Question

How does the Health Recommender System build the profile of the user and the features of the items? Use an architecture to clearly explain this.

Answer 1

Digital information available for patient-oriented decision making has increased drastically but is often scattered across different sites. As as solution, personal health record systems (PHRS) are meant to centralize an individual’s health data and to allow access for the owner as well as for authorized health professionals.

Recommender systems may supply patients with additional laymen-friendly information helping to better comprehend their health status as represented by their record. However, such systems must be adapted to cope with the specific requirements in the health domain in order to deliver highly relevant information for patients. They are referred to as health recommender systems (HRS).

Increasing health information needs and changes in information seeking behavior can be observed around the globe. This influence the patient-physician relationship as educated patients raise questions or discuss treatment options. Thus, patients tend to become active participants in the decision-making process. This change in the way of thinking is often referred to as patient empowerment. Medical information available for patient-oriented decision making has increased drastically but is often scattered across different sites. As as solution, personal health record systems (PHRS) are meant to centralize an individual’s health data and to allow access for the owner as well as for authorized health professionals. Recommender systems (RS) suggest items of interest to users of information systems or e-business systems and have evolved in recent decades.

A health recommender systems (HRS) is a specialization of an RS. In the context of an HRS, a recommendable item of interest is a piece of non-confidential, scientifically proven or at least generally accepted medical information, which in itself is not linked to an individual’s medical history. However, an HRS’s suggestions are driven by individualized health data such as documented in a personal health record (PHR).

The goal of an HRS is to supply it’s user with medical information which is meant to be highly relevant to the medical development of the patient associated with that PHR. Related medical information may be recommended to health professionals who work on or with the given PHR but also it may be recommended to laymen inspecting their own PHR. Depending on a user’s medical expertise an HRS should suggest medical information, which is comprehendable to that user. For a successful integration into any health related information system, it is important to consider the system context of an HRS. Profile-based HRS component must be implemented as an extension of an existing PHR system. Data entries in a PHR database (DB) constitute the medical history of a PHR owner. Supplied with medical facts, an HRS computes a set of potentially relevant items of interest for a target user (e.g., a PHR owner or an authorized health professional). Such items originate from trustworthy health knowledge repositories and may be displayed while he/she inspects the PHR online.

Electronic Medical Records (EMRs) and Electronic Health Records (EHRs) provide the technology for the electronic storage of medical data and enables hospitals and other healthcare players to share such data electronically among authorized caregivers.

Personal health record (PHR) systems enable users to keep track of their own health data, most of which is still provided by health professionals. Hence, a longterm individual medical history can be carried together for an individual. A PHR is an electronic application through wich individuals can access, manage and share their health information, and that of others for whom they are authorized, in a private, secure and confidential environment.