Luis Ramos-Ruperto

Background: Bacterial sexually transmitted infections (bSTIs) are frequent among men who have sex with men (MSM) with HIV or using pre-exposure prophylaxis (PrEP). Prospective comparisons within the same healthcare system are limited. Methods: We conducted a prospective multicenter study in Madrid (2022–2024), with 12-month follow-up and semiannual screening for MSM with HIV and quarterly screening for PrEP users. Associations with incident bSTIs were assessed using Poisson regression with robust standard errors and multiple imputation. Monthly condomless anal intercourse (CLAI) partner count was modeled using a restricted cubic spline. Results: Among 1,372 participants (733 with HIV and 639 using PrEP), 39.0% had ≥1 bSTI at baseline or during follow-up. Baseline prevalence was 16.8% and 19.7%, respectively. Incidence rates per 100 person-years among MSM with HIV versus PrEP users were 14.9 versus 21.4 for gonorrhea, 10.9 versus 15.9 for chlamydia, and 11.6 versus 9.4 for syphilis. Relative to one CLAI partner/month, adjusted incidence rate ratios (IRRs) were 0.81, 1.18, 1.42, and 1.53 for zero, two, four, and eight partners, respectively (P for nonlinearity=0.001). Chemsex (adjusted IRR, 1.33; 95% CI, 1.05–1.70) and screening rate (adjusted IRR per additional visit/year, 1.15; 95% CI, 1.04–1.27) were associated with higher incidence; older age and being born in Spain were associated with lower incidence. Conclusions: bSTIs were frequent in both groups. Higher CLAI partner counts, chemsex, and higher screening rates were independently associated with higher detected STI incidence, while no independent association with study group was identified.

Objectives: To gain a better understanding of PrEP‐users' preference for long‐acting vs. oral PrEP formulation. Methods: From April 2023 to January 2024, participants who were prescribed PrEP completed an anonymous, structured, self‐administered, cross‐sectional survey as part of their routine PrEP care in a hospital setting in Madrid, Spain. Inclusion criteria were attendance at the clinic for PrEP care and the ability to understand the Spanish language. Eligibility was not restricted by age. A convenience sample of 200 participants was used. The ethics committee approved a waiver of written consent. Descriptive statistics and chi‐square tests were used to analyse the data. Results: A sample of 201 participants completed the survey, of which 193 (96.5%) were male and most were 30–39 years old (48.8%). The response rate was estimated to be more than 90%. Among participants, 74.9% preferred LA‐PrEP (53.9% preferred a subcutaneous (SC) injection every 6 months and 21.0% preferred an intramuscular (IM) injection every 2 months). Participants reported that LA‐PrEP is more practical, indicating fewer visits to the clinic as a primary reason (67.4%). 29.4% of participants were aware of IM LA‐PrEP, 10.0% of SC LA‐PrEP and 10.4% were familiar with both. Respondents who selected LA‐PrEP were more often under 40 years of age ( p = 0.016) compared to those who preferred oral PrEP (73.7% vs. 61.2%, respectively). Limitations included the use of a cross‐sectional design, a homogeneous sample and the use of one study location, among others. Conclusion: LA‐PrEP is the preferred form of PrEP for the majority of respondents.

Background: Health research that uses predictive and generative artificial intelligence (AI) is rapidly growing. As in traditional clinical studies, the way in which AI studies are conducted can introduce systematic errors. The translation of this AI evidence into clinical practice and research needs critical appraisal tools for clinical decision-makers and researchers. Objective: This study aimed to identify existing tools for the critical appraisal of clinical studies that use AI and to examine the concepts and domains these tools explore. The research question was framed using the Population-Concept-Context (PCC) framework. Population (P): AI clinical studies; Concept (C): tools for critical appraisal and associated constructs such as quality, reporting, validity, risk of bias, and applicability; and context (C): clinical practice. In addition, studies on bias classification and chatbot assessment were included. Methods: We searched medical and engineering databases (MEDLINE, Embase, CINAHL, PsycINFO, and IEEE) from inception to April 2024. We included clinical primary research with tools for critical appraisal. Classical reviews and systematic reviews were included in the first phase of screening and excluded in the secondary phase after identifying new tools by forward snowballing. We excluded nonhuman, computer, and mathematical research, and letters, opinion papers, and editorials. We used Rayyan (Qatar Computing Research Institute) for screening. Data extraction was done by two reviewers, and discrepancies were resolved through discussion. The protocol was previously registered in Open Science Framework . We adhered to the PRISMA-ScR (Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews) and the PRISMA-S (PRISMA-Search) extension for reporting literature in systematic reviews. Results: We retrieved 4393 unique records for screening. After excluding 3803 records, 119 were selected for full-text screening. From these, 59 were excluded. After inclusion of 10 studies via other methods, a total of 70 records were finally included. We found 46 tools (26 guides for reporting AI studies, 16 tools for critical appraisal, 2 for study quality, and 2 for risk of bias). Nine papers focused on bias classification or mitigation. We found 15 chatbot assessment studies or systematic reviews of chatbot studies (6 and 9, respectively), which are a very heterogeneous group. Conclusions: The results picture a landscape of evidence tools where reporting tools predominate, followed by critical appraisal, and a few tools for risk of bias. The mismatch of bias in AI and epidemiology should be considered for critical appraisal, especially regarding fairness and bias mitigation in AI. Finally, chatbot assessment studies represent a vast and evolving field in which progress in design, reporting, and critical appraisal is necessary and urgent.

Background: Ongoing high-risk behaviors continue to fuel HCV transmission among men who have sex with men (MSM), challenging elimination efforts. We studied HCV epidemiology in MSM with HIV (MSM-WH) and without HIV in the region of Madrid. Methods: This prospective study (2022–2024) enrolled MSM-WH from 10 centers and MSM on PrEP from an STI clinic. Visits were scheduled at baseline, 3, 6, 9, and 12 months (PrEP group), or baseline, 6, and 12 months (HIV group). Assessments included liver enzymes, HCV serology, HCV-RNA, and STI screening (syphilis, chlamydia, and gonorrhea by PCR). Results: A total of 1372 MSM (733 with HIV; 639 on PrEP) were enrolled. Baseline HCV prevalence was 1.68%, significantly higher in those with prior HCV exposure (5.60% vs 0.72%; prevalence ratio: 7.72, 95% CI: 3.31–18.03). Over 1240.4 person-years (PY) of follow-up, overall HCV incidence was 1.45/100 PY. Primary infection incidence was 0.79/100 PY: 0.94 in PrEP users versus 0.65 in MSM-WH (IRR: 1.44, 95% CI: .24–9.80). Reinfection incidence was 4.32/100 PY overall: 12.90 in PrEP users and 4.05 in MSM-WH (IRR: 3.21, 95% CI: .07–22.53). Two participants experienced within study reinfection (8.7/100 PY, 95% CI: 1.05–31.4). Slamsex and condomless receptive anal intercourse with ≥4 partners were independently associated with HCV infection and reinfection. Conclusions: MSM with prior HCV exposure had markedly higher HCV prevalence and incidence, regardless of HIV status. Risky sexual behaviors remain key drivers of HCV transmission. Behavior-informed prevention strategies are critical to sustain elimination efforts in MSM populations.

Background: AI is increasingly used in clinical research, generating a growing need for robust critical appraisal tools to evaluate methodological quality, reporting standards, and potential biases. While traditional instruments exist for conventional clinical studies, specific tools designed for AI-based research are still emerging. Objective: This dataset accompanies a scoping review that aimed to identify and describe existing critical appraisal tools, reporting frameworks, and bias classification systems applicable to clinical studies using AI, including chatbot-based interventions. Methods: We systematically searched MEDLINE, Embase, CINAHL, PsycINFO, and IEEE Xplore from inception to April 2024. Eligible studies included those proposing or using tools for critical appraisal, reporting, quality assessment, or risk of bias in AI-related clinical research. Screening and extraction followed JBI and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) recommendations. Data extraction combined human review with a supervised GPT-4o–based retrieval-augmented generation (RAG) process to enhance transparency and reproducibility. All AI-assisted outputs were verified independently by two reviewers. Results: Seventy records were included: 46 reporting guidelines (comprising 26 guides for reporting AI studies, 16 critical appraisal tools, 2 quality assessment instruments, and 2 risk-of-bias tools), 9 bias classification or bias mitigation studies, and 15 chatbot evaluation studies. All datasets, extraction templates, and RAG prompts are publicly available to facilitate validation and reuse. Conclusions: This dataset provides a comprehensive overview of critical appraisal and reporting tools for AI-based clinical research. It may support the development of standardized evaluation frameworks and promote transparency in future AI-assisted health studies.

BACKGROUND Health research that uses predictive and/or generative AI is rapidly growing. Just as in traditional clinical studies, the way in which AI studies are conducted can introduce systematic errors. Transmission of this AI evidence into clinical practice and research needs critical appraisal tools for clinical decision makers and researchers. We carried out a scoping review (DOI: 10.2196/preprints.77110) to identify existing tools for critical appraisal of clinical studies that use artificial intelligence (AI) and examine the concepts and domains these tools explore. The question is in PCC framework, P: (population) Artificial intelligence clinical studies. C (Concept): tools for critical appraisal and associated constructs such as quality, reporting, validity, risk of bias, and applicability. C (context): in clinical practice context. In addition, bias classification and Chatbot assessment studies were included. A total of 70 records were finally included in the review. 46 of them were reporting guidelines, 15 tools for critical appraisal, 2 for quality of study and 2 for risk of bias. Nine papers ware focused on bias classification or mitigation. We found 15 Chatbots assessment studies or systematic reviews of Chatbots studies (6 and 9 respectively) which are a very heterogeneous group. OBJECTIVE To publish the primary data used in our scoping review for public availability. METHODS We searched in medical and engineering databases (MEDLINE, EMBASE, CINAHL, PsycINFO and IEEE) from inception to April 2024. We included clinical primary research with tools for critical appraisal. Classic reviews and systematic reviews were included in first phase of screening. They were excluded in the secondary phase, after identifying new tools by forward snowballing. We excluded non-human, computer and mathematical research, and letters, opinion papers and editorials. We used Rayyan for screening. Data extraction was done by two observers and discrepancies were solved by discussion. The protocol was previously registered in OSF (https://doi.org/10.17605/OSF.IO/ETYDS). We adhered to the PRISMA extension for Scoping reviews and to the PRISMA-Search extension for Reporting Literature in Systematic Reviews. Data extraction for chatbot studies used a hybrid approach, combining the active involvement of a researcher with a fully supervised ChatGPT-RAG (Retrieval-Augmented Generation) model. This strategy was adopted given the predictable heterogeneity of chatbot interventions, with the aim of enhancing the clarity and reproducibility of extracted data. ChatGPT-4o was employed to assist in drafting and refining the extraction tables, but all outputs were independently reviewed by two authors against the original articles. Discrepancies were reviewed and resolved through consensus. No sensitive data was exposed. To promote transparency and reproducibility the exact prompts used in the RAG process are incorporated into this data set. As an example to explain the process: the systematic review RAG (in Spanish) was used for the data extraction of Oh 2021. A PDF was uploaded to ChatGPT-4o and the output is shown in the PDF file (example of ChatGPT output in a paper). The result was incorporated as a column in the XLS Rev_sis extraction, (it may be seen in the H column). This procedure was repeated for all the articles both in systematic reviews and primary research (Rev_sis extraction and Primary studies extraction). Both XLS were tansposed from columns to rows to build the final xls (S reviews table draft and Primary studies table draft). The result was translated from Spanish to English by the reviewers. Both table drafts were supervised and compared to the actual papers by LLR afterwards verified by JCB. The final tables were synthetised as shown in the scoping review, where they appear as table 4 and 5. RESULTS We identified 4392 records in databases and registries. After eliminating 470 duplicates, 3922 records were screened by title and abstract and 3803 were excluded. The remaining 119 underwent full-text screening and 59 were excluded. The reasons for exclusion were: 50 were systematic reviews; 7 studies met the exclusion criteria; and 2 did not meet the inclusion criteria. Full details are available in supplementary material (Exclusions after full-text screening.) Of the 50 systematic reviews, 42 used specific AI tools to assess quality of the studies and the tools retrieved were incorporated into “Records identified via other methods”). Twelve studies were identified in the Equator-network library, and four additional studies were obtained from experts and organizations, therefore, there were 58 records identified via other methods. Forty-eight of these were already captured in the 60 included studies from the search of electronic databases, leaving 10 additional studies to be included. Thus, a total of 70 studies were included in this review. CONCLUSIONS This data set may be useful for other researchers who may want to corroborate or further develop our results on critical appraisal tools for artificial intelligence clinical studies. Conflict of Interest: All authors declare no conflict of interest. Funding: No funding was received for this research Multimedia Appendix: IRB approval was not applicable in this study and dataset. The scoping review built on this data set has been accepted for publication in the Journal of Medical Internet Research. We enclose the following files: GPT-RAG (prompting) TEMPLATE ENGLISH GPT-RAG (prompting) TEMPLATE PDF Example XLS CA Tools & Bias 10 10 2025 Chatbot 10 10 2025

BACKGROUND Health research that uses predictive and/or generative AI is rapidly growing. Just as in traditional clinical studies, the way in which AI studies are conducted can introduce systematic errors. Transmission of this AI evidence into clinical practice and research needs critical appraisal tools for clinical decision makers and researchers. OBJECTIVE To identify existing tools for critical appraisal of clinical studies that use artificial intelligence (AI) and examine the concepts and domains these tools explore. METHODS Inclusion criteria in PCC framework P: (population) Artificial intelligence clinical studies. C (Concept): tools for critical appraisal and associated constructs such as: quality, reporting, validity, risk of bias, and applicability. C (context): in clinical practice context. In addition, bias classification and Chatbot assessment studies were included. We searched in medical and engineering databases (MEDLINE, EMBASE, CINAHL, PsycINFO and IEEE). We included clinical primary research with tools for critical appraisal. Classic reviews and systematic reviews were included in first phase of screening. They were excluded in the secondary phase, after identifying new tools by forward snowballing. We excluded non-human, computer and mathematical research, and letters, opinion papers and editorials. We used Rayyan for screening. Data extraction was done by two observers and discrepancies were solved by discussion. The protocol was previously registered in OSF (https://doi.org/10.17605/OSF.IO/ETYDS). We adhered to the PRISMA extension for Scoping reviews and to the PRISMA-Search extension for Reporting Literature in Systematic Reviews. RESULTS We retrieved 4393 unique records for screening. After excluding 3803 records, 119 were selected for full-text screening. From these, 59 were excluded. After inclusion of 10 studies via other methods, a total of 70 records were finally included. 46 of them were reporting guidelines (15 tools for critical appraisal, 2 for quality of study and 2 for risk of bias). Nine papers ware focused on bias classification or mitigation. We found 15 Chatbots assessment studies or systematic reviews of Chatbots studies (6 and 9 respectively) which are a very heterogeneous group. CONCLUSIONS The results picture a landscape of the evidence tools where reporting tools predominate, followed by critical appraisal and risk of bias tools, and few tools for risk of bias. The mismatch of bias in AI and epidemiology should be considered for critical appraisal, especially regarding fairness and the mitigation bias in the AI. Finally, Chatbot assessment studies is a vast and evolving field in which progress in design, reporting and critical appraisal is necessary and urgent. CLINICALTRIAL https://doi.org/10.17605/OSF.IO/ETYDS

Background: We previously described the effectiveness of bictegravir/emtricitabine/tenofovir alafenamide (B/F/TAF) as a switch strategy in real life in people with HIV (PWH) at 48 weeks. We did not find that previous nucleoside reverse transcriptase inhibitor (NRTI) resistance-associated mutations (RAMs) had an impact on efficacy. Herein we report response rates after 3 years of follow-up. Methods: This retrospective review comprised PWH who were treatment experienced and switched to B/F/TAF in a single-center cohort. HIV RNA <50 copies/mL was analyzed at 96 and 144 weeks in an intention-to-treat analysis (missing = failure) and per-protocol analysis; patients with missing data or changes for reasons other than virologic failure were excluded. Results: An overall 506 PWH were included: 16.2% were women, the median age was 52.3 years, the median time of HIV infection was 18.9 years, and 13.6% had documented preexisting NRTI RAMs. At 96 weeks of follow-up in the intention-to-treat and per-protocol analyses, HIV RNA <50 copies/mL was seen in 73.1% and 95.4%, respectively. At 144 weeks, these figures were 68.2% and 94%. There were no statistically significant differences between patients with and without previous NRTI RAMs. A total of 140 patients were excluded for the per-protocol analysis at week 144: 46 were lost to follow-up, 32 discontinued treatment due to toxicity, 34 simplified to dual antiretroviral therapy, 7 switched for other reasons, and 20 patients died (no death was B/F/TAF related). Conclusions: Through 3 years of follow-up, switching to B/F/TAF maintained high rates of virologic suppression in long-term PWH. These results were seen even in patients with preexisting NRTI RAMs.

Background: Studies on switching to tenofovir alafenamide (TAF)‐based regimens raise concerns about a worse metabolic profile in people with HIV, even though most received tenofovir disoproxil fumarate (TDF) in their previous regimen. This study aims to evaluate changes in lipid fractions, glucose, and serum markers for hepatic steatosis (HS) after switching from a TDF‐ or TAF‐sparing regimen to bictegravir/emtricitabine/TAF (B/F/TAF).Methods: We performed a retrospective cohort study of people with HIV who switched to B/F/TAF from TDF‐ or TAF‐sparing regimens between January 2019 and May 2022 with at least 6 months of follow‐up. The primary endpoint was the absolute change in lipid fractions at 6 months. Secondary outcomes were changes in lipid fractions at 12 months and changes in other metabolic parameters (glucose, creatinine, and HS based on the triglyceride‐to‐glucose [TyG] ratio at 6 and 12 months). Changes were analysed using mixed linear regression models with random intercept and time as a fixed effect.Results: The study included 259 people with HIV (median age 55 [interquartile range (IQR) 47–60] years; 80% male; 88% Caucasian; CD4+ T‐cell count 675 [IQR 450–880] cells/mm³; 84.3% HIV‐RNA p = 0.002]), triglycerides (−23.4 [95% CI −42.07 to −4.65]; p = 0.003), and TyG ratio (−0.14 [95% CI −0.23 to −0.05]; p < 0.001).Conclusion: In our real‐life cohort, the effect of switching TDF‐/TAF‐sparing regimens to triple therapy with B/F/TAF improved total cholesterol, triglycerides, and serum markers of HS at 6 months and was neutral for the remaining metabolic parameters at 12 months.