Cargando…
Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia
Background: The objective of this study was to characterize patients with hyponatremia at hospital admission into clusters using an unsupervised machine learning approach, and to evaluate the short- and long-term mortality risk among these distinct clusters. Methods: We performed consensus cluster a...
Autores principales: | , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8395840/ https://www.ncbi.nlm.nih.gov/pubmed/34449583 http://dx.doi.org/10.3390/diseases9030054 |
_version_ | 1783744261876875264 |
---|---|
author | Thongprayoon, Charat Hansrivijit, Panupong Mao, Michael A. Vaitla, Pradeep K. Kattah, Andrea G. Pattharanitima, Pattharawin Vallabhajosyula, Saraschandra Nissaisorakarn, Voravech Petnak, Tananchai Keddis, Mira T. Erickson, Stephen B. Dillon, John J. Garovic, Vesna D. Cheungpasitporn, Wisit |
author_facet | Thongprayoon, Charat Hansrivijit, Panupong Mao, Michael A. Vaitla, Pradeep K. Kattah, Andrea G. Pattharanitima, Pattharawin Vallabhajosyula, Saraschandra Nissaisorakarn, Voravech Petnak, Tananchai Keddis, Mira T. Erickson, Stephen B. Dillon, John J. Garovic, Vesna D. Cheungpasitporn, Wisit |
author_sort | Thongprayoon, Charat |
collection | PubMed |
description | Background: The objective of this study was to characterize patients with hyponatremia at hospital admission into clusters using an unsupervised machine learning approach, and to evaluate the short- and long-term mortality risk among these distinct clusters. Methods: We performed consensus cluster analysis based on demographic information, principal diagnoses, comorbidities, and laboratory data among 11,099 hospitalized adult hyponatremia patients with an admission serum sodium below 135 mEq/L. The standardized mean difference was utilized to identify each cluster’s key features. We assessed the association of each hyponatremia cluster with hospital and one-year mortality using logistic and Cox proportional hazard analysis, respectively. Results: There were three distinct clusters of hyponatremia patients: 2033 (18%) in cluster 1, 3064 (28%) in cluster 2, and 6002 (54%) in cluster 3. Among these three distinct clusters, clusters 3 patients were the youngest, had lowest comorbidity burden, and highest kidney function. Cluster 1 patients were more likely to be admitted for genitourinary disease, and have diabetes and end-stage kidney disease. Cluster 1 patients had the lowest kidney function, serum bicarbonate, and hemoglobin, but highest serum potassium and prevalence of acute kidney injury. In contrast, cluster 2 patients were the oldest and were more likely to be admitted for respiratory disease, have coronary artery disease, congestive heart failure, stroke, and chronic obstructive pulmonary disease. Cluster 2 patients had lowest serum sodium and serum chloride, but highest serum bicarbonate. Cluster 1 patients had the highest hospital mortality and one-year mortality, followed by cluster 2 and cluster 3, respectively. Conclusion: We identified three clinically distinct phenotypes with differing mortality risks in a heterogeneous cohort of hospitalized hyponatremic patients using an unsupervised machine learning approach. |
format | Online Article Text |
id | pubmed-8395840 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-83958402021-08-28 Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia Thongprayoon, Charat Hansrivijit, Panupong Mao, Michael A. Vaitla, Pradeep K. Kattah, Andrea G. Pattharanitima, Pattharawin Vallabhajosyula, Saraschandra Nissaisorakarn, Voravech Petnak, Tananchai Keddis, Mira T. Erickson, Stephen B. Dillon, John J. Garovic, Vesna D. Cheungpasitporn, Wisit Diseases Article Background: The objective of this study was to characterize patients with hyponatremia at hospital admission into clusters using an unsupervised machine learning approach, and to evaluate the short- and long-term mortality risk among these distinct clusters. Methods: We performed consensus cluster analysis based on demographic information, principal diagnoses, comorbidities, and laboratory data among 11,099 hospitalized adult hyponatremia patients with an admission serum sodium below 135 mEq/L. The standardized mean difference was utilized to identify each cluster’s key features. We assessed the association of each hyponatremia cluster with hospital and one-year mortality using logistic and Cox proportional hazard analysis, respectively. Results: There were three distinct clusters of hyponatremia patients: 2033 (18%) in cluster 1, 3064 (28%) in cluster 2, and 6002 (54%) in cluster 3. Among these three distinct clusters, clusters 3 patients were the youngest, had lowest comorbidity burden, and highest kidney function. Cluster 1 patients were more likely to be admitted for genitourinary disease, and have diabetes and end-stage kidney disease. Cluster 1 patients had the lowest kidney function, serum bicarbonate, and hemoglobin, but highest serum potassium and prevalence of acute kidney injury. In contrast, cluster 2 patients were the oldest and were more likely to be admitted for respiratory disease, have coronary artery disease, congestive heart failure, stroke, and chronic obstructive pulmonary disease. Cluster 2 patients had lowest serum sodium and serum chloride, but highest serum bicarbonate. Cluster 1 patients had the highest hospital mortality and one-year mortality, followed by cluster 2 and cluster 3, respectively. Conclusion: We identified three clinically distinct phenotypes with differing mortality risks in a heterogeneous cohort of hospitalized hyponatremic patients using an unsupervised machine learning approach. MDPI 2021-08-01 /pmc/articles/PMC8395840/ /pubmed/34449583 http://dx.doi.org/10.3390/diseases9030054 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Thongprayoon, Charat Hansrivijit, Panupong Mao, Michael A. Vaitla, Pradeep K. Kattah, Andrea G. Pattharanitima, Pattharawin Vallabhajosyula, Saraschandra Nissaisorakarn, Voravech Petnak, Tananchai Keddis, Mira T. Erickson, Stephen B. Dillon, John J. Garovic, Vesna D. Cheungpasitporn, Wisit Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia |
title | Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia |
title_full | Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia |
title_fullStr | Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia |
title_full_unstemmed | Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia |
title_short | Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia |
title_sort | machine learning consensus clustering of hospitalized patients with admission hyponatremia |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8395840/ https://www.ncbi.nlm.nih.gov/pubmed/34449583 http://dx.doi.org/10.3390/diseases9030054 |
work_keys_str_mv | AT thongprayooncharat machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT hansrivijitpanupong machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT maomichaela machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT vaitlapradeepk machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT kattahandreag machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT pattharanitimapattharawin machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT vallabhajosyulasaraschandra machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT nissaisorakarnvoravech machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT petnaktananchai machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT keddismirat machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT ericksonstephenb machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT dillonjohnj machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT garovicvesnad machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia AT cheungpasitpornwisit machinelearningconsensusclusteringofhospitalizedpatientswithadmissionhyponatremia |