An image-based food quality analysis framework driven by large language models.

Large language models (LLMs) are increasingly adopted in educational contexts to provide personalized support to students and teachers. The unprecedented capacity of LLM‐based applications to understand and generate natural language can potentially improve instructional effectiveness and learning outcomes, but the integration of LLMs in education technology has renewed concerns over algorithmic bias, which may exacerbate educational inequalities. Building on prior work that mapped the traditional machine learning life cycle, we provide a framework of the LLM life cycle from the initial development of LLMs to customizing pre‐trained models for various applications in educational settings. We explain each step in the LLM life cycle and identify potential sources of bias that may arise in the context of education. We discuss why current measures of bias from traditional machine learning fail to transfer to LLM‐generated text (eg, tutoring conversations) because text encodings are high‐dimensional, there can be multiple correct responses, and tailoring responses may be pedagogically desirable rather than unfair. The proposed framework clarifies the complex nature of bias in LLM applications and provides practical guidance for their evaluation to promote educational equity. Practitioner notes What is already known about this topic The life cycle of traditional machine learning (ML) applications which focus on predicting labels is well understood. Biases are known to enter in traditional ML applications at various points in the life cycle, and methods to measure and mitigate these biases have been developed and tested. Large language models (LLMs) and other forms of generative artificial intelligence (GenAI) are increasingly adopted in education technologies (EdTech), but current evaluation approaches are not specific to the domain of education. What this paper adds A holistic perspective of the LLM life cycle with domain‐specific examples in education to highlight opportunities and challenges for incorporating natural language understanding (NLU) and natural language generation (NLG) into EdTech. Potential sources of bias are identified in each step of the LLM life cycle and discussed in the context of education. A framework for understanding where to expect potential harms of LLMs for students, teachers, and other users of GenAI technology in education, which can guide approaches to bias measurement and mitigation. Implications for practice and/or policy Education practitioners and policymakers should be aware that biases can originate from a multitude of steps in the LLM life cycle, and the life cycle perspective offers them a heuristic for asking technology developers to explain each step to assess the risk of bias. Measuring the biases of systems that use LLMs in education is more complex than with traditional ML, in large part because the evaluation of natural language generation is highly context‐dependent (eg, what counts as good feedback on an assignment varies). EdTech developers can play an important role in collecting and curating datasets for the evaluation and benchmarking of LLM applications moving forward.

SummarySustained engagement in HIV care and adherence to antiretroviral therapy (ART) are essential for achieving the UNAIDS “95-95-95” targets. Despite increased ART access, disengagement from care remains a significant issue, particularly in sub-Saharan Africa. Traditional machine learning (ML) models have shown moderate success in predicting care disengagement, which would enable early intervention. We develop an enhanced large language model (LLM) fine-tuned with electronic medical records (EMRs) to predict people at risk of disengaging from HIV care in Tanzania and to provide interpretative insights into modifiable risk factors.MethodsWe developed a novel AI model by enhancing a pre-trained LLM (LLaMA 3.1, an open-source pre-trained LLM released by Meta) using routinely collected EMRs from Tanzania’s National HIV Care and Treatment Program from January 1, 2018, to June 30, 2023 (4,809,765 records for 261,192 people) to identify people at risk of disengaging from HIV care or developing adverse outcomes. Outcomes included risk of ART non-adherence, non-suppressed viral load, and loss to follow-up. Models were evaluated internally (Kagera region) and externally (Geita region), with performance compared against state-of-art ML models and zero-shot LLMs. Additionally, a team of HIV physicians in Tanzania assessed the LLM’s predictions along with LLM provided justifications for a subset of patient records to evaluate their clinical relevance and reasoning.FindingsThe enhanced LLMs consistently outperformed the supervised ML model and zero-shot LLMs across all outcomes in both internal and external validation datasets. When focusing on the 25% of PLHIV predicted as most likely to lost-to-follow-up (LTFU), the model correctly identified 78% (2,515 of 3,224) of people living with HIV (PLHIV) genuinely at risk in internal validation and 73% (7,105 of 9,733) in external validation. Attention score analysis indicated that the enhanced LLM focused on keywords such as gaps in follow-up care and ART adherence. The human expert evaluation showed alignment between clinician assessments and the LLM’s predictions in 65% of cases, with experts finding the model’s justifications reasonable and clinically relevant in 92.3% of aligned cases.InterpretationIf implemented in HIV clinics, this LLM-based AI model could help allocate resources efficiently and deliver targeted interventions, improving retention in care and advancing the UNAIDS “95-95-95” targets. By functioning like a clinician–analyzing patient summaries, predicting risks, and offering reasoning–the enhanced LLM could be integrated into clinical workflows to complement human expertise, facilitating timely interventions and informed decision-making. If implemented widely, this human-AI collaboration has the potential to improve health outcomes for people living with HIV and reduce onward transmission.FundingThe study was supported by a grant from the US National Institutes of Health (NIH): NIH NIMH 1R01MH125746.

Since there is no known cure for Alzheimer's disease (AD), early detection is essential to controlling its progression.Because of the high cost and invasiveness of traditional diagnostic techniques like MRIs and pathological testing, researchers are looking into less expensive alternatives that use machine learning (ML) and natural language processing (NLP). By evaluating their performance against traditional ML and deep learning (DL) techniques, this study explores the possibility of using fine-tuned open-source large language models (LLMs) to identify AD through linguistic analysis. To optimize models like Qwen1.5–7B and OLMo1.7–7B, we used supervised fine-tuning (SFT) with parameter-efficient techniques like LoRA and QLoRA on the Pitt Corpus dataset, which consists of speech transcripts from the “Cookie Theft” picture description task. The findings showed that LLMs performed noticeably better than conventional techniques; Qwen1.5–7B had an F1-score of 0.8824, which was higher than CNN (0.7987), LSTM (0.7689), and logistic regression (0.83). The study demonstrates how LLMs can detect subtle linguistic impairments in AD that are difficult for traditional models to identify, like syntactic errors and repetitions. The comparatively small dataset size and exclusive reliance on textual data are limitations, though, and it is recommended that future studies include multimodal inputs and more varied datasets. Despite limitations, the results highlight the potential of optimized LLMs as scalable, non-invasive methods for early AD detection, providing a way to enhance patient care and diagnostic precision. Through this study, a novel, accurate, and reliable method for early diagnosis of Alzheimer's disease patients can be provided.

There is an increasing need for artificial intelligence in the field of medical related learning frameworks which is capable of efficiently handling the multimodal data which is under resource constrained situations. Conventional machine learning and deep learning algorithms are usually depending on the large labelled dataset and limited environment with less applicability for real world applications. The adoption of the Artificial intelligence in the field of healthcare is the need for the learning and effective handling of the multimodal healthcare data. Traditional machine learning and deep learning algorithms depends on the large-scale datasets with label, limiting the usage of the current clinical environment. This will limit the applicability of the real-world clinical environments by the data lackness and variance in the domain. In this work, Large Language Models are used with deep metric learning framework for multimodal medical journal classification. In this work, Large Language Model is implemented using deep metric learning framework for the multimodal dataset. The multimodal dataset comprises of text, table and images from online repository. The data manually downloaded from the PubMed website is used in this work. The proposed LLM guide framework outperformed all other models trained by various benchmark datasets.

ObjectivesTo determine the extent to which current Large Language Models (LLMs) can serve as substitutes for traditional machine learning (ML) as clinical predictors using data from electronic health records (EHRs), we investigated various factors that can impact their adoption, including overall performance, calibration, fairness, and resilience to privacy protections that reduce data fidelity.Materials and MethodsWe evaluated GPT-3.5, GPT-4, and ML (as gradient-boosting trees) on clinical prediction tasks in EHR data from Vanderbilt University Medical Center and MIMIC IV. We measured predictive performance with AUROC and model calibration using Brier Score. To evaluate the impact of data privacy protections, we assessed AUROC when demographic variables are generalized. We evaluated algorithmic fairness using equalized odds and statistical parity across race, sex, and age of patients. We also considered the impact of using in-context learning by incorporating labeled examples within the prompt.ResultsTraditional ML (AUROC: 0.847, 0.894 (VUMC, MIMIC)) substantially outperformed GPT-3.5 (AUROC: 0.537, 0.517) and GPT-4 (AUROC: 0.629, 0.602) (with and without in-context learning) in predictive performance and output probability calibration (Brier Score (ML vs GPT-3.5 vs GPT-4): 0.134 versus 0.384 versus 0.251, 0.042 versus 0.06 versus 0.219). Traditional ML is more robust than GPT-3.5 and GPT-4 to generalizing demographic information to protect privacy. GPT-4 is the fairest model according to our selected metrics but at the cost of poor model performance.ConclusionThese findings suggest that LLMs are much less effective and robust than locally-trained ML for clinical prediction tasks, but they are getting better over time.

Large Language Models (LLMs) have garnered increasing attention in neurosurgery and possess significant potential to improve the field. However, the breadth and performance of LLMs across diverse neurosurgical tasks have not been systematically examined, and LLMs come with their own challenges and unique terminology. We seek to identify key models, establish reporting guidelines for replicability, and highlight progress in key application areas of LLM use in the neurosurgical literature. We searched PubMed and Google Scholar using terms related to LLMs and neurosurgery ("large language model" OR "LLM" OR "ChatGPT" OR "GPT-3" OR "GPT3" OR "GPT-3.5" OR "GPT3.5" OR "GPT-4" OR "GPT4" OR "LLAMA" OR "MISTRAL" OR "BARD") AND "neurosurgery". The final set of articles was reviewed for publication year, application area, specific LLM(s) used, control/comparison groups used to evaluate LLM performance, whether the article reported specific LLM prompts, prompting strategy types used, whether the LLM query could be reproduced in its entirety (including both the prompt used and any adjoining data), measures of hallucination, and reported performance measures. Fifty-one articles met inclusion criteria, and were categorized into six application areas, with the most common being Generation of Text for Direct Clinical Use (n = 14, 27.5%), Answering Standardized Exam Questions (n = 12, 23.5%), and Clinical Judgement and Decision-Making Support (n = 11, 21.6%). The most frequently used LLMs were GPT-3.5 (n = 30, 58.8%), GPT-4 (n = 20, 39.2%), Bard (n = 9, 17.6%), and Bing (n = 6, 11.8%). Most studies (n = 43, 84.3%) used LLMs directly out-of-the-box, while 8 studies (15.7%) conducted advanced pre-training or fine-tuning. Large language models show advanced capabilities in complex tasks and hold potential to transform neurosurgery. However, research typically addresses basic applications and overlooks enhancing LLM performance, facing reproducibility issues. Standardizing detailed reporting, considering LLM stochasticity, and using advanced methods beyond basic validation are essential for progress.

Biomedical ultrasound imaging, as one of the most common, safe, and cost-effective modalities in clinical diagnosis, witnesses remarkable progress with the integration of artificial intelligence (AI). Early studies based on traditional machine learning (ML) rely on handcrafted features and classical classifiers to achieve automatic recognition and quantitative analysis of ultrasound images. However, such methods are limited in feature representation capacity and generalizability. With the advent of deep learning (DL), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and attention-based architectures are widely applied to tasks such as segmentation, detection, and lesion classification, significantly improving diagnostic accuracy and robustness. More recently, large language models (LLMs) and multimodal foundation models open new avenues for intelligent ultrasound analysis. These models not only integrate imaging and textual information to support automated report generation and cross-modal reasoning but also offer enhanced interpretability and greater potential for clinical adoption. In this review, we provide a systematic review of the evolution of AI in ultrasound image analysis, spanning from traditional ML to deep learning and LLMs, outlining a complete trajectory of methodological advances.

Accurately predicting relapse in multiple sclerosis (MS) remains challenging due to its variable clinical course. Recent advances in AI have shown that large language models (LLMs) can be effective in medical prediction tasks. This study compares LLMs and traditional machine learning (ML) models in forecasting relapse within three years of the first clinic visit across 2,192 patients with clinically isolated syndrome or relapsing-onset MS. Both approaches used identical structured clinical and demographic inputs, with LLMs fine-tuned on reformatted text representations. Fine-tuned LLMs matched or outperformed traditional models: BERT-MS achieved the highest F1 score (0.59), while LLaMA-MS led in ROC AUC (0.69) and PR AUC (0.55). SHAP (SHapley Additive exPlanation) analysis confirmed consistent directional effects across models and clinical relevance. These results highlight the potential of LLMs in medical bioinformatics and their value in individualized MS risk prediction using standard clinical data.

On the role of the UMLS in supporting diagnosis generation proposed by Large Language Models

<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>

Phishing attacks are becoming increasingly sophisticated, underscoring the need for detection systems that strike a balance between high accuracy and computational efficiency. This paper presents a comparative evaluation of traditional Machine Learning (ML), Deep Learning (DL), and quantized small-parameter Large Language Models (LLMs) for phishing detection. Through experiments on a curated dataset, we show that while LLMs currently underperform compared to ML and DL methods in terms of raw accuracy, they exhibit strong potential for identifying subtle, context-based phishing cues. We also investigate the impact of zero-shot and few-shot prompting strategies, revealing that LLM-rephrased emails can significantly degrade the performance of both ML and LLM-based detectors. Our benchmarking highlights that models like DeepSeek R1 Distill Qwen 14B (Q8_0) achieve competitive accuracy, above 80%, using only 17 GB of VRAM, supporting their viability for cost-efficient deployment. We further assess the models’ adversarial robustness and cost-performance tradeoffs, and demonstrate how lightweight LLMs can provide concise, interpretable explanations to support real-time decision-making. These findings position optimized LLMs as promising components in phishing defence systems and offer a path forward for integrating explainable, efficient AI into modern cybersecurity frameworks.

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.

Background and Aims Large language models (LLMs) have gained significant attention in the field of natural language processing (NLP), marking a shift from traditional techniques like Term Frequency-Inverse Document Frequency (TF-IDF). We developed a traditional NLP model to predict arteriovenous fistula (AVF) failure within next 30 days using clinical notes. The goal of this analysis was to investigate whether LLMs would outperform traditional NLP techniques, specifically in the context of predicting AVF failure within the next 30 days using clinical notes. Method We defined AVF failure as the change in status from active to permanently unusable status or temporarily unusable status. We used data from a large kidney care network from January 2021 to December 2021. Two models were created using LLMs and traditional TF-IDF technique. We used “distilbert-base-uncased”, a distilled version of BERT base model [1], and compared its performance with traditional TF-IDF-based NLP techniques. The dataset was randomly divided into 60% training, 20% validation and 20% test dataset. The test data, comprising of unseen patients’ data was used to evaluate the performance of the model. Both models were evaluated using metrics such as area under the receiver operating curve (AUROC), accuracy, sensitivity, and specificity. Results The incidence of 30 days AVF failure rate was 2.3% in the population. Both LLMs and traditional showed similar overall performance as summarized in Table 1. Notably, LLMs showed marginally better performance in certain evaluation metrics. Both models had same AUROC of 0.64 on test data. The accuracy and balanced accuracy for LLMs were 72.9% and 59.7%, respectively, compared to 70.9% and 59.6% for the traditional TF-IDF approach. In terms of specificity, LLMs scored 73.2%, slightly higher than the 71.2% observed for traditional NLP methods. However, LLMs had a lower sensitivity of 46.1% compared to 48% for traditional NLP. However, it is worth noting that training on LLMs took considerably longer than TF-IDF. Moreover, it also used higher computational resources such as utilization of graphics processing units (GPU) instances in cloud-based services, leading to higher cost. Conclusion In our study, we discovered that advanced LLMs perform comparably to traditional TF-IDF modeling techniques in predicting the failure of AVF. Both models demonstrated identical AUROC. While specificity was higher in LLMs compared to traditional NLP, sensitivity was higher in traditional NLP compared to LLMs. LLM was fine-tuned with a limited dataset, which could have influenced its performance to be similar to that of traditional NLP methods. This finding suggests that while LLMs may excel in certain scenarios, such as performing in-depth sentiment analysis of patient data for complex tasks, their effectiveness is highly dependent on the specific use case. It is crucial to weigh the benefits against the resources required for LLMs, as they can be significantly more resource-intensive and costly compared to traditional TF-IDF methods. This highlights the importance of a use-case-driven approach in selecting the appropriate NLP technique for healthcare applications.

Cancer treatments are known to introduce cardiotoxicity, negatively impacting outcomes and survivorship. Identifying cancer patients at risk of heart failure (HF) is critical to improving cancer treatment outcomes and safety. This study examined machine learning (ML) models to identify cancer patients at risk of HF using electronic health records (EHRs), including traditional ML, Time-Aware long short-term memory (T-LSTM), and large language models (LLMs) using novel narrative features derived from the structured medical codes. We identified a cancer cohort of 12,806 patients from the University of Florida Health, diagnosed with lung, breast, and colorectal cancers, among which 1,602 individuals developed HF after cancer. The LLM, GatorTron-3.9B, achieved the best F1 scores, outperforming the traditional support vector machines by 39%, the T-LSTM deep learning model by 7%, and a widely used transformer model, BERT, by 5.6%. The analysis shows that the proposed narrative features remarkably increased feature density and improved performance.

Phishing attacks continue to grow in scale and sophistication, causing substantial financial losses and privacy breaches worldwide. Recent advances in large language models (LLMs) have brought significant changes to the generation and detection of phishing content. This study systematically investigates the dual role of LLMs in facilitating phishing attacks and strengthening countermeasures. Using the PRISMA methodology, authors screened 142 records published between January 2023 and April 2025 and identified 36 eligible studies from major academic databases, including IEEE Xplore, ScienceDirect, ACM Digital Library, Web of Science, and Scopus. A comprehensive and rigorous analysis was conducted of research trends/themes over time, dataset characteristics, and the LLM architectures/models employed. The findings reveal that most studies relied on manually generated datasets rather than publicly available benchmark datasets, and that GPT-based models received considerably more attention than other LLM architectures. The review demonstrates that LLMs substantially enhance the generation of phishing content by producing coherent, contextually relevant, and persuasive email and website content. This capability lowers the technical barrier for attackers and potentially increases attack effectiveness. Conversely, LLMs also strengthen defensive strategies by enabling more effective analysis of textual and visual content for phishing detection. In many cases, LLM-based approaches outperform traditional machine learning and deep learning methods and, in certain contexts, approach or match human-level performance. Overall, the findings suggest that LLMs have accelerated and automated phishing-related processes, simultaneously intensifying the threat landscape and advancing defensive capabilities. • The first in-depth study to review LLMs usage in Phishing attack generation and detection. • The study reveals LLMs have accelerated and automated phishing-related processes, elevating both threats and defence mechanisms. • GenAI-based multimodal phishing attacks are on the rise due to the wider adoption of GenAI tools in general.