Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics

ANALYSIS OF HOSPITAL MANAGEMENT INFORMATION SYSTEM IMPLEMENTATION AT THE PLACE OF INPATIENT REGISTRATION USING THE PIECES METHOD AT AJIBARANG HOSPITAL

ABU SOFYAN AL AFGANI — 2024-04-02

Hospital Management Information System (SIMRS) is an information communication technology system that processes and integrates the entire process flow of hospital services in the form of coordination networks, reporting and administrative procedures to obtain information precisely and accurately, and is part of the Health Information System. The implementation of SIMRS at the Ajibarang Regional General Hospital (RSUD) has been implemented since 2014 in almost all units, one of which is the Inpatient Registration Place (TPPRI). Based on the results of the SIMRS analysis on TPPRI, there are still obstacles in its application, both from the aspects of Performance, Information, Economics, Control, Efficiency, and Service. This study aims to analyze SIMRS using the PIECES method. This type of research is descriptive with a qualitative approach. The results showed that there are still several problems, namely the existence of menus that have not functioned optimally, different TPPRI and TPPRJ SIMRS, inaccurate data, Human error, server down, and no warning if there is an error. SIMRS has been running according to user needs, but cannot be separated from various problems, so it is necessary to improve and develop SIMRS through researcher recommendations so that SIMRS can maintain and improve the quality of service to patients.

Implementation of the Web-Based K-Means Clustering Algorithm on Hypertension Levels in the Elderly at the Bungah District Health Center

Hermanto Hermanto — 2024-04-02

Hypertension is a systolic pressure above 140 mmHg and a diastolic pressure above 90
mmHg . Hypertension often occurs in the elderly, namely aged 45 to 90 years and over. This research
was carried out at the community health center in Bungah sub - district with the aim that so that patients
receive appropriate treatment, a web-based system is needed to group hypertension data into several
classes ( clusters ), so that degenerative diseases caused by hypertension can be minimized . The
method used in data grouping is the K-Means Clustering method . Clustering is one of the fields of
recognition science that is created so that a system can carry out grouping. In this study, 100
hypertension data were grouped into 4 clusters . The hypertension data used consists of two attributes,
namely systole and diastole . The working mechanism is to normalize the data first, then the system
groups the data into groups that have the same characteristics. Next, the system will display the results
of the clustering process which consists of four (4) clusters , namely cluster 1 Isolated Systolic
Hypertension, cluster 2 Grade 1 (mild hypertension), cluster 3 Grade 2 (moderate hypertension), and
cluster 4 Grade 3 (high hypertension). The data used for clustering is 100 data from blood pressure
examinations of patients at the Community Health Center using a sphygmomanometer. The results of
the last iteration of 100 hypertension data in the system were used as parameters for calculating the
level of effectiveness, by comparing the data from the clustering test results to the data from the
diagnosis a which produced an effectiveness value of 80%

Development of a Diabetes Mellitus Monitoring Information System in Health Monitoring and Health Decision Making

Agnes Lia Renata — 2024-05-10

Individuals with diabetes mellitus more likely to experience acute and chronic health complications. Information systems in the health sector can be utilized in managing health information as an effort to monitor risk factors for oral manifestations. The collection of information shows that there is no software that is used as health monitoring for people with diabetes mellitus. So that the SIP DM-DENT Monitoring was developed. This research aims to produce SIP DM-DENT Monitoring for people with diabetes mellitus that is feasible in health monitoring and helps make decisions for managing their health. This research uses the R&D method to develop a new product output. The application development using RAD method with DFD logic model to develop information systems faster with better product quality. Sampling using purposive sampling technique obtained 35 samples. Data from the model test results were tested using interclass correlation coefficient and descriptive analysis. The results of this software feasibility assessment amounted to 85.76 and p-value of 0.00 <0.05 indicates feasible. The assessment of the system shows the average respondent agrees that the system provides information and is easy to use. SIP DM-DENT Monitoring is feasible and effective in monitoring health in people with diabetes mellitus, especially in diabetes mellitus control and dental health and is able to provide information that can facilitate users in making health decisions. In addition, users can obtain their health information easily because there is a complete history of their health check results and display health education materials that can increase their knowledge

A Hybrid Approach for Optimal Multi-Class Classification of Neglected Tropical Skin Diseases using Multi-Channel HOG Features

Nyatte Steyve — 2024-05-10

Problem statemen: According to the WHO, the eradication of neglected tropical skin diseases is possible by 2030 if an early test to distinguish these diseases is available. For us, the analysis of the skin in the plaque or nodule phase could be an avenue to explore. Unfortunately, the most common and disabling diseases are often of bacterial origin and therefore have almost the same development and characteristics in their initial phase.Purpose of the study: Our goal is, therefore, to propose an efficient and simple method to provide an optimal dataset and an optimized multi-class classification method for early diagnosis.Method: The method consists of extracting the optimal Histogram of Oriented Gradient (HOG) features by browsing the images through different basic cell sizes (CS) of the Buruli Ulcer (BU), Leprosy, and Cutaneous Leishmaniasis skin lesion images. Then we obtain another dataset made of the averages of the different databases from these cell sizes. In order to solve the multi-class classification problem of the Support Vector Machine (SVM), we introduced an Error Correcting Output Code (ECOC) framework optimized by a hybrid metaheuristic algorithm to optimize the diagnosis of several diseases simultaneously.Result : A preliminary study of the different Cell Size 2*2, 4*4, 8*8, 16*16 allowed us to have 5 training databases, one of which is extracted from the other four by computing the averages of the HOG features of CS 2*2, CS4*4, CS8*8, CS16*16. This last multichannel database is the one that obtained the best results after the implementation of the hybrid whale optimization algorithm and shark smell optimization algorithm with Error Correcting Code (WOA-SSO-ECOC-SVM) on Matlab. We obtained 89% accuracy on the multi-channel dataset, 72% for CS4*4, 72% for CS8*8, and 72% for CS16*16.Conclusion: This study shows that it is possible to achieve an optimized multi-class skin NTD classification with good accuracy by optimally selecting the appropriate HOG characteristics.Implication: This result makes it possible to consider the development of mobile applications that allow, just by taking a picture of the lesion, to identify the diseases. This equipment could be used by front-line medical staff and community health workers. This could solve the effects of isolation and poverty in the fight against these diseases.

Diabetes Detection Using Extreme Gradient Boosting (XGBoost) with Hyperparameter Tuning

Devi Aprilya Dinathi — 2024-05-10

Diabetes is a metabolic disorder caused by problems with insulin production in the body. Diabetes is one of the deadliest diseases worldwide, especially in Indonesia. Diabetes can cause various serious complications to the sufferers and can lead to death. With current technological advances, machine learning algorithms can identify diabetes using available data for analysis. One of the machine learning methods that can be applied is Extreme Gradient Boosting (XGBoost). This study aims to find the best classification performance on diabetes datasets using the XGBoost method. The dataset used consists of 768 rows and 9 columns, with target values of 0 and 1. In this study, resampling is applied to overcome data imbalance using SMOTE and optimize hyperparameters using GridSearchCV and RandomSearchCV. Model evaluation is done using confusion matrix and various metrics such as accuracy, precision, recall, and f1-score. This research conducted several three test scenarios. The first test was hyperparameter optimization using GridSearchCV. The second test was hyperparameter optimization using RandomSearchCV. In the third test by applying data resampling, the XGBoost method achieved the highest accuracy of 82% with GridSearchCV hyperparameter optimization.

PID-based Flow Rate Stability Analysis on Syringe Pump Equipped with Bolus

Ayu Intan Nawang Wulan — 2024-05-26

Syringe Pump is a medical device used to deliver a concentrated liquid which is injected into the patient's body in a certain amount through a vein. For patients who need extra and intensive treatment, we need a tool that can control the dose, volume of drug use and flow rate. Therefore the authors decided to conduct research with the title PID-based Flow Rate Stability Analysis on Syringe Pumps equipped with Bolus. This tool uses the L298N motor driver and Optocoupler sensor to detect motor rotation whose pulses from the sensor will be feedback for PID control. In this study the researchers used two data collection settings, namely a flow rate of 10 ml/hour and 20 ml/hour with a volume of 10 ml and 20 ml. Results will be displayed on the Nextion TFT LCD in the form of achievement scores and the PC will use the Delphi application to display the PID graph.

Analysis of the Oxygen Fraction’s Stability and Accuracy in the Design of the HFNC Tool

Fahim Umar Djawas — 2024-05-26

In early 2020, the world was shocked by an outbreak of a new pneumonia that started in Wuhan, Hubei Province, which then spread rapidly to more than 190 countries and territories. This outbreak was named coronavirus disease 2019 (COVID-19) caused by Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2). The primary strategy for COVID-19 patients is supportive care, including oxygen therapy for hypoxemic patients, where high-flow nasal passages (HFNC) have been reported to be effective in improving oxygenation. The purpose of this study is to ensure that the readings of the HFNC device are accurate and stable so that it is safe and comfortable when used on patients. The development of the equipment that will be used by the author adds graphs to the TFTLCD to help monitor stable data in real time so that officers can monitor the flow and fraction of oxygen in the device to be stable. This study uses Arduino nano while the sensor used is the KE-25 sensor, then the results are displayed on the Nextion TFT LCD. While the comparison tool used is a gas flow analyzer (IMT Medical). In the testing phase, the setting value of the HFNC tool that appears on the TFT LCD is compared with a gas flow analyzer with a measurement range of 50% to 100% 5 times at each point. Based on measurements on the gas flow analyzer, the HFNC module has an average error (error (%)) of 2.31%. Average uncertainty (Ua) 0.07. The conclusion from these results is that the calibrator module has a relative error (error value) that is still within the allowable tolerance limit, which is ±10%, the tool is precise because of the small uncertainty and good stability of the stability test carried out within a certain time.

Analysis of Lost Data on Website-Based ECG Lead Data Sending and Receiving (Lead V1, V2, V3)

Wildan Darajat — 2024-05-26

Coronary heart disease is a major health problem in almost every country in the world and is responsible for around 30 percent of all deaths worldwide. Heart disease can be detected early using a medical device called electrocardiography (ECG). ECG is very effective in recording the electrical activity of the human heart. The tool that functions to record the electrical signals of the heart is an electrocardiograph. The purpose of making this tool is to find out if there is lost ECG lead data before and after delivery and the process of comparing the signal on the web with the application. This study uses the Arduino Mega system for data processing and uses the Website and the Android Studio application to display data. In this study, we examined signal capture and signal monitoring for 5 times with a time span of 5 minutes per data collection using Phantom at BPM settings of 60, 80, and 100. With this research, the ECG monitoring system with signal display is expected to lead to further development. carry on.

Analysis of Temperature Stability Distribution in Waterbath Using Fuzzy Logic

royan setia nurhidayat — 2024-05-26

Waterbath is a tool used to create a constant temperature. This tool is used for incubation in microbiological analysis. The temperature is maintained according to the desired setting. The heating element is controlled by the heater driver. This module is made using Arduino Uno R3 as a minimum system and time controller, using a Fuzzy Logic controller as a temperature controller, and using a DS18B20 sensor as a temperature sensor. The processor is an Arduino UNO, and is displayed on a 20x4 Character LCD. The temperature selection is 30 ˚C, 35 ˚C, 37 ˚C, 40 ˚C, 45 ˚C, 50 ˚C, 55 ˚C, 60 ˚C. This study used a pre-experimental method with after only design research. The measurement results were carried out by comparing the module with a standard measuring instrument which produced the largest % error at a temperature setting of 30 ˚C which was 1.13%, this was related to the limit between the water temperature and the temperature setting which was too short which affected the DS18B20 temperature sensor reader which it takes time, to get a stable temperature reading. The minimum % error lies at 60 ˚C, because it takes a long time to reach the temperature setting so that the DS18B20 sensor reading is stable from the setting temperature, which is 0.26%. The % error timer value is 5.4% where the magnitude of the error is influenced by the number of DS18B20 sensors used and the delay of the microcontroller. Based on the results obtained, the temperature control error value is still below the tolerance limit because the error value is less than 3%.

Temperature and Humidity Control System Using Fuzzy Logic In Baby Incubator (Humidity Control)

Anisia Yunita Maulani Argumery — 2024-05-26

Baby incubators help to monitor different aspects of the baby's environment, which are used to make the baby's condition similar to the ideal conditions inside the mother's womb. The normal temperature limit in the baby incubator is maintained around 33°C to 35°C. In addition, to help stabilize the baby's body temperature, humidity also needs to be maintained, which is relatively 40% to 60%. Fuzzy logic control also called Fuzzy Inference System / FIS is a control system that uses the concept of fuzzy set theory. When FIS is used as a controller, the required output is sharp (firm). Fuzzy logic control consists of fuzzification, database, rule base, and defuzzification. This incubator planning uses a DHT11 sensor as a humidity sensor and uses a steeper motor as an airflow open-close to maintain ideal humidity which is processed using a Mega 2560 microcontroller using fuzzy logic control. so it will generate a value and be displayed using Nextion TFT. The test was carried out by comparing the module with a standard measuring instrument, namely Incuanalizer. In this study, when setting the temperature 32⁰C had the highest humidity error of 7.8%, when setting the temperature 35⁰C had the highest humidity error of 2.12%, while when setting the temperature 32⁰C had the highest humidity error of 1.81%.

Development and Evaluation of an Arduino-based Photodiode Infrared Sensor Module for Improving Flow Rate Measurement Accuracy in Infusion Pumps

Alaika Azka — 2024-05-26

Precise quantification of flow rates in infusion pumps is essential for the accurate delivery of fluids to patients. Nevertheless, current techniques, like infrared photodiode sensors, may display notable measurement flaws, especially when dealing with larger flow rates, which could be beyond the specified tolerance limits. The objective of this study is to enhance the precision of flow rate measurements in infusion pumps, thereby improving patient safety and ensuring accurate fluid administration. The study suggests a new design for measuring the flow rate of an infusion pump. This design includes a photodiode infrared sensor and an Arduino microcontroller. The module being suggested employs a photodiode infrared sensor to detect fluid droplets. The output of the sensor is used as a reference input for an Arduino microcontroller. The microcontroller utilizes the droplet count and duration to compute the flow rate, enabling real-time monitoring capabilities. A calibration and performance evaluation of an infusion pump and a syringe pump was conducted using an Infusion Device Analyzer, following the ECRI 416-0595 criteria. Data measurements were stored on an SD card for analysis. An evaluation was conducted to determine the precision of the infrared photodiode sensor, and subsequently, a novel module design was created and subjected to testing. The measurements obtained from the infusion set showed greater levels of uncertainty in comparison to those obtained from the syringe pump. The infrared photodiode sensor exhibited an accuracy deviation of ±5 ml/hour, with a notable divergence of ±20 ml/hour for flow rates over 60 ml/hour up to 250 ml/hour, which may surpass the tolerance limits of the syringe pump. The suggested module design, which integrates a photodiode infrared sensor and an Arduino microcontroller, can enhance the precision of flow rate measurements in infusion pumps. Precise and reliable flow rate measurements in infusion pumps are crucial for ensuring patient safety and accurate administration of fluids. The suggested module has the potential to improve the precision of measurements, leading to improved patient care and a decrease in the likelihood of negative outcomes related to incorrect fluid administration.