Human needs are being increasingly addressed by information technologies. As a consequence, market competition has shifted toward developing innovative user experiences. Neuro information systems (NeuroIS) that detect user needs automatically can play a major role in addressing the continual demand for innovative user experiences in today's digital economy. By using sensors that can collect physiological measurements from users, NeuroIS can provide a continuous stream of valuable objective data for detecting user needs in various problem domains. One problem domain that can be addressed by NeuroIS is chronic pain. Chronic pain is a major public health problem that impacts 1 out of 5 American adults. Assessment of chronic pain is often achieved via self-reported scales. Research indicates that identifying measures that can objectively assess chronic pain can improve its effective treatment. Grounded in pain and eye tracking literature, I developed a theory-based eye tracking machine learning (ETML) engine as a proof of concept. Grounded in prior research, I develop a set of visual stimuli and an extensive set of eye tracking features that can be used to detect a person’s chronic pain status from the person’s eye movements. Grounded in user-centered design framework, I also propose and test an iterative process for developing such a NeuroIS (ETML engine) over time as more data becomes available. The results of my project show that the visual stimuli and the eye tracking features that I have developed for designing the ETML can indeed help to build a reliable NeuroIS for detecting chronic pain status. The results of my project also suggest that my proposed iterative process is likely to produce a robust ETML that can predict chronic pain status with 80% accuracy or more.

Creator

• Norouzi Nia, Javad

Contributors

• Strong, Diane M.
• Djamasbi, Soussan
• Paffenroth, Randy Clinton

Degree

• PhD

Unit

• Business Administration

Publisher

• Worcester Polytechnic Institute

Identifier

• etd-71721

Keyword

• User-Centered Design
• Chronic Pain
• Eye-Tracking
• NeuroIS
• Information Systems
• Machine Learning

Advisor

• Djamasbi, Soussan

Committee

• Paffenroth, Randy Clinton
• Djamasbi, Soussan
• Strong, Diane M.

Defense date

• 2022-08-10

Year

• 2022

Date created

• 2022-08-09

Resource type

• Dissertation

Source

• etd-71721

Rights statement

• In Copyright

Last modified

• 2022-12-09