Understanding cancer patient cohorts in virtual reality environment for better clinical decisions: a usability study

Abstract

Background: Visualising patient genomic data in a cohort with embedding data analytics models can provide relevant and sensible patient comparisons to assist a clinician with treatment decisions. As immersive technology is actively used around the medical world, there is a rising demand for an efficient environment that can effectively display genomic data visualisations on immersive devices such as a Virtual Reality (VR) environment. The VR technology will allow clinicians, biologists, and computer scientists to explore a cohort of individual patients within the 3D environment. However, demonstrating the feasibility of the VR prototype needs domain users' feedback for future user-centred design and a better cognitive model of human-computer interactions. There is limited research work for collecting and integrating domain knowledge into the prototype design.

Objective: A usability study for the VR prototype--Virtual Reality to Observe Oncology data Models (VROOM) was implemented. VROOM was designed based on a preliminary study among medical users. The goals of this usability study included establishing a baseline of user experience, validating user performance measures, and identifying potential design improvements that are to be addressed to improve efficiency, functionality, and end-user satisfaction.

Methods: The study was conducted with a group of domain users (10 males, 10 females) with portable VR devices and camera equipment. These domain users included medical users such as clinicians and genetic scientists and computing domain users such as bioinformatics and data analysts. Users were asked to complete routine tasks based on a clinical scenario. Sessions were recorded and analysed to identify potential areas for improvement to the data visual analytics projects in the VR environment. The one-hour usability study included learning VR interaction gestures, running visual analytics tool, and collecting before and after feedback. The feedback was analysed with different methods to measure effectiveness. The statistical method Mann-Whitney U test was used to analyse various task performances among the different participant groups, and multiple data visualisations were created to find insights from questionnaire answers.

Results: The usability study investigated the feasibility of using VR for genomic data analysis in domain users' daily work. From the feedback, 65% of the participants, especially clinicians (75% of them), indicated that the VR prototype is potentially helpful for domain users' daily work but needed more flexibility, such as allowing them to define their features for machine learning part, adding new patient data, and importing their datasets in a better way. We calculated the engaged time for each task and compared them among different user groups. Computing domain users spent 50% more time exploring the algorithms and datasets than medical domain users. Additionally, the medical domain users engaged in the data visual analytics parts (approximately 20%) longer than the computing domain users.

Keywords: Clinical Decision-making; Genomic Data Analysis; Usability Study; Virtual Reality; Visualisation.

Fig. 1

3D scatter plot for the entire patient population in the VR environment. The colour stands for the different levels of risk: red for high risk, green for low risk and orange for intermediate risk. This cohort uses “Hovon Three Risk” (http://www.hovon.nl/) data and the “Autoencoder” [16, 17] algorithm to decide the patient position. In this cohort, most high-risk (red) patients are clustered on the top right, some low-risk (green) and intermediate-risk (orange) patients are mixed in the middle, and a small group of low-risk (green) patients are also clustered together in the left bottom. Users can choose to A) show individual patient gene expression, B) compare two patients’ correlations, and C) compare multiple patients’ gene expression with heatmap [15]

Fig. 2

Usability Study Procedure: Activities and Expected Time. A Fill before-interview form, and consent form to check the participant’s experience in both genomic data analysis and using VR experience. B Learn how to use the VR device by using the VR device tutorial application “First Step”. C Finish a scenario with 16 tasks to find the scenario solution. D Fills the after-interview form for about 10 min to analyse users’ satisfactory feelings and collect users’ further potential requirements

Fig. 3

Time distribution for 16 tasks among two main groups: Medical Domain and Computing Domain

Fig. 4

Engaged time of different VR-experienced participants. Tasks are grouped to three main tasks based on the purpose: Tasks 1–3 are “Overview Interactions”, Tasks 4–14 are the “Analysis”, and Tasks 15–16 are “Exploration”. The colour of the table cells stands for the average engaged time

Fig. 5

Feedback rating for each question in the whole group (top chart) and comparison between two main groups (bottom chart). The charts show the percentage of the rating in the whole group and between two groups

Fig. 6

Trajectory for the virtual environment for a VR-experienced participant and a non-VR-experienced participant. The movement scope is in the human reaching scope. The participant can reach and interact with all the virtual objects in the movement scope without standing up

Fig. 7

Concept map for description feedbacks (A), and the potential using comments (B) to show a list of concepts contained in the text, and their relationship to each other