Browsing by Author "Alkhnbashi, Omer S"

Now showing 1 - 8 of 8

An Integrated Multimodal-Based CAD System for Breast Cancer Diagnosis.
(2024-11-05) Alkhnbashi, Omer S
Simple Summary: Diagnosis of breast cancer goes through multiple processes. Recently, a variety of system-aided diagnosis (CAD) systems have been proposed as Primary systems for initial diagnosis based on mammogram screenings. This paper enhances the diagnosis accuracy by using mammograms of both sides of the patient’s breasts instead of the infected side only. In addition, the paper boosts CAD accuracy by adding patient information and medical history along with mammogram images’ features. The proposed multimodal approach will serve as the nucleus for future work at both data and system levels to diagnose breast cancer and other diseases caused by various factors. Abstract: Breast cancer has been one of the main causes of death among women recently, and it has been the focus of attention of many specialists and researchers in the health field. Because of its seriousness and spread speed, breast cancer-resisting methods, early diagnosis, diagnosis, and treatment have been the points of research discussion. Many computers-aided diagnosis (CAD) systems have been proposed to reduce the load on physicians and increase the accuracy of breast tumor diagnosis. To the best of our knowledge, combining patient information, including medical history, breast density, age, and other factors, with mammogram features from both breasts in craniocaudal (CC) and mediolateral oblique (MLO) views has not been previously investigated for breast tumor classification. In this paper, we investigated the effectiveness of using those inputs by comparing two combination approaches. The soft voting approach, produced from statistical information-based models (decision tree, random forest, K-nearest neighbor, Gaussian naive Bayes, gradient boosting, and MLP) and an image-based model (CNN), achieved 90% accuracy. Additionally, concatenating statistical and image-based features in a deep learning model achieved 93% accuracy. We found that it produced promising results that would enhance the CAD systems. As a result, this study finds that using both sides of mammograms outperformed the result of using only the infected side. In addition, integrating the mammogram features with statistical information enhanced the accuracy of the tumor classification. Our findings, based on a novel dataset, incorporate both patient information and four-view mammogram images, covering multiple classes: normal, benign, and malignant.
Analysis of tracrRNAs reveals subgroup V2 of type V-K CAST systems
(2025) Alkhnbashi, Omer S
Clustered regularly interspaced palindromic repeats (CRISPR)-associated transposons (CAST) consist of an integration between certain class 1 or class 2 CRISPR-Cas systems and Tn7-like transposons. Class 2 type V-K CAST systems are restricted to cyanobacteria. Here, we identified a unique subgroup of type V-K systems through phylogenetic analysis, classified as V-K_V2. Subgroup V-K_V2 CAST systems are characterized by an alternative tracrRNA, the exclusive use of Arc_2-type transcriptional regulators, and distinct differences in the length of protein domains in TnsB and TnsC. Although the occurrence of V-K_V2 CAST systems is restricted to Nostocales cyanobacteria, it shows signs of horizontal gene transfer, indicating its capability for genetic mobility. The predicted V-K_V2 tracrRNA secondary structure has been integrated into an updated version of the CRISPRtracrRNA program available on GitHub under https://github.com/BackofenLab/CRISPRtracrRNA/releases/tag/2.0.
Aspect-Based Sentiment Analysis of Patient Feedback Using Large Language Models
(MDPI AG, 2024-11-21) Alkhnbashi, Omer S
Online medical forums have emerged as vital platforms for patients to share their experiences and seek advice, providing a valuable, cost-effective source of feedback for medical service management. This feedback not only measures patient satisfaction and improves health service quality but also offers crucial insights into the effectiveness of medical treatments, pain management strategies, and alternative therapies. This study systematically identifies and categorizes key aspects of patient experiences, emphasizing both positive and negative sentiments expressed in their narratives. We collected a dataset of approximately 15,000 entries from various sections of the widely used medical forum, patient.info. Our innovative approach integrates content analysis with aspect-based sentiment analysis, deep learning techniques, and a large language model (LLM) to analyze these data. Our methodology is designed to uncover a wide range of aspect types reflected in patient feedback. The analysis revealed seven distinct aspect types prevalent in the feedback, demonstrating that deep learning models can effectively predict these aspect types and their corresponding sentiment values. Notably, the LLM with few-shot learning outperformed other models. Our findings enhance the understanding of patient experiences in online forums and underscore the utility of advanced analytical techniques in extracting meaningful insights from unstructured patient feedback, offering valuable implications for healthcare providers and medical service management.
Disparate mechanisms counteract extraneous CRISPR RNA production in type II-C CRISPR-Cas systems
(Oxford University Press (OUP), 2025) Alkhnbashi, Omer S
CRISPR-Cas adaptive immune systems in bacteria and archaea enable precise targeting and elimination of invading genetic elements. An inherent feature of these systems is the 'extraneous' CRISPR RNA (ecrRNA), which is produced via the extra repeat in a CRISPR array lacking a corresponding spacer. As ecrRNAs would interact with the Cas machinery yet not direct acquired immunity, they pose a potential barrier to defence. Type II-A CRISPR-Cas systems resolve this barrier through the leader sequence upstream of a CRISPR array, which forms a hairpin structure with the extra repeat that inhibits ecrRNA production. However, the fate of ecrRNAs in other CRISPR types and subtypes remains to be explored. Here, we report that II-C systems likely employ disparate strategies to resolve the ecrRNA due to their distinct configuration in comparison to II-A. Applying bioinformatics analyses to over 650 II-C systems followed by experimental validation, we identified three strategies applicable to these systems: formation of an upstream Rho-independent terminator, formation of a hairpin that sequesters the ecrRNA guide, and mutations in the repeat expected to disrupt ecrRNA formation. These findings expand the list of mechanisms in CRISPR-Cas systems that could resolve the ecrRNA to optimize immune response.
Education in Transition: Adapting and Thriving in a Post-COVID World
(MDPI AG, 2024-09-28) Alkhnbashi, Omer S
The COVID-19 pandemic profoundly disrupted traditional education systems worldwide, prompting a rapid shift to online platforms and the emergence of innovative teaching strategies. This paper critically reviews the extensive body of research on post-COVID-19 education, focusing on the practical and feasible solutions proposed to maintain and enhance educational continuity. The review categorizes and examines studies on various approaches, including simulation-based training, project-based learning, and hybrid models, highlighting their effectiveness during and after the pandemic. Special attention is given to the role of information technology, the challenges faced by educators and students, and the importance of mental health support in the new educational landscape. The findings suggest that while digital tools such as virtual reality and 3D environments show promise, their implementation remains limited, particularly in resource-constrained settings. The study also identifies a significant gap in empirical research on these innovations in the post pandemic era. Furthermore, the paper highlights the need for systemic changes in curriculum design, educator training, and policy development to address the long-term impacts of the pandemic on education. This review provides a comprehensive overview of the lessons learned from the COVID-19 pandemic, offering insights into how educational institutions can better prepare for future crises.
Genomics of rare diseases in the Greater Middle East.
(2025-02-03) Chekroun, Ikram; Almarri, Mohamed A; Uddin, Mohammed; Alkhnbashi, Omer S; Ali, Fahad R; Alsheikh-Ali, Alawi; Abou Tayoun, Ahmad N
The Greater Middle East (GME) represents a concentrated region of unparalleled genetic diversity, characterized by an abundance of distinct alleles, founder mutations and extensive autozygosity driven by high consanguinity rates. These genetic hallmarks present a unique, yet vastly untapped resource for genomic research on Mendelian diseases. Despite this immense potential, the GME continues to face substantial challenges in comprehensive data collection and analysis. This Perspective highlights the region's unique position as a natural laboratory for genetic discovery and explores the challenges that have stifled progress thus far. Importantly, we propose strategic solutions, advocating for an all-inclusive research approach. With targeted investment and focused efforts, the latent genetic wealth in the GME can be transformed into a global hub for genomic research that will redefine and advance our understanding of the human genome.
Optimizing Large Language Models for Arabic Healthcare Communication: A Focus on Patient-Centered NLP Applications
(2024) Alkhnbashi, Omer S
Recent studies have highlighted the growing integration of Natural Language Processing (NLP) techniques and Large Language Models (LLMs) in healthcare. These technologies have shown promising outcomes across various healthcare tasks, especially in widely studied languages like English and Chinese. While NLP methods have been extensively researched, LLM applications in healthcare represent a developing area with significant potential. However, the successful implementation of LLMs in healthcare requires careful review and guidance from human experts to ensure accuracy and reliability. Despite their emerging value, research on NLP and LLM applications for Arabic remains limited particularly when compared to other languages. This gap is largely due to challenges like the lack of suitable training datasets, the diversity of Arabic dialects, and the language’s structural complexity. In this study, a panel of medical experts evaluated responses generated by LLMs, including ChatGPT, for Arabic healthcare inquiries, rating their accuracy between 85% and 90%. After fine tuning ChatGPT with data from the Altibbi platform, accuracy improved to a range of 87% to 92%. This study demonstrates the potential of LLMs in addressing Arabic healthcare queries especially in interpreting questions across dialects. It highlights the value of LLMs in enhancing healthcare communication within the Arabic-speaking world and points to a promising area for further research. This work establishes a foundation for optimizing NLP and LLM technologies to achieve greater linguistic and cultural adaptability in global healthcare settings.
SpacerPlacer: ancestral reconstruction of CRISPR arrays reveals the evolutionary dynamics of spacer deletions
(2024-10-14) Alkhnbashi, Omer S
Bacteria employ CRISPR-Cas systems for defense by integrating invader-derived sequences, termed spacers, into the CRISPR array, which constitutes an immunity memory. While spacer deletions occur randomly across the array, newly acquired spacers are predominantly integrated at the leader end. Consequently, spacer arrays can be used to derive the chronology of spacer insertions. Reconstruction of ancestral spacer acquisitions and deletions could help unravel the coevolution of phages and bacteria, the evolutionary dynamics in microbiomes, or track pathogens. However, standard reconstruction methods produce misleading results by overlooking insertion order and joint deletions of spacers. Here, we present SpacerPlacer, a maximum likelihood-based ancestral reconstruction approach for CRISPR array evolution. We used SpacerPlacer to reconstruct and investigate ancestral deletion events of 4565 CRISPR arrays, revealing that spacer deletions occur 374 times more frequently than mutations and are regularly deleted jointly, with an average of 2.7 spacers. Surprisingly, we observed a decrease in the spacer deletion frequency towards both ends of the reconstructed arrays. While the resulting trailer-end conservation is commonly observed, a reduced deletion frequency is now also detectable towards the variable leader end. Finally, our results point to the hypothesis that frequent loss of recently acquired spacers may provide a selective advantage.