Date of Award
2025
Degree Type
Open Access Dissertation
Degree Name
Information Systems and Technology, PhD
Program
Center for Information Systems and Technology
Advisor/Supervisor/Committee Chair
Rafeeq Al-Hashemi
Dissertation or Thesis Committee Member
Itamar Shabtai
Dissertation or Thesis Committee Member
David Bourgeois
Terms of Use & License Information
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Rights Information
© 2025 Mohammed Mohammed Raoof
Keywords
Geographic Information Systems, Cancer diseases, Low-dose computed tomography, San Diego County, Lung cancer
Subject Categories
Educational Technology
Abstract
Cancer diseases, such as lung cancer, are known as being among the scariest of diseases and are considered the deadliest form of cancer. It is a growing global health threat. However, effective lung cancer control is possible with the contributions of various information systems and technology and healthcare disciplines, including the Artificial Intelligence (AI) discipline in radiological settings. Spatiotemporal data is an integral part of Geographic Information Systems (GIS). The International Agency for Research on Cancer (IARC) and the Center for Disease Control and Prevention show that the current lung cancer spatiotemporal data statistics for new incidence cases are outdated. With the outdated spatiotemporal statistics data problem for global and local lung cancer incidence cases, it is less likely that researchers will be able to control lung cancer more effectively. While information systems and technology hold immense promise and significant impact on healthcare in various ways, this study discusses potential opportunities for AI applications and medical machines to generate better spatiotemporal statistics, which can help researchers control lung cancer and eventually improve the well-being of our society. According to the literature, low-dose computed tomography (LDCT) machines are recommended among the other methods for diagnosing and detecting lung cancer. However, this exploratory study investigates the possibility of quickly updating outdated spatiotemporal data statistics. Substantially, this study aims to assess the possibility of generating better statistics based on LDCT machines by relying on AI technology. This study examines the LDCT machines in San Diego County as a case study. Due to the complexity of the topic, semi-structured interviews have been conducted with technologists and radiologists who are experts in LDCT machines. These experts are affiliated with all LDCT lung cancer screening centers in San Diego County, such as imaging centers and hospitals’ radiology departments in San Diego County. In addition, multiple secondary data are used (e.g., websites and blogs). These data are publicly available with no restrictions on security and privacy issues; the data includes thousands of pages of documents from the United States' official cancer and healthcare agencies, imaging centers, hospitals, and health plans in San Diego County. The researcher used coding, memos, and Computer-Assisted Qualitative Data Analysis Software (CAQDAS) such as the ATLAS.ti tool to analyze the collected data. As a result, this study has various possible contributions to the medical industry that can help lower the risk of dying from lung cancer by getting better spatiotemporal statistics data. Other contributions include the delivery of a better quality of care, significantly reduced costs, shorter time, and less effort for all involved parties in the procedure of getting the LDCT lung cancer screening. These involved parties include patients, LDCT ordering doctors’ offices, hospitals, LDCT scan providers, and health insurances. In addition, it contributes to supporting all organizations’ missions that control lung cancer (e.g., National Institutes of Health (NIH), American Cancer Society). Moreover, it contributes to improving the future medical stations of smart cities. This study suggests the need to design and develop a new generation of LDCT machines based on the Internet of Things (IoT) and AI, which can help automatically generate better, updated spatiotemporal statistics data for lung cancer.
ISBN
9798291550571
Recommended Citation
Mohammed Raoof, Mohammed. (2025). Exploring AI Applications in Low-Dose CT Machines to Generate Better Lung Cancer Spatiotemporal Statistics: San Diego County Case Study. CGU Theses & Dissertations, 1025. https://scholarship.claremont.edu/cgu_etd/1025.
