Medical records consist of a lot of data. Nevertheless, in today’s digitized society it is difficult for humans to convert data into information and recognize hidden patterns. Effective decision support tools can assist medical staff to reveal important information hidden in the vast amount of data and support their medical decisions. The objective of this thesis is to compare five machine learning algorithms for clinical diagnosis. The selected machine learning algorithms are C4.5, Random Forest, Support Vector Machine (SVM), k-Nearest Neighbor (kNN) and Naïve Bayes classifier. First, the machine learning algorithms are applied on three publicly available datasets. Next, the Analytic hierarchy process (AHP) is applied to evaluate which algorithms are more suitable than others for medical diagnosis. Evaluation criteria are chosen with respect to typical clinical criteria and were narrowed down to five; sensitivity, specificity, positive predicted value, negative predicted value and interpretability. Given the results, Naïve Bayes and SVM are given the highest AHP-scores indicating they are more suitable than the other tested algorithm as clinical decision support. In most cases kNN performed the worst and also received the lowest AHP-score which makes it the least suitable algorithm as support for medical diagnosis.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:miun-33940 |
| Date | January 2018 |
| Creators | Hjalmarsson, Victoria |
| Publisher | Mittuniversitetet, Avdelningen för informationssystem och -teknologi |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0816 seconds