Citation

Sungheetha, Akey and R., Rajesh Sharma and M, Sathya and T, Venishkumar and A, Karthikeyan (2026) Multiplexed Protein Biomarker Panel for Early Detection of Amyotrophic Lateral Sclerosis: A Machine Learning-Enhanced Diagnostic Platform. In: 8th International Conference on Futuristic Trends in Networks and Computing Technologies, FTNCT 08, 18 December 2025 - 20 December 2025, Ghaziabad.

Text 13.pdf - Published Version Restricted to Repository staff only Download (448kB)

Abstract

Amyotrophic lateral sclerosis represents a progressive neurodegenerative disorder characterized by motor neuron degeneration, necessitating early diagnostic intervention to improve patient outcomes. Current diagnostic approaches face significant limitations including delayed detection, invasive procedures, and inadequate sensitivity during presymptomatic stages. This study introduces an innovative multiplexed protein biomarker detection platform integrating machine learning algorithms for enhanced early-stage ALS identification. The proposed methodology combines electrochemical immunosensing with deep neural network architectures to simultaneously quantify fifteen protein biomarkers including neurofilament light chain, phosphorylated TDP-43, and C9orf72 dipeptide repeats. The system achieves diagnostic sensitivity of 94.7 percent and specificity of 92.3 percent with detection limits reaching 0.15 picograms per milliliter. Machine learning classification employing gradient boosting decision trees demonstrates accuracy improvements of 23 percent compared to conventional single-biomarker approaches. The platform processes serum samples within 180 minutes, providing quantitative biomarker profiles with coefficient of variation below 4.2 percent. Implementation utilizes microfluidic chip technology with integrated sensor arrays, enabling point-of-care deployment for routine screening applications. This work establishes a foundation for translational neurodegenerative disease diagnostics with significant implications for early therapeutic intervention and personalized medicine approaches in ALS management.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Machine learning diagnostics, Electrochemical immunosensing
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	04 Sep 2026 06:42
Last Modified:	04 Sep 2026 06:42
URII:	http://shdl.mmu.edu.my/id/eprint/16725

Downloads

Edit (login required)