MicroRNA expression classification for pediatric multiple sclerosis identification

Abstract MicroRNAs (miRNAs) are a set of short non-coding RNAs that play significant regulatory roles in cells. The study of miRNA data produced by Next-Generation Sequencing techniques can be of valid help for the analysis of multifactorial diseases, such as Multiple Sclerosis (MS). Although extensive studies have been conducted on young adults affected by MS, very little work has been done to investigate the pathogenic mechanisms in pediatric patients, and none from a machine learning perspective. In this work, we report the experimental results of a classification study aimed at evaluating the effectiveness of machine learning methods in automatically distinguishing pediatric MS from healthy children, based on their miRNA expression profiles. Additionally, since Attention Deficit Hyperactivity Disorder (ADHD) shares some cognitive impairments with pediatric MS, we also included patients affected by ADHD in our study. Encouraging results were obtained with an artificial neural network model based on a set of features automatically selected by feature selection algorithms. The results obtained show that models developed on automatically selected features overcome models based on a set of features selected by human experts. Developing an automatic predictive model can support clinicians in early MS diagnosis and provide new insights that can help find novel molecular pathways involved in MS disease.

Download Full-text

Protein expression profiles in pediatric multiple sclerosis: potential biomarkers

Multiple Sclerosis Journal ◽

10.1177/1352458508100047 ◽

2009 ◽

Vol 15 (4) ◽

pp. 455-464 ◽

Cited By ~ 40

Author(s):

KN Rithidech ◽

L Honikel ◽

M Milazzo ◽

D Madigan ◽

R Troxell ◽

...

Keyword(s):

Multiple Sclerosis ◽

Mass Spectrometry ◽

Protein Expression ◽

Expression Profiles ◽

Low Frequency ◽

Complement Factor ◽

Protein Biomarkers ◽

Two Dimensional Gel Electrophoresis ◽

Pediatric Multiple Sclerosis ◽

Proteomic Approach

The diagnosis of pediatric multiple sclerosis (MS) is challenging due to its low frequency and the overlap with other acquired childhood demyelinating disorders of the central nervous system. To identify potential protein biomarkers which could facilitate the diagnosis, we used two-dimensional gel electrophoresis (2-DE) in combination with mass spectrometry to identify proteins associated with pediatric MS. Plasma samples from nine children with MS and nine healthy subjects, matched in aggregate by age and gender, were analyzed for differences in their patterns of protein expression. We found 12 proteins that were significantly up regulated in the pediatric MS group: alpha-1-acid-glycoprotein 1, alpha-1-B-glycoprotein, transthyretin, apoliprotein-C-III, serum amyloid P component, complement factor-I, clusterin, gelsolin, hemopexin, kininogen-1, hCG1993037-isoform, and vitamin D-binding protein. These results show that 2-DE in combination with mass spectrometry is a highly sensitive technique for the identification of blood-based biomarkers. This proteomic approach could lead to a new panel of diagnostic and prognostic markers in pediatric MS.

Download Full-text

Altered Expression of Circulating miR-377 and miR-98 in Relapsing-remitting Multiple Sclerosis

International Journal of Medical Laboratory ◽

10.18502/ijml.v7i1.2464 ◽

2020 ◽

Author(s):

Nasrin Hadi ◽

Faezeh Namazi ◽

Fatemeh Ketabchi ◽

Farinaz Khosravian ◽

Parisa Ravaghi ◽

...

Keyword(s):

Multiple Sclerosis ◽

Mononuclear Cells ◽

Expression Profiles ◽

Polymerase Chain Reaction Method ◽

Peripheral Blood Mononuclear ◽

Altered Expression ◽

Mirna Expression Profiles ◽

Relapsing Remitting ◽

Polymerase Chain ◽

Relapsing Remitting Multiple Sclerosis

Background and Aims: Multiple sclerosis (MS) has been assumed to be a Complex and indecipherable disease, and poorly understood with regard to etiology which is characterized by relapses and remissions. The expression of microRNAs (miRNAs) is known to be associated with the regulation of immune responses. Recently, investigations have reported that miRNA expression profiles in blood cells become changed in MS. The aim of this study was to elucidate the alterations in the expression of circulating miR377 and miR-98 in 60 relapsing-remitting MS (RRMS) patients in comparison with controls. Materials and Methods: This study was conducted using a quantitative real-time polymerase chain reaction method to explore the expression of circulating miR-377 and miR-98 in peripheral blood mononuclear cells from 60 RRMS patients, 30 of whom were recurring patients, 30 were two months after relapse patients, and 30 others were controls, in order to examine the association of expression level of these miRNAs with RRMS. Results: Results indicated that the expression of miR-377 significantly increases in recurring patients and two months after relapse patients in comparison with controls (p=0.0017 and p=0.0001, respectively). However, miR-98 demonstrated down regulation in recurring patients and two months after relapse patients (p=0.0002 and p=0.0001, respectively). Conclusions: It can be concluded that miR-377 and miR-98 may be prospective biomarkers with the potential use for diagnosis of RRMS patients in the future investigations.

Download Full-text

Evaluation of Cognitive Impairment in Pediatric Multiple Sclerosis with Machine Learning: An Exploratory Study of miRNA Expressions

2020 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS) ◽

10.1109/eais48028.2020.9122758 ◽

2020 ◽

Author(s):

Gabriella Casalino ◽

Gennaro Vessio ◽

Arianna Consiglio

Keyword(s):

Machine Learning ◽

Multiple Sclerosis ◽

Cognitive Impairment ◽

Exploratory Study ◽

Pediatric Multiple Sclerosis

Download Full-text

School performance, psychiatric comorbidity, and healthcare utilization in pediatric multiple sclerosis: A nationwide population-based observational study

Multiple Sclerosis Journal ◽

10.1177/1352458520959673 ◽

2020 ◽

pp. 135245852095967

Author(s):

Magnus Spangsberg Boesen ◽

Morten Blinkenberg ◽

Lau Caspar Thygesen ◽

Frank Eriksson ◽

Melinda Magyari

Keyword(s):

Multiple Sclerosis ◽

Chronic Disease ◽

Chronic Diseases ◽

Healthcare Utilization ◽

School Performance ◽

Psychiatric Comorbidity ◽

Hospital Admissions ◽

Healthy Children ◽

Grade Point ◽

Pediatric Multiple Sclerosis

Background: Pediatric multiple sclerosis (MS) may hamper educational achievements due to psychiatric comorbidity and cognitive impairment. Our aims were to investigate school performance, psychiatric comorbidity, and healthcare utilization following pediatric MS and to differentiate between disability in MS and that arising from a non-brain-related chronic disease. Methods: We included all children (<18 years) with MS onset during 2008–2015 in Denmark with a medical record–validated MS diagnosis. The control groups were children from the general population or children with non-brain-related chronic diseases. Outcomes were register-based on 9–12 grade point average, psychiatric comorbidity, and healthcare visits. Results: Cohorts were children with MS ( n = 92), control children matched to children with MS ( n = 920), children with non-brain-related chronic diseases ( n = 9108), and “healthy” children with neither MS nor brain-related chronic disease ( n = 811,464). School performance in grades 9–12 was similar, but children with MS compared to those with non-brain-related chronic disease had an almost doubled hazard for psychiatric comorbidity (hazard ratio = 1.87; 95% confidence interval = 1.38–2.53; p < 0.0001) and a higher rate of all hospital visits ( p < 0.0001) but a lower rate of hospital admissions ( p = 0.001). Conclusion: Children with MS have a seemingly standard school performance but increased psychiatric comorbidity and a high rate of healthcare utilization.

Download Full-text

Machine learning-based multiple cancer detections with circulating miRNA profiles in the blood.

Journal of Clinical Oncology ◽

10.1200/jco.2021.39.15_suppl.3037 ◽

2021 ◽

Vol 39 (15_suppl) ◽

pp. 3037-3037

Author(s):

Juntaro Matsuzaki ◽

Yusuke Yamamoto ◽

Ouyang Yi ◽

Sandeep Ayyar ◽

Ryo Miyajima ◽

...

Keyword(s):

Machine Learning ◽

Early Detection ◽

Mirna Expression ◽

Expression Profiles ◽

Mirna Expression Profile ◽

Diagnostic Methods ◽

Serum Samples ◽

Multiple Cancer ◽

Mirna Expression Profiles ◽

Cancer Types

3037 Background: Early detection of cancer is one of the most important unmet clinical demands. A wide variety of circulating microRNAs (miRNAs) that specifically indicate many types of cancer have been identified, and their miRNA expression profiles are considered as potential biomarkers. Therefore, circulating miRNAs may serve as a non-invasive liquid biopsy diagnostic tool for early detection of many types of cancer. Here, a novel blood-based diagnostic method combined with machine learning techniques is developed using the entire circulating miRNA expression repertoire in serum without prior selection of miRNA marker sets. Methods: To validate this diagnostic method, clinical serum samples from cancer patients with five types of cancer (breast cancer(272), colorectal cancer(239), lung cancer(223), stomach cancer(221) and pancreatic cancer(100)) and 289 non-cancer volunteers were collected. Serum samples were immediately processed and their small RNAs were extracted. The entire miRNA expression profile is analyzed via next generation sequencers. The resulting total miRNA expression profile was used to train machine learning models, including deep learning techniques, without prior selection of miRNAs by human intervention. The machine learning model was trained with a training set to test set ratio of 4:1 and was carefully monitored by 5-fold cross-validation to avoid overfitting. Results: The diagnostic model provided 88% accuracy for all five cancer types (mean). The overall average AUROC was 0.954. Especially for breast cancer, the machine learning model provided 90% accuracy and 91 % sensitivity at 90% specificity. The overall AUROC was 0.966. High sensitivity was obtained regardless of the stage of the cancers, indicating that the possibility of early detection of cancer is kept high. Conclusions: Circulating miRNAs can be informative biomarkers for the earliest cancer detection in combination with machine learning. Unlike other cancer diagnostic methods where only a handful number of biomarkers are considered, this novel miRNA diagnostic platform method that uses machine learning reads a large set of miRNA expression profiles and automatically extracts the specific patterns of miRNA expression for early detection of multiple cancer types. In addition, the main advantage of miRNA-based cancer diagnosis is that they are more sensitive even in the early stages of cancer, compared to other diagnostic methods, such as cell-free DNA diagnostics, where the sensitivity of many types of cancer in the early stages still remains low. This approach could be easily expanded to other cancer types. Given the potential value of early detection in fatal malignancies, further validation studies are justified in future population-based studies. Many cancer research institutes are currently conducting further clinical trials to validate this early cancer diagnosis based on miRNA expression profiles.

Download Full-text