Network Tomography for Understanding Phenotypic Presentations in Aortic Stenosis

Grace Casaclang-Verzosa, Sirish Shrestha, Muhammad Jahanzeb Khalil, Jung Sun Cho, Márton Tokodi, Sudarshan Balla, Mohamad Alkhouli, Vinay Badhwar, Jagat Narula, Jordan D. Miller, Partho P. Sengupta

Research output: Contribution to journalArticlepeer-review

22 Scopus citations


Objectives: This study sought to build a patient−patient similarity network using multiple features of left ventricular (LV) structure and function in patients with aortic stenosis (AS). The study further validated the observations in an experimental murine model of AS. Background: The LV response in AS is variable and results in heterogeneous phenotypic presentations. Methods: The patient similarity network was developed using topological data analysis (TDA) from cross-sectional echocardiographic data collected from 246 patients with AS. Multivariate features of AS were represented on the map, and the network topology was compared with that of a murine AS model by imaging 155 animals at 3, 6, 9, or 12 months of age. Results: The topological map formed a loop in which patients with mild and severe AS were aggregated on the right and left sides, respectively (p < 0.001). These 2 regions were linked through moderate AS; with upper arm of the loop showing patients with predominantly reduced ejection fractions (EFs), and the lower arm showing patients with preserved EFs (p < 0.001). The region of severe AS showed >3 times the increased risk of balloon valvuloplasty, and transcatheter or surgical aortic valve replacement (hazard ratio: 3.88; p < 0.001) compared with the remaining patients in the map. Following aortic valve replacement, patients recovered and moved toward the zone of mild and moderate AS. Topological data analysis in mice showed a similar distribution, with 1 side of the loop corresponding to higher peak aortic velocities than the opposite side (p < 0.0001). The validity of the cross-sectional data that revealed a path of AS progression was confirmed by comparing the locations occupied by 2 groups of mice that were serially imaged. LV systolic and diastolic dysfunction were frequently identified even during moderate AS in both humans and mice. Conclusions: Multifeature assessments of patient similarity by machine-learning processes may allow precise phenotypic recognition of the pattern of LV responses during the progression of AS.

Original languageEnglish (US)
Pages (from-to)236-248
Number of pages13
JournalJACC: Cardiovascular Imaging
Issue number2
StatePublished - Feb 2019


  • aortic stenosis
  • left ventricular function
  • patient similarity
  • topological data analysis

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Cardiology and Cardiovascular Medicine


Dive into the research topics of 'Network Tomography for Understanding Phenotypic Presentations in Aortic Stenosis'. Together they form a unique fingerprint.

Cite this