Mohamed Ahmed Abo El-Enen

Mr. Mohamed Ahmed Abo El-Enen

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 October 2025 in Neural Computing and Applications
Verified
Journal Article
Open access
PDF file
MEMohamed Ahmed Abo El-Enen
Mohamed Ahmed Abo El-Enen
SISally Saad Ismail
Sally Saad Ismail
TNTaymoor Nazmy
Taymoor Nazmy
Retrieval-augmented generation (RAG) models have become crucial in healthcare applications, significantly enhancing the relevance and reliability of AI-driven insights by combining the generative capabilities of large language models (LLMs) with retrieval-based methods. As healthcare data demand precision and accountability, RAG models address critical limitations of LLMs, such as the tendency to “hallucinate” or produce inaccurate information—by incorporating real-time retrieval from trusted medical knowledge bases and clinical literature. This dual process of retrieving and generating ensures that responses are both contextually accurate and aligned with the latest clinical evidence, making RAG models especially valuable for medical question answering, diagnostics, and treatment planning. This paper presents an in-depth exploration of RAG models and LLMs, specifically within healthcare contexts, to meet the unique demands of medical data processing and decision support. It reviews various RAG architectures, including Naive, Advanced, and Modular RAG approaches, discussing how each framework optimizes retrieval depth, response quality, and computational efficiency. By reducing errors in patient-care recommendations, RAG models play an essential role in scenarios that require high precision and accountability. Additionally, this survey addresses the ethical considerations and transparency requirements for deploying RAG models in healthcare, identifying current challenges and future directions, such as enhancing source interpretability and adapting RAG frameworks for specialized medical fields. By systematically analyzing RAG techniques, this paper provides a comprehensive guide to the state-of-the-art in RAG applications within healthcare, positioning RAG models as a transformative tool for advancing AI-supported healthcare outcomes.

18 February 2026 in IEEE Access
Verified
Journal Article
Open access
MEMohamed Ahmed Abo El-Enen
Mohamed Ahmed Abo El-Enen
RSRavi S. Sharma
Ravi S. Sharma
MAMustafa Abdulrazek
Mustafa Abdulrazek
ANAmril Nazir
Amril Nazir
RMReem Muhammad
Reem Muhammad
ASAhmed Talat Sahlol
Ahmed Talat Sahlol
Healthcare industry faces significant challenges due to fraudulent medical insurance claims, which result in substantial financial losses. We propose an automated system using domain-specific Small Language Models (SLMs) with a narrower scope and smaller parameter count than general-purpose Large Language Models (LLMs), combined with optimization algorithms to improve fraud detection. Our approach integrates numerical features, such as age and claim amount, with textual descriptions, including diagnoses and procedures, into a unified textual representation for each medical activity. This representation captures complex patterns, enhancing the model’s predictive ability. SLMs fine-tuned on medical corpora transform these textual inputs into fixed-dimensional numerical embeddings, capturing semantic and contextual information. Swarm-intelligence-based optimization algorithms then refine feature selection, identifying the most informative subset of features to reduce dimensionality and computational overhead. The system achieves up to 87% accuracy and 96% specificity in classifying medical activities, demonstrating that domain-specific SLMs deliver competitive performance with lower computational costs compared to larger general-purpose models, making the system scalable and efficient. To our knowledge, this is the first work to combine domain-specific SLMs with optimization algorithms for fraud detection in medical claims. This novel approach improves classification accuracy while reducing computational overhead, demonstrating the potential of domain-specific generative AI in healthcare applications.

17 June 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MEMohamed Ahmed Abo El-Enen
Mohamed Ahmed Abo El-Enen
SISally Saad Ismail
Sally Saad Ismail
TNTaymoor Mohamed Nazmy
Taymoor Mohamed Nazmy
Despite recent advances, medical question answering systems still struggle with domain-specific reasoning and data efficiency. This paper presents Med-LLaMA3, a family of medical large language models developed by parameter-efficient fine-tuning of the LLaMA-3.1 (8 billion) and LLaMA-3.2 (1 and 3 billion) architectures using quantized low-rank adaptation (QLoRA) and low-rank adaptation (LoRA) with 4-bit quantization. Beyond model training, this work contributes the following: (1) a formalized dataset curation taxonomy (source type × clinical granularity × task format) with a source-category ablation confirming that the multi-source combination drives benchmark gains beyond any single category; (2) a systematic characterization of low-rank-adaptation rank-scaling behavior for the LLaMA-3 family in the medical domain (monotonic improvement up to rank 128, with no observed plateau); and (3) statistically validated comparisons using McNemar’s test and 95% bootstrap confidence intervals. We curated a medical instruction dataset of over 1.5 million samples spanning medical examinations, clinical dialogues, and biomedical literature. Our approach trains only ∼4% of the base model’s parameters and, consistent with prior studies of parameter-efficient methods in the medical domain, achieves performance comparable to full fine-tuning at a fraction of the memory footprint. Evaluated with five in-context examples per prompt, the 8-billion-parameter model attains a mean accuracy of 75.71% across the eight medical-domain subsets of the Massive Multitask Language Understanding benchmark; improvements over the unmodified LLaMA-3.1-8B-Instruct baseline are statistically significant on the medical multiple-choice benchmark MedMCQA and, after Bonferroni correction across the eight subsets, on three subsets (Clinical Knowledge, Medical Genetics, and Nutrition), with two further subsets being significant only before correction. A structured named-entity-recognition evaluation on 100 hospital discharge summaries (macro-averaged F1 0.94; dual-annotator agreement κ=0.87) provides complementary evidence of clinical-text utility. A safety mitigation pilot shows that context-disambiguation preprocessing reduces the highest-severity abbreviation-ambiguity error rate from 30% to 10% on a 30-case held-out set. These results show that parameter-efficient fine-tuning can deliver high-performance medical large language models while training only ∼4% of the model’s parameters and reducing memory use by roughly 75%, enabling development on low-cost consumer-grade hardware.