Analysis of Clinical Phenotypes through Machine Learning of First-Line H. pylori Treatment in Europe during the Period 2013–2022: Data from the European Registry on H. pylori Management (Hp-EuReg)

Olga P. Nyssen; Pietro Pratesi; Miguel A. Spínola; Laimas Jonaitis; Ángeles Pérez-Aísa; Dino Vaira; Ilaria Maria Saracino; Matteo Pavoni; Giulia Fiorini; Bojan Tepes; Dmitry S. Bordin; Irina Voynovan; Ángel Lanas; Samuel J. Martínez-Domínguez; Enrique Alfaro; Luis Bujanda; Manuel Pabón-Carrasco; Luis Hernández; Antonio Gasbarrini; Juozas Kupcinskas; Frode Lerang; Sinead M. Smith; Oleksiy Gridnyev; Mārcis Leja; Theodore Rokkas; Ricardo Marcos-Pinto; Antonio Meštrović; Wojciech Marlicz; Vladimir Milivojevic; Halis Simsek; Lumir Kunovsky; Veronika Papp; Perminder S. Phull; Marino Venerito; Lyudmila Boyanova; Doron Boltin; Yaron Niv; Tamara Matysiak-Budnik; Michael Doulberis; Daniela Dobru; Vincent Lamy; Lisette G. Capelle; Emilija Nikolovska Trpchevska; Leticia Moreira; Anna Cano-Català; Pablo Parra; Francis Mégraud; Colm O’Morain; Guillermo J. Ortega; Javier P. Gisbert; Hp-EuReg Investigators

doi:10.3390/antibiotics12091427

Analysis of Clinical Phenotypes through Machine Learning of First-Line H. pylori Treatment in Europe during the Period 2013–2022: Data from the European Registry on H. pylori Management (Hp-EuReg)

Olga P. Nyssen, Pietro Pratesi, Miguel A. Spínola, Laimas Jonaitis, Ángeles Pérez-Aísa, Dino Vaira, Ilaria Maria Saracino, Matteo Pavoni, Giulia Fiorini, Bojan Tepes, Dmitry S. Bordin, Irina Voynovan, Ángel Lanas, Samuel J. Martínez-Domínguez, Enrique Alfaro, Luis Bujanda, Manuel Pabón-Carrasco, Luis Hernández, Antonio Gasbarrini, Juozas KupcinskasFrode Lerang, Sinead M. Smith, Oleksiy Gridnyev, Mārcis Leja, Theodore Rokkas, Ricardo Marcos-Pinto, Antonio Meštrović, Wojciech Marlicz, Vladimir Milivojevic, Halis Simsek, Lumir Kunovsky, Veronika Papp, Perminder S. Phull, Marino Venerito, Lyudmila Boyanova, Doron Boltin, Yaron Niv, Tamara Matysiak-Budnik, Michael Doulberis, Daniela Dobru, Vincent Lamy, Lisette G. Capelle, Emilija Nikolovska Trpchevska, Leticia Moreira, Anna Cano-Català, Pablo Parra, Francis Mégraud, Colm O’Morain, Guillermo J. Ortega^*, Javier P. Gisbert, Hp-EuReg Investigators

^*Corresponding author for this work

Applied Medicine

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

2 Citations (Scopus)

Abstract

The segmentation of patients into homogeneous groups could help to improve eradication therapy effectiveness. Our aim was to determine the most important treatment strategies used in Europe, to evaluate first-line treatment effectiveness according to year and country. Data collection: All first-line empirical treatments registered at AEGREDCap in the European Registry on Helicobacter pylori management (Hp-EuReg) from June 2013 to November 2022. A Boruta method determined the “most important” variables related to treatment effectiveness. Data clustering was performed through multi-correspondence analysis of the resulting six most important variables for every year in the 2013–2022 period. Based on 35,852 patients, the average overall treatment effectiveness increased from 87% in 2013 to 93% in 2022. The lowest effectiveness (80%) was obtained in 2016 in cluster #3 encompassing Slovenia, Lithuania, Latvia, and Russia, treated with 7-day triple therapy with amoxicillin–clarithromycin (92% of cases). The highest effectiveness (95%) was achieved in 2022, mostly in Spain (81%), with the bismuth–quadruple therapy, including the single-capsule (64%) and the concomitant treatment with clarithromycin–amoxicillin–metronidazole/tinidazole (34%) with 10 (69%) and 14 (32%) days. Cluster analysis allowed for the identification of patients in homogeneous treatment groups assessing the effectiveness of different first-line treatments depending on therapy scheme, adherence, country, and prescription year.

Original language	English
Article number	1427
Number of pages	18
Journal	Antibiotics
Volume	12
Issue number	9
DOIs	https://doi.org/10.3390/antibiotics12091427
Publication status	Published - 10 Sept 2023

Bibliographical note

Funding Information:
This project was promoted and funded by the European Helicobacter and Microbiota Study Group (EHMSG), the Spanish Association of Gastroenterology (AEG), and the Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBERehd). The Hp-EuReg was co-funded by the European Union programme HORIZON (grant agreement number 101095359) and supported by the UK Research and Innovation (grant agreement number 10058099). The Hp-EuReg was co-funded by the European Union programme EU4Health (grant agreement number 101101252). This study was funded by Richen; however, clinical data were not accessible, and the company was not involved in any stage of the Hp-EuReg study (design, data collection, statistical analysis, or manuscript writing). We want to thank Richen for their support.

Data Availability Statement

Raw data were generated at AEG-REDCap. Derived data supporting the findings of this study are available from the Hp-EuReg Scientific Director and the PI of the project (OPN and JPG) upon request. The data supporting the findings of this study are not publicly available given that the information they contain could compromise the privacy of research participants. However, previous published data on the Hp-EuReg study, or de-identified raw data referring to the current study, as well as further information on the methods used to explore the data could be shared, with no particular time constraint. Individual participant data will not be shared.

Keywords

clustering
eradication
Helicobacter pylori
machine learning
phenotyping
treatment

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.3390/antibiotics12091427Licence: CC BY

Nyssen_etal_AB_Analysis_of_Clinical_VOR
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Final published version, 1.33 MBLicence: CC BY

Cite this

Nyssen, O. P., Pratesi, P., Spínola, M. A., Jonaitis, L., Pérez-Aísa, Á., Vaira, D., Saracino, I. M., Pavoni, M., Fiorini, G., Tepes, B., Bordin, D. S., Voynovan, I., Lanas, Á., Martínez-Domínguez, S. J., Alfaro, E., Bujanda, L., Pabón-Carrasco, M., Hernández, L., Gasbarrini, A., ... Hp-EuReg Investigators (2023). Analysis of Clinical Phenotypes through Machine Learning of First-Line H. pylori Treatment in Europe during the Period 2013–2022: Data from the European Registry on H. pylori Management (Hp-EuReg). Antibiotics, 12(9), Article 1427. https://doi.org/10.3390/antibiotics12091427

Analysis of Clinical Phenotypes through Machine Learning of First-Line H. pylori Treatment in Europe during the Period 2013–2022: Data from the European Registry on H. pylori Management (Hp-EuReg). / Nyssen, Olga P.; Pratesi, Pietro; Spínola, Miguel A. et al.
In: Antibiotics, Vol. 12, No. 9, 1427, 10.09.2023.

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

Nyssen, OP, Pratesi, P, Spínola, MA, Jonaitis, L, Pérez-Aísa, Á, Vaira, D, Saracino, IM, Pavoni, M, Fiorini, G, Tepes, B, Bordin, DS, Voynovan, I, Lanas, Á, Martínez-Domínguez, SJ, Alfaro, E, Bujanda, L, Pabón-Carrasco, M, Hernández, L, Gasbarrini, A, Kupcinskas, J, Lerang, F, Smith, SM, Gridnyev, O, Leja, M, Rokkas, T, Marcos-Pinto, R, Meštrović, A, Marlicz, W, Milivojevic, V, Simsek, H, Kunovsky, L, Papp, V, Phull, PS, Venerito, M, Boyanova, L, Boltin, D, Niv, Y, Matysiak-Budnik, T, Doulberis, M, Dobru, D, Lamy, V, Capelle, LG, Nikolovska Trpchevska, E, Moreira, L, Cano-Català, A, Parra, P, Mégraud, F, O’Morain, C, Ortega, GJ, Gisbert, JP & Hp-EuReg Investigators 2023, 'Analysis of Clinical Phenotypes through Machine Learning of First-Line H. pylori Treatment in Europe during the Period 2013–2022: Data from the European Registry on H. pylori Management (Hp-EuReg)', Antibiotics, vol. 12, no. 9, 1427. https://doi.org/10.3390/antibiotics12091427

@article{8f47da36f238474e9f40a290559a5c84,

title = "Analysis of Clinical Phenotypes through Machine Learning of First-Line H. pylori Treatment in Europe during the Period 2013–2022: Data from the European Registry on H. pylori Management (Hp-EuReg)",

abstract = "The segmentation of patients into homogeneous groups could help to improve eradication therapy effectiveness. Our aim was to determine the most important treatment strategies used in Europe, to evaluate first-line treatment effectiveness according to year and country. Data collection: All first-line empirical treatments registered at AEGREDCap in the European Registry on Helicobacter pylori management (Hp-EuReg) from June 2013 to November 2022. A Boruta method determined the “most important” variables related to treatment effectiveness. Data clustering was performed through multi-correspondence analysis of the resulting six most important variables for every year in the 2013–2022 period. Based on 35,852 patients, the average overall treatment effectiveness increased from 87% in 2013 to 93% in 2022. The lowest effectiveness (80%) was obtained in 2016 in cluster #3 encompassing Slovenia, Lithuania, Latvia, and Russia, treated with 7-day triple therapy with amoxicillin–clarithromycin (92% of cases). The highest effectiveness (95%) was achieved in 2022, mostly in Spain (81%), with the bismuth–quadruple therapy, including the single-capsule (64%) and the concomitant treatment with clarithromycin–amoxicillin–metronidazole/tinidazole (34%) with 10 (69%) and 14 (32%) days. Cluster analysis allowed for the identification of patients in homogeneous treatment groups assessing the effectiveness of different first-line treatments depending on therapy scheme, adherence, country, and prescription year.",

keywords = "clustering, eradication, Helicobacter pylori, machine learning, phenotyping, treatment",

author = "Nyssen, {Olga P.} and Pietro Pratesi and Sp{\'i}nola, {Miguel A.} and Laimas Jonaitis and {\'A}ngeles P{\'e}rez-A{\'i}sa and Dino Vaira and Saracino, {Ilaria Maria} and Matteo Pavoni and Giulia Fiorini and Bojan Tepes and Bordin, {Dmitry S.} and Irina Voynovan and {\'A}ngel Lanas and Mart{\'i}nez-Dom{\'i}nguez, {Samuel J.} and Enrique Alfaro and Luis Bujanda and Manuel Pab{\'o}n-Carrasco and Luis Hern{\'a}ndez and Antonio Gasbarrini and Juozas Kupcinskas and Frode Lerang and Smith, {Sinead M.} and Oleksiy Gridnyev and Mārcis Leja and Theodore Rokkas and Ricardo Marcos-Pinto and Antonio Me{\v s}trovi{\'c} and Wojciech Marlicz and Vladimir Milivojevic and Halis Simsek and Lumir Kunovsky and Veronika Papp and Phull, {Perminder S.} and Marino Venerito and Lyudmila Boyanova and Doron Boltin and Yaron Niv and Tamara Matysiak-Budnik and Michael Doulberis and Daniela Dobru and Vincent Lamy and Capelle, {Lisette G.} and {Nikolovska Trpchevska}, Emilija and Leticia Moreira and Anna Cano-Catal{\`a} and Pablo Parra and Francis M{\'e}graud and Colm O{\textquoteright}Morain and Ortega, {Guillermo J.} and Gisbert, {Javier P.} and {Hp-EuReg Investigators}",

note = "Funding Information: This project was promoted and funded by the European Helicobacter and Microbiota Study Group (EHMSG), the Spanish Association of Gastroenterology (AEG), and the Centro de Investigaci{\'o}n Biom{\'e}dica en Red de Enfermedades Hep{\'a}ticas y Digestivas (CIBERehd). The Hp-EuReg was co-funded by the European Union programme HORIZON (grant agreement number 101095359) and supported by the UK Research and Innovation (grant agreement number 10058099). The Hp-EuReg was co-funded by the European Union programme EU4Health (grant agreement number 101101252). This study was funded by Richen; however, clinical data were not accessible, and the company was not involved in any stage of the Hp-EuReg study (design, data collection, statistical analysis, or manuscript writing). We want to thank Richen for their support. ",

year = "2023",

month = sep,

day = "10",

doi = "10.3390/antibiotics12091427",

language = "English",

volume = "12",

journal = "Antibiotics",

issn = "2079-6382",

publisher = "MDPI",

number = "9",

}

TY - JOUR

T1 - Analysis of Clinical Phenotypes through Machine Learning of First-Line H. pylori Treatment in Europe during the Period 2013–2022

T2 - Data from the European Registry on H. pylori Management (Hp-EuReg)

AU - Nyssen, Olga P.

AU - Pratesi, Pietro

AU - Spínola, Miguel A.

AU - Jonaitis, Laimas

AU - Pérez-Aísa, Ángeles

AU - Vaira, Dino

AU - Saracino, Ilaria Maria

AU - Pavoni, Matteo

AU - Fiorini, Giulia

AU - Tepes, Bojan

AU - Bordin, Dmitry S.

AU - Voynovan, Irina

AU - Lanas, Ángel

AU - Martínez-Domínguez, Samuel J.

AU - Alfaro, Enrique

AU - Bujanda, Luis

AU - Pabón-Carrasco, Manuel

AU - Hernández, Luis

AU - Gasbarrini, Antonio

AU - Kupcinskas, Juozas

AU - Lerang, Frode

AU - Smith, Sinead M.

AU - Gridnyev, Oleksiy

AU - Leja, Mārcis

AU - Rokkas, Theodore

AU - Marcos-Pinto, Ricardo

AU - Meštrović, Antonio

AU - Marlicz, Wojciech

AU - Milivojevic, Vladimir

AU - Simsek, Halis

AU - Kunovsky, Lumir

AU - Papp, Veronika

AU - Phull, Perminder S.

AU - Venerito, Marino

AU - Boyanova, Lyudmila

AU - Boltin, Doron

AU - Niv, Yaron

AU - Matysiak-Budnik, Tamara

AU - Doulberis, Michael

AU - Dobru, Daniela

AU - Lamy, Vincent

AU - Capelle, Lisette G.

AU - Nikolovska Trpchevska, Emilija

AU - Moreira, Leticia

AU - Cano-Català, Anna

AU - Parra, Pablo

AU - Mégraud, Francis

AU - O’Morain, Colm

AU - Ortega, Guillermo J.

AU - Gisbert, Javier P.

AU - Hp-EuReg Investigators

N1 - Funding Information: This project was promoted and funded by the European Helicobacter and Microbiota Study Group (EHMSG), the Spanish Association of Gastroenterology (AEG), and the Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBERehd). The Hp-EuReg was co-funded by the European Union programme HORIZON (grant agreement number 101095359) and supported by the UK Research and Innovation (grant agreement number 10058099). The Hp-EuReg was co-funded by the European Union programme EU4Health (grant agreement number 101101252). This study was funded by Richen; however, clinical data were not accessible, and the company was not involved in any stage of the Hp-EuReg study (design, data collection, statistical analysis, or manuscript writing). We want to thank Richen for their support.

PY - 2023/9/10

Y1 - 2023/9/10

N2 - The segmentation of patients into homogeneous groups could help to improve eradication therapy effectiveness. Our aim was to determine the most important treatment strategies used in Europe, to evaluate first-line treatment effectiveness according to year and country. Data collection: All first-line empirical treatments registered at AEGREDCap in the European Registry on Helicobacter pylori management (Hp-EuReg) from June 2013 to November 2022. A Boruta method determined the “most important” variables related to treatment effectiveness. Data clustering was performed through multi-correspondence analysis of the resulting six most important variables for every year in the 2013–2022 period. Based on 35,852 patients, the average overall treatment effectiveness increased from 87% in 2013 to 93% in 2022. The lowest effectiveness (80%) was obtained in 2016 in cluster #3 encompassing Slovenia, Lithuania, Latvia, and Russia, treated with 7-day triple therapy with amoxicillin–clarithromycin (92% of cases). The highest effectiveness (95%) was achieved in 2022, mostly in Spain (81%), with the bismuth–quadruple therapy, including the single-capsule (64%) and the concomitant treatment with clarithromycin–amoxicillin–metronidazole/tinidazole (34%) with 10 (69%) and 14 (32%) days. Cluster analysis allowed for the identification of patients in homogeneous treatment groups assessing the effectiveness of different first-line treatments depending on therapy scheme, adherence, country, and prescription year.

AB - The segmentation of patients into homogeneous groups could help to improve eradication therapy effectiveness. Our aim was to determine the most important treatment strategies used in Europe, to evaluate first-line treatment effectiveness according to year and country. Data collection: All first-line empirical treatments registered at AEGREDCap in the European Registry on Helicobacter pylori management (Hp-EuReg) from June 2013 to November 2022. A Boruta method determined the “most important” variables related to treatment effectiveness. Data clustering was performed through multi-correspondence analysis of the resulting six most important variables for every year in the 2013–2022 period. Based on 35,852 patients, the average overall treatment effectiveness increased from 87% in 2013 to 93% in 2022. The lowest effectiveness (80%) was obtained in 2016 in cluster #3 encompassing Slovenia, Lithuania, Latvia, and Russia, treated with 7-day triple therapy with amoxicillin–clarithromycin (92% of cases). The highest effectiveness (95%) was achieved in 2022, mostly in Spain (81%), with the bismuth–quadruple therapy, including the single-capsule (64%) and the concomitant treatment with clarithromycin–amoxicillin–metronidazole/tinidazole (34%) with 10 (69%) and 14 (32%) days. Cluster analysis allowed for the identification of patients in homogeneous treatment groups assessing the effectiveness of different first-line treatments depending on therapy scheme, adherence, country, and prescription year.

KW - clustering

KW - eradication

KW - Helicobacter pylori

KW - machine learning

KW - phenotyping

KW - treatment

UR - http://www.scopus.com/inward/record.url?scp=85172216208&partnerID=8YFLogxK

U2 - 10.3390/antibiotics12091427

DO - 10.3390/antibiotics12091427

M3 - Article

AN - SCOPUS:85172216208

SN - 2079-6382

VL - 12

JO - Antibiotics

JF - Antibiotics

IS - 9

M1 - 1427

ER -

Analysis of Clinical Phenotypes through Machine Learning of First-Line H. pylori Treatment in Europe during the Period 2013–2022: Data from the European Registry on H. pylori Management (Hp-EuReg)

Abstract

Bibliographical note

Data Availability Statement

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this