Rule-based ai system for early paediatric diabetes diagnosis using backward chaining and certainty factors
Diabetes mellitus (DM) is a major health threat that can cause complications if early diagnosis and treatment are not carried out, 1.3 million children aged 6–18 or about 1.1% of the population of children in Indonesia are affected by this disease. Furthermore, the incidence of type 1 diabetes melli...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | BIO Web of Conferences |
| Online Access: | https://www.bio-conferences.org/articles/bioconf/pdf/2025/03/bioconf_ichbs2025_01020.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Diabetes mellitus (DM) is a major health threat that can cause complications if early diagnosis and treatment are not carried out, 1.3 million children aged 6–18 or about 1.1% of the population of children in Indonesia are affected by this disease. Furthermore, the incidence of type 1 diabetes mellitus in children is on the rise in Indonesia but we do not have an accurate figure due to a high misdiagnosis rate. The aim of this study was to develop an artificial intelligence (AI)-based expert system for the early diagnosis of paediatric Type 1 DM using backward chaining and certainty factor methods. Backward Chaining is a reasoning method that starts with a hypothesis, then there is Certainty Factor method which is would make it become certainty by calculated the value from each symptom. Based on the National Diabetes Audit 2017-2021, the system processes clinical data such as HbA1c levels and symptoms. Testing shows accurate diagnoses about 79.2% for 10 validation tests with patients, aiding healthcare in underresourced areas. Future work includes expanding the dataset and integrating machine learning for improved adaptability. |
|---|---|
| ISSN: | 2117-4458 |