• Je něco špatně v tomto záznamu ?

Unsupervised meta-clustering identifies risk clusters in acute myeloid leukemia based on clinical and genetic profiles

JN. Eckardt, C. Röllig, K. Metzeler, P. Heisig, S. Stasik, JA. Georgi, F. Kroschinsky, F. Stölzel, U. Platzbecker, K. Spiekermann, U. Krug, J. Braess, D. Görlich, C. Sauerland, B. Woermann, T. Herold, W. Hiddemann, C. Müller-Tidow, H. Serve, CD....

. 2023 ; 3 (1) : 68. [pub] 20230517

Status neindexováno Jazyk angličtina Země Anglie, Velká Británie

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc23009752

BACKGROUND: Increasingly large and complex biomedical data sets challenge conventional hypothesis-driven analytical approaches, however, data-driven unsupervised learning can detect inherent patterns in such data sets. METHODS: While unsupervised analysis in the medical literature commonly only utilizes a single clustering algorithm for a given data set, we developed a large-scale model with 605 different combinations of target dimensionalities as well as transformation and clustering algorithms and subsequent meta-clustering of individual results. With this model, we investigated a large cohort of 1383 patients from 59 centers in Germany with newly diagnosed acute myeloid leukemia for whom 212 clinical, laboratory, cytogenetic and molecular genetic parameters were available. RESULTS: Unsupervised learning identifies four distinct patient clusters, and statistical analysis shows significant differences in rate of complete remissions, event-free, relapse-free and overall survival between the four clusters. In comparison to the standard-of-care hypothesis-driven European Leukemia Net (ELN2017) risk stratification model, we find all three ELN2017 risk categories being represented in all four clusters in varying proportions indicating unappreciated complexity of AML biology in current established risk stratification models. Further, by using assigned clusters as labels we subsequently train a supervised model to validate cluster assignments on a large external multicenter cohort of 664 intensively treated AML patients. CONCLUSIONS: Dynamic data-driven models are likely more suitable for risk stratification in the context of increasingly complex medical data than rigid hypothesis-driven models to allow for a more personalized treatment allocation and gain novel insights into disease biology.

Department of Hematology and Oncology University Hospital Schleswig Holstein Kiel Germany

Department of Hematology and Stem Cell Transplantation University Hospital Essen Essen Germany

Department of Hematology Oncology and Palliative Care Robert Bosch Hospital Stuttgart Germany

Department of Hematology Oncology and Tumor Immunology Charité Berlin Germany

Department of Internal Medicine 1 University Hospital Carl Gustav Carus Dresden Germany

Department of Internal Medicine 3 Klinikum Chemnitz GmbH Chemnitz Germany

Department of Internal Medicine 5 University Hospital Erlangen Erlangen Germany

Department of Internal Medicine 5 University Hospital Nuremberg Nuremberg Germany

Department of Internal Medicine A University Hospital Muenster Muenster Germany

Department of Internal Medicine Hematology and Oncology Masaryk University Hospital Brno Czech Republic

Department of Medicine 2 Hematology and Oncology Goethe University Frankfurt Frankfurt Germany

Department of Medicine 3 Hospital Leverkusen Leverkusen Germany

Department of Medicine 5 University Hospital Heidelberg Heidelberg Germany

Department of Software and Multimedia Technology Technical University Dresden Dresden Germany

Else Kröner Fresenius Center for Digital Health Technical University Dresden Dresden Germany

German Consortium for Translational Cancer Research DKFZ Heidelberg Germany

Hospital Barmherzige Brueder Regensburg Regensburg Germany

Institute for Biostatistics and Clinical Research University Muenster Muenster Germany

Laboratory for Leukemia Diagnostics Department of Medicine 3 University Hospital LMU Munich Munich Germany

Medical Clinic and Policlinic 1 Hematology and Cell Therapy University Hospital Leipzig Germany

National Center for Tumor Diseases Dresden Germany

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc23009752
003      
CZ-PrNML
005      
20230721095455.0
007      
ta
008      
230707s2023 enk f 000 0|eng||
009      
AR
024    7_
$a 10.1038/s43856-023-00298-6 $2 doi
035    __
$a (PubMed)37198246
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a enk
100    1_
$a Eckardt, Jan-Niklas $u Department of Internal Medicine I, University Hospital Carl Gustav Carus, Dresden, Germany. jan-niklas.eckardt@uniklinikum-dresden.de $u Else Kröner Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany. jan-niklas.eckardt@uniklinikum-dresden.de $1 https://orcid.org/0000000236492823
245    10
$a Unsupervised meta-clustering identifies risk clusters in acute myeloid leukemia based on clinical and genetic profiles / $c JN. Eckardt, C. Röllig, K. Metzeler, P. Heisig, S. Stasik, JA. Georgi, F. Kroschinsky, F. Stölzel, U. Platzbecker, K. Spiekermann, U. Krug, J. Braess, D. Görlich, C. Sauerland, B. Woermann, T. Herold, W. Hiddemann, C. Müller-Tidow, H. Serve, CD. Baldus, K. Schäfer-Eckart, M. Kaufmann, SW. Krause, M. Hänel, WE. Berdel, C. Schliemann, J. Mayer, M. Hanoun, J. Schetelig, K. Wendt, M. Bornhäuser, C. Thiede, JM. Middeke
520    9_
$a BACKGROUND: Increasingly large and complex biomedical data sets challenge conventional hypothesis-driven analytical approaches, however, data-driven unsupervised learning can detect inherent patterns in such data sets. METHODS: While unsupervised analysis in the medical literature commonly only utilizes a single clustering algorithm for a given data set, we developed a large-scale model with 605 different combinations of target dimensionalities as well as transformation and clustering algorithms and subsequent meta-clustering of individual results. With this model, we investigated a large cohort of 1383 patients from 59 centers in Germany with newly diagnosed acute myeloid leukemia for whom 212 clinical, laboratory, cytogenetic and molecular genetic parameters were available. RESULTS: Unsupervised learning identifies four distinct patient clusters, and statistical analysis shows significant differences in rate of complete remissions, event-free, relapse-free and overall survival between the four clusters. In comparison to the standard-of-care hypothesis-driven European Leukemia Net (ELN2017) risk stratification model, we find all three ELN2017 risk categories being represented in all four clusters in varying proportions indicating unappreciated complexity of AML biology in current established risk stratification models. Further, by using assigned clusters as labels we subsequently train a supervised model to validate cluster assignments on a large external multicenter cohort of 664 intensively treated AML patients. CONCLUSIONS: Dynamic data-driven models are likely more suitable for risk stratification in the context of increasingly complex medical data than rigid hypothesis-driven models to allow for a more personalized treatment allocation and gain novel insights into disease biology.
590    __
$a NEINDEXOVÁNO
655    _2
$a časopisecké články $7 D016428
700    1_
$a Röllig, Christoph $u Department of Internal Medicine I, University Hospital Carl Gustav Carus, Dresden, Germany
700    1_
$a Metzeler, Klaus $u Medical Clinic and Policlinic I Hematology and Cell Therapy, University Hospital, Leipzig, Germany $1 https://orcid.org/0000000339207490
700    1_
$a Heisig, Peter $u Department of Software and Multimedia Technology, Technical University Dresden, Dresden, Germany
700    1_
$a Stasik, Sebastian $u Department of Internal Medicine I, University Hospital Carl Gustav Carus, Dresden, Germany
700    1_
$a Georgi, Julia-Annabell $u Department of Internal Medicine I, University Hospital Carl Gustav Carus, Dresden, Germany
700    1_
$a Kroschinsky, Frank $u Department of Internal Medicine I, University Hospital Carl Gustav Carus, Dresden, Germany $1 https://orcid.org/0000000242357580
700    1_
$a Stölzel, Friedrich $u Department of Internal Medicine I, University Hospital Carl Gustav Carus, Dresden, Germany
700    1_
$a Platzbecker, Uwe $u Medical Clinic and Policlinic I Hematology and Cell Therapy, University Hospital, Leipzig, Germany
700    1_
$a Spiekermann, Karsten $u Laboratory for Leukemia Diagnostics, Department of Medicine III, University Hospital, LMU Munich, Munich, Germany
700    1_
$a Krug, Utz $u Department of Medicine III, Hospital Leverkusen, Leverkusen, Germany
700    1_
$a Braess, Jan $u Hospital Barmherzige Brueder Regensburg, Regensburg, Germany
700    1_
$a Görlich, Dennis $u Institute for Biostatistics and Clinical Research, University Muenster, Muenster, Germany $1 https://orcid.org/0000000225749419
700    1_
$a Sauerland, Cristina $u Institute for Biostatistics and Clinical Research, University Muenster, Muenster, Germany
700    1_
$a Woermann, Bernhard $u Department of Hematology, Oncology and Tumor Immunology, Charité, Berlin, Germany
700    1_
$a Herold, Tobias $u Laboratory for Leukemia Diagnostics, Department of Medicine III, University Hospital, LMU Munich, Munich, Germany $1 https://orcid.org/0000000296159432
700    1_
$a Hiddemann, Wolfgang $u Laboratory for Leukemia Diagnostics, Department of Medicine III, University Hospital, LMU Munich, Munich, Germany
700    1_
$a Müller-Tidow, Carsten $u Department of Medicine V, University Hospital Heidelberg, Heidelberg, Germany $u German Consortium for Translational Cancer Research DKFZ, Heidelberg, Germany $1 https://orcid.org/0000000271665232
700    1_
$a Serve, Hubert $u Department of Medicine 2, Hematology and Oncology, Goethe University Frankfurt, Frankfurt, Germany
700    1_
$a Baldus, Claudia D $u Department of Hematology and Oncology, University Hospital Schleswig Holstein, Kiel, Germany $1 https://orcid.org/000000020748834X
700    1_
$a Schäfer-Eckart, Kerstin $u Department of Internal Medicine 5, University Hospital Nuremberg, Nuremberg, Germany
700    1_
$a Kaufmann, Martin $u Department of Hematology, Oncology and Palliative Care, Robert-Bosch Hospital, Stuttgart, Germany
700    1_
$a Krause, Stefan W $u Department of Internal Medicine 5, University Hospital Erlangen, Erlangen, Germany $1 https://orcid.org/0000000252594651
700    1_
$a Hänel, Mathias $u Department of Internal Medicine 3, Klinikum Chemnitz GmbH, Chemnitz, Germany
700    1_
$a Berdel, Wolfgang E $u Department of Internal Medicine A, University Hospital Muenster, Muenster, Germany
700    1_
$a Schliemann, Christoph $u Department of Internal Medicine A, University Hospital Muenster, Muenster, Germany $1 https://orcid.org/0000000317559583
700    1_
$a Mayer, Jiri $u Department of Internal Medicine, Hematology and Oncology, Masaryk University Hospital, Brno, Czech Republic
700    1_
$a Hanoun, Maher $u Department of Hematology and Stem Cell Transplantation, University Hospital Essen, Essen, Germany $1 https://orcid.org/0000000217548940
700    1_
$a Schetelig, Johannes $u Department of Internal Medicine I, University Hospital Carl Gustav Carus, Dresden, Germany $1 https://orcid.org/0000000227802981
700    1_
$a Wendt, Karsten $u Else Kröner Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany $u Department of Software and Multimedia Technology, Technical University Dresden, Dresden, Germany
700    1_
$a Bornhäuser, Martin $u Department of Internal Medicine I, University Hospital Carl Gustav Carus, Dresden, Germany $u German Consortium for Translational Cancer Research DKFZ, Heidelberg, Germany $u National Center for Tumor Diseases (NCT), Dresden, Germany $1 https://orcid.org/0000000259163029
700    1_
$a Thiede, Christian $u Department of Internal Medicine I, University Hospital Carl Gustav Carus, Dresden, Germany $1 https://orcid.org/0000000312412048
700    1_
$a Middeke, Jan Moritz $u Department of Internal Medicine I, University Hospital Carl Gustav Carus, Dresden, Germany $u Else Kröner Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany
773    0_
$w MED00211272 $t Communications medicine $x 2730-664X $g Roč. 3, č. 1 (2023), s. 68
856    41
$u https://pubmed.ncbi.nlm.nih.gov/37198246 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20230707 $b ABA008
991    __
$a 20230721095448 $b ABA008
999    __
$a ok $b bmc $g 1958489 $s 1196016
BAS    __
$a 3
BAS    __
$a PreBMC-PubMed-not-MEDLINE
BMC    __
$a 2023 $b 3 $c 1 $d 68 $e 20230517 $i 2730-664X $m Communications medicine $n Commun Med (Lond) $x MED00211272
LZP    __
$a Pubmed-20230707

Najít záznam

Citační ukazatele

Možnosti archivace