AI in haemostasis and coagulation 

Artificial intelligence (AI) is rapidly transforming healthcare, with machine learning (ML) emerging as one of the most practical tools for improving diagnostic decision-making. But how can these technologies be applied in the medical laboratory?

This presentation explores the use of machine learning to unlock the diagnostic potential of underutilised laboratory data, with a particular focus on clot waveform analysis (CWA)—a routinely generated yet often overlooked output of coagulation analysers. Discover how deep learning models can analyse CWA time-series data to classify the underlying causes of prolonged activated partial thromboplastin time (aPTT), and why the way laboratory data is represented plays a critical role in improving model performance.

The session will also examine the future of AI in pathology, discussing how machine learning could be integrated into routine laboratory workflows as a clinical decision support tool to enhance diagnostic efficiency and guide targeted testing, while complementing—not replacing—traditional confirmatory assays. Challenges, limitations and future directions for AI implementation in haemostasis laboratories will also be explored.

What you'll gain:

• An introduction to AI and machine learning in laboratory medicine.
• Insights into the application of deep learning for clot waveform analysis.
• An understanding of how AI can support diagnostic decision-making in haemostasis.
• An overview of the opportunities and challenges of implementing AI in routine pathology practice.

Speakers:

Mr Mohammad Altememi, 2IC NSW Health Pathology and PhD candidate at CSU. 

Download the webinar flyer to share within your workplace, laboratory, or professional network.

Download Flyer