Jathurshan Pradeepkumar

Jathurshan Pradeepkumar

Auto-generated profile, based on publicly available information

Jathurshan Pradeepkumar

Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, Urbana, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 August 2024 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
JPJathurshan Pradeepkumar
Jathurshan Pradeepkumar
MAMithunjha Anandakumar
Mithunjha Anandakumar
VKVinith Kugathasan
Vinith Kugathasan
DSDhinesh Suntharalingham
Dhinesh Suntharalingham
SKSimon Lind Kappel
Simon Lind Kappel
CEChamira Udaya Shantha Edussooriya
Chamira Udaya Shantha Edussooriya
Accurate sleep stage classification is significant for sleep health assessment. In recent years, several machine-learning based sleep staging algorithms have been developed, and in particular, deep-learning based algorithms have achieved performance on par with human annotation. Despite improved performance, a limitation of most deep-learning based algorithms is their black-box behavior, which have limited their use in clinical settings. Here, we propose a cross-modal transformer , which is a transformer-based method for sleep stage classification. The proposed cross-modal transformer consists of a cross-modal transformer encoder architecture along with a multi-scale one-dimensional convolutional neural network for automatic representation learning. The performance of our method is on-par with the state-of-the-art methods and eliminates the black-box behavior of deep-learning models by utilizing the interpretability aspect of the attention modules. Furthermore, our method provides considerable reductions in the number of parameters and training time compared to the state-of-the-art methods. Our code is available at https://github.com/Jathurshan0330/Cross-Modal-Transformer. A demo of our work can be found at https://bit.ly/Cross_modal_transformer_demo.

4 March 2026 in Nature Health
Verified
Journal Article
Closed access
PDF file
CGChufan Gao
Chufan Gao
JPJathurshan Pradeepkumar
Jathurshan Pradeepkumar
TDTrisha Das
Trisha Das
STShivashankar Thati
Shivashankar Thati
JSJimeng Sun
Jimeng Sun

28 March 2025 in medRxiv
Verified
Preprint
Open access
PDF file
JPJathurshan Pradeepkumar
Jathurshan Pradeepkumar
SKShivam Pankaj Kumar
Shivam Pankaj Kumar
CRCourtney Bryce Reamer
Courtney Bryce Reamer
MDMarie Dreyer
Marie Dreyer
JPJyoti Patel
Jyoti Patel
JSJimeng Sun
Jimeng Sun
Cancer survivorship care plans (SCPs) are critical tools for guiding long-term follow-up care of cancer survivors. Yet, their widespread adoption remains hindered by the significant clinician burden and the time- and labor-intensive process of SCP creation. Current practices require clinicians to extract and synthesize treatment summaries from complex patient data, apply relevant survivorship guidelines, and generate a care plan with personalized recommendations, making SCP generation time-consuming. In this study, we systematically explore the potential of large language models (LLMs) for automating SCP generation and introduce Survivorship Navigator, a framework designed to streamline SCP creation and enhance integration with clinical systems. We evaluate our approach through automated assessments and a human expert study, demonstrating that Survivorship Navigator outperforms baseline methods, producing SCPs that are more accurate, guideline-compliant, and actionable.

3 September 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
YHYidi Huang
Yidi Huang
AAAsad Aali
Asad Aali
LCLi-Ching Chen
Li-Ching Chen
XHXiaoke Huang
Xiaoke Huang
CJChang-Uk Jeong
Chang-Uk Jeong
EHElizabeth Healey
Elizabeth Healey
The 5th Machine Learning for Health (ML4H) symposium was held in person on December 1-2, 2025, in San Diego, California. The symposium included research roundtable sessions to foster discussions between participants and senior researchers on timely and relevant topics for the ML4H community (Adibi et al., 2025; Jeong et al., 2024; Hegselmann et al., 2023). The organization of the research roundtables at the conference involved 12 senior, 18 junior, and 3 sponsor chairs across 13 tables, including 12 program roundtables coordinated by the organizing committee and one sponsored roundtable coordinated by a corporate sponsor. Each program roundtable consisted of an invited senior chair (with substantial experience in the field), junior chairs (responsible for facilitating the discussion), and attendees from diverse backgrounds with interest in the session’s topic. The sponsored roundtable was co-chaired by 3 employees of the sponsoring company and held concurrently with the program roundtables.

30 March 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
ZWZihang Wang
Zihang Wang
ZCZheng Chen
Zheng Chen
PCPeng Chen
Peng Chen
JPJathurshan Pradeepkumar
Jathurshan Pradeepkumar
JSJimeng Sun
Jimeng Sun
YSYouhua Shi
Youhua Shi
Recent electroencephalography (EEG) foundation models aim to learn transferable neural representations; however, most existing approaches rely on raw time-domain signals or fixed-resolution time– frequency representations, which struggle to capture the non-stationary and multi-scale nature of EEG dynamics. In this paper, we propose WaveBrain, an EEG foundation model built upon a wavelet-aligned representation that explicitly organizes EEG signals into temporally aligned, band-specific components. Based on this representation, WaveBrain employs a wavelet-based EEG tokenizer with integrated frequency processing and channel aggregation to discretize multi-band EEG dynamics and capture frequency-aware temporal patterns as well as spatial dependencies across channels. Furthermore, we introduce a temporal–frequency masking and contextual token dynamics pretraining strategy to learn transferable representations in the discrete token space, enabling effective modeling of scaledependent patterns and cross-band dependencies. Experimental results on the TUEV benchmark demonstrate that WaveBrain consistently outperforms state-of-the-art EEG representation learning methods, achieving improvements of 5.10% in balanced accuracy and 1.55% in Cohen’s kappa, while maintaining competitive performance on the TUAB benchmark.