Intelligent Healthcare Recommender Systems for Advanced Healthcare Informatics: A Data Fusion Perspective

Intelligent Healthcare Recommender Systems for Advanced Healthcare Informatics: A Data Fusion Perspective

G. S. Karthick, M. Sridhar
Copyright: © 2023 |Pages: 24
DOI: 10.4018/978-1-6684-8913-0.ch001
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Recommender systems (RS) are an important filtering tool for discovering services in a personalized way to guide users from the large space of possible options. Over the past decades, recommendation systems in healthcare application have become popular due to the exponential increase in health data available on various platforms. The chapter begins with an overview of recommender systems, discussing the purpose, functionality, and key components. It highlights the significance of recommender systems in healthcare, where the abundance of data and the complexity of medical decisions necessitate personalized recommendations to enhance the quality of care. Additionally, it introduces the concept of big data and its relevance in healthcare recommender systems, emphasizing the wealth of information available from various sources such as electronic health records, wearable devices, and social media. Moreover, the chapter addresses the challenges associated with the implementation of recommender systems in the healthcare domain.
Chapter Preview
Top

Introduction

Overview of Recommender Systems (RS)

Recommender System (RS) mainly deals with personalized interactions of an individual users. It is responsible to determine the user/person needs from the interaction of user-product through data speculation automatically. On the other hand, it is used to designate user requirement by an inventory of keywords in the appropriate platform. But in few cases, the RS will act as a recommendation engine rather than using specific needs based on its input features. In the emerging field, the middle evolution of RS concept was started at 1990s that the structure rating has been highlighted for research scholars (Lu et al. 2015). The Origin of several RS determines forecasting theories, cognitive science and information recovery which has been reviewed by many researchers (He et al. 2016).

Recommender Elements

The recommender system consists of main elements such as user profile, domains and products (Chen et al. 2015).

  • ➢

    User profile defines that the individual person with its unique identity and functions are determined regarding various domains. For illustration, a 30-year-old patient suffering from diabetic disease with a blood glucose level of 11.2 mmol/L. The recommender (doctors, nurses) collects patient/user profile information of date of birth, address, sugar level and diabetic type were included in the RS.

  • ➢

    Product can be interrelated with user needs based on their domains. The product involves information such as videos describing a disease, use instructions, drugs, dosing and indications.

  • ➢

    Domain is defined as the environment that all elements interact to each other. For example, the specific domains are mostly focused to build the RS for all documents, research, diseases and relationship between doctors and patients.

The health-related RS consist of three types: collaborative, content and knowledge-based approaches (Valdez et al. 2019).

Collaborative Based Recommender Systems

The collaborative model examined user’s past interactions and analyzes the process to provide a recommendation. This model is also called a memory- based approach. Initially, the interactions between the users and item are filled in rows and columns respectively along with the Boolean/integer values. This can be represented in the form of matrix. Likewise, the information about the past user is shared to find the user’s interest since the taste is also the same (Schafer et al. 2017). Thus, the model is suitable to find the user behavior for the recommendation.

Content Based Recommender Systems

Being the core of the RS, the content approach involves user profile and product functions that the recommender knows the information very well even if the past information is small to provide an accurate recommendation to the users.

This model is also called a model-based approach. All the main characteristics can be represented by a list of properties for each product. Initially, the online recommendation mode can only be learned to promote the offline learning phase for recommendation in an updated way. In addition, this approach contains attributes matched with the user profile and past preferred history of the user. For this case, the collected documents are filtered to obtain the keywords for the recommendation using content-based methods (Islam et al. 2019).

Knowledge Based Recommender Systems

To improve recommendation, the knowledge model generates information about product based on its characteristics in the subset of content- based approach. In some cases, the knowledge model solves the weakness of the content-based approach. For example, the knowledge-based recommendation model can be used for a recommendation based on previous user/item ratings. According to their specified requirements, the users may ask to change the requirements only if the recommender outcomes are not adequate (Colombo- Mendoza et al. 2015).

Complete Chapter List

Search this Book:
Reset