Evaluation of Patient Experience in Healthcare

  • Sumaya Almaazmi

    Student thesis: Master's Thesis

    Abstract

    Patient experience is a widely used indicator in assessing the quality of healthcare services. It is believed to be a crucial indicator when measuring a healthcare institution's quality and enables the implementation of improvements in healthcare institution strategies based upon the patient's voice. Within the concept of patient experience, three terms have rarely been discussed in the literature: patient stress, anxiety, and frustration. These are very important concepts that necessitate attention because they affect patient experience at healthcare institutions. It is vital to realize the drivers of patient stress, anxiety, and frustration on the patient journey in the hospital due to their negative effects on patients. Patient experience, stress, anxiety, and frustration are considered a multidimensional concept that is affected by various determinants, including both patient-related and provider-related factors. As it is still not clear in the literature which group of determinants drives patient stress, anxiety, and frustration in healthcare, this concept remains debatable. It is also observed that there are limitations regarding the use of advanced statistical analysis in this context. In particular, the amount of research devoted to capturing the determinants affecting patient stress, anxiety, and frustration levels throughout a patient's journey in the hospital is relatively small. In order to tackle this problem, we acquired patient experience–related data from a local hospital based in Abu Dhabi, UAE. The data was utilized to analyze the relationships among patient stress, anxiety, and frustration and different determinants in two steps of patients' journeys using both random forest (RF) and gradient boosting (GB) algorithms. The results reveal that the attribute 'age', which belongs to the patient-related determinant category, was the primary factor of patient stress, anxiety, and frustration in all models. Regarding provider-related determinants, 'CT3_S', 'CB3_S', and 'CB3' were the key drivers of patient stress, anxiety, and frustration, respectively, for the 'registration' step using the random forest algorithm. 'CP1_S', 'CT2', and 'CT2_S' were the key drivers in each model separately when using the GB algorithm. For the 'consultation process' step, 'ET3_S', 'EB7_S', and 'ET3_S' were the main drivers of patient stress, anxiety, and frustration, respectively, when using the random forest algorithm. On the other hand, 'ET3_S', 'ET3_S', 'EP6_S' were the main drivers in each model separately when using the gradient boosting algorithm.
    Date of AwardDec 2020
    Original languageAmerican English

    Keywords

    • patient experience
    • patient stress
    • patient anxiety
    • patient frustration
    • machine learning
    • random forest classifier
    • gradient boosting classifier.

    Cite this

    '