Evaluation of Autism Spectrum Disorder Based on the Healthcare by Using Artificial Intelligence Strategies

Abstract

The behaviors of children with autism spectrum disorder (ASD) are often erratic and difficult to predict. Most of the time, they are unable to communicate effectively in their own language. Instead, they communicate using hand gestures and pointing phrases. Because of this, it can be difficult for caregivers to grasp their patients’ requirements, although early detection of the condition can make this much simpler. Assistive technology and the Internet of Things (IoT) can alleviate the absence of verbal and nonverbal communication in the community. The IoT-based solutions use machine Learning (ML) and deep learning (DL) algorithms to diagnose and enhance the lives of patients. A thorough review of ASD techniques in the setting of IoT devices is presented in this research. Identifying important trends in IoT-based health care research is the primary objective of this review. There is also a technical taxonomy for organizing the current articles on ASD algorithms and methodologies based on different factors such as AI, SS network, ML, and IoT. On the basis of criteria such as accuracy and sensitivity, the statistical and operational analyses of the examined ASD techniques are presented.

Detection of autism spectrum disorder (ASD) in children and adults using machine learning

“…FL is an advanced ML based approach that never transmits data over the network 54 . Data is kept with its generating organization 55 whereas only a small sized local data model is trained from onsite data and transmitted over the network towards central server where all local models are combined to train meta classifier for determining which ML model is most effective in autism detection 56 . Objective of proposed model is to detect ASD symptoms at different stages of age with minimum time, controlled expense and maximum accuracy.…”

Multimodal Deep Learning in Early Autism Detection—Recent Advances and Challenges

“…Lightweight CNN models show high accuracy, precision, and F1 score. Challenges include data quality, interpretability, generalizability, and ethical considerations [14,20].…”

Investigating the Role of Machine Learning Algorithms in Predicting Sepsis using Vital Sign Data

“…Within clinical settings, the commonly employed sepsis scoring systems encompass the Systemic Inflammatory Response Syndrome (SIRS) criteria [6], the Modified Early Warning Scale (MEWS) [8], and the Sequential Organ Failure Assessment (SOFA) score [9]. While these systems exhibit commendable sensitivity, they often grapple with issues related to specificity and are not explicitly designed for predicting the development of sepsis.…”