A Model for Detecting Type 2 Diabetes Using Mixed Single-Cell RNA Sequencing with Optimized Data

Title

A Model for Detecting Type 2 Diabetes Using Mixed Single-Cell RNA Sequencing with Optimized Data

Creator

Padmaja K.; Mukhopadhyay D.

Description

Diabetes is a critical disease and is crucial to personage agility. Type 2 Diabetes (T2D) accounts for 92% of epithetical cases. This paper proposes an optimized type 2 diabetes detection model using mixed single-cell RNA sequencing (scRNA-seq) technology. Diabetes is a chronic metabolic disorder affecting millions of people worldwide. Early detection of the disease can greatly improve treatment outcomes, but current diagnostic methods have limitations. Our proposed model integrates scRNA-seq data from both human pancreatic beta cells to identify gene expression patterns associated with diabetes. Our study shows that the proposed model is highly accurate in identifying diabetes, achieving an area under the curve (AUC) of 0.98. We employed an optimized model to improve the detection of diabetes at an early stage, leading to better treatment outcomes and an improved quality of life for patients. We initially incorporated optimal features from the dataset using the Monte Carlo (MC) feature selection method. This method helped us to estimate the relative importance (RI) score of each gene or feature, which is then used to rank the features. Further, we proposed an optimized deep belief network (ODBN) as a classification model to classify T2D and non-diabetes. To improve the performance of ODBN, an adaptive chimp optimization algorithm (AChOA) is introduced to optimize the weight parameters and achieved a performance accuracy of 96.57%. 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

Source

SN Computer Science, Vol-4, No. 6

Date

2023-01-01

Publisher

Springer

Subject

AChOA; Gene; Monte Carlo; ODBN; scRNA-seq; Type 2 diabetes

Coverage

Padmaja K., Department of CSE, CHRIST (Deemed to be University), Karnataka, Bangalore, India; Mukhopadhyay D., Department of CSE, CHRIST (Deemed to be University), Karnataka, Bangalore, India

Rights

Restricted Access

Relation

ISSN: 2662995X

Format

Online

Language

English

Type

Article

Identifier

https://doi.org/10.1007/s42979-023-02215-z

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85173921389&doi=10.1007%2fs42979-023-02215-z&partnerID=40&md5=8b455e35c33da718ba9a467a19992151