Mohammed El-Hakim

Dr. Mohammed El-Hakim

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
25 August 2025 in Dentistry Journal
Verified
Journal Article
Open access
PDF file
Mohammed El-HakimMohammed El-Hakim
Mohammed El-Hakim
RARobert Anthonappa
Robert Anthonappa
Amr FawzyAmr Fawzy
Amr Fawzy
Background/Objectives: This scoping review aims to map existing AI applications in dental education, in student learning, assessment, and diagnostic training, identifying key limitations and challenges. Methods: Following the Arksey and O’Malley framework and PRISMA-ScR guidelines, six databases were searched in March 2025 using combinations of the following search words: “dental education,” “artificial intelligence,” “machine learning,” and “student assessment”. Inclusion was limited to English-language empirical studies focused on dental student education. Of 547 identified studies, 17 met the inclusion criteria. They were categorized into four domains: (1) Preclinical Training, (2) AI in Clinical, Diagnostic Training, and Radiographic Interpretation, (3) AI as an Assessment Tool and Feedback System, and (4) AI in Content Generation for Dental Education. Results: AI has positively influenced various domains, enhancing procedural accuracy, diagnostic confidence, assessment efficiency, and content delivery. However, it struggles to assess nuanced competencies like dexterity and clinical judgment. The challenges faced include disparate definitions of AI, ethical and privacy concerns, model variability, and a deficiency of dental leadership in AI development. At present, most tools are engineered by computer scientists and may not align effectively with the priorities of dental education. Conclusions: AI holds significant potential to enhance dental education outcomes. However, to guarantee its relevance and reliability, it requires standard frameworks, ethical oversight, and clinician-led development. Future research should concentrate on implementing real-time AI-driven feedback systems during preclinical training and advocate for more precise definitions to support consistent AI application and evaluation in dental education.

8 July 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Mohammed El-HakimMohammed El-Hakim
Mohammed El-Hakim
RARobert Anthonappa
Robert Anthonappa
Amr FawzyAmr Fawzy
Amr Fawzy
Background/Objectives: This scoping review aims to map existing AI applications in dental education, in student learning, assessment, and diagnostic training, identifying key limitations and challenges. Methods: Following the Arksey and O’Malley framework and PRISMA-ScR guidelines, six databases were searched in March 2025 using combinations of the following search words: “dental education,” “artificial intelligence,” “machine learning,” and “student assessment”. Inclusion was limited to English-language empirical studies focused on dental student education. Of 547 identified studies, 17 met the inclusion criteria. They were categorized into four domains: (1) Preclinical Training, (2) AI in Clinical, Diagnostic Training, and Radiographic Interpretation, (3) AI as an Assessment Tool and Feedback System, and (4) AI in Content Generation for Dental Education. Results: AI has positively influenced various domains, enhancing procedural accuracy, diagnostic confidence, assessment efficiency, and content delivery. However, it struggles to assess nuanced competencies like dexterity and clinical judgment. The challenges faced include disparate definitions of AI, ethical and privacy concerns, model variability, and a deficiency of dental leadership in AI development. At present, most tools are engineered by computer scientists and may not align effectively with the priorities of dental education. Conclusion: AI holds significant potential to enhance dental education outcomes. However, to guarantee its relevance and reliability, it requires standard frameworks, ethical oversight, and clinician-led development. Future research should concentrate on implementing real-time AI-driven feedback systems during preclinical training and advocate for more precise definitions to support consistent AI application and evaluation in dental education.

13 November 2025 in Dentistry Journal
Verified
Journal Article
Open access
PDF file
Mohammed El-HakimMohammed El-Hakim
Mohammed El-Hakim
HKHaitham Khaled
Haitham Khaled
Amr FawzyAmr Fawzy
Amr Fawzy
RARobert Anthonappa
Robert Anthonappa
Introduction: Artificial intelligence is emerging in dental education, but its use in preclinical assessment remains limited. Large language models like ChatGPT® V4.5 enable non-programmers to build AI models through real-time guidance, addressing the coding barrier. Aim: This study aims to empower clinician-led, low-cost, AI-driven assessment models in preclinical restorative dentistry and to evaluate the technical feasibility of using a neural network to score 3D cavity preparations. Methods: Twenty mandibular molars (tooth 46), each with two carious lesions, were prepared and scored by two expert examiners using a 20-point rubric. The teeth were scanned with a Medit i700® and exported as .OBJ files. Using Open3D, the models were processed into point clouds. With ChatGPT’s guidance, the clinician built a PointNet-based neural model in PyTorch, training it on 20 cases and testing it on 10 unseen preparations. Results: In training, the model achieved an MAE of 0.82, RMSE of 1.02, and Pearson’s r = 0.88, with 66.7% and 93.3% of the predictions within ±5% and ±10% of the examiner scores, respectively. On the test set, it achieved an MAE of 0.97, RMSE of 1.16, and r = 0.92, with 50% and 100% of scores within ±5% and ±10%, respectively. These results show a strong alignment with examiner scores and an early generalizability for scoring preclinical cavity preparations. Conclusions: This study confirms the feasibility of clinician-led, low-cost AI development for 3D cavity assessment using ChatGPT, even without prior coding expertise.