Claim Missing Document
Check
Articles

Found 6 Documents
Search

PENGARUH DESIGN USER INTERFACE TERHADAP KEPUASAN PENGGUNA PADA APLIKASI JAKSEHAT DI PUSKESMAS KEBON JERUK Santri, Santri; Kurniawati, Anastasia Cyntia Dewi
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 2 (2025): May 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i2.2954

Abstract

Jaksehat merupakan salah satu aplikasi yang dikembangkan oleh Dinas Kesehatan Jakarta yang bertujuan untuk memudahkan Masyarakat mengakses pelayanan Kesehatan khususnya puskesmas dan rumah sakit umum daerah (RSUD) di Jakarta agar lebih cepat dan efisien. Design User Interface menjadi salah satu bagian paling penting dalam pembuatan suatu aplikasi agar user mudah menggunakan aplikasi dan user dapat merasakan manfaat nyata dari aplikasi yang telah dibuat. Kepuasan pengguna dari suatu sistem dapat dilihat dari UI yang sudah sesuai dengan kebutuhan sistem dan tercapainya ekspektasi pengguna terhadap sistem. Tingkat penggunaan aplikasi Jaksehat di Puskesmas Kebon Jeruk masih rendah, hal ini disebabkan oleh kurangnya pemahaman tentang fitur-fitur aplikasi, desain UI yang tidak user-friendly, serta kurangnya panduan yang jelas, sehingga pasien lebih memilih mendaftar secara manual.Tujuan penelitian ini untuk mengetahui pengaruh Design user interface terhadap kepuasan pengguna aplikasi Jaksehat menggunakan metode End User Computing Satisfaction. Penelitian ini menggunakan rancangan kuantitatif dengan survey observasional dan pendekatan cross-sectional. Sampel penelitian ini 99 pengguna aplikasi Jaksehat di Puskesmas Kebon Jeruk. Pengumpulan data menggunakan kuesioner, analisis data menggunakan metode regresi linear sederhana. Hasil penelitian  didapatkan ada pengaruh yang signifikan antara design user interface terhadap kepuasan pengguna aplikasi Jaksehat dengan nilai P-value 0,000 dan nilai korelasi atau hubungan sebesar 0,644. Design User interface memberikan pengaruh sebesar 41% terhadap kepuasan pengguna aplikasi Jaksehat di Puskesmas Kebon Jeruk.
Length of Stay Patterns and Their Relation to Coding Accuracy: Polanya Lama Tinggal Pasien dan Hubungannya dengan Akurasi Koding Muchlis, Husni Abdul; Qomarania, Witri Zuama; Nurmalasari, Mieke; Kurniawati, Anastasia Cyntia Dewi; Lestari, Betri Widya
Procedia of Engineering and Life Science Vol. 9 (2025): Proceedings of the 2025 Annual Meeting of APTIRMIKI
Publisher : Universitas Muhammadiyah Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Hospitals face efficiency and quality challenges within the Case-Based Groups (CBG's) financing system, where a patient’s Length of Stay (LOS) is critical. Accurate LOS data is crucial for strategic decisions, cost management, and quality care. A study at a Type B Hospital in Bekasi City found significant variation and outliers in LOS, indicating a non-normal distribution. This observational analytic study, involving 3,151 inpatient claims from January 2024, analyzed LOS data and its impact on clinical documentation and coding quality. The analysis compared the Arithmetic Mean Length of Stay (AMLOS) and the Geometric Mean Length of Stay (GMLOS) to identify outliers, followed by a Wilcoxon test. Results showed LOS varied from 1 to 48 days, with an AMLOS of 7.13 and a GMLOS of 6.76 days, indicating positive skewness from outliers. AMLOS was consistently higher than GMLOS in the top 10 CBG's, especially for moderate and severe cases. The Wilcoxon test (p<0.05) confirmed a significant statistical difference, showing GMLOS more accurately represents the appropriate LOS. The presence of outliers (e.g., >30 or 44 days) suggests potential issues with documentation or coding. Therefore, using the more robust GMLOS is crucial for hospitals to optimize management, improve care, and maintain the quality of clinical documentation and coding.
PENGGUNAAN MYSQL DALAM PERANCANGAN DATABASE REKAM MEDIS ELEKTRONIK: STUDI LITERATUR Kurniawati, Anastasia Cyntia Dewi; Uli, Angel Septiana
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 4 (2025): November 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i4.4648

Abstract

Abstract: The amendment to the Minister of Health Regulation on medical records requires all healthcare facilities in Indonesia to implement Electronic Medical Records (EMR) no later than December 31, 2023. Many clinics, as part of these facilities, still rely on a file-based approach, resulting in scattered data that are difficult to retrieve, prone to duplication, and often inaccurate. This study aims to analyze the use of MySQL in designing a web-based EMR database. The method employed is a Systematic Literature Review (SLR), selecting articles based on inclusion and exclusion criteria, yielding 20 relevant journals. MySQL was chosen because it is an open-source database management system (DBMS) licensed under GPL, supports multi-user access, offers fast query performance, and provides adequate security features. Its advantages include easy distribution, compliance with standard SQL, and reliable performance for managing medical data. However, limitations such as inefficient decentralized configuration and longer execution times with large-scale data must be considered. The database design process follows five stages: Requirement, Design, Implementation, Verification, and Maintenance. The findings indicate that MySQL is suitable for EMR database design due to its functional strengths and flexibility, although large-scale optimization remains a challenge.Keywords: Electronic Medical Records, MySQL, Database Abstrak: Perubahan Peraturan Menteri Kesehatan tentang rekam medis mewajibkan seluruh fasilitas pelayanan kesehatan (fasyankes) di Indonesia menyelenggarakan Rekam Medis Elektronik (RME) paling lambat 31 Desember 2023. Klinik sebagai salah satu fasyankes masih banyak yang mengandalkan pendekatan file-based, sehingga data tersebar, sulit dicari, rawan duplikasi, dan sering tidak akurat. Penelitian ini bertujuan menganalisis pemanfaatan MySQL dalam perancangan database RME berbasis web. Metode yang digunakan adalah Systematic Literature Review (SLR) dengan menyeleksi artikel sesuai kriteria inklusi dan eksklusi, dan diperoleh 20 jurnal relevan. MySQL dipilih karena merupakan sistem manajemen database (DBMS) open source berlisensi GPL, mendukung multiuser, memiliki kecepatan query yang baik, serta fitur keamanan yang memadai. Kelebihan MySQL meliputi kemudahan distribusi, dukungan standar SQL, dan performa yang andal untuk pengelolaan data medis. Namun, kelemahan seperti konfigurasi desentralisasi yang kurang efisien dan peningkatan waktu eksekusi pada data berskala besar perlu diperhatikan. Proses perancangan database mengikuti lima tahap: Requirement, Design, Implementation, Verification, dan Maintenance. Hasil kajian menunjukkan MySQL layak digunakan untuk perancangan database RME karena keunggulan fungsional dan fleksibilitasnya, meskipun optimalisasi skala besar tetap menjadi tantangan.Kata kunci: Rekam Medis Elektronik, MySQL, Database
PERANCANGAN USER INTERFACE DIGITALISASI ANALISIS KELENGKAPAN REKAM MEDIS MENGGUNAKAN METODE DESIGN THINKING DI RSUD PALEMBANG BARI Yuliani, Dian; Kurniawati, Anastasia Cyntia Dewi; Hosizah, Hosizah; Ichwan, Arief
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 2 (2025): May 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i2.3053

Abstract

Abstract: The mandatory of Electronic Medical Records (EMR) in Indonesia encourages Health Information Recorders (HIMs) to find the best solution to maintain the quality of EMR. Although EMR has been implemented, the electronic system in hospitals does not have enough features for effective quality assurance, resulting in difficulties for HIMs in quantitative and qualitative analysis. Based on KMK HK.01.07/Menkes/1128/2022 on Hospital Accreditation Standards, if the electronic system does not support service quality assurance operations, system development is required. This study aims to design a User Interface (UI) for digitizing the completeness analysis of Medical Records (MR). The method used is design thinking with five UI principles (proximity, similarity, continuity, figure and background and common fate). Design testing using heuristic evaluation by five evaluators. The result was a UI with features of MR completeness analysis, notification, MR completeness analysis report and activity log. The three highest heuristic principles were Help and Documentation score 2.80 (major), Recognition Rather Than Recall score 2.20 (minor) and Help Users Recognize, Diagnose and Recover from Errors score 1.60 (minor). These principles have been improved according to the evaluator's recommendations. It is recommended to improve the UI to achieve a score of 0 (no problem). Keyword: Heuristic Evaluation, Medical Record Completeness Analysis, User Interface Abstrak: Kewajiban Rekam Medis Elektronik (RME) di Indonesia mendorong para Perekam Medis dan Informasi Kesehatan (PMIK) mencari solusi terbaik untuk menjaga kualitas RME. Meskipun RME telah diterapkan, sistem elektronik di Rumah Sakit (RS) belum memiliki fitur yang cukup untuk penjaminan mutu yang efektif, mengakibatkan PMIK kesulitan dalam analisis kuantitatif dan kualitatif. Berdasarkan KMK HK.01.07/Menkes/1128/2022 tentang Standar Akreditasi RS, bila sistem elektronik tidak mendukung operasional penjaminan mutu pelayanan, pengembangan sistem diperlukan. Penelitian ini bertujuan merancang User Interface (UI) digitalisasi analisis kelengkapan Rekam Medis (RM). Metode yang digunakan adalah design thinking dengan lima prinsip UI (proximity, similarity, continuity, figure and background dan common fate). Pengujian desain menggunakan evaluasi heuristik oleh lima evaluator. Hasil penelitian adalah UI dengan fitur analisis kelengkapan RM, notification, report analisis kelengkapan RM dan log aktivitas. Diperoleh tiga prinsip heuristik tertinggi yakni Help and Documentation skor 2,80 (major), Recognition Rather Than Recall skor 2,20 (minor) dan Help Users Recognize, Diagnose and Recover from Errors skor 1,60 (minor). Prinsip-prinsip tersebut telah diperbaiki sesuai rekomendasi evaluator. Disarankan untuk menyempurnakan UI guna mencapai skor 0 (no problem). Kata Kunci: Analisis Kelengkapan Rekam Medis, Evaluasi Heuristik, User Interface  
Peningkatan Kapasitas PMIK Dalam Mengolah dan Menganalisis Data Klaim INA-CBG’s untuk Meningkatkan Akurasi Kodefikasi & Dokumentasi di RSIJ Pondok Kopi Muchlis, Husni Abdul; Nurmalasari, Mieke; Qomarania, Witri Zuama; Kurniawati, Anastasia Cyntia Dewi; Iqbal, Muhammad Fuad; Maryati, Yati
Jurnal Kreativitas Pengabdian Kepada Masyarakat (PKM) Vol 9, No 2 (2026): Volume 9 Nomor 2 (2026)
Publisher : Universitas Malahayati Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33024/jkpm.v9i2.23624

Abstract

ABSTRAK Keberhasilan klaim JKN-BPJS sangat bergantung pada akurasi dokumentasi klinis dan kodefikasi diagnosis serta prosedur. RSIJ Pondok Kopi masih menghadapi kendala dalam pemanfaatan data klaim untuk evaluasi mutu dan optimalisasi nilai klaim. Kegiatan ini bertujuan meningkatkan kemampuan PMIK dalam mengolah dan menganalisis data klaim INA-CBG’s untuk mendukung akurasi kodefikasi dan dokumentasi. Program dilaksanakan melalui sosialisasi, pelatihan teknis Excel PivotTable, dan pendampingan penyusunan dashboard analisis klaim. Evaluasi menggunakan pre-test dan post-test serta observasi produk analisis. Pelatihan meningkatkan skor pengetahuan tim sebesar 22 poin, terutama pada materi MCC/CC. Tim berhasil menghasilkan dua laporan dashboard internal terkait capture rate MCC/CC dan distribusi LOS (AMLOS/GMLOS). Peningkatan kompetensi PMIK dalam analisis data klaim mampu memperbaiki akurasi kodefikasi dan mendorong pemanfaatan data klaim sebagai alat manajemen mutu dan optimalisasi nilai klaim rumah sakit. Kata Kunci: Data Klaim, Dokumentasi Klinis, INA-CBG’s, Klaim BPJS, Kodefikasi.  ABSTRACT The success of JKN–BPJS claims strongly depends on the accuracy of clinical documentation and clinical coding of diagnoses and procedures. RSIJ Pondok Kopi still faces challenges in utilizing claim data to evaluate service quality and optimize reimbursement values. This community service activity aims to improve the capacity of Health Information Management professionals (PMIK) in processing and analyzing INA-CBG’s claim data to support accurate coding and clinical documentation. The program was carried out through socialization, technical training using Excel PivotTable, and mentoring in developing analytical dashboards. Evaluation was conducted using pre-test and post-test assessments, as well as observation of the analytical products. The training improved staff knowledge by 22 points, with the highest increase in MCC/CC competence. The team successfully produced two internal dashboard reports related to MCC/CC capture rate and LOS distribution (AMLOS/GMLOS). Improving PMIK competency in claim data analysis enhances the accuracy of clinical coding and encourages the use of claim data as a tool for quality management and reimbursement optimization in hospitals. Keywords: Claim Data, Clinical Coding, Clinical Documentation, INA-CBG’s, BPJS Claim.
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