Hamid Moghaddasi

Background and Aims: Colorectal cancer is one of the most common causes of cancer mortality and the third most common cancer in the world. Systematic studies in Iran have also shown that this cancer has a growing trend in incidence rates for both genders. Given the role of information management and registries in tracking patients and improving the quality of treatment for this disease, the purpose of this study is to design an object‐oriented conceptual model for a hospital‐based colorectal cancer registry. Methods: This applied‐descriptive study was conducted in two phases, including conceptual model design and model validation. In the first phase, an expert panel was formed to identify the necessary data sets and requirements for a conceptual model of a hospital colorectal cancer registry, based on a review of similar studies and monitoring of the cancer registration process at a hospital. The conceptual model development process was carried out by adopting a modeling approach in three parts, including the design of an operational model, a structural model, and a behavioral model using Microsoft Visio software. In the second phase, the conceptual model was validated through a researcher‐made questionnaire of 55 questions based on a three‐choice Likert scale by 20 experts. Results: In the first stage, 42 core data sets in five categories (demographic information, diagnostic information, treatment information, clinical status assessment, and clinical trials), six registry processes (including case finding, data collection, summarization, quality control, reporting, and follow‐up), and 22 functional requirements and 6 non‐functional requirements were designed. This model was developed in three operational, structural, and behavioral dimensions by drawing requirement diagrams and then validated in two stages using the Delphi technique with the participation of 20 experts. The presented model was approved with an average agreement of over 99% and a final consensus of the experts. Conclusion: The proposed model will facilitate the design and implementation of a single registry within a medical or research institution to record patient information and track follow‐ups. Implementing this system will result in significant improvements compared to semi‐electronic or traditional paper registries and can have far greater capabilities and enhanced performance.

Introduction: Gastric cancer is one of the leading causes of cancer-related mortality worldwide, making early detection and prevention essential. Existing mobile health applications in this field are predominantly treatment-oriented and focused on post-diagnostic stages, leaving a significant gap in primary prevention coverage and identification of precursor conditions. The aim of this study is the systematic identification of data requirements related to precursor conditions of gastric cancer through review of clinical guidelines and evidence-based studies, in order to provide a conceptual framework for designing an informative, directive, and preventive mobile health application based on a rule-based (non-AI) approach. Method: This study is a systematic review conducted in accordance with the PRISMA 2020 protocol. A comprehensive search was performed across PubMed, Google Scholar, Scopus, Web of Science, and UpToDate databases from January 2005 to March 2024. Inclusion criteria encompassed authoritative clinical guidelines, consensus studies, and research articles related to diagnosis, screening, or precursor conditions of gastric cancer. Source quality was assessed using the Mixed Method Appraisal Tool. Finally, 24 sources (19 primary sources including 14 clinical guidelines, 1 consensus study, and 4 research articles; plus 5 UpToDate sources as supplementary evidence) were included in the analysis. Findings: From the systematic analysis of 19 primary sources, three main categories of precursor conditions for gastric cancer were identified: (a) baseline risk factors (family history, hereditary syndromes, previous gastric surgery), (b) diagnosed medical conditions ( Helicobacter pylori infection, gastritis, gastric ulcer, iron-deficiency anemia, Epstein-Barr virus), and (c) functional symptoms of the upper gastrointestinal tract (dyspepsia, gastroesophageal reflux, and related symptoms). This classification forms the basis of a four-level risk assessment framework that translates precursor conditions into understandable questions for general users. Conclusion: This study presents the first comprehensive evidence-based framework for data requirements of a preventive mobile health application for gastric cancer. The proposed framework, with its focus on primary prevention and deterministic decision-making engine, offers the potential to create a conceptual infrastructure for early interventions and public health literacy enhancement. Major limitations include the conceptual nature of the design and lack of field validation. Future studies should focus on practical implementation, clinical effectiveness evaluation, user acceptance, and integration with health systems to realize the potential for reducing the burden of gastric cancer, particularly in high-prevalence regions.

BACKGROUND Despite the high potential of artificial intelligence (AI) in diagnosing Alzheimer's disease, a profound gap exists between reported accuracy in ideal conditions and models' reliable performance in real-world clinical settings. OBJECTIVE This systematic analysis aimed to identify the root causes of this gap and propose practical solutions. METHODS We conducted a systematic analysis in accordance with PRISMA 2020, analyzing 56 studies (2013-2023). A qualitative content analysis was performed around four pillars: 1) Data repository characteristics, 2) Data preprocessing and model design, 3) Technical implementation frameworks, and 4) Performance evaluation protocols. RESULTS Results indicate a methodological transition towards standardized data repositories and modern AI frameworks. However, rapid algorithm development has outpaced the maturity required for clinical generalizability. Four key deficits were identified: 1. Data limitations due to reliance on restricted, low-diversity datasets (63% of studies used ADNI exclusively). 2. Insufficient standardization in preprocessing and modeling, prioritizing 'convenience' over 'generalizability'. 3. A disconnect between technical capabilities and critical clinical needs (only 7% focused on the crucial sMCI/pMCI distinction). 4. Deficiencies in evaluation protocols, notably scarce multi-center validation (only 7%) and inadequate reporting of comprehensive metrics (96% relied solely on Accuracy). Practical solutions to address these deficits across data, modeling, and evaluation domains are prop osed. CONCLUSIONS Transitioning from 'accuracy under ideal conditions' to 'reliability in real-world settings' is an unavoidable necessity. This requires investment in multi-center data repositories, alignment of models with clinical needs, and institutionalizing comprehensive evaluations. The findings and recommendations are generalizable to other domains of AI-based disease diagnosis.

Objective(s): Promoting the digitalization of healthcare is one of the key goals of the 21st century for the World Health Organization. Electronic prescribing is the computer-based electronic production, transmission, and filling of prescriptions that replaces paper and fax prescriptions. Methods: The was a quantitative study. Two descriptive and inferential statistical methods ...

Postoperative self-care is a critical determinant of treatment outcomes in ophthalmic patients. Recent advances in mobile health (mHealth) and the widespread adoption of smartphones have created new opportunities to enhance disease management and promote self-care. This study aimed to design and evaluate a mobile health application to support self-care among patients following glaucoma surgery, cataract extraction, and corneal transplantation. To determine the functional requirements of the mobile health application, a comprehensive literature review was conducted alongside a needs assessment involving patients who had undergone glaucoma surgery, cataract extraction, or corneal transplantation. Based on object-oriented analysis and design, a system blueprint was developed, and the application was implemented using the Java programming language. The usability and user satisfaction of the application were evaluated through a researcher-developed checklist, administered to both ophthalmic patients and ophthalmologists. The evaluation results indicated a high level of user satisfaction regarding the user interface, services, overall functionality, and usability of the application. Based on the predefined scoring scale, the application received an overall score of 24.82, placing it within the “acceptable” category. The findings suggest that this mobile health application can effectively support education and enhance postoperative self-care among patients undergoing glaucoma, cataract, and corneal transplant surgeries. Overall, the “INOOR” application, with its integrated features, demonstrates considerable potential to improve self-care practices and reduce the workload of healthcare providers.

To synthesize evidence on deep learning applications for diagnosing central serous chorioretinopathy (CSCR), a macular disorder associated with vision loss, this systematic review categorized studies by diagnostic task and imaging modality. The study evaluates advances in deep learning performance, clinical integration potential, dataset limitations, and the contributions of multimodal imaging and Explainable AI (XAI) to diagnostic accuracy and clinical decision-making. We conducted a PRISMA-compliant systematic review of PubMed, Scopus, and IEEE Xplore, including peer-reviewed English-language studies published from January 1990 to February 2024 that reported quantitative deep learning metrics for CSCR diagnosis. A two-stage selection process was applied (Cohen’s κ = 0.84), resulting in 96 studies for analysis. Risk of bias was evaluated using the QUADAS-2 tool, and data were synthesized by imaging modality, model architecture, and diagnostic task. Deep learning models demonstrate exceptional performance in CSCR diagnosis. DenseNet architectures applied to optical coherence tomography (OCT) images achieved peak Metrics, including 99.78% accuracy, 99.68% sensitivity, and 100% specificity. Segmentation models for subretinal fluid (SRF) reported Dice scores of up to 0.965, while multimodal models for differential diagnosis achieved an area under the curve (AUC) of 0.999. Despite these advances, clinical adoption remains limited by several challenges: scarce and imbalanced datasets (e.g., SRF/non-SRF ratio of 1:8), lack of open-access datasets and models, risks of overfitting, and insufficient external validation. Emerging approaches, such as few-shot learning and diffusion models, are promising for mitigating data constraints; however, improvements in dataset quality and the implementation of rigorous cross-institutional validation are essential for real-world deployment. By leveraging OCT and multimodal imaging data, deep learning has the potential to transform CSCR diagnosis through enhanced accuracy and automation. However, translating these advances into routine clinical practice necessitates overcoming key challenges, including limited and heterogeneous datasets and models with restricted generalizability. Future research should prioritize standardized reporting frameworks, transparent model interpretability through XAI, and rigorous large-scale validation. Essential strategies include employing federated learning to leverage distributed data, implementing effective multimodal fusion techniques, and fostering collaborative frameworks to improve diagnostic accuracy, ensure algorithmic fairness, and enable real-world clinical applicability.

Human aspirations have consistently centered on reducing mental burdens, prolonging life, and mastering destiny, with science and technology serving as primary tools toward these goals. Artificial intelligence (AI), particularly through machine learning, offers powerful means of transforming data into knowledge and addressing complex biological challenges. At the same time, the human microbiome has emerged as a crucial determinant of health, longevity, and disease resistance. The microbiome, comprising over 38 trillion microorganisms–including bacteria, fungi, protozoa, and viruses–interacts dynamically with the human body. Its collective genetic material exceeds that of the human genome by hundreds of times, positioning it as an equally influential factor in shaping individual destiny. Unlike DNA, the microbiome is highly adaptable and can be reshaped in relatively short periods through diet, lifestyle, or medication. This adaptability creates opportunities for preventive and personalized medical interventions. To illustrate its importance, the microbiome can be conceptualized as the body’s “microbial pets.” These companions coexist as dining partners and life-long residents whose well-being directly influences human vitality. Like pets, they require proper care–particularly fiber-rich nutrition–and neglect can result in harmful consequences. This metaphor highlights the need to view microbial ecosystems not as passive inhabitants but as active partners in human health. By combining microbiome research with AI, it becomes possible to map these “microbial pets” with precision, uncover hidden interactions, and identify early indicators of disease. Such integration points toward a future where preventive, predictive, and personalized medicine fundamentally reshape human health and extend life expectancy.

Image Analysis as tool for Predicting Colorectal Cancer Molecular Alterations: A Scoping Review - Molecular Imaging and Radionuclide Therapy

Background: Providing appropriate specialized treatment to the right patient at the right time is considered necessary in cancer management. Targeted therapy tailored to the genetic changes of each breast cancer patient is a desirable feature of precision oncology, which can not only reduce disease progression but also potentially increase patient survival. The use of artificial intelligence alongside precision oncology can help physicians by identifying and selecting more effective treatment factors for patients. Method: A systematic review was conducted using the PubMed, Embase, Scopus, and Web of Science databases in September 2023. We performed the search strategy with keywords, namely: Breast Cancer, Artificial intelligence, and precision Oncology along with their synonyms in the article titles. Descriptive, qualitative, review, and non-English studies were excluded. The quality assessment of the articles and evaluation of bias were determined based on the SJR journal and JBI indices, as well as the PRISMA2020 guideline. Results: Forty-six studies were selected that focused on personalized breast cancer management using artificial intelligence models. Seventeen studies using various deep learning methods achieved a satisfactory outcome in predicting treatment response and prognosis, contributing to personalized breast cancer management. Two studies utilizing neural networks and clustering provided acceptable indicators for predicting patient survival and categorizing breast tumors. One study employed transfer learning to predict treatment response. Twenty-six studies utilizing machine-learning methods demonstrated that these techniques can improve breast cancer classification, screening, diagnosis, and prognosis. The most frequent modeling techniques used were NB, SVM, RF, XGBoost, and Reinforcement Learning. The average area under the curve (AUC) for the models was 0.91. Moreover, the average values for accuracy, sensitivity, specificity, and precision were reported to be in the range of 90-96% for the models. Conclusion: Artificial intelligence has proven to be effective in assisting physicians and researchers in managing breast cancer treatment by uncovering hidden patterns in complex omics and genetic data. Intelligent processing of omics data through protein and gene pattern classification and the utilization of deep neural patterns has the potential to significantly transform the field of complex disease management.