Show simple item record

dc.contributor.advisor Premarathne, SC
dc.contributor.author Jayatilaka, PMUA
dc.date.accessioned 2017-12-06T22:26:13Z
dc.date.available 2017-12-06T22:26:13Z
dc.identifier.uri http://dl.lib.mrt.ac.lk/handle/123/12931
dc.description.abstract During the time a patient is admitted in hospital rich sources of clinical, bio medical, contextual, and environmental data about patients have been available in medical and health sciences. These clinical sources of information are marked increasing in both volume and variety. Due to continuous increasing of the size of health care data, certain complexity raised in it. The hidden patterns among patient data can be extracted by applying different techniques. The techniques and tools are very helpful as they provide health care professionals with significant knowledge towards a decision. This research has been conducted to analyze cancer patient's medical records in Sri Lanka in an effective manner to predict the future cost estimation for medicine. It is hypothesized that analyzing cancer patient's medical record can be done through machine learning data mining techniques. By doing so we can help the patients to schedule their financial matters in coming years. In Sri Lanka almost 23,000 individuals diagnosed with a new invasive cancer each year. The costs of the diagnosis and treatment for the cancer are considerable important. These costs have increased over the past years and are expected to increase in the future. It has been claimed that most of the families face difficulties with a diagnosis of cancer have financial issues. To respond to this challenge, we developed an interactive application which utilizes a multiple linear regression model to forecast financial schedule for cancer patients This solution take data set collected from Apeksha Hospital -Maharagama as the input and predict the factors associate with the question. Having received the input this approach prepossess the data set to remove the anomalies. Then build the data model to predict the future cost for the patient. Linear regression technique is used to develop for prediction of future cost estimation. This total solution is build using WEKA data mining software. (WEKA GUI and WEKA API). According to the evaluation of the predictive model the correlation coefficient value is 0.5725 and the root mean squared error is Rs. 553183.25. en_US
dc.language.iso en en_US
dc.title Forecasting financial schedules for cancer patients en_US
dc.type Thesis-Abstract en_US
dc.identifier.faculty IT en_US
dc.identifier.degree MSc in Information Technology. en_US
dc.identifier.department Department of Information Technology en_US
dc.date.accept 2017-05
dc.identifier.accno TH3391 en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record