Shereen Fouad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Shereen Fouad has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Bahadar Bhatia
Sandwell and West Birmingham Hospitals NHS Trust, Birmingham, U.K.
3 shared publications Arvind Rajasekaran
Sandwell and West Birmingham Hospitals NHS Trust
2 shared publications- Arvind Rajasekaran
Sandwell and West Birmingham NHS Trust, UK
2 shared publications Bahadar Bhatia
Sandwell and West Birmingham Hospitals NHS Trust
2 shared publications- Gabriel Landini
School of Dentistry, College of Medical and Dental Sciences, University of Birmingham, 5 Mill Pool Way, Edgbaston, Birmingham B5 7EG, UK
2 shared publications - Izegbua E. Ihongbe
School of Computer Science and Digital Technologies, Aston University, Birmingham, U.K.
2 shared publications
Latest Publications
- Open Access
- 19 August 2026
- Published by MDPI AG in Preprints.org
Multimodal Artificial Intelligence for Pneumonia Prognosis and Clinical Deterioration: A Systematic Review
Objective: To review multimodal artificial intelligence (AI) models for predicting adverse outcomes in pneumonia, with emphasis on prognosis, validation, benchmarking, explainability, and clinical implementation readiness. Materials and Methods: We conducted a PROSPERO-registered systematic review. PubMed, Scopus, IEEE Xplore, and supplementary register/citation-search sources were searched between 01 January 2000 and 27 February 2026. Eligible studies integrated at least two heterogeneous clinical data modalities within one predictive framework for pneumonia-related deterioration, mortality, escalation of care, ventilation, or related adverse outcomes. We extracted modality composition, fusion architecture, outcome alignment, validation, performance metrics, clinical benchmarking, explainability, predictive uncertainty, workflow integration, governance reporting, and risk of bias. Results: Of 10,460 identified records, 49 studies were included. The evidence base was dominated by COVID-era studies. Structured electronic health record data, laboratories, and vital signs were more common than imaging or clinical notes. Early fusion was the predominant strategy, while attention-based and graph-based fusion were rare. External validation was reported in 19/49 studies, calibration in 9/49, temporal validation in 5/49, decision curve analysis in 3/49, and prospective evaluation in 3/49. Incremental AUROC over the best unimodal baseline was computable in 19 studies and was usually modest. Discussion: The literature emphasised retrospective discrimination more than clinical utility, with limited reporting of added value, workflow, predictive uncertainty, and governance. Conclusion: Multimodal pneumonia prognosis research is active but not yet implementation-ready. Future studies should prioritise externally validated, calibrated, explainable, clinician-aligned, and workflow-aware models.
- 19 August 2026
- Published by MDPI AG in Preprints.org
Open AccessMultimodal Artificial Intelligence for Pneumonia Prognosis and Clinical Deterioration: A Systematic Review
Objective: To review multimodal artificial intelligence (AI) models for predicting adverse outcomes in pneumonia, with emphasis on prognosis, validation, benchmarking, explainability, and clinical implementation readiness. Materials and Methods: We conducted a PROSPERO-registered systematic review. PubMed, Scopus, IEEE Xplore, and supplementary register/citation-search sources were searched between 01 January 2000 and 27 February 2026. Eligible studies integrated at least two heterogeneous clinical data modalities within one predictive framework for pneumonia-related deterioration, mortality, escalation of care, ventilation, or related adverse outcomes. We extracted modality composition, fusion architecture, outcome alignment, validation, performance metrics, clinical benchmarking, explainability, predictive uncertainty, workflow integration, governance reporting, and risk of bias. Results: Of 10,460 identified records, 49 studies were included. The evidence base was dominated by COVID-era studies. Structured electronic health record data, laboratories, and vital signs were more common than imaging or clinical notes. Early fusion was the predominant strategy, while attention-based and graph-based fusion were rare. External validation was reported in 19/49 studies, calibration in 9/49, temporal validation in 5/49, decision curve analysis in 3/49, and prospective evaluation in 3/49. Incremental AUROC over the best unimodal baseline was computable in 19 studies and was usually modest. Discussion: The literature emphasised retrospective discrimination more than clinical utility, with limited reporting of added value, workflow, predictive uncertainty, and governance. Conclusion: Multimodal pneumonia prognosis research is active but not yet implementation-ready. Future studies should prioritise externally validated, calibrated, explainable, clinician-aligned, and workflow-aware models.
- 13 August 2026
- Published by Springer Nature
- p. 163-176
From Dialogue to Feedback: A GMC-Aligned Generative AI Simulation Platform for Clinical Communication Training
- 13 August 2026
- Published by Springer Nature
- p. 163-176
From Dialogue to Feedback: A GMC-Aligned Generative AI Simulation Platform for Clinical Communication Training
- Open Access
- 15 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 12498-12513
Human-Centered User Interface Design for Explainable AI in Chest Radiology: A Multi-Phase Co-Design Approach
The AI-powered computer vision is transforming medical imaging by improving analysis, diagnosis, and treatment. However, the opaque nature of deep learning often limits its adoption in critical clinical settings, where interpretability and trust are paramount. Explainable AI (XAI) aims at mitigating those limitations by creating visual and interpretable explanations of model decisions. However, poor user interface (UI) design frequently hampers the usability and clinical integration of these explanations. This paper addresses the critical need for human-centered UI design in XAI systems for chest radiology, a vital diagnostic domain for diseases such as pneumonia, lung cancer, and pulmonary embolism. Two deep learning–based XAI systems were developed for detecting pneumonia from chest X-rays and diagnosing COVID-19 from chest CT scans using post-hoc explanation methods, Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-Agnostic Explanations (LIME). Building on these systems, we introduce a novel multi-phase Human-Centered Design (HCD) methodology that actively involves radiologists and clinicians through participatory co-design, iterative prototyping, and multidisciplinary evaluation workshop. This process identified fifteen preliminary UI features tailored to clinical needs and led to a prototype XAI interface. Empirical evaluation from a multidisciplinary workshop revealed that radiologists preferred diagnostic prediction displays combining the original and AI-annotated images shown side-by-side or with adjustable overlays accompanied by explanatory text tailored to various audiences, including radiologists, clinicians, and patients. Participants agreed that highlighting the confidence scores of AI outputs aligned with clinical reasoning enhances perceived trust, diagnostic efficiency, and willingness to adopt XAI in daily practice. Our study demonstrates that collaborative multidisciplinary co-design is essential for bridging technical innovation and clinical utility, offering valuable insights for the future development of effective, trustworthy XAI user interfaces in medical imaging.
- 15 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 12498-12513
Open AccessHuman-Centered User Interface Design for Explainable AI in Chest Radiology: A Multi-Phase Co-Design Approach
The AI-powered computer vision is transforming medical imaging by improving analysis, diagnosis, and treatment. However, the opaque nature of deep learning often limits its adoption in critical clinical settings, where interpretability and trust are paramount. Explainable AI (XAI) aims at mitigating those limitations by creating visual and interpretable explanations of model decisions. However, poor user interface (UI) design frequently hampers the usability and clinical integration of these explanations. This paper addresses the critical need for human-centered UI design in XAI systems for chest radiology, a vital diagnostic domain for diseases such as pneumonia, lung cancer, and pulmonary embolism. Two deep learning–based XAI systems were developed for detecting pneumonia from chest X-rays and diagnosing COVID-19 from chest CT scans using post-hoc explanation methods, Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-Agnostic Explanations (LIME). Building on these systems, we introduce a novel multi-phase Human-Centered Design (HCD) methodology that actively involves radiologists and clinicians through participatory co-design, iterative prototyping, and multidisciplinary evaluation workshop. This process identified fifteen preliminary UI features tailored to clinical needs and led to a prototype XAI interface. Empirical evaluation from a multidisciplinary workshop revealed that radiologists preferred diagnostic prediction displays combining the original and AI-annotated images shown side-by-side or with adjustable overlays accompanied by explanatory text tailored to various audiences, including radiologists, clinicians, and patients. Participants agreed that highlighting the confidence scores of AI outputs aligned with clinical reasoning enhances perceived trust, diagnostic efficiency, and willingness to adopt XAI in daily practice. Our study demonstrates that collaborative multidisciplinary co-design is essential for bridging technical innovation and clinical utility, offering valuable insights for the future development of effective, trustworthy XAI user interfaces in medical imaging.
- Open Access
- 12 January 2026
- Published by Springer Nature in Research Square
Integrating Explainability for Sentiment Interpretation, Misclassification, and Bias Detection in Women-in-STEM Social Media
Transformer-based models have advanced sentiment analysis but remain difficult to interpret, especially in sensitive domains such as public discourse about women in science, technology, engineering, and mathematics (STEM). Building on earlier work on women-in-STEM sentiment, this study introduces an ethically curated corpus of over 140,000 English tweets/X posts and a validated automatic labelling pipeline that combines hand annotated data with state-of-the-art transformer-based sentiment models. We quantitatively compare several transfer-learning approaches and identify the best-performing model for this domain, achieving high overall accuracy while revealing systematic confusions between neutral and mildly positive content.To open this “black box,” we apply {SHAPley Additive exPlanations (SHAP)} and Integrated Gradients (IG) XAI methods to obtain word-level attributions for correctly and incorrectly classified tweets, showing how specific linguistic cues, such as celebratory hashtags, negation, and emotionally charged terms, drive sentiment predictions and common error modes. We further design a bias probing protocol based on minimally different gendered sentence pairs (e.g., “Women in STEM” vs. “Men in STEM”) and show that the model assigns systematically different sentiment scores and attributions to male- and female-marked variants, indicating learned gender bias. All data processing scripts, model configurations, and analysis code are released here to support transparency, reproducibility, and future research on explainable and fair sentiment analysis in socially critical contexts
- 12 January 2026
- Published by Springer Nature in Research Square
Open AccessIntegrating Explainability for Sentiment Interpretation, Misclassification, and Bias Detection in Women-in-STEM Social Media
Transformer-based models have advanced sentiment analysis but remain difficult to interpret, especially in sensitive domains such as public discourse about women in science, technology, engineering, and mathematics (STEM). Building on earlier work on women-in-STEM sentiment, this study introduces an ethically curated corpus of over 140,000 English tweets/X posts and a validated automatic labelling pipeline that combines hand annotated data with state-of-the-art transformer-based sentiment models. We quantitatively compare several transfer-learning approaches and identify the best-performing model for this domain, achieving high overall accuracy while revealing systematic confusions between neutral and mildly positive content.To open this “black box,” we apply {SHAPley Additive exPlanations (SHAP)} and Integrated Gradients (IG) XAI methods to obtain word-level attributions for correctly and incorrectly classified tweets, showing how specific linguistic cues, such as celebratory hashtags, negation, and emotionally charged terms, drive sentiment predictions and common error modes. We further design a bias probing protocol based on minimally different gendered sentence pairs (e.g., “Women in STEM” vs. “Men in STEM”) and show that the model assigns systematically different sentiment scores and attributions to male- and female-marked variants, indicating learned gender bias. All data processing scripts, model configurations, and analysis code are released here to support transparency, reproducibility, and future research on explainable and fair sentiment analysis in socially critical contexts
- Open Access
- 27 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 143-148
Explainable AI-Assisted Triage in Emergency Departments Using Multi-Modal Clinical Data
- 27 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 143-148
Open AccessExplainable AI-Assisted Triage in Emergency Departments Using Multi-Modal Clinical Data
- 4 April 2025
- Published by Springer Nature
- p. 187-197
Explainable Deep Learning Framework for Ground Glass Opacity (GGO) Segmentation from Chest CT Scans
- 4 April 2025
- Published by Springer Nature
- p. 187-197
Explainable Deep Learning Framework for Ground Glass Opacity (GGO) Segmentation from Chest CT Scans
- Open Access
- 26 February 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 38 (6) , 3634-3651
Explained Deep Learning Framework for COVID-19 Detection in Volumetric CT Images Aligned with the British Society of Thoracic Imaging Reporting Guidance: A Pilot Study
In March 2020, the British Society of Thoracic Imaging (BSTI) introduced a reporting guidance for COVID-19 detection to streamline standardised reporting and enhance agreement between radiologists. However, most current DL methods do not conform to this guidance. This study introduces a multi-class deep learning (DL) model to identify BSTI COVID-19 categories within CT volumes, classified as ‘Classic’, ‘Probable’, ‘Indeterminate’, or ‘Non-COVID’. A total of 56 CT pseudoanonymised images were collected from patients with suspected COVID-19 and annotated by an experienced chest subspecialty radiologist following the BSTI guidance. We evaluated the performance of multiple DL-based models, including three-dimensional (3D) ResNet architectures, pre-trained on the Kinetics-700 video dataset. For better interpretability of the results, our approach incorporates a post-hoc visual explainability feature to highlight the areas of the image most indicative of the COVID-19 category. Our four-class classification DL framework achieves an overall accuracy of 75%. However, the model struggled to detect the ‘Indeterminate’ COVID-19 group, whose removal significantly improved the model’s accuracy to 90%. The proposed explainable multi-classification DL model yields accurate detection of ‘Classic’, ‘Probable’, and ‘Non-COVID’ categories with poor detection ability for ‘Indeterminate’ COVID-19 cases. These findings are consistent with clinical studies that aimed at validating the BSTI reporting manually amongst consultant radiologists.
- 26 February 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 38 (6) , 3634-3651
Open AccessExplained Deep Learning Framework for COVID-19 Detection in Volumetric CT Images Aligned with the British Society of Thoracic Imaging Reporting Guidance: A Pilot Study
In March 2020, the British Society of Thoracic Imaging (BSTI) introduced a reporting guidance for COVID-19 detection to streamline standardised reporting and enhance agreement between radiologists. However, most current DL methods do not conform to this guidance. This study introduces a multi-class deep learning (DL) model to identify BSTI COVID-19 categories within CT volumes, classified as ‘Classic’, ‘Probable’, ‘Indeterminate’, or ‘Non-COVID’. A total of 56 CT pseudoanonymised images were collected from patients with suspected COVID-19 and annotated by an experienced chest subspecialty radiologist following the BSTI guidance. We evaluated the performance of multiple DL-based models, including three-dimensional (3D) ResNet architectures, pre-trained on the Kinetics-700 video dataset. For better interpretability of the results, our approach incorporates a post-hoc visual explainability feature to highlight the areas of the image most indicative of the COVID-19 category. Our four-class classification DL framework achieves an overall accuracy of 75%. However, the model struggled to detect the ‘Indeterminate’ COVID-19 group, whose removal significantly improved the model’s accuracy to 90%. The proposed explainable multi-classification DL model yields accurate detection of ‘Classic’, ‘Probable’, and ‘Non-COVID’ categories with poor detection ability for ‘Indeterminate’ COVID-19 cases. These findings are consistent with clinical studies that aimed at validating the BSTI reporting manually amongst consultant radiologists.
- Open Access
- 21 February 2025
- Published by Springer Nature
- p. 1-13
An Explainable Deep Learning Framework for Mandibular Canal Segmentation from Cone Beam Computed Tomography Volumes
Cone Beam Computed Tomography (CBCT) is an indispensable imaging modality in oral radiology, offering comprehensive dental anatomical information. Accurate detection of the mandibular canal (MC), a crucial anatomical structure in the lower jaw, within CBCT volumes is essential to support clinical dentistry workflows, including diagnosis, preoperative treatment planning, and postoperative evaluation. In this study, we present a deep learning-based (DL) approach for MC segmentation using 3D U-Net and 3D Attention U-Net networks. We collected a unique dataset of CBCT scans from 20 anonymous hemisected mandibular bones, which were further processed for analysis. The samples were scanned using a CBCT scanner after inserting a wire through the whole length of the MC to identify its location in space (as a gold standard). Our experimental results demonstrate that the 3D Attention U-Net outperforms the standard 3D U-Net in detecting the MC’s location, with Dice similarity score, Precision, and Recall values of 0.65, 0.75, and 0.60, respectively. Unlike current DL-enabled methods for MC segmentation, which face deployment and trust challenges due to their “black-box” nature, our approach incorporates a post-hoc visual explainability feature through the Grad-CAM++ (Gradient-weighted Class Activation Mapping) algorithm. This tool highlights important regions within the CBCT volumes that influence the model’s predictions, providing valuable insights into the segmentation process, and bridging the gap between cutting-edge DL technology and clinical practice.
- 21 February 2025
- Published by Springer Nature
- p. 1-13
Open AccessAn Explainable Deep Learning Framework for Mandibular Canal Segmentation from Cone Beam Computed Tomography Volumes
Cone Beam Computed Tomography (CBCT) is an indispensable imaging modality in oral radiology, offering comprehensive dental anatomical information. Accurate detection of the mandibular canal (MC), a crucial anatomical structure in the lower jaw, within CBCT volumes is essential to support clinical dentistry workflows, including diagnosis, preoperative treatment planning, and postoperative evaluation. In this study, we present a deep learning-based (DL) approach for MC segmentation using 3D U-Net and 3D Attention U-Net networks. We collected a unique dataset of CBCT scans from 20 anonymous hemisected mandibular bones, which were further processed for analysis. The samples were scanned using a CBCT scanner after inserting a wire through the whole length of the MC to identify its location in space (as a gold standard). Our experimental results demonstrate that the 3D Attention U-Net outperforms the standard 3D U-Net in detecting the MC’s location, with Dice similarity score, Precision, and Recall values of 0.65, 0.75, and 0.60, respectively. Unlike current DL-enabled methods for MC segmentation, which face deployment and trust challenges due to their “black-box” nature, our approach incorporates a post-hoc visual explainability feature through the Grad-CAM++ (Gradient-weighted Class Activation Mapping) algorithm. This tool highlights important regions within the CBCT volumes that influence the model’s predictions, providing valuable insights into the segmentation process, and bridging the gap between cutting-edge DL technology and clinical practice.
- Top Cited PapersOpen Access
- 9 October 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (10) , e0308758
Evaluating Explainable Artificial Intelligence (XAI) techniques in chest radiology imaging through a human-centered Lens
The field of radiology imaging has experienced a remarkable increase in using of deep learning (DL) algorithms to support diagnostic and treatment decisions. This rise has led to the development of Explainable AI (XAI) system to improve the transparency and trust of complex DL methods. However, XAI systems face challenges in gaining acceptance within the healthcare sector, mainly due to technical hurdles in utilizing these systems in practice and the lack of human-centered evaluation/validation. In this study, we focus on visual XAI systems applied to DL-enabled diagnostic system in chest radiography. In particular, we conduct a user study to evaluate two prominent visual XAI techniques from the human perspective. To this end, we created two clinical scenarios for diagnosing pneumonia and COVID-19 using DL techniques applied to chest X-ray and CT scans. The achieved accuracy rates were 90% for pneumonia and 98% for COVID-19. Subsequently, we employed two well-known XAI methods, Grad-CAM (Gradient-weighted Class Activation Mapping) and LIME (Local Interpretable Model-agnostic Explanations), to generate visual explanations elucidating the AI decision-making process. The visual explainability results were shared through a user study, undergoing evaluation by medical professionals in terms of clinical relevance, coherency, and user trust. In general, participants expressed a positive perception of the use of XAI systems in chest radiography. However, there was a noticeable lack of awareness regarding their value and practical aspects. Regarding preferences, Grad-CAM showed superior performance over LIME in terms of coherency and trust, although concerns were raised about its clinical usability. Our findings highlight key user-driven explainability requirements, emphasizing the importance of multi-modal explainability and the necessity to increase awareness of XAI systems among medical practitioners. Inclusive design was also identified as a crucial need to ensure better alignment of these systems with user needs.
- 9 October 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (10) , e0308758
Top Cited PapersOpen AccessEvaluating Explainable Artificial Intelligence (XAI) techniques in chest radiology imaging through a human-centered Lens
The field of radiology imaging has experienced a remarkable increase in using of deep learning (DL) algorithms to support diagnostic and treatment decisions. This rise has led to the development of Explainable AI (XAI) system to improve the transparency and trust of complex DL methods. However, XAI systems face challenges in gaining acceptance within the healthcare sector, mainly due to technical hurdles in utilizing these systems in practice and the lack of human-centered evaluation/validation. In this study, we focus on visual XAI systems applied to DL-enabled diagnostic system in chest radiography. In particular, we conduct a user study to evaluate two prominent visual XAI techniques from the human perspective. To this end, we created two clinical scenarios for diagnosing pneumonia and COVID-19 using DL techniques applied to chest X-ray and CT scans. The achieved accuracy rates were 90% for pneumonia and 98% for COVID-19. Subsequently, we employed two well-known XAI methods, Grad-CAM (Gradient-weighted Class Activation Mapping) and LIME (Local Interpretable Model-agnostic Explanations), to generate visual explanations elucidating the AI decision-making process. The visual explainability results were shared through a user study, undergoing evaluation by medical professionals in terms of clinical relevance, coherency, and user trust. In general, participants expressed a positive perception of the use of XAI systems in chest radiography. However, there was a noticeable lack of awareness regarding their value and practical aspects. Regarding preferences, Grad-CAM showed superior performance over LIME in terms of coherency and trust, although concerns were raised about its clinical usability. Our findings highlight key user-driven explainability requirements, emphasizing the importance of multi-modal explainability and the necessity to increase awareness of XAI systems among medical practitioners. Inclusive design was also identified as a crucial need to ensure better alignment of these systems with user needs.
- Open Access
- 29 June 2023
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 26 (3) , 823-846
A review of natural language processing in contact centre automation
Contact centres have been highly valued by organizations for a long time. However, the COVID-19 pandemic has highlighted their critical importance in ensuring business continuity, economic activity, and quality customer support. The pandemic has led to an increase in customer inquiries related to payment extensions, cancellations, and stock inquiries, each with varying degrees of urgency. To address this challenge, organizations have taken the opportunity to re-evaluate the function of contact centres and explore innovative solutions. Next-generation platforms that incorporate machine learning techniques and natural language processing, such as self-service voice portals and chatbots, are being implemented to enhance customer service. These platforms offer robust features that equip customer agents with the necessary tools to provide exceptional customer support. Through an extensive review of existing literature, this paper aims to uncover research gaps and explore the advantages of transitioning to a contact centre that utilizes natural language solutions as the norm. Additionally, we will examine the major challenges faced by contact centre organizations and offer recommendations for overcoming them, ultimately expediting the pace of contact centre automation.
- 29 June 2023
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 26 (3) , 823-846
Open AccessA review of natural language processing in contact centre automation
Contact centres have been highly valued by organizations for a long time. However, the COVID-19 pandemic has highlighted their critical importance in ensuring business continuity, economic activity, and quality customer support. The pandemic has led to an increase in customer inquiries related to payment extensions, cancellations, and stock inquiries, each with varying degrees of urgency. To address this challenge, organizations have taken the opportunity to re-evaluate the function of contact centres and explore innovative solutions. Next-generation platforms that incorporate machine learning techniques and natural language processing, such as self-service voice portals and chatbots, are being implemented to enhance customer service. These platforms offer robust features that equip customer agents with the necessary tools to provide exceptional customer support. Through an extensive review of existing literature, this paper aims to uncover research gaps and explore the advantages of transitioning to a contact centre that utilizes natural language solutions as the norm. Additionally, we will examine the major challenges faced by contact centre organizations and offer recommendations for overcoming them, ultimately expediting the pace of contact centre automation.