Claim Missing Document
Check
Articles

Found 2 Documents
Search

Expert System for Diagnosis of Lung Disease from X-Ray Using CNN and SVM Zulkifli, Zulkifli; Soeprihatini, Retno Ariza; Sfenrianto, Sfenrianto; Wiyanti, Zulvi; Bintoro, Panji; Fitriana, Fitriana; Sukarni, Sukarni; Putri, Nopi Anggista; Andini, Dwi Yana Ayu
International Journal of Artificial Intelligence Research Vol 7, No 2 (2023): December 2023
Publisher : STMIK Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v7i1.870

Abstract

The lung disease diagnosis expert system utilizes human knowledge to diagnose various conditions affecting the lung. Diseases caused by fungal or bacterial infection in the organ can cause inflammation as well as death when it is not detected on time. A standard method to diagnose these conditions is the use of a chest X-ray (CXR), which requires careful examination of the image by an expert. In this study, several CNN and SVM architectural models were proposed to classify CXR images to diagnose whether a person has COVID-19, Viral Pneumonia, Bacterial Pneumonia, Tuberculosis (TB), and Normal. The experiment showed that InceptionV3 had the best results compared to other CNN architectures and SVM. Classification accuracy, precision, recall, and f1-score of CXR images for COVID-19, Viral Pneumonia, Bacterial Pneumonia, TB, and Normal were 0.86, 0.91, 0.91, and 0.91, respectively. This study was based on a deep learning system with different CNN and SVM architectures that can work well on the CXR images dataset for diagnosing lung disease.
Analysis of Respondent Characteristics Regarding The Severity of Community-acquired Pneumonia Patients at Dr. H. Abdul Moeloek Hospital, Lampung. Sanjaya, Rizki Putra; Herdato, M. Junus Didiek; Ajipurnomo, Adhari; Herliyana, Lina; Dilangga, Pad; Soeprihatini, Retno Ariza; Lyanda, Apri; Hendarto, Gatot Sudiro; Sinaga, Fransisca Tarida Yuniar; Kusumajati, Pusparini
Jurnal Aisyah : Jurnal Ilmu Kesehatan Vol 10, No 1 (2025): March
Publisher : Universitas Aisyah Pringsewu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30604/jika.v10i1.3096

Abstract

Community-acquired pneumonia (CAP) is a leading cause of morbidity and mortality worldwide, particularly among the elderly and immunocompromised patients. Various factors, including age, gender, bacterial pattern, comorbidities, and Pneumonia Severity Index (PSI) score, influence CAP severity. Understanding these characteristics is crucial for optimizing treatment strategies and predicting clinical outcomes. This descriptive-analytical cross-sectional study was conducted at Dr. H. Abdul Moeloek Hospital, Lampung, from December 2022 to January 2023. A total of 102 CAP patients were analyzed based on their age, gender, bacterial pattern, comorbidities, and PSI score. Data were processed using IBM SPSS 21.0, with Pearson correlation applied to assess relationships between variables. A statistically significant correlation was found between age and PSI score (p = 0.018), with a low-strength positive correlation (R = 0.234). This suggests that as age increases, CAP severity also increases (p = 0.011). However, no significant correlations were found between PSI score and gender, bacterial pattern, or diabetes mellitus. This study confirms that age is a significant factor influencing CAP severity, emphasizing the need for early screening and intervention in elderly patients. Although gender, bacterial pattern, and diabetes mellitus were not significantly correlated with CAP severity.