Advancing patient care with data science in clinical laboratories

Already purchased this program? Access your education in ADLM's online learning center.

Description

Clinical laboratories generate vast amounts of data that are crucial for evaluating human health and disease. Beyond patient results, this data—metadata such as collection time, quality indices, age, and gender—can be used to enhance quality assurance, develop new diagnostic tools, and improve healthcare delivery. However, many laboratorians face barriers in using this data in part due to unfamiliarity with its potential.

In this course, which is based on sessions presented at ADLM 2024, experts share their experiences in initiating data analytics projects, addressing common pitfalls, and showcasing successful applications in visualization, reference interval validation, preventing machine learning bias, and more. Enroll in this course to explore accessible analytics methodologies and equip yourself with practical insights and strategies to leverage data analytics in your own practice.

Target audience

This activity is designed for physicians, lab supervisors, lab directors (and/or assistant directors), lab managers (supervisory and/or non-supervisory), fellows, residents, in-training individuals, nurses, payors, healthcare administrators, and other laboratory professionals who are seeking to implement or already using data science approaches in clinical laboratories to analyze clinical data for clinical decision-making and patient care.

Learning objectives

At the end of this activity, participants will be able to:

Recognize situations where data analytics can be applied in the clinical laboratory to improve workflow, stewardship programs, patient disease predictions, and other clinical scenarios.
Evaluate benefits, limitations, and abilities of data analytics methodologies for use in clinical laboratory algorithms and decision-making tools such as estimation of reference intervals.
Apply best practices in data visualizations to avoid misleading or confusing information when communicating with clinical laboratories and providers.
Describe current and emerging approaches for mitigating algorithmic bias in clinical predictions derived from machine learning.

Course outline

Participants will complete a brief survey at the beginning and end of the course.

Dipping your toesinto the data analytics pool: A session with laboratory professionals working on informatics projects (90 minutes) >Moderator: Mark Cervinski, PhD, DABCC, FADLM, Dartmouth-Hitchcock Medical Center

Through the shallows: Regional quality control and calibrations
Dustin Bunch, PhD, DABCC, Nationwide Children's Hospital
Developing machine learning models to improve test utilization and laboratory stewardship
Sarina Yang, PhD, DABCC, Weill Cornell Medicine
From idea to beta testing: Use cases to build your analytics skills
Steven Cotten, PhD, DABCC, NRCC, FADLM, University of North Carolina at Chapel Hill

Getting started with data analytics: Indirect reference intervals as a case study(90 minutes)
Moderator: Sarah Wheeler, PhD, FADLM, University of Pittsburgh Medical Center

Accessing and analyzing laboratory data: Tools, techniques, and tips
Sarah Wheeler, PhD, FADLM, University of Pittsburgh Medical Center
Exploring data analytics through case studies in indirect reference interval applications
Kelly Doyle, PhD, DABCC, FADLM, ARUP Laboratories
Systematic ways to avoid fantasy and self-deception with indirect reference interval determination
Daniel Holmes, MD, St Paul's Hospital Providence Health Care

Bad, better, best: Putting data visualizations to the test(90 minutes)
Moderator: T. Scott Isbell, PhD, DABCC, FADLM, Saint Louis University School of Medicine

A journey in data visualization: You be the judge!
T. Scott Isbell, PhD, DABCC, FADLM, Saint Louis University School of Medicine
Case presentations: Data visualizations for presentations and reports
Shannon Haymond, PhD, DABCC, FADLM, Ann & Robert H Lurie Children's Hospital of Chicago
Case presentations: Enhancing the accessibility of data visualizations
Christopher McCudden, PhD, DABCC, FADLM, FCAC, The Ottawa Hospital General Campus

Ensuring equity and fairnessin machine learning and data analytics (90 minutes)
Moderator: Mark Zaydman, MD, PhD, Washington University in St. Louis

Conceptualizing and measuring algorithmic fairness
Mark Zaydman, MD, PhD, Washington University in St. Louis
How machine learning algorithms incorporate biases and make unfair predictions
Weishen Pan, PhD, Weill Cornell Medicine
Strategies and tools for engineering algorithmic fairness
Jenny Yang, MSc, BASC, University of Oxford

Accreditation

ADLM offers ACCENT® continuing education credit to laboratory professionals to document their continuing education and meet requirements for licensure or certification. This educational activity is designated for a maximum of 6.0 ACCENT credits. Learners should claim only the credit commensurate with the extent of their participation in the activity.

ADLM is also accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education for physicians. This educational activity is designated for a maximum of 6.0 AMA PRA Category 1 Credits™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.

Click here to view full accreditation information.

Expiration date: December 31, 2027

Participants are not able to claim continuing education credit for this activity after December 31, 2027.