Predicting the drop out from the maternal, newborn and child healthcare continuum in three East African Community countries: application of machine learning models

BACKGROUND

For optimal health, the maternal, newborn, and child healthcare (MNCH) continuum necessitates that the mother/child receive the full package of antenatal, intrapartum, and postnatal care. In sub-Saharan Africa, dropping out from the MNCH continuum remains a challenge. Using machine learning, the study sought to forecast the MNCH continuum drop out and determine important predictors in three East African Community (EAC) countries.

METHODS

The study utilised Demographic Health Surveys data from the Democratic Republic of Congo (DRC) (2013/14), Kenya (2014) and Tanzania (2015/16). STATA 17 was used to perform the multivariate logistic regression. Python 3.0 was used to build five machine learning classification models namely the Logistic Regression, Random Forest, Decision Tree, Support Vector Machine and Artificial Neural Network. Performance of the models was assessed using Accuracy, Precision, Recall, Specificity, F1 score and area under the Receiver Operating Characteristics (AUROC).

RESULTS

The prevalence of the drop out from the MNCH continuum was 91.0% in the DRC, 72.4% in Kenya and 93.6% in Tanzania. Living in the rural areas significantly increased the odds of dropping out from the MNCH continuum in the DRC (AOR:1.76;95%CI:1.30-2.38), Kenya (AOR:1.23;95%CI:1.03-1.47) and Tanzania (AOR:1.41;95%CI:1.01-1.97). Lower maternal education also conferred a significant increase in the DRC (AOR:2.16;95%CI:1.67-2.79), Kenya (AOR:1.56;95%CI:1.30-1.84) and Tanzania (AOR:1.70;95%CI:1.24-2.34). Non exposure to mass media also conferred a significant positive influence in the DRC (AOR:1.49;95%CI:1.15-1.95), Kenya (AOR:1.46;95%CI:1.19-1.80) and Tanzania (AOR:1.65;95%CI:1.13-2.40). The Random Forest exhibited superior predictive accuracy (Accuracy = 75.7%, Precision = 79.1%, Recall = 92.1%, Specificity = 51.6%, F1 score = 85.1%, AUROC = 70%). The top four predictors with the greatest influence were household wealth, place of residence, maternal education and exposure to mass media.

CONCLUSIONS

The MNCH continuum dropout rate is very high in the EAC countries. Maternal education, place of residence, and mass media exposure were common contributing factors to the drop out from MNCH continuum. The Random Forest had the highest predictive accuracy. Household wealth, place of residence, maternal education and exposure to mass media were ranked among the top four features with significant influence. The findings of this study can be used to support evidence-based decisions in MNCH interventions and to develop web-based services to improve continuity of care retention.

Mediators of Ethnic Differences in Dropout Rates From a Randomized Controlled Treatment Trial Among Latinx and Non-Latinx White Primary Care Patients With Anxiety Disorders

ABSTRACT

Disparities in treatment engagement and adherence based on ethnicity have been widely recognized but are inadequately understood. Few studies have examined treatment dropout among Latinx and non-Latinx White (NLW) individuals. Using Andersen's Behavioral Model of Health Service Use (A behavioral model of families' use of health services. 1968; J Health Soc Behav. 1995; 36:1-10) as a framework, we examine whether pretreatment variables (categorized as predisposing, enabling, and need factors) mediate the relationship between ethnicity and premature dropout in a sample of Latinx and NLW primary care patients with anxiety disorders who participated in a randomized controlled trial (RCT) of cognitive behavioral therapy. Data from a total of 353 primary care patients were examined; 96 Latinx and 257 NLW patients participated. Results indicated that Latinx patients dropped out of treatment more often than NLW patients, resulting in roughly 58% of Latinx patients failing to complete treatment compared with 42% of NLW, and approximately 29% of Latinx patients dropping out before engaging in modules related to cognitive restructuring or exposure, relative to 11% of NLW patients. Mediation analyses suggest that social support and somatization partially explained the relationship between ethnicity and treatment dropout, highlighting the importance of these variables in understanding treatment disparities.

"I just keep quiet about it and act as if everything is alright" - The cascade from trauma to disengagement among adolescents living with HIV in western Kenya

INTRODUCTION

There are approximately 1.7 million adolescents living with HIV (ALHIV, ages 10 to 19) globally, including 110,000 in Kenya. While ALHIV experience poor retention in care, limited data exist on factors underlying disengagement. We investigated the burden of trauma among disengaged ALHIV in western Kenya, and its potential role in HIV care disengagement.

METHODS

We performed in-depth qualitative interviews with ALHIV who had disengaged from care at two sites, their caregivers and healthcare workers (HCW) at 10 sites, from 2018 to 2020. Disengagement was defined as not attending clinic ≥60 days past a missed scheduled visit. ALHIV and their caregivers were traced through phone calls and home visits. Interviews ascertained barriers and facilitators to adolescent retention in HIV care. Dedicated questions elicited narratives surrounding traumatic experiences, and the ways in which these did or did not impact retention in care. Through thematic analysis, a conceptual model emerged for a cascade from adolescent experience of trauma to disengagement from HIV care.

RESULTS

Interviews were conducted with 42 disengaged ALHIV, 34 caregivers and 28 HCW. ALHIV experienced a high burden of trauma from a range of stressors, including experiences at HIV disclosure or diagnosis, the loss of parents, enacted stigma and physical or sexual violence. A confluence of factors - trauma, stigma and isolation, and lack of social support - led to hopelessness and depression. These factors compounded each other, and resulted in complex mental health burdens, poor antiretroviral adherence and care disengagement. HCW approaches aligned with the factors in this model, suggesting that these areas represent targets for intervention and provision of trauma-informed care.

CONCLUSIONS

Trauma is a major factor underlying disengagement from HIV care among Kenyan adolescents. We describe a cascade of factors representing areas for intervention to support mental health and retention in HIV care. These include not only the provision of mental healthcare, but also preventing or addressing violence, trauma and stigma, and reinforcing social and familial support surrounding vulnerable adolescents. In this conceptualization, supporting retention in HIV care requires a trauma-informed approach, both in the individualized care of ALHIV and in the development of strategies and policies to support adolescent health outcomes.

Pre-diagnostic drop out of presumptive TB patients and its associated factors at Bugembe Health Centre IV in Jinja, Uganda

BACKGROUND

Drop out of presumptive TB individuals before making a final diagnosis poses a danger to the individual and their community. We aimed to determine the proportion of these presumptive TB drop outs and their associated factors in Bugembe Health Centre, Jinja, Uganda.

METHODS

We used data from the DHIS2, presumptive and laboratory registers of Bugembe Health Centre IV for 2017. Descriptive statistics were used to summarize the population characteristics. A modified Poisson regression model via the generalized linear model (GLM) with log link and robust standard errors was used for bivariate and multivariate analysis.We used data from the DHIS2, presumptive and laboratory registers of Bugembe Health Centre IV for 2017. Descriptive statistics were used to summarize the population characteristics. A modified Poisson regression model via the generalized linear model (GLM) with log link and robust standard errors was used for bivariate and multivariate analysis.

RESULT

Among the 216 registered presumptive TB patients who were less than 1% of patients visiting the outpatients' department, 40.7% dropped out before final diagnosis was made. Age and HIV status were significantly associated with pre-diagnostic drop out while gender and distance from the health center were not.

CONCLUSION

A high risk to individuals and the community is posed by the significant proportion of presumptive TB patients dropping out before final diagnosis. Health systems managers need to consider interventions targeting young persons, male patients, HIV positive persons.

Mental Health Disparities, Treatment Engagement, and Attrition Among Racial/Ethnic Minorities with Severe Mental Illness: A Review

Mounting evidence indicates that there are mental health disparities in the United States that disadvantage racial/ethnic minorities in medical and mental health settings. Less is known, however, about how these findings apply to a particularly vulnerable population, individuals with severe mental illness (SMI). The aim of this paper is to (1) provide a critical review of the literature on racial/ethnic disparities in mental health care among individuals with SMI; (2) identify factors which may contribute to the observed disparities; and (3) generate recommendations on how best to address these disparities. Specifically, this article provides an in-depth review of sociocultural factors that may contribute to differences in treatment engagement and rates of attrition from treatment among racial/ethnic minorities with SMI who present at medical and mental health facilities. This review is followed by a discussion of specific strategies that may promote engagement in mental health services and therefore reduce racial/ethnic disparities in SMI.

Sorafenib in Japanese Patients with Locally Advanced or Metastatic Medullary Thyroid Carcinoma and Anaplastic Thyroid Carcinoma

BACKGROUND

Therapeutic options for treating advanced or metastatic medullary thyroid carcinoma (MTC) and anaplastic thyroid carcinoma (ATC) are still limited in Japan, even though vandetanib for MTC and lenvatinib for MTC and ATC have been approved. Sorafenib is an oral multikinase inhibitor approved for the treatment of patients with radioactive iodine-refractory differentiated thyroid cancer (DTC). An uncontrolled, open-label, multicenter, single-arm, Phase 2 clinical study was conducted to evaluate the safety and efficacy of sorafenib in Japanese patients with MTC and ATC.

METHODS

Japanese patients with histologically confirmed ATC and locally advanced or metastatic MTC were enrolled from April to September 2014. The primary endpoint was to evaluate the safety of sorafenib. Treatment efficacy variables including progression-free survival (PFS), overall survival (OS), objective response rate (ORR), disease control rate (DCR), and maximum reduction in tumor size were evaluated as secondary endpoints. Patients received sorafenib 400 mg orally twice daily on a continuous basis and then continued treatment until the occurrence of disease progression, unacceptable toxicity, or withdrawal of consent.

RESULTS

A total of 20 patients were screened, and 18 (8 with MTC and 10 with ATC) were enrolled. The most common drug-related adverse events were palmar-plantar erythrodysesthesia (72%), alopecia (56%), hypertension (56%), and diarrhea (44%). In the ATC patients, median PFS was 2.8 months [confidence interval 0.7-5.6], and median OS was 5.0 months [confidence interval 0.7-5.7]; ORR and DCR were 0% and 40%, respectively. In the MTC population, neither median PFS nor OS had been reached at the time of this analysis; ORR was 25% and DCR was 75%.

CONCLUSIONS

The toxicities reported in this study were consistent with the known safety profile of sorafenib. Sorafenib seems to be effective in the treatment of advanced MTC but not ATC, and could be a new treatment option for locally advanced or metastatic MTC and radioactive iodine-refractory DTC.

Growth of Infants Fed Formula with Evolving Nutrition Composition: A Single-Arm Non-Inferiority Study

The nutritional composition of human milk evolves over the course of lactation, to match the changing needs of infants. This single-arm, non-inferiority study evaluated growth against the WHO standards in the first year of life, in infants consecutively fed four age-based formulas with compositions tailored to infants' nutritional needs during the 1st, 2nd, 3rd-6th, and 7th-12th months of age. Healthy full-term formula-fed infants (n = 32) were enrolled at ≤14 days of age and exclusively fed study formulas from enrollment, to the age of four months. Powdered study formulas were provided in single-serving capsules that were reconstituted using a dedicated automated preparation system, to ensure precise, hygienic preparation. The primary outcome was the weight-for-age z-score (WAZ) at the age of four months (vs. non-inferiority margin of -0.5 SD). Mean (95% CI) z-scores for the WAZ (0.12 (-0.15, 0.39)), as well as for the length-for-age (0.05 (-0.19, 0.30)), weight-for-length (0.16 (-0.16, 0.48)), BMI-for-age (0.11 (-0.20, 0.43)), and head circumferencefor-age (0.41 (0.16, 0.65)) at the age of four months, were non-inferior. Throughout the study, anthropometric z-scores tracked closely against the WHO standards (within ±1 SD). In sum, a fourstage, age-based infant formula system with nutritional compositions tailored to infants' evolving needs, supports healthy growth consistent with WHO standards, for the first year of life.

Culturally Competent Strategies for Recruitment and Retention of African American Populations into Clinical Trials

PURPOSE

To identify successful recruitment strategies, challenges and best practices for researchers to engage African American communities in clinical studies taken into consideration target participants' culture and context.

METHODS

We reviewed 50 studies conducted from 2001 to 2012 at an inner-city research center to determine the type, duration, anticipated enrollments and actual enrollments. Survey was sent to study coordinators to obtain data on recruitment and retention strategies, challenges and dropout rates. We also interviewed 25 study coordinators on challenges and strategies.

RESULTS

Of the 50 studies, 24 had completed recruitment at the time of this report. The completed studies achieved a median recruitment rate of 88% (range: 50-110). Successful recruitment and retention strategies included: field-based strategy and snowballing. Major barriers were: distrust, compensation, education disadvantage, lack of interest, and inability to have study partner. Strategies to reduce barriers included providing informational sessions, disseminating newsletters about study outcomes. Best practices include being culturally sensitive including demonstrating a caring attitude and being responsive to participants needs.

CONCLUSIONS

Cultural competence is critical in order to design and implement successful recruitment strategies in this population. Research teams should consist of multiethnic staff, involve the community, demonstrate trust and deliver concise education of the research endeavor.