Winarti ., Wahyu Fikri Zeni Putra, Nurus Danti Maghfirohc, Andin Rachma Nadila, Juliah ., Mukhammad Amar Fizaruddin, Bagus Hadi Sanjaya

Sistem Pakar Berbasis Website Untuk Diagnosis Stunting Balita Dengan metode Forward Chaining

Introduction

Sistem pakar berbasis website untuk diagnosis stunting balita dengan metode forward chaining. Sistem pakar web diagnosis stunting balita dengan metode forward chaining. Deteksi dini, tingkatkan kesadaran, dan bantu orang tua intervensi cepat. Akurasi tinggi.

Abstract

Artificial intelligence is the computer science sector which facilitates computers in performing tasks traditionally performed by humans. One of the interesting applications of ai is a system of experts, designed to mimic an expert's thinking and knowledge. In this study, a web-based expert system was developed to diagnose stunted potential in children of an early age by employing advanced methodologies of chaining. The purpose of this system is to increase public awareness and help parents recognize early stunting signs, thus enabling timely intervention. The system is developed with a cascading approach to ensure that each stage of development is implemented by a planned approach. Test results show that the system has a high diagnostic accuracy level, so it can be relied upon as an aid in a stunted risk assessment.  

Review

This paper presents a timely and relevant application of artificial intelligence in public health, specifically focusing on the early diagnosis of stunting in young children. The development of a web-based expert system utilizing the Forward Chaining method to identify potential stunting is a commendable effort to address a critical health issue, particularly in regions where access to specialized medical advice might be limited. The stated objective of increasing public awareness and facilitating early intervention through this system highlights its significant potential for improving child health outcomes and supporting parents. From a methodological standpoint, the choice of a web-based platform for an expert system is a practical decision, enhancing accessibility for a broader audience. The employment of the Forward Chaining inference mechanism is a standard yet effective approach for diagnostic systems, allowing for logical progression from observed symptoms to a potential diagnosis. The abstract also mentions a "cascading approach" for development, implying a structured, sequential process, which is good practice. The most crucial claim is the "high diagnostic accuracy level" demonstrated in test results, suggesting the system's potential robustness and reliability as a preliminary assessment tool for stunting risk. While the abstract provides a promising overview, a comprehensive review would benefit from more granular details regarding the system's validation and implementation. Specifically, information on the dataset used for testing, the number of cases evaluated, the precise metrics defining "high diagnostic accuracy" (e.g., sensitivity, specificity, precision, recall), and the extent of medical expert involvement in validating the knowledge base and diagnostic outcomes would significantly strengthen the claims. Furthermore, insights into user acceptance, scalability, and the practical deployment challenges or successes would be valuable for future research. Despite these points for further elaboration, the work represents a positive step towards leveraging AI for improved public health interventions and merits detailed reporting.

Full Text

Comments

You need to be logged in to post a comment.