PENINGKATAN KLASIFIKASI OBESITAS DENGAN METODE PEMBELAJARAN MESIN CANGGIH DAN SELEKSI FITUR

PENINGKATAN KLASIFIKASI OBESITAS DENGAN METODE PEMBELAJARAN MESIN CANGGIH DAN SELEKSI FITUR

• By WINARLIN DIRSAM;
• Tesis
• 18
• 1-67

Obesitas merupakan permasalahan kesehatan global yang semakin meningkat dan berpotensi menimbulkan berbagai komplikasi serius. Deteksi dini terhadap kondisi ini sangat penting karena dapat menurunkan risiko dan keparahan penyakit penyerta, sehingga membantu mengurangi beban kesehatan secara luas. Penelitian ini bertujuan untuk menganalisis penerapan berbagai metode pembelajaran mesin dalam memprediksi obesitas. Data yang digunakan berasal dari dataset terbuka pada Machine Learning Repository yang mencakup 2.112 individu dengan 17 variabel, meliputi kondisi fisik, pola konsumsi, serta karakteristik demografis. Analisis awal dilakukan menggunakan matriks korelasi, kemudian metode SpFSR diterapkan untuk meningkatkan proses seleksi fitur sekaligus mengidentifikasi keterkaitan antarvariabel. Selanjutnya, beberapa algoritma pembelajaran mesin, yaitu Logistic Regression (LR), k-Nearest Neighbors (k-NN), Decision Tree (DT), Support Vector Machine (SVM), Naïve Bayes (NB), dan Random Forest (RF), digunakan untuk membangun model klasifikasi obesitas. Hasil evaluasi menunjukkan bahwa algoritma Random Forest Memperoleh tingkat akurasi tertinggi sebesar 94%, diikuti oleh Decision Tree dengan akurasi 92%. Penerapan metode SpFSR berhasil menyaring 10 fitur paling berpengaruh, di antaranya riwayat obesitas dalam keluarga, tinggi badan, usia di atas 9 tahun, serta jumlah makan utama per hari, yang secara keseluruhan meningkatkan akurasi model hingga 95,3%. Temuan ini menunjukkan bahwa kombinasi SpFSR dan Random Forest memberikan kinerja terbaik dalam mengidentifikasi faktor risiko utama obesitas sekaligus menghasilkan informasi yang relevan untuk upaya pencegahan. Meski demikian, penelitian ini masih memiliki keterbatasan, terutama ketergantungan pada dataset dengan skala terbatas, sehingga generalisasi hasil pada populasi yang lebih luas perlu dikaji lebih lanjut. Secara keseluruhan, penelitian ini menegaskan pentingnya integrasi metode seleksi fitur yang canggih dalam model prediksi untuk mendukung deteksi dini dan pencegahan obesitas.

 

Kata Kunci: Klasifikasi, Deteksi dini, Seleksi fitur, Machine learning, Obesitas.

 

• Katakunci Klasifikasi, Deteksi dini, Seleksi fitur, Machine learning, Obesitas.
• URL http://
• Penerbit universitas nusa mandiri,

REFERENSI

 [1]    “Cell death and inflammation during obesity: ‘Know my methods, WAT(son)”, Cell Death Differ., Vol. 30, No. 2, pp. 279-292, 2023.

[2]     C. Boutari and C. S. Mantzoros, “A 2022 update on the epidemiology of obesity and a call to action: as its twin COVID-19 pandemic appears to be receding, the obesity and dysmetabolism pandemic continues to rage on”, Metabolism, Vol. 133, p. 155217, 2022.

[3]     P. Hossain, B. Kawar, and M. El Nahas, “Obesity and diabetes in the developing world—a growing challenge”, N. Engl. J. Med., Vol. 356, No. 3, pp. 213-215, 2007.

[4]     D. Kirwan, “Global health: current issues, future trends and foreign policy”, Clin. Med., Vol. 9, No. 3, pp. 247-253, 2009.

[5]     X. Lin and H. Li, “Obesity: Epidemiology, Pathophysiology, and Therapeutics”, Front. Endocrinol., Vol. 12, p. 706978, 2021.

[6]     F. Q. Nuttall, “Body Mass Index: Obesity, BMI, and Health—A Critical Review”, Nutr. Today, Vol. 50, No. 3, pp. 117-128, 2015.

[7]     A. Romero-Corral et al., “Accuracy of body mass index in diagnosing obesity in the adult general population”, Int. J. Obes., Vol. 32, No. 6, pp. 959-966, 2008.

[8]     N. H. Phelps et al., “Worldwide trends in underweight and obesity from 1990 to 2022: a pooled analysis of 3663 population-representative studies with 222 million children, adolescents, and adults”, The Lancet, Vol. 403, No. 10431, pp. 1027-1050, 2024.

[9]     A. W. Kranjac and D. Kranjac, “Explaining adult obesity, severe obesity, and BMI: Five decades of change”, Heliyon, Vol. 9, No. 5, p. e16210, 2023.

[10]   C. Koliaki, M. Dalamaga, and S. Liatis, “Update on the Obesity Epidemic: After the Sudden Rise, Is the Upward Trajectory Beginning to Flatten?”, Curr. Obes. Rep., Vol. 12, No. 4, pp. 514-527, 2023.

[11]   N. Temple, “The Origins of the Obesity Epidemic in the USA—Lessons for Today”, Nutrients, Vol. 14, No. 20, p. 4253, 2022.

[12]   A. Zilanawala, P. Davis-Kean, J. Nazroo, A. Sacker, S. Simonton, and Y. Kelly, “Race/ethnic disparities in early childhood BMI, obesity and overweight in the United Kingdom and United States”, Int. J. Obes., Vol. 39, No. 3, pp. 520-529, 2015.

[13]   B. A. Elfaki, “Factors contributing to overweight and obesity among young adults”, Int. J. Health Sci., Vol. 7, No. S1, pp. 698-709, 2023.

[14]   C. V. Anekwe, A. R. Jarrell, M. J. Townsend, G. I. Gaudier, J. M. Hiserodt, and F. C. Stanford, “Socioeconomics of Obesity”, Curr. Obes. Rep., Vol. 9, No. 3, pp. 272-279, 2020.

[15]   F. Lopez-Jimenez et al., “Obesity and cardiovascular disease: mechanistic insights and management strategies”, Eur. J. Prev. Cardiol., Vol. 29, No. 17, pp. 2218-2237, 2022.

[16]   G. M. M. D. Oliveira et al., “Estatística Cardiovascular—Brasil 2021”, Arq. Bras. Cardiol., Vol. 118, No. 1, pp. 115-373, 2022.

[17]   M. Knip et al., “SARS-CoV-2 and type 1 diabetes in children in Finland: an observational study”, Lancet Diabetes Endocrinol., Vol. 11, No. 4, pp. 251-260, 2023.

[18]   F. Zatterale et al., “Chronic Adipose Tissue Inflammation Linking Obesity to Insulin Resistance and Type 2 Diabetes”, Front. Physiol., Vol. 10, p. 01607, 2020.

[19]   Y. T. Wondmkun, “Obesity, Insulin Resistance, and Type 2 Diabetes: Associations and Therapeutic Implications”, Diabetes Metab. Syndr. Obes. Targets Ther., Vol. 13, pp. 3611-3616, 2020.

[20]   T. V. Rohm, D. T. Meier, J. M. Olefsky, and M. Y. Donath, “Inflammation in obesity, diabetes, and related disorders”, Immunity, Vol. 55, No. 1, pp. 31-55, 2022.

[21]   M. Gülü et al., “Is early or late biological maturation a trigger for obesity? A machine learning modeling research in Turkey boys and girls”, Front. Nutr., Vol. 10, p. 1139179, 2023.

[22]   Z. Dai, Z. Zhang, and S. Zhao, “The Risk of Type 2 Diabetes and Coronary Artery Disease in Non-obese Patients With Non-alcoholic Fatty Liver Disease: A Cohort Study”, Front. Cardiovasc. Med., Vol. 8, p. 680664, 2021.

[23]   J. Kuneš et al., “Obesity, Cardiovascular and Neurodegenerative Diseases: Potential Common Mechanisms”, Physiol. Res., Vol. 72, pp. S73-S90, 2023.

[24]   J. Jeon, “Age-specific risk factors for the prediction of obesity using a machine learning approach”, Front. Public Health, Vol. 10, p. 998782, 2022.

[25]   S. A. Thamrin et al., “Predicting Obesity in Adults Using Machine Learning Techniques: An Analysis of Indonesian Basic Health Research 2018”, Front. Nutr., Vol. 8, p. 669155, 2021.

[26]   F. Sugandh et al., “Advances in the Management of Diabetes Mellitus: A Focus on Personalized Medicine”, Cureus, 2023, https://doi.org/10.7759/cureus.43697.

[27]   X. Cheng et al., “Does Physical Activity Predict Obesity—A Machine Learning and Statistical Method-Based Analysis”, Int. J. Environ. Res. Public Health, Vol. 18, No. 8, p. 3966, 2021.

[28]   C. A. C. Montanez et al., “Machine learning approaches for the prediction of obesity using publicly available genetic profiles”, In: Proc. of Int. Joint Conf. Neural Networks (IJCNN), pp. 2743-2750, 2017.

[29]   K. Jindal, N. Baliyan, and P. S. Rana, “Obesity Prediction Using Ensemble Machine Learning Approaches”, In: Proc. of Recent Findings in Intelligent Computing Techniques, pp. 355-359, 2018.

[30]   H. Marcos-Pasero et al., “Ranking of a wide multidomain set of predictor variables of children obesity by machine learning variable importance techniques”, Sci. Rep., Vol. 11, p. 1910, 2021.

[31]   J. Li et al., “Feature Selection: A Data Perspective”, ACM Comput. Surv., Vol. 50, No. 6, pp. 1-45, 2018.

[32]   E. M. Senan et al., “Score and Correlation Coefficient-Based Feature Selection for Predicting Heart Failure Diagnosis by Using Machine Learning Algorithms”, Comput. Math. Methods Med., Vol. 2021, p. 1-16, 2021.

[33]   I. Guyon and A. Elisseeff, “An Introduction to Variable and Feature Selection”, J. Mach. Learn. Res., Vol. 3, pp. 1157-1183, 2003.

[34]   V. Bolón-Canedo, N. Sánchez-Maroño, and A. Alonso-Betanzos, “Recent advances and emerging challenges of feature selection in the context of big data”, Knowl-Based Syst., Vol. 86, pp. 33-45, 2015.

[35]   G. Chandrashekar and F. Sahin, “A survey on feature selection methods”, Comput. Electr. Eng., Vol. 40, No. 1, pp. 16-25, 2014.

[36]   J. M. Garibaldi and T. Ozen, “Uncertain Fuzzy Reasoning: A Case Study in Modelling Expert Decision Making”, IEEE Trans. Fuzzy Syst., Vol. 15, No. 1, pp. 16-35, 2007.

[37]   J. Kim et al., “Machine Learning Analysis to Identify Digital Behavioral Phenotypes for Engagement and Health Outcome Efficacy of an mHealth Intervention for Obesity: Randomized Controlled Trial”, J. Med. Internet Res., Vol. 23, No. 6, p. e27218, 2021.

[38]   N. P. M. Suwarno et al., “Performance comparison of machine learning algorithms for predicting obesity level”, In: Proc. of 3rd Ahmad Dahlan Int. Conf. Math. Math. Educ., pp. 20002-20007, 2023.

[39]   H. Gozukara et al., “Estimation of obesity levels through the proposed predictive approach based on physical activity and nutritional habits”, Diagnostics, Vol. 13, No. 18, pp. 2949-2950, 2023.

[40]   F. M. Palechor and A. D. L. H. Manotas, “Dataset for estimation of obesity levels based on eating habits and physical condition in individuals from Colombia, Peru, and Mexico”, Data Brief, Vol. 25, p. 104344, 2019.

[41]   P. Rana et al., “Relevant and Non-Redundant Feature Selection for Cancer Classification and Subtype Detection”, Cancers, Vol. 13, No. 17, p. 4297, 2021.

[42]   E. C. Blessie and E. Karthikeyan, “Sigmis: A Feature Selection Algorithm Using Correlation Based Method”, J. Algorithms Comput. Technol., Vol. 6, No. 3, pp. 385-396, 2012.

[43]   J. Loughrey and P. Cunningham, “Overfitting in Wrapper-Based Feature Subset Selection: The Harder You Try the Worse it Gets”, In: Proc. of Res. Dev. Intell. Syst. XXI, pp. 33-43, 2005.

[44]   J. Demšar and B. Zupan, “Hands-on training about overfitting”, PLoS Comput. Biol., Vol. 17, No. 3, p. e1008671, 2021.

[45]   H. M. Farghaly and T. A. El-Hafeez, “A high-quality feature selection method based on frequent and correlated items for text classification”, Soft Comput., Vol. 27, No. 16, pp. 11259-11267, 2023.

[46]   R. Kaur et al., “Predicting risk of obesity and meal planning to reduce the obese in adulthood using artificial intelligence”, Endocrine, Vol. 78, No. 3, pp. 458-469, 2022.

[47]   S. D. Stovitz, “Shorter adults, yet taller children: What’s up?”, Br. J. Nutr., Vol. 102, No. 3, pp. 329-330, 2009.

[48]   E. Christodoulou et al., “A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models”, J. Clin. Epidemiol., Vol. 110, pp. 12-22, 2019.

[49]   S. Suzuki et al., “Comparison of risk models for mortality and cardiovascular events between machine learning and conventional logistic regression analysis”, PLoS One, Vol. 14, No. 9, p. e0221911, 2019.

[50]   M. P. LaValley, “Logistic Regression”, Circulation, Vol. 117, No. 18, pp. 2395-2402, 2008.

[51]   M. Awad and R. Khanna, “Support Vector Machines for Classification”, Efficient Learning Machines, Apress, Berkeley, pp. 39-66, 2015.

[52]   C. Zhang et al., “Parallelization of multicategory support vector machines (PMC-SVM) for classifying microarray data”, BMC Bioinformatics, Vol. 7, No. S4, p. S15, 2006.

[53]   M. P. Behera et al., “A Hybrid Machine Learning Algorithm for Heart and Liver Disease Prediction Using Modified Particle Swarm Optimization with Support Vector Machine”, In: Proc. of Procedia Comput. Sci., Vol. 218, pp. 818-827, 2023.

[54]   Z. Liu et al., “A new belief-based K-nearest neighbor classification method”, Pattern Recognit., Vol. 46, No. 3, pp. 834-844, 2013.

[55]   A. J. Gallego et al., “Efficient k-nearest neighbor search based on clustering and adaptive k values”, Pattern Recognit., Vol. 122, p. 108356, 2022.

[56]   S. Saeed et al., “New techniques for efficiently k-NN algorithm for brain tumor detection”, Multimed. Tools Appl., Vol. 81, No. 13, pp. 18595-18616, 2022.

[57]   L.-Y. Hu et al., “The distance function effect on k-nearest neighbor classification for medical datasets”, SpringerPlus, Vol. 5, No. 1, p. 1304, 2016.

[58]   E. Xi, “Image Classification and Recognition Based on Deep Learning and Random Forest Algorithm”, Wirel. Commun. Mob. Comput., Vol. 2022, p. 2013181, 2022.

[59]   J. Hu and S. Szymczak, “A review on longitudinal data analysis with random forest”, Brief Bioinform., Vol. 24, No. 1, pp. 1-11, 2023.

[60]   J. K. Jaiswal and R. Samikannu, “Application of Random Forest Algorithm on Feature Subset Selection and Classification and Regression”, In: Proc. of World Congr. Comput. Commun. Technol. (WCCCT), 2017, pp. 65-68.

[61]   Y. Song and Y. Lu, “Decision tree methods: applications for classification and prediction”, Shanghai Arch. Psychiatry, Vol. 27, No. 2, pp. 130-135, 2015.

[62]   M. S. A. Rahman et al., “The Application of Decision Tree Classification Algorithm on Decision-Making for Upstream Business”, Int. J. Adv. Comput. Sci. Appl., Vol. 14, No. 8, pp. 112-120, 2023.

[63]   I. D. Mienye and N. Jere, “A Survey of Decision Trees: Concepts, Algorithms, and Applications”, IEEE Access, Vol. 12, pp. 86716-86727, 2024.

[64]   I. Wickramasinghe and H. Kalutarage, “Naive Bayes: applications, variations and vulnerabilities: a review of literature with code snippets for implementation”, Soft Comput., Vol. 25, No. 3, pp. 2277-2293, 2021.

[65]   Y. Yulhendri et al., “Correlated Naïve Bayes algorithm to determine healing rate of hepatitis patients”, Int. J. Sci. Technol. Manag., Vol. 4, No. 2, pp. 401-410, 2023.

[66]   P. Subarkah et al., “Comparison of correlated algorithm accuracy Naïve Bayes classifier and Naïve Bayes classifier for classification of heart failure”, Ilk. J. Ilm., Vol. 14, No. 2, pp. 120-125, 2022.

[67]   N. Pudjihartono et al., “A Review of Feature Selection Methods for Machine Learning-Based Disease Risk Prediction”, Front. Bioinform., Vol. 2, p. 927312, 2022.

[68]   M. D. Anasanti et al., “Exploring feature selection techniques on classification algorithms for predicting type 2 diabetes at early stage”, J. RESTI Rekayasa Sist. Teknol. Inf., Vol. 6, No. 5, pp. 832-839, 2022.

[69]   X. Shi et al., “An ensemble-based feature selection framework to select risk factors of childhood obesity for policy decision making”, BMC Med. Inform. Decis. Mak., Vol. 21, No. 1, p. 222, 2021.

[70]   F. H. Alfebi and M. D. Anasanti, “Improving Cardiovascular Disease Prediction by Integrating Imputation, Imbalance Resampling, and Feature Selection Techniques into Machine Learning Model”, Indones. J. Comput., Vol. 2, No. 1, pp. 45-56, 2022.

[71]   D. Parra et al., “Predicting the Risk of Overweight and Obesity in Madrid—A Binary Classification Approach with Evolutionary Feature Selection”, Appl. Sci., Vol. 12, No. 16, p. 8251, 2022.

[72]   G. F. A. Yeo et al., “Sequential Feature Selection and Instance Selection Using SpFSR and SpFixedIS”, In: Proc. of Int. Conf. Artif. Intell. Big Data (ICAIBD), pp. 843-848, 2023.

[73]   H. H. Htun et al., “Survey of feature selection and extraction techniques for stock market prediction”, Financ. Innov., Vol. 9, No. 1, p. 26, 2023.

[74]   X. Liu et al., “Adapting Feature Selection Algorithms for the Classification of Chinese Texts”, Syst., Vol. 11, No. 9, p. 483, 2023.

[75]   D. Terra et al., “Shape-based Features Investigation for Preneoplastic Lesions on Cervical Cancer Diagnosis”, In: Proc. of Int. Conf. Comput. Vision, Imaging Comput. Graphics Theory Appl., pp. 506-513, 2023.

[76]   M. R. Lowe et al., “Personal history of dieting and family history of obesity are unrelated: Implications for understanding weight gain proneness”, Eat. Behav., Vol. 17, pp. 144-148, 2015.

[77]   D. Corica et al., “Does Family History of Obesity, Cardiovascular, and Metabolic Diseases Influence Onset and Severity of Childhood Obesity?”, Front. Endocrinol., Vol. 9, p. 187, 2018.

[78]   M. H. Eisenberg et al., “‘It runs in my family’: The association of perceived family history with body dissatisfaction and weight bias internalization among overweight women”, Women Health, Vol. 57, No. 4, pp. 478-493, 2017.

[79]   A. M. A. Shammala et al., “The magnitude and related risk factors of obesity and overweight among medical students at Shendi University, Sudan”, SAR J. Pathol. Microbiol., Vol. 5, No. 1, pp. 1-6, 2024.

[80]   C. Strobl et al., “Bias in random forest variable importance measures: Illustrations, sources and a solution”, BMC Bioinformatics, Vol. 8, No. 1, p. 25, 2007.

[81]   K. Dissanayake and M. G. Md Johar, “Comparative Study on Heart Disease Prediction Using Feature Selection Techniques on Classification Algorithms”, Appl. Comput. Intell. Soft Comput., Vol. 2021, pp. 1-17, 2021.

[82]   X. Wang, “Predicting obesity risk through lifestyle habits: A comparative analysis of machine learning models”, E3S Web Conf., Vol. 553, p. 05037, 2024.

[83]   D. V. Akman et al., “k-best feature selection and ranking via stochastic approximation”, Expert Syst. Appl., Vol. 217, p. 118864, 2023.

[84]   T. M. Mitchell, Machine Learning. New York, NY, USA: McGraw-Hill, 1997.

[85]   W. Dirsam, and M. D. Anasanti, “Improving Obesity Classification with Advanced Machine Learning and Feature Selection Methods,” International Journal of Intelligent Engineering and Systems, vol. 18, no. 7. 2025, doi: 10.22266/ijies2025.0831.26.