Evaluation of artificial intelligence-powered screening for sexually transmitted infections-related skin lesions using clinical images and metadata.

BACKGROUND: Sexually transmitted infections (STIs) pose a significant global public health challenge. Early diagnosis and treatment reduce STI transmission, but rely on recognising symptoms and care-seeking behaviour of the individual. Digital health software that distinguishes STI skin conditions could improve health-seeking behaviour. We developed and evaluated a deep learning model to differentiate STIs from non-STIs based on clinical images and symptoms. METHODS: We used 4913 clinical images of genital lesions and metadata from the Melbourne Sexual Health Centre collected during 2010-2023. We developed two binary classification models to distinguish STIs from non-STIs: (1) a convolutional neural network (CNN) using images only and (2) an integrated model combining both CNN and fully connected neural network (FCN) using images and metadata. We evaluated the model performance by the area under the ROC curve (AUC) and assessed metadata contributions to the Image-only model. RESULTS: Our study included 1583 STI and 3330 non-STI images. Common STI diagnoses were syphilis (34.6%), genital warts (24.5%) and herpes (19.4%), while most non-STIs (80.3%) were conditions such as dermatitis, lichen sclerosis and balanitis. In both STI and non-STI groups, the most frequently observed groups were 25-34 years (48.6% and 38.2%, respectively) and heterosexual males (60.3% and 45.9%, respectively). The Image-only model showed a reasonable performance with an AUC of 0.859 (SD 0.013). The Image + Metadata model achieved a significantly higher AUC of 0.893 (SD 0.018) compared to the Image-only model (p < 0.01). Out of 21 metadata, the integration of demographic and dermatological metadata led to the most significant improvement in model performance, increasing AUC by 6.7% compared to the baseline Image-only model. CONCLUSIONS: The Image + Metadata model outperformed the Image-only model in distinguishing STIs from other skin conditions. Using it as a screening tool in a clinical setting may require further development and evaluation with larger datasets.

A typology of HIV self-testing support systems: a scoping review.

To maximise the benefits of HIV self-testing (HIVST), it is critical to support self-testers in the testing process and ensure that they access appropriate prevention and care. To summarise systems and tools supporting HIVST (hereafter, 'support systems') and categorise them for future analysis, we synthesised the global data on HIVST support systems and proposed a typology. We searched five databases for articles reporting on one or more HIVST support systems and included 314 publications from 224 studies. Across 189 studies, there were 539 reports of systems supporting HIVST use; while across 115 studies, there were 171 reports of systems supporting result interpretation. Most commonly, these were pictorial instructions, followed by in-person demonstrations and in-person assistance while self-testing or reading self-test results. Less commonly, virtual interventions were also identified, including online video conferencing and smartphone apps. Smartphone-based automated result readers have been used in the USA, China, and South Africa. Across 173 studies, there were 987 reports of systems supporting post-test linkage to care; most commonly, these were in-person referrals/counselling, written referrals, and phone helplines. In the USA, Bluetooth beacons have been trialled to monitor self-test use and facilitate follow-up. We found that, globally, HIVST support systems use a range of methods, including static media, virtual tools, and in-person engagement. In-person and printed approaches were more common than virtual tools. Other considerations, such as linguistic and cultural appropriateness, may also be important in the development of effective HIVST programs.

Cost-effectiveness of resistance-guided therapy for Mycoplasma genitalium in Australia.

The recommended first-line treatment for Mycoplasma genitalium infections is azithromycin. However, the prevalence of macrolide resistance for M. genitalium has increased to more than 50% worldwide. In 2013, Australia introduced a resistance-guided therapy (RGT) strategy to manage M. genitalium infections. This study assesses the cost-effectiveness of the RGT approach compared to no RGT (i.e., without macrolide resistance profile test) in women, men who have sex with men (MSM), and men who have sex with women (MSW) in Australia. We constructed dynamic transmission models of M. genitalium infections in women, MSM, and MSW in Australia, each with a population of 100,000. These models compared the costs and quality-adjusted life-years (QALYs) gained between RGT and no RGT scenarios from a healthcare perspective over ten years. All costs are reported in 2022 Australian dollars (Australian $). In our model, RGT is cost saving in women and MSM, with the incremental net monetary benefit of $1.3 million and $17.9 million, respectively. In MSW, the RGT approach is not cost-effective, with an incremental cost-effectiveness ratio of -$106.96 per QALY gained. RGT is cost saving compared to no RGT for M. genitalium infections in women and MSM, supporting its adoption as the national management strategy for these two population groups.

Synergistic interaction between pay-it-forward incentives and recreational drug use on hepatitis B virus and hepatitis C virus testing among men who have sex with men in China.

OBJECTIVES: Pay-it-forward incentives effectively promote hepatitis B virus (HBV) and hepatitis C virus (HCV) testing among men who have sex with men (MSM) by offering free testing and donation opportunities. This study aims to explore the interaction between pay-it-forward incentives and recreational drug use on HBV and HCV testing uptake among Chinese MSM. METHODS: We pooled data from two pay-it-forward studies that aimed to promote dual HBV and HCV testing among MSM in Jiangsu, China. We explored factors associated with hepatitis testing uptake in the two study groups and examined the interaction between pay-it-forward incentives and recreational drug use on hepatitis testing uptake. RESULTS: Overall, 511 MSM participated in these two studies, with 265 participants in the pay-it-forward incentives group and 246 participants in the standard-of-care group. Among these participants, 59.3% in the pay-it-forward incentive group and 24.8% in the standard-of-care group received dual HBV and HCV testing, respectively. In the pay-it-forward incentives group, participants who used recreational drugs in the past 12 months (adjusted OR (AOR)=1.83, 95% CI 1.09 to 3.06) were more likely to receive dual HBV and HCV testing, compared with those who never used recreational drugs, whereas in the standard-of-care group, those who used recreational drugs were less likely to receive dual HBC and HCV testing (AOR=0.38, 95% CI 0.18 to 0.78). MSM with higher community connectedness (AOR=1.10, 95% CI 1.00 to 1.21) were also more likely to receive hepatitis testing with pay-it-forward incentives. There was a synergistic interaction on both the multiplicative (ratio of ORs=4.83, 95% CI 1.98 to 11.7) and additive scales (the relative excess risk of interaction=2.97, 95% CI 0.56 to 5.38) of pay-it-forward incentives and recreational drug use behaviours on dual HBV and HCV testing uptake among MSM. CONCLUSION: Pay-it-forward incentives may be particularly useful in promoting hepatitis testing among MSM who use recreational drugs.

Missed opportunities for guidance on sexually transmitted infection services: a global review of national HIV PrEP guidance.

OBJECTIVES: People who use or would benefit from pre-exposure prophylaxis (PrEP) for HIV infection are disproportionately affected by sexually transmitted infections (STIs). Integrating STI services when offering PrEP fosters synergies and efficiencies in response to HIV/STI and promotes people-centred care. Including guidance on STI interventions for people on PrEP may facilitate implementation and uptake. We conducted a global review of national PrEP guidance documents and analysed the inclusion of recommendations for the provision of STI services by country level of income. METHODS: We searched national PrEP guidance documents published by WHO Member States through the WHO, the Joint United Nations Programme on HIV/AIDS (UNAIDS) databases, the PrEPWatch repository and Google. Information on a range of STI-related interventions was extracted from documents available by October 2023. RESULTS: Of the 113 national PrEP guidance documents retrieved, STIs were mentioned in 77% (90/117). Viral hepatitis B testing and vaccination were recommended by most high-income countries (HICs) and low-income and middle-income countries (LMICs). Recommendation for syphilis testing was prominent in HICs (91%) and moderately noted in LMICs (68%). Gonorrhoea and chlamydia testing was recommended frequently in HICs (88%) and 42% in LMICs. However, the review noted that, to a much lesser extent, specific type of testing for these pathogens was mentioned. Recommendation for quarterly STI testing for syphilis, gonorrhoea and chlamydia was ubiquitous, while the need to offer STI partner services was rarely mentioned. CONCLUSIONS: PrEP services offer an opportunity for improved and expanded STI services, increasing person-centred care and addressing STI epidemics alongside HIV. Our review highlights the strengths and gaps in incorporating critical STI interventions into national PrEP normative guidance. Addressing these gaps through a stepwise approach and increasing targeted testing and partner services can help improve quality of care and support an effective response to HIV and other STIs.

Development of a Mindfulness-Based Intervention for Narcolepsy: A Feasibility Study.

STUDY OBJECTIVES: Mindfulness-based interventions (MBI) have been shown to improve psychosocial functioning in medical populations but have not been studied in narcolepsy. This study examined the feasibility and acceptability of an MBI that was adapted for narcolepsy, including three variations in program length. METHODS: Adults with narcolepsy (N = 60) were randomized to MBI groups of varying durations: brief (4 weeks), standard (8 weeks), or extended (12 weeks). Participants completed assessments at baseline, 4 weeks, 8 weeks, and 12 weeks. To assess feasibility and acceptability, primary outcomes included attendance, meditation practice, and data completeness. Additionally, participants completed measures of mindfulness, self-compassion, mood, sleep, psychosocial functioning, and cognition. An effect size of Cohen's d ≥ 0.5 was used as the pre-specified benchmark for a minimal clinically important difference (MCID). RESULTS: The attendance, meditation, and data completeness benchmarks were met by 71.7%, 61.7%, and 78.3% of participants, respectively. Higher proportions of the brief and extended groups met these benchmarks compared to the standard group. All groups met the MCID for mindfulness, self-compassion, self-efficacy for managing emotions, positive psychosocial impact, global mental health, and fatigue. Standard and extended groups met the MCID for anxiety and depression, and extended group met the MCID for additional measures including social and cognitive functioning, daytime sleepiness, hypersomnia symptoms, and hypersomnia-related functioning. CONCLUSION: Results suggest that the remote delivery and data collection methods are feasible to employ in future clinical trials, and it appears that the extended MBI provides the most favorable clinical impact while maintaining attendance and engagement in meditation practice.

Economic evaluation alongside a clinical trial of near-to-patient testing for sexually transmitted infections.

BACKGROUND: Current clinical care for common bacterial STIs (Chlamydia trachomatis (CT), Neisseria gonorrhoeae (NG) and Mycoplasma genitalium (MG)) involves empiric antimicrobial therapy when clients are symptomatic, or if asymptomatic, waiting for laboratory testing and recall if indicated. Near-to-patient testing (NPT) can improve pathogen-specific prescribing and reduce unnecessary or inappropriate antibiotic use in treating sexually transmitted infections (STI) by providing same-day delivery of results and treatment. METHODS: We compared the economic cost of NPT to current clinic practice for managing clients with suspected proctitis, non-gonococcal urethritis (NGU), or as an STI contact, from a health provider's perspective. With a microsimulation of 1000 clients, we calculated the cost per client tested and per STI- and pathogen- detected for each testing strategy. Sensitivity analyses were conducted to assess the robustness of the main outcomes. Costs are reported as Australian dollars (2023). RESULTS: In the standard care arm, cost per client tested for proctitis, NGU in men who have sex with men (MSM) and heterosexual men were the highest at $247.96 (95% Prediction Interval (PI): 246.77-249.15), $204.23 (95% PI: 202.70-205.75) and $195.01 (95% PI: 193.81-196.21) respectively. Comparatively, in the NPT arm, it costs $162.36 (95% PI: 161.43-163.28), $158.39 (95% PI: 157.62-159.15) and $149.17 (95% PI: 148.62-149.73), respectively. Using NPT resulted in cost savings of 34.52%, 22.45% and 23.51%, respectively. Among all the testing strategies, substantial difference in cost per client tested between the standard care arm and the NPT arm was observed for contacts of CT or NG, varying from 27.37% to 35.28%. CONCLUSION: We found that NPT is cost-saving compared with standard clinical care for individuals with STI symptoms and sexual contacts of CT, NG, and MG.

Understanding Risk Factors for Oropharyngeal Gonorrhea Among Sex Workers Attending Sexual Health Clinics in 2 Australian Cities: Mixed Methods Study.

BACKGROUND: The risk factors for oropharyngeal gonorrhea have not been examined in sex workers despite the increasing prevalence of gonorrhea infection. OBJECTIVE: This study aims to determine the risk factors for oropharyngeal gonorrhea in female and gender-diverse sex workers (including cisgender and transgender women, nonbinary and gender fluid sex workers, and those with a different identity) and examine kissing, oral sex, and mouthwash practices with clients. METHODS: This mixed methods case-control study was conducted from 2018 to 2020 at 2 sexual health clinics in Melbourne, Victoria, and Sydney, New South Wales, Australia. We recruited 83 sex workers diagnosed with oropharyngeal gonorrhea (cases) and 581 sex workers without (controls). Semistructured interviews with 19 sex workers from Melbourne were conducted. RESULTS: In the case-control study, the median age of 664 sex workers was 30 (IQR 25-36) years. Almost 30% of sex workers (192/664, 28.9%) reported performing condomless fellatio on clients. Performing condomless fellatio with clients was the only behavior associated with oropharyngeal gonorrhea (adjusted odds ratio 3.6, 95% CI 1.7-7.6; P=.001). Most participants (521/664, 78.5%) used mouthwash frequently. In the qualitative study, almost all sex workers reported kissing clients due to demand and generally reported following clients' lead with regard to kissing style and duration. However, they used condoms for fellatio because they considered it a risky practice for contracting sexually transmitted infections, unlike cunnilingus without a dental dam. CONCLUSIONS: Our study shows that condomless fellatio is a risk factor for oropharyngeal gonorrhea among sex workers despite most sex workers using condoms with their clients for fellatio. Novel interventions, particularly targeting the oropharynx, will be required for oropharyngeal gonorrhea prevention.

Restarting pre-exposure prophylaxis (PrEP) for HIV: a systematic review and meta-analysis.

Background: High coverage of pre-exposure prophylaxis (PrEP) will reduce HIV transmission and help end the HIV/AIDS pandemic. However, PrEP users face challenges, including long-term adherence. The study aimed to document the proportions of individuals who restart HIV PrEP after they stop and the reasons for restarting PrEP. Methods: This study is a systematic review and meta-analysis. We systematically searched CINAHL, Embase, Emcare, Global Health, Medline, Scopus, and PsychINFO for peer-reviewed with no date restrictions. A grey literature search was conducted through Google search, a search of abstract books of AIDS conferences and the websites of WHO and UNAIDS. The data search was conducted in April 2023 and updated in February 2024. Two authors extracted data on the proportion of people who stopped and then restarted PrEP, reasons for restarting, and strategies to support people restarting PrEP. Two authors appraised the data using the Joanna Briggs Institute Appraisal Tools. We used a random-effects meta-analysis to pool estimates of restarting. We conducted meta-regression to determine potential sources of heterogeneity. This study is registered with PROSPERO, CRD42023416777. However, we deviated from our original plan as we did not identify enough studies for strategies to support restarting PrEP (primary objective). Subsequently, we revised our plan to strengthen our secondary objective to quantify the proportion of people who stopped and restarted PrEP, and explore possible reasons for its heterogeneity. Findings: Of 988 studies, 30 unique studieswere included: 27 reported the proportion restarting PrEP, and of these, 7 also reported reasons for restarting PrEP, and 3 studies reported only on the reasons for restarting PrEP. No study evaluated interventions for restarting PrEP. For the meta-analysis, we included 27 studies. Most studies were from high-income countries (17/27, 63%) or the USA (15/27, 56%). Overall, 23.8% (95% CI: 15.9-32.7, I2 = 99.8%, N = 85,683) of people who stopped PrEP restarted PrEP. There was a lower proportion of restarting in studies from middle-income countries compared to high-income countries (adjusted odds ratio (aOR) 0.6, 95% CI: 0.50-0.73, p < 0.001). There was higher restarting in studies from Africa compared to the USA (aOR 1.55, 95% CI: 1.30-1.86), heterosexual populations compared to men who have sex with men or transgender women (aOR 1.50, 95% CI: 1.25-1.81, p < 0.001) and in studies defining restarting as those who had stopped PrEP for >1 month compared to those who stopped <1 month (aOR 1.20, 95% CI: 1.06-1.36, p < 0.001). Reasons for restarting PrEP included perceived higher risk for HIV acquisition and removal of barriers to access PrEP. In terms of quality assessment, overall, both randomised controlled trials had a low risk of bias, while the observational studies used in the meta-analysis had some potential risk of bias related to not explicitly addressing potential confounders (15/25, 60%) or not describing strategies to address incomplete follow-up (24/25, 96%). Interpretation: About a quarter of people who stopped PrEP would restart, with substantial variation across countries and populations. It is important to understand the motivations and contextual factors influencing restarting PrEP and the support systems to enable restarting PrEP for those at ongoing risk. Funding: Australian National Health and Medical Research Council.

HIV self-testing knowledge, attitudes, and practices among Asian-born gay, bisexual, and other men who have sex with men in Australia: a qualitative study.

Background: Achieving virtual elimination of HIV transmission in Australia requires a combination of high treatment rates and high testing coverage among individuals at risk of acquiring HIV. HIV self-testing (HIVST) is an additional testing approach for key populations. Objective: We aimed to examine the knowledge, attitudes, and practices of HIVST among Asian-born gay, bisexual and other men who have sex with men (GBMSM). Methods: This qualitative study used semi-structured interviews of overseas-born GBMSM of Asian background in Australia. Participants were recruited from personal networks, social media platforms, snowballing, and the Melbourne Sexual Health Centre. Twenty-five participants were purposively sampled with a range of ages and previous levels of experience with HIVST. Interview transcripts were imported into Nvivo 12 for data management. Results: The age of the participants ranged from 19 to 44 years, with a median of 30 years. Most were unaware of HIVST before the interview, and only a few had ever used one. All had limited sexual health knowledge (i.e., HIV testing, PrEP) before they arrived in Australia. Upon learning about HIVST during the interview, many expressed willingness to use HIVST, but in limited circumstances, such as traveling overseas, interim testing while taking on-demand PrEP, and point-of-sex testing. Almost all were open to distributing HIVST to their casual partners or friends, especially those they knew who engaged in high-risk sexual practice (i.e., condomless anal sex) and were not engaged in sexual healthcare. About half still preferred conventional serology testing because of regular HIV testing as part of PrEP prescription and the need for testing for other sexually transmitted infections. Conclusion: HIVST may be an acceptable additional testing approach for HIV testing among Asian-born GBMSM. Peer education and secondary distribution may help raise HIVST awareness and use.

Factors associated with HIV pre-exposure prophylaxis use among Asian men who have sex with men in Sydney and Melbourne, Australia: a cross-sectional study.

Background: Asian-born MSM are a priority population as Australia aims to end HIV transmission, but they reported additional barriers to access PrEP and other HIV prevention methods. This study investigates factors associated with PrEP use among Asian MSM in Sydney and Melbourne, Australia, to inform strategies to improve PrEP uptake in this population. Methods: This was a sub-analysis of a community-based cross-sectional survey conducted from March to June 2021. We recruited participants online in Sydney and Melbourne, Australia. Univariable and multivariable logistic regression analyses were performed to identify the factors associated with PrEP use in the last six months and lifetime. Latent class analyses were used to identify subgroups of Asian MSM sharing similar characteristics related to their risk practices for HIV. Findings: Overall, 870 Asian MSM were included: 288 Oceanian-born Asian MSM and 582 Asian-born MSM. Three latent classes were identified: 1) Asian-born MSM who recently arrived in Australia with limited English, were less likely to use PrEP and at higher risk of HIV infection (e.g., had condomless anal sex with a casual sex partner in the last six months) (4.6%); 2) Asian MSM who were at lower risk of HIV infection and less likely to use PrEP (69.3%) and; 3) Asian MSM who were at substantial risk of HIV infection and more likely to use PrEP (26.1%). Compared to Oceanian-born Asian MSM, those who were born in Southeast Asia (adjusted odds ratio (aOR) = 0.5, 95% confidence interval (CI) 0.3-0.7) and South Asia (aOR = 0.4, 95% CI 0.2-0.8) were less likely to ever use PrEP. Compared to Oceanian-born Asian MSM, those who were born in Southeast Asia (aOR = 0.4, 95% CI 0.3-0.7), Northeast Asia (aOR = 0.5, 95% CI 0.3-0.8) and South Asia (aOR = 0.4, 95% CI 0.2-0.7) were less likely to use PrEP in the last six months. Interpretation: To end HIV transmission in Australia, it will be necessary to develop strategies to improve PrEP access for the significant minority of Asian-born MSM who are at substantial risk of HIV infection. Funding: EPFC and JJO are supported by an Australian National Health and Medical Research Council (NHMRC) Emerging Leadership Investigator Grant (EPFC: GNT1172873 and JJO: GNT1193955). CKF is supported by an Australian National Health and Medical Research Council (NHMRC) Leadership Investigator Grant (GNT1172900).

A Machine Learning Model for Identifying Sexual Health Influencers to Promote the Secondary Distribution of HIV Self-Testing Among Gay, Bisexual, and Other Men Who Have Sex With Men in China: Quasi-Experimental Study.

BACKGROUND: Sexual health influencers (SHIs) are individuals actively sharing sexual health information with their peers, and they play an important role in promoting HIV care services, including the secondary distribution of HIV self-testing (SD-HIVST). Previous studies used a 6-item empirical leadership scale to identify SHIs. However, this approach may be biased as it does not consider individuals' social networks. OBJECTIVE: This study used a quasi-experimental study design to evaluate how well a newly developed machine learning (ML) model identifies SHIs in promoting SD-HIVST compared to SHIs identified by a scale whose validity had been tested before. METHODS: We recruited participants from BlueD, the largest social networking app for gay men in China. Based on their responses to the baseline survey, the ML model and scale were used to identify SHIs, respectively. This study consisted of 2 rounds, differing in the upper limit of the number of HIVST kits and peer-referral links that SHIs could order and distribute (first round ≤5 and second round ≤10). Consented SHIs could order multiple HIV self-testing (HIVST) kits and generate personalized peer-referral links through a web-based platform managed by a partnered gay-friendly community-based organization. SHIs were encouraged to share additional kits and peer-referral links with their social contacts (defined as "alters"). SHIs would receive US $3 incentives when their corresponding alters uploaded valid photographic testing results to the same platform. Our primary outcomes included (1) the number of alters who conducted HIVST in each group and (2) the number of newly tested alters who conducted HIVST in each. We used negative binomial regression to examine group differences during the first round (February-June 2021), the second round (June-November 2021), and the combined first and second rounds, respectively. RESULTS: In January 2021, a total of 1828 men who have sex with men (MSM) completed the survey. Overall, 393 SHIs (scale=195 and ML model=198) agreed to participate in SD-HIVST. Among them, 229 SHIs (scale=116 and ML model=113) ordered HIVST on the web. Compared with the scale group, SHIs in the ML model group motivated more alters to conduct HIVST (mean difference [MD] 0.88, 95% CI 0.02-2.22; adjusted incidence risk ratio [aIRR] 1.77, 95% CI 1.07-2.95) when we combined the first and second rounds. Although the mean number of newly tested alters was slightly higher in the ML model group than in the scale group, the group difference was insignificant (MD 0.35, 95% CI -0.17 to -0.99; aIRR 1.49, 95% CI 0.74-3.02). CONCLUSIONS: Among Chinese MSM, SHIs identified by the ML model can motivate more individuals to conduct HIVST than those identified by the scale. Future research can focus on how to adapt the ML model to encourage newly tested individuals to conduct HIVST. TRIAL REGISTRATION: Chinese Clinical Trials Registry ChiCTR2000039632; https://www.chictr.org.cn/showprojEN.html?proj=63068. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1186/s12889-021-11817-2.

The use of suboptimal antiretroviral therapy when applying for migration to Australia: a case series.

Background Australia imposes restrictions for people living with HIV (PLHIV) applying for permanent residency (PR), including spending less than AUD51,000 on medical costs over 10years. Some PLHIV opted for suboptimal and cheaper antiretroviral therapy (ART) regimens to increase their chances of receiving PR. We collated a case series to examine PLHIV on suboptimal ART because of visa issues. Methods We identified all patients applying for a PR in Australia who obtained nevirapine, efavirenz or zidovudine between July 2022 and July 2023 from the Melbourne Sexual Health Centre. Pathology results and records detailing psychological issues relating to the patients' wishes to remain on suboptimal ART were extracted from clinical records by two researchers. Results We identified six patients with a mean age of 39years migrating from Asian and European countries. Three patients used efavirenz, and three used nevirapine. All desired to remain on cheaper, suboptimal ART to stay below visa cost thresholds, which they considered to aid favourably with their application. Four displayed stress and anxiety arising from visa rejections, appeal deadlines and the lengthy visa application process. Conclusions Despite access to more effective and safer ART, we identified patients who chose to remain on cheaper ART to improve chances of obtaining an Australian visa, potentially putting their health at risk. We found significant evidence of stress and anxiety among patients. There is a need to review and revise current migration policies and laws in Australia that discriminate against PLHIV and jeopardise public health.

Identifying Individuals at High Risk for HIV and Sexually Transmitted Infections With an Artificial Intelligence-Based Risk Assessment Tool.

Background: We have previously developed an artificial intelligence-based risk assessment tool to identify the individual risk of HIV and sexually transmitted infections (STIs) in a sexual health clinical setting. Based on this tool, this study aims to determine the optimal risk score thresholds to identify individuals at high risk for HIV/STIs. Methods: Using 2008-2022 data from 216 252 HIV, 227 995 syphilis, 262 599 gonorrhea, and 320 355 chlamydia consultations at a sexual health center, we applied MySTIRisk machine learning models to estimate infection risk scores. Optimal cutoffs for determining high-risk individuals were determined using Youden's index. Results: The HIV risk score cutoff for high risk was 0.56, with 86.0% sensitivity (95% CI, 82.9%-88.7%) and 65.6% specificity (95% CI, 65.4%-65.8%). Thirty-five percent of participants were classified as high risk, which accounted for 86% of HIV cases. The corresponding cutoffs were 0.49 for syphilis (sensitivity, 77.6%; 95% CI, 76.2%-78.9%; specificity, 78.1%; 95% CI, 77.9%-78.3%), 0.52 for gonorrhea (sensitivity, 78.3%; 95% CI, 77.6%-78.9%; specificity, 71.9%; 95% CI, 71.7%-72.0%), and 0.47 for chlamydia (sensitivity, 68.8%; 95% CI, 68.3%-69.4%; specificity, 63.7%; 95% CI, 63.5%-63.8%). High-risk groups identified using these thresholds accounted for 78% of syphilis, 78% of gonorrhea, and 69% of chlamydia cases. The odds of positivity were significantly higher in the high-risk group than otherwise across all infections: 11.4 (95% CI, 9.3-14.8) times for HIV, 12.3 (95% CI, 11.4-13.3) for syphilis, 9.2 (95% CI, 8.8-9.6) for gonorrhea, and 3.9 (95% CI, 3.8-4.0) for chlamydia. Conclusions: Risk scores generated by the AI-based risk assessment tool MySTIRisk, together with Youden's index, are effective in determining high-risk subgroups for HIV/STIs. The thresholds can aid targeted HIV/STI screening and prevention.

Challenges to integrating programs for the elimination of mother-to-child transmission of HIV, syphilis, and hepatitis B into antenatal care: Experiences from Indonesia.

The WHO's Asia-Pacific framework for triple elimination recommends that countries evaluate their programs for the elimination of mother-to-child transmission of HIV, syphilis, and hepatitis B (EMTCT), including identifying gaps to improve program planning and the implementation of elimination strategies in antenatal care (ANC) services. In 2022, the Indonesian Ministry of Health reported that only 39% of pregnant women were tested for HIV, 14% for syphilis, and 28% for hepatitis B, respectively. We conducted a qualitative study involving a focus group discussion (FGD) and in-depth interviews with 25 key stakeholders in Bali and West Nusa Tenggara Provinces to identify specific challenges to testing for HIV, syphilis, and hepatitis B in ANC settings. Thematic analysis was used to identify the themes generated from the data. Health system bottlenecks experienced by stakeholders included supply chain management issues involving stock forecasting and stock monitoring, stock-outs of rapid test reagents which were particularly most frequent and for longer durations for syphilis and hepatitis B, high staff turnover, lack of staff training on how to perform the test, the complexity and time needed to record the data on women's characteristics, risk behaviours, and testing in both paper format and into the computer-based surveillance systems, discrepancies in program coverage data from different divisions of the district health office involved in the reporting system, high levels of stigma that prevented women from being followed up, challenges in notifying partners, and inadequate reporting and referral of women from private providers to public ones for testing. Interventions addressing the above challenges are worthy of consideration to improve the health system function and integrate EMTCT into the ANC settings.

Designathons in health research: a global systematic review.

INTRODUCTION: A designathon is a three-stage participatory activity informed by design thinking. There is a growing literature on designathons in health. This study synthesised designathons' effectiveness and implementation-related factors to address health challenges. METHODS: We searched Cochrane Library, Embase, PubMed, Scopus and the ClinicalTrials.gov registry for articles containing primary data on designathons for health from their dates of inception to 29 November 2022. We retrieved additional studies from citation searching and a complementary open call. We synthesised data on designathons' effectiveness (ie, engagement, outputs and implementation), required resources and implementation-related factors (ie, resources, facilitators, barriers, strengths and limitations). We assessed the risk of bias using a checklist adapted from Joanna Briggs Institute Critical Appraisal tools. RESULTS: In total, 4973 citations were identified, and 42 studies were included. In total, 26 studies (62%) were from high-income countries. The median number of total participants was 49, divided into a median of 8 teams. The duration of the intensive collaboration phase ranged from 3 hours to 7 days. Common evaluation criteria were feasibility, innovation and impact. Idea and prototype outputs included mobile phone applications, educational programmes and medical devices. Interventions developed from a designathon was estimated to be highly cost-effective. The most common facilitators were interdisciplinary participants and high-quality mentorship. The most common barriers were suboptimal execution of the events, difficulties in balancing interdisciplinary participants across teams and limited support for participants along the process. There were limited data on required resources and further implementation of solutions after designathons. CONCLUSION: Given designathons' adaptability in terms of budget, mode of delivery, type of output and involvement of diverse participants, including end users, designathons can be implemented in a wide range of contexts to address various health issues. PROSPERO REGISTRATION NUMBER: CRD42023389685.

A proposal for a simplified measure of HIV preexposure prophylaxis prevention-effective adherence in self-report questionnaires.

Evaluating HIV preexposure prophylaxis (PrEP) use and HIV risk events concurrently remains challenging. We developed a single question method for measuring prevention-effective adherence with PrEP in self-report questionnaires. In a questionnaire completed by 409 gay and bisexual men, 46% reported condomless anal sex that was not covered by their own PrEP use, and this was more common among younger, lower-income participants. Refining this questionnaire item could improve measurement of prevention-effective adherence.

HIV Services Uptake Among People Living with HIV in Jiangsu Province, China: A Cross-Sectional Study.

Healthcare disparities are common among people living with HIV (PLWH) in China and likely impact access to HIV services. This study aimed to assess the current status of access to HIV services among PLWH and explore the correlates of service uptake using baseline data from a prospective cohort study among PLWH in Jiangsu Province. Guided by Andersen's behavioral model, univariable and multivariable logistic regressions were conducted to identify factors associated with access to HIV services. Out of 8989 eligible PLWH included in this study, 46.4% perceived difficulty in seeing a healthcare professional for HIV treatment services in 2021-2022. PLWH aged 18-34 years (adjusted odds ratio [AOR] = 1.69, 95% CI 1.32-2.15), 35-39 years (AOR = 1.33, 95% CI 1.08-1.65), identified as a bisexual/other (AOR = 1.14, 95% CI 1.01-1.29), had a college and above education (AOR = 1.32, 95% CI 1.07-1.63), and perceived moderate (AOR = 1.70, 95% CI 1.51-1.91) and severe (AOR = 2.20, 95% CI 1.94-2.49) levels of HIV stigma were more likely to perceive difficulty in seeing healthcare professionals for HIV treatment in 2021-2022. Living in northern Jiangsu was also associated with increased odds of perceiving difficulty in seeing healthcare professionals for HIV treatment (AOR = 1.12, 95% CI 1.00-1.26). These findings underscore the need for innovative solutions to eliminate the practical barriers to HIV services utilization among PLWH who are bisexual, well-educated, and effective HIV-related stigma reduction interventions.

Clinical features-based machine learning models to separate sexually transmitted infections from other skin diagnoses.

INTRODUCTION: Many sexual health services are overwhelmed and cannot cater for all the individuals who present with sexually transmitted infections (STIs). Digital health software that separates STIs from non-STIs could improve the efficiency of clinical services. We developed and evaluated a machine learning model that predicts whether patients have an STI based on their clinical features. METHODS: We manually extracted 25 demographic features and clinical features from 1315 clinical records in the electronic health record system at Melbourne Sexual Health Center. We examined 16 machine learning models to predict a binary outcome of an STI or a non-STI diagnosis. We evaluated the models' performance with the area under the ROC curve (AUC), accuracy and F1-scores. RESULTS: Our study included 1315 consultations, of which 36.8% (484/1315) were diagnosed with STIs and 63.2% (831/1315) had non-STI conditions. The study population predominantly consisted of heterosexual men (49.5%, 651/1315), followed by gay, bisexual and other men who have sex with men (GBMSM) (25.7%), women (21.6%) and unknown gender (3.2%). The median age was 31 years (intra-quartile range (IQR) 26-39). The top 5 performing models were CatBoost (AUC 0.912), Random Forest (AUC 0.917), LightGBM (AUC 0.907), Gradient Boosting (AUC 0.905) and XGBoost (AUC 0.900). The best model, CatBoost, achieved an accuracy of 0.837, sensitivity of 0.776, specificity of 0.831, precision of 0.782 and F1-score of 0.778. The key important features were lesion duration, type of skin lesions, age, gender, history of skin disorders, number of lesions, dysuria duration, anorectal pain and itchiness. CONCLUSIONS: Our best model demonstrates a reasonable performance in distinguishing STIs from non-STIs. However, to be clinically useful, more detailed information such as clinical images, may be required to reach sufficient accuracy.

Ignored and undervalued in public health: a systematic review of health state utility values associated with syphilis infection.

BACKGROUND: Syphilis is a sexually transmitted infection causing significant global morbidity and mortality. To inform policymaking and economic evaluation studies for syphilis, we summarised utility and disability weights for health states associated with syphilis. METHODS: We conducted a systematic review, searching six databases for economic evaluations and primary valuation studies related to syphilis from January 2000 to February 2022. We extracted health state utility values or disability weights, including identification of how these were derived. The study was registered in the international prospective register of systematic reviews (PROSPERO, CRD42021230035). FINDINGS: Of 3401 studies screened, 22 economic evaluations, two primary studies providing condition-specific measures, and 13 burden of disease studies were included. Fifteen economic evaluations reported outcomes as disability-adjusted life years (DALYs) and seven reported quality-adjusted life years (QALYs). Fourteen of 15 economic evaluations that used DALYS based their values on the original Global Burden of Disease (GBD) study from 1990 (published in 1996). For the seven QALY-related economic evaluations, the methodology varied between studies, with some studies using assumptions and others creating utility weights or converting them from disability weights. INTERPRETATION: We found a limited evidence base for the valuation of health states for syphilis, a lack of transparency for the development of existing health state utility values, and inconsistencies in the application of these values to estimate DALYs and QALYs. Further research is required to expand the evidence base so that policymakers can access accurate and well-informed economic evaluations to allocate resources to address syphilis and implement syphilis programs that are cost-effective.