TMThomas A. Miller

Thomas A. Miller

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Thomas A. Miller has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Ductus arteriosus closure and neurodevelopment in extremely low birth weight or preterm infants

    by Jonathan N. Flyer, Lauren E. Miller, Erika M. Edwards, Danielle E.Y. Ehret, Thomas A. Miller

  • Regional neurodevelopmental and psychosocial encounters for children with CHD: an updated validation cohort from Northern New England

    by Thomas Miller, Anya Cutler, Brooke Davey, Jonathan Flyer

    We have previously described how children with complex CHD access developmental and psychosocial services in Maine, most often beyond the reach of the surgical centre. In this follow-up study, we describe a similar pattern for children in Vermont. Of 406 at-risk children between 2017 and 2019, 37% had an encounter. Very few individuals underwent developmental assessment or psychological or neuropsychological testing (1–4%). Visit volume was highest for mental health assessments in children older than 5 years and occurred predominately in community clinics and private practices close to home.

  • Regional paediatric cardiac neurodevelopmental care: a survey of New England referral practices and institutional resources

    by Madeline E. Duncan, Brooke Davey, Jonathan Flyer, Susan Saleeb, Ruchika Karnik, Michael R. Epstein, Kristin Laraja, Jenifer A. Glatz, Thomas A. Miller

    Background: Reports of paediatric cardiac neurodevelopmental programmes are predominately limited to high-volume surgical centres. Regional characterisation of neurodevelopmental care practices across multiple centres both with and without cardiac surgery programmes has not yet been described.Objective: Assess cardiac neurodevelopmental infrastructure and approach across New England to describe regional support for children with CHD.Methods: A 16-item survey assessing inpatient and outpatient neurodevelopmental care practices was sent electronically via REDCap to all member institutions of the New England Congenital Cardiology Association Health Disparities Working Group. Centres were characterised by surgical capability, annual volume, and academic affiliation. Descriptive statistics and Fisher’s exact test were used for comparisons.Results: The survey response rate was 90% (9/10). Participating centres included non-surgical academic centres (55%), small surgical centres (22%) and medium-large surgical centres (22%). Surgical centres typically refer their patients to internal neurodevelopmental services (100%) and rely on automatic referral processes (100%). Non-surgical centres predominately refer to the institution where cardiac surgery was performed (80%) compared to engaging local teams (20%) and depend on family or physician-initiated referral (100%) to schedule neurodevelopmental services. While none of the non-surgical centres surveyed have cardiac-specific neurodevelopmental programmes, all have other developmental programmes that accommodate children with CHD.Conclusions: Varying neurodevelopmental infrastructure and resources are reported across New England. Academic, non-surgical centres may have infrastructure for neurodevelopmental follow-up despite not having cardiac neurodevelopmental programmes. Collaboration between surgical and non-surgical cardiac centres in New England may be leveraged to promote neurodevelopmental care closer to home.


  • Open Access

    An explainable artificial intelligence approach for predicting cardiovascular outcomes using electronic health records

    by Sergiusz Wesołowski, Gordon Lemmon, Edgar J. Hernandez, Alex Henrie, Thomas A. Miller, Derek Weyhrauch, Michael D. Puchalski, Bruce E. Bray, Rashmee U. Shah, Vikrant G. Deshmukh, et al.

    Understanding the conditionally-dependent clinical variables that drive cardiovascular health outcomes is a major challenge for precision medicine. Here, we deploy a recently developed massively scalable comorbidity discovery method called Poisson Binomial based Comorbidity discovery (PBC), to analyze Electronic Health Records (EHRs) from the University of Utah and Primary Children’s Hospital (over 1.6 million patients and 77 million visits) for comorbid diagnoses, procedures, and medications. Using explainable Artificial Intelligence (AI) methodologies, we then tease apart the intertwined, conditionally-dependent impacts of comorbid conditions and demography upon cardiovascular health, focusing on the key areas of heart transplant, sinoatrial node dysfunction and various forms of congenital heart disease. The resulting multimorbidity networks make possible wide-ranging explorations of the comorbid and demographic landscapes surrounding these cardiovascular outcomes, and can be distributed as web-based tools for further community-based outcomes research. The ability to transform enormous collections of EHRs into compact, portable tools devoid of Protected Health Information solves many of the legal, technological, and data-scientific challenges associated with large-scale EHR analyses.