NOV 14, 2019 06:00 AM PST

Future Directions of Sepsis Management: The Emergence of Artificial Intelligence and the Laboratory Diagnostic Ecosystem

Speakers
  • Director of Clinical Chemistry, Special Chemistry/Toxicology, Point-of-Care Testing, and SARC Sections, Pathology and Laboratory Medicine, University of California, Davis, School of Medicine
    Biography
      Dr. Tran is Associate Professor at the University of California, Davis School of Medicine in the Department of Pathology and Laboratory Medicine. He completed his doctoral training (PhD) at UC Davis in 2008. Thereafter, Dr. Tran completed a postdoctoral training scholarship under the National Institutes of Biomedical Imaging and Bioengineering funded Point-of-Care Technologies Center at UC Davis - focusing on the development of point-of-care molecular pathogen detection systems for critical, emergency, and disaster settings. In 2009, he was awarded a $1.8M Department of Defense grant to determine the clinical impact of near patient molecular pathogen detection in burn sepsis patients. Presently, Dr. Tran is a Board-Certified Clinical Chemist, and serves as and Director of Clinical Chemistry, Special Chemistry/Toxicology, and Point-of-Care Testing at UC Davis Health. His work has expanded to involve artificial intelligence and machine learning for acute kidney injury and sepsis in at risk populations.

    Abstract:

    Burn patients are at risk for organ dysfunction secondary to “burn shock” and sepsis. The initial 24 hours following major burn injury presents with significant hypotension due to profound systemic inflammation. This severe hypotension is further exacerbated by excessive evaporative water loss directly from the burn wound. Following the acute resuscitation period, burn patients are also at high risk for infection with sepsis-related multi-organ dysfunction being the most frequent cause of burn-related deaths. Acute kidney injury (AKI) is reported to be the most common type of organ dysfunction in both “burn shock” and sepsis.

    Traditional indicators of AKI include creatinine and urine output. Unfortunately, both biomarkers have known limitations—delaying recognition of AKI. The use of artificial intelligence (AI) and machine learning (ML) has been proposed to offset these limitations. Our study implemented the first AI/ML algorithm to quickly predict sepsis and AKI with and without novel renal injury biomarkers such as neutrophil gelatinase associated lipocalin (NGAL). For sepsis, our custom AI/ML technique exhibited clinical sensitivity and specificity superior to burn sepsis criteria recommended by the American Burn Association. For AKI, a separate AI/ML algorithm was developed and predicted AKI in burn patients nearly two days earlier than traditional techniques. This same AI/ML algorithm was then tested (generalization) in a mixed burned and non-burned trauma patient population. As in the burn-only cohort, the AI/ML algorithm enhanced the performance of traditional biomarkers.

    Artificial intelligence and ML may enable early recognition of challenging diseases such as AKI and sepsis in high-risk populations. Interestingly, AI/ML could enhance the predictive performance of legacy disease biomarkers. More studies are needed to determine the clinical impact of early sepsis and AKI recognition by AI/ML in the severely burned population.

    Learning Objectives:

    1. Describe the current state of artificial intelligence (AI) / machine learning (ML) in society versus laboratory medicine.
    2. Identify best practices for developing and validating a health-related AI/ML algorithm.
    3. Describe the clinical value of AI/ML for burn-related sepsis and acute kidney injury.


    Show Resources
    You May Also Like
    SEP 05, 2019 04:00 PM CEST
    C.E. CREDITS
    SEP 05, 2019 04:00 PM CEST
    DATE: September 5, 2019TIME: 7:00am PT, 10:00am ET, 4:00pm CEST PCR (Polymerase Chain Reaction) has gone through a massive evolution since its development in 1983. Besides it...
    OCT 02, 2019 11:00 AM PDT
    OCT 02, 2019 11:00 AM PDT
    DATE: October 2, 2019TIME: 11:00am PDT, 2:00pm EDT Ditch the Excel spreadsheets and manage your molecular workflows entirely in your LIMS Achieve configuration of molecular workf...
    AUG 27, 2019 09:00 AM PDT
    C.E. CREDITS
    AUG 27, 2019 09:00 AM PDT
    DATE: August 27, 2019 TIME: 9:00am PDT, 12:00pm EDT Immunotherapies targeting PD-1 or PD-L1 have proven remarkably effective for treating cancer in some patients, with considerabl...
    JUL 30, 2019 10:00 AM PDT
    C.E. CREDITS
    JUL 30, 2019 10:00 AM PDT
    DATE: July 30, 2019TIME: 10:00am PT/ 1:00pm ET The importance of building a validation structure within your lab cannot be overstated. Once in place, the ability to identify high...
    DEC 10, 2019 09:00 AM PST
    C.E. CREDITS
    DEC 10, 2019 09:00 AM PST
    DATE: December 10, 2019TIME: 9:00am PST, 12:00pm EST A major limitation in the ex vivo expansion of harvested human hematopoietic stem-progenitor cells (HSPCs) is the rapid dif...
    JUN 26, 2019 09:00 AM PDT
    C.E. CREDITS
    JUN 26, 2019 09:00 AM PDT
    DATE: June 26, 2019TIME: 9:00am PDT, 12:00pm EDT An excessive number of software solutions are available to help manage your clinical, biobank, or biorepository sample inform...
    Loading Comments...
    Show Resources