Achraf Toufah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Achraf Toufah has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
Mohamed Achraf Kadim
University of Hassan II Casablanca
1 shared publication- Mohamed El Hafidi
Hassan II University of Casablanca
1 shared publication
Latest Publications
- Open Access
- 24 June 2025
- Published by Springer Nature in Research Square
Quantum Neural Networks for Prostate Cancer Detection: A Feasibility and Design Study
Quantum machine learning is gaining attention for its ability to uncover complex patterns that classical models may overlook. In this research, we explore the use of a quantum neural network (QNN) for classifying prostate cancer based on clinical data. We started with a real-world dataset and applied essential preprocessing steps to prepare it for training. The QNN was built using a ZZFeatureMap for encoding and a variational circuit combining rotation gates and entanglement. Training was performed with the COBYLA optimizer using an 80–20 train-test split. The model achieved strong results, with 87.5% accuracy, 89% precision, and over 90% recall. These outcomes suggest that QNNs offer meaningful potential for improving cancer detection tasks, particularly in medical domains where capturing subtle feature interactions is crucial.
- 24 June 2025
- Published by Springer Nature in Research Square
Open AccessQuantum Neural Networks for Prostate Cancer Detection: A Feasibility and Design Study
Quantum machine learning is gaining attention for its ability to uncover complex patterns that classical models may overlook. In this research, we explore the use of a quantum neural network (QNN) for classifying prostate cancer based on clinical data. We started with a real-world dataset and applied essential preprocessing steps to prepare it for training. The QNN was built using a ZZFeatureMap for encoding and a variational circuit combining rotation gates and entanglement. Training was performed with the COBYLA optimizer using an 80–20 train-test split. The model achieved strong results, with 87.5% accuracy, 89% precision, and over 90% recall. These outcomes suggest that QNNs offer meaningful potential for improving cancer detection tasks, particularly in medical domains where capturing subtle feature interactions is crucial.