An Internet of Medical Things (IoMT) Approach for Remote Assessment of Head and Neck Cancer Patients
Graduation Year
2022
Document Type
Thesis
Degree
M.S.C.S.
Degree Name
MS in Computer Science (M.S.C.S.)
Degree Granting Department
Computer Science and Engineering
Major Professor
Srinivas Katkoori, Ph.D.
Co-Major Professor
Carmen S. Rodriguez, Ph.D.
Committee Member
Matthew John Mifsud, M.D.
Keywords
MediaPipe, OpenCV, Landmarks, Trismus, Shoulder Dysfunction
Abstract
Internet-of-Medical-Things (IoMT) allows for a smart healthcare system to remotely monitor and assess patient’s progress at home. Head and neck cancers (HNC) are treated with various treatment options which are associated with significant side effects, mainly shoulder dysfunction, and trismus (spasm of jaw muscles). However, measurement of patient’s progress, and side effects while undergoing treatment, is limited to evaluation received based on scheduled appointments. Development of strategies to enhance monitoring during follow-up period is needed for earlier identification of problems such as trismus and shoulder dysfunction. In this interdisciplinary research, for the first time, we develop an IoMT enabling application, namely, Automatic Measurement of Trismus and Shoulder Disfunction (AMTSD), to remotely monitor the recovery. An HNC patient can use AMTSD as a web application frequently (twice/daily) to virtually measure the mouth extension and shoulder range of motion (ROM). The data collected is stored in a database and can be automatically analyzed to assess the progress. Triggers can be set to alert the healthcare team if the patient’s condition is regressing. For the trismus, AMTSD measures the distance between the lips while the patient opens the mouth as widely as possible. For shoulder ROM, AMTSD measures the angle of a raised hand with a vertical line passing through the shoulder joint. The virtual measurements are based on the open-source MediaPipe, a cross-platform library from Google. For five volunteers, AMSTD yielded the average measurement error for mouth extension is 1.77% and shoulder ROM is 2.89%. A clinical study with at least ten simulated patients and atleast ten recovering HNC patients is underway.
Scholar Commons Citation
Chinthala, Ruchitha, "An Internet of Medical Things (IoMT) Approach for Remote Assessment of Head and Neck Cancer Patients" (2022). USF Tampa Graduate Theses and Dissertations.
https://digitalcommons.usf.edu/etd/10285
