The impact of HCV co-infection status on healthcare-related utilization among people living with HIV in British Columbia, Canada: a retrospective cohort study

Predicting the presence of depressive symptoms in the HIV-HCV co-infected population in Canada using supervised machine learning

BACKGROUND

Depression is common in the human immunodeficiency virus (HIV)-hepatitis C virus (HCV) co-infected population. Demographic, behavioural, and clinical data collected in research settings may be of help in identifying those at risk for clinical depression. We aimed to predict the presence of depressive symptoms indicative of a risk of depression and identify important classification predictors using supervised machine learning.

METHODS

We used data from the Canadian Co-infection Cohort, a multicentre prospective cohort, and its associated sub-study on Food Security (FS). The Center for Epidemiologic Studies Depression Scale-10 (CES-D-10) was administered in the FS sub-study; participants were classified as being at risk for clinical depression if scores ≥ 10. We developed two random forest algorithms using the training data (80%) and tenfold cross validation to predict the CES-D-10 classes-1. Full algorithm with all candidate predictors (137 predictors) and 2. Reduced algorithm using a subset of predictors based on expert opinion (46 predictors). We evaluated the algorithm performances in the testing data using area under the receiver operating characteristic curves (AUC) and generated predictor importance plots.

RESULTS

We included 1,934 FS sub-study visits from 717 participants who were predominantly male (73%), white (76%), unemployed (73%), and high school educated (52%). At the first visit, median age was 49 years (IQR:43-54) and 53% reported presence of depressive symptoms with CES-D-10 scores ≥ 10. The full algorithm had an AUC of 0.82 (95% CI:0.78-0.86) and the reduced algorithm of 0.76 (95% CI:0.71-0.81). Employment, HIV clinical stage, revenue source, body mass index, and education were the five most important predictors.

CONCLUSION

We developed a prediction algorithm that could be instrumental in identifying individuals at risk for depression in the HIV-HCV co-infected population in research settings. Development of such machine learning algorithms using research data with rich predictor information can be useful for retrospective analyses of unanswered questions regarding impact of depressive symptoms on clinical and patient-centred outcomes among vulnerable populations.

Hepatitis C virus-microelimination program and patient trajectories after hepatitis C virus cure in an outpatient HIV clinical unit

OBJECTIVE

Treatment recommendations for hepatitis C now make no distinction between HIV/HCV-coinfected and HCV-monoinfected patients. The largest challenge remained lack of effective models to eliminate HCV in people living with HIV. We report the results of a microelimination program evaluating the possibility of eradicating HCV in an HIV-outpatient clinical unit within 12 months.

METHODS

This HCV-microelimination program began in February 2016 in an unit following approximately 1000 HIV-infected patients and combined screening and therapeutic components according to the French guideline. A nested cohort study evaluating the impact of HCV cure on different health outcomes was conducted through self-administered questionnaires and using generalized mixed models.

RESULTS

Among 601 patients eligible for HCV serological testing, 445 were evaluated, and two HCV acute infections were diagnosed. Among the 151 patients eligible for HCV RNA quantification, 119 were evaluated, and one reinfection with HCV was diagnosed. Among the 110 patients eligible for direct-acting antiviral treatment, 51 (46.4%) initiated treatment within the 12 months program, and 35 (31.8%) after. Sustained virologic response (SVR) rate was 96.1%, and two treatments failed. At least one self-reported symptom was declared by 72.5% (n = 29) of patients. Positive impact of HCV cure was observed on various markers of physical and mental health as well as on health habits.

CONCLUSION

Our program should be considered as a proof of concept, which confirmed the feasibility of a HCV-microelimination program at the scale of an HIV clinical unit. However, 12 months were not sufficient to achieve our objective despite the specific organization.

Missed opportunities for earlier diagnosis of HIV in British Columbia, Canada: A retrospective cohort study

BACKGROUND

Late HIV diagnosis is associated with increased AIDS-related morbidity and mortality as well as an increased risk of HIV transmission. In this study, we quantified and characterized missed opportunities for earlier HIV diagnosis in British Columbia (BC), Canada.

DESIGN

Retrospective cohort.

METHODS

A missed opportunity was defined as a healthcare encounter due to a clinical manifestation which may be caused by HIV infection, or is frequently present among those with HIV infection, but no HIV diagnosis followed within 30 days. We developed an algorithm to identify missed opportunities within one, three, and five years prior to diagnosis. The algorithm was applied to the BC STOP HIV/AIDS population-based cohort. Eligible individuals were ≥18 years old, and diagnosed from 2001-2014. Multivariable logistic regression identified factors associated with missed opportunities.

RESULTS

Of 2119 individuals, 7%, 12% and 14% had ≥1 missed opportunity during one, three and five years prior to HIV diagnosis, respectively. In all analyses, individuals aged ≥40 years, heterosexuals or people who ever injected drugs, and those residing in Northern health authority had increased odds of experiencing ≥1 missed opportunity. In the three and five-year analysis, individuals with a CD4 count <350 cells/mm3 were at higher odds of experiencing ≥1 missed opportunity. Prominent missed opportunities were related to recurrent pneumonia, herpes zoster/shingles among younger individuals, and anemia related to nutritional deficiencies or unspecified cause.

CONCLUSIONS

Based on our newly-developed algorithm, this study demonstrated that HIV-diagnosed individuals in BC have experienced several missed opportunities for earlier diagnosis. Specific clinical indicator conditions and population sub-groups at increased risk of experiencing these missed opportunities were identified. Further work is required in order to validate the utility of this proposed algorithm by establishing the sensitivity, specificity, positive and negative predictive values corresponding to the incidence of the clinical indicator conditions among both HIV-diagnosed and HIV-negative populations.