University Medical City Annual Research Day Oman, Convention and Exhibition Centre, 24th September 2025
Sally Khalid Azeez, Aida Malik AlKindy, Rana Eljaber, Hasan Al-Sayegh, Najla Al Hashmi, Fatma AlFarsi, Marwan AlAbidi, Munjid AlHarthy, Abdulaziz Bakathir, Saleh Al Ghailani, Ahmed Al Hashmi, Ahmed Al Ajmi, Tiamour Al Baloshi, Waleed Alshukaili, Huda Al-Noumani, Nasser Al Salmi

TL;DR
This paper presents multiple studies from Oman's University Medical City Annual Research Day, covering topics like AI in clinical trial risk assessment, orbital fracture repair outcomes, medication adherence in hematological diseases, germline methylation analysis in breast cancer, and improved PET/CT imaging for prostate cancer.
Contribution
The studies introduce novel AI-augmented risk assessment methods, a bioinformatics pipeline for germline methylation analysis, and enhanced PET/CT reconstruction techniques for prostate cancer.
Findings
AI-augmented risk assessment showed higher consistency and efficiency compared to traditional methods in clinical trials.
MVCs were the primary cause of orbital fractures in Oman, with a 24.4% complication rate following surgical repair.
Combining TOF and PSF reconstruction improved SUV_mean, SNR, CNR, and CRC in prostate cancer PET/CT imaging.
Abstract
Risk-based assessment ensures participant safety, data integrity, and regulatory compliance in clinical trials. Institutional Review Boards (IRBs) lead evaluations; however, the absence of standardized tools can result in inconsistent risk evaluations. Artificial intelligence AI could enhance objectivity, efficiency, and reproducibility in risk assessments. This pilot study compared traditional methods (subjective judgment and the commonly used clinical trials risk assessment tool (SCTO) with AI-augmented approaches in Oman's IRB context, focusing on consistency, time efficiency, and output quality. Four IRB members independently assessed five clinical trial protocols using professional judgement and the SCTO tool, while four AI systems analysed the same protocols using predefined risk variables. AI-augmented risk assessment showed substantial inter-rater agreement (κ = 0.61),…
Genes, proteins, chemicals, diseases, species, mutations and cell lines named across the full text — each resolved to its canonical identifier and authoritative record.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsArtificial Intelligence in Healthcare and Education · Statistical Methods in Clinical Trials · Radiomics and Machine Learning in Medical Imaging
