Omid Pournik
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
Omid Pournik has a total of 159 co-authors. Here are the top co-authors by number of shared publications:
- Theodoros N. Arvanitis
University of Birmingham, UK
31 shared publications - Leila Ghalichi
Department of Applied Health Sciences, University of Birmingham, UK
15 shared publications - Saadullah Farooq Abbasi
Department of Electronic, Electrical and Systems Engineering, University of Birmingham, UK
15 shared publications - Teesta Mukherjee
Department of Electronic, Electrical and Systems Engineering, University of Birmingham, Edgbaston, Birmingham B15 2TT, UK
11 shared publications - Xuefei Ding
Department of Electronic, Electrical and Systems Engineering, University of Birmingham, UK
9 shared publications - Gokce Banu Laleci Erturkmen
SRDC Software Research Development & Consultancy Corp, Ankara, Turkey
7 shared publications
Latest Publications
- Open Access
- 21 May 2026
- Published by IOS Press
- Vol. 336, 969-973
Secure and Enhanced Cyber-Threat Detection in IoMT Using Locally Deployed Large Language Models
The Internet of Medical Things (IoMT) is growing exponentially with the advancements in image processing, large language models (LLMs), and other technologies. However, processing patient-identifiable information (PII) in cloud environments raises significant security and compliance concerns. Existing tools provide baseline threat detection; however, they miss complex vulnerabilities. Researchers used cloud-based LLMs such as GPT or Claude to enhance detection, however, these approaches compromise privacy. For this reason, this study proposes a locally deployed and cost-efficient LLM specifically, Llama 3.1 (8B parameters), to identify additional threats and recommend mitigation strategies. The locally deployed Llama 3.1 model identified 12 additional cyberthreats beyond SPYDERISK improving detection coverage and preserving privacy.
- 21 May 2026
- Published by IOS Press
- Vol. 336, 969-973
Open AccessSecure and Enhanced Cyber-Threat Detection in IoMT Using Locally Deployed Large Language Models
The Internet of Medical Things (IoMT) is growing exponentially with the advancements in image processing, large language models (LLMs), and other technologies. However, processing patient-identifiable information (PII) in cloud environments raises significant security and compliance concerns. Existing tools provide baseline threat detection; however, they miss complex vulnerabilities. Researchers used cloud-based LLMs such as GPT or Claude to enhance detection, however, these approaches compromise privacy. For this reason, this study proposes a locally deployed and cost-efficient LLM specifically, Llama 3.1 (8B parameters), to identify additional threats and recommend mitigation strategies. The locally deployed Llama 3.1 model identified 12 additional cyberthreats beyond SPYDERISK improving detection coverage and preserving privacy.
- Open Access
- 21 May 2026
- Published by IOS Press
- Vol. 336, 685-689
Membership Inference or Data Split Bias? Identifying False Positives in Synthetic Medical Image Privacy Audits
Membership Inference Attacks (MIAs) are the current standard for auditing the privacy of synthetic medical data. A high attack score is widely interpreted as a significant privacy leak, but this interpretation assumes the MIA is learning a true membership signal. We argue that these attacks may instead be learning experimental artefacts, specifically data split bias. To test this, we conduct experiments on synthetic brain MRI images from a StyleGAN3 model. We design a Primary MIA (member vs. non-member data) and a critical Control Experiment (disjoint subsets of member data alone). This member-only setup lacks any genuine membership distinction between classes, leaving only data split bias. Our results show the Control Experiment’s AUCs match or exceed the Primary MIA’s (+0.0205 on the 5k-pool Small corpus and +0.0113 on the 30k-pool Big corpus). This compelling evidence demonstrates that a high MIA score can be a false positive for a privacy breach, as the classifier is simply learning statistical artefacts. We conclude that MIA results are unreliable without rigorous control experiments to validate that they are detecting genuine privacy risks, not experimental bias.
- 21 May 2026
- Published by IOS Press
- Vol. 336, 685-689
Open AccessMembership Inference or Data Split Bias? Identifying False Positives in Synthetic Medical Image Privacy Audits
Membership Inference Attacks (MIAs) are the current standard for auditing the privacy of synthetic medical data. A high attack score is widely interpreted as a significant privacy leak, but this interpretation assumes the MIA is learning a true membership signal. We argue that these attacks may instead be learning experimental artefacts, specifically data split bias. To test this, we conduct experiments on synthetic brain MRI images from a StyleGAN3 model. We design a Primary MIA (member vs. non-member data) and a critical Control Experiment (disjoint subsets of member data alone). This member-only setup lacks any genuine membership distinction between classes, leaving only data split bias. Our results show the Control Experiment’s AUCs match or exceed the Primary MIA’s (+0.0205 on the 5k-pool Small corpus and +0.0113 on the 30k-pool Big corpus). This compelling evidence demonstrates that a high MIA score can be a false positive for a privacy breach, as the classifier is simply learning statistical artefacts. We conclude that MIA results are unreliable without rigorous control experiments to validate that they are detecting genuine privacy risks, not experimental bias.
- Open Access
- 21 May 2026
- Published by IOS Press
- Vol. 336, 874-878
Enhancing Ontology Engineering with Large Language Models: A Stage-Wise Human-in-the-Loop Study
Ontology engineering plays a critical role in modelling structured knowledge and ensuring semantic interoperability in digital healthcare. However, manually developing ontologies is time-consuming and dependent on human expertise. This study investigates the utility of large language models (LLMs) on enhancing ontology development with a human-in-the-loop workflow. LLMs were integrated at three checkpoints: (1) term extraction, (2) class and hierarchy definition, and (3) relation specification. Two experimental settings were tested, including LLM-only generation and LLM with additional manual inputs. Results were compared against the stage-wise outputs from a manually constructed ontology using precision, recall, and F1 metrics. Findings showed that human-in-the-loop input consistently improves output quality, while LLMs perform better in early conceptualisation stages than later formalisation stages. This study highlights the complementary strengths of transformer-based reasoning and human validation and presents a reproducible framework for stage-wise evaluation of LLM-assisted ontology engineering. The findings offer practical guidance for integrating generative AI into ontology-driven health data modelling and standardisation.
- 21 May 2026
- Published by IOS Press
- Vol. 336, 874-878
Open AccessEnhancing Ontology Engineering with Large Language Models: A Stage-Wise Human-in-the-Loop Study
Ontology engineering plays a critical role in modelling structured knowledge and ensuring semantic interoperability in digital healthcare. However, manually developing ontologies is time-consuming and dependent on human expertise. This study investigates the utility of large language models (LLMs) on enhancing ontology development with a human-in-the-loop workflow. LLMs were integrated at three checkpoints: (1) term extraction, (2) class and hierarchy definition, and (3) relation specification. Two experimental settings were tested, including LLM-only generation and LLM with additional manual inputs. Results were compared against the stage-wise outputs from a manually constructed ontology using precision, recall, and F1 metrics. Findings showed that human-in-the-loop input consistently improves output quality, while LLMs perform better in early conceptualisation stages than later formalisation stages. This study highlights the complementary strengths of transformer-based reasoning and human validation and presents a reproducible framework for stage-wise evaluation of LLM-assisted ontology engineering. The findings offer practical guidance for integrating generative AI into ontology-driven health data modelling and standardisation.
- Open Access
- 21 May 2026
- Published by IOS Press
- Vol. 336, 1287-1291
Large Language Models for Health Knowledge Modelling in Data Interoperability: A Scoping Review of Methods, Standards, and Applications
Achieving interoperability in healthcare requires semantic alignment of data with standards such as SNOMED CT, LOINC, and FHIR. Manual ontology mapping is slow and inconsistent. Evolving Large Language Models (LLMs) can automate knowledge modelling and data harmonisation. This review explores how LLMs are applied to enhance or automate health knowledge modelling for data interoperability. Following PRISMA-ScR guidance, PubMed and Compendex were searched. Studies applying LLMs to ontology alignment, terminology mapping, schema integration, or knowledge-graph construction were included. From 166 records, 20 studies met the inclusion criteria. Most used GPT-4 or BERT-derived models with retrieval-augmented or embedding-based methods. Reported gains included automation, improved mapping precision, and scalability across standards such as FHIR, OMOP, and UMLS. LLMs show strong potential for automating semantic interoperability in health informatics. Standardised evaluation benchmarks and explainable frameworks are essential for trustworthy adoption.
- 21 May 2026
- Published by IOS Press
- Vol. 336, 1287-1291
Open AccessLarge Language Models for Health Knowledge Modelling in Data Interoperability: A Scoping Review of Methods, Standards, and Applications
Achieving interoperability in healthcare requires semantic alignment of data with standards such as SNOMED CT, LOINC, and FHIR. Manual ontology mapping is slow and inconsistent. Evolving Large Language Models (LLMs) can automate knowledge modelling and data harmonisation. This review explores how LLMs are applied to enhance or automate health knowledge modelling for data interoperability. Following PRISMA-ScR guidance, PubMed and Compendex were searched. Studies applying LLMs to ontology alignment, terminology mapping, schema integration, or knowledge-graph construction were included. From 166 records, 20 studies met the inclusion criteria. Most used GPT-4 or BERT-derived models with retrieval-augmented or embedding-based methods. Reported gains included automation, improved mapping precision, and scalability across standards such as FHIR, OMOP, and UMLS. LLMs show strong potential for automating semantic interoperability in health informatics. Standardised evaluation benchmarks and explainable frameworks are essential for trustworthy adoption.
- Open Access
- 21 May 2026
- Published by IOS Press
- Vol. 336, 964-968
Evaluating Large Language Models for Extracting Clinical Recommendations from Practice Guidelines: A Preliminary Study
CPGs (Clinical Practice Guidelines) contain the best care practices for clinicians to use and are created in many formats. The development of LLMs (Large Language Models) has led to their use in extracting or adapting CPG content to improve the ease of access to information for clinicians. In this paper, we investigate four different LLMs’ ability to extract clinical recommendations from guidelines and apply basic categories to each recommendation, with one test being performed with an example of extracted recommendations and one test without this example. Of the LLMs used, DeepSeek and Grok created the best outputs, extracting the most recommendations and extracting them most correctly, achieving >90% accuracy. While this model does show that LLMs show promise in knowledge extraction, this preliminary evaluation highlights both potential and limitations of LLMs in automating knowledge extraction from clinical guidelines.
- 21 May 2026
- Published by IOS Press
- Vol. 336, 964-968
Open AccessEvaluating Large Language Models for Extracting Clinical Recommendations from Practice Guidelines: A Preliminary Study
CPGs (Clinical Practice Guidelines) contain the best care practices for clinicians to use and are created in many formats. The development of LLMs (Large Language Models) has led to their use in extracting or adapting CPG content to improve the ease of access to information for clinicians. In this paper, we investigate four different LLMs’ ability to extract clinical recommendations from guidelines and apply basic categories to each recommendation, with one test being performed with an example of extracted recommendations and one test without this example. Of the LLMs used, DeepSeek and Grok created the best outputs, extracting the most recommendations and extracting them most correctly, achieving >90% accuracy. While this model does show that LLMs show promise in knowledge extraction, this preliminary evaluation highlights both potential and limitations of LLMs in automating knowledge extraction from clinical guidelines.
- Open Access
- 21 May 2026
- Published by IOS Press
- Vol. 336, 670-674
A Hybrid Delphi-Inspired Expert–LLM Workflow for Efficient Evidence Screening in Systematic Reviews
Systematic reviews are essential for evidence-based healthcare but remain highly resource-intensive, with most retrieved studies ultimately excluded after manual screening. This study developed and evaluated a hybrid expert–LLM workflow to reduce human workload while maintaining accuracy and transparency. Within the Thyroid Risk Stratification Tool (ThyRST) project, ChatGPT-5 was used to classify 14,858 records on thyroid nodule malignancy risk into thematic categories. Recurrent irrelevant concepts were refined through expert consensus involving clinicians and informaticians and embedded as exclusion rules in structured prompts. The model then labelled each abstract as INCLUDE, EXCLUDE, or MAYBE, producing outputs for audit and verification. A random sample of 100 records was independently reviewed by human assessors to evaluate performance. The workflow achieved 96% concordance (κ = 0.91) with human reviewers, with only one false exclusion, and reduced manual screening time by approximately 70%. These results demonstrate that a transparent Delphi-inspired expert–LLM can accurately and reproducibly automate early-stage evidence screening, providing substantial efficiency gains while preserving human oversight and methodological rigor. The approach offers a practical pathway toward the responsible integration of generative AI in systematic review methodology and digital health research.
- 21 May 2026
- Published by IOS Press
- Vol. 336, 670-674
Open AccessA Hybrid Delphi-Inspired Expert–LLM Workflow for Efficient Evidence Screening in Systematic Reviews
Systematic reviews are essential for evidence-based healthcare but remain highly resource-intensive, with most retrieved studies ultimately excluded after manual screening. This study developed and evaluated a hybrid expert–LLM workflow to reduce human workload while maintaining accuracy and transparency. Within the Thyroid Risk Stratification Tool (ThyRST) project, ChatGPT-5 was used to classify 14,858 records on thyroid nodule malignancy risk into thematic categories. Recurrent irrelevant concepts were refined through expert consensus involving clinicians and informaticians and embedded as exclusion rules in structured prompts. The model then labelled each abstract as INCLUDE, EXCLUDE, or MAYBE, producing outputs for audit and verification. A random sample of 100 records was independently reviewed by human assessors to evaluate performance. The workflow achieved 96% concordance (κ = 0.91) with human reviewers, with only one false exclusion, and reduced manual screening time by approximately 70%. These results demonstrate that a transparent Delphi-inspired expert–LLM can accurately and reproducibly automate early-stage evidence screening, providing substantial efficiency gains while preserving human oversight and methodological rigor. The approach offers a practical pathway toward the responsible integration of generative AI in systematic review methodology and digital health research.
- Open Access
- 26 June 2025
- Published by IOS Press
- Vol. 328, 56-60
Enhancing Diagnostic Precision: Utilising a Large Language Model to Extract U Scores from Thyroid Sonography Reports
This study evaluates the performance of ChatGPT-4, a Large Language Model (LLM), in automatically extracting U scores from free-text thyroid ultrasound reports collected from University Hospitals Birmingham (UHB), UK, between 2014 and 2024. The LLM was provided with guidelines on the U classification system and extracted U scores independently from 14,248 de-identified reports, without access to human-assigned scores. The LLM-extracted scores were compared to initial clinician-assigned and refined U scores provided by expert reviewers. The LLM achieved 97.7% agreement with refined human U scores, successfully identifying the highest U score in 98.1% of reports with multiple nodules. Most discrepancies (2.5%) were linked to ambiguous descriptions, multi-nodule reports, and cases with human-documented uncertainty. While the results demonstrate the potential for LLMs to improve reporting consistency and reduce manual workload, ethical and governance challenges such as transparency, privacy, and bias must be addressed before routine clinical deployment. Embedding LLMs into reporting workflows, such as Online Analytical Processing (OLAP) tools, could further enhance reporting quality and consistency.
- 26 June 2025
- Published by IOS Press
- Vol. 328, 56-60
Open AccessEnhancing Diagnostic Precision: Utilising a Large Language Model to Extract U Scores from Thyroid Sonography Reports
This study evaluates the performance of ChatGPT-4, a Large Language Model (LLM), in automatically extracting U scores from free-text thyroid ultrasound reports collected from University Hospitals Birmingham (UHB), UK, between 2014 and 2024. The LLM was provided with guidelines on the U classification system and extracted U scores independently from 14,248 de-identified reports, without access to human-assigned scores. The LLM-extracted scores were compared to initial clinician-assigned and refined U scores provided by expert reviewers. The LLM achieved 97.7% agreement with refined human U scores, successfully identifying the highest U score in 98.1% of reports with multiple nodules. Most discrepancies (2.5%) were linked to ambiguous descriptions, multi-nodule reports, and cases with human-documented uncertainty. While the results demonstrate the potential for LLMs to improve reporting consistency and reduce manual workload, ethical and governance challenges such as transparency, privacy, and bias must be addressed before routine clinical deployment. Embedding LLMs into reporting workflows, such as Online Analytical Processing (OLAP) tools, could further enhance reporting quality and consistency.
- Open Access
- 26 June 2025
- Published by IOS Press
- Vol. 328, 51-55
Recent Advances in Generative Models for Synthetic Brain MRI Image Generation
With the use of artificial intelligence (AI) for image analysis of Magnetic Resonance Imaging (MRI), the lack of training data has become an issue. Realistic synthetic MRI images can serve as a solution and generative models have been proposed. This study investigates the most recent advances on synthetic brain MRI image generation with AI-based generative models. A search has been conducted on the relevant studies published within the last three years, followed by a narrative review on the identified articles. Popular models from the search results have been discussed in this study, including Generative Adversarial Networks (GANs), diffusion models, Variational Autoencoders (VAEs), and transformers.
- 26 June 2025
- Published by IOS Press
- Vol. 328, 51-55
Open AccessRecent Advances in Generative Models for Synthetic Brain MRI Image Generation
With the use of artificial intelligence (AI) for image analysis of Magnetic Resonance Imaging (MRI), the lack of training data has become an issue. Realistic synthetic MRI images can serve as a solution and generative models have been proposed. This study investigates the most recent advances on synthetic brain MRI image generation with AI-based generative models. A search has been conducted on the relevant studies published within the last three years, followed by a narrative review on the identified articles. Popular models from the search results have been discussed in this study, including Generative Adversarial Networks (GANs), diffusion models, Variational Autoencoders (VAEs), and transformers.
- Open Access
- 26 June 2025
- Published by IOS Press
- Vol. 328, 283-287
User Experience and Usability Evaluation of the CAREPATH Adaptive Integrated Care Platform
This study evaluates the user experience and usability of a web-based tool, AICP, that supports healthcare professionals in creating personalized care plans with the help of clinical decision support (CDS), using the System Usability Scale (SUS), User Experience Questionnaire (UEQ), and Single Ease Questions (SEQs). The results show high usability (SUS: 75.45) and positive user experience, particularly in stimulation and novelty. Following CDS recommendations in a structured way and displaying patients’ care plan adherence in charts and tables were found effective. However, dynamic content changes and raw sensor data presentation were identified as areas for improvement. Combining data through reasoning or allowing users to make inferences could further improve usability, supporting better patient care coordination.
- 26 June 2025
- Published by IOS Press
- Vol. 328, 283-287
Open AccessUser Experience and Usability Evaluation of the CAREPATH Adaptive Integrated Care Platform
This study evaluates the user experience and usability of a web-based tool, AICP, that supports healthcare professionals in creating personalized care plans with the help of clinical decision support (CDS), using the System Usability Scale (SUS), User Experience Questionnaire (UEQ), and Single Ease Questions (SEQs). The results show high usability (SUS: 75.45) and positive user experience, particularly in stimulation and novelty. Following CDS recommendations in a structured way and displaying patients’ care plan adherence in charts and tables were found effective. However, dynamic content changes and raw sensor data presentation were identified as areas for improvement. Combining data through reasoning or allowing users to make inferences could further improve usability, supporting better patient care coordination.
- Open Access
- 26 June 2025
- Published by IOS Press
- Vol. 328, 268-272
A Novel and Secure 3D Colour Medical Image Encryption Technique Using 3D Hyperchaotic Map, S-box and Discrete Wavelet Transform
Over the past two decades, there has been a substantial increase in the use of the Internet of Medical Things (IoMT). In the smart healthcare setting, patients’ data can be quickly collected, stored and processed through insecure medium such as the internet or cloud computing. To address this issue, researchers have developed a range of encryption algorithms to protect medical image data, however these remain vulnerable to brute force and differential cryptanalysis attacks by eavesdroppers. In this study, we propose an efficient approach to enhance the security of medical image transmission by transforming the ciphertext image into a visually meaningful image. The proposed algorithm uses a 3D hyperchaotic system to generate three chaotic sequences for permutation and diffusion, followed by the application of a substitution box (S Box) to increase redundancy. Additionally, the proposed study employed discrete wavelet transform (DWT) to transform ciphertext image into a visually meaningful image. This final image is not only secure but also improves its resistance to cyberattacks. The proposed encryption model demonstrates strong security performance, with key metrics including Unified Average Changing Intensity (UACI) of 36.17% and Number of Pixels Change Rate (NPCR) of 99.57%, highlighting its effectiveness in ensuring secure medical image transmission.
- 26 June 2025
- Published by IOS Press
- Vol. 328, 268-272
Open AccessA Novel and Secure 3D Colour Medical Image Encryption Technique Using 3D Hyperchaotic Map, S-box and Discrete Wavelet Transform
Over the past two decades, there has been a substantial increase in the use of the Internet of Medical Things (IoMT). In the smart healthcare setting, patients’ data can be quickly collected, stored and processed through insecure medium such as the internet or cloud computing. To address this issue, researchers have developed a range of encryption algorithms to protect medical image data, however these remain vulnerable to brute force and differential cryptanalysis attacks by eavesdroppers. In this study, we propose an efficient approach to enhance the security of medical image transmission by transforming the ciphertext image into a visually meaningful image. The proposed algorithm uses a 3D hyperchaotic system to generate three chaotic sequences for permutation and diffusion, followed by the application of a substitution box (S Box) to increase redundancy. Additionally, the proposed study employed discrete wavelet transform (DWT) to transform ciphertext image into a visually meaningful image. This final image is not only secure but also improves its resistance to cyberattacks. The proposed encryption model demonstrates strong security performance, with key metrics including Unified Average Changing Intensity (UACI) of 36.17% and Number of Pixels Change Rate (NPCR) of 99.57%, highlighting its effectiveness in ensuring secure medical image transmission.