ELECTRICA

A Linear Stochastic System Approach to Model Symptom Based Clinical Decision Support Tool for the Early Diagnosis for Psoriasis, Seborrheic Dermatitis, Rosacea and Chronic Dermatitis

1.

Department of Informatics, İstanbul University, İstanbul, Turkey

2.

Institue of Graduate Studies Science and Engineering, İstanbul University-Cerrahpaşa, İstanbul, Turkey

3.

Department of Biomedical Device Technology, İstanbul Aydın University, İstanbul, Turkey

4.

Department of Electrical and Electronics Engineering, İstanbul University-Cerrahpaşa, İstanbul, Turkey

ELECTRICA 2019; 19: 48-58
DOI: 10.26650/electrica.2018.081118
Read: 1243 Downloads: 607 Published: 01 January 2019

Prediction models provide the probability ofan event. These models can be used to predict disease’s outcomes, reccurenciesafter treatments. This paper presents an expert system called Symptom BasedClinical Decision Support Tool (SBCDST) for early diagnosis oferythemato-squamous diseases incorporating decisions made by Bayesianclassification algorithm. This tool enables family practitioners todifferentiate four types of erythemato-squamous diseases using clinicalparameters obtained from a patient. In SBCDST, Psoriasis, SeborrheicDermatitis, Rosacea and Chronic dermatitis diseases are described by means ofwell-classified set of attributes. Attributes are generated from the typicalsign and symptoms of disorder. Based on our clinical results, tool yields 72%,93%, 89% and 95% correct decisions on the selected dermatology diseasesrespectively. System proposed will provide the opportunity for early diagnosisfor the patient and the expert medical doctor to take the necessary preventivemeasures to treat the disease; and avoid malpractice which may causeirreversible health damages.

Cite this article as: Zaim Gökbay İ, ZileliZB, Sarı P, Aksoy TT, Yarman S. A Linear Stochastic System Approach to ModelSymptom Based Clinical Decision Support Tool for the Early Diagnosis forPsoriasis, Seborrheic Dermatitis, Rosacea and Chronic Dermatitis. Electrica,2019; 19(1): 48-58.

Files
EISSN 2619-9831