Machine learning for precision diagnostics of autoimmunity

Abstract Early and accurate diagnosis is crucial to prevent disease development and define therapeutic strategies. Due to predominantly unspecific symptoms, diagnosis of autoimmune diseases (AID) is notoriously challenging. Clinical decision support systems (CDSS) are a promising method with the pot...

Full description

Saved in:
Bibliographic Details
Main Authors: Jan Kruta, Raphael Carapito, Marten Trendelenburg, Thierry Martin, Marta Rizzi, Reinhard E. Voll, Andrea Cavalli, Eriberto Natali, Patrick Meier, Marc Stawiski, Johannes Mosbacher, Annette Mollet, Aurelia Santoro, Miriam Capri, Enrico Giampieri, Erik Schkommodau, Enkelejda Miho
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-76093-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846165329942675456
author Jan Kruta
Raphael Carapito
Marten Trendelenburg
Thierry Martin
Marta Rizzi
Reinhard E. Voll
Andrea Cavalli
Eriberto Natali
Patrick Meier
Marc Stawiski
Johannes Mosbacher
Annette Mollet
Aurelia Santoro
Miriam Capri
Enrico Giampieri
Erik Schkommodau
Enkelejda Miho
author_facet Jan Kruta
Raphael Carapito
Marten Trendelenburg
Thierry Martin
Marta Rizzi
Reinhard E. Voll
Andrea Cavalli
Eriberto Natali
Patrick Meier
Marc Stawiski
Johannes Mosbacher
Annette Mollet
Aurelia Santoro
Miriam Capri
Enrico Giampieri
Erik Schkommodau
Enkelejda Miho
author_sort Jan Kruta
collection DOAJ
description Abstract Early and accurate diagnosis is crucial to prevent disease development and define therapeutic strategies. Due to predominantly unspecific symptoms, diagnosis of autoimmune diseases (AID) is notoriously challenging. Clinical decision support systems (CDSS) are a promising method with the potential to enhance and expedite precise diagnostics by physicians. However, due to the difficulties of integrating and encoding multi-omics data with clinical values, as well as a lack of standardization, such systems are often limited to certain data types. Accordingly, even sophisticated data models fall short when making accurate disease diagnoses and presenting data analyses in a user-friendly form. Therefore, the integration of various data types is not only an opportunity but also a competitive advantage for research and industry. We have developed an integration pipeline to enable the use of machine learning for patient classification based on multi-omics data in combination with clinical values and laboratory results. The application of our framework resulted in up to 96% prediction accuracy of autoimmune diseases with machine learning models. Our results deliver insights into autoimmune disease research and have the potential to be adapted for applications across disease conditions.
format Article
id doaj-art-6b14c84f193c4cfea08961e9233c5fa1
institution Kabale University
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-6b14c84f193c4cfea08961e9233c5fa12024-11-17T12:22:08ZengNature PortfolioScientific Reports2045-23222024-11-0114111510.1038/s41598-024-76093-7Machine learning for precision diagnostics of autoimmunityJan Kruta0Raphael Carapito1Marten Trendelenburg2Thierry Martin3Marta Rizzi4Reinhard E. Voll5Andrea Cavalli6Eriberto Natali7Patrick Meier8Marc Stawiski9Johannes Mosbacher10Annette Mollet11Aurelia Santoro12Miriam Capri13Enrico Giampieri14Erik Schkommodau15Enkelejda Miho16School of Life Sciences, FHNW University of Applied Sciences and Arts Northwestern SwitzerlandLaboratoire d’ImmunoRhumatologie Moléculaire, plateforme GENOMAX, Faculté de Médecine, Fédération de Médecine Translationnelle de Strasbourg (FMTS), Institut Thématique Interdisciplinaire TRANSPLANTEX NG, INSERM UMR_S 1109, Fédération Hospitalo-Universitaire OMICARE, Université de StrasbourgDivision of Internal Medicine, University Hospital BaselLaboratoire d’ImmunoRhumatologie Moléculaire, plateforme GENOMAX, Faculté de Médecine, Fédération de Médecine Translationnelle de Strasbourg (FMTS), Institut Thématique Interdisciplinaire TRANSPLANTEX NG, INSERM UMR_S 1109, Fédération Hospitalo-Universitaire OMICARE, Université de StrasbourgDepartment of Rheumatology and Clinical Immunology, Medical Center, University of FreiburgDepartment of Rheumatology and Clinical Immunology, Medical Center, University of FreiburgFaBiT Department of Pharmacy and Biotechnology, Università di BolognaSchool of Life Sciences, FHNW University of Applied Sciences and Arts Northwestern SwitzerlandSchool of Life Sciences, FHNW University of Applied Sciences and Arts Northwestern SwitzerlandSchool of Life Sciences, FHNW University of Applied Sciences and Arts Northwestern SwitzerlandSchool of Life Sciences, FHNW University of Applied Sciences and Arts Northwestern SwitzerlandInstitute of Pharmaceutical Medicine, University of BaselDepartment of Experimental, Diagnostic and Specialty Medicine (DIMES), University of BolognaDepartment of Experimental, Diagnostic and Specialty Medicine (DIMES), University of BolognaDepartment of Experimental, Diagnostic and Specialty Medicine (DIMES), University of BolognaSchool of Life Sciences, FHNW University of Applied Sciences and Arts Northwestern SwitzerlandSchool of Life Sciences, FHNW University of Applied Sciences and Arts Northwestern SwitzerlandAbstract Early and accurate diagnosis is crucial to prevent disease development and define therapeutic strategies. Due to predominantly unspecific symptoms, diagnosis of autoimmune diseases (AID) is notoriously challenging. Clinical decision support systems (CDSS) are a promising method with the potential to enhance and expedite precise diagnostics by physicians. However, due to the difficulties of integrating and encoding multi-omics data with clinical values, as well as a lack of standardization, such systems are often limited to certain data types. Accordingly, even sophisticated data models fall short when making accurate disease diagnoses and presenting data analyses in a user-friendly form. Therefore, the integration of various data types is not only an opportunity but also a competitive advantage for research and industry. We have developed an integration pipeline to enable the use of machine learning for patient classification based on multi-omics data in combination with clinical values and laboratory results. The application of our framework resulted in up to 96% prediction accuracy of autoimmune diseases with machine learning models. Our results deliver insights into autoimmune disease research and have the potential to be adapted for applications across disease conditions.https://doi.org/10.1038/s41598-024-76093-7Multi-omicsAutoimmuneMachine learningEHRDiagnostics
spellingShingle Jan Kruta
Raphael Carapito
Marten Trendelenburg
Thierry Martin
Marta Rizzi
Reinhard E. Voll
Andrea Cavalli
Eriberto Natali
Patrick Meier
Marc Stawiski
Johannes Mosbacher
Annette Mollet
Aurelia Santoro
Miriam Capri
Enrico Giampieri
Erik Schkommodau
Enkelejda Miho
Machine learning for precision diagnostics of autoimmunity
Scientific Reports
Multi-omics
Autoimmune
Machine learning
EHR
Diagnostics
title Machine learning for precision diagnostics of autoimmunity
title_full Machine learning for precision diagnostics of autoimmunity
title_fullStr Machine learning for precision diagnostics of autoimmunity
title_full_unstemmed Machine learning for precision diagnostics of autoimmunity
title_short Machine learning for precision diagnostics of autoimmunity
title_sort machine learning for precision diagnostics of autoimmunity
topic Multi-omics
Autoimmune
Machine learning
EHR
Diagnostics
url https://doi.org/10.1038/s41598-024-76093-7
work_keys_str_mv AT jankruta machinelearningforprecisiondiagnosticsofautoimmunity
AT raphaelcarapito machinelearningforprecisiondiagnosticsofautoimmunity
AT martentrendelenburg machinelearningforprecisiondiagnosticsofautoimmunity
AT thierrymartin machinelearningforprecisiondiagnosticsofautoimmunity
AT martarizzi machinelearningforprecisiondiagnosticsofautoimmunity
AT reinhardevoll machinelearningforprecisiondiagnosticsofautoimmunity
AT andreacavalli machinelearningforprecisiondiagnosticsofautoimmunity
AT eribertonatali machinelearningforprecisiondiagnosticsofautoimmunity
AT patrickmeier machinelearningforprecisiondiagnosticsofautoimmunity
AT marcstawiski machinelearningforprecisiondiagnosticsofautoimmunity
AT johannesmosbacher machinelearningforprecisiondiagnosticsofautoimmunity
AT annettemollet machinelearningforprecisiondiagnosticsofautoimmunity
AT aureliasantoro machinelearningforprecisiondiagnosticsofautoimmunity
AT miriamcapri machinelearningforprecisiondiagnosticsofautoimmunity
AT enricogiampieri machinelearningforprecisiondiagnosticsofautoimmunity
AT erikschkommodau machinelearningforprecisiondiagnosticsofautoimmunity
AT enkelejdamiho machinelearningforprecisiondiagnosticsofautoimmunity