Revolutionizing Point-of-Care Ultrasound with Real-Time AI
WaveBase is empowering clinicians to save lives with faster, smarter bedside diagnostics.

The AI Bottleneck in Healthcare

Despite the immense potential of AI to improve patient outcomes, widespread adoption in clinical settings has been hindered by:

  • Incompatibility between AI software and existing ultrasound hardware.
  • High costs and workflow disruptions associated with equipment upgrades.
  • Limited access to diverse, real-world data for AI development and validation.

Key Benefits of WaveBase

WaveBase breaks through these barriers with a universal AI platform that is vendor-agnostic, user-friendly, and data-driven:

  • Rapid Deployment: Go from unboxing to AI-powered scanning in under 60 seconds.
  • Enhanced Accuracy: Detect critical conditions that may be missed by the human eye alone.
  • Improved Workflow: Enable less experienced users to acquire diagnostic-quality images.
  • Privacy by Design: Ensure data security and HIPAA compliance through edge processing.
Check out the WaveBase Website

My Role: Shaping the AI Strategy

As an AI Advisor to WaveBase from 2020-2023, I had the privilege of contributing to their mission at a pivotal stage. My work focused on:

  • Aligning AI development efforts with unmet clinical needs and emerging research opportunities.
  • Engaging key opinion leaders and clinical end-users to inform product requirements and study designs.
  • Evangelizing WaveBase's vision and milestones to build brand awareness and anticipation.

Real-World Impact: Detecting Life-Threatening Conditions in Seconds

In an ongoing study at London Health Sciences Centre, WaveBase is being used to identify lung abnormalities in critically ill patients with unprecedented speed and precision.

"We see a bright future for lung ultrasound imaging with AI within the critical care environment. We are trying to write the first chapter of this meaningful AI story here at LHSC and Lawson."

- Dr. Robert Arntfield, London Health Sciences Centre

Early results suggest that WaveBase is enabling AI that can detect signs of conditions like pneumothorax, pulmonary edema, and pneumonia with the same accuracy as trained experts. By putting this power into the hands of frontline staff, WaveBase could dramatically improve time to treatment for the most vulnerable patients.

Advancing the Science of AI in Ultrasound

WaveBase's technology has been validated in a growing body of peer-reviewed research:

  • Improving the Generalizability and Performance of an Ultrasound Deep Learning Model Using Limited Multicenter Data for Lung Sliding Artifact Identification (2024). Wu, Derek; Smith, Delaney; VanBerlo, Blake; Roshankar, Amir; Lee, Hoseok; Li, Brian; Ali, Faraz; Rahman, Marwan; Basmaji, John; Tschirhart, Jared; Diagnostics, 14(11), 1081.
  • Automated Real-Time Detection of Lung Sliding Using Artificial Intelligence: A Prospective Diagnostic Accuracy Study (2024). Fiedler, Hans Clausdorff; Prager, Ross; Smith, Delaney; Wu, Derek; Dave, Chintan; Tschirhart, Jared; Wu, Ben; Van Berlo, Blake; Malthaner, Richard; Arntfield, Robert; Chest. Article in press.
  • Prospective real-time validation of a lung ultrasound deep learning model in the ICU (2023). Dave, Chintan; Wu, Derek; Tschirhart, Jared; Smith, Delaney; VanBerlo, Blake; Deglint, Jason; Ali, Faraz; Chaudhary, Rushil; VanBerlo, Bennett; Ford, Alex; Critical Care Medicine, 51(2), 301-309.
  • Enhancing annotation efficiency with machine learning: Automated partitioning of a lung ultrasound dataset by view (2022). VanBerlo, Bennett; Smith, Delaney; Tschirhart, Jared; VanBerlo, Blake; Wu, Derek; Ford, Alex; McCauley, Joseph; Wu, Benjamin; Chaudhary, Rushil; Dave, Chintan; Diagnostics, 12(10), 2351.
  • Accurate assessment of the lung sliding artefact on lung ultrasonography using a deep learning approach (2022). VanBerlo, Blake; Wu, Derek; Li, Brian; Rahman, Marwan A; Hogg, Gregory; VanBerlo, Bennett; Tschirhart, Jared; Ford, Alex; Ho, Jordan; McCauley, Joseph; Computers in biology and medicine, 148, 105953.
  • Automation of lung ultrasound interpretation via deep learning for the classification of normal versus abnormal lung parenchyma: a multicenter study (2021). Arntfield, Robert; Wu, Derek; Tschirhart, Jared; VanBerlo, Blake; Ford, Alex; Ho, Jordan; McCauley, Joseph; Wu, Benjamin; Deglint, Jason; Chaudhary, Rushil; Diagnostics, 11(11), 2049.

By providing an accessible platform for real-time data collection and model refinement, we are accelerating the pace of translational research in AI for point-of-care ultrasound.

© 2024 Jason Deglint