Pediatric sepsis phenotypes for enhanced therapeutics: An application of clustering to electronic health records

Abstract

Objective The heterogeneity of pediatric sepsis patients suggests the potential benefits of clustering analytics to derive phenotypes with distinct host response patterns that may help guide personalized therapeutics. We evaluate the relative performance of latent class analysis (LCA) and K‐means, 2 commonly used clustering methods toward the derivation of clinically useful pediatric sepsis phenotypes. Methods Data were extracted from anonymized medical records of 6446 pediatric patients that presented to 1 of 6 emergency departments (EDs) between 2013 and 2018 and were thereafter admitted. Using International Classification of Diseases (ICD)‐9 and ICD‐10 discharge codes, 151 patients were identified with a sepsis continuum diagnosis that included septicemia, sepsis, severe sepsis, and septic shock. Using feature sets used in related clustering studies, LCA and K‐means algorithms were used to derive 4 distinct phenotypic pediatric sepsis segmentations. Each segmentation was evaluated for phenotypic homogeneity, separation, and clinical use. Results Using the 2 feature sets, LCA clustering resulted in 2 similar segmentations of 4 clinically distinct phenotypes, while K‐means clustering resulted in segmentations of 3 and 4 phenotypes. All 4 segmentations identified at least 1 high severity phenotype, but LCA‐identified phenotypes reflected superior stratification, high entropy approaching 1 (eg, 0.994) indicating excellent separation between estimated phenotypes, and differential treatment/treatment response, and outcomes that were non‐randomly distributed across phenotypes ( P < 0.001). Conclusion Compared to K‐means, which is commonly used in clustering studies, LCA appears to be a more robust, clinically useful statistical tool in analyzing a heterogeneous pediatric sepsis cohort toward informing targeted therapies. Additional prospective studies are needed to validate clinical utility of predictive models that target derived pediatric sepsis phenotypes in emergency department settings.

Refining empiric subgroups of pediatric sepsis using machine-learning techniques on observational data

“…On the other hand, Phenotype 2 is characterized by low severity with only a few elevated WBC parameters, phenotype 3 shows moderate severity with mild tachypnea, and phenotype 4 presents high severity with liver dysfunction with hypoxia. These 4 phenotypes were found to match well with the phenotypes from the other data set, demonstrating moderate reproducibility ( 60 ).…”

“…For example, Koutroulis et al, 2022 and ( 61 , 62 ) estimated the smallest sample size to delineate phenotypes through simulation experiments. As a result, both found that 150 samples were enough to identify 4 distinct phenotypes with 80% power ( 60 ).…”

Identification and Prediction of Clinical Phenotypes in Hospitalized Patients With COVID-19: Machine Learning From Medical Records

“…Concerning potential methodological weaknesses of this study, it should be noted that, in a head-to-head comparison of LCA versus k-means clustering in a relatively small sample of pediatric patients with sepsis (n=151), LCA was found to be somewhat more useful in identifying homogeneous phenotypes. However, both approaches identified at least one distinct high-severity phenotype [ 96 ]. Given that LCA is computationally challenging whereas k-means is better scaled to large data sets [ 97 ], most critical medicine clustering studies involving large cohorts (N>1000) in sepsis [ 20 ], ARDS [ 98 ], and COVID-19 [ 99 , 100 ] have effectively used k-means to identify well-separated phenotypes, leading to early detection of those who would benefit from certain treatments and close monitoring.…”

Novel digital approaches to the assessment of problematic opioid use

“…ML algorithms, in addition to detecting occurrences of a particular phenotype, can also enrich current phenotypes by expanding them into levels of severity or subtypes. As examples, two recent papers used latent class analysis to identify sub-phenotypes of acute respiratory distress syndrome [121] and pediatric sepsis [122]. Elucidating phenotype stratification is important as different sub-phenotypes often require different treatment strategies and responses.…”