Risk Factor Prediction of Hepatitis Patient Using Machine Learning Approach

Simple item page
dc.contributor.authorSeble Azene Alemu
dc.date.accessioned2024-12-24T13:27:33Z
dc.date.available2024-12-24T13:27:33Z
dc.date.issued2024
dc.descriptionIn this study 1,032 rows of data collected from Felege Hiwot Referral Hospital, Tibebe Ghion Referral Hospital, and Addis Alem Hospital. Data were collected from patient medical records. The dataset consists of Age, Gender, Steroid, Antivirals, Fatigue, Malaise, Anorexia, Liver big, Liver firm, Spleen palpable, Spiders, Ascites, Varies, Bilirubin, Alk phosphate, Sgot, Albumin, Protime, Hemoglobin, Creatinine and Class (Low risk or High risk) attributes that are used for predicting risk factor of hepatitis patient. Six machine learning techniques, namely Decision Tree (DT), Random Forest (RF), Deep Neural Network (DNN), Extreme Grahigh risknt Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Light Grahigh risknt Boosting Machine (LightGBM), were combined with PSO and GA for hyperparameter optimization to identify the best-performing model.
dc.identifier.urihttps://rdmc.aphi.gov.et/handle/123456789/110
dc.language.isoen
dc.titleRisk Factor Prediction of Hepatitis Patient Using Machine Learning Approach
dc.typeDataset
dspace.entity.type
local.PeriodOfTime2024
local.access.levelAccessible up on reasonable request.
local.contributor.emailsebleazene12@gmail.com
local.contributor.organizationBahir Dar university
local.contributor.phone0000000000000
local.contributor.unitInstitute of technology
local.coverage.ageYes
local.coverage.geographicFacility
local.coverage.sexYes
local.criteria.exclusionIncomplete medical cards was excluded from the study
local.criteria.inclusionThe medical cards having complete information.
local.data.qualityGood
local.datacollection.ended2024
local.datacollection.started2024
local.datatypeHealth facility data
local.date.dissemination2024-09-07
local.date.finalization2024-08-07
local.disseminatedbyBahir Dar university
local.formatExcel
local.funderNA
local.has.geospatialNo
local.has.microdataYes
local.idAPHI-RDMC-057
local.is.externalYes
local.keywordsHepatitis, Risk factor prediction, machine learning, Model Explainability
local.objectiveTo develop a machine learning model for predicting the risk factor of hepatitis patients and elucidate the predictive mechanisms of the models
local.publication.statusNot published
local.response.rateNA
local.samplingCensus
local.sampling.size1032
local.study.designCross-sectional study
local.study.populationAll hepatitis patients attending during the data collection period was the study population.
local.subject.areaHealth and health related
local.toolsIn-depth tools adapted

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Dataset.csv
Size:
58.17 KB
Format:
Unknown data format
Download

Collections

Evidence-Based Medicine