Emergency Departments (EDs) have the potential to play a crucial role in HIV prevention by identifying and linking high-risk HIV-negative clients to preexposure prophylaxis (PrEP) care, but it is difficult to perform HIV risk assessment for all ED patients. We aimed to develop and implement an electronic risk score to identify ED patients who are potential candidates for PrEP. Using electronic medical record (EMR) data, we used logistic regression to model the outcome of PrEP eligibility. We converted the model into an electronic risk score and incorporated it into the EMR. The risk score is automatically calculated at triage. For patients whose risk score is above a given threshold, an automated electronic alert is sent to an HIV prevention counselor who performs real time HIV prevention counseling, risk assessment, and PrEP linkage as appropriate. The electronic risk score includes the following EMR variables: age, gender, gender of sexual partner, chief complaint, and positive test for sexually transmitted infection in the prior 6 months. A risk score ≥21 has specificity of 80.6% and sensitivity of 50%. In the first 5.5 months of implementation, the alert fired for 180 patients, 34.4% (62/180) of whom were women. Of the 51 patients who completed risk assessment, 68.6% (35/51) were interested in PrEP, 17.6% (9/51) scheduled a PrEP appointment, and 7.8% (4/51) successfully initiated PrEP. The measured number of successful PrEP initiations is likely an underestimate, as it does include patients who initiated PrEP with outside providers or referred acquaintances for PrEP care.

Background: Mental illness and substance use are prevalent among people living with HIV and often lead to poor health outcomes. Electronic medical record (EMR) data are increasingly being utilized for HIV-related clinical research and care, but mental illness and substance use are often underdocumented in structured EMR fields. Natural language processing (NLP) of unstructured text of clinical notes in the EMR may more accurately identify mental illness and substance use among people living with HIV than structured EMR fields alone. Objective: The aim of this study was to utilize NLP of clinical notes to detect mental illness and substance use among people living with HIV and to determine how often these factors are documented in structured EMR fields. Methods: We collected both structured EMR data (diagnosis codes, social history, Problem List) as well as the unstructured text of clinical HIV care notes for adults living with HIV. We developed NLP algorithms to identify words and phrases associated with mental illness and substance use in the clinical notes. The algorithms were validated based on chart review. We compared numbers of patients with documentation of mental illness or substance use identified by structured EMR fields with those identified by the NLP algorithms. Results: The NLP algorithm for detecting mental illness had a positive predictive value (PPV) of 98% and a negative predictive value (NPV) of 98%. The NLP algorithm for detecting substance use had a PPV of 92% and an NPV of 98%. The NLP algorithm for mental illness identified 54.0% (420/778) of patients as having documentation of mental illness in the text of clinical notes. Among the patients with mental illness detected by NLP, 58.6% (246/420) had documentation of mental illness in at least one structured EMR field. Sixty-three patients had documentation of mental illness in structured EMR fields that was not detected by NLP of clinical notes. The NLP algorithm for substance use detected substance use in the text of clinical notes in 18.1% (141/778) of patients. Among patients with substance use detected by NLP, 73.8% (104/141) had documentation of substance use in at least one structured EMR field. Seventy-six patients had documentation of substance use in structured EMR fields that was not detected by NLP of clinical notes. Conclusions: Among patients in an urban HIV care clinic, NLP of clinical notes identified high rates of mental illness and substance use that were often not documented in structured EMR fields. This finding has important implications for epidemiologic research and clinical care for people living with HIV.

Consistent medical care among people living with HIV is essential for both individual and public health. HIV-positive individuals who are ‘retained in care’ are more likely to be prescribed antiretroviral medication and achieve HIV viral suppression, effectively eliminating the risk of transmitting HIV to others. However, in the United States, less than half of HIV-positive individuals are retained in care. Interventions to improve retention in care are resource intensive, and there is currently no systematic way to identify patients at risk for falling out of care who would benefit from these interventions. We developed a machine learning model to identify patients at risk for dropping out of care in an urban HIV care clinic using electronic medical records and geospatial data. The machine learning model has a mean positive predictive value of 34.6% [SD: 0.15] for flagging the top 10% highest risk patients as needing interventions, performing better than the previous state-of-the-art logistic regression model (PPV of 17% [SD: 0.06]) and the baseline rate of 11.1% [SD: 0.02]. Machine learning methods can improve the prediction ability in HIV care clinics to proactively identify patients at risk for not returning to medical care.

The risk of COVID-19 among people living with HIV (PLWH) is largely unknown and there have been very few reported cases in the literature. We report a case series of five PLWH with COVID-19. We identified all patients with a diagnosis of HIV who tested positive for SARS-CoV-2 at University of Chicago Medicine between March 1, 2020, and April 7, 2020. We retrospectively collected data regarding demographics, comorbidities, medications, laboratory test results, radiology results, and outcomes associated with COVID-19. All five PLWH with COVID-19 were African American; 80% (4/5) were cisgender females. The mean age of patients was 48 years old (range 38–53). The majority of patients presented with cough, fever, and shortness of breath. Three patients had diarrhea. One patient presented with predominantly cardiac symptoms. All were taking antiretroviral therapy (ART) with CD4 count >200 cells/mm³ and suppressed HIV viral loads at the time of COVID-19 diagnosis. All five patients were hospitalized, two required supplemental oxygen, and none required mechanical ventilation. Four patients were treated with azithromycin and a cephalosporin and two were also treated with hydroxychloroquine. The median length of stay was 3 days (range 2–7). All patients recovered. More research is needed to understand the risks of COVID-19 among PLWH and the impact of ART on outcomes for patients with COVID-19.

Background. To prevent transmission of influenza from healthcare workers (HCWs) to patients, many hospitals exclude febrile HCWs from working, but allow afebrile HCWs with respiratory symptoms to have contact with patients. During the 2013–2014 influenza season at our hospital, an influenza-positive HCW with respiratory symptoms but no fever was linked to a case of possible healthcare-associated influenza in a patient. Therefore, we implemented a temporary policy of mandatory influenza testing for HCWs with respiratory symptoms.