Novel Phenotyping for Acute Heart Failure—Unsupervised Machine Learning-Based Approach
Acute heart failure (AHF) is a life-threatening, heterogeneous disease requiring urgent diagnosis and treatment. The clinical severity and medical procedures differ according to a complex interplay between the deterioration cause, underlying cardiac substrate, and comorbidities. This study aimed to...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Biomedicines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9059/10/7/1514 |
| _version_ | 1827597906781143040 |
|---|---|
| author | Szymon Urban Mikołaj Błaziak Maksym Jura Gracjan Iwanek Agata Zdanowicz Mateusz Guzik Artur Borkowski Piotr Gajewski Jan Biegus Agnieszka Siennicka Maciej Pondel Petr Berka Piotr Ponikowski Robert Zymliński |
| author_facet | Szymon Urban Mikołaj Błaziak Maksym Jura Gracjan Iwanek Agata Zdanowicz Mateusz Guzik Artur Borkowski Piotr Gajewski Jan Biegus Agnieszka Siennicka Maciej Pondel Petr Berka Piotr Ponikowski Robert Zymliński |
| author_sort | Szymon Urban |
| collection | DOAJ |
| description | Acute heart failure (AHF) is a life-threatening, heterogeneous disease requiring urgent diagnosis and treatment. The clinical severity and medical procedures differ according to a complex interplay between the deterioration cause, underlying cardiac substrate, and comorbidities. This study aimed to analyze the natural phenotypic heterogeneity of the AHF population and evaluate the possibilities offered by clustering (unsupervised machine-learning technique) in a medical data assessment. We evaluated data from 381 AHF patients. Sixty-three clinical and biochemical features were assessed at the admission of the patients and were included in the analysis after the preprocessing. The K-medoids algorithm was implemented to create the clusters, and optimization, based on the Davies-Bouldin index, was used. The clustering was performed while blinded to the outcome. The outcome associations were evaluated using the Kaplan-Meier curves and Cox proportional-hazards regressions. The algorithm distinguished six clusters that differed significantly in 58 variables concerning i.e., etiology, clinical status, comorbidities, laboratory parameters and lifestyle factors. The clusters differed in terms of the one-year mortality (<i>p</i> = 0.002). Using the clustering techniques, we extracted six phenotypes from AHF patients with distinct clinical characteristics and outcomes. Our results can be valuable for future trial constructions and customized treatment. |
| first_indexed | 2024-03-09T03:40:59Z |
| format | Article |
| id | doaj.art-f64902a030bd4ae391b2ffffe9c1f514 |
| institution | Directory Open Access Journal |
| issn | 2227-9059 |
| language | English |
| last_indexed | 2024-03-09T03:40:59Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomedicines |
| spelling | doaj.art-f64902a030bd4ae391b2ffffe9c1f5142023-12-03T14:41:18ZengMDPI AGBiomedicines2227-90592022-06-01107151410.3390/biomedicines10071514Novel Phenotyping for Acute Heart Failure—Unsupervised Machine Learning-Based ApproachSzymon Urban0Mikołaj Błaziak1Maksym Jura2Gracjan Iwanek3Agata Zdanowicz4Mateusz Guzik5Artur Borkowski6Piotr Gajewski7Jan Biegus8Agnieszka Siennicka9Maciej Pondel10Petr Berka11Piotr Ponikowski12Robert Zymliński13Institute of Heart Diseases, Wroclaw Medical University, 50-556 Wroclaw, PolandInstitute of Heart Diseases, Wroclaw Medical University, 50-556 Wroclaw, PolandInstitute of Heart Diseases, Wroclaw Medical University, 50-556 Wroclaw, PolandInstitute of Heart Diseases, Wroclaw Medical University, 50-556 Wroclaw, PolandInstitute of Heart Diseases, Wroclaw Medical University, 50-556 Wroclaw, PolandInstitute of Heart Diseases, Wroclaw Medical University, 50-556 Wroclaw, PolandInstitute of Heart Diseases, Wroclaw Medical University, 50-556 Wroclaw, PolandInstitute of Heart Diseases, Wroclaw Medical University, 50-556 Wroclaw, PolandInstitute of Heart Diseases, Wroclaw Medical University, 50-556 Wroclaw, PolandDepartment of Physiology and Patophysiology, Wroclaw Medical University, 50-368 Wroclaw, PolandInstitute of Information Systems in Economics, Wroclaw University of Economics and Business, 53-345 Wroclaw, PolandDepartment of Information and Knowledge Engineering, Prague University of Economics and Business, W. Churchill Sq. 1938/4, 130 67 Prague, Czech RepublicInstitute of Heart Diseases, Wroclaw Medical University, 50-556 Wroclaw, PolandInstitute of Heart Diseases, Wroclaw Medical University, 50-556 Wroclaw, PolandAcute heart failure (AHF) is a life-threatening, heterogeneous disease requiring urgent diagnosis and treatment. The clinical severity and medical procedures differ according to a complex interplay between the deterioration cause, underlying cardiac substrate, and comorbidities. This study aimed to analyze the natural phenotypic heterogeneity of the AHF population and evaluate the possibilities offered by clustering (unsupervised machine-learning technique) in a medical data assessment. We evaluated data from 381 AHF patients. Sixty-three clinical and biochemical features were assessed at the admission of the patients and were included in the analysis after the preprocessing. The K-medoids algorithm was implemented to create the clusters, and optimization, based on the Davies-Bouldin index, was used. The clustering was performed while blinded to the outcome. The outcome associations were evaluated using the Kaplan-Meier curves and Cox proportional-hazards regressions. The algorithm distinguished six clusters that differed significantly in 58 variables concerning i.e., etiology, clinical status, comorbidities, laboratory parameters and lifestyle factors. The clusters differed in terms of the one-year mortality (<i>p</i> = 0.002). Using the clustering techniques, we extracted six phenotypes from AHF patients with distinct clinical characteristics and outcomes. Our results can be valuable for future trial constructions and customized treatment.https://www.mdpi.com/2227-9059/10/7/1514acute heart failuremachine learningclustering |
| spellingShingle | Szymon Urban Mikołaj Błaziak Maksym Jura Gracjan Iwanek Agata Zdanowicz Mateusz Guzik Artur Borkowski Piotr Gajewski Jan Biegus Agnieszka Siennicka Maciej Pondel Petr Berka Piotr Ponikowski Robert Zymliński Novel Phenotyping for Acute Heart Failure—Unsupervised Machine Learning-Based Approach Biomedicines acute heart failure machine learning clustering |
| title | Novel Phenotyping for Acute Heart Failure—Unsupervised Machine Learning-Based Approach |
| title_full | Novel Phenotyping for Acute Heart Failure—Unsupervised Machine Learning-Based Approach |
| title_fullStr | Novel Phenotyping for Acute Heart Failure—Unsupervised Machine Learning-Based Approach |
| title_full_unstemmed | Novel Phenotyping for Acute Heart Failure—Unsupervised Machine Learning-Based Approach |
| title_short | Novel Phenotyping for Acute Heart Failure—Unsupervised Machine Learning-Based Approach |
| title_sort | novel phenotyping for acute heart failure unsupervised machine learning based approach |
| topic | acute heart failure machine learning clustering |
| url | https://www.mdpi.com/2227-9059/10/7/1514 |
| work_keys_str_mv | AT szymonurban novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT mikołajbłaziak novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT maksymjura novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT gracjaniwanek novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT agatazdanowicz novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT mateuszguzik novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT arturborkowski novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT piotrgajewski novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT janbiegus novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT agnieszkasiennicka novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT maciejpondel novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT petrberka novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT piotrponikowski novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach AT robertzymlinski novelphenotypingforacuteheartfailureunsupervisedmachinelearningbasedapproach |