Lessons Learned in the Development of a Computable Phenotype for Response in Myeloproliferative Neoplasms

Sholle, Evan; Krichevsky, Spencer; Scandura, Joseph M.; Sosner, Claudia; Campion, Thomas R.

doi:10.1109/ichi.2018.00045

Cited by 4 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of the 17 custom RDRs live as of July 2021, academic output includes but is not limited to that from Cardiac Imaging, 30 , 31 Digestive Care, 32 Mental Health, 33 , 34 Myeloproliferative Neoplasms, 35 , 36 Pulmonary and Critical Care, 37 , 38 and Stroke. 39 Largely driven by investigators with grant funding, RDR projects have generated data marts to address specific clinical research questions (eg, predictors of outcomes in hospitalized cirrhotic patients) while also yielding generalizable resources for the institution, such as an i2b2 eye exam ontology from Ophthalmology and surgical pathology report NLP from Urology.…”

Section: Resultsmentioning

confidence: 99%

An architecture for research computing in health to support clinical and translational investigators with electronic patient data

Campion

Sholle

Pathak

et al. 2021

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

Objective Obtaining electronic patient data, especially from electronic health record (EHR) systems, for clinical and translational research is difficult. Multiple research informatics systems exist but navigating the numerous applications can be challenging for scientists. This article describes Architecture for Research Computing in Health (ARCH), our institution’s approach for matching investigators with tools and services for obtaining electronic patient data. Materials and Methods Supporting the spectrum of studies from populations to individuals, ARCH delivers a breadth of scientific functions—including but not limited to cohort discovery, electronic data capture, and multi-institutional data sharing—that manifest in specific systems—such as i2b2, REDCap, and PCORnet. Through a consultative process, ARCH staff align investigators with tools with respect to study design, data sources, and cost. Although most ARCH services are available free of charge, advanced engagements require fee for service. Results Since 2016 at Weill Cornell Medicine, ARCH has supported over 1200 unique investigators through more than 4177 consultations. Notably, ARCH infrastructure enabled critical coronavirus disease 2019 response activities for research and patient care. Discussion ARCH has provided a technical, regulatory, financial, and educational framework to support the biomedical research enterprise with electronic patient data. Collaboration among informaticians, biostatisticians, and clinicians has been critical to rapid generation and analysis of EHR data. Conclusion A suite of tools and services, ARCH helps match investigators with informatics systems to reduce time to science. ARCH has facilitated research at Weill Cornell Medicine and may provide a model for informatics and research leaders to support scientists elsewhere.

show abstract

Section: Resultsmentioning

confidence: 99%

An architecture for research computing in health to support clinical and translational investigators with electronic patient data

Campion

Sholle

Pathak

et al. 2021

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

show abstract

“…We developed MPN-centered research database repository (RDR) infrastructure that aggregates curated data from our MPN Research Electronic Data Capture (REDCap) databases, raw and research-ready data from EMRs (Epic Systems, and Allscripts Enterprise Electronic Health Records), and data from external sources (eg. CDC National Death Index) for all clinical, laboratory, and outcomes data 11 using the Observational Medical Outcomes Partnership Common Data Model (OMOP-CDM). Patients with PV were initially identified by querying the database for International Classification of Disease (ICD) v9.0/10.0 or Systematized Nomenclature of Medicine – Clinical Terms (SNOMED-CT) codes consistent with a PV diagnosis.…”

Section: Methodsmentioning

confidence: 99%

“…All non-MPN medications were extracted from the EMR medex and categorized by SNOMED (Systemized Nomenclature of Medicine – Clinical Terms) classes 17 (Supplementary Table 1). Bone marrow findings were extracted and tabulated from clinical hematopathology reports, using a rigorously validated method of natural language processing as previously described 11 . Composite parameters, such as ELN risk (Low or High), the neutrophil-to-lymphocyte ratio (NLR) 18 , binarized age (<60 or >60 years) 19 , binarized JAK2 variant allele burden (<50% or >50%) 20 and others were calculated from primary extracted data (e.g., laboratory values, medications, pre-existing conditions) 18–20 (Supplementary Table 1).…”

Section: Methodsmentioning

confidence: 99%

Facilitating clinical trials in Polycythemia vera (PV) by identifying patient cohorts at high near-term risk of thrombosis using rich data and machine learning

Abu-Zeinah,

Krichevsky,

Erdos

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Thrombosis remains the leading cause of morbidity and mortality for patients (pts) with polycythemia vera (PV), yet PV clinical trials are not powered to identify interventions that improve thrombosis-free survival (TFS). Such trials are infeasible in a contemporary PV cohort, even when selecting high-risk pts based on Age >60 and thrombosis history, because thousands of patients would be required for a short-term study to meet TFS endpoint. To address this problem, we used artificial intelligence and machine learning (ML) to dynamically predict near-term (1-year) thrombosis risk in PV pts with high sensitivity and positive predictive value (PPV) to enhance pts selection. Our automation-driven data extraction methods yielded more than 16 million data elements across 1,448 unique variables (parameters) from 11,123 clinical visits for 470 pts. Using the AutoGluon framework, the Random Forest ML classification algorithm was selected as the top performer. The full (309-parameter) model performed very well (F1=0.91, AUC=0.84) when compared with the current ELN gold-standard for thrombosis risk stratification in PV (F1=0.1, AUC=0.39). Parameter engineering, guided by Gini feature importance identified the 21 parameters (top-21) most important for accurate prediction. The top-21 parameters included known, suspected and previously unappreciated thrombosis risk factors. To identify the minimum number of parameters required for the accurate ML prediction, we tested the performance of every possible combination of 3-9 parameters from top-21 (>1.6M combinations). High-performing models (F1> 0.8) most frequently included age (continuous), time since dx, time since thrombosis, complete blood count parameters, blood type, body mass index, and JAK2 mutant allele frequency. Having trained at tested over 1.6M practical ML models with a feasible number of parameters (3-9 parameters in top-21 most predictive), it is clear that study cohorts of patients with PV at high near-term thrombosis risk can be identified with high enough sensitivity and PPV to power a clinical trial for TFS. Further validation with external, multicenter cohorts is ongoing to establish a universal ML model for PV thrombosis that would facilitate clinical trials aimed at improving TFS.

show abstract

Synthesizing Dimensions of Digital Maturity in Hospitals: Systematic Review

et al. 2022

View full text Add to dashboard Cite

Background Digital health in hospital settings is viewed as a panacea for achieving the “quadruple aim” of health care, yet the outcomes have been largely inconclusive. To optimize digital health outcomes, a strategic approach is necessary, requiring digital maturity assessments. However, current approaches to assessing digital maturity have been largely insufficient, with uncertainty surrounding the dimensions to assess. Objective The aim of this study was to identify the current dimensions used to assess the digital maturity of hospitals. Methods A systematic literature review was conducted of peer-reviewed literature (published before December 2020) investigating maturity models used to assess the digital maturity of hospitals. A total of 29 relevant articles were retrieved, representing 27 distinct maturity models. The articles were inductively analyzed, and the maturity model dimensions were extracted and consolidated into a maturity model framework. Results The consolidated maturity model framework consisted of 7 dimensions: strategy; information technology capability; interoperability; governance and management; patient-centered care; people, skills, and behavior; and data analytics. These 7 dimensions can be evaluated based on 24 respective indicators. Conclusions The maturity model framework developed for this study can be used to assess digital maturity and identify areas for improvement.

show abstract

Lessons Learned in the Development of a Computable Phenotype for Response in Myeloproliferative Neoplasms

Cited by 4 publications

References 3 publications

An architecture for research computing in health to support clinical and translational investigators with electronic patient data

An architecture for research computing in health to support clinical and translational investigators with electronic patient data

Facilitating clinical trials in Polycythemia vera (PV) by identifying patient cohorts at high near-term risk of thrombosis using rich data and machine learning

Synthesizing Dimensions of Digital Maturity in Hospitals: Systematic Review

Contact Info

Product

Resources

About