Machine Learning Consensus Clustering Approach for Hospitalized Patients with Dysmagnesemia
Background: The objectives of this study were to classify patients with serum magnesium derangement on hospital admission into clusters using unsupervised machine learning approach and to evaluate the mortality risks among these distinct clusters. Methods: Consensus cluster analysis was performed ba...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/11/2119 |
| _version_ | 1797510645474656256 |
|---|---|
| author | Charat Thongprayoon Janina Paula T. Sy-Go Voravech Nissaisorakarn Carissa Y. Dumancas Mira T. Keddis Andrea G. Kattah Pattharawin Pattharanitima Saraschandra Vallabhajosyula Michael A. Mao Fawad Qureshi Vesna D. Garovic John J. Dillon Stephen B. Erickson Wisit Cheungpasitporn |
| author_facet | Charat Thongprayoon Janina Paula T. Sy-Go Voravech Nissaisorakarn Carissa Y. Dumancas Mira T. Keddis Andrea G. Kattah Pattharawin Pattharanitima Saraschandra Vallabhajosyula Michael A. Mao Fawad Qureshi Vesna D. Garovic John J. Dillon Stephen B. Erickson Wisit Cheungpasitporn |
| author_sort | Charat Thongprayoon |
| collection | DOAJ |
| description | Background: The objectives of this study were to classify patients with serum magnesium derangement on hospital admission into clusters using unsupervised machine learning approach and to evaluate the mortality risks among these distinct clusters. Methods: Consensus cluster analysis was performed based on demographic information, principal diagnoses, comorbidities, and laboratory data in hypomagnesemia (serum magnesium ≤ 1.6 mg/dL) and hypermagnesemia cohorts (serum magnesium ≥ 2.4 mg/dL). Each cluster’s key features were determined using the standardized mean difference. The associations of the clusters with hospital mortality and one-year mortality were assessed. Results: In hypomagnesemia cohort (<i>n</i> = 13,320), consensus cluster analysis identified three clusters. Cluster 1 patients had the highest comorbidity burden and lowest serum magnesium. Cluster 2 patients had the youngest age, lowest comorbidity burden, and highest kidney function. Cluster 3 patients had the oldest age and lowest kidney function. Cluster 1 and cluster 3 were associated with higher hospital and one-year mortality compared to cluster 2. In hypermagnesemia cohort (<i>n</i> = 4671), the analysis identified two clusters. Compared to cluster 1, the key features of cluster 2 included older age, higher comorbidity burden, more hospital admissions primarily due to kidney disease, more acute kidney injury, and lower kidney function. Compared to cluster 1, cluster 2 was associated with higher hospital mortality and one-year mortality. Conclusion: Our cluster analysis identified clinically distinct phenotypes with differing mortality risks in hospitalized patients with dysmagnesemia. Future studies are required to assess the application of this ML consensus clustering approach to care for hospitalized patients with dysmagnesemia. |
| first_indexed | 2024-03-10T05:34:16Z |
| format | Article |
| id | doaj.art-3ab80296b4334b97afb4bc0d2561f609 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T05:34:16Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-3ab80296b4334b97afb4bc0d2561f6092023-11-22T23:02:39ZengMDPI AGDiagnostics2075-44182021-11-011111211910.3390/diagnostics11112119Machine Learning Consensus Clustering Approach for Hospitalized Patients with DysmagnesemiaCharat Thongprayoon0Janina Paula T. Sy-Go1Voravech Nissaisorakarn2Carissa Y. Dumancas3Mira T. Keddis4Andrea G. Kattah5Pattharawin Pattharanitima6Saraschandra Vallabhajosyula7Michael A. Mao8Fawad Qureshi9Vesna D. Garovic10John J. Dillon11Stephen B. Erickson12Wisit Cheungpasitporn13Division 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, Department of Medicine, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA 01702, 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, USADepartment of Internal Medicine, Faculty of Medicine, Thammasat University, Pathum Thani 12121, ThailandSection of Cardiovascular Medicine, Department of Medicine, Wake Forest University School of Medicine, Winston-Salem, NC 27101, USADivision of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Jacksonville, FL 85054, 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, USABackground: The objectives of this study were to classify patients with serum magnesium derangement on hospital admission into clusters using unsupervised machine learning approach and to evaluate the mortality risks among these distinct clusters. Methods: Consensus cluster analysis was performed based on demographic information, principal diagnoses, comorbidities, and laboratory data in hypomagnesemia (serum magnesium ≤ 1.6 mg/dL) and hypermagnesemia cohorts (serum magnesium ≥ 2.4 mg/dL). Each cluster’s key features were determined using the standardized mean difference. The associations of the clusters with hospital mortality and one-year mortality were assessed. Results: In hypomagnesemia cohort (<i>n</i> = 13,320), consensus cluster analysis identified three clusters. Cluster 1 patients had the highest comorbidity burden and lowest serum magnesium. Cluster 2 patients had the youngest age, lowest comorbidity burden, and highest kidney function. Cluster 3 patients had the oldest age and lowest kidney function. Cluster 1 and cluster 3 were associated with higher hospital and one-year mortality compared to cluster 2. In hypermagnesemia cohort (<i>n</i> = 4671), the analysis identified two clusters. Compared to cluster 1, the key features of cluster 2 included older age, higher comorbidity burden, more hospital admissions primarily due to kidney disease, more acute kidney injury, and lower kidney function. Compared to cluster 1, cluster 2 was associated with higher hospital mortality and one-year mortality. Conclusion: Our cluster analysis identified clinically distinct phenotypes with differing mortality risks in hospitalized patients with dysmagnesemia. Future studies are required to assess the application of this ML consensus clustering approach to care for hospitalized patients with dysmagnesemia.https://www.mdpi.com/2075-4418/11/11/2119artificial intelligenceclusteringconsensus clusteringdysmagnesemiaelectrolyteshypomagnesemia |
| spellingShingle | Charat Thongprayoon Janina Paula T. Sy-Go Voravech Nissaisorakarn Carissa Y. Dumancas Mira T. Keddis Andrea G. Kattah Pattharawin Pattharanitima Saraschandra Vallabhajosyula Michael A. Mao Fawad Qureshi Vesna D. Garovic John J. Dillon Stephen B. Erickson Wisit Cheungpasitporn Machine Learning Consensus Clustering Approach for Hospitalized Patients with Dysmagnesemia Diagnostics artificial intelligence clustering consensus clustering dysmagnesemia electrolytes hypomagnesemia |
| title | Machine Learning Consensus Clustering Approach for Hospitalized Patients with Dysmagnesemia |
| title_full | Machine Learning Consensus Clustering Approach for Hospitalized Patients with Dysmagnesemia |
| title_fullStr | Machine Learning Consensus Clustering Approach for Hospitalized Patients with Dysmagnesemia |
| title_full_unstemmed | Machine Learning Consensus Clustering Approach for Hospitalized Patients with Dysmagnesemia |
| title_short | Machine Learning Consensus Clustering Approach for Hospitalized Patients with Dysmagnesemia |
| title_sort | machine learning consensus clustering approach for hospitalized patients with dysmagnesemia |
| topic | artificial intelligence clustering consensus clustering dysmagnesemia electrolytes hypomagnesemia |
| url | https://www.mdpi.com/2075-4418/11/11/2119 |
| work_keys_str_mv | AT charatthongprayoon machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT janinapaulatsygo machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT voravechnissaisorakarn machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT carissaydumancas machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT miratkeddis machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT andreagkattah machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT pattharawinpattharanitima machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT saraschandravallabhajosyula machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT michaelamao machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT fawadqureshi machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT vesnadgarovic machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT johnjdillon machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT stephenberickson machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia AT wisitcheungpasitporn machinelearningconsensusclusteringapproachforhospitalizedpatientswithdysmagnesemia |