Understanding Cancer Survivorship Care Needs Using Amazon Reviews: Content Analysis, Algorithm Development, and Validation Study

The integration of deep learning (DL) and large language models (LLMs) has significantly advanced the field of cybersecurity, offering innovative approaches to threat detection, anomaly identification, and secure communication. Deep learning techniques, such as neural networks and reinforcement learning, have demonstrated robust capabilities in detecting previously unknown threats by learning patterns from vast amounts of cybersecurity data. Similarly, LLMs, particularly transformers, have revolutionized natural language processing tasks, enabling effective vulnerability analysis, malware classification, and phishing detection. This chapter explores the foundational concepts of deep learning and LLMs, highlighting their applications and challenges within the cybersecurity landscape. Additionally, it discusses the synergy between these technologies, focusing on how they complement traditional cybersecurity measures and drive the evolution of intelligent defense mechanisms.

Software vulnerabilities pose significant risks to the security and reliability of modern systems, making automated vulnerability detection an essential research area. Traditional static and rule-based approaches are limited in scalability and adaptability, motivating the adoption of data-driven methods. In this survey, we present a comprehensive review of Machine Learning (ML), Deep Learning (DL), and Large Language Models (LLMs) techniques for vulnerability detection. We analyze recent advances in feature representation, fine-tuning strategies, generative approaches, and prompt engineering, while highlighting their ability to capture both syntactic and semantic properties of source code. Furthermore, we examine commonly used evaluation metrics and provide a critical discussion of key challenges, including the lack of large-scale real-world datasets, limited vulnerability coverage, class imbalance, interpretability gaps, hallucination, and high computational costs. To address these issues, we outline promising future research directions, such as neuro-symbolic hybrid methods, parameter-efficient fine-tuning, continual learning, cross-language generalization, and explainable AI for vulnerability detection. Unlike previous studies, the present work explores learning paradigms from ML to LLMs using comprehensive evaluation criteria that highlight analytical capability, feature interpretability, and code-context comprehension. By combining these factors, our study addresses the methodological gap between classic feature-based approaches and current LLM-driven reasoning frameworks, providing beneficial insights to develop robust, scalable, and trustworthy software vulnerability detection systems.

Artificial intelligence is reshaping approaches to architectural heritage conservation by enabling a deeper understanding of how people perceive and experience historic built environments. This study employs deep learning and large language models (LLMs) to explore public perceptions of the Qinghefang Historical and Cultural District in Hangzhou, illustrating how AI-driven analytics can inform intelligent heritage management and architectural revitalization. Large-scale public online reviews were processed through BERTopic-based clustering to extract thematic structures of experience, while interpretive synthesis was refined using an LLM to identify core perceptual dimensions including Hangzhou Housing & Residential Choice, Hangzhou Urban Tourism & Culture, Hangzhou Food & Dining, and Qinghefang Culture & Creative. Sentiment polarity and emotional intensity were quantified using a fine-tuned BERT model, revealing distinct affective and perceptual patterns across the district’s architectural and cultural spaces. The results demonstrate that AI-based textual analytics can effectively decode human–heritage interactions, offering actionable insights for data-informed conservation, visitors’ experience optimization, and sustainable management of historic districts. This research contributes to the emerging field of AI-driven innovation in architectural heritage by bridging computational intelligence and heritage conservation practice.

This work aims to present an overview of using some artificial intelligence (AI) models in machine translation (MT). This work aims to integrate machine learning (ML), deep learning (DL), large language models (LLMs) to enhance machine translation between natural languages. The focus is directed to present the neural-based machine translation (NMT), and some DL models are presented. The bidirectional-encoder-representation from transformer (BERT) and LLMs are presented to utilize the big amount of textual data to learn translation patterns. The main measurable criteria that are used to evaluate the performance of MT and Arabic machine translation (AMT) are also presented. Some linguistic and technical challenges of MT and AMT are discussed. Some key points of future works in NMT are mentioned. A comparative study among some recent published related works is presented. A critical survey is presented to show the important role of DL and LLMs in MT. Some open-source toolkits, datasets and some commercial MT systems are collected and briefly presented. This work is expected to be useful for those people interested to know the up-to-date knowledge of MT and the potential role of DL and LLM in automatic translation.

Despite advances in early detection and effective treatment, cancer remains one of the most feared diseases. Among the most common side effects of cancer and treatments for cancer are pain, depression, and fatigue. Although research is producing increasingly hopeful insights into the causes and cures for cancer, efforts to manage the side effects of the disease and its treatments have not kept pace. The challenge that faces us is how to increase awareness of the importance of recognizing and actively addressing cancer-related distress. The National Institutes of Health (NIH) convened a State-of-the-Science Conference on Symptom Management in Cancer: Pain, Depression, and Fatigue to examine the current state of knowledge regarding the management of pain, depression, and fatigue in individuals with cancer and to identify directions for future research. Specifically, the conference examined how to identify individuals who are at risk for cancer-related pain, depression, and/or fatigue; what treatments work best to address these symptoms when they occur; and what is the best way to deliver interventions across the continuum of care. State-of-the-Science Process: A non-advocate, non-Federal, 14-member panel of experts representing the fields of oncology, radiology, psychology, nursing, public health, social work, and epidemiology prepared the statement. In addition, 24 experts in medical oncology, geriatrics, pharmacology, psychology, and neurology presented data to the panel and to the conference audience during the first 1.5 days of the conference. The panel then prepared its statement, addressing the five predetermined questions and drawing on submitted literature, the speakers' presentations, and discussions held at the conference. The statement was presented to the conference audience, followed by a press conference to allow the panel to respond to questions from the media. After its release at the conference, the draft statement was made available on the Internet. The panel's final statement is available at http://consensus.nih.gov. The panel concluded that the available evidence supports a variety of interventions for treating cancer patients' pain, depression, and fatigue. Clinicians should routinely use brief assessment tools to ask patients about pain, depression, and fatigue and to initiate evidence-based treatments. Assessment should include discussion about common symptoms experienced by cancer patients, and these discussions should continue over the duration of the illness. Impediments to effective symptom management in cancer patients can arise from different sources and interactions among providers, patients and their families, and the health care system. Numerous factors could interfere with adequate symptom management. Among these factors are incomplete effectiveness of some treatments, a lack of sufficient knowledge regarding effective treatment strategies, patient reluctance to report symptoms to caregivers, a belief that such symptoms are simply a part of the cancer experience that must be tolerated, and inadequate coverage and reimbursement for some treatments. Additional research is needed on the definition, occurrence, the treatment of pain, depression, and fatigue, alone and in combination, in adequately funded prospective studies. The panel also concluded that the state of the science in cancer symptom management should be reassessed periodically.

Accurate burn depth assessment remains a challenge, especially in emergency settings. This study aimed to develop a low-cost artificial intelligence (AI)-based system for burn wound classification using deep learning and large language models (LLMs). A total of 397 burn wound images from public databases were augmented to 7156 images and categorized by depth. A classification model was trained using PaddlePaddle, and a burn-specific LLM was developed based on clinical guidelines. Model performance was evaluated using accuracy, recall, and F1 score and compared against 10 medical students and 6 general LLMs on 80 out-of-sample images. Our model achieved an overall accuracy of 96.82% and F1 score of 96.70%, outperforming medical students (F1: 76.63%) and general LLMs (F1: 68.75%-73.75%). In a separate test using 10 guideline-based true/false questions, all AI models answered correctly, whereas students had only 64% accuracy. This integrated model offers accurate burn depth recognition and guideline-based treatment suggestions, addressing the shortage of burn care specialists, and supporting medical education.

<sec> <title>BACKGROUND</title> Substance use disorder (SUD) affects more than 48 million people in the US, but access to care is often constrained by factors such as stigma, financial barriers, and limited service availability. While digital health interventions have begun to mitigate these challenges, large language models (LLMs) such as GPT introduce new possibilities for scalable SUD recovery support. However, empirical evidence regarding LLM use in SUD contexts re-mains fragmented and unevenly evaluated. A scoping review is needed to synthesize cur-rent approaches, surface methodological and safety gaps, and inform future research. </sec> <sec> <title>OBJECTIVE</title> This scoping review synthesizes current evidence on the use of LLMs in SUD and addiction contexts. It examines how LLM-based tools are being applied across the full spectrum of care, identifies common tasks and data sources, evaluates risks and safety concerns, and maps early evidence of effectiveness and gaps that inform future research. </sec> <sec> <title>METHODS</title> We conducted a scoping review in accordance with PRISMA-ScR guidelines. We searched medical and technical databases for studies that reported empirical findings on LLMs in drug-related SUD contexts. Of 675 records identified, 492 were screened at the title and abstract level, 60 underwent full-text review, and 12 studies met inclusion criteria. </sec> <sec> <title>RESULTS</title> All included studies were published in 2024 or 2025, indicating a very recent and rapidly evolving evidence base. Most studies used public social media or online forums (8 of 12), while 3 studies used clinical data such as EHR, and 1 study used multimodal data that combined sensors, images, and chat logs. GPT-family models were the most frequently used (10 of 12), often evaluated alongside Llama or Mistral models. Across studies, LLM applications clustered into four task categories: text classification and extraction, response generation, conversational decision support, and predictive modeling using LLM-derived features. Classification and extraction tasks were most common and often showed im-proved performance compared with traditional machine learning or rule-based baselines. While general-purpose LLMs were prone to generating stigmatizing, biased, or clinically inappropriate content in SUD-related scenarios, it was also reported that targeted prompt engineering substantially reduced stigmatizing language and improved perceived ade-quacy and appropriateness of responses. However, safety evaluations remained limited in scope and depth. </sec> <sec> <title>CONCLUSIONS</title> LLM-based tools show emerging potential to support SUD-related research and care, particularly scalable classification and information extraction, conversational screening, and feature derivation from unstructured text or speech. Yet current work is predominantly preclinical, relying on public datasets and simulated prompts, with limited evidence on safety, clinical effectiveness, or real-world implementation in recovery settings. Responsible use in SUD contexts will require a safety-first development approach that integrates human-in-the-loop validation, systematic prompt engineering, and design constraints such as curated response libraries. It will also require efforts to strengthen LLM literacy among clinicians, peer specialists, and people in recovery. </sec>

Purpose This paper aims to evaluate how effectively large language models (LLMs) represent and generate minority cultural knowledge, specifically Taiwanese Hakka culture. To address this, the study proposes a structured and replicable evaluation framework integrating Bloom’s taxonomy and retrieval-augmented generation (RAG). The research is guided by the following questions: (1) How do LLMs perform across different cognitive domains when processing Hakka cultural content? (2) To what extent does the integration of RAG enhance the accuracy and contextual appropriateness of LLM outputs? And (3) How do different LLM architectures compare in their ability to recall, analyse and creatively synthesize culturally grounded information? Design/methodology/approach This study proposes a cognitive benchmarking framework to evaluate how LLMs process and apply culturally specific knowledge. The framework integrates Bloom’s taxonomy with RAG to assess model performance across six hierarchical cognitive domains: remembering, understanding, applying, analysing, evaluating and creating. Using a curated Taiwanese Hakka digital cultural archive as the primary testbed, the evaluation measures LLM-generated responses’ semantic accuracy and cultural relevance. Findings The evaluation results indicate that LLMs augmented with RAG exhibit marked improvements over baseline models in the cognitive domains of remembering, understanding and analysing. These enhancements are particularly evident in tasks requiring factual accuracy, contextual relevance and semantic precision, underscoring RAG’s effectiveness in addressing the knowledge sparsity typically observed in underrepresented cultural data sets. However, a notable limitation persists across all models including those equipped with RAG in the domain of creating. This suggests that while retrieval mechanisms bolster the reproduction and comprehension of cultural knowledge, they do not yet sufficiently support culturally nuanced generative synthesis. Originality/value This study introduces a novel evaluation framework integrating cognitive domain benchmarks with RAG-enhanced LLMs to assess cultural knowledge processing. The research advances culturally grounded artificial intelligence (AI) systems and digital archival quality by empirically demonstrating RAG’s impact on improving factual accuracy in lower and mid-level tasks. The findings affirm the strategic value of retrieval integration for enhancing representational fidelity in cultural AI applications, while also highlighting the need for future research into hybrid architectures that combine external grounding with culturally adaptive generation strategies.

Background:Even though patients have easy access to their electronic health records and lab test results data through patient portals, lab results are often confusing and hard to understand. Many patients turn to online forums or question and answering (Q&A) sites to seek advice from their peers. However, the quality of answers from social Q&A on health-related questions varies significantly, and not all the responses are accurate or reliable. Large language models (LLMs) such as ChatGPT have opened a promising avenue for patients to get their questions answered.Objective:We aim to assess the feasibility of using LLMs to generate relevant, accurate, helpful, and unharmful responses to lab test-related questions asked by patients and to identify potential issues that can be mitigated with augmentation approaches.Methods:We first collected lab test results related question and answer data from Yahoo! Answers and selected 53 Q&A pairs for this study. Using the LangChain framework and ChatGPT web portal, we generated responses to the 53 questions from four LLMs including GPT-4, Meta LLaMA 2, MedAlpaca, and ORCA_mini. We first assessed the similarity of their answers using standard QA similarity-based evaluation metrics including ROUGE, BLEU, METEOR, BERTScore. We also utilized an LLM-based evaluator to judge whether a target model has higher quality in terms of relevance, correctness, helpfulness, and safety than the baseline model. Finally, we performed a manual evaluation with medical experts for all the responses of seven selected questions on the same four aspects.Results:Regarding the similarity of the responses from 4 LLMs, where GPT-4 output was used as the reference answer, the responses from LLaMa 2 are the most similar ones, followed by LLaMa 2, ORCA_mini, and MedAlpaca. Human answers from Yahoo data were scored lowest and thus least similar to GPT-4-generated answers. The results of Win Rate and medical expert evaluation both showed that GPT-4’s responses achieved better scores than all the other LLM responses and human responses on all the four aspects (relevance, correctness, helpfulness, and safety). However, LLM responses occasionally also suffer from lack of interpretation in one’s medical context, incorrect statements, and lack of references.Conclusions:By evaluating LLMs in generating responses to patients’ lab test results related questions, we find that compared to other three LLMs and human answer from the Q&A website, GPT-4’s responses are more accurate, helpful, relevant, and safer. However, there are cases that GPT-4 responses are inaccurate and not individualized. We identified a number of ways to improve the quality of LLM responses including prompt engineering, prompt augmentation, retrieval augmented generation, and response evaluation.

Artificial intelligence (AI) technologies, including machine learning (ML), deep learning, and large language models, are increasingly applied in medical diagnostics. In rhinology, these tools are being evaluated for tasks such as image interpretation, cytology classification, and clinical decision support. To systematically evaluate the application and diagnostic accuracy of AI technologies in rhinology, with a focus on clinical utility and implementation barriers. This review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. Seventeen full-text studies were screened based on predefined eligibility criteria, focusing on AI applications with diagnostic metrics in rhinology. Data on AI type, diagnostic task, performance outcomes, and study quality were extracted and synthesized narratively. Twelve studies met the inclusion criteria. Image-based diagnostic tools using convolutional neural networks demonstrated high accuracy (81%-99%) in nasal polyp detection, cytology classification, and computed tomography (CT) scan interpretation. ML models using patient-reported data achieved accuracies of 74.5%-85.5% for chronic rhinosinusitis prediction. Large language models like ChatGPT and Gemini were evaluated for clinical question answering, with performance exceeding 80% in some domains. Risk of bias was moderate in most primary studies, and none reported clinical integration beyond prototype stages. AI exhibits promising diagnostic accuracy across several applications in rhinology. However, significant challenges persist, including limited validation, methodological heterogeneity, and lack of clinical implementation. Future research should focus on prospective trials, explainability, and regulatory frameworks to ensure safe integration into clinical workflows.

Accurate demand Soothsaying is a crucial element in force chain operation and business planning. Traditional statistical ways don’t consider the nonlinear, dynamic, and interdependent nature of variables that drive product demand, including deal history, prices, seasonality, elevations, request changes, and profitable pointers. This design presents a sophisticated soothsaying frame for guidance from an artificial intelligence system, integrating soothsaying using deep literacy models together with large language models(LLMs), that can negotiate both accurate soothsaying and give practicable intelligence. The deep literacy infrastructures used in this study include Long Short Term Memory(LSTM), Reopened intermittent Units(GRU), and other Motor models for timeseries soothsaying, which optimize temporal dependences and the complex cross-variable relations. To further increase interpretability of the vaticinations, LLMs are useful agents to convert the specialized cast affair into a completely automated and enhanced mortal-readable textbook and reports to develop intelligence for decision timber. Prophetic modeling and naturally generated reporting lead to better delicacy and practicable intelligence for their businesses. This intelligence empowers businesses to create better procurement processes, improve inventory management, and develop more resilient supply chains relevant to today’s business environment.

Software defect detection is particularly important for modern society, as it is a crucial step in ensuring the quality and reliability of software systems. With the emergence of artificial intelligence (AI), research in software defect detection has evolved from traditional methods to more complex approaches that utilize deep learning and large language models (LLMs). The advent of LLMs has fundamentally changed the paradigm of software development and defect detection, bringing new challenges and confusion to the field of software defect prediction research. To address these issues, we compare software defect detection methods based on traditional techniques, deep learning approaches, and LLMs through a literature review. We analyze the changes brought about by the introduction of LLMs to software development and propose new insights. Additionally, we examine the progress and trends in software defect prediction to provide inspiration for subsequent research.

As the number of cancer survivors continues to increase and given the shortage of oncology clinicians in safety net health care settings, primary care providers (PCPs) in these settings will increasingly provide cancer survivorship care. In order to ensure equitable care for low-income and underserved breast and colon cancer survivors, it is essential to understand the safety-net PCPs’ perspective. We conducted semi-structured, in-depth qualitative interviews with 11 PCPs working in a safety-net health care system to identify their needs in caring for cancer survivors. Interviews were audio-recorded and professionally transcribed. Two coders independently coded the interviews and conducted regular meetings until we reached consensus on the results. Analysis was based in grounded theory and performed using the constant comparative method. Thematic analysis identified six themes as follows: (1) Cancer survivorship care can be integrated with the whole person and chronic disease care management that occurs in primary care; (2) PCPs’ perceptions regarding patients’ survivorship care needs and their confidence in meeting those needs; (3) preference for a shared care model; (4) coordination of care; (5) PCPs’ need for survivorship care education and training; and (6) unique issues involved in the care of older cancer survivors. PCPs in the safety-net believe that providing comprehensive survivorship care requires coordination of care through the cancer continuum. Tools like checklists, electronic health records-based communication, and convenient electronic consultations with cancer specialists would enhance the quality of survivorship care. Respondents advocate the inclusion of survivorship care education in medical education. The continuity of care with PCPs means that they play a particularly important role in the care of older cancer survivors.

PurposeStudies focusing on patients with and survivors of cancer during the COVID-19 pandemic highlight unique psychological and behavioral challenges. These findings were obtained in surveys using self-report questionnaires with pre-specified response options that may not capture the broad range of experiences of individuals affected by cancer, including people with cancer and informal caregivers, in this unprecedented situation. Online forums produce a large amount of valuable first-hand user-generated content that can be used to better understand their day-to-day lives. This study, based on the analysis of narratives in cancer online forums, aims to describe and categorize the experiences of people affected by cancer during the outbreak of the COVID-19 pandemic.MethodAn inductive, descriptive, thematic approach was applied to publicly available cancer forums from Germany, the USA, the UK, and Ireland posted between mid-March and mid-April 2020.ResultsAn analysis of the content of 230 main posts revealed three major themes: (1) concerns related to the impact of COVID-19 on cancer care, the risks and fears of getting infected, logistic issues, and economic impact; (2) adaptation challenges faced at the individual and societal level; and (3) the need for advice including information about COVID-19 and the (self-)management of cancer symptoms and treatment.ConclusionOur qualitative description of the experiences of people affected by cancer during the COVID-19 pandemic outbreak can help to improve communication, education, and the development of supportive care strategies. Furthermore, the themes and subthemes identified could potentially inform item development for future self-report questionnaires.

With large-scale language models demonstrating superior capabilities in a wide range of downstream natural language processing tasks, the future trajectory of research in the field of text categorization faces increasing uncertainty. In this evolving paradigm of open-ended language modeling, where task delimitations are increasingly blurred, a pressing question arises: to what extent has text classification advanced under the full potential of large language model (LLM)? To address this pivotal inquiry, we introduce recurrent generative pre-trained transformer (RGPT), an adaptive boosting framework meticulously designed to craft a dedicated LLM for text classification. RGPT constructs a sequence of base learners by dynamically modulating the training data distribution and iteratively fine-tuning LLMs. These base learners are then progressively integrated, leveraging historical prediction trajectories to form a highly specialized text classification model. Extensive empirical evaluations demonstrate that RGPT surpasses eight state-of-the-art pretrained language models and seven cutting-edge LLMs across four benchmark datasets, achieving an average performance gain of 2.90%.