EUVIMEDEUVIMED entdecken
Crossref

AI-Driven Neuropharmacological Drug Discovery for Diabetic Peripheral Neuropathy Using Next-Generation Deep Learning Frameworks and Advanced Biomedical Data Analytics

C. Ganesh, B. Murugesakumar, Yogini Dilip Borole, CH. M. H. Sai Baba, Siva Ramakrishna Tatapudi, Ashok Koujalagi, Mukesh Soni

International Journal of Drug Delivery Technology · 30.04.2026 · 16 (23s)

DOI: 10.25258/ijddt.16.23s.13 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 30.04.2026. Verfasst von C. Ganesh und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic peripheral neuropathy (DPN) is a debilitating, progressive complication of diabetes that is characterized by the degeneration of nerves and defective sensory-motor function with chronic pain. Traditional Chinese Medicine, with its multi-component and multi-pathway therapeutic philosophy, offers rich potential sources of neuroprotective agents, but the mechanistic understanding and systematic validation of these remain insufficient. To overcome these issues, AI-Driven Neuropharmacological Drug Discovery for Diabetic Peripheral Neuropathy using Next-Generation Deep Learning Frameworks and Advanced Biomedical Data Analytics (DD-DPN-BDA) is proposed. Initially, the input data is used from Chinese Medicine Entity Recognition Dataset. Then, the collected data are pre-processed using Constrained Normalized Sub band Adaptive Filter (CNSAF) for data cleaning, normalization and duplicate removal. Then, the pre-processed data are given to feature extraction process performed using the High-Order Time-Reassigned Synchrosqueezing Transform (HTST) to extract contextual features such as Surrounding Words, Pre-trained Language Model Embeddings, Lexicon Matches, Structural Information. These features are given to Multi-Fidelity Physics-Informed Convolutional Neural Networks (MPCNN) for drug discovery in diabetic peripheral neuropathy. To enhance accuracy, the Single Candidate Optimization Algorithm (SCOA) is utilized to optimize MPCNN parameters ensuring drug discovery. Performance of the DD-DPN-BDA approach attains 7.54%, 8.27% and 7.37% higher accuracy; 7.68%, 5.89% and 7.93% higher precision; 8.54%, 7.67% and 8.87% higher recall, when compared with existing techniques such as IDM-TCM-DDDN, HR-DM-DL and TC-AAD-ML respectively.

Zitieren

APA

Ganesh, C., Murugesakumar, B., Borole, Y. D., Baba, C. M. H. S., Tatapudi, S. R., Koujalagi, A., & Soni, M. (2026). AI-Driven Neuropharmacological Drug Discovery for Diabetic Peripheral Neuropathy Using Next-Generation Deep Learning Frameworks and Advanced Biomedical Data Analytics. International Journal of Drug Delivery Technology, 16(23s). https://doi.org/10.25258/ijddt.16.23s.13

Vancouver

Ganesh C, Murugesakumar B, Borole YD, Baba CMHS, Tatapudi SR, Koujalagi A, et al. AI-Driven Neuropharmacological Drug Discovery for Diabetic Peripheral Neuropathy Using Next-Generation Deep Learning Frameworks and Advanced Biomedical Data Analytics. International Journal of Drug Delivery Technology. 2026;16(23s). doi:10.25258/ijddt.16.23s.13

BibTeX
@article{Ganesh2026,
  author = {Ganesh, C. and Murugesakumar, B. and Borole, Yogini Dilip and Baba, CH. M. H. Sai and Tatapudi, Siva Ramakrishna and Koujalagi, Ashok and Soni, Mukesh},
  title = {AI-Driven Neuropharmacological Drug Discovery for Diabetic Peripheral Neuropathy Using Next-Generation Deep Learning Frameworks and Advanced Biomedical Data Analytics},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {23s},
  doi = {10.25258/ijddt.16.23s.13}
}
Kostenlos starten →