APSR2026-807

Yes
Late-Breaking
Submitted
Oral Presentation
AO21-004
 
 
https://storage.unitedwebnetwork.com/files/1285/1221240-46903-APSR26_Fabiola Anastasia_434202.pptx
Format: PPTX Only
 
Format: PDF Only
06. Tuberculosis
5

No more than 15 authors can be listed.
Please ensure the authors are listed in the right order.
If there are multiple affiliations, please use the "+" button next to "Select Country/Region" to add additional affiliation fields.

Fabiola Anastasia Kartini Fau * Persahabatan Hospital National Respiratory Center Department of Pulmonology and Respiratory Medicine, Faculty of Medicine Universitas Indonesia Bekasi Indonesia
Heidy Agustin - Persahabatan Hospital National Respiratory Center Department of Pulmonology and Respiratory Medicine, Faculty of Medicine Universitas Indonesia Jakarta Indonesia
Diah Handayani - Persahabatan Hospital National Respiratory Center Department of Pulmonology and Respiratory Medicine, Faculty of Medicine Universitas Indonesia Jakarta Indonesia
Rosa Marlina - Infectious Disease Hospital Prof. Dr. Sulianti Saroso Department of Pulmonology and Respiratory Medicine, Faculty of Medicine Universitas Indonesia Jakarta Indonesia
Iman Firmansyah - Infectious Disease Hospital Prof. Dr. Sulianti Saroso Department of Pulmonology and Respiratory Medicine, Faculty of Medicine Universitas Indonesia Jakarta Indonesia
 
 
 
 
 
 
 
 
 
 
Presenting Author Details
Fabiola Anastasia Kartini
Fau
fabiolaanastasiafau@gmail.com
+6281213149426
31-40
Indonesia
Original Research
Artificial intelligence-based chest photo profile in HIV patient in Indonesia Infectious Disease Center Hospital
Maximum 25 words
Abstract Content
Tuberculosis (TB) is the most common opportunistic infection in HIV patients with a high mortality rate. Conventional chest X-ray examinations often have limitations in detecting TB, especially in HIV patients with atypical clinical manifestations. Advances in artificial intelligence (AI) technology allow for more objective and rapid chest X-ray analysis. This study aims to analyze AI-based chest X-ray profiles as a screening tool for TB in HIV patients.
This study is an analytical cross-sectional study of 30 HIV patients who had never received antituberculosis treatment before. All subjects who met the study criteria (adults aged ≥ 18 years and HIV patients who have never received OAT treatment before) underwent AI-based chest X-ray examinations at Sulianti Saroso Infectious Disease Hospital, Jakarta. Collected data included patient characteristics, AI-based TB scores, TCM results, and CRP levels.
Total of the subject about 30 HIV patients, 66.7% were male with a median age of 34 years. Based on AI, 6.7% had a TB score ≥50, and 10% of patients were classified as TB based on clinician assessment. There was a significant difference between AI-based TB scores in the TB and non-TB groups (p=0.008). AI results showed significant agreement with TCM results (p<0.001). Lung lesion findings based on AI are pleural effusion (13.3%) followed by consolidation, infiltrate and atelectasis (3.3%). CRP values in patients with TB showed an increase (6.51–12.16 mg/dL)
AI-based chest X-rays have potential as a TB screening tool in HIV patients with good sensitivity compared to TCM results. CRP testing may serve as an additional parameter for confirming TB diagnosis in HIV patients.
 
 
 
 
 
No
No
 
JPG or JPEG or PNG format ONLY
AI-based chest X-ray, HIV, tuberculosis
maximum 3 keywords and no abbreviations, separated by commas
 
270