Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus Clustering
<i>Background and Objectives</i>: Despite the association between hyperchloremia and adverse outcomes, mortality risks among patients with hyperchloremia have not consistently been observed among all studies with different patient populations with hyperchloremia. The objective of this st...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Medicina |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1648-9144/57/9/903 |
| _version_ | 1829091988296695808 |
|---|---|
| author | Charat Thongprayoon Voravech Nissaisorakarn Pattharawin Pattharanitima Michael A. Mao Andrea G. Kattah Mira T. Keddis Carissa Y. Dumancas Saraschandra Vallabhajosyula Tananchai Petnak Stephen B. Erickson John J. Dillon Vesna D. Garovic Kianoush B. Kashani Wisit Cheungpasitporn |
| author_facet | Charat Thongprayoon Voravech Nissaisorakarn Pattharawin Pattharanitima Michael A. Mao Andrea G. Kattah Mira T. Keddis Carissa Y. Dumancas Saraschandra Vallabhajosyula Tananchai Petnak Stephen B. Erickson John J. Dillon Vesna D. Garovic Kianoush B. Kashani Wisit Cheungpasitporn |
| author_sort | Charat Thongprayoon |
| collection | DOAJ |
| description | <i>Background and Objectives</i>: Despite the association between hyperchloremia and adverse outcomes, mortality risks among patients with hyperchloremia have not consistently been observed among all studies with different patient populations with hyperchloremia. The objective of this study was to characterize hyperchloremic patients at hospital admission into clusters using an unsupervised machine learning approach and to evaluate the mortality risk among these distinct clusters. <i>Materials and Methods</i>: We performed consensus cluster analysis based on demographic information, principal diagnoses, comorbidities, and laboratory data among 11,394 hospitalized adult patients with admission serum chloride of >108 mEq/L. We calculated the standardized mean difference of each variable to identify each cluster’s key features. We assessed the association of each hyperchloremia cluster with hospital and one-year mortality. <i>Results</i>: There were three distinct clusters of patients with admission hyperchloremia: 3237 (28%), 4059 (36%), and 4098 (36%) patients in clusters 1 through 3, respectively. Cluster 1 was characterized by higher serum chloride but lower serum sodium, bicarbonate, hemoglobin, and albumin. Cluster 2 was characterized by younger age, lower comorbidity score, lower serum chloride, and higher estimated glomerular filtration (eGFR), hemoglobin, and albumin. Cluster 3 was characterized by older age, higher comorbidity score, higher serum sodium, potassium, and lower eGFR. Compared with cluster 2, odds ratios for hospital mortality were 3.60 (95% CI 2.33–5.56) for cluster 1, and 4.83 (95% CI 3.21–7.28) for cluster 3, whereas hazard ratios for one-year mortality were 4.49 (95% CI 3.53–5.70) for cluster 1 and 6.96 (95% CI 5.56–8.72) for cluster 3. <i>Conclusions</i>: Our cluster analysis identified three clinically distinct phenotypes with differing mortality risks in hospitalized patients with admission hyperchloremia. |
| first_indexed | 2024-03-10T07:28:02Z |
| format | Article |
| id | doaj.art-6ae8648aadcd44489035b3fa5bcd0c69 |
| institution | Directory Open Access Journal |
| issn | 1010-660X 1648-9144 |
| language | English |
| last_indexed | 2024-03-10T07:28:02Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Medicina |
| spelling | doaj.art-6ae8648aadcd44489035b3fa5bcd0c692023-11-22T14:08:02ZengMDPI AGMedicina1010-660X1648-91442021-08-0157990310.3390/medicina57090903Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus ClusteringCharat Thongprayoon0Voravech Nissaisorakarn1Pattharawin Pattharanitima2Michael A. Mao3Andrea G. Kattah4Mira T. Keddis5Carissa Y. Dumancas6Saraschandra Vallabhajosyula7Tananchai Petnak8Stephen B. Erickson9John J. Dillon10Vesna D. Garovic11Kianoush B. Kashani12Wisit Cheungpasitporn13Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USADepartment of Internal Medicine, MetroWest Medical Center, Tufts University School of Medicine, Boston, MA 01702, USADepartment of Internal Medicine, Faculty of Medicine, Thammasat University, Pathum Thani 12120, ThailandDivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Jacksonville, FL 32224, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Phoenix, AZ 85054, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USASection of Cardiovascular Medicine, Department of Medicine, Wake Forest University School of Medicine, Winston-Salem, NC 27101, USADivision of Pulmonary and Critical Care Medicine, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA<i>Background and Objectives</i>: Despite the association between hyperchloremia and adverse outcomes, mortality risks among patients with hyperchloremia have not consistently been observed among all studies with different patient populations with hyperchloremia. The objective of this study was to characterize hyperchloremic patients at hospital admission into clusters using an unsupervised machine learning approach and to evaluate the mortality risk among these distinct clusters. <i>Materials and Methods</i>: We performed consensus cluster analysis based on demographic information, principal diagnoses, comorbidities, and laboratory data among 11,394 hospitalized adult patients with admission serum chloride of >108 mEq/L. We calculated the standardized mean difference of each variable to identify each cluster’s key features. We assessed the association of each hyperchloremia cluster with hospital and one-year mortality. <i>Results</i>: There were three distinct clusters of patients with admission hyperchloremia: 3237 (28%), 4059 (36%), and 4098 (36%) patients in clusters 1 through 3, respectively. Cluster 1 was characterized by higher serum chloride but lower serum sodium, bicarbonate, hemoglobin, and albumin. Cluster 2 was characterized by younger age, lower comorbidity score, lower serum chloride, and higher estimated glomerular filtration (eGFR), hemoglobin, and albumin. Cluster 3 was characterized by older age, higher comorbidity score, higher serum sodium, potassium, and lower eGFR. Compared with cluster 2, odds ratios for hospital mortality were 3.60 (95% CI 2.33–5.56) for cluster 1, and 4.83 (95% CI 3.21–7.28) for cluster 3, whereas hazard ratios for one-year mortality were 4.49 (95% CI 3.53–5.70) for cluster 1 and 6.96 (95% CI 5.56–8.72) for cluster 3. <i>Conclusions</i>: Our cluster analysis identified three clinically distinct phenotypes with differing mortality risks in hospitalized patients with admission hyperchloremia.https://www.mdpi.com/1648-9144/57/9/903hyperchloremiachlorideartificial intelligenceclusteringmortalitymachine learning |
| spellingShingle | Charat Thongprayoon Voravech Nissaisorakarn Pattharawin Pattharanitima Michael A. Mao Andrea G. Kattah Mira T. Keddis Carissa Y. Dumancas Saraschandra Vallabhajosyula Tananchai Petnak Stephen B. Erickson John J. Dillon Vesna D. Garovic Kianoush B. Kashani Wisit Cheungpasitporn Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus Clustering Medicina hyperchloremia chloride artificial intelligence clustering mortality machine learning |
| title | Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus Clustering |
| title_full | Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus Clustering |
| title_fullStr | Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus Clustering |
| title_full_unstemmed | Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus Clustering |
| title_short | Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus Clustering |
| title_sort | subtyping hyperchloremia among hospitalized patients by machine learning consensus clustering |
| topic | hyperchloremia chloride artificial intelligence clustering mortality machine learning |
| url | https://www.mdpi.com/1648-9144/57/9/903 |
| work_keys_str_mv | AT charatthongprayoon subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT voravechnissaisorakarn subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT pattharawinpattharanitima subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT michaelamao subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT andreagkattah subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT miratkeddis subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT carissaydumancas subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT saraschandravallabhajosyula subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT tananchaipetnak subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT stephenberickson subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT johnjdillon subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT vesnadgarovic subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT kianoushbkashani subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering AT wisitcheungpasitporn subtypinghyperchloremiaamonghospitalizedpatientsbymachinelearningconsensusclustering |