Deep Learning for Personalized Healthcare Services

Vishal Jain, Jyotir Moy Chatterjee, Hadi Hedayati, Salahddine Krit, Omer Deperlioglu, Vishal Jain, Jyotir Moy Chatterjee, Hadi Hedayati, Salahddine Krit, Omer Deperlioglu

• Publisher: De Gruyter
• Year: 2021
• Print ISBN:
  9783110708004
• eBook ISBN:
  9783110708172
• Topic: Informatica
• Subtopic: Intelligenza artificiale (IA) e semantica

This book uncovers the stakes and possibilities involved in realising personalised healthcare services through efficient and effective deep learning algorithms, enabling the healthcare industry to develop meaningful and cost-effective services. This requires effective understanding, application and amalgamation of deep learning with several other computing technologies, such as machine learning, data mining, and natural language processing.

Early cancer predictions using ensembles of machine learning and deep learning

Wasiur Rhmann

Babasaheb Bhimrao Ambedkar University, Satellite Campus, Amethi, India

Babita Pandey

Babasaheb Bhimrao Ambedkar University, Amethi, India

Abstract

Cancer is the most frequent cause that is responsible for large number of deaths globally. According to the report published in 2018 by the international agency of research on cancer, one man in five and one women in six in the whole world develops cancer during their life. One in eight men and one in eleven women in the whole world die of cancer each year. Lung cancer and breast cancer are two major types of cancer with the highest numbers of new cases. Breast cancer is a prevalent and the second most deadly disease among women after lung cancers that are responsible for deaths. Survival of cancer patients largely depends on timely and accurate diagnosis of disease. In literature, various machine learning (ML) techniques are applied for breast cancer prediction. ML techniques utilize past data for the prediction of disease. Identification of tumors as benign and malignant is a crucial part in the detection of cancer and is considered as a classification problem. In this chapter, ensemble-based techniques and deep learning (DL) techniques are used for lung and breast cancer prediction. Two datasets, Wisconsin and Coimbra, obtained from well-known UCI ML repository are used for experimental purposes. Ensemble techniques are used to make effective classifiers with improved prediction capability. Generally, ML classifiers like Logistic regression (LR), random forest (RF), naïve Bayes (NB), and support vector machine are used for prediction. Combinations of different classifiers are used to enhance the performance of single classifier, and combined classifier is known as an ensemble. In recent years, a subfield of ML, DL, has emerged as a promising area with several techniques that have drastically boosted the performances of models that have caught the attention of researchers. DL originated from neural network. Although DL techniques have shown very good performance on different types of problems, they are computationally intensive. In this chapter, ensemble ML techniques have shown best performance on two cancer datasets, Coimbra and lung cancer datasets, while deep neural network has shown best results for Wisconsin dataset, and ensemble technique is very close to it.

Keywords: machine learning, ensemble, deep learning, breast cancer, lung cancer,

1 Introduction

Treatment of any type of cancer is costly due to its recurrent nature and high mortality rate. Artificial intelligence (AI)-assisted clinical techniques can be very effective in early diagnosis of cancer for pathologists and doctors. The accuracy of AI-based diagnosis techniques is much better compared to empirical methods [1]. Survival of cancer patients largely depends on the timely and accurate diagnosis of disease. Identification of tumors as benign and malignant is a crucial part in the detection of cancer. Different researchers have used machine learning (ML)-based models for cancer detection.

A large number of women suffer from breast cancer and die each year. Lung cancer is also responsible for a large number of deaths. Supervised classification techniques are used extensively for the detection of both breast cancer and lung cancer. ML is a part of the evolving field of AI-based computational research with diverse applications in different domains. With the rise in data availability, the use of ML techniques is on the rise for the creation of prediction models. Different ML alg...

Table of contents

• Title Page
• Copyright
• Contents
• Preface
• Short Biography of Editors
• List of Contributors
• Deep learning for health and medicine
• Exploring Indian Yajna and mantra sciences for personalized health: pandemic threats and possible cures in twenty-first-century healthcare
• Advanced deep learning techniques and applications in healthcare services
• Visualizations of human bioelectricity with internal symptom captures: the Indo-Vedic concepts on Healthcare 4.0
• Early cancer predictions using ensembles of machine learning and deep learning
• Deep learning in patient management and clinical decision making
• Patient health record system
• Prediction of multiclass cervical cancer using deep machine learning algorithms in healthcare services
• Comparative analysis for detecting skin cancer using SGD-based optimizer on a CNN versus DCNN architecture and ResNet-50 versus AlexNet on Adam optimizer
• Coronary heart disease analysis using two deep learning algorithms, CNN and RNN, and their sensitivity analyses
• An overview of the technological performance of deep learning in modern medicine
• Index
• Computational Intelligence for Machine Learning and Healthcare Informatics