Article Per Year (5 Year)
p-Index From 2021 - 2026
2.189
P-Index
This Author published in this journals
All Journal Indonesian Journal of Artificial Intelligence and Data Mining Jurnal Kreativitas PKM JOURNAL OF SCIENCE AND SOCIAL RESEARCH Jurnal Manajemen Informasi Kesehatan Indonesia (JMIKI) Indonesian of Health Information Management Journal (INOHIM) PREPOTIF : Jurnal Kesehatan Masyarakat Jurnal Ilmiah Perekam dan Informasi Kesehatan Imelda (JIPIKI) J-REMI : Jurnal Rekam Medik dan Informasi Kesehatan Sehat Rakyat: Jurnal Kesehatan Masyarakat PELS (Procedia of Engineering and Life Science) Indonesian Journal of Health Information Management Services (IJHIMS) Jurnal Akuntansi, Ekonomi dan Manajemen Bisnis
Husni Abdul Muchlis
Universitas Esa Unggul
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Health Professions Medicine & Pharmacology Nursing Public Health Social Sciences Veterinary

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 14 Documents
Search

 1   2 
Convolutional Neural Networks-Based Deep Learning for Diabetic Retinopathy Detection Nurmalasari, Mieke; Kurniawati, Anastasia Cyntia Dewi; Herwanto, Agus; Kurniawati, Dyah; Muchlis, Husni Abdul; Pertiwi, Tria Saras
Indonesian Journal of Artificial Intelligence and Data Mining Vol 9, No 1 (2026): March 2026
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v9i1.38631

Abstract

Diabetic retinopathy (DR) is a major complication of diabetes that can cause permanent vision loss, affecting about 35% of people with type 2 diabetes worldwide. However, existing diagnostic models often struggle with class imbalance and limited generalizability across diverse real-world datasets. Early detection is crucial, yet manual screening is time-consuming and depends on expert assessment. This study develops an automated DR diagnostic system using deep learning to classify fundus images by severity. The model uses an EfficientNetB3 CNN pretrained on ImageNet, combined with CLAHE preprocessing to enhance image contrast. The preprocessing steps include resizing, CLAHE, normalization, and data augmentation (±20° rotation, horizontal flipping, and ZCA whitening). The dataset is the Gaussian-filtered APTOS 2019 set, consisting of 2,750 images across five DR levels (0–4). The model achieved 95% training accuracy and 75% validation accuracy, with overfitting observed after epoch 14. While training performance was high, evaluation metrics (Precision, Recall, F1-Score, and AUC) indicate the need for early stopping or regularization to improve generalization. Overall, CNN-based deep learning can effectively automate DR detection, though further optimization is required for better performance on unseen data. Clinically, this automated pipeline offers a reliable decision-support tool to prioritize high-risk patients for immediate ophthalmological review
BIMBINGAN TEKNIS VISUALISASI DATA KLAIM INA-CBG’S UNTUK PMIK DI RSIJ PONDOK KOPI Nurmalasari, Mieke; Muchlis, Husni Abdul; Qomarania, Witri Zuama; Iqbal, Muhammad Fuad; Kendrastuti, Nungky Nurkasih; Maryati, Yati; Simanjuntak, Herliani Florentina; Aruni, Amelia; Rachmadiany, Syalaisha Nuraini; Arman, Akhmad Tri; Rhinaldi, Steven
Indonesian Journal of Health Information Management Services Vol. 6 No. 1 (2026): Indonesian Journal of Health Information Management Services (IJHIMS)
Publisher : APTIRMIKI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33560/ijhims.v6i1.159

Abstract

Visualisasi data klaim INA-CBG’s memiliki peran strategis dalam meningkatkan efisiensi dan kualitas pelayanan rumah sakit. Unit Rekam Medis dan Informasi Kesehatan (RMIK) RSIJ Pondok Kopi menghadapi keterbatasan kompetensi dalam mengolah dan memvisualisasikan data klaim secara analitis. Tujuan bimbingan teknis ini meningkatkan kompetensi Perekam Medis dan Informasi Kesehatan (PMIK) dalam mengolah dan memvisualisasikan data klaim INA-CBG’s menggunakan Tableau Public untuk mendukung pengambilan keputusan berbasis data. Kegiatan dilaksanakan pada tanggal 12 November 2025 dengan metode pelatihan sistem yang meliputi sosialisasi, pretest, penyajian materi, praktik langsung dalam pembuatan visualisasi data, pengumpulan, dan evaluasi. Sebanyak 14 peserta dari unit Pelatihan, Rekam Medis, Casemix, dan perawat melakukan pelatihan selama 120 menit. Hasil dari kegiatan peserta mampu membuat berbagai jenis visualisasi (pie chart, bar chart, boxplot, dan interactive dashboard) dengan penilaian nilai rata-rata dari 52 (pretest) hingga 73 (evaluasi akhir), menghasilkan penilaian kepuasan sebesar 40,4%. Kegiatan yang dilaksanakan telah meningkatkan kompetensi PMIK dalam visualisasi data klaim INA-CBG’s dan mendorong terbentuknya budaya kerja berbasis data di rumah sakit.
Pengaruh Kualitas Catatan terhadap Keakuratan Kode Penyebab Kematian di Rumah Sakit Pertamina Jaya Regy Permata Sari; Husni Abdul Muchlis; Hosizah, Hosizah; Yati Maryati
Sehat Rakyat: Jurnal Kesehatan Masyarakat Vol. 5 No. 2 (2026): Mei 2026
Publisher : Yayasan Pendidikan Penelitian Pengabdian Algero

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54259/sehatrakyat.v5i2.7440

Abstract

The accuracy of cause-of-death coding is essential for health statistics and policy-making. Incomplete, inaccurate, and unclear documentation by physicians can lead to coding errors and reduce the validity of mortality data. This study aimed to analyze the effect of documentation quality on the accuracy of cause-of-death coding at Pertamina Jaya Hospital. This quantitative study used a cross-sectional design and was conducted in January 2026. The sample consisted of 56 Medical Certificates of Cause of Death (MCCD) from September–November 2024, selected using quota  sampling. Data were collected through observation and analyzed using univariate and bivariate analyses with logistic regression. The results showed that 14 MCCDs (25%) had accurate cause-of-death coding, while 42 MCCDs (75%) were inaccurate. Poor-quality documentation was found in 30 MCCDs (54%), while good-quality documentation was found in 26 MCCDs (46%). Bivariate analysis demonstrated a significant effect of documentation quality on coding accuracy (p = 0.037). An odds ratio of 4.062 indicated that good-quality documentation had four times greater odds of producing accurate cause-of-death codes, explaining 12.1% of the variance in coding accuracy (R² = 0.121). The study concludes that standard operating procedures and training for physicians and coders are needed to improve accuracy and validity of mortality data.
PERANCANGAN INSTRUMEN AUDIT KUALITAS DOKUMENTASI KLINIS KASUS NON BEDAH DI RUMAH SAKIT UKRIDA Ayuningtyas, Meta; Muchlis, Husni Abdul; Hosizah, Hosizah; Temesvari, Nauri Anggita
PREPOTIF : JURNAL KESEHATAN MASYARAKAT Vol. 10 No. 1 (2026): APRIL 2026
Publisher : Universitas Pahlawan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/prepotif.v10i1.57516

Abstract

Pendokumentasian berkualitas harus memenuhi kriteria kelengkapan, akurasi, ketepatan waktu, konsistensi, sehingga diperlukan audit rekam medis melalui analisis kualitatif. Hasil Observasi periode Oktober-November 2024 terhadap 80 berkas rekam medis kasus bedah menggunakan Medical Record Quality Scoring Tool (MeReQ) menunjukan Completeness 64%, Operative Procedures 78%, Acuracy 100%, Tracking 50%, Informed Consent 89%. Beberapa komponen mencapai 100% tanda vital, ringkasan pulang, catatan terapi. Selain itu komponen riwayat kesehatan keluarga 6%, pelacakan instrumen operasi 0%, alternatif 61%, data ini menunjukan kualitas dokumentasi perlu ditingkatkan. Penelitian bertujuan merancang instrumen audit kualitas dokumentasi klinis kasus non bedah di rumah sakit. Penelitian menggunakan metode Research and Development (R&D) model ADDIE, meliputi tahap analisis, perancangan, pengembangan, dan uji coba. Penelitian bulan Desember 2025. Tahap analisis melalui wawancara dengan 10 informan Dokter Spesialis, Perawat, Kepala Instalasi Rekam Medis, Tim Mutu, Verifikator Internal. Tahap perancangan dan pengembangan dengan mengintegrasikan indikator kualitas dokumentasi klinis (legible, reliable, precise, complete, consistent, clear, timely) dan Standar Akreditasi Rumah Sakit (STARKES 2024). Uji coba instrumen pada 50 berkas rekam medis kasus non bedah periode September–Oktober 2025 oleh 5 orang Perekam Medis dan Informasi Kesehatan dengan pengalaman kerja minimal 6 bulan. Uji validitas menggunakan Content Validity Index (CVI). Hasil penelitian sebagian besar item memperoleh nilai I-CVI 1,00, dua item nilai I-CVI 0,80, dan nilai S-CVI/Ave 0,98, menunjukkan validitas isi sangat baik. Instrumen audit layak digunakan sebagai alat evaluasi kualitas dokumentasi klinis kasus non bedah di Rumah Sakit UKRIDA
Co-Authors Ambarwati Arman, Akhmad Tri Aruni, Amelia Ayuningtyas, Meta Dyah Kurniawati Herwanto, Agus Hosizah Hosizah Iqbal, Muhammad Fuad Kurniawati, Anastasia Cyntia Dewi Lestari, Betri Widya Lestari, Jayanti Menna, Yasinta Rosalia Muzdalifah, Ifah Nanda Dina Cahya Nungky Nurkasih Kendrastuti Nurmalasari, Mieke Oktavianti, Putri Purba, Andrea Krisler Qomarania, Witri Uama Rachmadiany, Syalaisha Nuraini Regy Permata Sari Rhinaldi, Steven Simanjuntak, Herliani Florentina Temesvari, Nauri Anggita Tria Saras Pertiwi Wahyu Sulistiadi Witri Zuama Qomarania Yati Maryati Yati Maryati Yulia, Noor Yusnaeni Yusnaeni, Yusnaeni