Artificial Intelligence Platform Demonstrates High Adherence in Patients Receiving Fixed-Dose Ledipasvir and Sofosbuvir: A Pilot Study

OBJECTIVE: This study aims to assess the accuracy and clinical utility of artificial intelligence (AI) platforms in responding to questions related to penile fracture, a rare but urgent urological emergency. MATERIAL and METHODS: Twenty-five questions addressing key clinical aspects of penile fracture were submitted to four AI platforms: ChatGPT, Copilot, Gemini, and Perplexity. Two expert urologists evaluated each response across five domains –relevance, clarity, structure, utility, and factual accuracy– using a 5-point Likert scale. Inter-rater reliability was assessed using the intraclass correlation coefficient (ICC), and statistical comparisons were made using one-way ANOVA and Tukey’s post-hoc tests. RESULTS: Copilot and ChatGPT scored highest overall, with mean scores of 4.90 and 4.89 respectively, while Perplexity scored significantly lower (4.68; p <0.001). Copilot also achieved the highest ratings in clarity and factual accuracy. Inter-rater reliability was high, and dimensional analysis confirmed the consistent superiority of Copilot and ChatGPT in clinical relevance and clarity. CONCLUSION: While AI platforms –especially Copilot and ChatGPT– show promise in generating medically relevant content about penile fracture, limitations in factual accuracy and clinical specificity remain. Caution is advised in using these tools in urgent care settings without professional oversight. Keywords: artificial intelligence, clinical accuracy, emergency medicine, large language models, penile fracture, urology

Artificial intelligence in pediatric otorhinolaryngology: Assessing readability, understandability, and actionability of postoperative instructions.

BackgroundThere has been a resurgence of Artificial Intelligence (AI) on a global scale in recent times, resulting in the development of cutting-edge AI solutions within hospitals. However, this has also led to the creation of isolated AI solutions that are not integrated into clinical IT. To tackle this issue, a clinical Artificial Intelligence (AI) platform that handles the entire development cycle of clinical AI models and is integrated into clinical IT is required. This research investigates the integration of a clinical AI platform into the clinical IT infrastructure. This is demonstrated by outlining the stages of the AI model development cycle within the clinical IT infrastructure, illustrating the interaction between different IT system landscapes within the hospital with BPMN diagrams.MethodsInitially, a thorough analysis of the requirements is conducted to refine the necessary aspects of the clinical AI platform with consideration of the individual aspects of clinical IT. Subsequently, processes representing the entire development cycle of an AI model are identified. To facilitate the architecture of the AI platform, BPMN diagrams of all the identified processes are created. Clinical use cases are used to evaluate the processes using the FEDS framework.ResultsOur BPMN process diagrams cover the entire development cycle of a clinical AI model within the clinical IT. The processes involved are Data Selection, Data Annotation, On-site Training and Testing, and Inference, with distinctions between (Semi-Automated) Batch Inference and Real-Time Inference. Three clinical use cases were assessed to evaluate the processes and demonstrate that this approach covers a wide range of clinical AI use cases.ConclusionsThe evaluations were executed successfully, which indicate the comprehensive nature of our approach. The results have shown that different clinical AI use cases are covered by the BPMN diagrams. Our clinical AI platform is ideally suited for the local development of AI models within clinical IT. This approach provides a basis for further developments, e.g., enabling the training and deployment of an AI model across multiple sites or the integration of security- and privacy-related aspects.

Background Birth control methods (BCMs) are often underutilized or misunderstood, especially among young individuals entering their reproductive years. With the growing reliance on artificial intelligence (AI) platforms for health-related information, this study evaluates the performance of ChatGPT-4o and Google Gemini in addressing commonly asked questions about BCMs. Methods Thirty questions, derived from the American College of Obstetrics and Gynecologists (ACOG) website, were posed to both AI platforms. Questions spanned four categories: general contraception, specific contraceptive types, emergency contraception, and other topics. Responses were evaluated using a five-point rubric assessing Relevance, Completeness, and Lack of False Information (RCL). Overall scores were calculated by averaging the rubric scores. Statistical analysis, including the Wilcoxon Signed-Rank test, Friedman test, and Kruskal-Wallis test, was performed to compare metrics. Results ChatGPT-4o and Google Gemini provided high-quality responses to birth control-related queries, with overall scores averaging 4.38 ± 0.58 and 4.37 ± 0.52, respectively, both categorized as "very good" to "excellent." ChatGPT-4o demonstrated higher scores in the lack of false information, based on descriptive statistics (4.70 ± 0.60 vs. 4.47 ± 0.73), while Google Gemini outperformed in relevance, with a statistically significant difference (4.53 ± 0.57 vs. 4.30 ± 0.70, p = 0.035, large effect size). Completeness scores were comparable (p = 0.655). Statistical analyses revealed no significant differences in overall performance (p = 0.548), though Google Gemini demonstrated a potential trend of stronger performance in the "Other Topics" category. Within-model variability showed ChatGPT-4o had more pronounced differences among metrics (moderate effect size, Kendall's W = 0.357), while Google Gemini exhibited smaller variability (Kendall's W = 0.165). These findings suggest that both platforms offer reliable and complementary tools for addressing knowledge gaps in contraception, with nuanced strengths that warrant further exploration. Conclusions ChatGPT-4o and Google Gemini provided reliable and accurate responses to BCM-related queries, with slight differences in strengths. These findings underscore the potential of AI tools, in addressing public health information needs, particularly for young individuals seeking guidance on contraception. Further studies with larger datasets may elucidate nuanced differences between AI platforms.

The performance of two artificial intelligence (AI) platforms, ChatGPT 3.5 (OpenAI, California, United States) and Gemini (Google AI, California, United States) was assessed by answering 200 questions of microbiology drawn from validated sources. The questions were selected from topics such as General Microbiology, Immunology, and Microbiology Applied to Infectious Diseases. The study was conducted from December 2023 to March 2024, and the responses of the different AI platforms were compared with an answer key. Statistical analysis was performed to assess accuracy. ChatGPT 3.5 and Gemini had comparable accuracy with correct response scores of 71% and 70.5%, respectively. Their performance varied across different sections. Gemini performed better in General Microbiology and Immunology, and ChatGPT 3.5 had a better score in the Applied Microbiology section. The study's findings highlight that AI platforms such as ChatGPT and Gemini can be utilized in microbiology and medical education.The evolution and continuous updating of AI platforms are required to improve their performance.

The primary objective of the study was to evaluate and compare the effectiveness of four artificial intelligence (AI) platforms - ChatGPT, DeepSeek AI, Copilot, and Gemini - in providing solutions to common human resource (HR) challenges in corporate hospitals across India. A cross-sectional, questionnaire-based online study was conducted among 50 h professionals with over 10 years of experience across corporate hospitals in India. Ten real-world HR problem scenarios were designed and fed into the four AI platforms using a standardized prompt. The responses were anonymized, coded, and rated by participants on five criteria: accuracy, relevance, practicability, overall response, and likelihood of use. Data were analyzed using Epi Info (version 7.0) with Chi-square tests; P < 0.05 was considered significant. Among participants, 40% were male and 60% female; 50% had over 25 years of HR experience. ChatGPT and DeepSeek AI received the highest ratings for accuracy (85% and 84% "strongly agree"), relevance, and practicability, with 80%-81% indicating a high likelihood of future use. Copilot and Gemini showed moderate acceptance (55%-60% likelihood of use). There was no significant association between responses and participant gender or years of experience. AI platforms, particularly ChatGPT and DeepSeek AI, demonstrate strong potential to support HR professionals in solving routine challenges, improving efficiency, and decision-making. However, effective adoption requires training, data accuracy, and ethical safeguards to address issues such as bias and privacy.

Researchers at INFN (National Institute for Nuclear Physics) face challenges from basic to hard science use cases (e.g., big-data latest generation experiments) in many areas: High Energy Physics (HEP), Astrophysics, Quantum Computing, Genomics, etc. Machine Learning (ML) adoption is ubiquitous in these areas, requiring researchers to solve problems related to the specificity of applications (e.g., tailored models and intricate domain knowledge), but also requiring solving general infrastructure-level and ML-workflow related problems. As the demand for ML solutions continues to rise across the diverse research domains, there exists a critical need for an innovative approach to accelerate ML adoption. In this regard we introduce an Artificial Intelligence (AI) platform designed as an application-agnostic Machine Learning as a Service (MLaaS) solution. The platform provides a paradigm shift by offering a flexible and generalized infrastructure that decouples the ML development process from the specific use cases. The AI platform is implemented as a software layer on top of our cloud platform: the INFN Cloud, a dedicated, geographically distributed infrastructure which offers composable, scalable, and open-source solutions. The AI platform leverages INFN Cloud resources and principles, gathering and orchestrating technologies to support end-to-end scalable ML solutions: Kubernetes, Kubeflow, KServe, KNative, Kueue, Horovod, etc., ensuring support for several ML frameworks: TensorFlow, PyTorch, Apache MXNet, XGBoost, etc. This paper describes the platform’s design and principles, as well as some selected use cases from Natural Language Processing and HEP domains that can take advantage of the “aaS” approach.

Simulation-based medical education (SBME) is a critical training tool in healthcare, shaping learners' skills, professional identities, and inclusivity. Leadership demographics in SBME, including age, gender, race/ethnicity, and medical specialties, influence program design and learner outcomes. Artificial intelligence (AI) platforms increasingly generate demographic data, but their biases may perpetuate inequities in representation. This study evaluated the demographic profiles of simulation instructors and heads of simulation labs generated by three AI platforms-ChatGPT, Gemini, and Claude-across nine global locations. A global cross-sectional study was conducted over 5days (November 2024). Standardized English prompts were used to generate demographic profiles of simulation instructors and heads of simulation labs from ChatGPT, Gemini, and Claude. Outputs included age, gender, race/ethnicity, and medical specialty data for 2014 instructors and 1880 lab heads. Statistical analyses included ANOVA for continuous variables and chi-square tests for categorical data, with Bonferroni corrections for multiple comparisons: P significant < 0.05. Significant demographic differences were observed among AI platforms. Claude profiles depicted older heads of simulation labs (mean: 57years) compared to instructors (mean: 41years), while ChatGPT and Gemini showed smaller age gaps. Gender representation varied, with ChatGPT and Gemini generating balanced profiles, while Claude showed a male predominance (63.5%) among lab heads. ChatGPT and Gemini outputs reflected greater racial diversity, with up to 24.4% Black and 20.6% Hispanic/Latin representation, while Claude predominantly featured White profiles (47.8%). Specialty preferences also differed, with Claude favoring anesthesiology and surgery, whereas ChatGPT and Gemini offered broader interdisciplinary representation. AI-generated demographic profiles of SBME leadership reveal biases that may reinforce inequities in healthcare education. ChatGPT and Gemini demonstrated broader diversity in age, gender, and race, while Claude skewed towards older, White, and male profiles, particularly for leadership roles. Addressing these biases through ethical AI development, enhanced AI literacy, and promoting diverse leadership in SBME are essential to fostering equitable and inclusive training environments. Not applicable. This study exclusively used AI-generated synthetic data.

Artificial intelligence (AI) platforms have emerged as pivotal tools in genetics and molecular medicine, as in many other fields. The growth in patient data, identification of new diseases and phenotypes, discovery of new intracellular pathways, availability of greater sets of omics data, and the need to continuously analyse them have led to the development of new AI platforms. AI continues to weave its way into the fabric of genetics with the potential to unlock new discoveries and enhance patient care. This technology is setting the stage for breakthroughs across various domains, including dysmorphology, rare hereditary diseases, cancers, clinical microbiomics, the investigation of zoonotic diseases, omics studies in all medical disciplines. AI's role in facilitating a deeper understanding of these areas heralds a new era of personalised medicine, where treatments and diagnoses are tailored to the individual's molecular features, offering a more precise approach to combating genetic or acquired disorders. The significance of these AI platforms is growing as they assist healthcare professionals in the diagnostic and treatment processes, marking a pivotal shift towards more informed, efficient, and effective medical practice. In this review, we will explore the range of AI tools available and show how they have become vital in various sectors of genomic research supporting clinical decisions.

Aim: In the digital age, artificial intelligence (AI) platforms have gradually replaced traditional manual techniques for information retrieval. However, their effectiveness in conducting academic literature searches remains unclear, necessitating a comparative assessment. This study examined the efficacy of AI search engines (Elicit, Consensus, ChatGPT) vs. manual search for literature retrieval, focusing on the surgical management of trapeziometacarpal osteoarthritis. Methods: The study was executed per the Cochrane Handbook for Systematic Reviews and PRISMA guidelines. AI platforms were given relevant keywords and prompts, while manual searches used PubMed, Cochrane CENTRAL, Web of Science, and Scopus databases from January 1901 to April 2024. The study focused on English-language randomized controlled trials (RCTs) comparing surgical management of trapeziometacarpal osteoarthritis (TMCJ OA). Two independent evaluators screened and extracted data from the studies. Primary outcomes involved the quality and relevancy of studies chosen by both search methods, evaluated by false positive rates and number of studies, including outcomes of interest. Results: The manual search yielded the most results (6,018), followed by Elicit (4,980), Consensus (3,436), and ChatGPT (6). Elicit identified the highest number of RCTs (205) but also had the greatest false positive rate (94%). Ultimately, the manual search identified 23 suitable studies, Elicit found 10, Consensus found 9, and ChatGPT identified only 1. No additional studies were found by AI search engines that were not discovered in the manual search. Conclusion: The findings highlight the potential advantages and drawbacks of AI search engines for literature searches. While Elicit was prone to error, Consensus and ChatGPT were less comprehensive. Significant enhancements in the precision and thoroughness of AI search engines are required before they can be effectively utilized in academia.

Background Balochistan is the largest province of Pakistan by area, and the least developed. It suffers from several political, tribal and border conflicts. The distances to health facilities for the catchment population are long with limited accessibility. Immunization is one of the most cost-effective interventions to prevent deaths from vaccine preventable diseases (VPDs), especially in children. While Pakistan has an overall routine immunization coverage of 66 per cent for fully immunized children (FIC), coverage in the province of Balochistan is much lower at 29 per cent. This study aimed to assess the feasibility of introducing mHealth intervention using an artificial intelligence (AI) platform based on SMS (short-message service) and Interactive Voice Response (IVRs) to remind and persuade parents to get their children vaccinated. Methods We employed a mixed study design using both quantitative and qualitative approaches. Baseline data were collected from 1,600 eligible mothers/parents within the catchment areas of 75 basic health units (BHUs) in Quetta (provincial capital of Balochistan province), and the automated platform was instituted with SMS and IVRs from EPI (Expanded Programme on Immunization) Quetta. Daily reminders and IVRs were sent to the cell numbers in the database/records. Responses were noted on the AI platform. After a period of about two months, an end line survey of 1,203 participants was undertaken with a loss of 397 (25%) participants due to seasonal migration to warmer cities in Sindh province. For the qualitative part, three key informant interviews (KII) were conducted; two KIIs with Lady Health Supervisors and one KII with the WHO staff responsible for routine immunization. There were also three focus group discussions (FGDs). Results We found that the intervention was feasible as well as acceptable both at the community and programme management levels. The baseline indicators of immunization coverage improved significantly on end line survey (95% confidence interval, CI = 0.208-0.269; P&lt;0.001). Conclusions Our study demonstrates the potential for mHealth and AI to improve childhood immunization and addresses equity in the least developed areas of this country. The replication of the strategy in subnational immunization programmes could decrease morbidity and mortality due to VPDs.

<bold>Introduction:</bold> Artificial intelligence (AI) is increasingly applied in respiratory medicine. Its role in detecting patient–ventilator asynchronies during non-invasive ventilation (NIV) remains unclear. Asynchrony is associated with worse outcomes and NIV failure (Longini F et al, Front Med; Ghosh D et al ERJ Open Research 2017). Current identification relies on expert visual inspection, which is subjective and time-consuming. <bold>Aim.</bold> To evaluate the agreement between AI platforms and expert pulmonologists in identifying patient–ventilator asynchronies during NIV. <bold>Materials and Methods.</bold> NIV waveforms were independently analysed by two experienced pulmonologists using SOMNONIV criteria (Gonzalez-Bermejo J, et al. Thorax 2019), retaining only traces with full inter-observer agreement. Two AI platforms (Perplexity® and ChatGPT-5®) were pretrained with 10 representative waveforms and then applied to 80 validated traces using a standardized prompt. <bold>Results.</bold> AI platforms showed poor agreement with pulmonologists. ChatGPT-5® slightly outperformed Perplexity®, though performance varied by software (table 1). <bold>Conclusions.</bold> AI currently shows poor agreement with pulmonologists in detecting asynchronies during NIV. ChatGPT5® performed slightly better, but results remain inconsistent and not suitable for clinical use. <table-wrap><object-id>erjor;12/suppl_17/191/TB1</object-id><object-id>T1</object-id><object-id>TB1</object-id><caption> Table 1. Concordance in asynchrony detection. </caption><table><colgroup><col></col><col></col><col></col></colgroup><tbody><tr><td> Pulmonologist vs AI platform </td><td>Kappa (95%CI)</td><td>Global agreement</td></tr><tr><td> Perplexity® -ResScan® -Orchestrator® -Breas® </td><td> 0.11 (-0.03 – 0.25) 0.21 (-0.05 – 0.48) 0.02 (-0.13 – 0.18) -0.06 (-0.41 – 0.28) </td><td> 47.5% 60.0% 37.5% 38.5% </td></tr><tr><td> ChatGPT5® -ResScan® -Orchestrator® -Breas® </td><td> 0.13 (-0.07 – 0.32) 0.30 (0.10 – 0.50) 0.13 (-0.23 – 0.48) -0.31 (-0.81 – 0.18) </td><td> 56.2% 60.0% 62.5% 30.8% </td></tr></tbody></table></table-wrap>

Objectives: This systematic review investigates clinical and environmental outcomes associated with policy-driven digital health interventions for health promotion and disease prevention. Methods: Following PRISMA 2020 guidelines, six databases (Scopus, Web of Science, PubMed, IEEE Xplore, ScienceDirect, and MDPI) were systematically searched for empirical studies published between January 2020 and June 2025, using keywords including “digital health,” “telemedicine,” “mHealth,” “wearable,” “AI,” “environmental impact,” and “sustainability.” From 1038 unique records screened, 68 peer-reviewed studies met inclusion criteria and underwent qualitative thematic synthesis. Results: Results show digital health interventions such as telemedicine, mobile health (mHealth) apps, wearable devices, and artificial intelligence (AI) platforms improve healthcare accessibility, chronic disease management, patient adherence, and clinical efficiency. Environmentally, these interventions significantly reduce carbon emissions, hospital energy consumption, and medical waste. Conclusion: The studies lacked standardized environmental metrics and predominantly originated from high-income regions. Future research should prioritize the development of uniform sustainability indicators, broaden geographic representation, and integrate rigorous life-cycle assessments. Policymakers are encouraged to embed environmental considerations into digital health strategies to support resilient, sustainable healthcare systems globally.

BackgroundLarge bowel biopsies are one of the commonest types of biopsy specimen. We describe a service evaluation study to test the feasibility of using artificial intelligence (AI) to triage large bowel biopsies from a reporting backlog and prioritize those that require more urgent reporting. MethodsThe pathway was developed in the UK by National Health Service (NHS) laboratory staff working in a medium-sized general hospital. The AI platform was interfaced with the slide scanner software and the reporting platform’s software, so that pathologists could correct the AI label and reinforce the training set as they reported the cases. ResultsThe AI classifier achieved a sensitivity of 97.56% and specificity of 93.02% for the case-level-diagnosis of neoplasia (adenoma and adenocarcinoma) and for an AI diagnosis of any significant pathology (i.e., adenomas, adenocarcinomas, inflammation, hyperplastic polyps, and sessile serrated lesions) sensitivity was 95.65% and specificity 92.96%. The automated AI diagnostic classification pathway took approximately 175 s per slide to download and process the scanned whole slide image (WSI) and return an AI diagnostic classification. Biopsies with an AI diagnosis of neoplasia or inflammation were prioritized for reporting while the remainder followed the routine reporting pathway. The AI triaged pathway resulted in a significantly shorter reporting turnaround time for pathologist verified neoplastic cases (P < 0.001) and inflammation (P < 0.05). The project’s costs amounted to £14800, excluding laboratory staff salaries. More time and resources were spent on developing the interface between the AI platform and laboratory IT systems than on the development of the AI platform itself. ConclusionsNHS laboratory staff were able to implement an AI solution to accurately triage large bowel biopsies into several diagnostic classes and this improved reporting turnaround times for cases with neoplasia or with inflammation.

PurposeTo study the role of artificial intelligence (AI) in developing diabetic macular edema (DME) management recommendations by creating and comparing responses to clinicians in hypothetical AI-generated case scenarios. The study also examined whether its joint recommendations followed national DME management guidelines.MethodsThe AI hypothetically generated 50 ocular case scenarios from 25 patients using keywords like age, gender, type, duration and control of diabetes, visual acuity, lens status, retinopathy stage, coexisting ocular and systemic co-morbidities, and DME-related retinal imaging findings. For DME and ocular co-morbidity management, we calculated inter-rater agreements (kappa analysis) separately for clinician responses, AI-platforms, and the “majority clinician response” (the maximum number of identical clinician responses) and “majority AI-platform” (the maximum number of identical AI responses). Treatment recommendations for various situations were compared to the Indian national guidelines.ResultsFor DME management, clinicians (ĸ=0.6), AI platforms (ĸ=0.58), and the ‘majority clinician response’ and ‘majority AI response’ (ĸ=0.69) had moderate to substantial inter-rate agreement. The study showed fair to substantial agreement for ocular co-morbidity management between clinicians (ĸ=0.8), AI platforms (ĸ=0.36), and the ‘majority clinician response’ and ‘majority AI response’ (ĸ=0.49). Many of the current study’s recommendations and national clinical guidelines agreed and disagreed. When treating center-involving DME with very good visual acuity, lattice degeneration, renal disease, anaemia, and a recent history of cardiovascular disease, there were clear disagreements.ConclusionFor the first time, this study recommends DME management using large language model-based generative AI. The study’s findings could guide in revising the global DME management guidelines.