Measuring the performance of computer vision artificial intelligence to interpret images of HIV self-testing results.

Introduction: HIV self-testing (HIVST) is highly sensitive and specific, addresses known barriers to HIV testing (such as stigma), and is recommended by the World Health Organization as a testing option for the delivery of HIV pre-exposure prophylaxis (PrEP). Nevertheless, HIVST remains underutilized as a diagnostic tool in community-based, differentiated HIV service delivery models, possibly due to concerns about result misinterpretation, which could lead to inadvertent onward transmission of HIV, delays in antiretroviral therapy (ART) initiation, and incorrect initiation on PrEP. Ensuring that HIVST results are accurately interpreted for correct clinical decisions will be critical to maximizing HIVST's potential. Early evidence from a few small pilot studies suggests that artificial intelligence (AI) computer vision and machine learning could potentially assist with this task. As part of a broader study that task-shifted HIV testing to a new setting and cadre of healthcare provider (pharmaceutical technologists at private pharmacies) in Kenya, we sought to understand how well AI technology performed at interpreting HIVST results. Methods: At 20 private pharmacies in Kisumu, Kenya, we offered free blood-based HIVST to clients ≥18 years purchasing products indicative of sexual activity (e.g., condoms). Trained pharmacy providers assisted clients with HIVST (as needed), photographed the completed HIVST, and uploaded the photo to a web-based platform. In real time, each self-test was interpreted independently by the (1) client and (2) pharmacy provider, with the HIVST images subsequently interpreted by (3) an AI algorithm (trained on lab-captured images of HIVST results) and (4) an expert panel of three HIVST readers. Using the expert panel's determination as the ground truth, we calculated the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for HIVST result interpretation for the AI algorithm as well as for pharmacy clients and providers, for comparison. Results: From March to June 2022, we screened 1,691 pharmacy clients and enrolled 1,500 in the study. All clients completed HIVST. Among 854 clients whose HIVST images were of sufficient quality to be interpretable by the AI algorithm, 63% (540/854) were female, median age was 26 years (interquartile range: 22-31), and 39% (335/855) reported casual sexual partners. The expert panel identified 94.9% (808/854) of HIVST images as HIV-negative, 5.1% (44/854) as HIV-positive, and 0.2% (2/854) as indeterminant. The AI algorithm demonstrated perfect sensitivity (100%), perfect NPV (100%), and 98.8% specificity, and 81.5% PPV (81.5%) due to seven false-positive results. By comparison, pharmacy clients and providers demonstrated lower sensitivity (93.2% and 97.7% respectively) and NPV (99.6% and 99.9% respectively) but perfect specificity (100%) and perfect PPV (100%). Conclusions: AI computer vision technology shows promise as a tool for providing additional quality assurance of HIV testing, particularly for catching Type II error (false-negative test interpretations) committed by human end-users. We discuss possible use cases for this technology to support differentiated HIV service delivery and identify areas for future research that is needed to assess the potential impacts-both positive and negative-of deploying this technology in real-world HIV service delivery settings.

Barriers and Expectations of Adolescents Regarding the Identification and Management of Their Psychoactive Substance Use by Their General Practitioner.

AIMS: General practitioners (GPs), who are the most frequently consulted health professionals by adolescents, play a key role in screening for psychoactive substance (PAS) use. The purpose of our study was to determine the barriers and expectations of adolescents regarding the identification and management of their PAS use by their general practitioner. METHODS: Descriptive, cross-sectional study of a population of adolescents aged 12 to 17 years, followed up in general practice in France. Adolescents were recruited from general practice offices by open-access questionnaires. An opaque box was provided to ensure the anonymity of the adolescents. RESULTS: A total of 277 adolescents were included: 155 girls, mean age 14.5 ± 1.7 years, 113 adolescents (41%) had used a PAS at least once in the past 12 months. Alcohol was the most used PAS, followed by tobacco and cannabis. Three groups were identified: the nonusers group (n = 134); the group of moderate users (n = 71); the group of users at risk of substance abuse or misusing (n = 38). Regardless of group, adolescents felt that their GP was attentive, responsive, competent, understanding, and took the time to ask the appropriate questions in their role. The at-risk group was less confident and less comfortable, and they felt more judged and more afraid of the GP telling their parents. Despite this, the at-risk group was the most willing to talk to their GP about their PAS. Almost half of the adolescents surveyed found it useful to use a questionnaire to discuss PAS. CONCLUSIONS: Reminding each consultation of the principles of the relationship of trust and confidentiality while maintaining an empathetic attitude would make it easier for GPs to remove adolescents' inhibitions about communicating about their PAS use.

Understanding how social support influences peer-delivered HIV prevention interventions among Ugandan female sex workers: a case study from HIV self-testing.

BACKGROUND: Female sex workers (FSWs) have tightly connected peer networks and remain at high risk of HIV acquisition. Peer delivery of HIV prevention interventions, such as HIV self-testing (HIVST), is a recommended implementation strategy for increasing intervention uptake and continuation among FSWs. We analyzed qualitative data from a peer-delivered HIVST intervention among FSWs in urban Uganda to understand the ways social support within this peer network can motivate or discourage the uptake of peer-delivered HIVST. METHODS: Between February and April 2017, we conducted in-depth interviews (IDIs) with FSWs (n = 30) and focus group discussions (FGDs) with FSW peer educators (PEs, n = 5) finishing participation in a four-month randomized implementation trial testing models of peer-delivered HIVST in Kampala. FSW participants were ≥ 18 years old, self-reported exchanging sex for money or goods (past month) and had not recently tested for HIV (past 3 months). FSW PEs either directly distributed HIVST kits to participants or provided coupons exchangeable for HIVST kits from specified healthcare facilities. In the IDIs and FGDs, we asked participants to share their experiences receiving or delivering peer-delivered HIVST, respectively. Using a hybrid deductive and inductive coding approach, we arranged findings along the dimensions of an established social support theory: informational, instrumental, and emotional support. RESULTS: The median age of participants was 30 years (IQR: 27-33) and PEs was 33 years (IQR: 29-37). We found that social support within FSW peer networks both motivated and discouraged uptake of peer-delivered HIVST. For example, sharing positive HIVST experiences (informational support), directly delivering HIVST kits (instrumental support), and encouraging linkage to care (emotional support) motivated HIVST uptake among FSWs. Conversely, the spread of misinformation (informational support), limited HIVST kit availability fostering mistrust of PEs (instrumental support), and fear of social exclusion following HIV status disclosure (emotional support) discouraged HIVST uptake among FSWs. CONCLUSIONS: In Uganda, social support (e.g., informational, instrumental, and emotional support) among FSW peers can work in ways that both motivate and discourage peer-delivered intervention uptake. Future FSW peer-delivered HIV prevention interventions should be designed around the dimensions of social support within FSW peer networks to maximize initial and repeat intervention delivery and uptake.

Effects Of A Communication-And-Resolution Program On Hospitals' Malpractice Claims And Costs.

To promote communication with patients after medical injuries and improve patient safety, numerous hospitals have implemented communication-and-resolution programs (CRPs). Through these programs, hospitals communicate transparently with patients after adverse events; investigate what happened and offer an explanation; and, when warranted, apologize, take responsibility, and proactively offer compensation. Despite growing consensus that CRPs are the right thing to do, concerns over liability risks remain. We evaluated the liability effects of CRP implementation at four Massachusetts hospitals by examining before-and-after trends in claims volume, cost, and time to resolution and comparing them to trends among nonimplementing peer institutions. CRP implementation was associated with improved trends in the rate of new claims and legal defense costs at some hospitals, but it did not significantly alter trends in other outcomes. None of the hospitals experienced worsening liability trends after CRP implementation, which suggests that transparency, apology, and proactive compensation can be pursued without adverse financial consequences.

Freedom of choice, expressions of gratitude: Patient experiences of short-term surgical missions in Guatemala.

Lack of surgical care has been highlighted as a critical global health problem, and short-term medical missions (STMMs) have become a de facto measure to address this shortfall. Participation in STMMs is an increasingly popular activity for foreign medical professionals to undertake in low- and middle-income countries (LMICs) where their clinical skills may be in short supply. While there is emerging literature on the STMM phenomenon, patient experiences of surgical missions are underrepresented. This research addresses this gap through thirty-seven in-depth interviews with patients or caregivers who received care from a short-term surgical mission within the three years prior to the four-week data collection period in July and August 2013. Interviews were conducted in Antigua, Guatemala and nearby communities, and participants came from 9 different departments of the country. These first-hand accounts of health-seeking through a surgical mission provide important insights into the benefits and challenges of STMMs that patients encounter, including waiting time, ancillary costs, and access to care. Patient agency in care-seeking is considered within the pluralistic, privatized health care context in Guatemala in which foreign participants deliver STMM care.

Outcomes In Two Massachusetts Hospital Systems Give Reason For Optimism About Communication-And-Resolution Programs.

Through communication-and-resolution programs, hospitals and liability insurers communicate with patients when adverse events occur; investigate and explain what happened; and, where appropriate, apologize and proactively offer compensation. Using data recorded by program staff members and from surveys of involved clinicians, we examined case outcomes of a program used by two academic medical centers and two of their community hospitals in Massachusetts in the period 2013-15. The hospitals demonstrated good adherence to the program protocol. Ninety-one percent of the program events did not meet compensation eligibility criteria, and those events that did were not costly to resolve (the median payment was $75,000). Only 5 percent of events led to malpractice claims or lawsuits. Clinicians were supportive of the program but desired better communication about it from staff members. Our findings suggest that communication-and-resolution programs will not lead to higher liability costs when hospitals adhere to their commitment to offer compensation proactively.

Making surgical missions a joint operation: NGO experiences of visiting surgical teams and the formal health care system in Guatemala.

Each year, thousands of Guatemalans receive non-emergent surgical care from short-term medical missions (STMMs) hosted by local non-governmental organizations (NGOs) and staffed by foreign visiting medical teams (VMTs). The purpose of this study was to explore the perspectives of individuals based in NGOs involved in the coordination of surgical missions to better understand how these missions articulate with the larger Guatemalan health care system. During the summers of 2011 and 2013, in-depth interviews were conducted with 25 representatives from 11 different Guatemalan NGOs with experience with surgical missions. Transcripts were analysed for major themes using an inductive qualitative data analysis process. NGOs made use of the formal health care system but were limited by several factors, including cost, issues of trust and current ministry of health policy. Participants viewed the government health care system as a potential resource and expressed a desire for more collaboration. The current practices of STMMs are not conducive to health system strengthening. The role of STMMs must be defined and widely understood by all stakeholders in order to improve patient safety and effectively utilise health resources. Priority should be placed on aligning the work of VMTs with that of the larger health care system.