results: Significant upregulation of miR-223-3p and downregulation of miR-21-5p in saliva were observed in patients with gastric cancer. The area under ROC curve (AUC) values for salivary miR-21-5p, salivary miR-223-3p, and their multiple logistic regression were determined to be 0.723, 0.791, and 0.850, respectively. The AUC for multiple logistic regression model was 0.919. The PCA model led to the highest diagnostic odds ratio (DOR) of 134.33 (sensitivity = 0.785, specificity = 1.00, AUC = 903). Application of machine learning methods, and in particular a random forest algorithm, showed high accuracy in diagnosing patients with gastric cancer (sensitivity = 1.00, specificity = 0.857, AUC = 0.93).
Conclusion: The application of validated salivary diagnostics in clinical practice could help facilitate earlier diagnosis of gastric cancer and improve medical outcome. Expression of miR-21 and miR-223-3p in saliva together with clinical and demographic features, appears promising in screening for GC.
期刊介绍:
The Journal of Gastrointestinal Cancer is a multidisciplinary medium for the publication of novel research pertaining to cancers arising from the gastrointestinal tract.The journal is dedicated to the most rapid publication possible.The journal publishes papers in all relevant fields, emphasizing those studies that are helpful in understanding and treating cancers affecting the esophagus, stomach, liver, gallbladder and biliary tree, pancreas, small bowel, large bowel, rectum, and anus. In addition, the Journal of Gastrointestinal Cancer publishes basic and translational scientific information from studies providing insight into the etiology and progression of cancers affecting these organs. New insights are provided from diverse areas of research such as studies exploring pre-neoplastic states, risk factors, epidemiology, genetics, preclinical therapeutics, surgery, radiation therapy, novel medical therapeutics, clinical trials, and outcome studies.In addition to reports of original clinical and experimental studies, the journal also publishes: case reports, state-of-the-art reviews on topics of immediate interest or importance; invited articles analyzing particular areas of pancreatic research and knowledge; perspectives in which critical evaluation and conflicting opinions about current topics may be expressed; meeting highlights that summarize important points presented at recent meetings; abstracts of symposia and conferences; book reviews; hypotheses; Letters to the Editors; and other items of special interest, including:Complex Cases in GI Oncology: This is a new initiative to provide a forum to review and discuss the history and management of complex and involved gastrointestinal oncology cases. The format will be similar to a teaching case conference where a case vignette is presented and is followed by a series of questions and discussion points. A brief reference list supporting the points made in discussion would be expected.