Deep Learning-Based Health Risk Classification Using Lifestyle and Physiological Indicators Yaşam Tarzi ve Fizyolojik Göstergeler Kullanarak Derin Ö?grenme Tabanli Sa?glik Riski Siniflandirmasi
34th Signal Processing and Communications Applications Conference, SIU 2026, İstanbul, Türkiye, 7 - 10 Temmuz 2026, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/siu71813.2026.11636975
- Basıldığı Şehir: İstanbul
- Basıldığı Ülke: Türkiye
- Anahtar Kelimeler: Artificial neural networks, Health data analytics, Health risk prediction, Machine learning, Metabolic health classification
- Ankara Yıldırım Beyazıt Üniversitesi Adresli: Evet
Özet
Accurate assessment of metabolic health status is critically important in preventing diabetes and similar diseases. In recent years, data-driven analyses based on lifestyle and physiological indicators have been increasingly used in assessing health risks. Due to their ability to model complex and nonlinear relationships, artificial intelligence methods used as effective tools in predicting health risks. In this study, a new deep learning architecture was developed to classify health status in a dataset consisting of lifestyle and physiological indicators. To validate the architecture's performance, an analysis was conducted using three machine learning methods (K-nearest neighbors, Gaussian naive Bayes, multinomial logistic regression). The architecture performed significantly better than the compared methods in terms of accuracy (93.00%), precision (95.10%), recall (91.70%), and macro F1(93.04%) metrics.