Portfolio

Projects &
Publications

Explore our innovative projects and published research in AI, healthcare, and cutting-edge technology.

Projects(3)

AI cybersecurity

Featured

Csword

CSWORD is a full-stack AI cybersecurity platform delivering phishing simulations, adaptive training, risk analytics, and 24/7 AI defense.

AI psychiatry

RafiqCare

RafiqCare is an AI assistant for psychiatrists, providing session insights, patient progress tracking, and data-driven recommendations.

AI autism

Wisal

AI tool for therapists and parents to create custom educational images, boosting children's descriptive language and visual communication skills.

Publications(8)

Audio + Text for Mental Health AI: Compumacy’s Research into Multimodal LLM Performance

2025

AI for psychiatry

Audio + Text for Mental Health AI: Compumacy’s Research into Multimodal LLM Performance

This paper investigates how large language models perform in mental health assessment when using text, audio, and combined multimodal inputs. Evaluated on the E-DAIC dataset, the study finds that integrating both modalities can improve performance in tasks such as depression detection, underscoring the promise of multimodal LLMs in mental health applications.

Abdelrahman A. Ali, Aya E. Fouda, Radwa J. Hanafy, Mohammed E. Fouda

Benchmarking LLMs for Psychiatry: Compumacy’s Research into Multi-Task Clinical Evaluation

PsychiatryBench is a comprehensive benchmark for evaluating large language models on psychiatry-related tasks. Covering 11 task categories with 5,188 expert-annotated examples, it helps measure model performance across diagnostic, treatment, and follow-up scenarios while revealing key limitations in clinical consistency and management reasoning.

Aya E. Fouda, Abdelrahamn A. Hassan, Radwa J. Hanafy, Mohammed E. Fouda

Advancing Arabic AI for Mental Wellness: Compumacy’s Research into the Language Model Evaluation

The global mental health crisis continues to challenge healthcare systems worldwide, and the Arab world is no exception. With high prevalence rates of conditions like stress, depression, and anxiety, coupled with a significant shortage of trained mental health professionals, there’s an urgent need for innovative, accessible, and culturally sensitive support tools. At Compumacy, we believe Artificial Intelligence, particularly Large Language Models (LLMs), holds immense promise in bridging this gap.

Noureldin Zahran, Aya E. Fouda, Radwa J. Hanafy, Mohammed E. Fouda

Listen

Read

SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models

2026

LLM Safety and Alignment

SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models

SalamahBench is an Arabic-first standardized benchmark for evaluating the safety of language models across 12 harm categories, enabling more rigorous and culturally grounded assessment.

Omar Abdelnasser, Fatemah Alharbi, Khaled Khasawneh, Ihsen Alouani, Mohammed E. Fouda

Read

Evaluating LLMs for Mental Health Understanding: Compumacy’s Research into Model Reliability and Safety

2025

AI for psychiatry

Evaluating LLMs for Mental Health Understanding: Compumacy’s Research into Model Reliability and Safety

A Comprehensive Evaluation of Large Language Models on Mental Illnesses examines how effectively large language models understand, analyze, and respond to mental health–related content across a range of psychiatric conditions. The study provides a broad assessment of model capabilities, limitations, and reliability, highlighting both the promise and the challenges of using LLMs in mental health applications. Its findings contribute to the development of safer, more accurate, and more clinically informed AI systems for mental healthcare.

Abdelrahman Hanafi, Mohammed Saad, Noureldin Zahran, Radwa J. Hanafy

Advancing Multimodal AI for Mental Wellness: Compumacy’s Research into Machine Learning and Embedding-Based Diagnostics

The increasing global prevalence of mental disorders like depression and PTSD has highlighted severe limitations in traditional clinical assessments, such as subjectivity, recall bias, and limited access to professional healthcare. Over one billion people worldwide suffer from mental health conditions, exacerbated notably during the COVID-19 pandemic, underscoring the need for scalable, objective, and accessible diagnostic tools. Multimodal Machine Learning (MMML), integrating text, audio, and video data, emerges as a transformative approach, addressing these clinical challenges by providing comprehensive diagnostic insights through automated methods.

Abdelrahaman A. Hassan, Abdelrahman A. Ali, Aya E. Fouda, Radwa J. Hanafy, Mohammed E. Fouda

Automated Multi-Label Annotation for Mental Health Illnesses Using Large Language Models

The research addresses the challenge of accurately diagnosing co-occurring mental health conditions, such as depression and anxiety, from social media data, noting that existing datasets often focus on single-disorder labels. This paper proposes a novel methodology utilizing Large Language Models (LLMs) for creating versatile multi-label datasets.

Abdelrahaman A. Hassan, Radwa J. Hanafy, Mohammed E. Fouda

Smarter Multimodal Mental Health Assessment: Compumacy’s Research into Embeddings and Machine Learning

Leveraging Embedding Techniques in Multimodal Machine Learning for Mental Illness Assessment explores how multimodal AI can improve mental health assessment by combining text, audio, and video signals. The study evaluates embedding strategies, chunking methods, fusion techniques, and deep learning architectures to detect conditions such as depression and PTSD, showing that multimodal integration can substantially improve performance and support more accurate, scalable mental health screening.

Abdelrahaman A. Hassan, Abdelrahman A. Ali, Aya E. Fouda, Radwa J. Hanafy, Mohammed E. Fouda

Listen

Read

Projects &Publications

Projects(3)

Csword

RafiqCare

Wisal

Publications(8)

Audio + Text for Mental Health AI: Compumacy’s Research into Multimodal LLM Performance

Benchmarking LLMs for Psychiatry: Compumacy’s Research into Multi-Task Clinical Evaluation

Advancing Arabic AI for Mental Wellness: Compumacy’s Research into the Language Model Evaluation

SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models

Evaluating LLMs for Mental Health Understanding: Compumacy’s Research into Model Reliability and Safety

Advancing Multimodal AI for Mental Wellness: Compumacy’s Research into Machine Learning and Embedding-Based Diagnostics

Automated Multi-Label Annotation for Mental Health Illnesses Using Large Language Models

Smarter Multimodal Mental Health Assessment: Compumacy’s Research into Embeddings and Machine Learning

Projects(3)

Csword

RafiqCare

Wisal

Publications(8)

Audio + Text for Mental Health AI: Compumacy’s Research into Multimodal LLM Performance

Benchmarking LLMs for Psychiatry: Compumacy’s Research into Multi-Task Clinical Evaluation

Advancing Arabic AI for Mental Wellness: Compumacy’s Research into the Language Model Evaluation

SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models

Evaluating LLMs for Mental Health Understanding: Compumacy’s Research into Model Reliability and Safety

Advancing Multimodal AI for Mental Wellness: Compumacy’s Research into Machine Learning and Embedding-Based Diagnostics

Automated Multi-Label Annotation for Mental Health Illnesses Using Large Language Models

Smarter Multimodal Mental Health Assessment: Compumacy’s Research into Embeddings and Machine Learning

Projects &
Publications