Publications

Everything below is listed with the status it actually has. Accepted means accepted and not yet printed. Preprint means preprint. Where a paper is under anonymous review I say so and leave the title out until notification.

Each entry has a plain-English summary, an APA citation, and a BibTeX entry, because I have spent enough time retyping other people’s citations. The full list is also on Google Scholar.

Journal articles

2026
HARMONY: Hybrid Aggregation and Reputation Mechanism for Cooperative Federated Survival Analysis

Navid Seidi, Satyaki Roy, Sajal K. Das

IEEE Journal of Biomedical and Health Informatics (JBHI)

Journalaccepted September 1, 2026Code
Hospitals in a federation score each other on whether a peer's update actually improved local survival prediction, and that score decides how much the peer counts. Peers only ever see privacy-protected versions of each other's updates, while the server still aggregates the real ones.
Cite
APA

Seidi, N., Roy, S., & Das, S. K. (2026). HARMONY: Hybrid aggregation and reputation mechanism for cooperative federated survival analysis. IEEE Journal of Biomedical and Health Informatics. (Accepted September 2026.)

BibTeX
```
@article{seidi2026harmony,
  author  = {Seidi, Navid and Roy, Satyaki and Das, Sajal K.},
  title   = {{HARMONY}: Hybrid Aggregation and Reputation Mechanism for Cooperative Federated Survival Analysis},
  journal = {IEEE Journal of Biomedical and Health Informatics},
  year    = {2026},
  note    = {Accepted September 2026}
}
```

Conference papers

2026
Evolving Sparse P2P Networks for Federated Survival Prediction with Adaptive Utility

Navid Seidi, Satyaki Roy, Sajal K. Das

IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) 2026, Pittsburgh, PA, USA

Conferenceaccepted August 2, 2026; presented August 2026
No central server. Hospitals train over a sparse peer-to-peer graph in which every connection has to keep earning its place, and the graph reorganizes itself within two epochs when the data shifts underneath it.
Cite
APA

Seidi, N., Roy, S., & Das, S. K. (2026). Evolving sparse P2P networks for federated survival prediction with adaptive utility. In 2026 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), Pittsburgh, PA, USA.

BibTeX
```
@inproceedings{seidi2026sparsep2p,
  author    = {Seidi, Navid and Roy, Satyaki and Das, Sajal K.},
  title     = {Evolving Sparse {P2P} Networks for Federated Survival Prediction with Adaptive Utility},
  booktitle = {2026 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE)},
  address   = {Pittsburgh, PA, USA},
  year      = {2026}
}
```
2026
Federated Deep Survival Machines for Collaborative Time-to-Event Analysis

Shaun Wolfe, Navid Seidi, Sajal K. Das

IEEE International Conference on E-health Networking, Application & Services (Healthcom) 2026

Conferenceaccepted
Deep survival machines, which model time-to-event outcomes as a mixture of distributions, trained collaboratively across sites instead of in one place. This one came out of mentoring an undergraduate researcher over two years.
Cite
APA

Wolfe, S., Seidi, N., & Das, S. K. (2026). Federated deep survival machines for collaborative time-to-event analysis. In 2026 IEEE International Conference on E-health Networking, Application & Services (Healthcom). (Accepted.)

BibTeX
```
@inproceedings{wolfe2026fdsm,
  author    = {Wolfe, Shaun and Seidi, Navid and Das, Sajal K.},
  title     = {Federated Deep Survival Machines for Collaborative Time-to-Event Analysis},
  booktitle = {2026 IEEE International Conference on E-health Networking, Application \& Services (Healthcom)},
  year      = {2026},
  note      = {Accepted}
}
```
2024
Addressing Data Heterogeneity in Federated Learning of Cox Proportional Hazards Models

Navid Seidi, Satyaki Roy, Sajal K. Das, Ardhendu Tripathy

IEEE International Conference on E-health Networking, Application & Services (Healthcom) 2024, Nara, Japan

ConferencepublishedarXiv:2407.14960
Different hospitals record different things, so their data does not line up. This paper groups centers by which features they actually have before training a shared Cox model, and proves the grouping converges linearly.
Cite
APA

Seidi, N., Roy, S., Das, S. K., & Tripathy, A. (2024). Addressing data heterogeneity in federated learning of Cox proportional hazards models. In 2024 IEEE International Conference on E-health Networking, Application & Services (Healthcom), Nara, Japan. https://arxiv.org/abs/2407.14960

BibTeX
```
@inproceedings{seidi2024coxph,
  author    = {Seidi, Navid and Roy, Satyaki and Das, Sajal K. and Tripathy, Ardhendu},
  title     = {Addressing Data Heterogeneity in Federated Learning of Cox Proportional Hazards Models},
  booktitle = {2024 IEEE International Conference on E-health Networking, Application \& Services (Healthcom)},
  address   = {Nara, Japan},
  year      = {2024},
  eprint    = {2407.14960},
  archivePrefix = {arXiv}
}
```
2023
Using Geographic Location-based Public Health Features in Survival Analysis

Navid Seidi, Ardhendu Tripathy, Sajal K. Das

IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) 2023, Orlando, FL, USA

ConferencepublishedIEEE Xplore
My first Ph.D. paper, and the one that set up everything after it. It asks whether where a patient lives changes what we can predict about how their disease will go.
Cite
APA

Seidi, N., Tripathy, A., & Das, S. K. (2023). Using geographic location-based public health features in survival analysis. In 2023 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), Orlando, FL, USA. https://ieeexplore.ieee.org/document/10183765

BibTeX
```
@inproceedings{seidi2023geo,
  author    = {Seidi, Navid and Tripathy, Ardhendu and Das, Sajal K.},
  title     = {Using Geographic Location-based Public Health Features in Survival Analysis},
  booktitle = {2023 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE)},
  address   = {Orlando, FL, USA},
  year      = {2023}
}
```
2019
PV2MS: Patient Virtual Visitation Management System in the Context of a Smart City

Navid Seidi, Farshad Eshghi, Manoochehr Kelarestaghi

IEEE EUROCON 2019, 18th International Conference on Smart Technologies, Novi Sad, Serbia

ConferencepublishedIEEE Xplore
A system for managing patient visitation remotely, designed as one service inside a connected city rather than as a standalone hospital tool.
Cite
APA

Seidi, N., Eshghi, F., & Kelarestaghi, M. (2019). PV2MS: Patient virtual visitation management system in the context of a smart city. In Proceedings of IEEE EUROCON 2019 - 18th International Conference on Smart Technologies, Novi Sad, Serbia. https://ieeexplore.ieee.org/document/8861958

BibTeX
```
@inproceedings{seidi2019pv2ms,
  author    = {Seidi, Navid and Eshghi, Farshad and Kelarestaghi, Manoochehr},
  title     = {{PV2MS}: Patient Virtual Visitation Management System in the Context of a Smart City},
  booktitle = {Proceedings of IEEE EUROCON 2019 - 18th International Conference on Smart Technologies},
  address   = {Novi Sad, Serbia},
  year      = {2019}
}
```
2017
VID: Virtual Information Desk

Navid Seidi, Farshad Eshghi, Manoochehr Kelarestaghi

IEEE 41st Annual Computer Software and Applications Conference (COMPSAC) 2017, Turin, Italy

ConferencepublishedIEEE Xplore
A pervasive-computing information desk: the desk finds the person who needs it instead of the person having to find the desk. This grew out of my master's thesis work.
Cite
APA

Seidi, N., Eshghi, F., & Kelarestaghi, M. (2017). VID: Virtual information desk. In 2017 IEEE 41st Annual Computer Software and Applications Conference (COMPSAC), Turin, Italy. https://ieeexplore.ieee.org/document/8029957

BibTeX
```
@inproceedings{seidi2017vid,
  author    = {Seidi, Navid and Eshghi, Farshad and Kelarestaghi, Manoochehr},
  title     = {{VID}: Virtual Information Desk},
  booktitle = {2017 IEEE 41st Annual Computer Software and Applications Conference (COMPSAC)},
  address   = {Turin, Italy},
  year      = {2017}
}
```

Book chapters

2026
Federated Learning Framework for Survival Analysis in Healthcare

Navid Seidi, Satyaki Roy, Sajal K. Das

Federated Learning: Foundations and Applications (R. Buyya, A. Mukherjee, and S. K. Das, Eds.), 1st ed., Morgan Kaufmann, ch. 17, pp. 287-302

Book chapterpublishedPublisher
A book chapter that lays out how federated learning and survival analysis fit together for healthcare, and what breaks when you combine them.
Cite
APA

Seidi, N., Roy, S., & Das, S. K. (2026). Federated learning framework for survival analysis in healthcare. In R. Buyya, A. Mukherjee, & S. K. Das (Eds.), Federated learning: Foundations and applications (1st ed., Ch. 17, pp. 287-302). Morgan Kaufmann.

BibTeX
```
@incollection{seidi2026chapter,
  author    = {Seidi, Navid and Roy, Satyaki and Das, Sajal K.},
  title     = {Federated Learning Framework for Survival Analysis in Healthcare},
  booktitle = {Federated Learning: Foundations and Applications},
  editor    = {Buyya, Rajkumar and Mukherjee, Anwesha and Das, Sajal K.},
  edition   = {1st},
  chapter   = {17},
  pages     = {287--302},
  publisher = {Morgan Kaufmann},
  year      = {2026}
}
```

Preprints

2026
Adaptive Bayesian Partner Selection for Federated Clinical Centers

Navid Seidi, Satyaki Roy, Sajal K. Das

arXiv preprint

Preprint
Each clinical center keeps a Bayesian belief about which other centers are worth training with, and updates it as evidence comes in. On MIMIC-IV in-hospital mortality across 230 federated centers it matches the accuracy of a strong baseline while sending about a tenth of the data.
Cite
APA

Seidi, N., Roy, S., & Das, S. K. (2026). Adaptive Bayesian partner selection for federated clinical centers [Preprint]. arXiv.

BibTeX
```
@misc{seidi2026abps,
  author = {Seidi, Navid and Roy, Satyaki and Das, Sajal K.},
  title  = {Adaptive Bayesian Partner Selection for Federated Clinical Centers},
  year   = {2026},
  note   = {arXiv preprint}
}
```
2025
Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcare

Navid Seidi, Satyaki Roy, Sajal K. Das

arXiv

Preprint
The preprint version of the peer-reputation idea: let the clients themselves, rather than the server alone, decide whose contributions to trust in a federated survival model.
Cite
APA

Seidi, N., Roy, S., & Das, S. K. (2025). Enhancing federated survival analysis through peer-driven client reputation in healthcare [Preprint]. arXiv.

BibTeX
```
@misc{seidi2025peerreputation,
  author = {Seidi, Navid and Roy, Satyaki and Das, Sajal K.},
  title  = {Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcare},
  year   = {2025},
  note   = {arXiv}
}
```
2024
A Stable Matching Assignment for Cancer Treatment Centers using Survival Analysis

Navid Seidi

arXiv

PreprintarXiv:2401.10469
Survival analysis flags which cancer patients are at highest risk, and a stable matching algorithm then assigns them to treatment centers using income and location. A recommendation system with a scarcity problem at its center.
Cite
APA

Seidi, N. (2024). A stable matching assignment for cancer treatment centers using survival analysis [Preprint]. arXiv. https://arxiv.org/abs/2401.10469

BibTeX
```
@misc{seidi2024stablematching,
  author = {Seidi, Navid},
  title  = {A Stable Matching Assignment for Cancer Treatment Centers using Survival Analysis},
  year   = {2024},
  eprint = {2401.10469},
  archivePrefix = {arXiv}
}
```

Under review

2026
Title withheld during anonymous review

Navid Seidi, et al.

Under review

Conferenceunder review

One manuscript on rational federated collaboration across multi-center clinical prediction is under anonymous review. Details after notification.

Patents

2026
A method and systems for updating a federated survival model and generating personalized treatment recommendations

Navid Seidi, Ardhendu Tripathy, Sajal K. Das

PatentUS non-provisional patent application, 2026

Reference 23MST030 Filed through Missouri S&T (invention disclosure form on file).

Posters and symposium talks

2026
Trust-Aware Federated Survival Analysis for Translational Precision Health

Navid Seidi, Sajal K. Das

NextGen Pathways Symposium, March 2026

Poster
2025
Heterogeneity-Aware Federated Survival Analysis Delivery using Pre-Trained Large Language Models in Digital Health

Navid Seidi

NextGen Pathways Symposium, March 2025

Poster
2024
Addressing Data Heterogeneity in Federated Learning of Cox Proportional Hazards Models

Navid Seidi, Satyaki Roy, Sajal K. Das, Ardhendu Tripathy

Doctoral Symposium, Conference on Health, Inference, and Learning (CHIL), June 2024

Poster

Publications

Journal articles

HARMONY: Hybrid Aggregation and Reputation Mechanism for Cooperative Federated Survival Analysis

Conference papers

Evolving Sparse P2P Networks for Federated Survival Prediction with Adaptive Utility

Federated Deep Survival Machines for Collaborative Time-to-Event Analysis

Addressing Data Heterogeneity in Federated Learning of Cox Proportional Hazards Models

Using Geographic Location-based Public Health Features in Survival Analysis

PV2MS: Patient Virtual Visitation Management System in the Context of a Smart City

VID: Virtual Information Desk

Book chapters

Federated Learning Framework for Survival Analysis in Healthcare

Preprints

Adaptive Bayesian Partner Selection for Federated Clinical Centers

Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcare

A Stable Matching Assignment for Cancer Treatment Centers using Survival Analysis

Under review

Title withheld during anonymous review

Patents

A method and systems for updating a federated survival model and generating personalized treatment recommendations

Posters and symposium talks

Trust-Aware Federated Survival Analysis for Translational Precision Health

Heterogeneity-Aware Federated Survival Analysis Delivery using Pre-Trained Large Language Models in Digital Health

Addressing Data Heterogeneity in Federated Learning of Cox Proportional Hazards Models