Date of Award


Degree Type

Restricted to Claremont Colleges Dissertation

Degree Name

Information Systems and Technology, PhD


Center for Information Systems and Technology

Advisor/Supervisor/Committee Chair

Samir Chatterjee

Dissertation or Thesis Committee Member

Saeideh Heshmati

Dissertation or Thesis Committee Member

Paula Healani Palmer

Terms of Use & License Information

Creative Commons Attribution-Noncommercial 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 4.0 License.

Rights Information

© 2023 Md. Moniruzzaman


Cancer, caregiver, feature selection, Machine learning model, support, wellbeing

Subject Categories

Medicine and Health Sciences


This research focuses on investigating the multifaceted characteristics (demographic, mental, social, physical, etc.) of caregivers and identifying the significant factors that predict caregiver burden using advanced machine learning techniques. A mobile app ("Caregiver Well-being," designed and developed by IDEA lab) and Garmin wearable devices were provided to participating caregivers to collect both qualitative (survey) and quantitative (vital) data, aiding health providers in understanding, addressing, and enhancing caregivers' well-being. The study employs a mixed methods approach, combining quantitative data tools such as surveys and machine learning algorithms with design science research to comprehend factors related to caregiver burden and devise mechanisms for awareness building, ultimately striving to enhance Caregiver Quality of Life (QOL). The research focuses on cancer caregivers due to the unique challenges posed by caring for cancer patients. Caregivers of cancer patients face considerable physical, emotional, and quality-of-life effects, making understanding their challenges crucial. The study aims to answer research questions related to demographics, burden factors, machine learning's role in identifying significant factors, and the design of an application to measure and enhance caregivers' QOL in the USA. The study adopts a design science theoretical framework based on the caregiver health model, expectation confirmation model, and mPERMA reference theory to instantiate a technologicalsolution (a mobile app) to measure caregivers' well-being. The research utilizes a comprehensive secondary dataset of cancer caregivers and employs machine learning to predict caregiver burden, contributing to the body of knowledge and offering potential solutions for known problems in caregiving. Nevertheless, the research encounters obstacles such as hurdles in recruiting participants, the possibility of bias in selecting participants for the study, and technological problems associated with gathering data via mobile apps and wearable devices. Notwithstanding these obstacles, the study is anticipated to provide useful insights into the burden and well-being of cancer carers, hence facilitating future research in this crucial domain.



Available for download on Sunday, March 08, 2026