Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus Clustering

Background and Objectives: 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. Materials and Methods: 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. Results: 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. Conclusions: Our cluster analysis identified three clinically distinct phenotypes with differing mortality risks in hospitalized patients with admission hyperchloremia.

Download Full-text

Machine Learning Consensus Clustering Approach for Hospitalized Patients with Dysmagnesemia

Diagnostics ◽

10.3390/diagnostics11112119 ◽

2021 ◽

Vol 11 (11) ◽

pp. 2119

Author(s):

Charat Thongprayoon ◽

Janina Paula T. Sy-Go ◽

Voravech Nissaisorakarn ◽

Carissa Y. Dumancas ◽

Mira T. Keddis ◽

...

Keyword(s):

Cluster Analysis ◽

Kidney Function ◽

Serum Magnesium ◽

Hospitalized Patients ◽

Consensus Clustering ◽

Comorbidity Burden ◽

Clustering Approach ◽

One Year ◽

Cluster 2 ◽

Function Cluster

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 (n = 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 (n = 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.

Download Full-text

Machine Learning Consensus Clustering Approach for Hospitalized Patients with Phosphate Derangements

Journal of Clinical Medicine ◽

10.3390/jcm10194441 ◽

2021 ◽

Vol 10 (19) ◽

pp. 4441

Author(s):

Charat Thongprayoon ◽

Carissa Y. Dumancas ◽

Voravech Nissaisorakarn ◽

Mira T. Keddis ◽

Andrea G. Kattah ◽

...

Keyword(s):

Machine Learning ◽

Cluster Analysis ◽

Kidney Disease ◽

Serum Phosphate ◽

Older Age ◽

Consensus Clustering ◽

Clustering Approach ◽

Key Features ◽

One Year ◽

Cluster 2

Background: The goal of this study was to categorize patients with abnormal serum phosphate upon hospital admission into distinct clusters utilizing an unsupervised machine learning approach, and to assess the mortality risk associated with these clusters. Methods: We utilized the consensus clustering approach on demographic information, comorbidities, principal diagnoses, and laboratory data of hypophosphatemia (serum phosphate ≤ 2.4 mg/dL) and hyperphosphatemia cohorts (serum phosphate ≥ 4.6 mg/dL). The standardized mean difference was applied to determine each cluster’s key features. We assessed the association of the clusters with mortality. Results: In the hypophosphatemia cohort (n = 3113), the consensus cluster analysis identified two clusters. The key features of patients in Cluster 2, compared with Cluster 1, included: older age; a higher comorbidity burden, particularly hypertension; diabetes mellitus; coronary artery disease; lower eGFR; and more acute kidney injury (AKI) at admission. Cluster 2 had a comparable hospital mortality (3.7% vs. 2.9%; p = 0.17), but a higher one-year mortality (26.8% vs. 14.0%; p < 0.001), and five-year mortality (20.2% vs. 44.3%; p < 0.001), compared to Cluster 1. In the hyperphosphatemia cohort (n = 7252), the analysis identified two clusters. The key features of patients in Cluster 2, compared with Cluster 1, included: older age; more primary admission for kidney disease; more history of hypertension; more end-stage kidney disease; more AKI at admission; and higher admission potassium, magnesium, and phosphate. Cluster 2 had a higher hospital (8.9% vs. 2.4%; p < 0.001) one-year mortality (32.9% vs. 14.8%; p < 0.001), and five-year mortality (24.5% vs. 51.1%; p < 0.001), compared with Cluster 1. Conclusion: Our cluster analysis classified clinically distinct phenotypes with different mortality risks among hospitalized patients with serum phosphate derangements. Age, comorbidities, and kidney function were the key features that differentiated the phenotypes.

Download Full-text

Clinically Distinct Subtypes of Acute Kidney Injury on Hospital Admission Identified by Machine Learning Consensus Clustering

Medical Sciences ◽

10.3390/medsci9040060 ◽

2021 ◽

Vol 9 (4) ◽

pp. 60

Author(s):

Charat Thongprayoon ◽

Pradeep Vaitla ◽

Voravech Nissaisorakarn ◽

Michael A. Mao ◽

Jose L. Zabala Genovez ◽

...

Keyword(s):

Machine Learning ◽

Acute Kidney Injury ◽

Hospital Admission ◽

Clustering Analysis ◽

Kidney Injury ◽

Consensus Clustering ◽

Serum Bicarbonate ◽

Lower Serum ◽

Serum Chloride ◽

Cluster 2

Background: We aimed to cluster patients with acute kidney injury at hospital admission into clinically distinct subtypes using an unsupervised machine learning approach and assess the mortality risk among the distinct clusters. Methods: We performed consensus clustering analysis based on demographic information, principal diagnoses, comorbidities, and laboratory data among 4289 hospitalized adult patients with acute kidney injury at admission. The standardized difference of each variable was calculated to identify each cluster’s key features. We assessed the association of each acute kidney injury cluster with hospital and one-year mortality. Results: Consensus clustering analysis identified four distinct clusters. There were 1201 (28%) patients in cluster 1, 1396 (33%) patients in cluster 2, 1191 (28%) patients in cluster 3, and 501 (12%) patients in cluster 4. Cluster 1 patients were the youngest and had the least comorbidities. Cluster 2 and cluster 3 patients were older and had lower baseline kidney function. Cluster 2 patients had lower serum bicarbonate, strong ion difference, and hemoglobin, but higher serum chloride, whereas cluster 3 patients had lower serum chloride but higher serum bicarbonate and strong ion difference. Cluster 4 patients were younger and more likely to be admitted for genitourinary disease and infectious disease but less likely to be admitted for cardiovascular disease. Cluster 4 patients also had more severe acute kidney injury, lower serum sodium, serum chloride, and serum bicarbonate, but higher serum potassium and anion gap. Cluster 2, 3, and 4 patients had significantly higher hospital and one-year mortality than cluster 1 patients (p < 0.001). Conclusion: Our study demonstrated using machine learning consensus clustering analysis to characterize a heterogeneous cohort of patients with acute kidney injury on hospital admission into four clinically distinct clusters with different associated mortality risks.

Download Full-text

Machine Learning Consensus Clustering of Hospitalized Patients with Admission Hyponatremia

Diseases ◽

10.3390/diseases9030054 ◽

2021 ◽

Vol 9 (3) ◽

pp. 54

Author(s):

Charat Thongprayoon ◽

Panupong Hansrivijit ◽

Michael A. Mao ◽

Pradeep K. Vaitla ◽

Andrea G. Kattah ◽

...

Keyword(s):

Machine Learning ◽

Kidney Function ◽

Serum Sodium ◽

Learning Approach ◽

Serum Bicarbonate ◽

Unsupervised Machine Learning ◽

Disease Cluster ◽

Machine Learning Approach ◽

One Year ◽

Cluster 2

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.

Download Full-text

625 Cluster analysis of weather and pollution features and its role in predicting acute cardiac or cerebrovascular events

European Heart Journal Supplements ◽

10.1093/eurheartj/suab145 ◽

2021 ◽

Vol 23 (Supplement_G) ◽

Author(s):

Alberto Testa ◽

Sabrina Anticoli ◽

Francesca Romana Pezzella ◽

Marilena Mangiardi ◽

Alessandro Di Giosa ◽

...

Keyword(s):

Machine Learning ◽

Cluster Analysis ◽

Hierarchical Clustering ◽

Metropolitan Area ◽

Unsupervised Machine Learning ◽

Large Metropolitan Area ◽

Cerebrovascular Events ◽

Increased Risk ◽

The Impact ◽

Cluster 2

Abstract Aims The impact of the interplay between weather and pollution features on the risk of acute cardiac and cerebrovascular events has not been entirely appraised. The aim of this study was to perform a comprehensive cluster analysis of weather and pollution features in a large metropolitan area, and their association with acute cardiac and cerebrovascular events. Methods and results Anonymized data on acute myocardial infarction (AMI) and acute cerebrovascular events were obtained from three tertiary care centre from a single large metropolitan area. Weather and pollution data were obtained averaging measurements from several city measurement stations managed by the competent regional agency for environmental protection, and from the Meteorologic Center of Italian Military Aviation. Unsupervised machine learning was performed with hierarchical clustering to identify specific days with distinct weather and pollution features. Clusters were then compared for rate of acute cardiac and cerebrovascular events with Poisson models. As expected, significant pairwise correlations were found between weather and pollution features. Building upon these correlations, hierarchical clustering, from a total of 1169 days, generated four separate clusters: Cluster 1, including 60 (5.1%) days, Cluster 2 with 419 (35.8%) days, Cluster 3 with 673 (57.6%) days, and Cluster 4 with 17 (1.5%) days, with significant between-cluster differences in weather and pollution features. Notably, Cluster 1 was characterized by low temperatures and high ozone concentrations (P < 0.001). Overall cluster-wise comparisons showed significant overall differences in adverse cardiac and cerebrovascular events (P < 0.001), as well as in cerebrovascular events (P < 0.001) and strokes (P = 0.001). Between-cluster comparisons showed that Cluster 1 was associated with an increased risk of any event, cerebrovascular events, and strokes in comparison to Cluster 2, Cluster 3, and Cluster 4 (all P < 0.05), as well as AMI in comparison to Cluster 3 (P = 0.047). In addition, Cluster 2 was associated with a higher risk of strokes in comparison to Cluster 4 (P = 0.030). Analysis adjusting for season confirmed the increased risk of any event, cerebrovascular events, and strokes for Cluster 1 and Cluster 2. Conclusions Unsupervised machine learning can be leveraged to identify specific days with a unique clustering of adverse weather and pollution features which are associated with an increases risk of acute cardiovascular events, especially cerebrovascular events.

Download Full-text

The prognostic importance of serum sodium levels at hospital discharge and one‐year mortality among hospitalized patients

International Journal of Clinical Practice ◽

10.1111/ijcp.13581 ◽

2020 ◽

Vol 74 (10) ◽

Author(s):

Charat Thongprayoon ◽

Wisit Cheungpasitporn ◽

Tananchai Petnak ◽

Ranine Ghamrawi ◽

Sorkko Thirunavukkarasu ◽

...

Keyword(s):

Hospital Discharge ◽

Serum Sodium ◽

Hospitalized Patients ◽

Prognostic Importance ◽

One Year

Download Full-text

Analysis of the mandibular canal course using unsupervised machine learning algorithm

PLoS ONE ◽

10.1371/journal.pone.0260194 ◽

2021 ◽

Vol 16 (11) ◽

pp. e0260194

Author(s):

Young Hyun Kim ◽

Kug Jin Jeon ◽

Chena Lee ◽

Yoon Joo Choi ◽

Hoi-In Jung ◽

...

Keyword(s):

Machine Learning ◽

Cluster Analysis ◽

Learning Algorithm ◽

Mandibular Canal ◽

Unsupervised Machine Learning ◽

Computed Tomography Images ◽

Significant Difference ◽

Cluster 2 ◽

Axial View

Objectives Anatomical structure classification is necessary task in medical field, but the inevitable variability of interpretation among experts makes reliable classification difficult. This study aims to introduce cluster analysis, unsupervised machine learning method, for classification of three-dimensional (3D) mandibular canal (MC) courses, and to visualize standard MC courses derived from cluster analysis in the Korean population. Materials and methods A total of 429 cone-beam computed tomography images were used. Four sites in the mandible were selected for the measurement of the MC course and four parameters, two vertical and two horizontal parameters were measured per site. Cluster analysis was carried out as follows: parameter measurement, parameter normalization, cluster tendency evaluation, optimal number of clusters determination, and k-means cluster analysis. The 3D MC courses were classified into three types with statistically significant mean differences by cluster analysis. Results Cluster 1 showed a smooth line running towards the lingual side in the axial view and a steep slope in the sagittal view. Cluster 2 ran in an almost straight line closest to the lingual and inferior border of mandible. Cluster 3 showed the pathway with a bent buccally in the axial view and an increasing slope in the sagittal view in the posterior area. Cluster 2 showed the highest distribution (42.1%), and males were more widely distributed (57.1%) than the females (42.9%). Cluster 3 comprised similar ratio of male and female cases and accounted for 31.9% of the total distribution. Cluster 1 had the least distribution (26.0%) Distributions of the right and left sides did not show a statistically significant difference. Conclusion The MC courses were automatically classified as three types through cluster analysis. Cluster analysis enables the unbiased classification of the anatomical structures by reducing observer variability and can present representative standard information for each classified group.

Download Full-text

Lower Serum Sodium Is Associated With Increased Short-Term Mortality in Hospitalized Patients With Worsening Heart Failure

Circulation ◽

10.1161/01.cir.0000165065.82609.3d ◽

2005 ◽

Vol 111 (19) ◽

pp. 2454-2460 ◽

Cited By ~ 313

Author(s):

Liviu Klein ◽

Christopher M. O’Connor ◽

Jeffrey D. Leimberger ◽

Wendy Gattis-Stough ◽

Ileana L. Piña ◽

...

Keyword(s):

Heart Failure ◽

Serum Sodium ◽

Hospitalized Patients ◽

Short Term ◽

Lower Serum ◽

Short Term Mortality

Download Full-text

Serum Chloride Levels at Hospital Discharge and One-Year Mortality among Hospitalized Patients

Medical Sciences ◽

10.3390/medsci8020022 ◽

2020 ◽

Vol 8 (2) ◽

pp. 22 ◽

Cited By ~ 1

Author(s):

Tananchai Petnak ◽

Charat Thongprayoon ◽

Wisit Cheungpasitporn ◽

Tarun Bathini ◽

Saraschandra Vallabhajosyula ◽

...

Keyword(s):

Hospital Discharge ◽

Mortality Risk ◽

Serum Sodium ◽

Reference Group ◽

Hazard Analysis ◽

Serum Bicarbonate ◽

Tertiary Referral Hospital ◽

Serum Chloride ◽

Increased Risk ◽

One Year

This study aimed to assess the one-year mortality risk based on discharge serum chloride among the hospital survivors. We analyzed a cohort of adult hospital survivors at a tertiary referral hospital from 2011 through 2013. We categorized discharge serum chloride; ≤96, 97–99, 100–102, 103–105, 106–108, and ≥109 mmoL/L. We performed Cox proportional hazard analysis to assess the association of discharge serum chloride with one-year mortality after hospital discharge, using discharge serum chloride of 103–105 mmoL/L as the reference group. Of 56,907 eligible patients, 9%, 14%, 26%, 28%, 16%, and 7% of patients had discharge serum chloride of ≤96, 97–99, 100–102, 103–105, 106–108, and ≥109 mmoL/L, respectively. We observed a U-shaped association of discharge serum chloride with one-year mortality, with nadir mortality associated with discharge serum chloride of 103–105 mmoL/L. When adjusting for potential confounders, including discharge serum sodium, discharge serum bicarbonate, and admission serum chloride, one-year mortality was significantly higher in both discharge serum chloride ≤99 hazard ratio (HR): 1.45 and 1.94 for discharge serum chloride of 97–99 and ≤96 mmoL/L, respectively; p < 0.001) and ≥109 mmoL/L (HR: 1.41; p < 0.001), compared with discharge serum chloride of 103–105 mmoL/L. The mortality risk did not differ when discharge serum chloride ranged from 100 to 108 mmoL/L. Of note, there was a significant interaction between admission and discharge serum chloride on one-year mortality. Serum chloride at hospital discharge in the optimal range of 100–108 mmoL/L predicted the favorable survival outcome. Both hypochloremia and hyperchloremia at discharge were associated with increased risk of one-year mortality, independent of admission serum chloride, discharge serum sodium, and serum bicarbonate.

Download Full-text

Classification of Observations through Combination of the Dimension Reduction and the Cluster Analysis

International Journal of Advanced Research in Computer Science and Software Engineering ◽

10.23956/ijarcsse.v7i8.13 ◽

2017 ◽

Vol 7 (8) ◽

pp. 30

Author(s):

Hyeuk Kim

Keyword(s):

Machine Learning ◽

Principal Component Analysis ◽

Cluster Analysis ◽

Unsupervised Learning ◽

Principal Component ◽

Component Analysis ◽

Baseball Players ◽

Partitioning Around Medoids ◽

Different Characteristics

Unsupervised learning in machine learning divides data into several groups. The observations in the same group have similar characteristics and the observations in the different groups have the different characteristics. In the paper, we classify data by partitioning around medoids which have some advantages over the k-means clustering. We apply it to baseball players in Korea Baseball League. We also apply the principal component analysis to data and draw the graph using two components for axis. We interpret the meaning of the clustering graphically through the procedure. The combination of the partitioning around medoids and the principal component analysis can be used to any other data and the approach makes us to figure out the characteristics easily.

Download Full-text