Development of a Predictive Model for the Classification of the Survival of Hepatitis Patients Using Decision Trees Algorithm (Record no. 6176)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02777nam a22001457a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 210809b ||||| |||| 00| 0 eng d |
| 100 ## - MAIN ENTRY--AUTHOR | |
| Author | OWIE-OBAZEE, Esosa Deris |
| 245 ## - TITLE STATEMENT | |
| Title | Development of a Predictive Model for the Classification of the Survival of Hepatitis Patients Using Decision Trees Algorithm |
| 250 ## - SUPERVISOR | |
| Supervisor | Prof. IDOWU, P. A. |
| 260 ## - IMPRINT | |
| Place of publication | Ibafo |
| Department (College) | Computer Science and Mathematics |
| Date of publication | 2020 |
| 300 ## - COLLATION | |
| Pagination | xi,; 74p. |
| Other physical details | dia, tables |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc | This study is aimed at the application of decision trees algorithm for the<br/>classification of the survival of patients living with hepatitis C virus. The study<br/>achieved this by eliciting knowledge on the variables monitored during the treatment<br/>of Hepatitis C patients and collecting relevant data, formulating the classification<br/>model, simulating the model and validating the model.<br/>Structured interview was used to elicit information on the variables monitored<br/>among Hepatitis patients receiving treatment. C4.5 decision trees algorithm was used<br/>to formulate the classification model for the survival of Hepatitis C disease based on<br/>the information collected. The classification model was simulated using Waikato<br/>Environment for Knowledge Analysis (WEKA) software. The classification model was<br/>validated based on accuracy, sensitivity, false alarm rate and precision.<br/>The results of the study showed that 19 variables were associated with the<br/>classification of the survival of patients receiving treatment for Hepatitis C. The results<br/>also identified a number of variables which had missing values from the data collected.<br/>The results of the simulation showed that the higher the proportion of datasets use for<br/>training then the higher the performance of the model on the testing dataset. Therefore,<br/>using 90% of the dataset for training and 10% of the dataset for testing showed the<br/>highest performance. The results also showed that twelve rules were inferred from the<br/>decision trees which was formulated from the simulation with the best performance.<br/>The results also showed that among the 19 variables identified, 11 variables were the<br/>most relevant, namely: ascites, age, spiders, bilirubin, liver firmness, sgot, palpable<br/>spleen, anorexia, and liver size.<br/>The study concluded that the classification model developed can be adopted for<br/>use by physicians in locations where there are no experts to provide as decision support <br/>vi<br/>thus improving survival which may mitigate untimely deaths. The study also concluded<br/>that the identification of a smaller yet relevant number of variables will reduce the<br/>challenge of focusing on irrelevant variables monitored thus reducing the response time<br/>of data collection and survival classification. |
| 650 ## - TRACINGS | |
| Main Subject | Computer Science |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Item type | Students Thesis |
No items available.