publications | Saarang Panchavati

2025

Comparing P300 flashing paradigms in online typing with language models

Nand Chandravadia, Shrita Pendekanti, Dustin Roberts, and 5 more authors

PloS one, 2025

@article{chandravadia2025comparing,
  title = {Comparing P300 flashing paradigms in online typing with language models},
  author = {Chandravadia, Nand and Pendekanti, Shrita and Roberts, Dustin and Tran, Robert and Panchavati, Saarang and Arnold, Corey and Pouratian, Nader and Speier, William},
  journal = {PloS one},
  volume = {20},
  number = {2},
  pages = {e0303390},
  year = {2025},
  publisher = {Public Library of Science San Francisco, CA USA},
}

Fast ripple band high-frequency activity associated with thalamic sleep spindles in pediatric epilepsy

Atsuro Daida, Yuanyi Ding, Yipeng Zhang, and 8 more authors

Clinical Neurophysiology, 2025

Bib

@article{daida2025fast,
  title = {Fast ripple band high-frequency activity associated with thalamic sleep spindles in pediatric epilepsy},
  author = {Daida, Atsuro and Ding, Yuanyi and Zhang, Yipeng and Oana, Shingo and Panchavati, Saarang and Edmonds, Benjamin D and Ahn, Samuel S and Salamon, Noriko and Sankar, Raman and Fallah, Aria and others},
  journal = {Clinical Neurophysiology},
  year = {2025},
  publisher = {Elsevier},
}

Evidence of thalamocortical network activation during epileptic spasms: A thalamic stereotactic EEG study

Atsuro Daida, Saarang Panchavati, Shingo Oana, and 8 more authors

Epilepsia, 2025

Bib

@article{daida2025evidence,
  title = {Evidence of thalamocortical network activation during epileptic spasms: A thalamic stereotactic EEG study},
  author = {Daida, Atsuro and Panchavati, Saarang and Oana, Shingo and Kanai, Sotaro and Zhang, Yipeng and Ding, Yuanyi and Rajsekar, Rajaraman R and Salamon, Noriko and Sankar, Raman and Fallah, Aria and others},
  journal = {Epilepsia},
  year = {2025},
}

Short-Term Modulation of Epileptic Network with Low-Frequency Thalamic Stimulation

Sotaro Kanai, Atsuro Daida, Saarang Panchavati, and 8 more authors

medRxiv, 2025
Effect of Large Language Models on P300 Speller Performance with Cross-Subject Training

Nithin Parthasarathy, James Soetedjo, Saarang Panchavati, and 5 more authors

bioRxiv, 2025

2024

Uncovering spatiotemporal dynamics of the corticothalamic network at ictal onset

Saarang Panchavati, Atsuro Daida, Benjamin Edmonds, and 8 more authors

Epilepsia, 2024

Bib

@article{panchavati2024uncovering,
  title = {Uncovering spatiotemporal dynamics of the corticothalamic network at ictal onset},
  author = {Panchavati, Saarang and Daida, Atsuro and Edmonds, Benjamin and Miyakoshi, Makoto and Oana, Shingo and Ahn, Samuel S and Arnold, Corey and Salamon, Noriko and Sankar, Raman and Fallah, Aria and others},
  journal = {Epilepsia},
  volume = {65},
  number = {7},
  pages = {1989--2003},
  year = {2024},
}

Mentality: A Mamba-based Approach towards Foundation Models for EEG

Saarang Panchavati, Corey Arnold, and William Speier

In The Twelfth International Conference on Learning Representations (ICLR), 2024

Bib

@inproceedings{panchavati2024mentality,
  title = {Mentality: A Mamba-based Approach towards Foundation Models for EEG},
  author = {Panchavati, Saarang and Arnold, Corey and Speier, William},
  booktitle = {The Twelfth International Conference on Learning Representations (ICLR)},
  year = {2024},
}

High performance P300 spellers using GPT2 word prediction with cross-subject training

Nithin Parthasarathy, James Soetedjo, Saarang Panchavati, and 4 more authors

Brain-Computer Interfaces, 2024

Bib

@article{parthasarathy2024high,
  title = {High performance P300 spellers using GPT2 word prediction with cross-subject training},
  author = {Parthasarathy, Nithin and Soetedjo, James and Panchavati, Saarang and Parthasarathy, Nitya and Arnold, Corey and Pouratian, Nader and Speier, William},
  journal = {Brain-Computer Interfaces},
  volume = {11},
  number = {4},
  pages = {210--224},
  year = {2024},
  publisher = {Taylor \& Francis},
}

Evaluation Of P300 Speller Performance Using Large Language Models Along With Cross-Subject Training

Nithin Parthasarathy, James Soetedjo, Saarang Panchavati, and 4 more authors

arXiv preprint arXiv:2410.15161, 2024

Bib

@article{parthasarathy2024evaluation,
  title = {Evaluation Of P300 Speller Performance Using Large Language Models Along With Cross-Subject Training},
  author = {Parthasarathy, Nithin and Soetedjo, James and Panchavati, Saarang and Parthasarathy, Nitya and Arnold, Corey and Pouratian, Nader and Speier, William},
  journal = {arXiv preprint arXiv:2410.15161},
  year = {2024},
}

2023

Pretrained transformers for seizure detection

Saarang Panchavati, Samuel Vander Dussen, Hemal Semwal, and 5 more authors

In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

Bib

@inproceedings{panchavati2023pretrained,
  title = {Pretrained transformers for seizure detection},
  author = {Panchavati, Saarang and Vander Dussen, Samuel and Semwal, Hemal and Ali, Ahmed and Chen, Justin and Li, Haoran and Arnold, Corey and Speier, William},
  booktitle = {ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages = {1--2},
  year = {2023},
  organization = {IEEE},
}

An Automated Deep Learning Approach for the Diagnosis of Limbal Stem Cell Deficiency

Nathan Siu, Patrick Liu, Saarang Panchavati, and 4 more authors

Investigative Ophthalmology & Visual Science, 2023

Bib

@article{siu2023automated,
  title = {An Automated Deep Learning Approach for the Diagnosis of Limbal Stem Cell Deficiency},
  author = {Siu, Nathan and Liu, Patrick and Panchavati, Saarang and Pleasure, Mara and Bonnet, Clemence and Deng, Sophie X and Speier, William},
  journal = {Investigative Ophthalmology \& Visual Science},
  volume = {64},
  number = {8},
  pages = {1096--1096},
  year = {2023},
  publisher = {The Association for Research in Vision and Ophthalmology},
}

2022

A comparative analysis of machine learning approaches to predict C. difficile infection in hospitalized patients

Saarang Panchavati, Nicole S Zelin, Anurag Garikipati, and 7 more authors

American Journal of Infection Control, 2022

Bib

@article{panchavati2022comparative,
  title = {A comparative analysis of machine learning approaches to predict C. difficile infection in hospitalized patients},
  author = {Panchavati, Saarang and Zelin, Nicole S and Garikipati, Anurag and Pellegrini, Emily and Iqbal, Zohora and Barnes, Gina and Hoffman, Jana and Calvert, Jacob and Mao, Qingqing and Das, Ritankar},
  journal = {American Journal of Infection Control},
  volume = {50},
  number = {3},
  pages = {250--257},
  year = {2022},
  publisher = {Mosby},
}

MobileNetV2 based diagnosis and grading of limbal stem cell deficiency

Patrick Liu, Saarang Panchavati, Mara Pleasure, and 5 more authors

In 2022 IEEE 22nd international conference on bioinformatics and bioengineering (BIBE), 2022

Bib

@inproceedings{liu2022mobilenetv2,
  title = {MobileNetV2 based diagnosis and grading of limbal stem cell deficiency},
  author = {Liu, Patrick and Panchavati, Saarang and Pleasure, Mara and Siu, Nathan and Bonnet, Clemence and Deng, Sophie and Arnold, Corey and Speier, William},
  booktitle = {2022 IEEE 22nd international conference on bioinformatics and bioengineering (BIBE)},
  pages = {174--179},
  year = {2022},
  organization = {IEEE},
}

2021

Retrospective validation of a machine learning clinical decision support tool for myocardial infarction risk stratification

Saarang Panchavati, Carson Lam, Nicole S Zelin, and 7 more authors

Healthcare technology letters, 2021

Bib

@article{panchavati2021retrospective,
  title = {Retrospective validation of a machine learning clinical decision support tool for myocardial infarction risk stratification},
  author = {Panchavati, Saarang and Lam, Carson and Zelin, Nicole S and Pellegrini, Emily and Barnes, Gina and Hoffman, Jana and Garikipati, Anurag and Calvert, Jacob and Mao, Qingqing and Das, Ritankar},
  journal = {Healthcare technology letters},
  volume = {8},
  number = {6},
  pages = {139--147},
  year = {2021},
}

A MACHINE LEARNING CLINICAL DECISION SUPPORT TOOL FOR MYOCARDIAL INFARCTION DIAGNOSIS

Emily Pellegrini, Saarang Panchavati, Carson Lam, and 8 more authors

Journal of the American College of Cardiology, 2021

Bib

@article{pellegrini2021machine,
  title = {A MACHINE LEARNING CLINICAL DECISION SUPPORT TOOL FOR MYOCARDIAL INFARCTION DIAGNOSIS},
  author = {Pellegrini, Emily and Panchavati, Saarang and Lam, Carson and Garikipati, Anurag and Zelin, Nicole and Barnes, Gina and Siefkas, Anna and Hoffman, Jana and Handley, Megan and Calvert, Jacob and others},
  journal = {Journal of the American College of Cardiology},
  volume = {77},
  number = {18\_Supplement\_1},
  pages = {653--653},
  year = {2021},
  publisher = {American College of Cardiology Foundation Washington DC},
}

2020

Generation of model tissues with dendritic vascular networks via sacrificial laser-sintered carbohydrate templates

Ian S Kinstlinger, Sarah H Saxton, Gisele A Calderon, and 8 more authors

Nature biomedical engineering, 2020

Bib

@article{kinstlinger2020generation,
  title = {Generation of model tissues with dendritic vascular networks via sacrificial laser-sintered carbohydrate templates},
  author = {Kinstlinger, Ian S and Saxton, Sarah H and Calderon, Gisele A and Ruiz, Karen Vasquez and Yalacki, David R and Deme, Palvasha R and Rosenkrantz, Jessica E and Louis-Rosenberg, Jesse D and Johansson, Fredrik and Janson, Kevin D and others},
  journal = {Nature biomedical engineering},
  volume = {4},
  number = {9},
  pages = {916--932},
  year = {2020},
  publisher = {Nature Publishing Group UK London},
}

An automated system for reactive accelerated aging of implant materials with in-situ testing

Konlin Shen, Annabel Yau, Saarang Panchavati, and 1 more author

In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020

Bib

@inproceedings{shen2020automated,
  title = {An automated system for reactive accelerated aging of implant materials with in-situ testing},
  author = {Shen, Konlin and Yau, Annabel and Panchavati, Saarang and Maharbiz, Michel M},
  booktitle = {2020 42nd Annual International Conference of the IEEE Engineering in Medicine \& Biology Society (EMBC)},
  pages = {4466--4469},
  year = {2020},
  organization = {IEEE},
}

Multicenter validation of a machine-learning algorithm for 48-h all-cause mortality prediction

Hamid Mohamadlou, Saarang Panchavati, Jacob Calvert, and 13 more authors

Health Informatics J., Sep 2020

Abs DOI Bib

In order to evaluate mortality predictions based on boosted trees, this retrospective study uses electronic medical record data from three academic health centers for inpatients 18 years or older with at least one observation of each vital sign. Predictions were made 12, 24, and 48 hours before death. Models fit to training data from each institution were evaluated using hold-out test data from the same institution, and from the other institutions. Gradient-boosted trees (GBT) were compared to regularized logistic regression (LR) predictions, support vector machine (SVM) predictions, quick Sepsis-Related Organ Failure Assessment (qSOFA), and Modified Early Warning Score (MEWS) using area under the receiver operating characteristic curve (AUROC). For training and testing GBT on data from the same institution, the average AUROCs were 0.96, 0.95, and 0.94 across institutional test sets for 12-, 24-, and 48-hour predictions, respectively. When trained and tested on data from different hospitals, GBT AUROCs achieved up to 0.98, 0.96, and 0.96, for 12-, 24-, and 48-hour predictions, respectively. Average AUROC for 48-hour predictions for LR, SVM, MEWS, and qSOFA were 0.85, 0.79, 0.86 and 0.82, respectively. GBT predictions may help identify patients who would benefit from increased clinical care.
@article{mohamadlou_multicenter_2020, title = {Multicenter validation of a machine-learning algorithm for 48-h all-cause mortality prediction}, volume = {26}, issn = {1460-4582}, url = {http://dx.doi.org/10.1177/1460458219894494}, doi = {10.1177/1460458219894494}, number = {3}, journal = {Health Informatics J.}, author = {Mohamadlou, Hamid and Panchavati, Saarang and Calvert, Jacob and Lynn-Palevsky, Anna and Le, Sidney and Allen, Angier and Pellegrini, Emily and Green-Saxena, Abigail and Barton, Christopher and Fletcher, Grant and Shieh, Lisa and Stark, Philip B and Chettipally, Uli and Shimabukuro, David and Feldman, Mitchell and Das, Ritankar}, month = sep, year = {2020}, keywords = {notion, machine learning, prediction, electronic health record, mortality, Personal}, pages = {1912--1925}, }