ANALYSIS OF TUBERCULOSIS PATIENT CHARACTERISTICS OF GORONTALO CITY HOSPITAL USING K-MEANS CLUSTERING METHOD

Background: Tuberculosis (TBC) is a major health problem in Indonesia, especially in Gorontalo, with high spread due to poor ventilation, overcrowding, and unhealthy lifestyles. Purpose: To analyze the characteristics of TB patients in one of Gorontalo City's hospitals using K-Means Clustering. Methods: Data including age, gender, TBC history, HIV status, diabetes history, hypertension, drug resistance, drug side effects, and treatment results were analyzed for the number of clusters using the K-Means method because it is effective in grouping data based on similarity, easy to implement, and works well on large datasets. Results: The analysis resulted in three clusters. Cluster 0 (219 individuals): majority female (63.50%), mean age 45.37 years, low address score (0.49), low resistance and therapy (6.40%), no comorbidities, all experienced side effects (100%), and survival rate 4.10%. Cluster 1 (150 individuals): mean age 52.21 years, higher address score (0.77), resistance 7.30%, therapy 5.30%, comorbidities 100%, all experienced adverse events, and survival rate 4.70%. Cluster 2 (98 individuals): mean age 48.58 years, address score 0.65, very low resistance and therapy (2%), no side effects, 42.90% had comorbidities, and the highest survival rate (12.20%). Conclusion: Three clusters were obtained from the analysis using K-Means. Clustering supports specific interventions such as comorbidity management or intensive surveillance, improving TB control programs in Gorontalo.

Abstract licence: CC BY-SA

29 more references, whose wording the paper’s licence keeps private.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.