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

J 2023

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

ECKARDT, Jan-Niklas, Christoph ROELLIG, Klaus METZELER, Peter HEISIG, Sebastian STASIK et. al.

Základní údaje

Originální název

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

Autoři

ECKARDT, Jan-Niklas (garant), Christoph ROELLIG, Klaus METZELER, Peter HEISIG, Sebastian STASIK, Julia-Annabell GEORGI, Frank KROSCHINSKY, Friedrich STOELZEL, Uwe PLATZBECKER, Karsten SPIEKERMANN, Utz KRUG, Jan BRAESS, Dennis GOERLICH, Cristina SAUERLAND, Bernhard WOERMANN, Tobias HEROLD, Wolfgang HIDDEMANN, Carsten MUELLER-TIDOW, Hubert SERVE, Claudia D BALDUS, Kerstin SCHAEFER-ECKART, Martin KAUFMANN, Stefan W KRAUSE, Mathias HAENEL, Wolfgang E BERDEL, Christoph SCHLIEMANN, Jiří MAYER (203 Česká republika, domácí), Maher HANOUN, Johannes SCHETELIG, Karsten WENDT, Martin BORNHAEUSER, Christian THIEDE a Jan Moritz MIDDEKE

Vydání

Communications Medicine, LONDON, SPRINGERNATURE, 2023, 2730-664X

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

30205 Hematology

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Kód RIV

RIV/00216224:14110/23:00130966

Organizační jednotka

Lékařská fakulta

DOI

http://dx.doi.org/10.1038/s43856-023-00298-6

UT WoS

000995218000001

Klíčová slova anglicky

acute myeloid leukemia; unsupervised meta-clustering; clinical and genetic profiles

Štítky

14110212, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 15. 6. 2023 12:47, Mgr. Tereza Miškechová

Anotace

V originále

Plain language summaryThere are various ways in which clinicians can predict the risk of disease progression in patients with leukemia, helping them to treat the patients accordingly. However, these approaches are usually designed by human experts and might not fully capture the complexity of a patient's disease. Here, with a large cohort of patients with acute myeloid leukemia, we design an unsupervised machine learning model - a type of computer model that learns from patterns in data without human input-to separate these patients into subgroups according to risk. We identify four distinct groups which differ with regards to patient genetics, laboratory values, and clinical characteristics. These groups have differences in response to treatment and patient survival, and we validate our findings in another dataset. Our approach might help clinicians to better predict outcomes in patients with leukemia and make decisions on treatment. Eckardt et al. identify four distinct risk clusters of patients with acute myeloid leukemia using unsupervised metaclustering, which is agnostic to current risk stratification models, in a large multicenter cohort. Clusters differ in terms of response to induction therapy and long-term survival, and are externally validated. BackgroundIncreasingly 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.MethodsWhile 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.ResultsUnsupervised 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.ConclusionsDynamic 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.

Citovat

ECKARDT, Jan-Niklas, Christoph ROELLIG, Klaus METZELER, Peter HEISIG, Sebastian STASIK, Julia-Annabell GEORGI, Frank KROSCHINSKY, Friedrich STOELZEL, Uwe PLATZBECKER, Karsten SPIEKERMANN, Utz KRUG, Jan BRAESS, Dennis GOERLICH, Cristina SAUERLAND, Bernhard WOERMANN, Tobias HEROLD, Wolfgang HIDDEMANN, Carsten MUELLER-TIDOW, Hubert SERVE, Claudia D BALDUS, Kerstin SCHAEFER-ECKART, Martin KAUFMANN, Stefan W KRAUSE, Mathias HAENEL, Wolfgang E BERDEL, Christoph SCHLIEMANN, Jiří MAYER, Maher HANOUN, Johannes SCHETELIG, Karsten WENDT, Martin BORNHAEUSER, Christian THIEDE a Jan Moritz MIDDEKE. Unsupervised meta-clustering identifies risk clusters in acute myeloid leukemia based on clinical and genetic profiles. Communications Medicine. LONDON: SPRINGERNATURE, 2023, roč. 3, č. 1, s. 1-13. ISSN 2730-664X. Dostupné z: https://dx.doi.org/10.1038/s43856-023-00298-6.

@article{2291619,
   author = {Eckardt, JanandNiklas and Roellig, Christoph and Metzeler, Klaus and Heisig, Peter and Stasik, Sebastian and Georgi, JuliaandAnnabell and Kroschinsky, Frank and Stoelzel, Friedrich and Platzbecker, Uwe and Spiekermann, Karsten and Krug, Utz and Braess, Jan and Goerlich, Dennis and Sauerland, Cristina and Woermann, Bernhard and Herold, Tobias and Hiddemann, Wolfgang and MuellerandTidow, Carsten and Serve, Hubert and Baldus, Claudia D and SchaeferandEckart, Kerstin and Kaufmann, Martin and Krause, Stefan W and Haenel, Mathias and Berdel, Wolfgang E and Schliemann, Christoph and Mayer, Jiří and Hanoun, Maher and Schetelig, Johannes and Wendt, Karsten and Bornhaeuser, Martin and Thiede, Christian and Middeke, Jan Moritz},
   article_location = {LONDON},
   article_number = {1},
   doi = {http://dx.doi.org/10.1038/s43856-023-00298-6},
   keywords = {acute myeloid leukemia; unsupervised meta-clustering; clinical and genetic profiles},
   language = {eng},
   issn = {2730-664X},
   journal = {Communications Medicine},
   title = {Unsupervised meta-clustering identifies risk clusters in acute myeloid leukemia based on clinical and genetic profiles},
   url = {https://www.nature.com/articles/s43856-023-00298-6},
   volume = {3},
   year = {2023}
}

TY  - JOUR
ID  - 2291619
AU  - Eckardt, Jan-Niklas - Roellig, Christoph - Metzeler, Klaus - Heisig, Peter - Stasik, Sebastian - Georgi, Julia-Annabell - Kroschinsky, Frank - Stoelzel, Friedrich - Platzbecker, Uwe - Spiekermann, Karsten - Krug, Utz - Braess, Jan - Goerlich, Dennis - Sauerland, Cristina - Woermann, Bernhard - Herold, Tobias - Hiddemann, Wolfgang - Mueller-Tidow, Carsten - Serve, Hubert - Baldus, Claudia D - Schaefer-Eckart, Kerstin - Kaufmann, Martin - Krause, Stefan W - Haenel, Mathias - Berdel, Wolfgang E - Schliemann, Christoph - Mayer, Jiří - Hanoun, Maher - Schetelig, Johannes - Wendt, Karsten - Bornhaeuser, Martin - Thiede, Christian - Middeke, Jan Moritz
PY  - 2023
TI  - Unsupervised meta-clustering identifies risk clusters in acute myeloid leukemia based on clinical and genetic profiles
JF  - Communications Medicine
VL  - 3
IS  - 1
SP  - 1-13
EP  - 1-13
PB  - SPRINGERNATURE
SN  - 2730664X
KW  - acute myeloid leukemia
KW  - unsupervised meta-clustering
KW  - clinical and genetic profiles
UR  - https://www.nature.com/articles/s43856-023-00298-6
N2  - Plain language summaryThere are various ways in which clinicians can predict the risk of disease progression in patients with leukemia, helping them to treat the patients accordingly. However, these approaches are usually designed by human experts and might not fully capture the complexity of a patient's disease. Here, with a large cohort of patients with acute myeloid leukemia, we design an unsupervised machine learning model - a type of computer model that learns from patterns in data without human input-to separate these patients into subgroups according to risk. We identify four distinct groups which differ with regards to patient genetics, laboratory values, and clinical characteristics. These groups have differences in response to treatment and patient survival, and we validate our findings in another dataset. Our approach might help clinicians to better predict outcomes in patients with leukemia and make decisions on treatment. Eckardt et al. identify four distinct risk clusters of patients with acute myeloid leukemia using unsupervised metaclustering, which is agnostic to current risk stratification models, in a large multicenter cohort. Clusters differ in terms of response to induction therapy and long-term survival, and are externally validated. BackgroundIncreasingly 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.MethodsWhile 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.ResultsUnsupervised 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.ConclusionsDynamic 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.
ER  -

ECKARDT, Jan-Niklas, Christoph ROELLIG, Klaus METZELER, Peter HEISIG, Sebastian STASIK, Julia-Annabell GEORGI, Frank KROSCHINSKY, Friedrich STOELZEL, Uwe PLATZBECKER, Karsten SPIEKERMANN, Utz KRUG, Jan BRAESS, Dennis GOERLICH, Cristina SAUERLAND, Bernhard WOERMANN, Tobias HEROLD, Wolfgang HIDDEMANN, Carsten MUELLER-TIDOW, Hubert SERVE, Claudia D BALDUS, Kerstin SCHAEFER-ECKART, Martin KAUFMANN, Stefan W KRAUSE, Mathias HAENEL, Wolfgang E BERDEL, Christoph SCHLIEMANN, Jiří MAYER, Maher HANOUN, Johannes SCHETELIG, Karsten WENDT, Martin BORNHAEUSER, Christian THIEDE a Jan Moritz MIDDEKE. Unsupervised meta-clustering identifies risk clusters in acute myeloid leukemia based on clinical and genetic profiles. \textit{Communications Medicine}. LONDON: SPRINGERNATURE, 2023, roč.~3, č.~1, s.~1-13. ISSN~2730-664X. Dostupné z: https://dx.doi.org/10.1038/s43856-023-00298-6.

Podrobný výpis o publikaci