Journal of Applied Informatics and Technology

Warfarin Care: Warfarin Management System for Older Adults

Mon, 23 Jun 2025 00:00:00 +0700

Warfarin Care emerges as a transformative solution in digital healthcare for the elderly reliant on warfarin. Addressing specific needs, Warfarin Care serves as a communication and information exchange among medical personnel, elderly patients, and family members or caregivers. With a user-friendly interface, rigorous content evaluation, and a shared database architecture, Warfarin Care endeavors to mitigate medication errors and augment overall treatment outcomes. Through the integration of risk assessment, medication history, and warfarin knowledge, medication reminders, and educational tools, the application fosters a deeper understanding of proper medication behavior. The research is based on the clinical trial, in which 60 cases of elderly patients and family members, 30 elderly patients, and 30 family members or caregivers were selected as the sample receiving treatment in the outpatient department of Sakonnakhon Hospital. The study from the clinical trial revealed that the majority of elderly participants fall within the 60–69 age group, predominantly women and married. The data reveals high satisfaction among both elderly users and caregivers, underscoring Warfarin Care's positive impact on enhancing knowledge, confidence, and support for proper medication adherence with user-friendly communication. Users agreed that the use and suitability of the Warfarin Care application had an average of 4.57 and a S.D. of 0.57 from elderly users and an average of 4.67 and a S.D. of 0.61 from caregivers or family members. The robust data analysis utilizing mean and standard deviation values underscores the application's effectiveness.

Measuring Neck Abnormalities for Preliminary Assessment of Neck Pain Disease using Virtual Reality

Mon, 23 Jun 2025 00:00:00 +0700

Neck pain is an increasingly prevalent issue in the general population, leading to a growing incidence of chronic cases and potential future health risks. The economic impact is significant, as individuals with neck pain often cease working due to discomfort. Traditional assessments of treatment effectiveness involve the measurement of neck deformity and movement, typically requiring expensive and limited Cervical Range of Motion (CROM) equipment found primarily in large hospitals. The challenges posed by the COVID-19 outbreak further hinder access to such evaluations. This study proposes the development of a Virtual Reality (VR) application designed to measure neck movement range, enabling users to self-administer assessments under the guidance of the VR application. The VR application development process commences with storyboard creation, all components were designed and creates models object using Blender. The development of VR applications for angle measurement follows the storyboard, was executed using the Unity program. Prioritizing user satisfaction, the application capitalizes on the proven accuracy and reliability of VR devices. Usability experimental focused on user independence, with participants autonomously following instructional videos. Noteworthy user satisfaction, reflected in an average score of 4.36 ± 0.52, underscores the potential of the VR application in addressing neck pain symptoms. The study emphasizes meticulous design considerations, including character and scene elements, aiming to enhance user engagement and immersion in the virtual environment. Users demonstrated focused attention during the measurement process, unaffected by external factors.

An In-House Time Tracking Application Development with a Low-To-No-Code Platform

Sorn Tanharaphan, Thanabadee Rodvanich, Yatawee Aupasao, Natsuda Kaothanthong — Mon, 23 Jun 2025 00:00:00 +0700

We demonstrate a procedure exhaustively to develop an in-house application without requiring database establishment and technician using a low-to-no-code (LCNC) platform that aligns with the organization’s business case for tracking working time and leave request of employees. We developed the application using Google AppSheet and Google Sheets for data storage. The proposed application has three main functions to accurately collect a daily clock-in, clock-out, retrieve the total number of working hours in the current month, and deal with leave requests that align with the organization’s regulations. Furthermore, there are three functions for an administrative employee manage the staff’s information, generate a monthly work report, and perform leave request approvement. The application has been tested at the Artificial Intelligence Association Thailand (AIAT), where time tracking and leave request were previously managed with paper-based. The usability test shows that the staff takes on average less than 1 minute to perform a daily clock-in and clock-out, less than 2 minutes to complete a leave request as well as cancel the submitted request. The learnability test shows that the users take less than 1 minute to complete the daily working timestamp and send leave requests.

Leveraging PyThaiNLP for Sentiment Analysis of Thai Online Text: A Comparative Study of Logistic Regression and Support Vector Machine

Mon, 23 Jun 2025 00:00:00 +0700

The objective of this study is to compare the performance of sentiment analysis models for Thai online text using the existing PyThaiNLP libraries. For extracting text from online sources to create a dataset, the text was manually categorized into positive, neutral, and negative sentiments. Data preprocessing involved removing punctuation marks, tokenizing, removing non-Thai characters, and Bag of Words creation. The data was then divided into training and testing sets to build models using three algorithms: logistic regression, logistic regression with stochastic gradient descent (SGD), and support vector machine (SVM). Upon comparison, the logistic regression model was found to perform the best – achieving accuracy of 80.73% with a 90:10 train-test split using the newmm word tokenization tool and the augmented dictionary. The accuracy for analyzing positive sentiment was 81.10%, for neutral sentiment, 80.16%, and for negative sentiment, 80.97%.