University of Twente Student Theses
Using Decision Tree Classifiers to Support Healthcare Diagnosis
Arconada Sousa, Luis (2023) Using Decision Tree Classifiers to Support Healthcare Diagnosis.
Full text not available from this repository.
| Full Text Status: | Access to this publication is restricted |
| Abstract: | This thesis describes all the process consisting of creating a classification model based in decision trees, exploring the different rules, and collecting knowledge through the best paths found in the trees. Every step of the process has been documented, from the very beginning to the current state of it. Not only a realworld case scenario is presented, but also a more general description of what a data science project is, and the key points to carry out one regardless of the specific field it is placed in. The document begins with a brief list of the goals that wanted to be accomplished through the completion of this thesis, also the scope and the different steps the project has gone through. Then, the context and motivation of the project are described, after which, an extended explanation of the field of machine learning is given, with some real examples of previous successful research. As this project is strongly related to the healthcare world, these examples are focused on the use of machine learning in such field. A section to explain what decision trees are and how they work is given, for the reader to understand how this type of classification model works and why it is very useful for such task. Once the more theoretical part has been covered, the practical side, and what this thesis is mainly built upon, is described. In this section of the document all the different components of the project are detailed step by step. Different approaches were taken when making the project and so are they shown here, covering the obstacles encountered during the process but also insights found are shown. At the end of the document, the results obtained by applying the concepts described throughout the document are shown, along with the future work that could be done (e.g.: improvements), closing with a conclusion that explains, from a personal point of view, how this work has helped me to apply the knowledge obtained during the master to a real-world project and therefore expand my experience in the field of data science. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Programme: | Computer Science MSc (60300) |
| Link to this item: | https://purl.utwente.nl/essays/97399 |
| 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