BACKGROUND
Viral load (VL) suppression is key to ending the global HIV epidemic, and predicting it is critical for healthcare providers and people living with HIV (PLHIV). Traditional research has focused on statistical analysis, but machine learning (ML) is gradually influencing HIV clinical care. While ML has been used in various settings, there’s a lack of research supporting antiretroviral therapy (ART) programs, especially in resource-limited settings like Guinea. This study aims to identify the most predictive variables of VL suppression and develop ML models for PLHIV in Conakry (Guinea).
METHODS
Anonymized data from HIV patients in eight Conakry health facilities were pre-processed, including variable recoding, record removal, missing value imputation, grouping small categories, creating dummy variables, and oversampling the smallest target class. Support vector machine (SVM), logistic regression (LR), naïve Bayes (NB), random forest (RF), and four stacked models were developed. Optimal parameters were determined through two cross-validation loops using a grid search approach. Sensitivity, specificity, predictive positive value (PPV), predictive negative value (PNV), F-score, and area under the curve (AUC) were computed on unseen data to assess model performance. RF was used to determine the most predictive variables.
RESULTS
RF (94% F-score, 82% AUC) and NB (89% F-score, 82% AUC) were the most optimal models to detect VL suppression and non-suppression when applied to unseen data. The optimal parameters for RF were 1,000 estimators and no maximum depth (Random state = 40), and it identified Regimen schedule_6-Month, Duration on ART (months), Last ART CD4, Regimen schedule_Regular, and Last Pre-ART CD4 as top predictors for VL suppression.
CONCLUSION
This study demonstrated the capability to predict VL suppression but has some limitations. The results are dependent on the quality of the data and are specific to the Guinea context and thus, there may be limitations with generalizability. Future studies may be to conduct a similar study in a different context and develop the most optimal model into an application that can be tested in a clinical context.
BACKGROUND
Zaire Ebolavirus disease (EVD) outbreaks can be controlled using rVSV-ZEBOV vaccination and other public health measures. People in high-risk areas may have pre-existing antibodies from asymptomatic Ebolavirus exposure that might affect response to rVSV-ZEBOV. Therefore, we assessed the impact pre-existing immunity had on post-vaccination IgG titre, virus neutralisation, and reactogenicity following vaccination.
METHODS
In this prospective cohort study, 2115 consenting close contacts (“proches”) of EVD survivors were recruited. Proches were vaccinated with rVSV-ZEBOV and followed up for 28 days for safety and immunogenicity. Anti-GP IgG titre at baseline and day 28 was assessed by ELISA. Samples from a representative subset were evaluated using live virus neutralisation.
RESULTS
Ten percent were seropositive at baseline. At day 28, IgG in baseline seronegative (GMT 0.106 IU/ml, 95% CI: 0.100 to 0.113) and seropositive (GMT 0.237 IU/ml, 0.210 to 0.267) participants significantly increased from baseline (both p < 0.0001). There was strong correlation between antibody titres and virus neutralisation in day 28 samples (Spearman’s rho 0.75). Vaccinees with baseline IgG antibodies against Zaire Ebolavirus had similar safety profiles to those without detectable antibodies (63.6% vs 66.1% adults experienced any adverse event; 49.1% vs 60.9% in children), with almost all adverse events graded as mild. No serious adverse events were attributed to vaccination. No EVD survivors tested positive for Ebolavirus by RT-PCR.
CONCLUSIONS
These data add further evidence of rVSV-ZEBOV safety and immunogenicity, including in people with pre-existing antibodies from suspected natural ZEBOV infection whose state does not blunt rVSV-ZEBOV immune response. Pre-vaccination serological screening is not required.
Under-diagnosis of tuberculosis in children remains a major concern worldwide. The World Health Organization (WHO) recommends two new treatment decision algorithms for TB in children less than 10 years presenting with presumptive pulmonary TB. The algorithms are adapted to contexts with, and without radiography, include laboratory testing if available, and aim to facilitate treatment decision by assigning scores to symptoms and radiological features. However, little is known about the feasibility and acceptability of implementing these algorithms in Sub-Saharan Africa settings.
METHODS
Using a qualitative study design, we conducted 45 semi-structured interviews with health workers in nine health facilities in Uganda, Niger and Guinea. We analyzed the data thematically, and using the critical discourse analysis with a deductive and inductive approach to identify contextual barriers and acceptance of the intervention among health workers.
RESULTS
Firstly, discourse analysis shows that health workers identify various socio-cultural factors (e.g.: delays in children arriving at health facilities, stigmatization) and structural factors (e.g. high workload for health workers, lack of resources in the health centres) as the major barriers that make TB diagnosis difficult. In this context, implementation of the algorithms is positively perceived (e.g.: the scoring system was found to be useful and user-friendly) but raises some challenges (e.g.: additional paperwork). Otherwise, results shows that the implementation of the algorithms plays a role in strengthening health worker's sense of autonomy and efficiency, and some paramedical staff (nurses) express the wish to be more directly involved in applying the algorithms.
CONCLUSION
This study found that the new TB algorithms were perceived positively by health workers, and well accepted in the three countries. However, it illustrates the extent to which the implementation of innovative tools in healthcare structures needs to consider the existing system, potential barriers, and opportunities to ensure long-term use.
In 2016, UNAIDS identified the Prevention of Mother-to-Child Transmission of HIV (PMTCT) as a significant challenge in the fight against HIV/AIDS in Guinea. This abstract presents the key findings of an evaluation conducted on the PMTCT component of MSF's HIV project in Guinea, implemented since the early 2000’s. The main objective of the evaluation was to assess its relevance, coherence, effectiveness, efficiency, impact, and sustainability.
METHODS
A mixed quantitative and qualitative methodology was applied, including a desk review of MSF project documents, field observations, and interviews with key stakeholders. The data were analysed by triangulation and benchmarking to ensure internal validity. Quantitative indicators provided information on the number of women receiving PMTCT treatment and the rate of HIV mother-to-child transmission (MTCT) in health facilities supported by MSF, allowing the measurement of the effectiveness of the intervention. The quality of data and the lack of primary data from 2011 to 2015 was the main limitation, hindering the calculation of statistical significance (p-value) for the observed change in the rate of MTCT of HIV.
RESULTS
MSF's PMTCT intervention was highly relevant and aligned with the country's needs. It demonstrated effectiveness through the significant number of women receiving PMTCT treatment, the establishment of a platform for viral load testing, drug supply support, and a reduction in the HIV MTCT rate. The rate of MTCT in health facilities supported by MSF decreased from 35.9% to 12% [7 – 12] between 2010 and 2021. The challenges relating to data accuracy, monitoring activities, the follow-up of babies born from HIV-infected mothers, and the readiness of the MoH to take over the programme were identified, highlighting the need for improvement to enhance the effectiveness and efficiency. Sustainability efforts remained low as the Guinean health system lacked enough funding to take over the programme.
CONCLUSIONS
The evaluation affirms the positive impact of the PMTCT intervention in reducing MTCT of HIV, even if project target (5%) was not achieved. Recommendations aim to strengthen investment in PMTCT and enhance the hand-over strategy to ensure sustainability after MSF exit.
In 2016, UNAIDS identified the Prevention of Mother-to-Child Transmission of HIV (PMTCT) as a significant challenge in the fight against HIV/AIDS in Guinea. This abstract presents the key findings of an evaluation conducted on the PMTCT component of MSF's HIV project in Guinea, implemented since the early 2000’s. The main objective of the evaluation was to assess its relevance, coherence, effectiveness, efficiency, impact, and sustainability.
METHODS
A mixed quantitative and qualitative methodology was applied, including a desk review of MSF project documents, field observations, and interviews with key stakeholders. The data were analysed by triangulation and benchmarking to ensure internal validity. Quantitative indicators provided information on the number of women receiving PMTCT treatment and the rate of HIV mother-to-child transmission (MTCT) in health facilities supported by MSF, allowing the measurement of the effectiveness of the intervention. The quality of data and the lack of primary data from 2011 to 2015 was the main limitation, hindering the calculation of statistical significance (p-value) for the observed change in the rate of MTCT of HIV.
RESULTS
MSF's PMTCT intervention was highly relevant and aligned with the country's needs. It demonstrated effectiveness through the significant number of women receiving PMTCT treatment, the establishment of a platform for viral load testing, drug supply support, and a reduction in the HIV MTCT rate. The rate of MTCT in health facilities supported by MSF decreased from 35.9% to 12% [7 – 12] between 2010 and 2021. The challenges relating to data accuracy, monitoring activities, the follow-up of babies born from HIV-infected mothers, and the readiness of the MoH to take over the programme were identified, highlighting the need for improvement to enhance the effectiveness and efficiency. Sustainability efforts remained low as the Guinean health system lacked enough funding to take over the programme.
CONCLUSIONS
The evaluation affirms the positive impact of the PMTCT intervention in reducing MTCT of HIV, even if project target (5%) was not achieved. Recommendations aim to strengthen investment in PMTCT and enhance the hand-over strategy to ensure sustainability after MSF exit.
CONTEXTE ET OBJECTIFS
Les épidémies de maladies évitables par la vaccination sont récurrentes en Guinée. En 2020, Matoto a enregistré 86% des cas de rougeole rapportés à Conakry. Cette étude avait pour objectif d’évaluer les occasions manquées de vaccination chez les enfants de 0-59 mois.
METHODES
Il s’agissait d’une étude transversale par entretien de sortie dans quatre établissements de santé (ES) de Matoto (Bernay Fotoba, Saint Gabriel, Tombolia, Dabompa) du 11-19 avril 2023. A été considéré comme OMV, tout enfant qui n'avait pas reçu les vaccins indiqués à l’issue de sa visite même s'il avait dépassé l'âge recommandé pour les recevoir selon la politique du pays.
Un échantillon de convenance par défaut a été utilisé avec au minimum, 100 enfants sélectionnés (50 âgés de 0-23 mois et 50 âgés de 24-59 mois) dans chaque ES. Les données ont été recueillies à l'aide d’un questionnaire anonyme standardisé MSF puis saisies dans une base de données Excel développé par MSF où les indicateurs ont été calculés automatiquement. Cette évaluation a reçu les approbations du comité national d’éthique et du comité d’éthique de MSF.
RESULTATS
Sur 357 enfants (0-23 mois=182 ; 24-59 mois=175) éligibles pour une vaccination, 300 ont présenté une OMV soit une prévalence des OMV de 84% (300/357). Parmi les enfants avec OMV, 53% (159/300) avait 24-59 mois. Ceux de 0-23 mois, cible du PEV, représentaient 47% (141/300). Le vaccin antirougeoleux (56%) et le vaccin antipoliomyélitique oral (50%) ont été les plus manqués. Nous notons que 41% (124/300) des enfants avec OMV étaient présents dans ces ES pour une vaccination. Le manque d’information (47%) et les ruptures de vaccins (38%) étaient les principales raisons invoquées par les participants pour justifier les OMV.
CONCLUSIONS
Nos résultats montrent la nécessité d’intégrer l’évaluation des OMV dans le système de santé en tant que processus de routine et d’assurer un approvisionnement constant et suffisant en vaccins et matériel de vaccination.
CONTEXTE ET OBJECTIFS
Les épidémies de maladies évitables par la vaccination sont récurrentes en Guinée. En 2020, Matoto a enregistré 86% des cas de rougeole rapportés à Conakry. Cette étude avait pour objectif d’évaluer les occasions manquées de vaccination chez les enfants de 0-59 mois.
METHODES
Il s’agissait d’une étude transversale par entretien de sortie dans quatre établissements de santé (ES) de Matoto (Bernay Fotoba, Saint Gabriel, Tombolia, Dabompa) du 11-19 avril 2023. A été considéré comme OMV, tout enfant qui n'avait pas reçu les vaccins indiqués à l’issue de sa visite même s'il avait dépassé l'âge recommandé pour les recevoir selon la politique du pays.
Un échantillon de convenance par défaut a été utilisé avec au minimum, 100 enfants sélectionnés (50 âgés de 0-23 mois et 50 âgés de 24-59 mois) dans chaque ES. Les données ont été recueillies à l'aide d’un questionnaire anonyme standardisé MSF puis saisies dans une base de données Excel développé par MSF où les indicateurs ont été calculés automatiquement. Cette évaluation a reçu les approbations du comité national d’éthique et du comité d’éthique de MSF.
RESULTATS
Sur 357 enfants (0-23 mois=182 ; 24-59 mois=175) éligibles pour une vaccination, 300 ont présenté une OMV soit une prévalence des OMV de 84% (300/357). Parmi les enfants avec OMV, 53% (159/300) avait 24-59 mois. Ceux de 0-23 mois, cible du PEV, représentaient 47% (141/300). Le vaccin antirougeoleux (56%) et le vaccin antipoliomyélitique oral (50%) ont été les plus manqués. Nous notons que 41% (124/300) des enfants avec OMV étaient présents dans ces ES pour une vaccination. Le manque d’information (47%) et les ruptures de vaccins (38%) étaient les principales raisons invoquées par les participants pour justifier les OMV.
CONCLUSIONS
Nos résultats montrent la nécessité d’intégrer l’évaluation des OMV dans le système de santé en tant que processus de routine et d’assurer un approvisionnement constant et suffisant en vaccins et matériel de vaccination.
Shorter but effective tuberculosis treatment regimens would be of value to the tuberculosis treatment community. High-dose rifampicin has been associated with more rapid and secure lung sterilization and may enable shorter tuberculosis treatment regimens.
METHODS
We randomly assigned adults who were given a diagnosis of rifampicin-susceptible pulmonary tuberculosis to a 6-month control regimen, a similar 4-month regimen of rifampicin at 1200?mg/d (study regimen 1 [SR1]), or a 4-month regimen of rifampicin at 1800?mg/d (study regimen 2 [SR2]). Sputum specimens were collected at regular intervals. The primary end point was a composite of treatment failure and relapse in participants who were sputum smear positive at baseline. The noninferiority margin was 8 percentage points. Using a sequence of ordered hypotheses, noninferiority of SR2 was tested first.
RESULTS
Between January 2017 and December 2020, 672 patients were enrolled in six countries, including 191 in the control group, 192 in the SR1 group, and 195 in the SR2 group. Noninferiority was not shown. Favorable responses rates were 93, 90, and 87% in the control, SR1, and SR2 groups, respectively, for a country-adjusted absolute risk difference of 6.3 percentage points (90% confidence interval, 1.1 to 11.5) comparing SR2 with the control group. The proportions of participants experiencing a grade 3 or 4 adverse event were 4.0, 4.5, and 4.4% in the control, SR1, and SR2 groups, respectively.
CONCLUSIONS
Four-month high-dose rifampicin regimens did not have dose-limiting toxicities or side effects but failed to meet noninferiority criteria compared with the standard 6-month control regimen for treatment of pulmonary tuberculosis.