Predicting progression events in multiple myeloma from routine blood work

Abstract This study introduces a system for predicting disease progression events in multiple myeloma patients from the CoMMpass study (N = 1186). Utilizing a hybrid neural network architecture, our model predicts future blood work from historical lab results with high accuracy, significantly outper...

Full description

Saved in:
Bibliographic Details
Main Authors: Maximilian Ferle, Nora Grieb, Markus Kreuz, Jonas Ader, Hartmut Goldschmidt, Elias K. Mai, Uta Bertsch, Uwe Platzbecker, Thomas Neumuth, Kristin Reiche, Alexander Oeser, Maximilian Merz
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01636-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850231101674487808
author Maximilian Ferle
Nora Grieb
Markus Kreuz
Jonas Ader
Hartmut Goldschmidt
Elias K. Mai
Uta Bertsch
Uwe Platzbecker
Thomas Neumuth
Kristin Reiche
Alexander Oeser
Maximilian Merz
author_facet Maximilian Ferle
Nora Grieb
Markus Kreuz
Jonas Ader
Hartmut Goldschmidt
Elias K. Mai
Uta Bertsch
Uwe Platzbecker
Thomas Neumuth
Kristin Reiche
Alexander Oeser
Maximilian Merz
author_sort Maximilian Ferle
collection DOAJ
description Abstract This study introduces a system for predicting disease progression events in multiple myeloma patients from the CoMMpass study (N = 1186). Utilizing a hybrid neural network architecture, our model predicts future blood work from historical lab results with high accuracy, significantly outperforming baseline estimators for key disease parameters. Disease progression events are annotated in the forecasted data, predicting these events with significant reliability. We externally validated our model using the GMMG-MM5 study dataset (N = 504), and could reproduce the main results of our study. Our approach enables early detection and personalized monitoring of patients at risk of impeding progression. Designed modularly, our system enhances interpretability, facilitates integration of additional modules, and uses routine blood work measurements to ensure accessibility in clinical settings. With this, we contribute to the development of a scalable, cost-effective virtual human twin system for optimized healthcare resource utilization and improved outcomes in multiple myeloma patient care.
format Article
id doaj-art-b00a2c8dad6e4d128d7a8c95c270d8b4
institution OA Journals
issn 2398-6352
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-b00a2c8dad6e4d128d7a8c95c270d8b42025-08-20T02:03:39ZengNature Portfolionpj Digital Medicine2398-63522025-04-018111510.1038/s41746-025-01636-9Predicting progression events in multiple myeloma from routine blood workMaximilian Ferle0Nora Grieb1Markus Kreuz2Jonas Ader3Hartmut Goldschmidt4Elias K. Mai5Uta Bertsch6Uwe Platzbecker7Thomas Neumuth8Kristin Reiche9Alexander Oeser10Maximilian Merz11Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Universität LeipzigInnovation Center Computer Assisted Surgery (ICCAS), University of LeipzigDepartment of Medical Bioinformatics, Fraunhofer Institute for Cell Therapy and ImmunologyCenter for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Universität LeipzigDepartment of Internal Medicine V, University Hospital HeidelbergDepartment of Internal Medicine V, University Hospital HeidelbergDepartment of Internal Medicine V, University Hospital HeidelbergDepartment of Hematology, Hemostaseology, Cellular Therapy and Infectiology, University Hospital of LeipzigCenter for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Universität LeipzigCenter for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Universität LeipzigInnovation Center Computer Assisted Surgery (ICCAS), University of LeipzigDepartment of Hematology, Hemostaseology, Cellular Therapy and Infectiology, University Hospital of LeipzigAbstract This study introduces a system for predicting disease progression events in multiple myeloma patients from the CoMMpass study (N = 1186). Utilizing a hybrid neural network architecture, our model predicts future blood work from historical lab results with high accuracy, significantly outperforming baseline estimators for key disease parameters. Disease progression events are annotated in the forecasted data, predicting these events with significant reliability. We externally validated our model using the GMMG-MM5 study dataset (N = 504), and could reproduce the main results of our study. Our approach enables early detection and personalized monitoring of patients at risk of impeding progression. Designed modularly, our system enhances interpretability, facilitates integration of additional modules, and uses routine blood work measurements to ensure accessibility in clinical settings. With this, we contribute to the development of a scalable, cost-effective virtual human twin system for optimized healthcare resource utilization and improved outcomes in multiple myeloma patient care.https://doi.org/10.1038/s41746-025-01636-9
spellingShingle Maximilian Ferle
Nora Grieb
Markus Kreuz
Jonas Ader
Hartmut Goldschmidt
Elias K. Mai
Uta Bertsch
Uwe Platzbecker
Thomas Neumuth
Kristin Reiche
Alexander Oeser
Maximilian Merz
Predicting progression events in multiple myeloma from routine blood work
npj Digital Medicine
title Predicting progression events in multiple myeloma from routine blood work
title_full Predicting progression events in multiple myeloma from routine blood work
title_fullStr Predicting progression events in multiple myeloma from routine blood work
title_full_unstemmed Predicting progression events in multiple myeloma from routine blood work
title_short Predicting progression events in multiple myeloma from routine blood work
title_sort predicting progression events in multiple myeloma from routine blood work
url https://doi.org/10.1038/s41746-025-01636-9
work_keys_str_mv AT maximilianferle predictingprogressioneventsinmultiplemyelomafromroutinebloodwork
AT noragrieb predictingprogressioneventsinmultiplemyelomafromroutinebloodwork
AT markuskreuz predictingprogressioneventsinmultiplemyelomafromroutinebloodwork
AT jonasader predictingprogressioneventsinmultiplemyelomafromroutinebloodwork
AT hartmutgoldschmidt predictingprogressioneventsinmultiplemyelomafromroutinebloodwork
AT eliaskmai predictingprogressioneventsinmultiplemyelomafromroutinebloodwork
AT utabertsch predictingprogressioneventsinmultiplemyelomafromroutinebloodwork
AT uweplatzbecker predictingprogressioneventsinmultiplemyelomafromroutinebloodwork
AT thomasneumuth predictingprogressioneventsinmultiplemyelomafromroutinebloodwork
AT kristinreiche predictingprogressioneventsinmultiplemyelomafromroutinebloodwork
AT alexanderoeser predictingprogressioneventsinmultiplemyelomafromroutinebloodwork
AT maximilianmerz predictingprogressioneventsinmultiplemyelomafromroutinebloodwork