University of Twente Student Theses
Leveraging machine learning and process mining to predict anaemia with the help of biomarker data
Pingel, M.S. (2021) Leveraging machine learning and process mining to predict anaemia with the help of biomarker data.
|
PDF
4MB |
| Abstract: | With almost a third of the world population affected by anaemia, accurate diagnostic tools need to be developed that offer transparency and understandability. Diagnostic pathways are one such tool and are often used in the context of anaemia diagnostics. This thesis has the aim of assessing the anaemia standard from the Dutch Nederlands Huisartsen Genootschap (NHG). By using a combination of process mining and machine learning techniques, biomarkers are identified that have a great impact on the prediction performance of machine learning classifiers. Different pre-processing techniques are compared and their effect on the machine learning performance explained. This involves the use of various missing value imputation techniques, as well as class imbalance handling and feature selection. By doing this, biomarker sets can be defined that have the potential of complementing the already existing standard. For the assessment performance, a methodology process is developed that can also be applied to other types of diagnostic models. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 44 medicine, 54 computer science, 85 business administration, organizational science |
| Programme: | Business Information Technology MSc (60025) |
| Link to this item: | https://purl.utwente.nl/essays/88331 |
| 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