Analysis of AI techniques for healthcare data with implementation of a classification model using support vector machine

Abstract

Artificial intelligence (AI) is imposed to impersonate human cognitive functions. AI Techniques are most popular across healthcare. The motive behind implementing an AI system is to make the system more fast and efficient. Now, AI can assist medical physician for fast and accurate diagnosis of diseases. When the time of deployment of the AI system will come then, systems need to be ‘trained’ for a huge amount of data will be generated from different clinical performance data. Now a day’s data is available in a structured, unstructured and, semi-structured format. For supporting, retrieving results and knowledge from this data, its analysis using different AI techniques are available. This includes machine learning methods for structured data and unsupervised learning for unstructured data which is useful for retrieving features when the outcome for some subjects is missing. In this paper different conventional machine learning techniques used in healthcare, domains is analyzed using different data types. Also, a comparison of different methods used in Artificial intelligence fiction in the healthcare domain is explored. A flow from clinical data creation, through NLP data enhancement and Machine learning data analysis for making clinical diagnosis decisions and its predictions are discussed and implementation using a support vector machine (SVM) on the healthcare dataset consisting of the patient questionnaire isdone.

An Assessment of Machine Learning and Deep Learning Techniques with Applications

“…Incorporation of machine learning techniques along with high tenacity remotely data for longitudinal forecasting of soil properties (23). Assessment of usage of AI algorithms in healthcare field with machine learning algorithms (24).…”

A Non-Linear Trend Function for Kriging with External Drift Using Least Squares Support Vector Regression

“…Furthermore, this SVM regression-based algorithm has the generalization ability to reduce overfitting issues by introducing a regularization term into the loss function. Due to all these advantages, the technique has, therefore, been applied in diverse disciplines, including finance [26][27][28], economics [29][30][31], climate modeling [32,33], and healthcare [34,35]. However, SVR requires substantial computational time and significant memory usage to solve the QP problem.…”