Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Indonesian Journal of Health Information Management (IJHIM) JIKTEKS : Jurnal Ilmu Komputer dan Teknologi Informasi
Reza Widiantoro
STIKes Mitra Husada Karanganyar
Computer Science & IT Health Professions Public Health

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Tinjauan Keakuratan Kode External Cause Diagnosis Cedera Kepala Berdasarkan ICD-10 Pada Rekam Medis Pasien Rawat Inap Di RSUP Dr. Soeradji Tirtonegoro Reza Widiantoro; Astri Sri Wariyanti; Ninawati
Indonesian Journal of Health Information Management Vol. 3 No. 1 (2023)
Publisher : Sekolah Tinggi Ilmu Kesehatan Mitra Husada Karanganyar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54877/ijhim.v3i1.97

Abstract

A preliminary survey was conducted, showing that 10 out of 10 external code medical records for the diagnosis of head injuries were inaccurate. The purpose of this study was to determine the accuracy of the external cause code for diagnosing head injuries based on the ICD-10 in the medical records of inpatients at dr. Soeradji Tirtonegoro. The research type was descriptive, with a retrospective approach. The study was conducted in the filing room. Time in May 2018. The total population of medical records for inpatients diagnosed with head injuries was 175 medical records. The sample size is 44 documents, with a systematic sampling technique. The instruments used were checklists, questionnaires, and observation guidelines. How to collect data from unstructured interviews and observation. Data analysis is descriptive in nature. The results of accuracy of the code external causes a diagnosis of head injury from 44 medical record documents 100% inaccurate code. Inaccuracy is incorrect code, there are 17 cases (39%) and there is incorect 5 categories code as many as 27 cases (61%). The conclusion is that inaccuracies occur because the officer has not carried out the inclusion and exclusion guidelines on the selected code, or the bottom of a chapter, block, category, or sub category in determining the selected code, directly coding without looking at the ICD when getting external cause information that often appear, and officers do not carry out coding up to 5 character digits because the standard for coding in hospitals is 15 minutes and officers still have to do an analysis of the completeness of medical records, code for claims, code in medical records, and still input into a computer.
Tinjauan Keakuratan Kode External Cause Diagnosis Cedera Kepala Berdasarkan ICD-10 Pada Rekam Medis Pasien Rawat Inap Di RSUP Dr. Soeradji Tirtonegoro Reza Widiantoro; Astri Sri Wariyanti; Ninawati
Indonesian Journal of Health Information Management Vol. 3 No. 1 (2023)
Publisher : Sekolah Tinggi Ilmu Kesehatan Mitra Husada Karanganyar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54877/ijhim.v3i1.97

Abstract

A preliminary survey was conducted, showing that 10 out of 10 external code medical records for the diagnosis of head injuries were inaccurate. The purpose of this study was to determine the accuracy of the external cause code for diagnosing head injuries based on the ICD-10 in the medical records of inpatients at dr. Soeradji Tirtonegoro. The research type was descriptive, with a retrospective approach. The study was conducted in the filing room. Time in May 2018. The total population of medical records for inpatients diagnosed with head injuries was 175 medical records. The sample size is 44 documents, with a systematic sampling technique. The instruments used were checklists, questionnaires, and observation guidelines. How to collect data from unstructured interviews and observation. Data analysis is descriptive in nature. The results of accuracy of the code external causes a diagnosis of head injury from 44 medical record documents 100% inaccurate code. Inaccuracy is incorrect code, there are 17 cases (39%) and there is incorect 5 categories code as many as 27 cases (61%). The conclusion is that inaccuracies occur because the officer has not carried out the inclusion and exclusion guidelines on the selected code, or the bottom of a chapter, block, category, or sub category in determining the selected code, directly coding without looking at the ICD when getting external cause information that often appear, and officers do not carry out coding up to 5 character digits because the standard for coding in hospitals is 15 minutes and officers still have to do an analysis of the completeness of medical records, code for claims, code in medical records, and still input into a computer.
Perancangan Basis Data Knowledge Base Berbasis Relasional untuk Mendukung AI Agent pada Sistem Layanan Informasi Rohmadi; Reza Widiantoro
JIKTEKS : Jurnal Ilmu Komputer dan Teknologi Informasi Vol. 4 No. 03 (2026): Agustus
Publisher : Faatuatua Media Karya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70404/jikteks.v4i03.706

Abstract

The rapid advancement of Artificial Intelligence (AI), particularly Large Language Models (LLMs), has accelerated the adoption of AI Agents in various information service systems. However, the quality of responses generated by AI Agents depends not only on language models but also on the structure and management of the underlying knowledge source. Most previous studies have focused on AI Agent implementation and API integration, while limited attention has been given to the design of relational knowledge base databases. This study aims to design a relational knowledge base database that supports AI Agents in information service systems. The research adopts the Database Life Cycle (DBLC) methodology, including data requirement analysis, entity identification, conceptual database design, normalization, logical database design, physical database implementation, and database testing. The proposed database consists of several core entities, including information categories, knowledge repository, metadata, users, administrators, conversation history, user feedback, and AI processing logs. The resulting schema satisfies Third Normal Form (3NF), reducing data redundancy while improving consistency, scalability, and maintainability. Furthermore, the proposed database supports AI Agent integration by providing structured retrieval mechanisms for contextual information before being processed by Large Language Models. The proposed relational database architecture contributes as a scalable foundation for developing AI Agent-based information service systems across various application domains.
Co-Authors Astri Sri Wariyanti Ninawati Rohmadi