Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data

Magdalena Mazur-Milecka; Natalia Kowalczyk; Kinga Jaguszewska; Dorota Zamkowska; Dariusz Wójcik; Krzysztof Preis; Henriette Skov; Stefan Wagner; Puk Sandager; Milena Sobotka; Jacek Rumiński

doi:10.1007/978-3-031-38430-1_21

Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data

Magdalena Mazur-Milecka^*, Natalia Kowalczyk, Kinga Jaguszewska, Dorota Zamkowska, Dariusz Wójcik, Krzysztof Preis, Henriette Skov, Stefan Wagner, Puk Sandager, Milena Sobotka, Jacek Rumiński

^*Corresponding author af dette arbejde

Publikation: Bidrag til bog/antologi/rapport/proceeding › Konferencebidrag i proceedings › Forskning › peer review

1 Citationer (Scopus)

Abstract

This paper describes a research study that investigates the use of machine learning algorithms on synthetic data to classify the risk of developing preeclampsia by pregnant women. Synthetic datasets were generated based on parameter distributions from three real patient studies. Four models were compared: XGBoost, Support Vector Machine (SVM), Random Forest, and Explainable Boosting Machines (EBM). The study found that the XGBoost and EBM consistently outperform the other models. An analysis of patient subsets based on their pregnancy history was also conducted, revealing that the group of patients in their first pregnancy achieved the highest prediction accuracy. Additionally, the study explored the efficacy of risk prediction based on various parameters and found that the results vary depending on the models used and the degree of class balance in the database. Finally, an additional test was performed on the dataset annotated by physicians.

Originalsprog	Engelsk
Titel	The Latest Developments and Challenges in Biomedical Engineering : Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, Lodz, Poland, September 27–29, 2023
Redaktører	Paweł Strumiłło, Artur Klepaczko, Michał Strzelecki, Dorota Bociąga
Antal sider	15
Udgivelsessted	Cham
Forlag	Springer
Publikationsdato	sep. 2023
Sider	267-281
ISBN (Trykt)	978-3-031-38429-5
ISBN (Elektronisk)	978-3-031-38430-1
DOI	https://doi.org/10.1007/978-3-031-38430-1_21
Status	Udgivet - sep. 2023
Begivenhed	Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023 - Lodz, Polen Varighed: 27 sep. 2023 → 29 sep. 2023

Konference

Konference	Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023
Land/Område	Polen
By	Lodz
Periode	27/09/2023 → 29/09/2023

Navn	Lecture Notes in Networks and Systems
Vol/bind	746
ISSN	2367-3370

Adgang til dokumentet

10.1007/978-3-031-38430-1_21

OpenUrl tilgængelighed

Fuld tekst

Citationsformater

Mazur-Milecka, M., Kowalczyk, N., Jaguszewska, K., Zamkowska, D., Wójcik, D., Preis, K., Skov, H., Wagner, S., Sandager, P., Sobotka, M., & Rumiński, J. (2023). Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data. I P. Strumiłło, A. Klepaczko, M. Strzelecki, & D. Bociąga (red.), The Latest Developments and Challenges in Biomedical Engineering: Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, Lodz, Poland, September 27–29, 2023 (s. 267-281). Springer. https://doi.org/10.1007/978-3-031-38430-1_21

Mazur-Milecka, Magdalena ; Kowalczyk, Natalia ; Jaguszewska, Kinga et al. / Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data. The Latest Developments and Challenges in Biomedical Engineering: Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, Lodz, Poland, September 27–29, 2023. red. / Paweł Strumiłło ; Artur Klepaczko ; Michał Strzelecki ; Dorota Bociąga. Cham : Springer, 2023. s. 267-281 (Lecture Notes in Networks and Systems, Bind 746).

@inproceedings{2da965b6207042ed8b2dfce3920dc7c5,

title = "Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data",

abstract = "This paper describes a research study that investigates the use of machine learning algorithms on synthetic data to classify the risk of developing preeclampsia by pregnant women. Synthetic datasets were generated based on parameter distributions from three real patient studies. Four models were compared: XGBoost, Support Vector Machine (SVM), Random Forest, and Explainable Boosting Machines (EBM). The study found that the XGBoost and EBM consistently outperform the other models. An analysis of patient subsets based on their pregnancy history was also conducted, revealing that the group of patients in their first pregnancy achieved the highest prediction accuracy. Additionally, the study explored the efficacy of risk prediction based on various parameters and found that the results vary depending on the models used and the degree of class balance in the database. Finally, an additional test was performed on the dataset annotated by physicians.",

keywords = "Digital twin, Machine learning, Preeclamspia risk, Pregnancy, Women health",

author = "Magdalena Mazur-Milecka and Natalia Kowalczyk and Kinga Jaguszewska and Dorota Zamkowska and Dariusz W{\'o}jcik and Krzysztof Preis and Henriette Skov and Stefan Wagner and Puk Sandager and Milena Sobotka and Jacek Rumi{\'n}ski",

note = "Publisher Copyright: {\textcopyright} 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023 ; Conference date: 27-09-2023 Through 29-09-2023",

year = "2023",

month = sep,

doi = "10.1007/978-3-031-38430-1_21",

language = "English",

isbn = "978-3-031-38429-5",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer",

pages = "267--281",

editor = "Pawe{\l} Strumi{\l}{\l}o and Artur Klepaczko and Micha{\l} Strzelecki and Dorota Boci{\c a}ga",

booktitle = "The Latest Developments and Challenges in Biomedical Engineering",

address = "Netherlands",

}

Mazur-Milecka, M, Kowalczyk, N, Jaguszewska, K, Zamkowska, D, Wójcik, D, Preis, K, Skov, H , Wagner, S , Sandager, P, Sobotka, M & Rumiński, J 2023, Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data. i P Strumiłło, A Klepaczko, M Strzelecki & D Bociąga (red), The Latest Developments and Challenges in Biomedical Engineering: Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, Lodz, Poland, September 27–29, 2023. Springer, Cham, Lecture Notes in Networks and Systems, bind 746, s. 267-281, Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023, Lodz, Polen, 27/09/2023. https://doi.org/10.1007/978-3-031-38430-1_21

Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data. / Mazur-Milecka, Magdalena; Kowalczyk, Natalia; Jaguszewska, Kinga et al.
The Latest Developments and Challenges in Biomedical Engineering: Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, Lodz, Poland, September 27–29, 2023. red. / Paweł Strumiłło; Artur Klepaczko; Michał Strzelecki; Dorota Bociąga. Cham: Springer, 2023. s. 267-281 (Lecture Notes in Networks and Systems, Bind 746).

Publikation: Bidrag til bog/antologi/rapport/proceeding › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data

AU - Mazur-Milecka, Magdalena

AU - Kowalczyk, Natalia

AU - Jaguszewska, Kinga

AU - Zamkowska, Dorota

AU - Wójcik, Dariusz

AU - Preis, Krzysztof

AU - Skov, Henriette

AU - Wagner, Stefan

AU - Sandager, Puk

AU - Sobotka, Milena

AU - Rumiński, Jacek

PY - 2023/9

Y1 - 2023/9

N2 - This paper describes a research study that investigates the use of machine learning algorithms on synthetic data to classify the risk of developing preeclampsia by pregnant women. Synthetic datasets were generated based on parameter distributions from three real patient studies. Four models were compared: XGBoost, Support Vector Machine (SVM), Random Forest, and Explainable Boosting Machines (EBM). The study found that the XGBoost and EBM consistently outperform the other models. An analysis of patient subsets based on their pregnancy history was also conducted, revealing that the group of patients in their first pregnancy achieved the highest prediction accuracy. Additionally, the study explored the efficacy of risk prediction based on various parameters and found that the results vary depending on the models used and the degree of class balance in the database. Finally, an additional test was performed on the dataset annotated by physicians.

AB - This paper describes a research study that investigates the use of machine learning algorithms on synthetic data to classify the risk of developing preeclampsia by pregnant women. Synthetic datasets were generated based on parameter distributions from three real patient studies. Four models were compared: XGBoost, Support Vector Machine (SVM), Random Forest, and Explainable Boosting Machines (EBM). The study found that the XGBoost and EBM consistently outperform the other models. An analysis of patient subsets based on their pregnancy history was also conducted, revealing that the group of patients in their first pregnancy achieved the highest prediction accuracy. Additionally, the study explored the efficacy of risk prediction based on various parameters and found that the results vary depending on the models used and the degree of class balance in the database. Finally, an additional test was performed on the dataset annotated by physicians.

KW - Digital twin

KW - Machine learning

KW - Preeclamspia risk

KW - Pregnancy

KW - Women health

U2 - 10.1007/978-3-031-38430-1_21

DO - 10.1007/978-3-031-38430-1_21

M3 - Article in proceedings

AN - SCOPUS:85172351450

SN - 978-3-031-38429-5

T3 - Lecture Notes in Networks and Systems

SP - 267

EP - 281

BT - The Latest Developments and Challenges in Biomedical Engineering

A2 - Strumiłło, Paweł

A2 - Klepaczko, Artur

A2 - Strzelecki, Michał

A2 - Bociąga, Dorota

PB - Springer

CY - Cham

T2 - Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023

Y2 - 27 September 2023 through 29 September 2023

ER -

Mazur-Milecka M, Kowalczyk N, Jaguszewska K, Zamkowska D, Wójcik D, Preis K et al. Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data. I Strumiłło P, Klepaczko A, Strzelecki M, Bociąga D, red., The Latest Developments and Challenges in Biomedical Engineering: Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, Lodz, Poland, September 27–29, 2023. Cham: Springer. 2023. s. 267-281. (Lecture Notes in Networks and Systems, Bind 746). doi: 10.1007/978-3-031-38430-1_21

Preeclampsia Risk Prediction Using Machine Learning Methods Trained on Synthetic Data

Abstract

Konference

Adgang til dokumentet

OpenUrl tilgængelighed

Fingeraftryk

Citationsformater