AI software for predicting response to neoadjuvant chemotherapy in breast cancer patients (AI-PredictChemo)

Programme

Co-financed by the European Regional Development Fund (ERDF, EU) and the Economic and Tourism Promotion of the State of Lower Austria (Lower Austria, Austria)

Project coordination

Danube Private University, Assoc.-Prof. Dr. Sepideh Hatamikia 

Project Partners

• University Hospital Wiener Neustadt

Researchers involved at DPU 

• Dr. Ali Abbasian Ardakani
• Birgit Pohn, MSc
• Dr. Sebastian Fitzek
• Univ. Prof. Anna Choi, PhD

Abstract

Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide. Neoadjuvant chemotherapy (NACT) is a common treatment strategy, but its effectiveness varies greatly from patient to patient. Currently, physicians cannot predict response to NACT, which limits decision-making. There is therefore an urgent need for predictive tools to personalize the use of NACT and minimize adverse effects. The planned AI-PredictChemo project aims to take steps toward developing the first robust AI software capable of predicting response to NACT in a personalized manner. 

The AI-PredictChemo project is developing AI-based software that uses multiple datatypes to predict breast cancer patients’ response to neoadjuvant chemotherapy. The goal is to enable personalized treatment decisions and avoid unnecessary side effects. The system will be trained and validated using multicenter patient data from the Lower Austrian Oncology Information System. In addition to high predictive accuracy, a focus is placed on the trustworthiness of the AI in accordance with the EU AI Act.