Applied Computing in Medicine and Health

Dhiya Al-Jumeily,Abir Hussain,Conor Mallucci,Carol Oliver

• Publisher: Morgan Kaufmann
• Year: 2015
• ISBN:
  9780128034989
• Topic: Informatik
• Subtopic: Datenbanken

Applied Computing in Medicine and Health is a comprehensive presentation of on-going investigations into current applied computing challenges and advances, with a focus on a particular class of applications, primarily artificial intelligence methods and techniques in medicine and health.

Applied computing is the use of practical computer science knowledge to enable use of the latest technology and techniques in a variety of different fields ranging from business to scientific research. One of the most important and relevant areas in applied computing is the use of artificial intelligence (AI) in health and medicine. Artificial intelligence in health and medicine (AIHM) is assuming the challenge of creating and distributing tools that can support medical doctors and specialists in new endeavors. The material included covers a wide variety of interdisciplinary perspectives concerning the theory and practice of applied computing in medicine, human biology, and health care.

Particular attention is given to AI-based clinical decision-making, medical knowledge engineering, knowledge-based systems in medical education and research, intelligent medical information systems, intelligent databases, intelligent devices and instruments, medical AI tools, reasoning and metareasoning in medicine, and methodological, philosophical, ethical, and intelligent medical data analysis.

• Discusses applications of artificial intelligence in medical data analysis and classifications
• Provides an overview of mobile health and telemedicine with specific examples and case studies
• Explains how behavioral intervention technologies use smart phones to support a patient centered approach
• Covers the design and implementation of medical decision support systems in clinical practice using an applied case study approach

Chapter 1

Early Diagnosis of Neurodegenerative Diseases from Gait Discrimination to Neural Synchronization

Shamaila Iram¹, Francois-Benoit Vialatte², and Muhammad Irfan Qamar^{3 1}University of Salford, Greater Manchester, UK ²Laboratoire SIGMA, ESPCI ParisTech, Paris, France ³IBM Canada Ltd., Canada
E-mail: [email protected], [email protected], [email protected]

Abstract

It is generally believed that early detection of neurodegenerative diseases will provide a much more sustainable framework for dealing with age-related diseases in the future. This chapter presents a strategic framework for the early diagnosis of neurodegenerative disease from gait discrimination to neural synchronization. Here, we propose and present a new classifier fusion strategy that combines classification algorithms and rules (voting, product, mean, median, maximum, and minimum) to measure specific behaviors in people with neurodegenerative diseases. On the other hand, it is now evident that electroencephalographic (EEG) signals of patients with Alzheimer disease usually have less synchronization than those of healthy subjects. Computing neural synchronization of EEG signals to detect any perturbation will help diagnose this fatal disease at an earlier stage. Three neural synchrony measurement techniques, phase synchrony, magnitude-squared coherence, and cross-correlation, are applied to analyze three different databases of mild Alzheimer disease patients and healthy subjects to compare the right and left temporal lobe of the brain with the rest of the brain area. Results are compared using Mann–Whitney U statistical test.

Keywords

Combining Classifiers; Pattern Recognition; Machine Learning; Behavior classification; Neurodegenerative Diseases; Movement Signals; Electroencephalographic Signals; Neural Synchronization; Cross-correlation; Phase synchrony; Coherence; Mann–Whitney U Test

Introduction

Advancements in machine learning provoke new challenges by integrating data mining with biomedical sciences in the area of computer science. This emergent research line provides a multidisciplinary approach to combine engineering, mathematical analysis, computational simulation, and neuro-computing to solve complex problems in medical science. One of the most significant applications of machine learning is data mining. Data mining provides a solution to find out the relationships between multiple features, ultimately improving the efficiency of systems and designs of the machines. Data-mining techniques provide computer-based information systems to find out data patterns, generate information for the hidden relationships, and discover knowledge that unveils significant findings that are not accessible by traditional computer-based systems.

Neurodegenerative diseases (NDDs) are accompanied by the deterioration of functional neurons in the central nervous system. These include Parkinson, Alzheimer, Huntington, and amyotrophic lateral sclerosis (ALS) among others. The progression of these diseases can be divided into three distinct stages: retrogenesis, cognitive impairment, and gait impairment. Retrogenesis is the initial stage of any NDD which starts with the malfunctioning of the cholinergic system of the basal forebrain that further extends to the entorhinal cortex and hippocampus [1]. During retrogenesis, the patient’s memory is severely affected as a result of the accumulation of pathologic neurofibrillary plaques and tangles in the entorhinal cortex, hippocampus, caudate, and substantia nigra [2]. This stage is known as cognitive impairment. Finally, a patient cannot maintain his or her healthy, normal gait because of disturbances in the corticocortical and corticosubcortical connections in the brain, for example, frontal connection with parietal lobes and frontal lobes with the basal ganglia, respectively [3].

Early detection or diagnosis of life-threatening and irreversible diseases such as NDDs (Alzheimer, Parkinson, Huntington, and ALS) is an area of great interest for researchers from different academic backgrounds. Diagnosing NDDs at an earlier stage is hard, where symptoms are often dismissed as the normal consequences of aging. Moreover, the situation becomes more challenging where the symptoms or data patterns of different NDDs turn out to be similar, and discrimination among these diseases becomes as crucial as the treatment itself. In this...