EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Advancing Genomic Diagnostics: Fast Fourier Transform Optimization and Machine Learning in Huntington’s Disease Detection

Saravanakumar C, Marirajan S, Pandian A, Durgadevi K

Journal of Electronics, Electromedical Engineering, and Medical Informatics · 20.02.2025 · 7 (2) · 283-294

DOI: 10.35882/jeeemi.v7i2.650 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Electronics, Electromedical Engineering, and Medical Informatics, online erschienen am 20.02.2025. Verfasst von Saravanakumar C und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Optimizing the Fast Fourier Transform (FFT) for genomic data analysis offers a significant advancement in addressing challenges related to sequential input processing and computational efficiency. By integrating advanced signal processing techniques such as Infinite Impulse Response (IIR) filtering, the proposed approach effectively identifies spectral characteristics and dominant frequencies in DNA sequences. This framework demonstrates improved accuracy and reduced computational overhead, making it highly suitable for large-scale and real-time genomic applications. Machine learning models were employed to classify Huntington’s Disease (HD)-associated and normal DNA sequences, using spectral features as predictive markers. Among the models evaluated, K-Nearest Neighbors (KNN) achieved perfect scores across all performance metrics, including Classification Accuracy (CA), Area Under the Curve (AUC), Precision, Recall, Matthews Correlation Coefficient (MCC) and F1 Score. Support Vector Machine (SVM) and Neural Networks also delivered competitive results, emphasizing the effectiveness of combining signal processing with machine learning for medical diagnostics and genomic studies. The computational efficiency of the proposed FFT algorithm was validated using 2,300 genomic sequences, with 90% demonstrating enhanced processing speeds compared to traditional methods. These improvements were particularly notable for longer sequences, showcasing the algorithm’s capability in high-throughput genomic analysis. This approach is particularly impactful for investigating complex conditions like Huntington’s disease, where rapid and accurate identification of genetic markers is essential. This work underscores the potential of integrating FFT optimization with machine learning to revolutionize genomic data processing and disease detection. Beyond advancing computational genomics, the proposed methodology offers a foundation for broader bioinformatics applications, including the analysis of other genetic disorders and real-time clinical diagnostics, contributing to the evolution of precision medicine.

Zitieren

APA

C, S., S, M., A, P., & K, D. (2025). Advancing Genomic Diagnostics: Fast Fourier Transform Optimization and Machine Learning in Huntington’s Disease Detection. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 7(2), 283-294. https://doi.org/10.35882/jeeemi.v7i2.650

Vancouver

C S, S M, A P, K D. Advancing Genomic Diagnostics: Fast Fourier Transform Optimization and Machine Learning in Huntington’s Disease Detection. Journal of Electronics, Electromedical Engineering, and Medical Informatics. 2025;7(2):283-294. doi:10.35882/jeeemi.v7i2.650

BibTeX
@article{C2025,
  author = {C, Saravanakumar and S, Marirajan and A, Pandian and K, Durgadevi},
  title = {Advancing Genomic Diagnostics: Fast Fourier Transform Optimization and Machine Learning in Huntington’s Disease Detection},
  journal = {Journal of Electronics, Electromedical Engineering, and Medical Informatics},
  year = {2025},
  volume = {7},
  number = {2},
  pages = {283--294},
  doi = {10.35882/jeeemi.v7i2.650}
}
Kostenlos starten →