Wajiha Moussa Abu Haliqa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wajiha Moussa Abu Haliqa has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Abeir Abdalrubb
Department of Endocrine, Qatar Metabolic Institute, Hamad Medical Corporation, Doha, Qatar
1 shared publicationButhaina Alowainati
Department of Endocrine, Qatar Metabolic Institute, Hamad Medical Corporation, Doha, Qatar
1 shared publicationHamda Ali
Department of Endocrine, Qatar Metabolic Institute, Hamad Medical Corporation, Doha, Qatar
1 shared publicationMariam Al Malaheem
Department of Endocrine, Qatar Metabolic Institute, Hamad Medical Corporation, Doha, Qatar
1 shared publication- Rawan Youssef Majzoub
Diet Center, Doha, Qatar
1 shared publication - Reem Dhobaian Alshammari
Department of Patient Education and Diabetes Care, University of Doha for Science and Technology, Doha, Qatar
1 shared publication
Latest Publications
- Open Access
- 6 November 2025
- Published by Springer Nature in Journal of Medical Imaging and Interventional Radiology
- Vol. 12 (1) , 1-15
Diagnostic accuracy of AI or DL-enhanced technologies in the diagnosis of diabetic retinopathy: a systematic review
Background: Diabetic retinopathy (DR) remains a leading cause of preventable vision loss globally, particularly among individuals with long-standing diabetes. Conventional DR screening methods, such as manual retinal grading by ophthalmologists, are labor-intensive, time-consuming, and subject to inter-grader variability. These limitations highlight the urgent need for automated, scalable, and reliable diagnostic solutions that can improve early detection and the need for clinical detection. Objective: This systematic review aimed to evaluate the diagnostic accuracy of artificial intelligence (AI) and deep learning (DL) models for DR detection, with a particular focus on hybrid architectures that combine convolutional neural networks (CNNs), Vision Transformers (ViTs), and traditional machine learning (ML) classifiers. Methods: A comprehensive search of six databases covering 2012–2024 identified 327 studies, of which 20 met the inclusion criteria. Two independent reviewers conducted screening, data extraction, and risk of bias assessment using the QUADAS-2 tool. Due to heterogeneity in model architectures, datasets, and reporting, a meta-analysis was not feasible. Complete database search strategies are available in the supplementary appendix. Results: Hybrid AI models consistently outperformed conventional DL and ML approaches, achieving sensitivities of 92–100% and specificities above 80%. Models that integrated both fundus photography and optical coherence tomography (OCT) images achieved the highest diagnostic accuracy (sensitivity 97.2%). Attention mechanisms, ensemble learning, and explainable AI (XAI) methods (e.g., Grad-CAM, LIME) enhanced model interpretability and clinical applicability. Conclusions: Hybrid AI-based diagnostic platforms show strong potential to transform DR screening by offering improved scalability, accuracy, and cost-effectiveness. However, clinical translation will require greater data diversity, robust external validation, and regulatory compliance. These findings provide timely evidence to support the integration of AI-driven DR screening into national diabetes strategies and public health policies, particularly in regions with high diabetes prevalence, such as Qatar and the Middle East.
- 6 November 2025
- Published by Springer Nature in Journal of Medical Imaging and Interventional Radiology
- Vol. 12 (1) , 1-15
Open AccessDiagnostic accuracy of AI or DL-enhanced technologies in the diagnosis of diabetic retinopathy: a systematic review
Background: Diabetic retinopathy (DR) remains a leading cause of preventable vision loss globally, particularly among individuals with long-standing diabetes. Conventional DR screening methods, such as manual retinal grading by ophthalmologists, are labor-intensive, time-consuming, and subject to inter-grader variability. These limitations highlight the urgent need for automated, scalable, and reliable diagnostic solutions that can improve early detection and the need for clinical detection. Objective: This systematic review aimed to evaluate the diagnostic accuracy of artificial intelligence (AI) and deep learning (DL) models for DR detection, with a particular focus on hybrid architectures that combine convolutional neural networks (CNNs), Vision Transformers (ViTs), and traditional machine learning (ML) classifiers. Methods: A comprehensive search of six databases covering 2012–2024 identified 327 studies, of which 20 met the inclusion criteria. Two independent reviewers conducted screening, data extraction, and risk of bias assessment using the QUADAS-2 tool. Due to heterogeneity in model architectures, datasets, and reporting, a meta-analysis was not feasible. Complete database search strategies are available in the supplementary appendix. Results: Hybrid AI models consistently outperformed conventional DL and ML approaches, achieving sensitivities of 92–100% and specificities above 80%. Models that integrated both fundus photography and optical coherence tomography (OCT) images achieved the highest diagnostic accuracy (sensitivity 97.2%). Attention mechanisms, ensemble learning, and explainable AI (XAI) methods (e.g., Grad-CAM, LIME) enhanced model interpretability and clinical applicability. Conclusions: Hybrid AI-based diagnostic platforms show strong potential to transform DR screening by offering improved scalability, accuracy, and cost-effectiveness. However, clinical translation will require greater data diversity, robust external validation, and regulatory compliance. These findings provide timely evidence to support the integration of AI-driven DR screening into national diabetes strategies and public health policies, particularly in regions with high diabetes prevalence, such as Qatar and the Middle East.
- Open Access
- 22 July 2019
- Published by Wiley in International Journal of Endocrinology
- Vol. 2019, 1-5
A Prospective Study Comparing Two-Time Points of Thyroid Hormone Replacement during the Holy Month of Ramadan
Background. Muslims all over the world fast during the month of Ramadan from dawn until dusk. There is little data regarding the best timing of levothyroxine intake during the month of Ramadan where taking it on an empty stomach represents a challenge to most patients. Our study aims to compare two-time points of levothyroxine intake during Ramadan in terms of change in thyroid stimulating hormone (TSH), compliance, and convenience. Study Design and Methods. This was an open-label, randomized, prospective trial. Adult patients known to have primary hypothyroidism with stable TSH for the last 6 months who intended to fast during the month of Ramadan were invited to participate in this prospective study. The study took place during Ramadan of H1438 (May-June 2017). All patients were randomly assigned to two groups. In group A (n= 50) patients took levothyroxine 30 minutes before breaking the fast at sunset (iftar), and in group B (n= 46) patients took it 30 minutes before an early morning meal before sunrise (suhour). Results. TSH levels increased in both group A (from 1.99 to 3.28 mIU/L) and group B (from 1.54 to 3.28 mIU/L) after Ramadan fasting. There was no difference between the two groups. Compliance with intake instructions, all of the time, was reported in 41.6% of group A and 35.7% of group B patients. In both the groups, 95% of patients said it was convenient for them to take the medication at the assigned time. Conclusion. Choosing an optimal time for levothyroxine intake during the month of Ramadan remains a challenge. The current study did not provide any evidence on ideal time and dose of levothyroxine administration during fasting to manage hypothyroidism. Studies with a larger number of patients need to be done to further explore this issue.
- 22 July 2019
- Published by Wiley in International Journal of Endocrinology
- Vol. 2019, 1-5
Open AccessA Prospective Study Comparing Two-Time Points of Thyroid Hormone Replacement during the Holy Month of Ramadan
Background. Muslims all over the world fast during the month of Ramadan from dawn until dusk. There is little data regarding the best timing of levothyroxine intake during the month of Ramadan where taking it on an empty stomach represents a challenge to most patients. Our study aims to compare two-time points of levothyroxine intake during Ramadan in terms of change in thyroid stimulating hormone (TSH), compliance, and convenience. Study Design and Methods. This was an open-label, randomized, prospective trial. Adult patients known to have primary hypothyroidism with stable TSH for the last 6 months who intended to fast during the month of Ramadan were invited to participate in this prospective study. The study took place during Ramadan of H1438 (May-June 2017). All patients were randomly assigned to two groups. In group A (n= 50) patients took levothyroxine 30 minutes before breaking the fast at sunset (iftar), and in group B (n= 46) patients took it 30 minutes before an early morning meal before sunrise (suhour). Results. TSH levels increased in both group A (from 1.99 to 3.28 mIU/L) and group B (from 1.54 to 3.28 mIU/L) after Ramadan fasting. There was no difference between the two groups. Compliance with intake instructions, all of the time, was reported in 41.6% of group A and 35.7% of group B patients. In both the groups, 95% of patients said it was convenient for them to take the medication at the assigned time. Conclusion. Choosing an optimal time for levothyroxine intake during the month of Ramadan remains a challenge. The current study did not provide any evidence on ideal time and dose of levothyroxine administration during fasting to manage hypothyroidism. Studies with a larger number of patients need to be done to further explore this issue.