Ditemukan 28948 dokumen yang sesuai dengan query :: Simpan CSV
Latar Belakang: Fraud dalam klaim Jaminan Kesehatan Nasional (JKN), khususnya dalam bentuk upcoding diagnosis penyakit kardiovaskular, merupakan tantangan serius yang dapat mengancam keberlanjutan sistem jaminan kesehatan di Indonesia. Penyakit kardiovaskular, sebagai penyebab beban biaya tertinggi dalam layanan rawat inap, rentan terhadap praktik kecurangan yang sulit dideteksi melalui metode konvensional. Oleh karena itu, diperlukan pendekatan berbasis data dan teknologi untuk mendeteksi potensi fraud secara lebih efisien. Metode: Penelitian ini menggunakan pendekatan kuantitatif eksploratif dengan metode supervised machine learning. Data klaim rawat inap penyakit kardiovaskular tahun 2022–2024 dianalisis berdasarkan beberapa variabel yaitu lama hari rawat, lama rawat di ICU, waktu penggunaan ventilator, jumlah diagnosis sekunder, jumlah prosedur, dan biaya RS. Proses mencakup cleansing, encoding, pseudo-labeling, feature selection, serta pelatihan model menggunakan beberapa algoritma supervised, seperti Random Forest, Tree, Gradient Boosting, Neural Network, Naïve Bayes, Logistic Regression, Support Vector Machine (SVM), dan kNN. Evaluasi kinerja model dilakukan dengan menggunakan metrik akurasi, precision, recall, F1-score, dan AUC. Hasil: Hasil penelitian menunjukkan bahwa algoritma Random Forest menghasilkan performa terbaik dalam mendeteksi potensi fraud pada sebagian besar kategori diagnosis dan kelas rumah sakit. Nilai akurasi dan AUC yang dihasilkan berada dalam kategori baik hingga sangat baik. Selain itu, analisis pola klaim menunjukkan adanya perbedaan distribusi biaya dan indikator klinis antara klaim normal dan klaim yang terindikasi anomali, mendukung keberadaan pola upcoding Kesimpulan: Model machine learning, khususnya Random Forest, terbukti efektif dalam mendeteksi potensi fraud upcoding diagnosis penyakit kardiovaskular pada klaim JKN. Penerapan sistem berbasis algoritma ini berpotensi menjadi alat bantu auditor dalam pengawasan klaim yang lebih akurat dan efisien. Hasil penelitian ini memberikan dasar bagi pengembangan sistem deteksi fraud terintegrasi di masa depan guna meningkatkan akuntabilitas dan efisiensi pembiayaan kesehatan.
Background: Fraud in the National Health Insurance (JKN) claims, particularly in the form of upcoding for cardiovascular disease diagnoses, poses a serious threat to the sustainability of Indonesia’s health financing system. As the leading contributor to inpatient service expenditures, cardiovascular disease claims are highly susceptible to fraudulent practices that are difficult to detect using conventional methods. Therefore, a data-driven and technology-based approach is essential for more efficient fraud detection. Methods: This study employed a quantitative exploratory approach using supervised machine learning methods. The dataset consisted of inpatient cardiovascular disease claims from 2022 to 2024. The analysis involved data cleansing, encoding, pseudo-labeling, feature selection, and model training using several classification algorithms such as Random Forest, XGBoost, and Logistic Regression. Model performance was evaluated using metrics including accuracy, precision, recall, F1-score, and AUC. Results: The results demonstrated that the Random Forest algorithm achieved the highest performance in detecting potential fraud across most diagnosis categories and hospital classes. The accuracy and AUC values indicated good to excellent classification performance. Furthermore, the claim pattern analysis revealed distinct differences in cost and clinical indicators between normal and anomaly-labeled claims, supporting the presence of potential upcoding. Conclusion: Machine learning models, particularly Random Forest, proved to be effective in detecting potential upcoding fraud in cardiovascular disease claims within the JKN program. The implementation of algorithm-based fraud detection systems can serve as a decision-support tool for auditors, enabling more accurate and efficient claim monitoring. This study provides a foundation for the future development of integrated fraud detection systems to enhance accountability and efficiency in national health financing.
Mental health is an important component in the realization of the quality of life ofsociety as a whole. The prevention of mental health disorders can be earlydetection in primary health care facilities. However, not all primary health carefacilities are able to provide mental health services. The rapid development ofInternet technology today can be a solution in early detection services usinginternet-based media website. This study aims to develop a prototype mentalhealth early detection that can be used for detection of mental health communityand media promotion. Researchers identify determinants mental health (man,material, method, machine and market) to determine the needs of system by usingqualitative research methods. The prototype system was developed by SystemDevelopment Life Cycle (SDLC) which the stages are planning, analysis, design,and implementation of system. This research resulted a prototype website thatprovides information level overview of mental disorder of visitors website as asimple portrait of mental health community problems, media information andeducation. The prototype can be developed with the addition of online chatfeatures as well as mapping ODMK (People With Mental Health Problems) area-based to support access community mental health services.Keywords: development, website, early detection, mental health
Permasalahan kesehatan masyarakat terkait pelaksanaan kegiatan deteksi tumbuh kembang anak di Kabupaten Nunukan adalah rendahnya jumlah anak yang dideteksi tumbuh kembang. Jumlah anak yang dideteksi tumbuh kembang pada tahun 2007 sebesar 23,5% (target pada standart pelayanan minimal = 90%). Rendahnya cakupan anak yang di deteksi menyebabkan beberapa anak yang tidak datang lepas dari pengamatan, sehingga perubahan tumbuh kembang tidak bisa terdeteksi secara berkala. Kejadian tersebut menyebabkan kejadian gangguan tumbuh kembang tidak bisa diketahui secara cepat dan akurat. Akibatnya anak terlambat untuk dirujuk ke tempat pelayanan kesehatan lanjutan karena kejadiannya lambat diketahui. Sistem informasi pemantauan gangguan tumbuh kembang anak yang sedang berjalan belum bisa menjawab kebutuhan manajemen program, sehingga penelitian ini bertujuan agar tersusun model sistem pemantauan yang efektif dan efisien dengan prototipe program dan basis data sehingga dapat mendukung manajemen program. Prototipe diharapkan dapat menghasilkan laporan tepat waktu, cakupan indikator tumbuh kembang anak yang lebih valid, daftar kasus yang terinci, jumlah anak yang melakukan deteksi secara rutin, daftar anak yang harus dideteksi dan informasi keberadaan tenaga terlatih di posyandu, TK dan puskesmas. Rancangan penelitian ini menggunakan metodologi pengembangan sistem dengan metode incremental yaitu menggabungkan elemen-elemen dalam model berurutan linear dengan filosofi iteratif dari metode prototipe. Hasil penelitian menunjukkan bahwa pelaksanaan pemantauan gangguan tumbuh kembang anak di Kabupaten Nunukan belum berjalan sesuai pedoman. Tenaga pelaksana belum melibatkan kader dan guru TK, keluaran sistem belum menghasilkan informasi kasus baru atau lama, jumlah anak yang dideteksi secara rutin dan persen puskesmas, posyandu dan TK dengan tenaga terlatih. Kesimpulan penelitian ini menunjukkan bahwa 1)Rendahnya cakupan deteksi disebabkan karena belum ada keterlibatan masyarakat dan lintas sektor terkait dalam kegiatan ini. 2) Sistem informasi yang dikembangkan menggunakan visual programming dengan database dari SQL, agar dapat ditanam di website. 3)Sistem baru dapat menghasilkan indikator input, proses dan output yang lebih valid dan lebih cepat. 4) Menghasilkan daftar sasaran yang harus dideteksi tumbuh kembang secara rinci sehingga permasalahan pemantauan gangguan tumbuh kembang anak di Kabupaten Nunukan dapat terselesaikan.
It has already known that the problems of publich health about development and growth monitoring abnormally children program in Nunukan Regency on 2007th is the descent number of the children who detected development and growth. The number of the children who detected development and growth on 2007th is 23,5% (minimum standart = 90%). The descent of the children who detected coverage to make some children who don?t come to detection and stimulation place out of evaluation, so that development and growth change can?t detection regularly. It has to make the children development and growth abnormal can not known on time and accurately. The impact it, the children late revered to the publich health serveice, because it has to late to known. The information system development to monitor development and growth abnormally children in Nunukan Regency can not given yet manajemen program demand., so that this research goal is to create effective and efficient monitoring system with prototype and basis data so that be able to support manajemen program. Prototype be hoped can to produce routine and incidental report, development and growth indicator program more valid, listing case detail, number of the children who detected routinely, the children listing who have to detected and man power. This research design to develop system with incremental and iterative model to add elemens in the linear structure. Result of this research known that monitor abnormal development and growth children in Nunukan Regency haven?t been doing like the guidens program yet. Kader posyandu and kindergarden teacher not joint this program yet, output system not result 1) old and new case information 2) number of children to detected routinely and 3) persen posyandu, kindergarden and puskesmas with man power have trained. This research conclussion to show that 1) Descent of children detected coverage, because kader and another departemet not joined this program yet 2) The information system development with visual programming and SQL database in order to upload website. 3) New system able to produce indicator input, proses and output more valid and fastly. 4) Produce children listing who have to detected development and growth detail so that the problem of abnormal development and growth children in Nunukan Regency can to solved.
In the National Health System (SKN), health workers are central to health promotion.Producing, recruiting and sustaining health are still the main challenges facing the world.Lack of Human Resources for Health (HRH) is not only happening in Indonesia, mostcountries in the world experience two major demographic factors related to this problem.First, higher life expectancy, resulting in the number of patients requiring better healthcare. Secondly, it is a large increase in the population that has resulted in the need forincreased health human resources (WHO, 2006). SKN point 288 states: "Health HRPlanning is basically fact-based through improvement of Health Information System (SI-SDMK)" (Perpres 72/2012).PPSDM Kesehatan Agency has developed 3 (three) Data Instruments to support SI-SDMK in Excel-Based Applications, Desktop-Based Applications, and Web-BasedApplications to facilitate the tasks of SDMK managers in all districts / cities throughoutIndonesia. This SI-SDMK application can inform the number of functional position ofhealth data either level of work unit or province, information obtained either in the formof report or in the form of graph and map. However, when looking at data coverage thatSI-SDMK get for Puskesmas and Hospitals for individual data SDMK year 2016 forPuskesmas 84% and 2017 (until October) 92%. While for hospitals in 2016 36% and 2017(until October) 41% (SI-SDMK, BPPSDMK).The results of a brief interview on the preliminary study at the Center for Data andInformation of PPSDM Agency for Health and DKI Jakarta Provincial Health Office andPuskesmas, it is known that data collection and recording of individual data working infashankes so far is still done manually in Microsoft Excel. So that the SDMK datamanagers at the fashankes level need to recapitulate the form of individual data that hasbeen written. This study aims to develop prototype SI-SDMK based on Android withright to health personnel in Fasyankes directly to register, check the status of individualdata, as well as to update individual data if there are inaccurate / incomplete individualdata in accordance with the actual situation by attaching supporting documents.Keyword:Information System, Prototype, SI-SDMK.