Design of Python-Based Expert System for Healthy Diet Recommendations Using Forward Chaining

Sevyna Wenata; Juliano Handal; Monika Monika; Kurniawan Hamidi; Harira Prada

doi:10.63643/jges.v4i1.406

Penulis

Sevyna Wenata Universal University
Juliano Handal Universal University
Monika Monika Universal University
Kurniawan Hamidi Universal University
Harira Prada Universal University

DOI:

https://doi.org/10.63643/jges.v4i1.406

Kata Kunci:

BMI (Body Maks Index), expert system, forward chaining, healthy diet, python

Abstrak

A healthy diet is an important factor in maintaining overall health. However, many people still have difficulties determining their weight status, daily calorie requirements, and appropriate dietary patterns based on their individual conditions. In addition, the variety of diet information available on the internet may make it difficult for users to select appropriate recommendations. This study aims to design an expert system that calculates Body Mass Indes (BMI), determines calorie requirements, and provides dietary recommendations and health advice based on user conditions. The inference method used is Forward Chaining, supported by a knowledge base consisting of user facts and IF-THEN rules based on nutritional expertise. Specifically, the IF-THEN rules map user inputs (such as age, height, weight, target weight, and meal frequency) to evaluate BMI classification thresholds (e.g., if 25 ≤ BMI ≤ 30, the system triggers an Overweight status and assigns an 1800 kcal target) along with supplementary goal-adjustment rules. The validation of these rules and the system's mathematical accuracy were verified through clinical test scenarios. The results show that the system can automatically calculate BMI, determine BMI status, provide calorie requirement information, and generate meal recommendations and health advice based on predefined rules. However, the system's scope is strictly limited to general BMI-based nutritional estimation and does not account for biological sex, physical activity levels, or pre-existing medical conditions; therefore, its automated outputs serve solely as a practical supporting tool and do not replace professional medical or nutritional consultation.

Referensi

M. L. Neuhouser, “HHS Public Access,” pp. 3–6, 2020, doi: 10.1016/j.nutres.2018.06.002.The.

F. Teknik, T. Informatika, and U. T. Raya, “IMPLEMENTASI FORWARD CHAINING Jurnal Insan Peduli Informatika ( JIPETIK ),” pp. 100–107, 2026.

M. L. Neuhouser, R. L. Prentice, L. F. Tinker, and J. W. Lampe, “Enhancing Capacity for Food and Nutrient Intake Assessment in Population Sciences Research,” pp. 37–54, 2023.

A. H. Lichtenstein, L. J. Appel, M. Vadiveloo, F. B. Hu, and P. M. Kris-etherton, “2021 Dietary Guidance to Improve Cardiovascular Health : A Scientific Statement From the American Heart Association,” 2021, doi: 10.1161/CIR.0000000000001031.

P. Wang, M. Song, A. Eliassen, and M. Wang, “Optimal dietary patterns for prevention of chronic disease Citation,” 2023, doi: 10.1038/s41591-023-02235-5.

N. Putu et al., “Sistem Pakar Pemilihan Menu Diet Sesuai Kondisi Kesehatan Pasien: Expert System for Diet Menu Selection Based on Patient Health Conditions,” vol. 5, pp. 876–888, 2025.

S. I. Suwella and F. Riandari, “Expert System Diagnosing Diabetes Using the Web-Based Dempster Shafer Method,” vol. 4, no. 4, pp. 122–128, 2021.

L. J. Dominguez et al., “Healthy Aging and Dietary Patterns,” pp. 1–22, 2022.

J. Tsuzaki et al., “Diet Quality and Body Mass Index Over 20 Years in the Multiethnic Cohort,” vol. 124, no. 2, pp. 194–204, 2025, doi: 10.1016/j.jand.2023.02.001.Diet.

M. R. Anwar, A. Info, F. Chaining, C. Diagnosis, and C. Damage, “Analysis of Expert System Implementation in Computer Damage Diagnosis with Forward Chaining Method,” vol. 1, no. 2, pp. 139–152, 2023.