Details

Autor(en) / Beteiligte

• Juan Ramon, Albert
• Parmar, Chaitanya
• Carrasco-Zevallos, Oscar M
• Csiszer, Carlos
• Yip, Stephen S F
• Raciti, Patricia
• Stone, Nicole L
• Triantos, Spyros
• Quiroz, Michelle M
• Crowley, Patrick
• Batavia, Ashita S
• Greshock, Joel
• Mansi, Tommaso
• Standish, Kristopher A

Titel

Development and deployment of a histopathology-based deep learning algorithm for patient prescreening in a clinical trial

Ist Teil von

• Nature communications, 2024-06, Vol.15 (1), p.4690-14, Article 4690

Ort / Verlag

England: Nature Publishing Group

Erscheinungsjahr

2024

Link zum Volltext

Quelle

MEDLINE

Beschreibungen/Notizen

• Accurate identification of genetic alterations in tumors, such as Fibroblast Growth Factor Receptor, is crucial for treating with targeted therapies; however, molecular testing can delay patient care due to the time and tissue required. Successful development, validation, and deployment of an AI-based, biomarker-detection algorithm could reduce screening cost and accelerate patient recruitment. Here, we develop a deep-learning algorithm using >3000 H&E-stained whole slide images from patients with advanced urothelial cancers, optimized for high sensitivity to avoid ruling out trial-eligible patients. The algorithm is validated on a dataset of 350 patients, achieving an area under the curve of 0.75, specificity of 31.8% at 88.7% sensitivity, and projected 28.7% reduction in molecular testing. We successfully deploy the system in a non-interventional study comprising 89 global study clinical sites and demonstrate its potential to prioritize/deprioritize molecular testing resources and provide substantial cost savings in the drug development and clinical settings.