Learning a Comorbidity-Driven Taxonomy of Pediatric Pulmonary Hypertension

Abstract

Rationale Pediatric pulmonary hypertension (PH) is a heterogeneous condition with varying natural history and therapeutic response. Precise classification of PH subtypes is therefore crucial for individualizing care. However, gaps remain in our understanding of the spectrum of PH in children. Objective We seek to study the manifestations of PH in children, and to assess the feasibility of applying a network-based approach to discern disease subtypes from comorbidity data recorded in longitudinal datasets. Methods and Results A retrospective cohort study comprising 6,943,263 children (<18 years of age) enrolled in a commercial health insurance plan in the US, between January 2010 and May 2013. A total of 1,583 (0.02%) children met the criteria for PH. We identified comorbidities significantly associated with PH compared with the general population of children without PH. A Bayesian comorbidity network was constructed to model the interdependencies of these comorbidities, and network clustering analysis was applied to derive disease subtypes comprising subgraphs of highly connected comorbid conditions. A total of 186 comorbidities were found to be significantly associated with PH. Network analysis of comorbidity patterns captured most of the major PH subtypes with known etiological basis defined by the World Health Organization and Panama classifications. The analysis further identified a number of subtypes documented in only a few case studies, including rare subtypes associated with several well-described genetic syndromes. Conclusions Application of network science to model comorbidity patterns recorded in longitudinal datasets can facilitate the discovery of disease subtypes. Our analysis relearned established subtypes, thus validating the approach, and identified rare subtypes that are difficult to discern through clinical observations, providing impetus for deeper investigation of the disease subtypes that will enrich current disease classifications.

Common Variable Immunodeficiency Non-Infectious Disease Endotypes Redefined Using Unbiased Network Clustering in Large Electronic Datasets

“…Together these data suggest that PH and solid organ malignancy, including skin and cervical cancer as the major etiologies identified here, may be underrecognized complications in CVID. Consistent with these data, recent retrospective analysis of 1,583 pediatric PH cases identified an unexpected association with primary immune deficiency (OR 37.9) ( 50 ). Further detailed analyzes are underway in the Partners cohort to determine the underlying pathophysiology and importantly, whether additional screening is required for these complications in the CVID demographic moving forward.…”

Network Analysis to Risk Stratify Patients With Exercise Intolerance

“…A number of recent reports have expanded the clinical characteristics of diseases that influence exercise performance, such as heart failure with preserved ejection fraction, 14 chronic obstructive pulmonary disease, 15 and sarcopenia 16 , among others. 17 However, comprehensive studies utilizing network-based methods to analyze exercise performance directly are lacking. Moreover, prior reports investigating the clinical relevance of analyzing combinations of exercise measurements have aimed to alter the diagnostic yield for a specific disease sub-type, such as adjusting the pulmonary artery pressure threshold at peak exercise to inform the prevalence of ‘exercise-induced pulmonary hypertension’.…”

The application of big data to cardiovascular disease: paths to precision medicine

“…Clinical networks, in which nodes and links are represented by physiological parameters and physiological effects, respectively, have been reported on a small scale (97). Although comprehensive information on a larger "physiome" remains a goal, a modified approach using correlative networks has already proven useful in numerous venues, including comorbidity-driven schemata that improve pediatric cardiovascular disease diagnostics, and reports that clarify the clinical heterogeneity of patients with chronic obstructive pulmonary disease, a common cardiovascular disease comorbidity (98,99).…”