دانشگاه علوم پزشکی کرمان Journal of Health and Biomedical Informatics 2423-3870 12 1 2025 6 1 Design an Optimized Deep Learning Model for Liver Disease Prediction 1 17 FA Davoud Jalalian PhD in Electrical and Electronic Engineering, Assistant Professor, Department of Electrical Engineering, Islamic Azad University, Fouman and Shaft Branch, Fouman and Shaft, Iran Safoura Ashoori PhD Student in Computer Science, Rasht Branch, Islamic Azad University, Rasht, Iran Introduction: The incidence of liver disease resulting from excessive alcohol consumption, inhalation of polluted gases, drug use, contaminated food, and food packaging is rapidly increasing. As this disease often presents no symptoms or complications in its early stages, timely diagnosis can be challenging. However, if diagnosed early, treatment can be administered more easily and at a lower cost. In more advanced stages, liver diseases can progress to cirrhosis and liver cancer, leading to significantly more difficult treatment options and, in some cases, resulting in the patient's death. Method: Considering the challenges involved, early diagnosis of liver disease is crucial for determining treatment solutions, duration of treatment, and recovery. With advancements in machine learning and deep learning technologies, which can analyze and learn from complex and large datasets, these tools can be employed for the early prediction of liver disease. In this study, we utilized a dataset of liver disease patients from India. After data preprocessing, a deep learning model optimized by the metaheuristic algorithm of the Lizard Search was proposed to enhance prediction accuracy by leveraging the advantages of metaheuristic algorithms and to assist in timely disease diagnosis. Results: Our proposed method employs a deep neural network optimized using the metaheuristic RSA algorithm. This model achieved promising results in diagnosing liver disease, with an approximate accuracy of 96.9%, a reliability of around 97.2%, and an F1 score close to 96.7%. This approach demonstrates high efficiency in the early and accurate detection of liver diseases, contributing to improved treatment processes. Conclusion: The results demonstrated that combining a feedforward neural network with metaheuristic algorithms significantly improved the accuracy and reliability of liver disease diagnosis. The proposed model enhanced prediction accuracy and diagnostic validity compared to previous methods. These advancements can effectively facilitate the early detection of liver diseases, leading to improved treatment processes and a reduction in complications associated with disease progression.

دانشگاه علوم پزشکی کرمان Journal of Health and Biomedical Informatics 2423-3870 12 1 2025 6 1 Equipment Design for Telemedicine Examinations: An Approach to Enhancing Primary Healthcare 18 29 FA Rezvan Alidadi Department of Industrial Design, Faculty of Architecture and Urban Planning, Iran University of Science and Technology, Tehran, Iran Hasan Sadeghi Naeini Associate Professor, Department of Industrial Design, Faculty of Architecture and Urban Planning, Iran University of Science and Technology, Tehran, Iran Introduction: In many developing countries, particularly Iran, providing medical services in rural areas faces numerous challenges, including shortages of healthcare professionals, dispersed populations, limited infrastructure, and high travel costs. In this context, telemedicine emerges as an innovative solution that can enhance both access to and efficiency of healthcare services. However, there is still limited evidence regarding the feasibility of replacing in-person examinations with remote alternatives. This study aims to offer a comprehensive framework to guide designers in understanding contextual challenges and effectively navigating the early stages of designing telemedicine examination equipment before defining specific technical solutions. Method: This descriptive-analytical study was conducted in two phases. First, needs were identified through field observations and semi-structured interviews with 25 residents of the rural village of Zamenjan. In the second phase, a multidisciplinary team comprising physicians, local health workers, and residents collaboratively developed a checklist for designing remote medical examination tools, ensuring alignment with both community needs and professional medical standards. Results: Qualitative data were analyzed using thematic analysis. Key themes included resource limitations, technological access barriers, and implementation challenges. These insights were directly utilized to develop the final design checklist, highlighting essential features such as a modular structure, a user-friendly interface, a sustainable power supply, data security, and the incorporation of advanced technologies like augmented reality and haptic feedback. Conclusion: The findings indicate that developing remote examination equipment through a comprehensive and multidisciplinary approach can significantly enhance access to and the quality of medical services in rural and underserved areas. By utilizing the provided checklist, designers can create efficient, sustainable, and user-friendly tools that address local limitations and specific needs, ultimately improving access to medical services and the quality of primary healthcare in these regions.

دانشگاه علوم پزشکی کرمان Journal of Health and Biomedical Informatics 2423-3870 12 1 2025 6 1 Spatial Distribution Analysis of Hypertension Patients: A Case Study 30 51 FA Fatemeh Taghizadeh M.A in Geography and Urban Planning, Department of Geography, Faculty of Social Sciences, University of Mohaghegh Ardabili, Ardabil, Iran Alireza Mohammadi Department of Geography, Faculty of Social Sciences, University of Mohaghegh Ardabili, Ardabil, Iran. Mansour Rahmati Department of Geography, Faculty of Social Sciences, University of Mohaghegh Ardabili, Ardabil, Iran. Roya Moghabeli Department of Geography, Faculty of Social Sciences, University of Mohaghegh Ardabili, Ardabil, Iran. Introduction: Hypertension is a major global public health challenge, closely linked to serious complications such as stroke and heart attack. Spatial analysis, as a modern tool in health geography, provides insights into disease distribution and its relationship with environmental and demographic factors. This study aimed to investigate the spatial distribution of hypertension patients in the Abotaleb neighborhood of Ardabil city and to offer spatially informed recommendations for improving access to healthcare services. Method: This descriptive-analytical study utilized secondary data from medical records of 600 patients diagnosed with hypertension, aged 36 to 87, between 2018 and 2022. Patients’ addresses were geocoded using Google Maps and OpenStreetMap and analyzed in ArcGIS. Analytical techniques included Kernel Density Estimation, Hot Spot Analysis, Shortest Distance to Facilities, Average Nearest Neighbor Index, Global and Local Moran’s I, Buffer Analysis, Service Area Network, and the Operational Radius Method. To reduce geolocation errors, ambiguous or incomplete records were reviewed and removed. A consistent coordinate system was maintained throughout the analysis. Results: The findings revealed that the spatial pattern of hypertension was clustered. Initially, clusters were concentrated in the central and northern parts of the neighborhood but later spread to the southern and western areas. Higher densities were linked to proximity to healthcare centers and population concentration. The disease was more prevalent among women (62.7%), with most cases occurring in the 56–65 age group. Additionally, 68% of patients had at least one comorbid condition, such as diabetes or obesity. The highest number of cases was recorded in 2021, possibly due to enhanced screening and lifestyle changes during the COVID-19 pandemic. These findings align with global reports, including those from the World Health Organization. Conclusion: This study highlights the need for optimized healthcare facility locations, targeted screening for high-risk groups, and integrated interventions in vulnerable areas. Despite limitations related to clinical data and geographic scope, the results provide a valuable foundation for localized health planning and reducing inequalities in healthcare access.  

دانشگاه علوم پزشکی کرمان Journal of Health and Biomedical Informatics 2423-3870 12 1 2025 6 1 Evaluating the Effectiveness of Virtual EMDR Therapy Platform on Reducing PTSD Symptoms 52 63 FA Mohammad Mehdi Sedaghat Pour Haghighi Ph.D. in General Psychology, Department of Psychology, Science and Arts University, Yazd, Iran Farangis Kazemi Associate Professor of exceptional children Psychology, Department of Psychology and Education of Exceptional Children, Faculty of Psychology and Educational Sciences, Allameh Tabataba'i University, Tehran, Iran Mohsen Saeidmanesh Associate Professor of Cognitive Neuroscience, Department of Psychology, Science and Arts University, Yazd, Iran Shiva Dolatabadi Assistant Professor of General Psychology, Department of Psychology and Education of Exceptional Children, Faculty of Psychology and Educational Sciences, Allameh Tabataba'i University, Tehran, Iran Farangis Demehri Assistant Professor of Psychology of exceptional children, Department of Psychology, Science and Arts University, Yazd, Iran Introduction: Post-Traumatic Stress Disorder (PTSD) has profound adverse effects on mental health. Eye Movement Desensitization and Reprocessing (EMDR) therapy has been endorsed as an effective intervention for PTSD; however, limited access to this method remains a significant challenge. Given the potential of digital therapeutic innovations to address such barriers, further research is warranted to evaluate the efficacy of online EMDR and its viability as a substitute for in-person treatment. Method: This study employed a sequential exploratory design and a quasi-experimental randomized controlled trial with pre-test, post-test, and three-month follow-up. Forty PTSD patients in Shiraz were screened using structured clinical interviews and randomly assigned to intervention and control groups. The intervention group received eight individual EMDR sessions (60–90 minutes) through a virtual EMDR platform. Data were collected via standardized questionnaires and analyzed in Python using mixed ANOVA, Bonferroni post-hoc tests, and effect size calculations. Results: The findings indicated that participants in the treatment group experienced a statistically significant reduction in PTSD symptom severity compared to the control group. Bonferroni post hoc tests confirmed that the difference between pretest and posttest scores in the treatment group was statistically significant, while no significant difference was observed between posttest and three-month follow-up scores—suggesting the stability of therapeutic outcomes. Moreover, participants in the treatment group reported high levels of satisfaction regarding the quality and usability of the virtual platform. Conclusion: The EMDR-based virtual therapy platform developed in this study demonstrated high efficacy in the treatment of PTSD and offers a promising, innovative alternative to conventional face-to-face therapy. This approach also presents advantages such as cost reduction, enhanced accessibility, and improved therapeutic experience. The results align with similar international findings. Furthermore, theoretical models such as the Adaptive Information Processing (AIP) model and Cognitive Load Theory offer explanatory frameworks for the effectiveness of digital EMDR interventions. Future studies are encouraged to explore the long-term effects of this intervention and its application to other psychological disorders.

دانشگاه علوم پزشکی کرمان Journal of Health and Biomedical Informatics 2423-3870 12 1 2025 6 1 Diagnosis and Analysis of Brain Tumors in Medical Images Using a Feedforward Neural Network Optimized with Quantum-Inspired Algorithms 64 78 FA Mostafa Kashani Ph.D. in Computer Software, Assistant Professor, Department of Health Information Technology, Sirjan School of Medical Sciences, Sirjan, Iran Shayan Rahman Setayesh Bachelor’s Student in Computer Engineering, Shahid Bahonar University of Kerman, Kerman, Iran Seddigheh Barzekar Subspecialist in Endocrinology and Metabolism, Assistant Professor, Department of Medicine, Sirjan School of Medical Sciences, Sirjan, Iran Introduction: Rapid and accurate diagnosis of brain tumors significantly improves treatment planning and survival rates. However, the manual review of multi‑modal magnetic resonance images is often slow and prone to errors due to lesion heterogeneity, similarity to healthy tissue, and large data volumes. This study presents an automated framework that incorporates a lightweight feed‑forward neural network with an intrinsic attention mechanism and quantum‑behaved particle swarm optimization (QPSO). The aim of this study is to improve the speed and accuracy of tumor identification while maintaining interpretability in clinical environments with limited resources. Method: Multimodal MRI images (T1, T1ce, T2, and FLAIR) were sourced from reputable databases, including the Brain Tumor Segmentation Challenge (BraTS) and The Cancer Imaging Archive (TCIA). The images underwent preprocessing, which included intensity normalization (Z-score), noise reduction using Gaussian and median filters, and correction of intensity inhomogeneity. Statistical, textural, and frequency-based features were extracted and reduced to 300 principal components using Principal Component Analysis (PCA). Feature weighting was performed using a document relevance-inspired method. The proposed model, a five-layer feedforward neural network (FNN) with a ReLU activation function and an internal attention mechanism, was optimized using QPSO. Heatmaps were generated to enhance result interpretability. Results: The proposed model achieved an accuracy of 99.6 %, sensitivity of 99.4 %, and specificity of 99.7 %, outperforming reference convolutional networks (97.1 %) and U‑Net architectures (96.2 %). The mean prediction time per image was less than 0.5 seconds, facilitating real‑time clinical use. Heatmaps produced by the attention layer, effectively highlighted abnormal regions and enhanced interpretability. These metrics were consistently replicated across multiple random splits, and qualitative evaluations by imaging specialists confirmed the absence of specificity loss and the clinical relevance of the findings. Conclusion: A feedforward network equipped with intrinsic attention and optimized with QPSO demonstrated near‑perfect accuracy and sub‑second inference for brain tumor diagnosis on multi‑modal MRI. Its high performance on standard GPUs, combined with the generation of intuitive heatmaps, positions this framework as a practical decision‑support tool, particularly in centers lacking advanced infrastructure. Future evaluations will focus on multi‑center data and deployment on edge devices to strengthen clinical adoption and regulatory compliance.

دانشگاه علوم پزشکی کرمان Journal of Health and Biomedical Informatics 2423-3870 12 1 2025 6 1 Examining the Usability of The SIPAD System Using an Exploratory Evaluation Method 79 90 FA Marziyhe Meraji Associate Professor of Health Information Management, Department of Health Information Technology, School of Paramedical and Rehabilitation Sciences, Mashhad University of Medical Sciences, Mashhad, Iran Sahar Shariatnia MSc in Biostatistics, Natural Products and Medicinal Plants Research Center, North Khorasan University of Medical Sciences, Bojnurd, Iran Fatemeh Ameri MSc Student of Health Information Technology, Department of Health Information Technology, School of Paramedical and Rehabilitation Sciences, Mashhad University of Medical Sciences, Mashhad, Iran Introduction: The SIPAD system is used by a diverse range of users, including students, professors, administrators, and university staff. Therefore, it requires continuous evaluation to prevent possible errors and identify problems in the system, plan for resolving them, and ultimately provide better quality services. Thus, this study was conducted to evaluate the usability of the SIPAD system, aiming to identify and resolve problems within it. Method: This descriptive cross-sectional study was conducted in 2024 to evaluate the usability of the SIPAD system at Mashhad University of Medical Sciences using an exploratory evaluation method. The evaluators independently examined different parts of the SIPAD system (from the perspective of students, professors, and the education unit) using the Pierotti checklist for compliance with the Nielsen usability principles. For each type under study, evaluators were asked to rate the severity of the problem related to the item from 0 to 4 if they selected the “No” option (including non-compliance with the desired item in the SIPAD system). Results: Sixteen evaluators participated in the study. 56.25 % of the evaluators were master's and Ph.D. students, 37.5 % were faculty members in health information management, medical informatics, and artificial intelligence, and 6.25 % were experts in the education unit. The majority of problems identified were related to the principles of website flexibility and efficiency (1.35), guidance and documentation (1.28), and the fewest problems accounted for aesthetic aspects and simple design (0.08). The average severity of the identified problems showed that the SIPAD system has minor problems in some Nielsen's usability principles. Conclusion: This study identified shortcomings in user experience design by evaluating the SIPAD system. The findings show that despite proper technical performance, the neglect of user-centered principles has reduced productivity and satisfaction. The main problems include incomprehensible symbols, a lack of return capabilities, and failure to address the real needs of users. The proposed solutions are low-cost, operational, and have the potential to significantly improve the user experience. Continuous improvement through periodic evaluations and attention to user feedback is essential for the system to remain dynamic.

دانشگاه علوم پزشکی کرمان Journal of Health and Biomedical Informatics 2423-3870 12 1 2025 6 1 Role of Recommender Systems in Optimizing Healthcare and Personalizing Treatment 91 95 FA Amir Hossein Nabizadeh Medical Informatics Research Center, Institute for Futures Studies in Health, Kerman University of Medical Sciences, Kerman, Iran / INESC-ID, Lisbon, Portugal The article is a letter to the editor, so it does not have an abstract.

دانشگاه علوم پزشکی کرمان Journal of Health and Biomedical Informatics 2423-3870 12 1 2025 6 1 The two Sides of the Artificial Intelligence Coin in Medical Sciences: a Look at the Human and Ethical Dimensions 96 104 FA Sara Shafian Department of Medical Education, School of medicine, Kerman University of Medical Sciences, Kerman, Iran Erfan Monemi Student Research Committee, School of Medicine, Kerman University of Medical Sciences, Kerman, Iran Introduction: Artificial Intelligence (AI) has transformative potential in medical sciences, promising increased accuracy in diagnosis, disease progression prediction, and personalized treatments. However, the growing emphasis on technical aspects has raised significant human and ethical challenges related to doctor-patient communication, privacy, accountability, and trust. This study aims to examine these two contrasting aspects—opportunities and challenges—while emphasizing the necessity of integrating artificial intelligence with human values in medicine. Method: This research was conducted as a narrative review by searching scientific databases, including PubMed, Scopus, and Web of Science, using relevant keywords. Articles published between 2014 and 2024 that examined the human, communicative, and ethical aspects of AI applications in medicine were collected and analyzed through qualitative content analysis. Results: The findings revealed that while AI automates repetitive tasks and analyzes vast amounts of data, allowing physicians to focus more on patient care, significant challenges were identified in several areas: deficiencies in establishing empathetic and nonverbal communication, concerns regarding data privacy and security, ambiguity in legal and ethical accountability in the event of errors, and the risk of algorithmic bias, which could lead to inequalities in healthcare delivery. Conclusion: The successful implementation of AI in medicine requires moving beyond a purely technical perspective and adopting a human-centered approach. AI should function as an assistive tool for physicians rather than replace their human judgment and communication. To ensure the future of this collaboration, it is essential to develop transparent ethical frameworks, train healthcare professionals, and design efficient systems that uphold human values.