Medical Information Modeling for Diabetes Based on Logistic Regression

Medical Information Modeling for Diabetes Based on Logistic Regression

Karthika Natarajan, Anjali Gautam, Pravalika Somisetty, Ramya Venigalla, Veeramachaneni Jhansi Lekha
Copyright: © 2022 |Pages: 27
DOI: 10.4018/978-1-6684-4580-8.ch015
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

In this digital health technology world, many health applications are being developed. Artificial intelligence (AI) plays an important role for such important. Popular AI techniques include ML for handling structured and unstructured data. Machine learning detects health issues by studying many health records and data of the patients, hence increasing the efficiency of detection of chronic diseases in the medical field. Medical information modeling is to predict the medical needs in future and is a representation of a complex system into a simplified representation. Diabetes is one of the major diseases in the world population. It is a chronic disease associated with abnormally high levels of glucose in the blood. Gestational diabetes is a temporary condition associated with pregnancy. Several parameters are considered for the study (i.e., age, BMI, insulin levels, BP, number of pregnancies, glucose levels, etc.). Results can be obtained by using machine learning approaches like logistic regression and naive bayes.
Chapter Preview
Top

Case Description

The prevalence of gestational diabetes mellitus (GDM) is rising in lockstep with the rise in overweight and obesity among women of childbearing age. GDM develops when a pregnant woman's insulin response is insufficient to compensate for her normal insulin resistance (Merav, C. et al. 2012). Treatment and prevention of GDM, as well as the long and short-term effects of gestational diabetes on both the mother and the baby (Feig, D.S. et al. 2008)(Ioannis, K. et al. 2017). Gestational diabetes mellitus (GDM) affects roughly 5% of pregnancies, however the percentage varies greatly depending on the criteria utilized and the demographic parameters of the population (Kavishwar, B. W.et al. 2012)(Gorgal, R. et al. 2012). The importance of paying close attention to GDM cannot be overstated, and the goal of this review is to cover a wide variety of clinical concerns connected to GDM (Mitushi S. et al. 2020) (Ferrara, A. et al. 2007).

More Concerns

Determining the true prevalence of GDM is difficult. As a result, the prevalence is higher in the United States than in other countries. GDM screening and diagnostic tests, on the other hand, are critical in identifying women who are at risk of acquiring the disease and, as a result, reducing or preventing the risk of adverse events for both mother and child associated with GDM. Past GDM, previous large for gestational age babies, diabetes (of any sort) in first degree relatives, pre-pregnancy adipositas, belonging to a particular ethnic group associated with a high prevalence of GDM, glucosuria, and high maternal age are all the characteristics that are used in most of the countries. There are a number of known risk factors for GDM, including a higher pre-pregnancy BMI and a higher BMI at 28 weeks, both of which are strongly linked to greater insulin resistance at 28 weeks (Kampmann, U. et al. 2015) (Griffin, M.E. et al. 2000).

Complete Chapter List

Search this Book:
Reset