Show simple item record

dc.contributor.advisorAlam, Md. Ashraful
dc.contributor.authorSiddiquee, Mohib Billah
dc.contributor.authorFuad, Mostofa Jamil
dc.contributor.authorAzmain, Md. Fahim
dc.date.accessioned2019-03-20T05:35:52Z
dc.date.available2019-03-20T05:35:52Z
dc.date.copyright2018
dc.date.issued2018-07
dc.identifier.otherID 12201043
dc.identifier.otherID 13301081
dc.identifier.otherID 14201057
dc.identifier.urihttp://hdl.handle.net/10361/11602
dc.descriptionThis thesis is submitted in partial fulfilment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2018.en_US
dc.descriptionCataloged from PDF version of thesis.
dc.descriptionIncludes bibliographical references (pages 37-41).
dc.description.abstractPatients in the intensive care unit (ICU) receive a deep observation for controlling and responding to their rapidly changing physiological conditions. The quality of their care depends on clinical staff combining large amounts of clinical data to understand the severity of their illness. Actually in real time doctors and nurses have to take care of huge amount of data. Sometimes, they cannot focus on all the parameters at the same time. After collecting all the parameters, they take decisions. A lack of early recognition of physiologic decline can play a major role in failure to rescue patients. Early prediction is one of the important tasks in the ICU. In this paper, we propose a machine learning approach to improve decision support in ICU. In the proposed model decision tree will be used to predict the future health condition of patients. The curve of the decision tree of the proposed model will show how severe the patient‘s condition is. It will also show the health improvements and decrements. In this model there is option for controlling the lifesaving machines of ICU like ventilation machine, blood warmer machine and syringe pump machine. To control the machines this model uses logistic regression algorithm. It will use some independent variables to predict the decision of automatic intervention. Using the proposed model doctors can easily monitor the health of ICU patients. As it predicts risks, doctors can take early preparation for worst situation. Automatic intervention decisions for ICU machines can save lives in critical moments. As a whole, the model is specially designed for coronary care unit of ICU.en_US
dc.description.statementofresponsibilityMohib Billah Siddiquee
dc.description.statementofresponsibilityMostofa Jamil Fuad
dc.description.statementofresponsibilityMd. Fahim Azmain
dc.format.extent41 pages
dc.language.isoenen_US
dc.publisherBRAC Universityen_US
dc.rightsBRAC University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.
dc.subjectICUen_US
dc.subject.lcshMachine learning
dc.subject.lcshArtificial intelligence
dc.titleMachine learning approach for improving decision support in ICUen_US
dc.typeThesisen_US
dc.contributor.departmentDepartment of Computer Science and Engineering, BRAC University
dc.description.degreeB. Computer Science and Engineering


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record