University of Twente Student Theses
Input Variable Selection for a Classification Algorithm to Predict Personalised Health Advice in Secondary Prevention : A Pilot Study
Kivits, Enno (2023) Input Variable Selection for a Classification Algorithm to Predict Personalised Health Advice in Secondary Prevention : A Pilot Study.
|
PDF
3MB |
| Abstract: | This study examines the relationship between personal characteristics and personalised health advice in order to select input variables for a classification algorithm. To meet this objective, an explanatory pilot study was conducted. The study identified a set of candidate predictors based on existing literature, analysed, and evaluated the observations and results of the pilot study, and proposed a revised study design to ensure more robust follow-up research. Chi-square tests and logistic regression were used to examine the relationships between personal characteristics and domains of health care or social services. Obtaining valid and reliable results regarding the relationship between personal characteristics and the domains of personalised health advice is not feasible due to various limitations. The role of the outpatient clinic in recruiting potential patients, it is crucial to ensure that processes, such as the referral process, are established effectively in the first place. The revised study design offers a framework to enhance patient inclusion, data quality, and candidate predictor selection. The revised design can be used in further research to gain a better understanding of the relationship between personal characteristics and the service domains. Considering alternative classification algorithms for selecting the input variables for the final algorithm could be valuable. |
| Item Type: | Essay (Master) |
| Faculty: | TNW: Science and Technology |
| Subject: | 54 computer science |
| Programme: | Health Sciences MSc (66851) |
| Link to this item: | https://purl.utwente.nl/essays/97067 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page