Educational content on VJHemOnc is intended for healthcare professionals only. By visiting this website and accessing this information you confirm that you are a healthcare professional.

Share this video  

ICML 2025 | The role of AI in the diagnosis of hematological malignancies

In this interview, Pierre Brousset, MD, Toulouse University, Toulouse, France, comments on the role of artificial intelligence (AI) in the diagnosis of hematological malignancies, stating that AI is currently in its infancy in this field and emphasizing that it represents a valuable tool to assist pathologists rather than replace them. AI excels at handling large datasets, but its use must be carefully controlled to avoid incorrect conclusions and ensure the quality of the dataset. This interview took place during the 18th International Conference on Malignant Lymphoma (18-ICML) in Lugano, Switzerland.

These works are owned by Magdalen Medical Publishing (MMP) and are protected by copyright laws and treaties around the world. All rights are reserved.

Transcript

What is the role of AI in pathologic diagnosis? Today the role of AI in pathologic diagnosis is in its infancy. There is no reliable solution that can replace the pathologist in routine diagnosis. There are some hopes with the use of these technologies, rather to assist the pathologist in their everyday routine than replace them. So this is not the subject of replacing the pathologist but just to assist them and to improve their accuracy for the diagnosis...

What is the role of AI in pathologic diagnosis? Today the role of AI in pathologic diagnosis is in its infancy. There is no reliable solution that can replace the pathologist in routine diagnosis. There are some hopes with the use of these technologies, rather to assist the pathologist in their everyday routine than replace them. So this is not the subject of replacing the pathologist but just to assist them and to improve their accuracy for the diagnosis. And the problem of AI is that the problem is the reproducibility of the results published. There are many manuscripts in the literature and the difficulty is that to reproduce the results published by others. So we need a kind of standardization of the results and to work on the same solution and with the same tools. This is not the case today. The advantage of using AI is to deal with a huge amount of data, which is the main property of the AI solution, is to handle huge amounts of data and datasets. So today we have no other way to manage all this information. The AI solution is very useful for that, but we have to be very careful in the use of the solution and to avoid obtaining wrong conclusions on the results and to control the dataset, which is the most important thing. Now, there are many hopes with this solution. We have to be very careful in the use. This is not magic. And we have to be very practical in the use of the solution. It’s rather an assistant than a replacement of the doctor practicing.

This transcript is AI-generated. While we strive for accuracy, please verify this copy with the video.

Read more...