-
Je něco špatně v tomto záznamu ?
Machine-learning-based prediction of disability progression in multiple sclerosis: An observational, international, multi-center study
E. De Brouwer, T. Becker, L. Werthen-Brabants, P. Dewulf, D. Iliadis, C. Dekeyser, G. Laureys, B. Van Wijmeersch, V. Popescu, T. Dhaene, D. Deschrijver, W. Waegeman, B. De Baets, M. Stock, D. Horakova, F. Patti, G. Izquierdo, S. Eichau, M....
Status neindexováno Jazyk angličtina Země Spojené státy americké
Typ dokumentu časopisecké články
NLK
Directory of Open Access Journals
od 2022
Public Library of Science (PLoS)
od 2021
PubMed Central
od 2022
ProQuest Central
od 2022-02-01
Health & Medicine (ProQuest)
od 2022-02-01
Public Health Database (ProQuest)
od 2022-02-01
ROAD: Directory of Open Access Scholarly Resources
od 2022
- Publikační typ
- časopisecké články MeSH
BACKGROUND: Disability progression is a key milestone in the disease evolution of people with multiple sclerosis (PwMS). Prediction models of the probability of disability progression have not yet reached the level of trust needed to be adopted in the clinic. A common benchmark to assess model development in multiple sclerosis is also currently lacking. METHODS: Data of adult PwMS with a follow-up of at least three years from 146 MS centers, spread over 40 countries and collected by the MSBase consortium was used. With basic inclusion criteria for quality requirements, it represents a total of 15, 240 PwMS. External validation was performed and repeated five times to assess the significance of the results. Transparent Reporting for Individual Prognosis Or Diagnosis (TRIPOD) guidelines were followed. Confirmed disability progression after two years was predicted, with a confirmation window of six months. Only routinely collected variables were used such as the expanded disability status scale, treatment, relapse information, and MS course. To learn the probability of disability progression, state-of-the-art machine learning models were investigated. The discrimination performance of the models is evaluated with the area under the receiver operator curve (ROC-AUC) and under the precision recall curve (AUC-PR), and their calibration via the Brier score and the expected calibration error. All our preprocessing and model code are available at https://gitlab.com/edebrouwer/ms_benchmark, making this task an ideal benchmark for predicting disability progression in MS. FINDINGS: Machine learning models achieved a ROC-AUC of 0⋅71 ± 0⋅01, an AUC-PR of 0⋅26 ± 0⋅02, a Brier score of 0⋅1 ± 0⋅01 and an expected calibration error of 0⋅07 ± 0⋅04. The history of disability progression was identified as being more predictive for future disability progression than the treatment or relapses history. CONCLUSIONS: Good discrimination and calibration performance on an external validation set is achieved, using only routinely collected variables. This suggests machine-learning models can reliably inform clinicians about the future occurrence of progression and are mature for a clinical impact study.
1 Biostat Hasselt University Belgium
AHEPA University Hospital Thessaloniki Greece
American University of Beirut Medical Center Beirut Lebanon
AZ Alma Ziekenhuis Sijsele Damme Belgium
Azienda Ospedaliera di Rilievo Nazionale San Giuseppe Moscati Avellino Avellino Italy
Azienda Sanitaria Unica Regionale Marche AV3 Macerata Italy
Bakirkoy Education and Research Hospital for Psychiatric and Neurological Diseases Istanbul Turkey
BAZ County Hospital Miskolc Hungary
Biobix Department of Data Analysis and Mathematical Modelling Ghent University Belgium
Biomedical Research Institute Hasselt University Belgium
Box Hill Hospital Melbourne Australia
Brain Ghent University Belgium
Centro Hospitalar Universitario de Sao Joao Porto Portugal
Charles University Prague and General University Hospital Prague Czech Republic
CHUM and Université de Montreal Montreal Canada
CISSS Chaudière Appalache Levis Canada
Cliniques Universitaires Saint Luc Brussels Belgium
College of Medicine and Health Sciences and Sultan Qaboos University Hospital SQU Oman
Concord Repatriation General Hospital Sydney Australia
CORe Department of Medicine University of Melbourne Melbourne Australia
Data Science Institute Hasselt University Belgium
Department of Medical and Surgical Sciences and Advanced Technologies GF Ingrassia Catania Italy
Department of Neurology Buffalo General Medical Center Buffalo United States of America
Department of Neurology Ghent University Belgium
Dept of Rehabilitation CRFF Mons Luigi Novarese Moncrivello Italy
ESAT STADIUS KU Leuven Belgium
Geneva University Hospital Geneva Switzerland
Groene Hart Ziekenhuis Gouda Netherlands
Hospital Clinic de Barcelona Barcelona Spain
Hospital de Galdakao Usansolo Galdakao Spain
Hospital Fernandez Capital Federal Argentina
Hospital General Universitario de Alicante Alicante Spain
Hospital Universitario Donostia San Sebastián Spain
Hospital Universitario Virgen Macarena Sevilla Spain
Jahn Ferenc Teaching Hospital Budapest Hungary
KERMIT Department of Data Analysis and Mathematical Modelling Ghent University Belgium
King Fahad Specialist Hospital Dammam Khobar Saudi Arabia
Koc University School of Medicine Istanbul Turkey
Liverpool Hospital Sydney Australia
Mater Dei Hospital Msida Malta
Mayis University Samsun Turkey
Melbourne MS Centre Department of Neurology Royal Melbourne Hospital Melbourne Australia
MS center UOC Neurologia ARNAS Garibaldi Catania Italy
Nemocnice Jihlava Jihlava Czech Republic
Noorderhart ziekenhuizen Pelt Belgium
Ospedali Riuniti di Salerno Salerno Italy
Royal Hobart Hospital Hobart Australia
Royal Victoria Hospital Belfast United Kingdom
School for Mental Health and Neuroscience Maastricht University Maastricht The Netherlands
Semmelweis University Budapest Budapest Hungary
South Eastern HSC Trust Belfast United Kingdom
St Michael's Hospital Toronto Canada
St Vincent's University Hospital Dublin Ireland
SUMO IDLAB Ghent University imec Belgium
The Alfred Hospital Melbourne Australia
Universidade Metropolitana de Santos Santos Brazil
Universitair MS Centrum Hasselt Pelt Belgium
Universitary Hospital Ghent Ghent Belgium
University Hospital Reina Sofia Cordoba Spain
University Newcastle Newcastle Australia
Citace poskytuje Crossref.org
- 000
- 00000naa a2200000 a 4500
- 001
- bmc24018163
- 003
- CZ-PrNML
- 005
- 20241016082012.0
- 007
- ta
- 008
- 241008s2024 xxu f 000 0|eng||
- 009
- AR
- 024 7_
- $a 10.1371/journal.pdig.0000533 $2 doi
- 035 __
- $a (PubMed)39052668
- 040 __
- $a ABA008 $b cze $d ABA008 $e AACR2
- 041 0_
- $a eng
- 044 __
- $a xxu
- 100 1_
- $a De Brouwer, Edward $u ESAT-STADIUS, KU Leuven, Belgium $1 https://orcid.org/0000000306080155
- 245 10
- $a Machine-learning-based prediction of disability progression in multiple sclerosis: An observational, international, multi-center study / $c E. De Brouwer, T. Becker, L. Werthen-Brabants, P. Dewulf, D. Iliadis, C. Dekeyser, G. Laureys, B. Van Wijmeersch, V. Popescu, T. Dhaene, D. Deschrijver, W. Waegeman, B. De Baets, M. Stock, D. Horakova, F. Patti, G. Izquierdo, S. Eichau, M. Girard, A. Prat, A. Lugaresi, P. Grammond, T. Kalincik, R. Alroughani, F. Grand'Maison, O. Skibina, M. Terzi, J. Lechner-Scott, O. Gerlach, SJ. Khoury, E. Cartechini, V. Van Pesch, MJ. Sà, B. Weinstock-Guttman, Y. Blanco, R. Ampapa, D. Spitaleri, C. Solaro, D. Maimone, A. Soysal, G. Iuliano, R. Gouider, T. Castillo-Triviño, JL. Sánchez-Menoyo, G. Laureys, A. van der Walt, J. Oh, E. Aguera-Morales, A. Altintas, A. Al-Asmi, K. de Gans, Y. Fragoso, T. Csepany, S. Hodgkinson, N. Deri, T. Al-Harbi, B. Taylor, O. Gray, P. Lalive, C. Rozsa, C. McGuigan, A. Kermode, AP. Sempere, S. Mihaela, M. Simo, T. Hardy, D. Decoo, S. Hughes, N. Grigoriadis, A. Sas, N. Vella, Y. Moreau, L. Peeters
- 520 9_
- $a BACKGROUND: Disability progression is a key milestone in the disease evolution of people with multiple sclerosis (PwMS). Prediction models of the probability of disability progression have not yet reached the level of trust needed to be adopted in the clinic. A common benchmark to assess model development in multiple sclerosis is also currently lacking. METHODS: Data of adult PwMS with a follow-up of at least three years from 146 MS centers, spread over 40 countries and collected by the MSBase consortium was used. With basic inclusion criteria for quality requirements, it represents a total of 15, 240 PwMS. External validation was performed and repeated five times to assess the significance of the results. Transparent Reporting for Individual Prognosis Or Diagnosis (TRIPOD) guidelines were followed. Confirmed disability progression after two years was predicted, with a confirmation window of six months. Only routinely collected variables were used such as the expanded disability status scale, treatment, relapse information, and MS course. To learn the probability of disability progression, state-of-the-art machine learning models were investigated. The discrimination performance of the models is evaluated with the area under the receiver operator curve (ROC-AUC) and under the precision recall curve (AUC-PR), and their calibration via the Brier score and the expected calibration error. All our preprocessing and model code are available at https://gitlab.com/edebrouwer/ms_benchmark, making this task an ideal benchmark for predicting disability progression in MS. FINDINGS: Machine learning models achieved a ROC-AUC of 0⋅71 ± 0⋅01, an AUC-PR of 0⋅26 ± 0⋅02, a Brier score of 0⋅1 ± 0⋅01 and an expected calibration error of 0⋅07 ± 0⋅04. The history of disability progression was identified as being more predictive for future disability progression than the treatment or relapses history. CONCLUSIONS: Good discrimination and calibration performance on an external validation set is achieved, using only routinely collected variables. This suggests machine-learning models can reliably inform clinicians about the future occurrence of progression and are mature for a clinical impact study.
- 590 __
- $a NEINDEXOVÁNO
- 655 _2
- $a časopisecké články $7 D016428
- 700 1_
- $a Becker, Thijs $u I-Biostat, Hasselt University, Belgium $u Data Science Institute, Hasselt University, Belgium
- 700 1_
- $a Werthen-Brabants, Lorin $u SUMO, IDLAB, Ghent University - imec, Belgium
- 700 1_
- $a Dewulf, Pieter $u KERMIT, Department of Data Analysis and Mathematical Modelling, Ghent University, Belgium $1 https://orcid.org/0000000345641672
- 700 1_
- $a Iliadis, Dimitrios $u KERMIT, Department of Data Analysis and Mathematical Modelling, Ghent University, Belgium
- 700 1_
- $a Dekeyser, Cathérine $u Department of Neurology, Ghent University, Belgium $u 4 Brain, Ghent University, Belgium $u Biomedical Research Institute, Hasselt University, Belgium
- 700 1_
- $a Laureys, Guy $u Department of Neurology, Ghent University, Belgium $u 4 Brain, Ghent University, Belgium
- 700 1_
- $a Van Wijmeersch, Bart $u Noorderhart ziekenhuizen Pelt, Belgium $u Universitair MS Centrum Hasselt-Pelt, Belgium
- 700 1_
- $a Popescu, Veronica $u Noorderhart ziekenhuizen Pelt, Belgium $u Universitair MS Centrum Hasselt-Pelt, Belgium
- 700 1_
- $a Dhaene, Tom $u SUMO, IDLAB, Ghent University - imec, Belgium
- 700 1_
- $a Deschrijver, Dirk $u SUMO, IDLAB, Ghent University - imec, Belgium
- 700 1_
- $a Waegeman, Willem $u KERMIT, Department of Data Analysis and Mathematical Modelling, Ghent University, Belgium
- 700 1_
- $a De Baets, Bernard $u KERMIT, Department of Data Analysis and Mathematical Modelling, Ghent University, Belgium
- 700 1_
- $a Stock, Michiel $u KERMIT, Department of Data Analysis and Mathematical Modelling, Ghent University, Belgium $u Biobix, Department of Data Analysis and Mathematical Modelling, Ghent University, Belgium
- 700 1_
- $a Horakova, Dana $u Charles University in Prague and General University Hospital, Prague, Czech Republic
- 700 1_
- $a Patti, Francesco $u Department of Medical and Surgical Sciences and Advanced Technologies, GF Ingrassia, Catania, Italy
- 700 1_
- $a Izquierdo, Guillermo $u Hospital Universitario Virgen Macarena, Sevilla, Spain
- 700 1_
- $a Eichau, Sara $u Hospital Universitario Virgen Macarena, Sevilla, Spain
- 700 1_
- $a Girard, Marc $u CHUM and Université de Montreal, Montreal, Canada
- 700 1_
- $a Prat, Alexandre $u CHUM and Université de Montreal, Montreal, Canada
- 700 1_
- $a Lugaresi, Alessandra $u IRCCS Istituto delle Scienze Neurologiche di Bologna, Bologna, Italia and Dipartimento di Scienze Biomediche e Neuromotorie, Università di Bologna, Bologna, Italia $1 https://orcid.org/0000000329025589
- 700 1_
- $a Grammond, Pierre $u CISSS Chaudière-Appalache, Levis, Canada
- 700 1_
- $a Kalincik, Tomas $u Melbourne MS Centre, Department of Neurology, Royal Melbourne Hospital, Melbourne, Australia $u CORe, Department of Medicine, University of Melbourne, Melbourne, Australia
- 700 1_
- $a Alroughani, Raed $u Amiri Hospital, Sharq, Kuwait
- 700 1_
- $a Grand'Maison, Francois $u Neuro Rive-Sud, Quebec, Canada
- 700 1_
- $a Skibina, Olga $u Box Hill Hospital, Melbourne, Australia
- 700 1_
- $a Terzi, Murat $u 19 Mayis University, Samsun, Turkey
- 700 1_
- $a Lechner-Scott, Jeannette $u University Newcastle, Newcastle, Australia
- 700 1_
- $a Gerlach, Oliver $u Academic MS Center Zuyderland, Department of Neurology, Zuyderland Medical Center, Sittard-Geleen, The Netherlands $u School for Mental Health and Neuroscience, Maastricht University, Maastricht, The Netherlands
- 700 1_
- $a Khoury, Samia J $u American University of Beirut Medical Center, Beirut, Lebanon
- 700 1_
- $a Cartechini, Elisabetta $u Azienda Sanitaria Unica Regionale Marche - AV3, Macerata, Italy
- 700 1_
- $a Van Pesch, Vincent $u Cliniques Universitaires Saint-Luc, Brussels, Belgium
- 700 1_
- $a Sà, Maria José $u Centro Hospitalar Universitario de Sao Joao, Porto, Portugal
- 700 1_
- $a Weinstock-Guttman, Bianca $u Department of Neurology, Buffalo General Medical Center, Buffalo, United States of America
- 700 1_
- $a Blanco, Yolanda $u Hospital Clinic de Barcelona, Barcelona, Spain
- 700 1_
- $a Ampapa, Radek $u Nemocnice Jihlava, Jihlava, Czech Republic
- 700 1_
- $a Spitaleri, Daniele $u Azienda Ospedaliera di Rilievo Nazionale San Giuseppe Moscati Avellino, Avellino, Italy
- 700 1_
- $a Solaro, Claudio $u Dept. of Rehabilitation, CRFF Mons. Luigi Novarese, Moncrivello, Italy
- 700 1_
- $a Maimone, Davide $u MS center, UOC Neurologia, ARNAS Garibaldi, Catania, Italy
- 700 1_
- $a Soysal, Aysun $u Bakirkoy Education and Research Hospital for Psychiatric and Neurological Diseases, Istanbul, Turkey
- 700 1_
- $a Iuliano, Gerardo $u Ospedali Riuniti di Salerno, Salerno, Italy
- 700 1_
- $a Gouider, Riadh $u Razi Hospital, Manouba, Tunisia
- 700 1_
- $a Castillo-Triviño, Tamara $u Hospital Universitario Donostia, San Sebastián, Spain $1 https://orcid.org/0000000292493185
- 700 1_
- $a Sánchez-Menoyo, José Luis $u Hospital de Galdakao-Usansolo, Galdakao, Spain
- 700 1_
- $a Laureys, Guy $u Universitary Hospital Ghent, Ghent, Belgium
- 700 1_
- $a van der Walt, Anneke $u The Alfred Hospital, Melbourne, Australia
- 700 1_
- $a Oh, Jiwon $u St. Michael's Hospital, Toronto, Canada
- 700 1_
- $a Aguera-Morales, Eduardo $u University Hospital Reina Sofia, Cordoba, Spain
- 700 1_
- $a Altintas, Ayse $u Koc University, School of Medicine, Istanbul, Turkey
- 700 1_
- $a Al-Asmi, Abdullah $u College of Medicine & Health Sciences and Sultan Qaboos University Hospital, SQU, Oman $1 https://orcid.org/0000000228518157
- 700 1_
- $a de Gans, Koen $u Groene Hart Ziekenhuis, Gouda, Netherlands
- 700 1_
- $a Fragoso, Yara $u Universidade Metropolitana de Santos, Santos, Brazil
- 700 1_
- $a Csepany, Tunde $u University of Debrecen, Debrecen, Hungary $1 https://orcid.org/0000000283053209
- 700 1_
- $a Hodgkinson, Suzanne $u Liverpool Hospital, Sydney, Australia
- 700 1_
- $a Deri, Norma $u Hospital Fernandez, Capital Federal, Argentina
- 700 1_
- $a Al-Harbi, Talal $u King Fahad Specialist Hospital-Dammam, Khobar, Saudi Arabia
- 700 1_
- $a Taylor, Bruce $u Royal Hobart Hospital, Hobart, Australia
- 700 1_
- $a Gray, Orla $u South Eastern HSC Trust, Belfast, United Kingdom
- 700 1_
- $a Lalive, Patrice $u Geneva University Hospital, Geneva, Switzerland
- 700 1_
- $a Rozsa, Csilla $u Jahn Ferenc Teaching Hospital, Budapest, Hungary
- 700 1_
- $a McGuigan, Chris $u St Vincent's University Hospital, Dublin, Ireland
- 700 1_
- $a Kermode, Allan $u University of Western Australia, Nedlands, Australia $1 https://orcid.org/0000000244764016
- 700 1_
- $a Sempere, Angel Pérez $u Hospital General Universitario de Alicante, Alicante, Spain
- 700 1_
- $a Mihaela, Simu $u Emergency Clinical County Hospital Pius Brinzeu, Timisoara, Romania and University of Medicine and Pharmacy Victor Babes, Timisoara, Romania
- 700 1_
- $a Simo, Magdolna $u Semmelweis University Budapest, Budapest, Hungary
- 700 1_
- $a Hardy, Todd $u Concord Repatriation General Hospital, Sydney, Australia
- 700 1_
- $a Decoo, Danny $u AZ Alma Ziekenhuis, Sijsele - Damme, Belgium
- 700 1_
- $a Hughes, Stella $u Royal Victoria Hospital, Belfast, United Kingdom
- 700 1_
- $a Grigoriadis, Nikolaos $u AHEPA University Hospital, Thessaloniki, Greece
- 700 1_
- $a Sas, Attila $u BAZ County Hospital, Miskolc, Hungary
- 700 1_
- $a Vella, Norbert $u Mater Dei Hospital, Msida, Malta
- 700 1_
- $a Moreau, Yves $u ESAT-STADIUS, KU Leuven, Belgium
- 700 1_
- $a Peeters, Liesbet $u Data Science Institute, Hasselt University, Belgium $u Universitair MS Centrum Hasselt-Pelt, Belgium $1 https://orcid.org/0000000260663899
- 773 0_
- $w MED00215633 $t PLOS digital health $x 2767-3170 $g Roč. 3, č. 7 (2024), s. e0000533
- 856 41
- $u https://pubmed.ncbi.nlm.nih.gov/39052668 $y Pubmed
- 910 __
- $a ABA008 $b sig $c sign $y - $z 0
- 990 __
- $a 20241008 $b ABA008
- 991 __
- $a 20241016082007 $b ABA008
- 999 __
- $a ok $b bmc $g 2196482 $s 1230114
- BAS __
- $a 3
- BAS __
- $a PreBMC-PubMed-not-MEDLINE
- BMC __
- $a 2024 $b 3 $c 7 $d e0000533 $e 20240725 $i 2767-3170 $m PLOS digital health $n PLOS Digit Health $x MED00215633
- LZP __
- $a Pubmed-20241008
