Publications

You can also find my articles on my Google Scholar profile.

Papers

Federated Foundation Model for GI Endoscopy Images

Published in arXiv preprint, 2025

We propose a federated learning framework to train foundation models for gastrointestinal endoscopy imaging, allowing hospitals to collaboratively develop general-purpose models while keeping data private. Our approach is evaluated on classification, detection, and segmentation tasks, demonstrating improved performance in a privacy-preserving, federated setting.

Citation: Devkota, A., Amireskandari, A., Palko, J., Thakkar, S., Adjeroh, D., Jiang, X., Bhattarai, B. and Gyawali, P.K., 2025. Federated Foundation Model for GI Endoscopy Images. arXiv preprint arXiv:2505.24108.
Download Paper

AI analysis for ejection fraction estimation from 12-lead ECG

Published in Scientific Reports, 2025

This study investigates the use of 12-lead ECG signals to estimate heart ejection fraction (EF) in a rural Appalachian population. Using a range of machine learning and deep learning models—including Transformers—our analysis shows deep learning models achieve the highest performance (AUROC ~0.86), with specific multi-lead combinations improving accuracy and model interpretability providing insights into predictive features.

Citation: Devkota, A., Prajapati, R., El-Wakeel, A., Adjeroh, D., Patel, B. and Gyawali, P., 2025. AI analysis for ejection fraction estimation from 12-lead ECG. Scientific Reports, 15(1), p.13502.
Download Paper

TE-SSL: Time and Event-aware Self Supervised Learning for Alzheimer’s Disease Progression Analysis

Published in MICCAI 2024, 2024

We introduce TE-SSL, a time and event-aware self-supervised learning framework for Alzheimer’s disease progression analysis. By incorporating time-to-event and event data as supervisory signals, TE-SSL improves representation learning and outperforms existing SSL methods in downstream survival analysis tasks.

Citation: Thrasher, J., Devkota, A., Tafti, A.P., Bhattarai, B., Gyawali, P. and Alzheimer’s Disease Neuroimaging Initiative, 2024, October. TE-SSL: Time and Event-aware Self Supervised Learning for Alzheimer’s Disease Progression Analysis. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 324-333). Cham: Springer Nature Switzerland.
Download Paper

Multimodal Federated Learning for Secure and Accurate Healthcare AI

Published in arXiv preprint, 2023

This paper reviews the role of multimodal federated learning in healthcare, highlighting its potential to combine diverse medical data while preserving patient privacy. It surveys state-of-the-art approaches, identifies current challenges and limitations, and outlines future directions for advancing secure and effective healthcare AI.

Citation: Thrasher, J., Devkota, A., Siwakotai, P., Chivukula, R., Poudel, P., Hu, C., Bhattarai, B. and Gyawali, P., 2023. Multimodal federated learning in healthcare: a review. arXiv preprint arXiv:2310.09650.
Download Paper

Near Real-Time Mobile Profiling and Modeling of Fine-Scale Environmental Proxies Along Major Road Lines of Nepal

Published in ICMSI, 2021

We present a methodology using GPS-enabled mobile sensors to collect and model fine-scale environmental proxies (e.g., temperature, CO₂, PM₂.₅) along major roadways in Nepal, demonstrating the effectiveness of ARIMA and RNNs for real-time and historical climate modeling.

Citation: Adhikari, N.B., Gautam, S., Devkota, A., Shikha, S., Pyakurel, S. and Adhikari, M.P., 2020, January. Near Real-Time Mobile Profiling and Modeling of Fine-Scale Environmental Proxies Along Major Road Lines of Nepal. In International Conference on Mobile Computing and Sustainable Informatics (pp. 605-617). Cham: Springer International Publishing.
Download Paper

Sentence Ranking and Answer Pinpointing in Online Discussion Forums Utilizing User-generated Metrics and Highlights

Published in NASCOIT, 2018

This work presents a framework for extracting precise answers from online discussion forums by combining sentence ranking with user-generated metrics and highlights. The approach enables accurate answer pinpointing, improving search relevance and supporting better question-answering in forums.

Citation: Gautam, S., Shikha, S., Devkota, A. and Pyakurel, S., 2018. Sentence Ranking and Answer Pinpointing in Online Discussion Forums Utilising User-generated Metrics and Highlights. Proceedings of the NaSCoIT.
Download Paper