Decision Support System Erythemato-Squamous Diseases Classification Diagnosis Using Linear Vector Quantization Based Clinical Atributes

Telemedicine technology is currently a necessity in society. This study aims to design and build a decision support system to classify Erythemato-Squamous disease using Linear Vector Quantization, which is later expected to contribute to strengthening the decision support system regarding Erythemato-Squamous disease used in telemedicine. Erythemato-squamous is a group of skin diseases. This skin disease is categorized into 6 groups, including psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis and pityriasis rubra pilaris. Each group has its own characteristics and signs. The decision support system built in this research is based on clinical attribute data. The data used in this study is data from the UCI Repository which consists of 180 data, consisting of 60 learning data and 120 testing data. The results of this study indicate that learning based on clinical attribute data is psoriasis cluster, seboreic dermatitis, lichen planus, pityriasis rosea, and chronic dermatitis not enough based on clinical attribute data/attributes, or it can be said that other data/attributes are still needed that characterize these clusters. Meanwhile, to detect the sixth cluster (pityriasis rubra pilaris) using data/clinical attributes, the system has been able to identify it well.