Cambridge Healthtech’s Inaugural

Data-Driven Diagnostics

AI and Advanced Analytics for Clinical Care and Diagnostics

August 21-22, 2019

 

The utilization of data for clinical care and diagnostics is not a new idea, however the sheer volume, velocity, veracity and variety of these data is unprecedented. Coupled with disruptive digital innovations, such as machine learning and artificial intelligence, we are now witnessing the digital revolution of the diagnostics world. Join us at Cambridge Healthtech Institute's Inaugural Data-Driven Diagnostics where we will discuss enabling technologies to leverage data to drive diagnostics and clinical care as well as market access decisions and solutions.

Final Agenda

WEDNESDAY, AUGUST 21

10:30 am Registration


11:30 Plenary Keynote Session

11:30 Chairperson’s Remarks

Charles Mathews, Principal, ClearView Healthcare Partners

 

 

 

 

 

11:40 Plenary Keynote Presentation: FDA Updates: Now and Looking to the Future

Tim Stenzel, MD, PhD, Director, Office of In Vitro Diagnostics and Radiological Health, Center for Devices and Radiological Health, U.S. Food and Drug Administration

Introduction and background of the new Office Director of OIR and updates on precision medicine and other initiatives at the FDA.

12:10-1:05 pm Plenary Keynote Discussion: Proposals and Solutions for Diagnostic Reform Including Oversight of Laboratory Developed Tests (LDTs)

Moderator:
Cynthia A. Bens, Senior Vice President, Public Policy, Personalized Medicine Coalition

 

 

 

 

  • How are stakeholders influencing congressional activity on the Verifying Accurate Leading-edge IVCT Development (VALID) Act?
  • How will the VALID Act change the current oversight landscape for diagnostics, including LDTs?
  • How are policymakers addressing the role of CMS and CLIA in the VALID Act?
  • How will increased regulatory and oversight activities at the FDA affect the diagnostics industry?
  • What impact will changes in diagnostics regulation and oversight have on patient care?

Panelists:

Julie Khani, MPA, President, American Clinical Laboratory Association (ACLA)

 

 

 

 

 

Donald E. Horton, Jr., Senior Vice President, Global Government Relations & Public Policy, Laboratory Corporation of America Holdings

 

 

 

 

 

Susan Van Meter, Executive Director, AdvaMedDx

 

 

 

 

 

1:05 pm Luncheon Presentation (Sponsorship Opportunity Available) or Enjoy Lunch on Your Own

1:35 Ice Cream & Break in the Exhibit Hall with Poster Viewing

GOING FROM DATA TO INFORMATION TO ACTION

2:05 Chairperson’s Remarks

David Ledbetter, Senior Data Scientist, Virtual Pediatric ICU, Children’s Hospital Los Angeles

2:10 KEYNOTE PRESENTATION: Making Data Useable

Christoph Pedian, PhD, Executive Vice President, Point of Care Diagnostics, Siemens Healthineers

  • The benefits of seamless communication along the patient care pathway
  • Connectivity of point-of-care devices and concordance of test results in practical terms and applications
  • The need for networking data
  • Challenges in accessing relevant data
  • Why you should make room for something new and different

Putting it together: Centralized and decentralized application of diagnostics in a networked healthcare system

2:40 What’s Data Got to Do with It

Belinson_SuzanneSuzanne Belinson, PhD, Vice President, Commercial Market, Tempus

The value from genetic testing is not from the consumable good, it is not inherent in the test itself but in the insights that can be gained through interpretation of the results and the aggregation of those results with the results of others. Tempus is a technology company that has build the world’s largest library of clinical and molecular data and an operating system to make that data accessible and useful, starting with cancer. Dr. Belinson will discuss how these insights can make precision medicine a reality for patients, providers and payers.

3:10 Data Scientists Are from Mars, Clinicians Are from Venus

Ledbetter_DavidDavid Ledbetter, Senior Data Scientist, Virtual Pediatric ICU, Children’s Hospital Los Angeles

Clinicians and data scientists come from very different backgrounds and speak different languages. Bridging that gap is a critical component to being able to successfully execute projects in healthcare. This talk will discuss some of the successful strategies for improving communication to foster collaboration between interdisciplinary teams. Topics will include embedding data scientists in a clinical environment, embedding clinicians in data analysis, and providing clinical education to aspiring data scientists.

3:40 Sponsored Presentation (Opportunity Available)

4:10 Refreshment Break in the Exhibit Hall with Poster Viewing

ADVANCES IN DATA ANALYSIS

4:55 Chairperson’s Remarks

Margaret Bray, PhD, Senior Data Scientist, Data Science, Genomics, and Bioinformatics, Alexion Pharmaceuticals, Inc

5:00 High-Performance Integrated Virtual Environment (HIVE) and BioCompute Objects for Regulatory Sciences

Mazumder_RajaRaja Mazumder, PhD, Associate Professor, Biochemistry and Molecular Medicine Georgetown Washington University

Advances in sequencing technologies combined with extensive systems level -omics analysis have contributed to a wealth of data which requires sophisticated bioinformatic analysis pipelines. Accurate communication describing these pipelines is critical for knowledge and information transfer. In my talk I will provide an overview of how we have been engaging with the scientific community to develop BioCompute specifications to build a framework to standardize bioinformatics computations and analyses communication with US FDA. I will also describe how BioCompute Objects (https://osf.io/h59uh/) can be created using the High-performance Integrated Virtual Environment (HIVE) and other bioinformatics platforms

5:30 Machine Learning in Genomic Diagnostics: A Model for Automated Screening of Genomic Variants

Sarmady_MahdiMahdi Sarmady, PhD, Assistant Professor, Clinical Pathology, University of Pennsylvania School of Medicine, Director of Clinical Bioinformatics, Division of Genomic Diagnostics, The Children’s Hospital of Philadelphia

Genomic diagnostics in clinical laboratories increasingly relies on high-throughput technologies and therefore is subject to associated complexities. Challenges include inherent artifacts in the results as well as size of data. Despite advances in genomic databases to help with interpretation, the process still involves manual curation of genomic variants. Here we present a machine learning model to use the curated information to be able to screen somatic variants automatically.

6:00 Panel Discussion: Using AI to Diagnose Rare Diseases

Moderator: Jodie Sherman Gillon, Global Medical Lead, Patient Engagement Rare Diseases, Pfizer

Panelists: Margaret Bray, PhD, Senior Data Scientist, Data Science, Genomics, and Bioinformatics, Alexion Pharmaceuticals, Inc

More Speakers to be Announced

A look into the data science techniques applied to diagnostic support tools along with a discussion about how methods must be adapted when the data is big versus when it is rare.

6:30 Close of Day

6:30 Dinner Short Course Registration


6:45 - 9:15 pm Recommended dinner Short Course*

SC13: Data-Driven Process Development in the Clinical Laboratory

Young_RobertRobert Young, CGMBS, MS Bioinformatics, Owner, Principal Consultant, Lab Insights, LLC

The modern clinical laboratory utilizes complex, data-rich computer systems. In this course, you will learn how to leverage your laboratory information systems to build data-driven processes, create data-driven process improvements, and make data-driven business decisions.

*Separate registration required.

THURSDAY, AUGUST 22

7:15 am Registration


7:30 Problem Solving Breakout Discussions with Continental Breakfast

DATA STRATEGIES FOR CLINICAL LABS

8:25 Chairperson’s Remarks

Julie Ramage, National Account Director, Diagnostics, Pfizer Oncology

8:30 Panel Discussion: Data Curation, Management, and Usege In the Clinical Lab

Ramage_JulieModerator: Julie Ramage, National Account Director, Diagnostics, Pfizer Oncology


Young_RobertPanelists: Robert Young, CGMBS, MS Bioinformatics, Owner, Principal Consultant, Lab Insights, LLC


More Speakers to be Announced

  • Discuss changing landscapes, challenges, and trends – and what it all means for laboratory data
  • How to implement a laboratory informatics infrastructure to facilitate data curation for clinical validation and quality reporting
  • Case study and strategy on how laboratories can derive value from existing data assets

9:30 Sponsored Presentation (Opportunity Available)

10:00 Coffee Break in the Exhibit Hall with Poster Viewing

AI-BASED INFECTIOUS DISEASE DIAGNOSTICS

11:00 Chairperson’s Remarks

James Courtney Fackler, MD, Director, Pediatric Critical Care Medicine, Associate Professor of Anesthesiology and Critical Medicine, Johns Hopkins Medicine

11:05 Harnessing the Host Response for Real Time Infectious Disease Diagnosis

Tsalik_EphraimEphraim L. Tsalik, MD, MHS, PhD, Associate Professor, Medicine, Duke University School of Medicine; Founder, Predigen, Inc.

For more than a decade, Duke, and now Predigen, have been at the forefront of capturing the molecular response to exogenous perturbations to develop diagnostic and predictive signatures for disease. Infectious disease pathogens induce robust and specific host responses that can be assayed using RNA and proteomic technologies. Using machine learning and advanced analytics we have pioneered the discovery of highly specific signatures and have translated them into clinically relevant assays. Our strategy is to develop rapid diagnostic tests for use in hospital, clinic, and home.

11:35 CO-PRESENTATION: Burn Sepsis and Acute Kidney Injury: Unique Population and the Promise of Artificial Intelligence

rashidi_hoomanHooman H. Rashidi, MD, FASCP, Professor and Vice Chair, GME, Director of Residency Program; Director, Flow Cytometry & Immunology, Department of Pathology and Laboratory Medicine, University of California, Davis School of Medicine


Nam Tran, PhD, Associate Professor, Pathology and Laboratory Medicine, University of California, Davis School of Medicine

Burn patients are at high risk for sepsis. Acute kidney injury (AKI) is common in burn sepsis patients. Early recognition of AKI is impeded by the poor performance biomarkers such as urine output and creatinine. Artificial intelligence (AI) could be used to augment the performance of current biomarkers of AKI. Our study evaluates the clinical utility of AI in detecting sepsis vs. non-sepsis related AKI in severely burned patients.

12:05 pm Integrating Artificial Intelligence Technologies into Clinical Care for Infectious Disease

Fackler_JamesJames Courtney Fackler, MD, Director, Pediatric Critical Care Medicine, Associate Professor of Anesthesiology and Critical Medicine, Johns Hopkins Medicine

AI techniques (e.g., deep learning) are finding patterns in data that humans cannot routinely see. The opportunity for improved health care value is early diagnosis and intervention The key, however, to delivering this value will be optimizing and managing the symbiosis between the AI machines and the expert clinician.

12:35 Sponsored Presentation (Opportunity Available)

1:05 Luncheon Presentation (Sponsorship Opportunity Available) or Enjoy Lunch on Your Own

1:35 Dessert Break in the Exhibit Hall with Poster Viewing

DEVELOPING APPS FOR DIAGNOSTICS

2:15 Chairperson’s Remarks

Wilbur A. Lam, MD, PhD, Associate Professor,Wallace H. Coulter Department of Biomedical Engineering and Department of Pediatrics, Aflac Cancer and Blood Disorders Center of Children’s Healthcare of Atlanta, Georgia Institute of Technology and Emory University School of Medicine

2:20 AMA Guidelines on MHealth Apps

Michael L Hodgkins, MD, MPH, Chief Medical Information Officer, AMA

2:50 Development of a Smartphone App for Non-Invasive Detection of Anemia Using Only Patient-Sourced Photos

Lam_WilburWilbur A. Lam, MD, PhD, Associate Professor,Wallace H. Coulter Department of Biomedical Engineering and Department of Pediatrics, Aflac Cancer and Blood Disorders Center of Children’s Healthcare of Atlanta, Georgia Institute of Technology and Emory University School of Medicine

We introduce a paradigm of non-invasive, on-demand diagnostics for hematologic diseases using only a smartphone app and photos. We initially targeted anemia, characterized by low blood hemoglobin levels, which afflicts >2 billion people. Our app estimates hemoglobin levels by analyzing color and metadata of fingernail smartphone photos and screens for anemia (hemoglobin levels <12.5 g/dL) with a 97% sensitivity (n = 100 subjects). Moreover, with personalized calibration, this system achieves an accuracy of ±0.92 g/dL compared to gold standard hemoglobin levels (n = 16 subjects), empowering chronic anemia patients to serially monitor their hemoglobin levels instantaneously and non-invasively.

RWD FOR ONCOLOGY

3:20 How Can Real-World Data Enhance Clinical Evidence Generation?

Margaret McCusker, MD, Senior Medical Director, Flatiron Health

As the cancer treatment landscape becomes increasingly complex, biomarkers are playing a more prominent role in drug development and clinical decision support. In this setting, research-quality clinical evidence derived from cancer patients’ electronic health records and paired genomic data are a valuable asset. This session will highlight examples of how clinico-genomic data can provide critical insights into the impact of biomarkers on real-world oncology practice and accelerate clinical research.

3:50 Establishing the Next Generation of Clinico-Genomic Data in Oncology and Healthcare

Lang_KathrynKathryn Lang, MBBS, MRCP, Vice President, Outcomes and Evidence, Guardant Health

The emergence of real-world clinco-genomic data promises great value for all aspects of the healthcare system, how do organizations and individuals combine efforts to support all aspects of care and treatment?


4:20 End of Summit