2012 · 54 citations · 17 references
ComputingBiomedical InformaticsHealth InformaticsData MiningHealthcare Information SystemsMachine LearningClassificationDecision Support In HealthcareEnsemble LearningEnsemble MethodsPredictive Health ModelingClassification AlgorithmsClinical Data MiningDiagnostic Prediction ModelsElectronic Health Record Prediction ModelsElectronic Medical RecordsMachine Learning For HealthcarePatient Medical RecordsRough Set Theory
This paper applies the data mining process to predict hypertension from patient medical records with eight other diseases. A sample with the size of 9862 cases has been studied. The sample was extracted from a real world Healthcare Information System database containing 309383 medical records. We observed that the distribution of patient diseases in the medical database is imbalanced. Under-sampling technique has been applied to generate training data sets, and data mining tool Weka has been used to generate the NaIve Bayesian and J-48 classifiers. In addition, an ensemble of five J-48 classifiers was created trying to improve the prediction performance, and rough set tools were used to reduce the ensemble based on the idea of second-order approximation. Experimental results showed a little improvement of the ensemble approach over pure Na'ive Bayesian and J-48 in accuracy, sensitivity, and F-measure.
17
Mark Hall, Eibe Frank, Geoffrey Holmes et al. · ACM SIGKDD Explorations Newsletter · 2009 · 17.8K citations
Shirin Khambata‐Ford, Christopher R. Garrett, Neal J. Meropol et al. · Journal of Clinical Oncology · 2007 · 1.1K citations · Full text
Coronary Artery Calcium Score and Risk Classification for Coronary Heart Disease Prediction
Tamar S. Polonsky · JAMA · 2010 · 1.1K citations · Full text
Medicine, Cardiology, Epidemiology +16
A. Richey Sharrett, Christie M. Ballantyne, Sean A. Coady et al. · Circulation · 2001 · 939 citations · Full text