A network and thematic analysis of mental health-related Prevention of Future Death reports from 2013 to 2025 in England and Wales.

LLMs application to clinical practice is growing fast. However, LLMs are less studied in geriatrics practice but are urgently needed. This symposium will address whether LLMs allocation to geriatric practice can be trusted via five approaches. 1) LLMs generated gender and race-biased outputs. We will demonstrate whether LLMs generated age-biased output by assessing their geriatric attitude evaluated by social workers. 2). LLMs passed USMLE and other examinations. We will demonstrate whether LLMs can pass geriatrics knowledge competence tests evaluated by geriatricians 3). LLMs performed well on clinical vignettes from different clinical disciplines. We will demonstrate whether LLMs can perform well on geriatrics 5M-based vignettes of older adults evaluated by clinical providers and trainees 4) LLMs reviewed and summarized clinical charts. We will demonstrate whether LLMs can review geriatrics and general medicine notes to extract Mobility (one of Geriatrics 5Ms) documentation evaluated by geriatricians 5). LLMs can generate deprescribing recommendations, tapering schedules, and patient education materials. We will demonstrate their accuracy, safety, and appropriateness compared to recommendations from a multidisciplinary team of pharmacists, geriatricians, and nurses. Specifically, this symposium will address the following topics: 1) Geriatric Attitude of ChatGPT4.o and Its Evaluation by Social Workers. 2) ChatGPT4.o Geriatrics Knowledge Competency and Its Evaluation by Geriatricians. 3) LLMs application to geriatrics 5Ms evaluated by clinical providers and trainees. 4) Using LLMs to Extract and Assess Mobility Documentation for Age-Friendly Health System evaluated by geriatricians. 5) Using LLMs to generate medication deprescribing recommendations compared to clinician-led deprescribing recommendations.

Patient experiences and perspectives are essential for shaping patient-centered healthcare. While large language models (LLMs) in healthcare are typically applied to specific clinical or patient-facing tasks, they have not been used for qualitative patient preference assessment, which often relies on thematic analysis to understand patient views expressed in interviews or focus groups. LLMs show initial promise for performing inductive thematic analysis of healthcare interview or focus group transcripts, yet no empirical studies have investigated LLMs to facilitate qualitative patient preference assessment. We employed the open-source Hermes-3-Llama-3.1-70B LLM to perform inductive thematic analysis on focus group transcripts from a previously published qualitative patient preference assessment study using three optimized prompt frameworks, and evaluated semantic similarity of LLM generated themes against human-analyzed themes using the Sentence-T5-XXL language embedding model. Sentence-level theme similarity was assessed using Jaccard similarity coefficients (0-1 range), computing coefficient scores across a broad range of discrete cosine similarity thresholds. We further evaluated LLM themes for similarity in lexical diversity and reading grade-level metrics and benchmarked semantic similarity results with published similarity thresholds previously used with qualitative healthcare data. All prompt frameworks generated themes with median Jaccard similarity coefficients with human-analyzed themes between 0.46-0.64, indicating moderate semantic overlap. Our best-performing framework instructed to pursue thematic saturation scored closest to human-analyzed themes on all reading grade-level metrics, and demonstrated 12% higher semantic overlap with human-analyzed themes compared to published benchmarks. Our worst-performing framework produced themes with moderate semantic overlap and hallucinated findings unidentified in human-analyzed themes. We demonstrate that LLMs can perform inductive thematic analysis of qualitative patient preference data, producing themes substantively similar in content and style to human-analyzed themes when augmented with sufficient domain-specific context. While LLMs may augment thematic analysis, the contextual nature of qualitative analysis remains a challenge requiring collaborative LLM frameworks integrating human expertise.

BackgroundPatient complaints provide valuable insights into the performance of health care systems, highlighting potential risks not apparent to staff. Patient complaints can drive systemic changes that enhance patient safety. However, manual categorization and analysis pose a huge logistical challenge, hindering the ability to harness the potential of these data.ObjectiveThis study aims to evaluate the accuracy of artificial intelligence (AI)–powered categorization of patient complaints in primary care based on the Healthcare Complaint Analysis Tool (HCAT) General Practice (GP) taxonomy and assess the importance of advanced large language models (LLMs) in complaint categorization.MethodsThis cross-sectional study analyzed 1816 anonymous patient complaints from 7 public primary care clinics in Singapore. Complaints were first coded by trained human coders using the HCAT (GP) taxonomy through a rigorous process involving independent assessment and consensus discussions. LLMs (GPT-3.5 turbo, GPT-4o mini, and Claude 3.5 Sonnet) were used to validate manual classification. Claude 3.5 Sonnet was further used to identify complaint themes. LLM classifications were assessed for accuracy and consistency with human coding using accuracy and F1-score. Cohen κ and McNemar test evaluated AI-human agreement and compared AI models’ concordance, respectively.ResultsThe majority of complaints fell under the HCAT (GP) domain of management (1079/1816, 59.4%), specifically relating to institutional processes (830/1816, 45.7%). Most complaints were of medium severity (994/1816, 54.7%), occurred within the practice (627/1816, 34.5%), and resulted in minimal harm (75.4%). LLMs achieved moderate to good accuracy (58.4%‐95.5%) in HCAT (GP) field classifications, with GPT-4o mini generally outperforming GPT-3.5 turbo, except in severity classification. All 3 LLMs demonstrated moderate concordance rates (average 61.9%‐68.8%) in complaints classification with varying levels of agreement (κ=0.114‐0.623). GPT-4o mini and Claude 3.5 significantly outperformed GPT-3.5 turbo in several fields (P<.05), such as domain and stage of care classification. Thematic analysis using Claude 3.5 identified long wait times (393/1816, 21.6%), staff attitudes (287/1816, 15.8%), and appointment booking issues (191/1816, 10.5%) as the top concerns, which accounted for nearly half of all complaints.ConclusionsOur study highlighted the potential of LLMs in classifying patient complaints in primary care using HCAT (GP) taxonomy. While GPT-4o and Claude 3.5 demonstrated promising results, further fine-tuning and model training are required to improve accuracy. Integrating AI into complaint analysis can facilitate proactive identification of systemic issues, ultimately enhancing quality improvement and patient safety. By leveraging LLMs, health care organizations can prioritize complaints and escalate high-risk issues more effectively. Theoretically, this could lead to improved patient care and experience; further research is needed to confirm this potential benefit.

Thematic analysis and other variants of inductive coding are widely used qualitative analytic methods within empirical legal studies (ELS). We propose a novel framework facilitating effective collaboration of a legal expert with a large language model (LLM) for generating initial codes (phase 2 of thematic analysis), searching for themes (phase 3), and classifying the data in terms of the themes (to kick-start phase 4). We employed the framework for an analysis of a dataset (n = 785) of facts descriptions from criminal court opinions regarding thefts. The goal of the analysis was to discover classes of typical thefts. Our results show that the LLM, namely OpenAI’s GPT-4, generated reasonable initial codes, and it was capable of improving the quality of the codes based on expert feedback. They also suggest that the model performed well in zero-shot classification of facts descriptions in terms of the themes. Finally, the themes autonomously discovered by the LLM appear to map fairly well to the themes arrived at by legal experts. These findings can be leveraged by legal researchers to guide their decisions in integrating LLMs into their thematic analyses, as well as other inductive coding projects.

Agentic AI and Large Language Models (LLMs) are transforming how language is understood and generated while reshaping decision-making, automation, and research practices. LLMs provide underlying reasoning capabilities, and Agentic AI systems use them to perform tasks through interactions with external tools, services, and Application Programming Interfaces (APIs). Based on a structured scoping review and thematic analysis, this study identifies that core challenges of LLMs, relating to security, privacy and trust, misinformation, misuse and bias, energy consumption, transparency and explainability, and value alignment, can propagate into Agentic AI. Beyond these inherited concerns, Agentic AI introduces new challenges, including context management, security, privacy and trust, goal misalignment, opaque decision-making, limited human oversight, multi-agent coordination, ethical and legal accountability, and long-term safety. We analyse the applications of Agentic AI powered by LLMs across six domains: education, healthcare, cybersecurity, autonomous vehicles, e-commerce, and customer service, to reveal their real-world impact. Furthermore, we demonstrate some LLM limitations using DeepSeek-R1 and GPT-4o. To the best of our knowledge, this is the first comprehensive study to integrate the challenges and applications of LLMs and Agentic AI within a single forward-looking research landscape that promotes interdisciplinary research and responsible advancement of this emerging field.

Background:Artificial intelligence (AI) and large language models (LLMs) are increasingly integrated into healthcare, yet their adoption in pediatric urology remains insufficiently explored. Pediatric urology, with its complex and rare conditions, may particularly benefit from AI-based innovations.Objectives:This study aimed to assess pediatric urologists’ awareness, usage patterns, and perceptions regarding AI and LLMs, while also identifying potential applications, barriers, and educational needs.Design:A cross-sectional, descriptive survey was conducted among pediatric urologists.Methods:Between May and July 2025, a 21-item questionnaire was distributed via professional networks and mailing lists. Items addressed demographics, knowledge of AI, frequency and purpose of AI and LLM use, perceived clinical and surgical applications, ethical concerns, and interest in AI training. Descriptive statistics were used for analysis.Results:Of 368 invited pediatric urologists, 103 (28%) responded. Most reported moderate (35.0%) or low (29.1%) knowledge of AI, yet more than half (51.5%) used AI tools daily. LLMs had been used by 96.1% of participants, mainly for scientific writing (78.8%), language editing (54.5%), and text summarization (46.5%). Surgical simulation (46.6%), imaging-based strategy planning (40.8%), and preoperative planning (36.9%) were identified as promising clinical applications. Barriers included lack of trust (52.4%), ethical concerns (43.7%), and insufficient knowledge (35.0%). A strong interest in structured AI training was expressed by 81% of participants. Although responses were obtained from multiple countries, the majority of participants were based in Turkey, and the findings should be interpreted accordingly.Conclusion:Pediatric urologists demonstrate substantial engagement with AI in academic work, while clinical integration is still limited. The findings highlight a strong demand for AI education and emphasize the need for regulatory clarity, ethical frameworks, and validated tools to enable safe and effective use of AI in pediatric urology.

ObjectiveMixed‐methods research is valuable in health care to gain insights into patient perceptions. However, analyzing textual data from interviews can be time‐consuming and require multiple analysts for investigator triangulation. This study aims to explore a novel approach to investigator triangulation in mixed‐methods research by employing a large language model (LLM) for analyzing data from patient interviews.MethodsThis study compared the thematic analysis and survey generation performed by human investigators and ChatGPT‐4, which uses GPT‐4 as its backbone model, using data from an existing study that explored patient perceptions of barriers to arthroplasty. The human‐ and ChatGPT‐4–generated themes and surveys were compared and evaluated based on their representation of salient themes from a predetermined topic guide.ResultsChatGPT‐4 generated analogous dominant themes and a comprehensive corresponding survey as the human investigators but in significantly less time. The survey questions generated by ChatGPT‐4 were less precise than those developed by human investigators. The mixed‐methods flowchart proposes integrating LLMs and human investigators as a supplementary tool for the preliminary thematic analysis of qualitative data and survey generation.ConclusionBy utilizing a combination of LLMs and human investigators through investigator triangulation, researchers may be able to conduct more efficient mixed‐methods research to better understand patient perspectives. Ethical and qualitative implications of using LLMs should be considered.

Large language models (LLMs) have the potential to address social and behavioral determinants of health by transforming labor intensive workflows in resource-constrained settings. Creating LLM-based applications that serve the needs of underserved communities requires a deep understanding of their local context, but it is often the case that neither LLMs nor their developers possess this local expertise, and the experts in these communities often face severe time/resource constraints. This creates a disconnect: how can one engage in meaningful co-design of an LLM-based application for an under-resourced community when the communication channel between the LLM developer and domain expert is constrained? We explored this question through a real-world case study, in which our data science team sought to partner with social workers at a safety net hospital to build an LLM application that summarizes patients' social needs. Whereas prior works focus on the challenge of prompt tuning, we found that the most critical challenge in this setting is the careful and precise specification of *what* information to surface to providers so that the LLM application is accurate, comprehensive, and verifiable. Here we present a novel co-design framework for settings with limited access to domain experts, in which the summary generation task is first decomposed into individually-optimizable attributes and then each attribute is efficiently refined and validated through a multi-tier cascading approach.

Large language models (LLMs) are increasingly used by retail traders to interpret information and design complex strategies, yet existing adoption constructs do not capture the decision-time experience of being cognitively scaffolded by an LLM. We define Perceived Cognitive Assistance (PCA) as the trader’s felt expansion of cognitive capability at the moment of trading decision when an LLM is available, and we report initial content validation of a PCA item pool. Study 1 specified the PCA content domain using a two-tier qualitative corpus (8 interviews and 44 YouTube narratives on LLM-assisted trading, plus 24 qualitative and mixed-method studies on robo-advice and social trading). Reflexive thematic analysis yielded five facilitative assistance facets and one adjacent risk facet (over-reliance), and these were translated into a 16-item PCA pool. Study 2 used a naïve-judge sort-and-rate task with 48 retail traders to test whether items show definitional correspondence to PCA and definitional distinctiveness from similar constructs: perceived usefulness, perceived ease of use, trust in the LLM, and trading self-efficacy. The resulting 9 item set is ready for subsequent factor-analytic and predictive validation. This study advances our understanding of how large language models shape retail trading behaviour by identifying and empirically grounding Perceived Cognitive Assistance as the decision-time psychological experience through which LLMs cognitively scaffold traders, clarifying how LLM use differs from generic technology adoption, trust, or self-efficacy effects.

Large Language Models (LLMs) are rapidly revolutionizing scientific research. These tools, powered by LLMs, are not just assistants for tasks such as literature synthesis, hypothesis generation, pattern identification, and research paper writing, but are evolving into autonomous discovery systems. This review explores the capabilities of these 'AI Scientists' and compares leading entities like Sakana AI's autonomous system and Google's collaborative 'AI co-scientist'. While these advancements promise unprecedented acceleration of scientific progress, they also bring significant ethical challenges, such as bias amplification, reproducibility, transparency, authorship, and equity. By identifying current limitations and analyzing these challenges, we aim to ensure the responsible use of AI in scientific discovery.

This study investigates how large language models (LLMs) can support informal learning in social reading environments. Focusing on critical thinking, collaborative knowledge construction, and group learning, it adopts a stage-based co-design approach grounded in an informal learning cycle. Two participatory design workshops were conducted with social readers, LLM experts, and interaction designers. Participants used first-person narratives and shared tasks to envision LLM-assisted learning processes. Thematic and visual analyses revealed three key design principles: stage-specific intervention, bidirectional prompting, and balancing individual autonomy with collaborative engagement. Building on these findings, we propose a conceptual design model illustrating how LLMs can facilitate social learning in future reading platforms. The study contributes to HCI by expanding the theoretical application of informal learning with LLMs, introducing a novel participatory method, and offering actionable insights for the development of AI-mediated social reading tools.

Purpose With the democratization of access to artificial intelligence (AI) via large language models, questions about AI ethics in education are at the forefront of educational policymaking. This paper aims to understand how US universities address AI ethics in education, particularly in coursework, research and academic integrity. Design/methodology/approach This research empirically evaluates emerging AI policies at 170 US universities via a hybrid content analysis approach that applied both inductive and thematic analysis. The deductive analysis is applied to identify the structures of strategies, norms and rules based on established institutional theory. Findings This study identified many diverse strategies, with fewer emergent norms and scant rules, along with a pattern that suggests those universities with both undergraduate teaching and research excellence lead the way in setting boundaries and articulating expectations and consequences for misuse of AI in higher education. Originality/value Using thematic and structured content analysis, this study identifies policy concerns, institutional frameworks and emerging norms related to AI use in US higher education. The study also highlights universities’ concerns and intervention strategies, while providing policy recommendations based on identified trends and best practices.

Large Language Models (LLMs) have gained attention in research and industry, aiming to streamline processes and enhance text analysis performance. Thematic Analysis (TA), a prevalent qualitative method for analyzing interview content, often requires at least two human experts to review and analyze data. This study demonstrates the feasibility of LLM-Assisted Thematic Analysis (LATA) using GPT-4 and Gemini. Specifically, we conducted semi-structured interviews with 14 researchers to gather insights on their experiences generating and analyzing Online Social Network (OSN) communications datasets. Following Braun and Clarke's six-phase TA framework with an inductive approach, we initially analyzed our interview transcripts with human experts. Subsequently, we iteratively designed prompts to guide LLMs through a similar process. We compare and discuss the manually analyzed outcomes with responses generated by LLMs and achieve a cosine similarity score up to 0.76, demonstrating a promising prospect for LATA. Additionally, the study delves into researchers' experiences navigating the complexities of collecting and analyzing OSN data, offering recommendations for future research and application designers.

Large language models (LLMs) are increasingly used to provide health-related information, yet their clinical reliability remains uncertain. This study aimed to evaluate the accuracy, comprehensiveness, and readability of AI-based LLMs in providing evidence-based guidance on early maxillary expansion for children in the primary and mixed dentition phases, assessing their potential as trustworthy resources for parental decision-making. Eight LLMs (DeepSeek V3, Gemini 2.5 Flash, Claude 4.5 Sonnet, MediSearch, Copilot, GPT-5, GPT-4o, and Grok) were tasked with responding to a total of 20 questions reflecting common parental concerns about early maxillary expansion, with 10 questions assigned to each dentition phase (primary and mixed). Responses were evaluated for accuracy and comprehensiveness, and readability was assessed using the Flesch Reading Ease Score (FRES) and Flesch-Kincaid Grade Level (FKGL). Statistical analyses included descriptive statistics and appropriate parametric and non-parametric tests based on data distribution, with significance set at p < 0.05. Significant differences were observed among the LLMs in terms of accuracy, comprehensiveness, and readability (p < 0.001). DeepSeek V3 and Grok achieved the highest scores for both accuracy and comprehensiveness across both dentition phases, with DeepSeek V3 also demonstrating the highest readability in the mixed dentition phase. Copilot, GPT-5, and GPT-4o produced the most readable outputs, as indicated by their highest FRES and lowest FKGL scores, though their content accuracy was comparatively lower. In contrast, MediSearch, Gemini 2.5 Flash, and Claude 4.5 Sonnet showed consistently weaker performance across all evaluated criteria. This study concluded that, although some LLMs can offer reliable and understandable information about early maxillary expansion, none consistently excel across all evaluated criteria. In healthcare contexts, integrating scientific accuracy with readability is crucial for supporting informed parental decision-making, enhancing overall health literacy, and strengthening patient–clinician communication. These findings highlight that AI-based LLMs should serve as supplementary tools that support, rather than replace, professional orthodontic guidance.

BackgroundThis study evaluated the feasibility of ChatGPT and Gemini, two off-the-shelf large language models (LLMs), to automate causality assessments, focusing on Adverse Events Following Immunizations (AEFIs) of myocarditis and pericarditis related to COVID-19 vaccines.MethodsWe assessed 150 COVID-19-related cases of myocarditis and pericarditis reported to the Vaccine Adverse Event Reporting System (VAERS) in the United States of America (USA). Both LLMs and human experts conducted the World Health Organization (WHO) algorithm for vaccine causality assessments, and inter-rater agreement was measured using percentage agreement. Adherence to the WHO algorithm was evaluated by comparing LLM responses to the expected sequence of the algorithm. Statistical analyses, including descriptive statistics and Random Forest modeling, explored case complexity (e.g., string length measurements) and factors affecting LLM performance and adherence.ResultsChatGPT showed higher adherence to the WHO algorithm (34%) compared to Gemini (7%) and had moderate agreement (71%) with human experts, whereas Gemini had fair agreement (53%). Both LLMs often failed to recognize listed AEFIs, with ChatGPT and Gemini incorrectly identifying 6.7% and 13.3% of AEFIs, respectively. ChatGPT showed inconsistencies in 8.0% of cases and Gemini in 46.7%. For ChatGPT, adherence to the algorithm was associated with lower string complexity in prompt sections. The random forest analysis achieved an accuracy of 55% (95% confidence interval: 35.7–73.5) for predicting adherence to the WHO algorithm for ChatGPT.ConclusionNotable limitations of ChatGPT and Gemini have been identified in their use for aiding causality assessments in vaccine safety. ChatGPT performed better, with higher adherence and agreement with human experts. In the investigated scenario, both models are better suited as complementary tools to human expertise.Supplementary InformationThe online version contains supplementary material available at 10.1007/s40264-025-01531-y.