Evaluation of Maternal Patient Experience During COVID-19 Using Natural Language Processing
Abstract
Healthcare policymakers are constantly investigating how to improve this situation and provide a more patient-centered care. Delivering excellent medical care involves ensuring that patients have a positive experience. Most healthcare organizations use patient survey feedback, like HCAHPS, to measure their patients' experiences. The United States has the highest maternal mortality or morbidity rate of the developed countries, so we used maternal patients as the patient cohort to evaluate various touchpoints. The power of social media can be harnessed to provide researchers with valuable insights into understanding patient's experience and care. We used the "COVID-19Tweets" Dataset, which has over twenty-eight million tweets, to evaluate patient experience using Natural Language Processing (NLP) and extract tweets from the US with words relevant to maternal patients. This research's objective is to develop a model to evaluate the patient experience during the COVID-19 pandemic. We created word clouds, word clustering, frequency analysis, and network analysis of words that relate to “pains” and “gains” expressed through social media regarding the maternal patient experience. This model will help process improvement experts without domain expertise to efficiently understand various challenges in the domain. Such insights can help decision-makers improve the patient care system. Additionally, the model will also discover if there is any racial health inequity faced by any particular group. Artificial Intelligence can be used to get information from social media about how patients feel. This allows healthcare organizations to be more patient centered.
Subject Area
Industrial engineering|Artificial intelligence|Health care management|Bioinformatics
Recommended Citation
Banik, Debapriya, "Evaluation of Maternal Patient Experience During COVID-19 Using Natural Language Processing" (2023). ETD Collection for University of Texas, El Paso. AAI30490852.
https://scholarworks.utep.edu/dissertations/AAI30490852