Identifying Pregnancies in Population-Based Data Sources: Development and Application of the ConcePTION Pregnancy Algorithm

Giorgio Limoncella; Anna Girardi; Claudia Bartolini; Giulia Hyeraci; Giuseppe Roberto; Olga Paoletti; Davide Messina; Felipe Villalobos; Carlo Alberto Bisacco; Jesse van den Berg; Eline Houben; Katia Santacà; Ylenia Ingrasciotta; Gianluca Trifirò; Giorgia Pellegrini; Valentina Ientile; Vjola Hoxhaj; Carlos Durán; Judit Riera-Arnau; Patricia García-Poza; Mar Martín-Pérez; Ana Llorente-García; Lucia Cea-Soriano; Consuelo Huerta-Álvarez; Francisco Sánchez-Sáez; Gabriel Sanfélix-Gimeno; Clara L Rodríguez-Bernal; Jérémy Jové; Marie-Agnès Bernard; Nicolas H Thurin; Sue Jordan; Daniel Thayer; Hywel Turner Evans; Alex-Ioan Coldea; Marco Manfrini; Marleen van Gelder; Michele Tari; Romin Pajouheshnia; Ana Sofia Afonso Maciel; Maryline Le Noan-Lainé; Ditte Mølgaard-Nielsen; Marianne Cunnington; Caitlin Dodd; Leonardo Grilli; Constanza L Andaur Navarro; Miriam Sturkenboom; Hedvig Nordeng; Rosa Gini

doi:10.1002/pds.70438

Identifying Pregnancies in Population-Based Data Sources: Development and Application of the ConcePTION Pregnancy Algorithm

Giorgio Limoncella^*
, Anna Girardi
, Claudia Bartolini
, Giulia Hyeraci
, Giuseppe Roberto
, Olga Paoletti
, Davide Messina
, Felipe Villalobos
, Carlo Alberto Bisacco
, Jesse van den Berg
, Eline Houben
, Katia Santacà
, Ylenia Ingrasciotta
, Gianluca Trifirò
, Giorgia Pellegrini
, Valentina Ientile
, Vjola Hoxhaj
, Carlos Durán
, Judit Riera-Arnau
, Patricia García-Poza

Mar Martín-Pérez, Ana Llorente-García, Lucia Cea-Soriano, Consuelo Huerta-Álvarez, Francisco Sánchez-Sáez, Gabriel Sanfélix-Gimeno, Clara L Rodríguez-Bernal, Jérémy Jové, Marie-Agnès Bernard, Nicolas H Thurin, Sue Jordan, Daniel Thayer, Hywel Turner Evans, Alex-Ioan Coldea, Marco Manfrini, Marleen van Gelder, Michele Tari, Romin Pajouheshnia, Ana Sofia Afonso Maciel, Maryline Le Noan-Lainé, Ditte Mølgaard-Nielsen, Marianne Cunnington, Caitlin Dodd, Leonardo Grilli, Constanza L Andaur Navarro, Miriam Sturkenboom, Hedvig Nordeng, Rosa Gini

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

PURPOSE: In 2019, the Innovative Medicines Initiative funded the ConcePTION project to enhance monitoring of medication safety in pregnancy and breastfeeding. This paper describes how the ConcePTION Pregnancy Algorithm (PA) identified pregnancies in 10 diverse European electronic healthcare data sources and estimated their duration.

METHODS: Data sources from six European countries were mapped to the ConcePTION Common Data Model. Any pregnancy-related record was retrieved from various available data banks, including birth register, primary care records, and hospital records, and reconciled into episodes of pregnancy (starting between 01/2015 and 12/2019), each with start date, end date, and type of end. A random forest model was used to estimate missing gestational ages for incomplete records. Parameters were tailored to data sources to address local variations in data availability, collection, and governance. Model performance was evaluated using cross-validated Root Mean Squared Error (RMSE).

RESULTS: The PA identified ~2.7 million pregnancies, in over 2.2 million individuals. Most ended in live births (50%-83%), 1%-15% in elective terminations, and 4%-10% in spontaneous abortions, depending on data sources. Pregnancies with unknown type of end were also retrieved (2%-34%). Gestational age was predicted for 6%-89% of records (RMSE: 17-50 days). The median gestational age at first identified pregnancy record ranged from 47 to 280 days.

CONCLUSIONS: We developed an open-source algorithm to identify and date pregnancies, including early-stage pregnancies with unknown end and/or ongoing at the time of data extraction. This algorithm may facilitate multinational studies, improving generation of timely real-world evidence about use and safety of medicinal products in pregnancy.

Original language	English
Article number	e70438
Journal	Pharmacoepidemiology and Drug Safety
Volume	35
Issue number	8
DOIs	https://doi.org/10.1002/pds.70438
Publication status	Published - Aug 2026

Keywords

Female
Pregnancy
Humans
Algorithms
Europe/epidemiology
Prediction Algorithms
Gestational Age
Databases, Factual/statistics & numerical data
Electronic Health Records/statistics & numerical data
Random Forest

Access to Document

10.1002/pds.70438Licence: CC BY

Pharmacoepidemiology and Drug - 2026 - Limoncella - Identifying Pregnancies in Population‐Based Data Sources DevelopmentFinal published version, 2.1 MBLicence: CC BY

Cite this

Limoncella, G., Girardi, A., Bartolini, C., Hyeraci, G., Roberto, G., Paoletti, O., Messina, D., Villalobos, F., Bisacco, C. A., van den Berg, J., Houben, E., Santacà, K., Ingrasciotta, Y., Trifirò, G., Pellegrini, G., Ientile, V., Hoxhaj, V., Durán, C., Riera-Arnau, J., ... Gini, R. (2026). Identifying Pregnancies in Population-Based Data Sources: Development and Application of the ConcePTION Pregnancy Algorithm. Pharmacoepidemiology and Drug Safety, 35(8), Article e70438. https://doi.org/10.1002/pds.70438

@article{b6aee7de2d2d44528ca15bd99f0aa85d,

title = "Identifying Pregnancies in Population-Based Data Sources: Development and Application of the ConcePTION Pregnancy Algorithm",

abstract = "PURPOSE: In 2019, the Innovative Medicines Initiative funded the ConcePTION project to enhance monitoring of medication safety in pregnancy and breastfeeding. This paper describes how the ConcePTION Pregnancy Algorithm (PA) identified pregnancies in 10 diverse European electronic healthcare data sources and estimated their duration.METHODS: Data sources from six European countries were mapped to the ConcePTION Common Data Model. Any pregnancy-related record was retrieved from various available data banks, including birth register, primary care records, and hospital records, and reconciled into episodes of pregnancy (starting between 01/2015 and 12/2019), each with start date, end date, and type of end. A random forest model was used to estimate missing gestational ages for incomplete records. Parameters were tailored to data sources to address local variations in data availability, collection, and governance. Model performance was evaluated using cross-validated Root Mean Squared Error (RMSE).RESULTS: The PA identified \textasciitilde{}2.7 million pregnancies, in over 2.2 million individuals. Most ended in live births (50\%-83\%), 1\%-15\% in elective terminations, and 4\%-10\% in spontaneous abortions, depending on data sources. Pregnancies with unknown type of end were also retrieved (2\%-34\%). Gestational age was predicted for 6\%-89\% of records (RMSE: 17-50 days). The median gestational age at first identified pregnancy record ranged from 47 to 280 days.CONCLUSIONS: We developed an open-source algorithm to identify and date pregnancies, including early-stage pregnancies with unknown end and/or ongoing at the time of data extraction. This algorithm may facilitate multinational studies, improving generation of timely real-world evidence about use and safety of medicinal products in pregnancy.",

keywords = "Female, Pregnancy, Humans, Algorithms, Europe/epidemiology, Prediction Algorithms, Gestational Age, Databases, Factual/statistics \& numerical data, Electronic Health Records/statistics \& numerical data, Random Forest",

author = "Giorgio Limoncella and Anna Girardi and Claudia Bartolini and Giulia Hyeraci and Giuseppe Roberto and Olga Paoletti and Davide Messina and Felipe Villalobos and Bisacco, \{Carlo Alberto\} and \{van den Berg\}, Jesse and Eline Houben and Katia Santac{\`a} and Ylenia Ingrasciotta and Gianluca Trifir{\`o} and Giorgia Pellegrini and Valentina Ientile and Vjola Hoxhaj and Carlos Dur{\'a}n and Judit Riera-Arnau and Patricia Garc{\'i}a-Poza and Mar Mart{\'i}n-P{\'e}rez and Ana Llorente-Garc{\'i}a and Lucia Cea-Soriano and Consuelo Huerta-{\'A}lvarez and Francisco S{\'a}nchez-S{\'a}ez and Gabriel Sanf{\'e}lix-Gimeno and Rodr{\'i}guez-Bernal, \{Clara L\} and J{\'e}r{\'e}my Jov{\'e} and Marie-Agn{\`e}s Bernard and Thurin, \{Nicolas H\} and Sue Jordan and Daniel Thayer and Evans, \{Hywel Turner\} and Alex-Ioan Coldea and Marco Manfrini and \{van Gelder\}, Marleen and Michele Tari and Romin Pajouheshnia and \{Afonso Maciel\}, \{Ana Sofia\} and \{Le Noan-Lain{\'e}\}, Maryline and Ditte M{\o}lgaard-Nielsen and Marianne Cunnington and Caitlin Dodd and Leonardo Grilli and \{Andaur Navarro\}, \{Constanza L\} and Miriam Sturkenboom and Hedvig Nordeng and Rosa Gini",

note = "{\textcopyright} 2026 The Author(s). Pharmacoepidemiology and Drug Safety published by John Wiley \& Sons Ltd.",

year = "2026",

month = aug,

doi = "10.1002/pds.70438",

language = "English",

volume = "35",

journal = "Pharmacoepidemiology and Drug Safety",

issn = "1053-8569",

publisher = "John Wiley \& Sons Inc.",

number = "8",

}

Limoncella, G, Girardi, A, Bartolini, C, Hyeraci, G, Roberto, G, Paoletti, O, Messina, D, Villalobos, F, Bisacco, CA, van den Berg, J, Houben, E, Santacà, K, Ingrasciotta, Y, Trifirò, G, Pellegrini, G, Ientile, V, Hoxhaj, V , Durán, C, Riera-Arnau, J, García-Poza, P, Martín-Pérez, M, Llorente-García, A, Cea-Soriano, L, Huerta-Álvarez, C, Sánchez-Sáez, F, Sanfélix-Gimeno, G, Rodríguez-Bernal, CL, Jové, J, Bernard, M-A, Thurin, NH, Jordan, S, Thayer, D, Evans, HT, Coldea, A-I, Manfrini, M, van Gelder, M, Tari, M, Pajouheshnia, R, Afonso Maciel, AS, Le Noan-Lainé, M, Mølgaard-Nielsen, D, Cunnington, M, Dodd, C, Grilli, L, Andaur Navarro, CL , Sturkenboom, M, Nordeng, H & Gini, R 2026, 'Identifying Pregnancies in Population-Based Data Sources: Development and Application of the ConcePTION Pregnancy Algorithm', Pharmacoepidemiology and Drug Safety, vol. 35, no. 8, e70438. https://doi.org/10.1002/pds.70438

TY - JOUR

T1 - Identifying Pregnancies in Population-Based Data Sources

T2 - Development and Application of the ConcePTION Pregnancy Algorithm

AU - Limoncella, Giorgio

AU - Girardi, Anna

AU - Bartolini, Claudia

AU - Hyeraci, Giulia

AU - Roberto, Giuseppe

AU - Paoletti, Olga

AU - Messina, Davide

AU - Villalobos, Felipe

AU - Bisacco, Carlo Alberto

AU - van den Berg, Jesse

AU - Houben, Eline

AU - Santacà, Katia

AU - Ingrasciotta, Ylenia

AU - Trifirò, Gianluca

AU - Pellegrini, Giorgia

AU - Ientile, Valentina

AU - Hoxhaj, Vjola

AU - Durán, Carlos

AU - Riera-Arnau, Judit

AU - García-Poza, Patricia

AU - Martín-Pérez, Mar

AU - Llorente-García, Ana

AU - Cea-Soriano, Lucia

AU - Huerta-Álvarez, Consuelo

AU - Sánchez-Sáez, Francisco

AU - Sanfélix-Gimeno, Gabriel

AU - Rodríguez-Bernal, Clara L

AU - Jové, Jérémy

AU - Bernard, Marie-Agnès

AU - Thurin, Nicolas H

AU - Jordan, Sue

AU - Thayer, Daniel

AU - Evans, Hywel Turner

AU - Coldea, Alex-Ioan

AU - Manfrini, Marco

AU - van Gelder, Marleen

AU - Tari, Michele

AU - Pajouheshnia, Romin

AU - Afonso Maciel, Ana Sofia

AU - Le Noan-Lainé, Maryline

AU - Mølgaard-Nielsen, Ditte

AU - Cunnington, Marianne

AU - Dodd, Caitlin

AU - Grilli, Leonardo

AU - Andaur Navarro, Constanza L

AU - Sturkenboom, Miriam

AU - Nordeng, Hedvig

AU - Gini, Rosa

PY - 2026/8

Y1 - 2026/8

N2 - PURPOSE: In 2019, the Innovative Medicines Initiative funded the ConcePTION project to enhance monitoring of medication safety in pregnancy and breastfeeding. This paper describes how the ConcePTION Pregnancy Algorithm (PA) identified pregnancies in 10 diverse European electronic healthcare data sources and estimated their duration.METHODS: Data sources from six European countries were mapped to the ConcePTION Common Data Model. Any pregnancy-related record was retrieved from various available data banks, including birth register, primary care records, and hospital records, and reconciled into episodes of pregnancy (starting between 01/2015 and 12/2019), each with start date, end date, and type of end. A random forest model was used to estimate missing gestational ages for incomplete records. Parameters were tailored to data sources to address local variations in data availability, collection, and governance. Model performance was evaluated using cross-validated Root Mean Squared Error (RMSE).RESULTS: The PA identified ~2.7 million pregnancies, in over 2.2 million individuals. Most ended in live births (50%-83%), 1%-15% in elective terminations, and 4%-10% in spontaneous abortions, depending on data sources. Pregnancies with unknown type of end were also retrieved (2%-34%). Gestational age was predicted for 6%-89% of records (RMSE: 17-50 days). The median gestational age at first identified pregnancy record ranged from 47 to 280 days.CONCLUSIONS: We developed an open-source algorithm to identify and date pregnancies, including early-stage pregnancies with unknown end and/or ongoing at the time of data extraction. This algorithm may facilitate multinational studies, improving generation of timely real-world evidence about use and safety of medicinal products in pregnancy.

AB - PURPOSE: In 2019, the Innovative Medicines Initiative funded the ConcePTION project to enhance monitoring of medication safety in pregnancy and breastfeeding. This paper describes how the ConcePTION Pregnancy Algorithm (PA) identified pregnancies in 10 diverse European electronic healthcare data sources and estimated their duration.METHODS: Data sources from six European countries were mapped to the ConcePTION Common Data Model. Any pregnancy-related record was retrieved from various available data banks, including birth register, primary care records, and hospital records, and reconciled into episodes of pregnancy (starting between 01/2015 and 12/2019), each with start date, end date, and type of end. A random forest model was used to estimate missing gestational ages for incomplete records. Parameters were tailored to data sources to address local variations in data availability, collection, and governance. Model performance was evaluated using cross-validated Root Mean Squared Error (RMSE).RESULTS: The PA identified ~2.7 million pregnancies, in over 2.2 million individuals. Most ended in live births (50%-83%), 1%-15% in elective terminations, and 4%-10% in spontaneous abortions, depending on data sources. Pregnancies with unknown type of end were also retrieved (2%-34%). Gestational age was predicted for 6%-89% of records (RMSE: 17-50 days). The median gestational age at first identified pregnancy record ranged from 47 to 280 days.CONCLUSIONS: We developed an open-source algorithm to identify and date pregnancies, including early-stage pregnancies with unknown end and/or ongoing at the time of data extraction. This algorithm may facilitate multinational studies, improving generation of timely real-world evidence about use and safety of medicinal products in pregnancy.

KW - Female

KW - Pregnancy

KW - Humans

KW - Algorithms

KW - Europe/epidemiology

KW - Prediction Algorithms

KW - Gestational Age

KW - Databases, Factual/statistics & numerical data

KW - Electronic Health Records/statistics & numerical data

KW - Random Forest

U2 - 10.1002/pds.70438

DO - 10.1002/pds.70438

M3 - Article

C2 - 42571911

SN - 1053-8569

VL - 35

JO - Pharmacoepidemiology and Drug Safety

JF - Pharmacoepidemiology and Drug Safety

IS - 8

M1 - e70438

ER -

Identifying Pregnancies in Population-Based Data Sources: Development and Application of the ConcePTION Pregnancy Algorithm

Abstract

Keywords

Access to Document

Fingerprint

Cite this