An EMR-Based Alert with Brief Provider-Led ART Adherence Counseling: Promising Results of the InfoPlus Adherence Pilot Study Among Haitian Adults with HIV Initiating ART

"Following the data": perceptions of and willingness to use clinical decision support tools to inform HIV care among Haitian clinicians

Background

Clinical decision support (CDS) tools can support HIV care, including through case tracking, treatment and medication monitoring, and promoting provider compliance with care guidelines. There has been limited research into the technical, organizational, and behavioral factors that impact perceptions of and willingness to use CDS tools at scale in resource-limited settings, including in Haiti.

Methods

Our sample included fifteen purposively chosen Haitian HIV program experts, including active clinicians and HIV program managers. Participants completed structured quantitative surveys and one-on-one qualitative semi-structured interviews.

Results

Study participants had high levels of familiarity and experience with CDS tools. The primary motivator for CDS tool use was a perceived benefit to quality of care, including improved provider time use, efficiency, and decision-making ability, and patient outcomes. Participants highlighted decision-making autonomy and how CDS tools could support provider decision making but should not supplant provider knowledge and experience. Participants highlighted the need for sufficient provider training/sensitization, inclusion of providers in the system design process, and prioritization of tool user-friendliness as key mechanisms to drive tool use and impact. Some participants noted that systemic issues, such as limited laboratory capacity, may reduce the usefulness of CDS alerts, particularly concerning differentiated care and priority viral load testing.

Conclusion

Respondents had largely positive perceptions of EMRs and CDS tools, particularly due to perceived improvements in quality of care. To improve tool use, stakeholders should prioritize tool user-friendliness and provider training. Addressing systemic health system issues is necessary to unlock the full potential of these tools.

Person-centred interventions to improve patient-provider relationships for HIV services in low- and middle-income countries: a systematic review

INTRODUCTION

Person-centred care (PCC) has been recognized as a critical element in delivering quality and responsive health services. The patient-provider relationship, conceptualized at the core of PCC in multiple models, remains largely unexamined in HIV care. We conducted a systematic review to better understand the types of PCC interventions implemented to improve patient-provider interactions and how these interventions have improved HIV care continuum outcomes and person-reported outcomes (PROs) among people living with HIV in low- and middle-income countries.

METHODS

We searched databases, conference proceedings and conducted manual targeted searches to identify randomized trials and observational studies published up to January 2023. The PCC search terms were guided by the Integrative Model of Patient-Centeredness by Scholl. We included person-centred interventions aiming to enhance the patient-provider interactions. We included HIV care continuum outcomes and PROs.

RESULTS

We included 28 unique studies: 18 (64.3%) were quantitative, eight (28.6.%) were mixed methods and two (7.1%) were qualitative. Within PCC patient-provider interventions, we inductively identified five categories of PCC interventions: (1) providing friendly and welcoming services; (2) patient empowerment and improved communication skills (e.g. supporting patient-led skills such as health literacy and approaches when communicating with a provider); (3) improved individualized counselling and patient-centred communication (e.g. supporting provider skills such as training on motivational interviewing); (4) audit and feedback; and (5) provider sensitisation to patient experiences and identities. Among the included studies with a comparison arm and effect size reported, 62.5% reported a significant positive effect of the intervention on at least one HIV care continuum outcome, and 100% reported a positive effect of the intervention on at least one of the included PROs.

DISCUSSION

Among published HIV PCC interventions, there is heterogeneity in the components of PCC addressed, the actors involved and the expected outcomes. While results are also heterogeneous across clinical and PROs, there is more evidence for significant improvement in PROs. Further research is necessary to better understand the clinical implications of PCC, with fewer studies measuring linkage or long-term retention or viral suppression.

CONCLUSIONS

Improved understanding of PCC domains, mechanisms and consistency of measurement will advance PCC research and implementation.

The Roles of Electronic Health Records for Clinical Trials in Low- and Middle-Income Countries: Scoping Review

BACKGROUND

Clinical trials are a crucial element in advancing medical knowledge and developing new treatments by establishing the evidence base for safety and therapeutic efficacy. However, the success of these trials depends on various factors, including trial design, project planning, research staff training, and adequate sample size. It is also crucial to recruit participants efficiently and retain them throughout the trial to ensure timely completion.

OBJECTIVE

There is an increasing interest in using electronic health records (EHRs)-a widely adopted tool in clinical practice-for clinical trials. This scoping review aims to understand the use of EHR in supporting the conduct of clinical trials in low- and middle-income countries (LMICs) and to identify its strengths and limitations.

METHODS

A comprehensive search was performed using 5 databases: MEDLINE, Embase, Scopus, Cochrane Library, and the Cumulative Index to Nursing and Allied Health Literature. We followed the latest version of the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guideline to conduct this review. We included clinical trials that used EHR at any step, conducted a narrative synthesis of the included studies, and mapped the roles of EHRs into the life cycle of a clinical trial.

RESULTS

A total of 30 studies met the inclusion criteria: 13 were randomized controlled trials, 3 were cluster randomized controlled trials, 12 were quasi-experimental studies, and 2 were feasibility pilot studies. Most of the studies addressed infectious diseases (15/30, 50%), with 80% (12/15) of them about HIV or AIDS and another 40% (12/30) focused on noncommunicable diseases. Our synthesis divided the roles of EHRs into 7 major categories: participant identification and recruitment (12/30, 40%), baseline information collection (6/30, 20%), intervention (8/30, 27%), fidelity assessment (2/30, 7%), primary outcome assessment (24/30, 80%), nonprimary outcome assessment (13/30, 43%), and extended follow-up (2/30, 7%). None of the studies used EHR for participant consent and randomization.

CONCLUSIONS

Despite the enormous potential of EHRs to increase the effectiveness and efficiency of conducting clinical trials in LMICs, challenges remain. Continued exploration of the appropriate uses of EHRs by navigating their strengths and limitations to ensure fitness for use is necessary to better understand the most optimal uses of EHRs for conducting clinical trials in LMICs.

Development and validation of a prediction tool to support engagement in HIV care among young people ages 10-24 years in Kenya

INTRODUCTION

Loss to follow-up (LTFU) among adolescents and young adults living with HIV (AYALWH) is a barrier to optimal health and HIV services. We developed and validated a clinical prediction tool to identify AYALWH at risk of LTFU.

METHODS

We used electronic medical records (EMR) of AYALWH ages 10 to 24 in HIV care at 6 facilities in Kenya and surveys from a subset of participants. Early LTFU was defined as >30 days late for a scheduled visit in the last 6 months, which accounts for clients with multi-month refills. We developed a tool combining surveys with EMR ('survey-plus-EMR tool'), and an 'EMR-alone' tool to predict high, medium, and low risk of LTFU. The survey-plus-EMR tool included candidate sociodemographics, partnership status, mental health, peer support, any unmet clinic needs, WHO stage, and time in care variables for tool development, while the EMR-alone included clinical and time in care variables only. Tools were developed in a 50% random sample of the data and internally validated using 10-fold cross-validation of the full sample. Tool performance was evaluated using Hazard Ratios (HR), 95% Confidence Intervals (CI), and area under the curve (AUC) ≥ 0.7 for good performance and ≥0.60 for modest performance.

RESULTS

Data from 865 AYALWH were included in the survey-plus-EMR tool and early LTFU was (19.2%, 166/865). The survey-plus-EMR tool ranged from 0 to 4, including PHQ-9 ≥5, lack of peer support group attendance, and any unmet clinical need. High (3 or 4) and medium (2) prediction scores were associated with greater risk of LTFU (high, 29.0%, HR 2.16, 95%CI: 1.25-3.73; medium, 21.4%, HR 1.52, 95%CI: 0.93-2.49, global p-value = 0.02) in the validation dataset. The 10-fold cross validation AUC was 0.66 (95%CI: 0.63-0.72). Data from 2,696 AYALWH were included in the EMR-alone tool and early LTFU was 28.6% (770/2,696). In the validation dataset, high (score = 2, LTFU = 38.5%, HR 2.40, 95%CI: 1.17-4.96) and medium scores (1, 29.6%, HR 1.65, 95%CI: 1.00-2.72) predicted significantly higher LTFU than low-risk scores (0, 22.0%, global p-value = 0.03). Ten-fold cross-validation AUC was 0.61 (95%CI: 0.59-0.64).

CONCLUSIONS

Clinical prediction of LTFU was modest using the surveys-plus-EMR tool and the EMR-alone tool, suggesting limited use in routine care. However, findings may inform future prediction tools and intervention targets to reduce LTFU among AYALWH.

Predicting Treatment Interruption Among People Living With HIV in Nigeria: Machine Learning Approach

BACKGROUND

Antiretroviral therapy (ART) has transformed HIV from a fatal illness to a chronic disease. Given the high rate of treatment interruptions, HIV programs use a range of approaches to support individuals in adhering to ART and in re-engaging those who interrupt treatment. These interventions can often be time-consuming and costly, and thus providing for all may not be sustainable.

OBJECTIVE

This study aims to describe our experiences developing a machine learning (ML) model to predict interruption in treatment (IIT) at 30 days among people living with HIV newly enrolled on ART in Nigeria and our integration of the model into the routine information system. In addition, we collected health workers' perceptions and use of the model's outputs for case management.

METHODS

Routine program data collected from January 2005 through February 2021 was used to train and test an ML model (boosting tree and Extreme Gradient Boosting) to predict future IIT. Data were randomly sampled using an 80/20 split into training and test data sets, respectively. Model performance was estimated using sensitivity, specificity, and positive and negative predictive values. Variables considered to be highly associated with treatment interruption were preselected by a group of HIV prevention researchers, program experts, and biostatisticians for inclusion in the model. Individuals were defined as having IIT if they were provided a 30-day supply of antiretrovirals but did not return for a refill within 28 days of their scheduled follow-up visit date. Outputs from the ML model were shared weekly with health care workers at selected facilities.

RESULTS

After data cleaning, complete data for 136,747 clients were used for the analysis. The percentage of IIT cases decreased from 58.6% (36,663/61,864) before 2017 to 14.2% (3690/28,046) from October 2019 through February 2021. Overall IIT was higher among clients who were sicker at enrollment. Other factors that were significantly associated with IIT included pregnancy and breastfeeding status and facility characteristics (location, service level, and service type). Several models were initially developed; the selected model had a sensitivity of 81%, specificity of 88%, positive predictive value of 83%, and negative predictive value of 87%, and was successfully integrated into the national electronic medical records database. During field-testing, the majority of users reported that an IIT prediction tool could lead to proactive steps for preventing IIT and improving patient outcomes.

CONCLUSIONS

High-performing ML models to identify patients with HIV at risk of IIT can be developed using routinely collected service delivery data and integrated into routine health management information systems. Machine learning can improve the targeting of interventions through differentiated models of care before patients interrupt treatment, resulting in increased cost-effectiveness and improved patient outcomes.

Effect of characteristics on the clinical course at the initiation of treatment for human immunodeficiency virus infection using dimensionality reduction

The beginning of human immunodeficiency virus (HIV) infection treatment depends on various factors, which are significantly correlated with the initial CD4 cell number. However, a covariate correlation between these factors may not reflect the correct outcome variable. Thus, we evaluated the effects of a combination of fixed factors (reduced dimensions), which determine when to start treatment for the first time, on short-term outcome, long-term outcome, and survival, considering correlations between factors. Multiple correspondence analysis was performed on variables obtained from 925 patients who participated in a Korean HIV/acquired immunodeficiency syndrome cohort study (2006-2017). Five reduced dimension groups were derived according to clinical data, viral load, CD4 cell count at diagnosis, initial antiretroviral therapy, and others. The dimension group with high initial viral loads (55,000 copies/mL) and low CD4 cell counts (< 200 cells/mm³) should start treatment promptly after diagnosis. Groups with high initial CD4 cell counts (> 350 cells/mm³) that did not require immediate treatment according to previous guidelines had a higher failure rate for long-term relative CD4 recovery. Our results highlight the importance of early diagnosis and treatment to positively influence long-term disease outcomes, even if the initial immune status is poor, given the patient's combination of early diagnostic symptoms.

Patient and health worker perspectives on quality of HIV care and treatment services in Haiti

BACKGROUND

Poor quality of care is a barrier to engagement in HIV care and treatment in low- and middle-income country settings. This study involved focus group discussions (FGD) with patients and health workers in two large urban hospitals to describe quality of patient education and psychosocial support services within Haiti's national HIV antiretroviral therapy (ART) program. The purpose of this qualitative study was to illuminate key gaps and salient "ingredients" for improving quality of care.

METHODS

The study included 8 FGDs with a total of 26 male patients and 32 female patients and 15 smaller FGDs with 57 health workers. The analysis used a directed content analysis method, with the goal of extending existing conceptual frameworks on quality of care through rich description.

RESULTS

Dimension of safety, patient-centeredness, accessibility, and equity were most salient. Patients noted risks to privacy with both clinic and community-based services as well as concerns with ART side effects, while health workers described risks to their own safety in providing community-based services. While patients cited examples of positive interactions with health workers that centered their needs and perspectives, they also noted concerns that inhibited trust and satisfaction with services. Health workers described difficult working conditions that challenged their ability to provide patient-centered services. Patients sought favored relationships with health workers to help them navigate the health care system, but this undermined the sense of fairness. Both patients and health workers described frustration with lack of resources to assist patients in dire poverty, and health workers described great pressure to help patients from their "own pockets."

CONCLUSIONS

These concerns reflected the embeddedness of patient - provider interactions within a health system marked by scarcity, power dynamics between patients and health workers, and social stigma related to HIV. Reinforcing a respectful and welcoming atmosphere, timely service, privacy protection, and building patient perception of fairness in access to support could help to build patient satisfaction and care engagement in Haiti. Improving working conditions for health workers is also critical to achieving quality.

Predictive Analytics Using Machine Learning to Identify ART Clients at Health System Level at Greatest Risk of Treatment Interruption in Mozambique and Nigeria

BACKGROUND

A core objective of HIV/AIDS programming is keeping clients on treatment to improve their health outcomes and to limit spread. Machine learning and artificial intelligence can combine client, temporal, and locational attributes to identify which clients are at greatest risk of loss to follow-up (LTFU) and enable health providers to direct support interventions accordingly.

SETTING

The analysis was part of a project funded by U.S. President's Emergency Plan for AIDS Relief and United States Agency for International Development, Data for Implementation, and applied to data from publicly available sources (health facility data, geospatial data, and satellite imagery) and de-identified electronic medical record data on antiretroviral therapy clients in Nigeria and Mozambique.

METHODS

The project applied binary classification techniques using temporal cross-validation to predict the risk that patients would be LTFU. Classifiers included logistic regression, neural networks, and tree-based models.

RESULTS

Models showed strong predictive power in both settings. In Mozambique, the best-performing model, a Random Forest, achieved an area under the precision-recall curve of 0.65 compared against an underlying LTFU rate of 23%. In Nigeria, the best-performing model, a boosted tree, achieved an area under the precision-recall curve of 0.52 compared against an underlying LTFU rate of 27%.

CONCLUSIONS

Machine-learned models outperformed current classification techniques and showed potential to better direct health worker resources toward patients at greatest risk of LTFU. Moreover, models performed equally across sex and age groups, supporting the model's generalizability and wider application.

An EMR-based alert with brief provider-led ART adherence counseling in Haiti: effects on information, motivation, and behavioral skills (IMB) and patient-provider communication (PPC)

We examined the secondary effects of an antiretroviral therapy (ART) adherence intervention on information, motivation, and behavioral skills (IMB) and patient-provider communication (PPC). Data were from a sample of 116 patients enrolled in a quasi-experimental mixed-methods study at two large ART clinics in Haiti. We examined changes in IMB and PPC scores after the intervention and the association between baseline PPC and endline IMB.The intervention was associated with increased scores in information (ß = 0.89, 95% CI [0.07, 1.70]) and motivation (ß = 2.55, 95% CI [0.38, 4.72]) but a decreased score in behavioral skills (ß = -2.39, 95% CI [-4.29, -0.49]), after controlling for demographic and clinical variables. Baseline PPC was associated with higher endline IMB total scores (ß = 0.17, 95% CI [0.02, 0.31]), controlling for demographic variables, clinical variables, and baseline IMB score. At the subscale level, baseline PPC was associated with higher endline motivation score (ß = 0.09, 95% CI [0.01, 0.17]), marginally associated with higher endline information score (ß = 0.04, 95% CI [0.00, 0.08]), after controlling for demographic and clinical variables.The intervention was beneficial to patients' adherence related motivation. Favorable patient-provider communication is associated with more motivation to adhere to ART.

The Situated Information, Motivation, and Behavioral Skills Model of HIV Antiretroviral Therapy Adherence Among Persons Living With HIV in Haiti: A Qualitative Study Incorporating Culture and Context

ABSTRACT

To inform a clinic-based adherence-promotion intervention, this qualitative study applied the Situated Information, Motivation, and Behavioral Skills Model of Care Initiation and Maintenance to elucidate cultural and contextual factors affecting antiretroviral therapy adherence in Haiti. From the 23 focus group discussions with patients (n = 58) and health care workers (n = 57), culturally specific themes emerged relating to Information (e.g., conflicts with allopathic medicine and heuristics about how treatment failure occurs), Motivation (e.g., protecting family members, health and physical appearance, material advantages, and relationships with health workers), and Behavioral Skills (e.g., managing food intake and side effects, navigating health services utilization, accessing medication, and advocating for care needs). Recommendations include: provide therapeutic education on HIV drug resistance; promote the concept of "undetectable = untransmittable"; develop treatment buddy relationships; invest in training and enforcement of patient privacy, transparency, and fairness in access to services and resources; and provide patient-centered behavioral skills counseling.

Patient-Provider Communication and Information, Motivation, and Behavioral Skills in HIV-Positive Adults Initiating Antiretroviral Therapy in Haiti

While Haiti has scaled up use of antiretroviral therapy (ART), current studies suggest sub-optimal adherence threatens long-term viral suppression in this understudied setting. Patient-provider communication (PPC) and information, motivation, and behavioral skills (IMB) have been implicated in ART adherence globally. However, no studies have examined their relevance in Haiti. The present mixed-methods study utilized cross-sectional survey data from 128 ART-initiating patients at 2 large HIV treatment sites in Haiti, as well as observational data from 12 clinic visits, to document associations between adherence-related PPC and IMB. Multivariate regression analyses suggested that PPC is associated with IMB constructs. At the bivariate level, more effective PPC was associated with higher levels of adherence-related information and motivation, but not behavioral skills. Observational findings indicate infrequent and non-collaborative adherence support. Taken together, findings lay the groundwork for additional research in the area of PPC, IMB, and ART adherence in Haiti.

Machine Learning and Clinical Informatics for Improving HIV Care Continuum Outcomes

PURPOSE OF REVIEW

This manuscript reviews the use of electronic medical record (EMR) data for HIV care and research along the HIV care continuum with a specific focus on machine learning methods and clinical informatics interventions.

RECENT FINDINGS

EMR-based clinical decision support tools and electronic alerts have been effectively utilized to improve HIV care continuum outcomes. Accurate EMR-based machine learning models have been developed to predict HIV diagnosis, retention in care, and viral suppression. Natural language processing (NLP) of clinical notes and data sharing between healthcare systems and public health agencies can enhance models for identifying people living with HIV who are undiagnosed or in need of relinkage to care. Challenges related to using these technologies include inconsistent EMR documentation, alert fatigue, and the potential for bias. Clinical informatics and machine learning models are promising tools for improving HIV care continuum outcomes. Future research should focus on methods for combining EMR data with additional data sources (e.g., social media, geospatial data) and studying how to effectively implement predictive models for HIV care into clinical practice.