Towards Distributed Process Discovery in Healthcare: Testing and Proving the Feasibility of the Federated Alpha+ Algorithm

Leonardo Nucciarelli; Roberto Gatta; Andrada Mihaela Tudor; Erica Tavazzi; Giovanni Arcuri; Mauro Vallati; Gema Ibanez-Sanchez; Zoe Valero-Ramon; Carlos Fernández Llatas; Andrea Damiani

doi:10.1007/978-3-031-95841-0_55

Towards Distributed Process Discovery in Healthcare: Testing and Proving the Feasibility of the Federated Alpha+ Algorithm

Leonardo Nucciarelli, Roberto Gatta, Andrada Mihaela Tudor, Erica Tavazzi, Giovanni Arcuri, Mauro Vallati, Gema Ibanez-Sanchez, Zoe Valero-Ramon, Carlos Fernández Llatas, Andrea Damiani

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Protecting patient privacy while enabling model training and data analysis is crucial. Federated Learning (FL) is a leading privacy-preserving approach that allows model training while keeping data within healthcare institutions and sharing only data aggregates. However, there is limited work on process discovery algorithms for federated execution in healthcare. Although a federated version of the Alpha Algorithm (AA) has been proposed, its inherent limitations restrict its practical use. In this paper, we propose a federated adaptation of the enhanced Alpha+ Algorithm (AA+). We formally demonstrate the equivalence between the results of the distributed and centralized algorithms, and provide an open-source software implementation. In preliminary test results we show the capabilities of the proposed federated algorithm.

Original language	English
Title of host publication	Artificial Intelligence in Medicine
Subtitle of host publication	23rd International Conference, AIME 2025, Pavia, Italy, June 23–26, 2025, Proceedings, Part II
Editors	Riccardo Bellazzi, José Manuel Juarez Herrero, Lucia Sacchi, Blaž Zupan
Publisher	Springer, Cham
Pages	294-299
Number of pages	6
Edition	1st
ISBN (Electronic)	9783031958410
ISBN (Print)	9783031958403
DOIs	https://doi.org/10.1007/978-3-031-95841-0_55
Publication status	Published - 22 Jun 2025
Event	23rd International Conference on Artificial Intelligence in Medicine - Pavia, Italy Duration: 23 Jun 2025 → 26 Jun 2025 https://aime25.aimedicine.info/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Cham
Volume	15735 LNAI
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	23rd International Conference on Artificial Intelligence in Medicine
Abbreviated title	AIME 2025
Country/Territory	Italy
City	Pavia
Period	23/06/25 → 26/06/25
Internet address	https://aime25.aimedicine.info/

Access to Document

10.1007/978-3-031-95841-0_55Licence: Unspecified

Cite this

Nucciarelli, L., Gatta, R., Tudor, A. M., Tavazzi, E., Arcuri, G., Vallati, M., Ibanez-Sanchez, G., Valero-Ramon, Z., Llatas, C. F., & Damiani, A. (2025). Towards Distributed Process Discovery in Healthcare: Testing and Proving the Feasibility of the Federated Alpha+ Algorithm. In R. Bellazzi, J. M. Juarez Herrero, L. Sacchi, & B. Zupan (Eds.), Artificial Intelligence in Medicine: 23rd International Conference, AIME 2025, Pavia, Italy, June 23–26, 2025, Proceedings, Part II (1st ed., pp. 294-299). (Lecture Notes in Computer Science; Vol. 15735 LNAI). Springer, Cham. https://doi.org/10.1007/978-3-031-95841-0_55

Nucciarelli, Leonardo ; Gatta, Roberto ; Tudor, Andrada Mihaela et al. / Towards Distributed Process Discovery in Healthcare : Testing and Proving the Feasibility of the Federated Alpha+ Algorithm. Artificial Intelligence in Medicine: 23rd International Conference, AIME 2025, Pavia, Italy, June 23–26, 2025, Proceedings, Part II. editor / Riccardo Bellazzi ; José Manuel Juarez Herrero ; Lucia Sacchi ; Blaž Zupan. 1st. ed. Springer, Cham, 2025. pp. 294-299 (Lecture Notes in Computer Science).

@inproceedings{55807798c5cc42f18808e83afd586065,

title = "Towards Distributed Process Discovery in Healthcare: Testing and Proving the Feasibility of the Federated Alpha+ Algorithm",

abstract = "Protecting patient privacy while enabling model training and data analysis is crucial. Federated Learning (FL) is a leading privacy-preserving approach that allows model training while keeping data within healthcare institutions and sharing only data aggregates. However, there is limited work on process discovery algorithms for federated execution in healthcare. Although a federated version of the Alpha Algorithm (AA) has been proposed, its inherent limitations restrict its practical use. In this paper, we propose a federated adaptation of the enhanced Alpha+ Algorithm (AA+). We formally demonstrate the equivalence between the results of the distributed and centralized algorithms, and provide an open-source software implementation. In preliminary test results we show the capabilities of the proposed federated algorithm.",

keywords = "patient privacy, Federated Learning, Alpha Algorithm",

author = "Leonardo Nucciarelli and Roberto Gatta and Tudor, \{Andrada Mihaela\} and Erica Tavazzi and Giovanni Arcuri and Mauro Vallati and Gema Ibanez-Sanchez and Zoe Valero-Ramon and Llatas, \{Carlos Fern{\'a}ndez\} and Andrea Damiani",

note = "Funding Information: R. Gatta\textbackslash{}u2019s collaboration is funded by the Ministerial Project-M.U.R.-Department of Excellence 2023-2027 awarded to the Department of Clinical and Experimental Sciences at the University of Brescia. Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; 23rd International Conference on Artificial Intelligence in Medicine, AIME 2025 ; Conference date: 23-06-2025 Through 26-06-2025",

year = "2025",

month = jun,

day = "22",

doi = "10.1007/978-3-031-95841-0\_55",

language = "English",

isbn = "9783031958403",

series = "Lecture Notes in Computer Science",

publisher = "Springer, Cham",

pages = "294--299",

editor = "Riccardo Bellazzi and \{Juarez Herrero\}, \{Jos{\'e} Manuel\} and Lucia Sacchi and Bla{\v z} Zupan",

booktitle = "Artificial Intelligence in Medicine",

address = "Switzerland",

edition = "1st",

url = "https://aime25.aimedicine.info/",

}

Nucciarelli, L, Gatta, R, Tudor, AM, Tavazzi, E, Arcuri, G, Vallati, M, Ibanez-Sanchez, G, Valero-Ramon, Z, Llatas, CF & Damiani, A 2025, Towards Distributed Process Discovery in Healthcare: Testing and Proving the Feasibility of the Federated Alpha+ Algorithm. in R Bellazzi, JM Juarez Herrero, L Sacchi & B Zupan (eds), Artificial Intelligence in Medicine: 23rd International Conference, AIME 2025, Pavia, Italy, June 23–26, 2025, Proceedings, Part II. 1st edn, Lecture Notes in Computer Science, vol. 15735 LNAI, Springer, Cham, pp. 294-299, 23rd International Conference on Artificial Intelligence in Medicine, Pavia, Italy, 23/06/25. https://doi.org/10.1007/978-3-031-95841-0_55

Towards Distributed Process Discovery in Healthcare: Testing and Proving the Feasibility of the Federated Alpha+ Algorithm. / Nucciarelli, Leonardo; Gatta, Roberto; Tudor, Andrada Mihaela et al.
Artificial Intelligence in Medicine: 23rd International Conference, AIME 2025, Pavia, Italy, June 23–26, 2025, Proceedings, Part II. ed. / Riccardo Bellazzi; José Manuel Juarez Herrero; Lucia Sacchi; Blaž Zupan. 1st. ed. Springer, Cham, 2025. p. 294-299 (Lecture Notes in Computer Science; Vol. 15735 LNAI).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Towards Distributed Process Discovery in Healthcare

T2 - 23rd International Conference on Artificial Intelligence in Medicine

AU - Nucciarelli, Leonardo

AU - Gatta, Roberto

AU - Tudor, Andrada Mihaela

AU - Tavazzi, Erica

AU - Arcuri, Giovanni

AU - Vallati, Mauro

AU - Ibanez-Sanchez, Gema

AU - Valero-Ramon, Zoe

AU - Llatas, Carlos Fernández

AU - Damiani, Andrea

N1 - Funding Information: R. Gatta\u2019s collaboration is funded by the Ministerial Project-M.U.R.-Department of Excellence 2023-2027 awarded to the Department of Clinical and Experimental Sciences at the University of Brescia. Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025/6/22

Y1 - 2025/6/22

N2 - Protecting patient privacy while enabling model training and data analysis is crucial. Federated Learning (FL) is a leading privacy-preserving approach that allows model training while keeping data within healthcare institutions and sharing only data aggregates. However, there is limited work on process discovery algorithms for federated execution in healthcare. Although a federated version of the Alpha Algorithm (AA) has been proposed, its inherent limitations restrict its practical use. In this paper, we propose a federated adaptation of the enhanced Alpha+ Algorithm (AA+). We formally demonstrate the equivalence between the results of the distributed and centralized algorithms, and provide an open-source software implementation. In preliminary test results we show the capabilities of the proposed federated algorithm.

AB - Protecting patient privacy while enabling model training and data analysis is crucial. Federated Learning (FL) is a leading privacy-preserving approach that allows model training while keeping data within healthcare institutions and sharing only data aggregates. However, there is limited work on process discovery algorithms for federated execution in healthcare. Although a federated version of the Alpha Algorithm (AA) has been proposed, its inherent limitations restrict its practical use. In this paper, we propose a federated adaptation of the enhanced Alpha+ Algorithm (AA+). We formally demonstrate the equivalence between the results of the distributed and centralized algorithms, and provide an open-source software implementation. In preliminary test results we show the capabilities of the proposed federated algorithm.

KW - patient privacy

KW - Federated Learning

KW - Alpha Algorithm

UR - https://www.scopus.com/pages/publications/105009756480

UR - https://link.springer.com/book/10.1007/978-3-031-95841-0

U2 - 10.1007/978-3-031-95841-0_55

DO - 10.1007/978-3-031-95841-0_55

M3 - Conference contribution

AN - SCOPUS:105009756480

SN - 9783031958403

T3 - Lecture Notes in Computer Science

SP - 294

EP - 299

BT - Artificial Intelligence in Medicine

A2 - Bellazzi, Riccardo

A2 - Juarez Herrero, José Manuel

A2 - Sacchi, Lucia

A2 - Zupan, Blaž

PB - Springer, Cham

Y2 - 23 June 2025 through 26 June 2025

ER -

Nucciarelli L, Gatta R, Tudor AM, Tavazzi E, Arcuri G, Vallati M et al. Towards Distributed Process Discovery in Healthcare: Testing and Proving the Feasibility of the Federated Alpha+ Algorithm. In Bellazzi R, Juarez Herrero JM, Sacchi L, Zupan B, editors, Artificial Intelligence in Medicine: 23rd International Conference, AIME 2025, Pavia, Italy, June 23–26, 2025, Proceedings, Part II. 1st ed. Springer, Cham. 2025. p. 294-299. (Lecture Notes in Computer Science). Epub 2025 Jun 21. doi: 10.1007/978-3-031-95841-0_55