Search

The rapid digitalization of healthcare has created a pressing need for solutions that manage clinical data securely while ensuring patient privacy. This study evaluates the capabilities of GPT-3.5 and GPT-4 models in de-identifying clinical notes and generating synthetic data, using API access and zero-shot prompt engineering to optimize computational efficiency. Results show that GPT-4 significantly outperformed GPT-3.5, achieving a precision of 0.9925, a recall of 0.8318, an F1 score of 0.8973, and an accuracy of 0.9911. These results demonstrate GPT-4’s potential as a powerful tool for safeguarding patient privacy while increasing the availability of clinical data for research. This work sets a benchmark for balancing data utility and privacy in healthcare data management. [ABSTRACT FROM AUTHOR]

Non-small cell lung cancer (NSCLC) is a leading cause of death worldwide. Targeted monotherapies produce high regression rates, albeit for limited patient subgroups, who inevitably succumb. We present a novel strategy for identifying customized combinations of triplets of targeted agents, utilizing a simplified interventional mapping system (SIMS) that merges knowledge about existent drugs and their impact on the hallmarks of cancer. Based on interrogation of matched lung tumor and normal tissue using targeted genomic sequencing, copy number variation, transcriptomics, and miRNA expression, the activation status of 24 interventional nodes was elucidated. An algorithm was developed to create a scoring system that enables ranking of the activated interventional nodes for each patient. Based on the trends of co-activation at interventional points, combinations of drug triplets were defined in order to overcome resistance. This methodology will inform a prospective trial to be conducted by the WIN consortium, aiming to significantly impact survival in metastatic NSCLC and other malignancies.

Simple Summary: In the face of significant hurdles stemming from conflicts and resource constraints, Jordan has emerged as an exemplary paradigm, solidifying cancer care both locally and regionally. Despite the positive progress being made, a significant obstacle is emerging in the form of increasing rates of cancer, which is representative of a larger upsurge in non-communicable diseases. However, a thorough grasp of the various contributing factors is still lacking. Therefore, we aimed to carefully examine and discuss the current identified barriers that are hindering the achievement of optimal cancer care in Jordan. This narrative review explores the multifaceted barriers hindering access to quality cancer care in Jordan. A literature-based narrative review was undertaken to explore the current identified barriers to cancer care in Jordan. Four databases were searched using relevant keywords to identify key insights on barriers and proposed solutions. Key challenges and potential solutions were identified based on evidence from studies, reports, and initiatives. Medical services and infrastructure exhibit centralized disparities, impacting rural and underserved areas. Human resources shortages, geopolitical instability, and quality management issues pose significant challenges. Public awareness campaigns face hurdles in addressing the tobacco epidemic and late-stage diagnosis. Socioeconomic disparities, particularly in health insurance and urban–rural divides, further compound barriers. Refugees encounter distinct challenges, including late-stage diagnosis, financial barriers, and psychological distress. Despite multiple challenges, Jordan presents a model for regional development and health equity. This study not only contributes to improving cancer care in Jordan but also offers a roadmap for policymakers, healthcare practitioners, and researchers in similar contexts globally. Government initiatives, financial aspects, and proposed policy measures are examined as potential solutions. Recommendations include coordinated prevention strategies, enhanced screening uptake, training programs, the equitable distribution of facilities, and policy directives aligned with global commitments. The role of digital technologies, telemedicine, and community engagement models is emphasized. [ABSTRACT FROM AUTHOR]

Cancer is a major contributing cause of morbidity and mortality in the Eastern Mediterranean region. The aim of the current study was to estimate the cancer burden attributable to major lifestyle and environmental risk factors. We used age‐, sex‐ and site‐specific incidence estimates for 2012 from IARC's GLOBOCAN, and assessed the following risk factors: smoking, alcohol, high body mass index, insufficient physical activity, diet, suboptimal breastfeeding, infections and air pollution. The prevalence of exposure to these risk factors came from different sources including peer‐reviewed international literature, the World Health Organization, noncommunicable disease Risk Factor Collaboration, and the Food and Agriculture Organization. Sex‐specific population‐attributable fraction was estimated in the 22 countries of the Eastern Mediterranean region based on the prevalence of the selected risk factors and the relative risks obtained from meta‐analyses. We estimated that approximately 33% (or 165,000 cases) of all new cancer cases in adults aged 30 years and older in 2012 were attributable to all selected risk factors combined. Infections and smoking accounted for more than half of the total attributable cases among men, while insufficient physical activity and exposure to infections accounted for more than two‐thirds of the total attributable cases among women. A reduction in exposure to major lifestyle and environmental risk factors could prevent a substantial number of cancer cases in the Eastern Mediterranean. Population‐based programs preventing infections and smoking (particularly among men) and promoting physical activity (particularly among women) in the population are needed to effectively decrease the regional cancer burden. What's new? How many cancers could be prevented by lifestyle changes? These authors set out to quantify the fraction of the cancer burden attributable to 8 major lifestyle factors in the Eastern Mediterranean region, which includes 22 countries. The risk factors they analyzed included smoking, alcohol, infections, and high BMI. Fully one third of new cancer cases among adults, they found, could be prevented by reducing exposure to risk factors. They conclude that public health programs to promote physical activity, reduce smoking, and prevent infections, would significantly reduce cancer mortality in this region. [ABSTRACT FROM AUTHOR]

The Syrian crisis, which started in 2011, has had a profound impact on the entire region. Jordan, with its limited resources, now has the second highest ratio of refugees to inhabitants in the world (89 to 1,000). The actual number of Syrians in Jordan is hotly contested: more than 630,776 refugees registered in November 2015 compared with 1,265,514 reported by the national census conducted at the same time. Although the numbers are slowly but steadily increasing, the number of patients with cancer who were registered by the Jordan Cancer Registry peaked in 2013 at 510 patients reported and subsequently slumped downward, which coincided with changes in funding as a result of the increasing strains on the Ministry of Health. Older individuals, women, and patients with advanced diseases were less likely to be registered. These findings overlap with data obtained from the authors' own center registry. Using age- and sex-specific population-based incidence rates, we estimated that 869 Syrians are diagnosed with cancer in Jordan annually. Using diagnosis-specific cost records of the King Hussein Cancer Foundation, we estimated that the cost of their treatments is 15.6 million Jordan dinars (US$22.1 million). [ABSTRACT FROM AUTHOR]

Purpose: Epidemiologic data from several populations suggest that metformin may decrease cancer risk and mortality in patients with colorectal cancer (CRC) and type II diabetes mellitus (DM). Although type II DM and CRC are major health problems in the Middle East, no investigations have been performed to test the effect metformin has on the outcome of patients with type II DM and CRC who are also treated with metformin. Materials and Methods: We retrospectively reviewed the medical records of 1,902 patients diagnosed with CRC at King Hussein Cancer Center between January 2004 and December 2012, and identified 349 patients (18%) with type II DM; we censored the data of 28 patients because their antidiabetic medications were unknown. We then categorized these 321 patients into two groups: 192 patients treated with metformin (group A) and 129 patients treated with other antidiabetic medications (group B). Results: Group A patients had significantly longer overall survival (89 months; 95% CI, 66 to 112 months) and progression-free survival (47 months; 95% CI, 15 to 79 months) than group B patients (overall survival: 36 months; 95% CI, 24 to 48 months; P ≤.001; progression-free survival: 21 months; 95% CI, 13 to 29 months; P =.016). After adjustment for age, sex, body mass index, aspirin use, anticholesterol treatment, and CRC stage, group A patients had a 40% reduction in mortality (hazard ratio, 0.58; 95% CI, 0.4% to 0.85%; P =.005). Conclusion: Our results support findings from other populations that patients with diabetes and CRC who are also treated with metformin have better outcomes than those treated with other antidiabetic medications. [ABSTRACT FROM AUTHOR]

Recent advancements in large language models (LLMs), particularly GPT-3.5 and GPT-4, have sparked significant interest in their application within the medical field. This research offers a detailed comparative analysis of the abilities of GPT-3.5 and GPT-4 in the context of annotating radiology reports and generating impressions from chest computed tomography (CT) scans. The primary objective is to use these models to assist healthcare professionals in handling routine documentation tasks. Employing methods such as in-context learning (ICL) and retrieval-augmented generation (RAG), the study focused on generating impression sections from radiological findings. Comprehensive evaluation was applied using a variety of metrics, including recall-oriented understudy for gisting evaluation (ROUGE) for n-gram analysis, Instructor Similarity for contextual similarity, and BERTScore for semantic similarity, to assess the performance of these models. The study shows distinct performance differences between GPT-3.5 and GPT-4 across both zero-shot and few-shot learning scenarios. It was observed that certain prompts significantly influenced the performance outcomes, with specific prompts leading to more accurate impressions. The RAG method achieved a superior BERTScore of 0.92, showcasing its ability to generate semantically rich and contextually accurate impressions. In contrast, GPT-3.5 and GPT-4 excel in preserving language tone, with Instructor Similarity scores of approximately 0.92 across scenarios, underscoring the importance of prompt design in effective summarization tasks. The findings of this research emphasize the critical role of prompt design in optimizing model efficacy and point to the significant potential for further exploration in prompt engineering. Moreover, the study advocates for the standardized integration of such advanced LLMs in healthcare practices, highlighting their potential to enhance the efficiency and accuracy of medical documentation., Competing Interests: The authors declare no conflicts of interest., (Copyright © 2025 Bayan Altalla' et al. International Journal of Biomedical Imaging published by John Wiley & Sons Ltd.)