Article Per Year (5 Year)
p-Index From 2021 - 2026
2.083
P-Index
This Author published in this journals
All Journal Jurnal Kesehatan Masyarakat Journal of Environmental Science Sustainable JURNAL INOVASI DAN PENGABDIAN MASYARAKAT INDONESIA Jurnal Salingka Abdimas Jurnal Kesehatan Amanah Journal of Computing Theories and Applications ACTIVE: Journal of Physical Education, Sport, Health and Recreation Jurnal Pengabdian Masyarakat Indonesia International Journal of Health Science
Ismi Elya Wirdati
Universitas Muhammadiyah Semarang
Humanities Computer Science & IT Decision Sciences, Operations Research & Management Education Environmental Science Health Professions Law, Crime, Criminology & Criminal Justice Nursing Public Health Social Sciences Other

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Identifikasi Keselamatan dan Kesehatan Kerja dengan Metode Job Safety Analysis (JSA) di Industri Bengkel Farisna, Semarang Ismi Elya Wirdati; Annisa Nur Utami; Lutfi Muzaqi; Izzatul Alifah Sifai
Jurnal Kesehatan Amanah Vol. 8 No. 1 (2024): Jurnal Kesehatan Amanah
Publisher : Universitas Muhammadiyah Manado

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57214/jka.v8i1.724

Abstract

Hazard identification and risk assessment in the Farisna workshop are classified based on the work performed. The use of machinery, equipment, supporting materials, workshop environment, and mechanical work procedures can be a source of potential hazards for workers in the workshop, therefore it is necessary to evaluate health in the Farisna workshop to prevent the risk of harm. This study aims to determine the planning and evaluation of occupational health in the engineering sector in the Farisna workshop. This research method is descriptive qualitative. Using total sampling technique. Data collection by observation with research instruments using JSA or Job Safety forms. The results of this study indicate that of the 7 work activities in the workshop there are 5 activities with medium or medium risk, and there are 2 high risk or high. Medium risks such as being crushed and crushed by heat stress montors, heat disorders, slipping and skin irritation, skin blisters, scratches and punctures, back pain. While the high risk of work activities in the workshop is exposed to explosions, burns, skin irritation, and respiratory problems. Prevention to avoid the risk of work in the workshop should be when working using PPE, doing work carefully, and putting tools in place, and providing fire extinguishers to prevent accidents.
An Explainable Multimodal Framework for Chest X-Ray Alert Classification Using Radiology Reports and Images Edy Winarno; Indah Manfaati Nur; Abdul Karim; Saeful Amri; Ismi Elya Wirdati; Prajanto Wahyu Adi
Journal of Computing Theories and Applications Vol. 3 No. 4 (2026): JCTA 3(4) 2026
Publisher : Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/jcta.16023

Abstract

Artificial intelligence has the potential to support radiology workflows by assisting in the identification of cases that may require additional clinical attention. However, alert-oriented medical AI systems should provide not only classification outputs but also interpretable evidence that can be reviewed and audited by clinicians. This study develops and evaluates an explainable multimodal framework for binary chest X-ray alert classification using paired radiology reports and chest X-ray images. The text branch employs TF-IDF n-gram features with a class-balanced Logistic Regression classifier, while the image branch fine-tunes a pretrained ResNet18 model. The two branches are integrated through probability-level late fusion using a validation-selected fusion weight. Explainability is implemented in a modality-specific manner: global coefficient analysis is used to identify influential textual cues, while Grad-CAM heatmaps are used to visualize salient image regions. Experiments were conducted on paired samples from the Open-i/IU X-Ray dataset using text-only, image-only, and fusion-based evaluation settings. Additional analyses include case-level complementarity analysis, bootstrap confidence intervals for ROC-AUC, shortcut-feature inspection, and qualitative Grad-CAM auditing. The results indicate that the text modality provides the dominant predictive signal under the current proxy-label setting. Late fusion produced a small descriptive improvement on the test set, increasing accuracy from 0.8533 to 0.8667, F1-score from 0.8817 to 0.8936, and ROC-AUC from 0.8936 to 0.9025 compared with the text-only baseline. However, the observed ROC-AUC improvement was not statistically conclusive based on bootstrap analysis. These findings suggest that the proposed framework is useful as a reproducible and auditable multimodal prototype, while also highlighting important limitations, including proxy-label ambiguity, potential label leakage from radiology reports, limited image-branch contribution, lack of external validation, and the need for stronger explanation and calibration assessment.
Co-Authors Abdul Karim Aditya Wisnu Saputra Agustiani, Rina Amri, Saeful Annisa Nur Utami Bayu Cahyo Bina Kurniawan Cahulul Rizaldy Hasan Dewi Puspitaningrum Edy Winarno Fadhila Rahman Nugoroho Hanifa Maher Denny, Hanifa Maher Heni Rusmitasari Hiktiawati, Vilda Indah Manfaati Nur Inna Nur Rahma Fajrin Irmawati, Isti Istiqomah, Willa Avdinta Izzatul Alifah Sifai Kurnia Dewi, Maria Ulfah Laila Zulvatun Nikmah Lestari, Tika Lutfi Muzaqi M. Yogi Riyantama Isjoni Muhammad Muhibbi Musdalifah, Fatma Auliya Nurafifah, Preedes Dwiani Nurjanah, Salisah Prajanto Wahyu Adi Putra, Rizal Dona Pradana Putrisari, Maya Fifit Rahayu Astuti Rifqoh, Lana Isbatur Safika, Nur Salim, Baatsani Febrianti Sarni Sarni Shafira Aulia Az Zahra Syakir Maghfuri Thosim Thosim Yudha, Devara Satria Kartika