Sexual Health Centre Research Articles

Accuracy of symptom checker for the diagnosis of sexually transmitted infections using machine learning and Bayesian network algorithms

BackgroundA significant proportion of individuals with symptoms of sexually transmitted infection (STI) delay or avoid seeking healthcare, and digital diagnostic tools may prompt them to seek healthcare earlier. Unfortunately, none of the currently available tools fully mimic clinical assessment or cover a wide range of STIs.MethodsWe prospectively invited attendees presenting with STI-related symptoms at Melbourne Sexual Health Centre to answer gender-specific questionnaires covering the symptoms of 12 common STIs using a computer-assisted self-interviewing system between 2015 and 2018. Then, we developed an online symptom checker (iSpySTI.org) using Bayesian networks. In this study, various machine learning algorithms were trained and evaluated for their ability to predict these STI and anogenital conditions. We used the Z-test to compare their average area under the ROC curve (AUC) scores with the Bayesian networks for diagnostic accuracy.ResultsThe study population included 6,162 men (median age 30, IQR: 26–38; approximately 40% of whom had sex with men in the past 12 months) and 4,358 women (median age 27, IQR: 24–31). Non-gonococcal urethritis (NGU) (23.6%, 1447/6121), genital warts (11.7%, 718/6121) and balanitis (8.9%, 546/6121) were the most common conditions in men. Candidiasis (16.6%, 722/4538) and bacterial vaginosis (16.2%, 707/4538) were the most common conditions in women. During evaluation with unseen datasets, machine learning models performed well for most male conditions, with the AUC ranging from 0.81 to 0.95, except for urinary tract infections (UTI) (AUC 0.72). Similarly, the models achieved AUCs ranging from 0.75 to 0.95 for female conditions, except for cervicitis (AUC 0.58). Urethral discharge and other urinary symptoms were important features for predicting urethral gonorrhoea, NGU and UTIs. Similarly, participants selected skin images that were similar to their own lesions, and the location of the anogenital skin lesions were also strong predictors. The vaginal discharge (odour, colour) and itchiness were important predictors for bacterial vaginosis and candidiasis. The performance of the machine learning models was significantly better than Bayesian models for male balanitis, molluscum contagiosum and genital warts (P < 0.05) but was similar for the other conditions.ConclusionsBoth machine learning and Bayesian models could predict correct diagnoses with reasonable accuracy using prospectively collected data for 12 STIs and other common anogenital conditions. Further work should expand the number of anogenital conditions and seek ways to improve the accuracy, potentially using patient collected images to supplement questionnaire data.

Increase in Neisseria gonorrhoeae infections after ending COVID-19 lockdown measures in Amsterdam, the Netherlands

ObjectiveVarious European countries noted increasing Neisseria gonorrhoeae (Ng) positivity among cis-gender women and heterosexual men. We assessed changes over time in Ng among men who exclusively have sex with men...

Oropharyngeal gonorrhoea among heterosexual men and women at a sexual health centre in Rotterdam, the Netherlands, 2023: reservoir for transmission?

BackgroundSexual health centres (SHCs) in the Netherlands report a surge in gonorrhoea, especially among young women (notably oropharyngeal) and men who have sex with women (MSW) since the second half...

Recent infection testing to inform HIV prevention responses and surveillance in a programme context: lessons from implementation within a nationally scaled female sex worker programme in Zimbabwe.

In the context of key population HIV testing programmes, identifying new HIV acquisitions, tracking incidence, and responding with prevention and treatment interventions will be critical for achieving HIV epidemic control. Laboratory tests for recently acquired HIV used as part of a "recent infection testing algorithm" (RITA), offer a potential tool to support this work. We implemented a RITA for female sex workers (FSWs) in Zimbabwe to explore opportunities and programmatic benefits. Between October 2021 and January 2023, recency testing was offered to FSWs attending the Centre for Sexual Health and HIV/AIDS Research (CeSHHAR) Zimbabwe's key populations programme. Dried blood spot (DBS) samples were taken at 86 clinic sites across 10 provinces and Laboratory LAg Avidity and viral load testing conducted. RITA results were analysed and linked to programme data to explore geographical differences and calculate HIV incidence. We describe concurrent efforts in HIV testing for social (social network testing [SNT]) and sexual (index case testing [ICT]) contacts of those testing HIV positive. Among 24,976 FSWs tested at programme sites, 9.5% (2363/24,976) were confirmed HIV positive. We enrolled 55.5% (1311/2363) of eligible HIV-positive FSWs to our study, of whom 11.7% (153/1311) were identified as having recently acquired HIV. It took a median of 37 days (IQR 20-67) for samples to be processed. Enrolment rates varied between provinces but the proportion of recently acquired HIV was similar (range: 18.4% to 4.0%). Overall HIV incidence was 3.4 (95% CI 2.7-4.0) per 100py. Where results could be linked to routinely collected data, we found no evidence of a difference in test-positivity between the ICT and SNT contacts of those with recently acquired compared to those with long-term HIV. Implementation of a RITA was possible within a nationally scaled sex worker programme, and while challenging to implement, can provide an understanding of transmission dynamics and HIV incidence in this context. Sub-optimal recruitment and data linkage limited the interpretation of our findings and opportunities for strategic gains though focusing on HIV prevention efforts.

Preferences for attributes of an artificial intelligence-based risk assessment tool for HIV and sexually transmitted infections: a discrete choice experiment

IntroductionEarly detection and treatment of HIV and sexually transmitted infections (STIs) are crucial for effective control. We previously developed MySTIRisk, an artificial intelligence-based risk tool that predicts the risk of HIV and STIs. We examined the attributes that encourage potential users to use it.MethodsBetween January and March 2024, we sent text message invitations to the Melbourne Sexual Health Centre (MSHC) attendees to participate in an online survey. We also advertised the survey on social media, the clinic's website, and posters in affiliated general practice clinics. This anonymous survey used a discrete choice experiment (DCE) to examine which MySTIRisk attributes would encourage potential users. We analysed the data using random parameters logit (RPL) and latent class analysis (LCA) models.ResultsThe median age of 415 participants was 31 years (interquartile range, 26–38 years), with a minority of participants identifying as straight or heterosexual (31.8%, n = 132). The choice to use MySTIRisk was most influenced by two attributes: cost and accuracy, followed by the availability of a pathology request form, level of anonymity, speed of receiving results, and whether the tool was a web or mobile application. LCA revealed two classes: "The Precisionists" (66.0% of respondents), who demanded high accuracy and "The Economists" (34.0% of respondents), who prioritised low cost. Simulations predicted a high uptake (97.7%) for a tool designed with the most preferred attribute levels, contrasting with lower uptake (22.3%) for the least preferred design.ConclusionsParticipants were more likely to use MySTIRisk if it was free, highly accurate, and could send pathology request forms. Tailoring the tool to distinct user segments could enhance its uptake and effectiveness in promoting early detection and prevention of HIV and STIs.

Duration of kissing in different intimate positions among men who have sex with men: A cross-sectional study.

Despite mounting evidence showing that kissing (tongue-kissing) may transmit gonorrhoea between men who have sex with men (MSM), little data exists on factors influencing the duration of kissing while they are above and/or lying underneath a partner for this population group. Between May 2019 and March 2020, we invited MSM aged ≥18years who attended the Melbourne Sexual Health Centre (MSHC) to participate in a survey about the duration of their kissing (minutes) and intimate position while kissing (i.e., kissing while above, or while lying underneath) their most recent partner. Univariable and multivariable negative binomial regressions were performed to examine the associations between the duration of kissing in different intimate positions, and demographic and behavioural characteristics (including age, region of birth, HIV status or PrEP use, and role in anal sex). Of the 965 men with a recent male kissing partner, 89.0% (n = 859) also had sex with that partner. Of the 166 men with a recent female kissing partner, 71.7% (n = 119) also had sex with that partner. Our adjusted analyses showed that, on average, men born in Asia (mean 8.52 vs 11.69min, p < .001) and South America or the Caribbean (mean 8.61 vs 11.69min, p = .022) spent less time kissing compared to men born in Oceania, and the same was also observed for kissing while above or lying underneath. Men who had only receptive anal sex spent less time kissing while above than those who only had insertive anal sex (mean 3.04 vs 5.86min, p < .001). Our study is the first to examine factors that influence duration of kissing in different intimate positions. These factors could be associated with oropharyngeal gonorrhoea if saliva transmitted gonorrhoea and if gravity played a role.

User Views on Online Sexual Health Symptom Checker Tool: Qualitative Research.

Delayed diagnosis and treatment of sexually transmitted infections (STIs) contributes to poorer health outcomes and onward transmission to sexual partners. Access to best-practice sexual health care may be limited by barriers such as cost, distance to care providers, sexual stigma, and trust in health care providers. Online assessments of risk offer a novel means of supporting access to evidence-based sexual health information, testing, and treatment by providing more individualized sexual health information based on user inputs. This developmental evaluation aims to find potential users' views and experiences in relation to an online assessment of risk, called iSpySTI (Melbourne Sexual Health Center), including the likely impacts of use. Individuals presenting with urogenital symptoms to a specialist sexual health clinic were given the opportunity to trial a web-based, Bayesian-powered tool that provides a list of 2 to 4 potential causes of their symptoms based on inputs of known STI risk factors and symptoms. Those who tried the tool were invited to participate in a once-off, semistructured research interview. Descriptive, action, and emotion coding informed the comparative analysis of individual cases. Findings from interviews with 14 people who had used the iSpySTI tool support the superiority of the online assessment of STI risk compared to existing sources of sexual health information (eg, internet search engines) in providing trusted and probabilistic information to users. Additionally, potential users reported benefits to their emotional well-being in the intervening period between noticing symptoms and being able to access care. Differences in current and imagined urgency of health care seeking and emotional impacts were found based on clinical diagnosis (eg, non-STI, curable and incurable but treatable STIs) and whether participants were born in Australia or elsewhere. Online assessments of risk provide users experiencing urogenital symptoms with more individualized and evidence-based health information that can improve their health care-seeking and provide reassurance in the period before they can access care.

What Do People Want from an AI-Assisted Screening App for Sexually Transmitted Infection-Related Anogenital Lesions: A Discrete Choice Experiment.

One of the World Health Organization (WHO) recommendations to achieve its global targets for sexually transmitted infections (STIs) is the increased use of digital technologies. Melbourne Sexual Health Centre (MSHC) has developed an AI-assisted screening application (app) called AiSTi for the detection of common STI-related anogenital skin conditions. This study aims to understand the community's preference for using the AiSTi app. We used a discrete choice experiment (DCE) to understand community preferences regarding the attributes of the AiSTi app for checking anogenital skin lesions. The DCE design included the attributes: data type; AI accuracy; verification of result by clinician; details of result; speed; professional support; and cost. The anonymous DCE survey was distributed to clients attending MSHC and through social media channels in Australia between January and March 2024. Participant preferences on various app attributes were examined using random parameters logit (RPL) and latent class analysis (LCA) models. The median age of 411 participants was 32 years (interquartile range 26-40 years), with 64% assigned male at birth. Of the participants, 177 (43.1%) identified as same-sex attracted and 137 (33.3%) as heterosexual. In the RPL model, the most influential attribute was the cost of using the app (24.1%), followed by the clinician's verification of results (20.4%), the AI accuracy (19.5%) and the speed of receiving the result (19.1%). The LCA identified two distinct groups: 'all-rounders' (88%), who considered every attribute as important, and a 'cost-focussed' group (12%), who mainly focussed on the price. On the basis of the currently available app attributes, the predicted uptake was 72%. In the short term, a more feasible scenario of improving AI accuracy to 80-89% with clinician verification at a $5 cost could increase uptake to 90%. A long-term optimistic scenario with AI accuracy over 95%, no clinician verification and no cost could increase it to 95%. Preferences for an AI-assisted screening app targeting STI-related anogenital skin lesions are one that is low-cost, clinician-verified, highly accurate and provides results rapidly. An app with these key qualities would substantially improve user uptake.

Unnecessary antibiotic use in men who have sex with men (MSM) with anogenital symptoms attending a sexual health clinic: a retrospective analysis

ObjectivesTo quantify the amount of unnecessary antibiotics, in particular ceftriaxone, given to men who have sex with men (MSM) with anogenital symptoms as part of presumptive management in an urban...

Barriers and enablers that influence the uptake of HIV testing among heterosexual migrants in the Netherlands.

Heterosexual migrant men and women in the Netherlands often face barriers to accessing health services, including HIV testing, that may lead to late-stage HIV diagnoses. This study explored factors of influence in the usage of HIV testing among heterosexual migrants. Qualitative evaluation with semi-structured interviews at the Amsterdam-based AIDS Healthcare Foundation (AHF) Checkpoint and one focus group discussion (FGD) conducted during June-July 2023 with 19 participants: interviews with 12 heterosexual migrants from low- or middle-income countries (LMICs) and FGD (n = 5) and interviews (n = 2) with 7 key informants from the (public) health sector. Recorded interviews were transcribed and thematically analyzed, using the framework of Andersen's Expanded Behavioral Model of Health Services Use. In total, 55 themes emerged from the interviews and the FGD. Examples include insufficient availability of information on HIV and testing services, and difficulty in accessing these services (e.g. the barrier of the online appointment system of the Centre for Sexual Health (CSH)). HIV test participants expressed free, rapid testing, no appointment required, and a positive experience during their HIV test as enablers to test in the future. Results from key informants showed that poor health literacy and lack of clarity on the healthcare system's guidelines were barriers for heterosexual migrants in accessing information on HIV and testing services. It also revealed past initiatives and interventions that were successful in reaching at-risk groups such as the integration of HIV testing into sexually transmitted infection (STI) testing, but that were subsequently discontinued due to financial constraints. Factors contributing to a low HIV test uptake were participants' perception of limited accessibility of CSH facilities, insufficient available information on HIV (testing) services, and low perception of HIV risk. Unclear policies on accessing HIV/STI testing services at CSHs, and potential missed opportunities for HIV testing at general practitioners were contributing factors identified by key informants.

Uptake of gynecological consultation following domestic or sexual violence: A case-control study in the context of induced abortion

ObjectiveThe aim of this study was to determine the prevalence of domestic and sexual violence and to characterize the association between exposure to domestic and sexual violence and low uptake of gynecological care, in the context of induced abortion.Study design.We conducted a case-control study among women seeking abortion care, in mother and child centers and sexual health centers in the Paris, France area (April 2022-March 2023). ResultsA total of 103 women were included in the study during induced abortion care. Physical, psychological or sexual domestic violence was reported by 48.5 % and sexual violence, whoever the perpetrator, was reported by 23.3 %. In the bivariate analysis, a history of physical, psychological or sexual domestic violence was not associated with the absence of a gynecological consultation in the past two years, compared with no history of intimate partner violence (p = 0.09). After adjustment for regular pelvic pain, dysmenorrhea, vulvodynia and dyspareunia, there was no association between a history of sexual violence and the absence of a gynecological consultation in the past two years (OR 1.05; CI95% 0.27–4.13, p = 0.93). ConclusionViolence was a common finding among women seeking abortion care. We did not find any association between a history of sexual violence and the absence of a gynecological consultation in the past two years. We suggest investigating multiple or frequent use of gynecological care following violence. The combination of ethical, moral, and psychological constraints associated with violence screening and abortion care is a challenge to patient recruitment in future studies.

Exploring cultural competence barriers in the primary care sexual and reproductive health centres in Catalonia, Spain: perspectives from immigrant women and healthcare providers

BackgroundImmigrant populations, especially women, continue facing challenges in accessing quality healthcare, particularly sexual and reproductive health services (SRH). Poor cultural competent health systems contribute to communication challenges between immigrant women and healthcare providers perpetuating health disparities. This exploratory study describes these communication barriers from the perspective of Moroccan and Pakistani immigrant women and healthcare providers within the Catalan health system and its implications to ensure an equitable provision of SRH services.MethodsAn exploratory-descriptive qualitative study was conducted in various municipalities of Barcelona with high concentration of immigrants. Eight focus groups (N = 51) and semi-structured interviews (N = 22) with Moroccan and Pakistani immigrant women were combined with key informant interviews (N = 13) with healthcare professionals. Thematic analysis and data triangulation were performed primarily using an inductive approach.ResultsLanguage barriers and cultural differences in health needs, expectations, care-seeking behaviours and understanding of quality healthcare provision hindered the ability of immigrant women and providers to interact effectively. Limited availability of intercultural mediators and inadequate cultural competence training opportunities for health staff were also identified. Findings suggest a lack of minority representation in the Catalan health workforce and leadership roles.ConclusionThis study reinforces the evidence of persistent inequities in accessing healthcare among immigrant populations by focusing on the cultural competence barriers of the Catalan health system in the provision and access to SRH services. The regularization of adequately trained intercultural mediators, quality training in cultural competence for health staff and a commitment to increase workforce diversity would contribute to improve intercultural communication between immigrant patients and providers. An urgent call to action in this direction is needed to ensure an equitable access to SRH services among immigrant women.

Outcomes of a policy to prioritize populations with expected healthcare barriers for subsidized preexposure prophylaxis care in Amsterdam, the Netherlands.

The Dutch HIV preexposure prophylaxis (PrEP) pilot provided subsidized PrEP care to maximum 2900 individuals at a time in Amsterdam. Populations with expected barriers to accessing PrEP elsewhere were prioritized for program inclusion. We evaluated their prior sexual health service engagement and PrEP need. Cross-sectional analysis using enrolment data. We included individuals ever enrolled in the PrEP program at the Center for Sexual Health (CSH) Amsterdam between 2019 and 2023. We calculated the proportion belonging to higher-priority groups (i.e., <25 years old, transgender, sex worker, uninsured or migrant). We defined classes of sexual health service engagement in the 12 months preceding enrolment using latent class analysis (LCA). We compared engagement classes, sexual behavior and positivity of HIV and sexually transmitted infections (STI) between higher- and lower-priority groups. 2004/4075 (49%) individuals enrolled belonged to higher-priority groups. LCA showed three classes of prior engagement: "newly engaged" (14%, n = 551) were new to the CSH-Amsterdam; "PrEP initiators" (40%, n = 1642) previously visited the CSH-Amsterdam but had not used PrEP; "PrEP experienced" individuals (46%, n = 1882) previously accessed PrEP. Higher-priority groups were more often "newly engaged" or "PrEP-initiators" than "PrEP-experienced". Higher-priority groups less often had condomless anal sex with casual partners or chemsex in the prior 6 months. Positivity of bacterial STI was similar between higher-priority ( n = 300/2004, 15.0%) and lower-priority ( n = 315/2071, 15.2%) groups. 13/14 HIV diagnoses at enrolment were in higher-priority groups. Higher-priority populations had less often previously used sexual health services and accounted for most new HIV diagnoses at enrolment. Engaging these populations in sexual healthcare, including PrEP, should be stressed.

Association between saliva use for masturbation and urethral gonorrhoea in men who have sex with men: A cross-sectional study

ObjectivesThe saliva of individuals with oropharyngeal gonorrhoea can contain viable Neisseria gonorrhoeae. This study examined if using saliva as a lubricant for masturbation is a risk factor for urethral gonorrhoea among men who have sex with men (MSM). MethodsIn this cross-sectional study, MSM aged ≥18 years attending the Melbourne Sexual Health Centre between February 2021 and December 2023 were surveyed. Data were collected on sexual activities in the past 7 days, including receiving fellatio, condomless insertive anal sex, docking, and using saliva for masturbation. Multivariable logistic regression examined associations between these exposures and urethral gonorrhoea. ResultsThe median age of the 3114 men was 32 (IQR: 27-40), with 4.7% (n = 145) testing positive for urethral gonorrhoea. Urethral gonorrhoea was independently associated with an increasing number of partners for condomless insertive anal sex (P < 0.001). It was not significantly associated with receiving fellatio (P = 0.613), docking (P = 0.207), or using saliva for masturbation (P = 0.117). However, of the 110 men who only used saliva for masturbation, two (1.8%) had urethral gonorrhoea, and one (0.9%) had both urethral and oropharyngeal gonorrhoea. ConclusionCondomless insertive anal sex is the leading risk factor for urethral gonorrhoea and not using saliva as a lubricant for masturbation.

Sexual mixing in bisexual activity in male-male partnerships in Melbourne, Australia.

Background The patterns of sexually transmitted infections (STIs) in populations may be influenced by the sexual mixing within the population. We aimed to investigate the assortative sexual mixing pattern by bisexuality in male-male partnerships. Methods This was a retrospective repeated cross-sectional study of men with mostly regular male partners attending the Melbourne Sexual Health Centre between 2011 and 2019. Data on sexual practices, including their sexual practices, presence of other male/female sex partners and the gender of sexual partners in the previous 3 and 12months, were collected using computer-assisted self-interview. We calculated the proportion of male partnerships where at least one man in the partnership reported a female sex partner. Results A total of 2056 male-male partnerships (i.e. 4112 individuals) with a median age of 29 years (IQR 25 to 35) were included. Overall, in 94.4% (1941/2056) of male-male partnerships both men had male partners only; however, in 5.5% (113/2056) of partnerships, one man had both male and female partners, and in 0.1% (2/2056) partnerships, both men had both male and female partners. No assortative relationship was found on the sexual mixing by bisexuality in male-male partnerships due to the low assortativity coefficient (r =0.006, 95% CI: -0.004 to 0.016). Conclusion One in 20 male-male partnerships had at least one man who had both male and female partners within the preceding year. Individuals were not selective by bisexuality, suggesting that partnerships of bisexual individuals are mixed proportionately to the distribution of their characteristics. Still, these sexual mixing practices may affect STI transmission dynamics.

Using a patient-reported outcome measure to assess quality of life at Western Sydney Sexual Health Centre.

Background Attaining a good quality of life (QOL) is a priority for people living with HIV (PLHIV). We explored the interaction between QOL and the associated demographic, behavioural and clinical factors for PLHIV attending an outer-metropolitan clinical setting in Western Sydney, Australia. The clinic's cohort of PLHIV is characterised by relatively high proportions of women, heterosexual men, and patients from culturally and linguistically diverse (CALD) communities. Methods We assessed QOL using the PozQol tool that is specifically designed for PLHIV. QOL scores and de-identified socio-demographic and clinical data were extracted from the electronic and paper medical records of PLHIV who completed a PozQol tool (September 2020-March 2022). We performed descriptive analyses and logistic regression to identify associations. Results Among 188 patients, there were 77.7% men, 21.3% women, 1.1% transwomen; 67.0% were born overseas, 85.1% spoke English, 84.4% were Medicare-eligible, 85.9% were employed, 58.5% were diagnosed with HIV 6-20years ago, and 33.0% within the past 5years. Overall, 58.0% had a high or very high QOL. A low score in any domain was associated with Medicare-ineligibility. Low QOL scores in specific domains were associated with the following factors: health (being born overseas, having partners of both sexes), psychological (unemployment, having a mental health condition, having a viral load >20 copies/mL), social (unemployment), and functional (Medicare-eligibility, unemployment, having a viral load >20 copies/mL). Conclusions The PozQol tool has enhanced understanding of factors impacting on QOL for PLHIV attending our service in Western Sydney. Identifying patients with low QOL scores allows targeted clinical interventions to improve QOL, and re-alignment of clinical services to better support PLHIV.

Toward Zero New HIV Infections in Amsterdam in 2026: Building Bridges Between Community Organizations, Undocumented Migrants, and Sexual Health Care Providers.

In the 4 largest cities in the Netherlands, an estimated 400 people live with undiagnosed HIV, including 170 in Amsterdam. Amsterdam targets having zero new HIV infections in 2026. Undocumented migrants are disproportionately affected by HIV and often contract HIV after migration. Moreover, they often experience difficulties accessing health care. The aim of this study was to analyze the outcomes of an HIV/sexually transmitted infection testing program for undocumented migrants through community based testing. Between May 2021 and January 2022, data for this cross-sectional study were collected during outreach testing activities of the Amsterdam Center for Sexual Health of the Public Health Service, and the NGO Doctors of the World. Activities were organized in collaboration with migrant partner organizations. Participants were tested free-of-charge for HIV, syphilis, gonorrhea, chlamydia, and, if indicated, hepatitis B and C. Before testing, a health care provider-administered questionnaire was filled out. A total of 126 people from 22 countries were tested for HIV during 28 outreach activities. Mean age was 37 (IQR 32-43). Forty-nine people (39%) were additionally tested, (through self-sampling) for chlamydia, gonorrhea and syphilis, 42 (33%) for Hepatitis B and 14 (11%) for Hepatitis C. We found zero new HIV infections and 5 positive chlamydia cases.Reaching 52 HIV first time testers and 19 first time testers since migration shows the importance of these activities. The number of participants tested were lower than initially expected due to lower attendance per testing day for various reasons. To increase the likelihood of reaching undocumented migrants for HIV/sexually transmitted infection testing and linkage to care, focus should be on on-site provider-initiated testing, e.g. during outreach health care activities, and on easy access to centers for sexual health. Collaboration between health care providers and community stakeholders is essential.

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

BackgroundSexually 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.MethodsWe 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.ResultsOur 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.ConclusionsThe 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.

First-line treatment with ceftriaxone for Neisseria gonorrhoeae infection less likely to be prescribed to patients with a penicillin allergy label: a retrospective audit of medical records.

Background Gonorrhoea notifications have increased substantially in Australia over the past decade. Neisseria gonorrhoeae is already highly resistant to several antibiotics and so, alternatives to first-line treatment are generally strongly discouraged. The penicillin allergy label (AL) on patient medical records has previously been shown to influence prescribing practices, to the detriment of best-practice management and antimicrobial stewardship. This study aimed to understand how the penicillin AL influences antibiotic selection for gonorrhoea treatment at Canberra Sexual Health Centre. Methods A retrospective chart audit of gonorrhoea cases treated at Canberra Sexual Health Centre between January 2020 and October 2023 (n =619 patients, n =728 cases). Antibiotic selection was assessed according to penicillin AL status. Ceftriaxone selection was assessed according to penicillin allergy severity reported in the medical records and as determined using a validated antibiotic allergy assessment tool. Results Cases with a penicillin AL were more likely to receive antibiotics other than ceftriaxone (n =7/41, 17.1%) than cases without the label (n =8/687, 1.2%, P n =28/41, 68.3%) to apply the assessment tool. Those reported as low-severity in the records were more likely to receive ceftriaxone (n =21/22, 95.5%) than those reported as moderate-high (n =7/11, 63.6%) or unreported (n =6/8, 0.75%). Conclusions Treatment of gonorrhoea in outpatient settings requires an understanding of penicillin allergy, and the ability to quickly and accurately identify penicillin-AL patients who can safely tolerate ceftriaxone. Institutionally endorsed penicillin allergy de-labelling protocols and access to easy-to-navigate prescribing advice within national sexually transmitted infection management guidelines would support this.

Vaginal anaerobes are associated with cervicitis: A case-control study

Cervicitis is associated with important reproductive sequelae. Primary causes include chlamydia and gonorrhoea, but a known sexually transmitted infection (STI) is not identified in >50% of cases (i.e. STI-negative cervicitis). Bacterial vaginosis (BV) and specific BV-associated bacteria have also been associated with cervicitis, but data are limited. We investigated the association between STI-negative cervicitis and vaginal microbiota composition. This was a case-control sub-study of the OhMG study conducted at the Melbourne Sexual Health Centre. Cases were women with cervicitis who tested negative for STIs (STI-negative cervicitis, n=64). Controls were STI-negative asymptomatic women attending for STI-screening (n=128). The vaginal microbiota was characterised using 16S rRNA gene sequencing. Vaginal community state types were compared between cases and controls using logistic regression. Differential abundance analysis was performed to identify taxa associated with STI-negative cervicitis. STI-negative cervicitis cases were more likely than controls to have a Lactobacillus-deficient non-optimal microbiota (adjusted-odds-ratio 2.55, 95% CI 1.18-5.50). Compared to controls, cases had increased abundance of four BV-associated bacteria (Gardnerella, Fannyhessea vaginae, Prevotella bivia, Dialister micraerophilus) and decreased abundance of optimal lactobacilli. We report a positive association between non-optimal vaginal microbiota composition and STI-negative cervicitis. Specific anaerobic BV-associated bacteria may represent infectious causes of cervicitis.