SSA-classifier based screening study for Alzheimer's disease

Alzheimer's is a disease (AD) that affects 10 % of individuals aged ≥ 65, is the most prevalent neurodegenerative disorder. We propose a diagnostic framework integrating plasma attenuated total reflection Fourier transform infrared (ATR-FTIR) spectroscopy with machine learning for AD screening. Four classifiers (SVM, Logistic Regression, XGBoost, LDA) were optimized using a modified Sparrow Search Algorithm (GSSA), benchmarked against its standard version (SSA) and Bayesian methods. GSSA-optimized classifiers demonstrated superior performance, with GSSA-XGBoost achieving peak metrics: 88.51 % accuracy (+2.30 % vs SSA-XGBoost), 95.35 % sensitivity, and 81.82 % specificity. Comparative test-set results revealed consistent improvements: SSA-optimized models attained 83.91 % (SVM), 77.01 % (Logistic), 86.21 % (XGBoost), and 79.31 % (LDA) accuracy, and Bayesian counterparts achieved 85.06 %, 80.46 %, 85.06 %, and 79.31 %,while GSSA-optimized models achieved 86.21 %,80.46 %,88.51 %,80.46 %,respectively. Moreover, GSSA further enhanced sensitivities to 97.67 % (SVM/LDA) and specificities to 81.82 % (XGBoost), outperforming both SSA and Bayesian approaches. This ATR-FTIR/GSSA-machine learning synergy shows significant potential as a minimally invasive AD screening tool, with XGBoost delivering optimal diagnostic balance. Our methodology advances spectroscopic biomarker discovery while demonstrating algorithmic optimization efficacy.