An Effective Diagnostic Model for Personalized Healthcare Using Deep Learning Techniques

An Effective Diagnostic Model for Personalized Healthcare Using Deep Learning Techniques

Parul Agarwal, Syed Imtiyaz Hassan, Syed Khalid Mustafa, Jawed Ahmad
Copyright: © 2020 |Pages: 19
DOI: 10.4018/978-1-7998-2101-4.ch005
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

This chapter discusses a deep learning and IoE (Internet of Everything) based analytical model for disease detection, prediction and correct treatment for the patient would be proposed. In the proposed model, all the stakeholders, namely doctors, patients, medical staff within a clinic, hospital or a medical institute, would be embedded with micro-sensors. The sensors would in turn sense and capture the information gathered from these sources and the surrounding environment and then send it to a single repository, a base or a server, where it would be stored for further processing. These sensors produce massive amounts of data, which needs to be encrypted as well. Then, in order to improve the effectiveness and accuracy of prediction from the data received from these sensors, deep learning methods are used. Further, the advantages of the proposed model would be explored. To conclude, the limitations, opportunities and future applications of deep learning techniques would be discussed in this chapter.
Chapter Preview
Top

Introduction

Health-Care sector is one of the most prioritized sectors where technologies like Machine Learning, AI, and deep learning have the potential to bring about revolutionary changes.

Various types of data can be generated from the health care segment, which would include the health records in text form, images, sensor data and text which is complex, unstructured, poorly annotated and heterogeneous in nature. Traditional data mining (Kaur, 2014), machine learning statistical learning approaches has to first perform the feature engineering so as to get robust and effective features from the data, and build either prediction or clustering models on them. Due to the lack of sufficient domain knowledge, it poses a lot of challenges. Deep learning is a subtype of machine learning. With machine learning, you manually extract the relevant features of an image. With deep learning, you feed the raw images directly into a deep neural network that learns the features automatically. Deep learning needs lots of data to produce the best results, and is computationally intensive. Table 1 compares Machine learning and Deep Learning approach.

Table 1.
Comparison of Machine learning and Deep learning approach
S. no./Approach usedMachine LearningDeep Learning
1.Works for small datasetsRequires large datasets
2.Quickly, the model can be trainedRequires a lot of time to be trained
3.The features need to be entered manuallyLearns the features of the object automatically
4.The classifiers need to be tried to obtain best resultsLearns classifiers to be applied on the model automatically.
5.Accuracy is limitedAccuracy is unlimited.

Complete Chapter List

Search this Book:
Reset