AMIA 2021 Virtual Informatics Summit Panels

Monday, March 22

S01: Panel - The Digital Recipe for Success: Conducting Clinical Research Using Mobile Apps

A. Turchin, Brigham and Women's Hospital; M. Kamdar, Massachusetts General Hospital; J. Onnela, Harvard T. H. Chan School of Public Health; T. Smith, Brigham and Women's Hospital

Digital revolution is coming to clinical research. Mobile applications can both be used to study traditional – medication- and device-based – therapeutic interventions and can also form the basis of medical interventions themselves. However, using mobile applications as the tools of clinical research is often different in many ways from using pen and paper or even online tools to record participants’ data. Evaluating the effectiveness of mobile applications for diagnosis and treatment of medical conditions difference also presents many new opportunities and challenges compared to the conventional clinical trials. To help researchers, clinicians and developers of mHealth applications learn how to take advantage of the strengths and navigate the pitfalls of using mobile applications in clinical research. The panelists will discuss their experience studying mHealth apps in special patient populations, using them as innovative tools for clinical research and recruiting participants for mHealth clinical trials.

S03: Panel - Working Towards Shareable and Interoperable Patient and Clinician Facing Clinical Decision Support - Experiences from the Field

R. Gamache, AHRQ; L. Marcial, RTI International; K. Miller, MedStar Health; J. Richardson, RTI International

A confluence of efforts is changing clinical decision support (CDS) from siloed knowledge management efforts within single institutions to open-source efforts that leverage rapidly evolving standards that enable healthcare organizations to share and implement CDS. This panel provides perspectives from the Agency for Healthcare Research and Quality and its goals for promoting a more robust CDS ecosystem through two funded projects that leverage standards-based, interoperable, and shareable knowledge artifacts in real-world settings for pain management. The panelists will each provide their unique perspectives based on their projects’ activities for developing and implementing those knowledge artifacts and share how their experiences can inform future efforts to meet the needs for standards-based and interoperable CDS that support patients and providers. The speakers will also address the challenges for developing and implementing CDS that meet the needs of multiple stakeholders within the key area of chronic pain management.

S05: Panel - Data Acquisition and Harmonization of COVID-19 Case Data Across Common Data Models: Early Field Reports from the National COVID Cohort Collaborative (N3C)

E. Pfaff, UNC Chapel Hill; S. Hong, D. Jiao, X. Zhang, C. Chute, Johns Hopkins University

The National COVID Cohort Collaborative (N3C), sponsored by the National Center for Advancing Translational Sciences (NCATS) is a partnership among Clinical Translational Science Awardees (CTSAs) and other academic medical centers; the National Center for Data to Health (CD2H); and members and subject matter experts from Observational Health Data Sciences and Informatics (OHDSI), PCORnet, the Accrual to Clinical Trials (ACT) network, and TriNetX. N3C’s goals are to demonstrate that a “multi-site collaborative learning health network can overcome barriers to rapidly build a scalable infrastructure incorporating multi-organizational clinical data for COVID-19 analytics. This panel is composed of informaticians supporting the data acquisition, ingestion and harmonization processes of N3C, with a focus on phenotype development and implementation, building the data ingestion pipeline, improving COVID test results from early data sets and developing and implementation of a data quality framework for the project.

S06: Panel - Unlocking Clinical Concepts Embedded in Unstructured Text to Advance COVID-19 Analytics for National COVID Cohort Collaborative (N3C)

H. Liu, Mayo Clinic; R. Fuentes, National Institute of Health; J. Guinney, Sage Bionetworks; S. Liu, Mayo Clinic; P. Szolovits, Massachusetts Institute of Technology; H. Xu, The University of Texas Health Science Center at Houston

The National COVID Cohort Collaborative (N3C) aims to assemble a multi-site learning health infrastructure with electronic health record (EHR) data for a nationwide cohort made available for COVID-19 analytics. One known challenge of EHR-based observational studies is that detailed patient information required by a study often resides in clinical narratives. Various natural language processing (NLP) technologies have been investigated to accelerate the use of clinical narratives for rapid clinical research. This panel describes a collaborative effort among Clinical Data to Health (CD2H), Open Health Natural Language Processing (OHNLP), and Observational Health Data Sciences and Informatics (OHSDI) NLP towards a national clinical NLP ecosystem.

S11: Panel - Lessons Learned from Healthcare Organizations Contributing Clinical Data to the National COVID Cohort Collaborative (N3C)

S. Meystre, Medical University of South Carolina; R. Gouripeddi, University of Utah; J. Harper, Regenstrief Institute; J. Talbert, University of Kentucky

The COVID-19 pandemic was officially declared by the World Health Organization in March 2020, after initial cases declared in China and a worldwide expansion. The first case in the U.S. was confirmed in January and a rapid expansion to all 50 U.S. states followed. We have seen a scattered approach for data collection and public data sets not being adequately available to explain the disease progression and key insights remaining unavailable to the public. To enable data sharing and collaborative research focused on COVID-19 across healthcare organizations in the U.S., the National COVID Cohort Collaborative (N3C) was created in the Spring of 2020 with support from NCATS and a focus on CTSA program hubs. It fostered a rapidly growing collaborative network of healthcare organizations and research communities. At the end of August 2020, more than 20 healthcare organizations were already sharing clinical data with N3C regularly. In order to share clinical data with N3C, participating healthcare organizations have to go through several steps and ensure availability of clinical data in a selection of data models (OMOP CDM, PCORnet, ACT, or TriNetX). This panel features speakers from four academic healthcare organizations currently sharing clinical data with N3C. They will share their institution and practical experiences, ideas and advice for healthcare organizations already sharing or planning to share clinical data with N3C.

S14: Panel - Implementability of Deep Learning based Predictive Models: Bridging Data Science Research and Real-world Practice

L. Rasmy, A. Ross, UTHealth; K. McGrow, Microsoft; R. Murphy, D. Zhi, UTHealth

With the abundant availability of secondary electronic health record (EHR) data, researchers start to focus on developing predictive algorithms using such big clinical data. Deep learning (DL)-based models are offering promising prediction accuracy and proved to outperform traditional statistical or machine learning algorithms. Yet, we rarely see those models implemented or validated in practice. Data scientists need to consider the implementability of those models during the development phase to facilitate clinicians' acceptance for further clinical validation. The main objective of this panel is to identify factors associated with the implementability of DL-based predictive models. We will define each factor in the context of predictive modeling of clinical events and describe how it impacts the feasibility of the model implementation. We will also discuss the magnitude of the impact of each factor and how to objectively measure or evaluate it.

S15: Panel - Intelligent Integrative Informatics Approaches for Big Data Aggregation, Sharing and Analytics in Stem Cell Research

J. Finkelstein, Icahn School of Medicine at Mount Sinai; F. Shaya, University of Maryland; K. Borziak, Icahn School of Medicine at Mount Sinai; C. Macarthur, University of Southampton; A. Ma'ayan, Icahn School of Medicine at Mount Sinai

Advancements in regenerative medicine have brought to the forefront the need for increased standardization and sharing of stem cell product characterization to help drive these innovative interventions toward public availability. Although numerous stem cell databases exist and attempts have been made to standardize stem cell characterization, there is still a lack of a platform that incorporates heterogeneous stem cell information into a harmonized project-based framework. The aim of this panel is to introduce approaches for intelligent integration of heterogenous data sets generated in the course of preclinical and interventional stem cell research as well as discuss promising big data applications in this area targeting prediction of stem cell fate and explaining regenerative potency. Panelists from early adopter institutions will compare their experiences in aggregating and analyzing stem cell data. Key implementation issues that will be addressed by the panelist include common data elements, regulatory and ethical requirements, agile and flexible data hub development, and promising data analytics approaches.

S16: Panel - Are We There Yet? Finding, Analyzing, and Using Better Information for Pandemics

K. Fultz Hollis, Oregon Health & Sciences University; N. Tatonetti, Columbia University; S. McGrath, Providence Health and Services

How do we find and analyze better and accurate information to study and report pandemics like COVID-19? This panel intends to bring together translational informaticians working on COVID data and a prominent journalist from Bloomberg News who specializes in medical science reporting. We will present both good examples of pandemic data science appearing in journals and the news as well as look at where we might not be best at explaining a pandemic to a community. For the AMIA 2021 Summits, we will attempt to bring participants what we as informaticians need: to present an integrated set of perspectives or experience on COVID-19 information and how we use this information to study the science and work to treat the disease.

Tuesday, March 23

S19: Panel - Evidence-based Tools and Strategies for Evaluating the Safety of Health Information Technology Systems: The State of Practice, Challenges, and the Road Ahead

A. Dietz, U.S. Department of Veterans Affairs; D. Classen, University of Utah School of Medicine, Pascal Metrics; T. Kuruganti, Oak Ridge National Laboratory; M. Rosen, Johns Hopkins University School of Medicine, Johns Hopkins Bloomberg School of Public Health, Johns Hopkins School of Nursing; J. Scott, U.S. Department of Veterans Affairs

Learning health systems need evidence-based methods to detect vulnerabilities within health information technology (HIT) systems and to identify strategies to mitigate risk. The application of such approaches is critical for ensuring the safety of HIT systems not just at deployment, but that (1) existing systems continue to function properly and that (2) organizational leadership and governance structures are in place to manage the safety of operations. This panel brings together leaders in the field of health care informatics to discuss the development and validation of prominent HIT evaluation tools and best practices, their application and lessons learned, and what the future may bring for evaluating HIT safety. Specific learning objectives for this panel include: (1) Identify ways to evaluate HIT system performance, (2) Understand the tradeoffs between different methods and approaches for evaluating HIT safety, (3) Determine how to translate evaluation findings to foster organizational learning and continuous improvement.

S20: Panel - Computable Phenotypes: A Primer on Creation, Evaluation, and Applications

M. Weiner, Weill Cornell Medicine; N. Tatonetti, Columbia University Irving Medical Center; J. Brown, Harvard Medical School; L. Bastarche, Vanderbilt University

Computable phenotypes (CPs) are programmable specifications of patient characteristics that enable identification of cohorts of similar individuals from electronic health data. The appropriate development, evaluation and application of CPs are all active areas of informatics research that are critical to our understanding of the scope and course of disease and effective therapeutics. This panel will describe the idiosyncrasies of clinical data that need to be considered in defining a CP. We will discuss the variety of methods used to evaluate the accuracy of a CP and address the implications of these differences. The panel will also provide practical examples of applications of CPs in clinical research, GWAS and PheWAS studies, and show how different decisions in developing and evaluating the CP can impact the results and interpretation of research findings.

S21: Panel - Harmonizing What to Analyze in the National COVID Cohort Collaborative (N3C): Lessons Learned

S21: Panel - Harmonizing What to Analyze in the National COVID Cohort Collaborative (N3C): Lessons Learned

The National COVID Cohort Collaborative (N3C) was established to provide patient-level data to further COVID-19 research. While the data are made available for research in the form in which they were submitted, providing constructs of the data should make that research go faster, be more consistent across projects, and more transparent. This panel, comprising informaticians, domain experts, data scientists, and experts in common data models, will describe the process by which we selected which variables needed harmonization, how we accomplished and vetted that harmonization, and how we made public that process and their results for over hundreds of variables and code sets. Our experience has implications for others involved in large-scale projects of pooled electronic health record data.

S26: Panel - Performance of COVID-19 Research in the CTSA ACT Network

S. Murphy, Massachusetts General Hospital, Harvard Medical School; M. Morris, University of Pittsburgh; D. Ranganathan, University of Chicago; J. Klann, Massachusetts General Hospital, Harvard Medical School; G. Weber, Harvard Medical School

The Accrual for Clinical Trials (ACT) NIH Research Network was established for CTSA-attached organizations to perform Electronic Health Record research on COVID-19 infections. The goal for performing research in the ACT network is to allow participation from all joining institutions to create hypotheses and perform analyses across the network. We began during the 2020 pandemic to assemble and work with the pieces that could enable not only general health record queries, but focused questions that were arising from the pandemic. This could be achieved by a joint effort that allowed specifically constructed COVID-19 ontologies to be applied to the site data, analytic programs to be built and run at local sites, data quality to be assessed and validated at the sites, and governance to allow results to be pooled and published. The methods, tools and data structures used are open source and can be feely learned, exchanged, and reproduced.

Wednesday, March 24

S27: Panel - Extracting Clinical Data from EHRs to Support Research: Early Lessons from the Cancer Moonshot’s IMPACT Consortium

J. Popovic, RTI International; R. Jensen, National Cancer Institute; P. Rahman, Mayo Clinic; F. Wehbe, Northwestern University; M. Hassett, Dana-Farber Cancer Institute

In 2018, the National Cancer Institute established an initiative to fund a consortium that aims to improve the monitoring and management of patients’ cancer-related symptoms. The Improving the Management of symPtoms during And following Cancer Treatment (IMPACT) consortium is supported by funding provided through the Cancer MoonshotSM, and is comprised of three research centers (RCs) and a coordinating center (CC) tasked with collecting and sharing symptom data from across the cancer care continuum. One data stream includes elements from each RC’s electronic health record (EHR) system, including patient demographics and associated clinical data such as diagnoses, procedures and medications. Despite each RC utilizing the same EHR vendor platform, a standardized approach to extracting data across sites has proven deceptively challenging. This panel will highlight RCs’ varied approaches, challenges, and solutions. Learning objectives include understanding current EHR data extraction and standardization approaches and the potential that emerging technologies may hold.

S29: Panel - Tales from the Front Line - What Happens Between Here and There with HL7 Data Exchanges

S. Mitchell, Veterans Administration; F. Martin, VVI, Inc. - VISION, VALUE, IMPACT; M. Layden, Veterans Administration; J. Vogt, Meditech; E. Lachance, PathogenDx

Too often, health care interoperability success is defined merely as the technology exchange without considering the content. True interoperability is realized only when the entire health care ecosystem has easy access to high-quality clinical data.

In VA’s journey to become a high reliability organization, the Veterans Health Information Exchange (VHIE) Clinical Data Quality Team took a deep dive into production data, developed evaluations and scoring tools, and actively engaged health care actors for insights into the state of clinical data and identify opportunities in the health care ecosystem where it could be improved. We propose that every actor in the health care ecosystem has a role to play in improving clinical data quality, advancing interoperability, and facilitating better decisions and research. Through engagement and education of actors (e.g. health care organizations, vendors, clinicians, standards organizations), we can collectively shape a very real and tangible impact on people’s lives.

S31: Panel - Consortium for Clinical Characterization of COVID-19 by EHR (4CE)

G. Weber, Harvard Medical School; G. Brat, Beth Israel Deaconess Medical Center; S. Murphy, Massachusetts General Hospital; D. Keogh, i2b2 tranSMART Foundation

There are several large, national and international projects to build informatics infrastructure to analyze the electronic health record (EHR) data of patients with COVID-19. However, aggregating data from multiple EHRs only works if you can trust the final results. This means being able to talk to the people at each site who know the data best, to understand the local clinical guidelines, coding practices, data quality problems, and other factors that affect the data. In March 2020, we launched an international effort called the Consortium for Clinical Characterization of COVID-19 by EHR (4CE), which brings together more than 100 informatics experts, statisticians, and physicians representing 200+ hospitals around the world. We run analyses locally within sites and share aggregate results centrally, where we review the data together and iteratively fix any issues. Through this process, we have identified key laboratory tests associated with COVID-19 disease severity.

Thursday, March 25

S42: Panel - Health Information Technology Interoperability Standards to Advance the Precision Medicine Initiative

T. Zayas Caban, T. Okubo, Office of the National Coordinator for Health Information Technology; R. Freimuth, Mayo Clinic; I. Sim, University of California, San Francisco

The Precision Medicine Initiative (PMI) ushers in a new area of health care delivery centered on tailoring prevention and treatment to an individual’s unique characteristics. Success of the PMI hinges on the ability to collect and analyze large electronic datasets. PMI projects led by the Office of the National Coordinator for Health Information Technology (ONC) are accelerating standards development for health information technology (IT) for research; specifically, standards needed to collect relevant data for the PMI. This panel will provide timely information about these projects, being conducted in close collaboration with the All of Us Research Program, a foundational component of the PMI led by the National Institutes of Health. The panel will describe other innovative collaborations to realize the PMI’s potential—Sync for Science, Sync for Genes, and Advancing Standards for Precision Medicine. The panel will actively encourage participant interaction and feedback, essential to informing and strengthening future priorities.

S43: Panel - Virtually Ready: Technological Tools and Adaptations in a Children’s Hospital during the COVID-19 Pandemic

T. Rungvivatjarus, B. Lee, A. Chong, M. Bialostozky, J. Huang, C. Kuelbs, University of California San Diego, Rady Children's Hospital

In this current COVID-19 pandemic, healthcare systems across the country have undergone drastic changes in patient care and operational workflow. The distribution of up-to-date and reliable information to healthcare workers, patients, and the community is also of paramount importance. Pediatric institutions are undergoing similar changes. In this panel, we outlined the various technological tools/adaptations and organizational changes that occurred at our academic institution in the midst of the COVID-19 pandemic. With panelists from various backgrounds and administrative roles, we will share our experiences in leading organizational changes from the informatics perspective and engage the audience in the different ways to leverage telemedicine, conserve personal protective equipment (PPE), provide clinical decision support, disseminate real-time organizational data, and optimize communication and access to care for families. In a pandemic, healthcare systems need to prepare for sudden and frequent changes in patient care and disruption of usual workflows.

S44: Panel - FHIR in the Research Continuum: The Emerging Vulcan FHIR Accelerator

C. Jaffe, Health Level 7 (HL7), University of California at San Diego; M. Tripathi, Arcadia; V. Nguyen, Stratametrics; J. Campbell, Epic; C. McDonald, National Library of Medicine; C. Chute, Johns Hopkins University

HL7 FHIR (Fast Healthcare Interoperability Resources) is now 10 years old. To date, it has been implemented in over 5000 sites worldwide. FHIR supports the broad continuum including patient care, population health, evolving payment models and clinical research. In March of last year, both the Center for Medicare and Medicaid Services (CMS) and the Office of the National Coordinater for Health IT (ONC) released two complementary Final Rules to improve the Interoperability of health data. The HL7 FHIR Accelerator Program has been the principal enabler of FHIR implementation. Vulcan, the newest FHIR Accelerator, is dedicated to enabling regulated and non-regulated research. This panel will explore the emergence of FHIR implementation across the broad continuum of biomedical research, regulated clinical research and population health.

S45: Panel - Using Synthetic Data to Enhance Antimicrobial Use Data Quality within the National Healthcare Safety Network

W. Wise, Centers for Disease Control and Prevention, Lantana Consulting Group; S. Nachimuthu, Veterans Affairs Salt Lake City Health Care System, University of Utah School of Medicine; J. Chuong, Asolva; J. Kim, Cerner Corporation; S. Zheng, Centers for Disease Control and Prevention

The Centers for Disease Control and Prevention’s (CDC) National Healthcare Safety Network (NHSN) Team partnered with the Veterans Affairs (VA) Informatics, Decision-Enhancement and Analytic Sciences (IDEAS 2.0) Center at the VA Salt Lake City Health Care System to create an Antimicrobial Use (AU) synthetic data set (SDS) and a vendor software validation process. NHSN will require all vendor systems electronically submitting AU data to NHSN be validated by January 2021 using the AU SDS.

The panel will provide an overview of the AU SDS and validation process along with a discussion of challenges faced including lessons learned during the implementation of this unique validation effort for NHSN data. Panelists will speak about the motivation, insights and methods behind the AU SDS and the validation process. Additionally, two vendors that have successfully completed the AU SDS validation process will share their experiences completing the validation process.

S46: Panel - Machine Learning to Improve Care Delivery: Opportunities and Challenges

K. Wagholikar, Harvard Medical School; J. Pathak, Cornell University; H. Liu, Mayo Clinic; N. Shah, Stanford University; S. Murphy, Harvard Medical School

Stratification of patients into clinical cohorts is a critical task for academic research and clinical operations—accurate cohorts facilitate epidemiological analysis and enable efficient population programs for clinical interventions, respectively. Cohort identification technologies based on machine learning (ML)— referred to as phenotyping – have been pioneered by the academic community, and they are being increasingly used for optimizing clinical operations. The resulting data-infrastructure offers a unique opportunity to drive the optimal utilization of existing therapies. However, successful adoption of phenotyping approaches requires advances in methodology as well as technological and cultural changes in the healthcare ecosystem. This panel brings together experts from a diverse set of health systems and aims to provide insights for using ML in the clinical setting. Each of the panelists will describe specific projects at their health-system that either facilitates or directly use phenotyping in the clinical setting.

S47: Panel - Accelerating an Application Programing Interface-based Ecosystem with Real-world Use Cases

K. Chaney, Office of the National Coordinator for Health IT; K. Mandl, Boston Children’s Hospital; D. Chavez, San Diego Health Connect; A. Khurshid, The University of Texas at Austin

The utilization of application programming interfaces (APIs) in healthcare has the potential to enhance population health, patient care and research. Furthered by regulations issued by the Office of the National Coordinator for Health Information Technology (ONC) and the Centers for Medicare & Medicaid Services (CMS), patients and providers will have greater access to electronic health information. In anticipation of a new generation of health IT, ONC issued the Leading Edge Acceleration Projects (LEAP) in Health IT funding opportunity, to advance well-designed, interoperable, and scalable health IT for care and research. This panel will showcase four innovative initiatives, including a provider-payor use case employing a universal bulk-data API; a provider-facing clinical knowledge risk calculator app embedded in an electronic health record; an efficient, transparent and secure consent management prototype using a standards-based authorization framework; and a patient-engagement platform that empowers patients to gain and control access to their personal health data.

S48: Panel - Challenges and Opportunities for Implementing Artificial Intelligence at the Speed of Technology Innovation During the COVID-19 Era

B. South, IBM Watson Health; W. Chapman, University of Melbourne; I. Dankwa-Mullan, IBM Watson Health; M. Matheny, Vanderbilt University; Y. Quintana, Harvard Medical School

The COVID-19 pandemic has created multiple opportunities to implement Artificial Intelligence (AI) technologies in new ways that address the initial infectious curve (e.g., triaging patients and disseminating information during disease outbreaks), as well as the subsequent curves of pandemic sequelae (managing gaps in care of chronic conditions, addressing new and exacerbated mental health needs, and rectifying worsening health disparities. However, numerous challenges limit scaling development and application of AI technologies in healthcare settings, especially in the context of a rapidly evolving public health emergency. Data representing diverse patient cohorts are necessary both to train and to test systems but often are labor intensive to create and deidentify. The need for new codes and concepts can delay data availability. Biases in data must be identified, evaluated, and managed to mitigate downstream effects. System performance must be continuously monitored and validated as clinical information, such as disease transmission characteristics, become available. This panel will discuss these challenges and propose solutions that include ensuring adequate, equitable, and unbiased data sources are used for AI development, validation of AI in clinical settings, with the context of the rapidly evolving COVID-19 public health crisis as a discussion focus.

S52: Panel - Precision Medicine Facilitated through Registry Science: The Challenges and Solutions Associated with Constructing Nationally-focused Registries by Aggregating a Multi-faceted Patient-focused Datasets

S. Labkoff, Multiple Myeloma Research Foundation; L. Rozenblit, Prometheus Research; C. Faria, Alexion Pharmaceuticals; K. Hewitt, The ASH Research Collaborative

Large data sets with disparate kinds of data are needed to facilitate precision medicine. Data such as patient journeys, outcomes, genomics, immunologic, and proteomic data - joined with real-world evidence data from EHRs and claims are needed to facilitate research. Many organizations have taken up the challenge to help generate these data sets via the construction of longitudinal registries focused on a single disease state. This panel will highlight experiences, challenges, and solutions in bringing together data sets for research. The discussion will focus on informatics, data science, outcomes research, legal, regulatory and social challenges.

S53: Panel - Pandemic Informatics: Tuning Expectations of Real World Data - Lessons Learned from the National COVID Cohort Collaborative (N3C)

K. Kostka, Observational Health Data Sciences & Informatics, IQVIA; M. Morris, University of Pittsburgh; M. Palchuk, TriNetX; E. Pfaff, University of North Carolina at Chapel Hill; R. Miller, Tufts University

The first case of a novel coronavirus, subsequently named SARS-CoV-2, was detected in Wuhan, Hubei Province, China in 2019. By the end of August 2020, the coronavirus has since spread across the world, causing over 25 million cases of COVID-19 (the disease caused by SARS-CoV-2) and over 844,000 deaths. The use of real-world data is an important piece of understanding the epidemiology of COVID-19, the natural history/severity of disease and potential therapies. The National COVID Cohort Collaborative (N3C), sponsored by the National Center for Advancing Translational Sciences (NCATS), is a multi-site collaborative learning health network designed to overcome barriers to rapidly build a scalable infrastructure incorporating multi-organizational clinical data for COVID-19 analytics. This panel is composed of informaticians supporting the harmonization of COVID-19 data for downstream analytics. Here we will discuss the need to balance pragmatism versus perfectionism in informatics projects during a pandemic.

Title Sponsor