• Terapevt Arkh · Nov 2021

    [Neural networks in the predictive diagnosis of cognitive impairment in type 1 and type 2 diabetes mellitus].

    • I G Samoilova, M V Matveeva, D A Kudlay, O S Tonkikh, and I V Tolmachev.
    • Siberian State Medical University.
    • Terapevt Arkh. 2021 Nov 15; 93 (11): 1349-1358.

    BackgroundCognitive dysfunction, including mild cognitive impairment and dementia, is increasingly recognized as a serious complication of diabetes mellitus (DM) that affects patient well-being and disease management. Magnetic resonance imaging (MRI)-studies have shown varying degrees of cortical atrophy, cerebral infarcts, and deep white matter lesions. To explain the relationship between DM and cognitive decline, several hypotheses have been proposed, based on the variability of glycemia leading to morphometric changes in the brain. The ability to predict cognitive decline even before its clinical development will allow the early prevention of this pathology, as well as to predict the course of the existing pathology and to adjust medication regimens.AimTo create a computer neural network model for predicting the development of cognitive impairment in DM on the basis of brain neuroimaging techniques.Materials And MethodsThe study was performed in accordance with the standards of good clinical practice; the protocol was approved by the Ethics Committee. The study included 85 patients with type 1 diabetes and 95 patients with type 2 diabetes, who were divided into a group of patients with normal cognitive function and a group with cognitive impairment. The patient groups were comparable in age and duration of disease. Cognitive impairment was screened using the Montreal Cognitive Assessment Scale. Data for glycemic variability were obtained using continuous glucose monitoring (iPro2, Libre). A standard MRI scan of the brain was performed axially, sagittally, and coronally on a Signa Creator E, GE Healthcare, 1.5 Tesla, China. For MRI data processing we used Free Surfer program (USA) for analysis and visualization of structural and functional neuroimaging data from cross-sectional or longitudinal studies, and for segmentation we used Recon-all batch program directly. All statistical analyses and data processing were performed using Statistica Statsofi software (version 10) on Windows 7/XP Pro operating systems. The IBM WATSON cognitive system was used to build a neural network model.ResultsAs a result of the study, cognitive impairment in DM type 1was predominantly of mild degree 36.9% (n=24) and moderate degree 30.76% (n=20), and in DM type 2 mild degree 37% (n=30), moderate degree 49.4% (n=40) and severe degree 13.6% (n=11). Cognitive functions in DM type 1 were impaired in memory and attention, whereas in DM type 2 they were also impaired in tasks of visual-constructive skills, fluency, and abstraction (p0.001). The analysis revealed differences in glycemic variability indices in patients with type 1 and type 2 DM and cognitive impairment. Standard MRI of the brain recorded the presence of white and gray matter changes (gliosis and leukoareosis). General and regional cerebral atrophy is characteristic of type 1 and type 2 DM, which is associated with dysglycemia. When building neural network models for type 1 diabetes, the parameters of decreased volumes of the brain regions determine the development of cognitive impairment by 93.5%, whereas additionally, the coefficients of glycemic variability by 98.5%. The same peculiarity was revealed in type 2 DM 95.3% and 97.9%, respectively.ConclusionIn DM type 1 and type 2 with cognitive impairment, elevated coefficients of glycemic variability are more frequently recorded. This publication describes laboratory and instrumental parameters as potential diagnostic options for effective management of DM and prevention of cognitive impairment. Neural network models using glycemic variability coefficients and MR morphometry allow for predictive diagnosis of cognitive disorders in both types of diabetes.

      Pubmed     Copy Citation     Plaintext  

      Add institutional full text...

    Notes

     
    Knowledge, pearl, summary or comment to share?
    300 characters remaining
    help        
    You can also include formatting, links, images and footnotes in your notes
    • Simple formatting can be added to notes, such as *italics*, _underline_ or **bold**.
    • Superscript can be denoted by <sup>text</sup> and subscript <sub>text</sub>.
    • Numbered or bulleted lists can be created using either numbered lines 1. 2. 3., hyphens - or asterisks *.
    • Links can be included with: [my link to pubmed](http://pubmed.com)
    • Images can be included with: ![alt text](https://bestmedicaljournal.com/study_graph.jpg "Image Title Text")
    • For footnotes use [^1](This is a footnote.) inline.
    • Or use an inline reference [^1] to refer to a longer footnote elseweher in the document [^1]: This is a long footnote..

    hide…