JMIR Publications

ABSTRACT

Background:

Visual analytics promotes the understanding of data with visual, interactive techniques, using ‘analytic’ and ‘visual’ engines. The analytic engine includes machine learning and other automated techniques, while common visual outputs include flow maps and spatiotemporal hotspots for studying service gaps and disease distribution. The principal objective of this scoping review is to examine the state of science on visual analytics, and the various tools, strategies and frameworks used in population health and health services research.

Objective:

The main objective is to explore, map and synthesize the literature related to visual analytics in its application to population health and health services research. The purpose is to develop an overarching global view of the methods, including the tools, techniques and frameworks applied to these areas of health care since 2005.

Methods:

Using Tricco et al’s 2018 PRISMA-ScR guidelines, our scoping review focused on peer reviewed sources including journal articles and conference papers published between 2005 and March 2019. Using the Covidence platform, two independent researchers were involved at all stages including title, abstract and full text screening and data abstraction. Another independent researcher served as the arbitrator in case of disagreement during screening, and for validation of abstracted data. A comprehensive abstraction platform was built to capture the data from diverse bodies of literature primarily from computer science and health, while findings were thematized for reporting.

Results:

After screening 11,310 articles, findings from 55 articles were synthesized under 10 major headings: visual and analytic engines, visual presentation characteristics, tools used and their capabilities, application to the healthcare areas, data types and sources, VA frameworks, frameworks used for VA applications, availability and innovation, and knowledge translation. We found a wide application of VA methods used in areas of epidemiology, surveillance and modelling, health services access, utilization, and cost analyses. All articles included a distinct analytic and visualization engine, with varying levels of detail on each. There were seven articles presenting analytic frameworks. Related to knowledge translation, 7 articles targeted policy and decision makers. Most articles included tools that were prototypes, with 5 in use at publication time.

Conclusions:

With the advent of learning health system approaches, and increasing availability and generation of healthcare data, visual analytics is a fast growing method applied to complex healthcare data. What makes VA innovative is its capability to process multiple varied data sources for providing trends and patterns for exploratory analysis from big healthcare data leading to knowledge generation and decision support. This is the first review in this area that attempts to bridge a critical gap in the literature on the methods applied in areas of population health and health services. Clinical Trial: Not applicable.