Boris Martinez

An mHealth monitoring system for traditional birth attendant-led antenatal risk assessment in rural Guatemala.

Abstract Limited funding for medical technology, low levels of education and poor infrastructure for delivering and maintaining technology severely limit medical decision support in low- and middle-income countries. Perinatal and maternal mortality is of particular concern with millions dying every year from potentially treatable conditions. Guatemala has one of the worst maternal mortality ratios, the highest incidence of intra-uterine growth restriction (IUGR), and one of the lowest gross national incomes per capita within Latin America. To address the lack of decision support in rural Guatemala, a smartphone-based system is proposed including peripheral sensors, such as a handheld Doppler for the identification of foetal compromise. Designed for use by illiterate birth attendants, the system uses pictograms, audio guidance, local and cloud processing, SMS alerts and voice calling. The initial prototype was evaluated on 22 women in highland Guatemala. Results were fed back into the refinement of the system, currently undergoing RCT evaluation.

Implementation and Outcomes of a Comprehensive Type 2 Diabetes Program in Rural Guatemala

Background The burden of chronic, non-communicable diseases such as diabetes is growing rapidly in low- and middle-income countries. Implementing management programs for diabetes and other chronic diseases for underserved populations is thus a critical global health priority. However, there is a notable dearth of shared programmatic and outcomes data from diabetes treatment programs in these settings. Program Description We describe our experiences as a non-governmental organization designing and implementing a type 2 diabetes program serving Maya indigenous people in rural Guatemala. We detail the practical challenges and solutions we have developed to build and sustain diabetes programming in this setting. Methods We conduct a retrospective chart review from our electronic medical record to evaluate our program’s performance. We generate a cohort profile, assess cross-sectional indicators using a framework adapted from the literature, and report on clinical longitudinal outcomes. Results A total of 142 patients were identified for the chart review. The cohort showed a decrease in hemoglobin A1C from a mean of 9.2% to 8.1% over an average of 2.1 years of follow-up (p <0.001). The proportions of patients meeting glycemic targets were 53% for hemoglobin A1C < 8% and 32% for the stricter target of hemoglobin A1C < 7%. Conclusion We first offer programmatic experiences to address a gap in resources relating to the practical issues of designing and implementing global diabetes management interventions. We then present clinical data suggesting that favorable diabetes outcomes can be attained in poor areas of rural Guatemala.

Case reportAccompanying indigenous Maya patients with complex medical needs: A patient navigation system in rural Guatemala

a Wuqu’ Kawoq | Maya Health Alliance, Guatemala b Department of Emergency Medicine, Massachusetts General Hospital, United States c Departments of Internal Medicine and Pediatrics, University of Minnesota, United States d Division of Women’s Health, Department of Medicine, Brigham and Women’s Hospital, United States e University of California, San Francisco, United States f Burrell College of Osteopathic Medicine, United States g Division of Global Health Equity, Brigham and Women’s Hospital, United States

Insights into Global Health Practice from the Agile Software Development Movement

Global health practitioners may feel frustration that current models of global health research, delivery, and implementation are overly focused on specific interventions, slow to provide health services in the field, and relatively ill-equipped to adapt to local contexts. Adapting design principles from the agile software development movement, we propose an analogous approach to designing global health programs that emphasizes tight integration between research and implementation, early involvement of ground-level health workers and program beneficiaries, and rapid cycles of iterative program improvement. Using examples from our own fieldwork, we illustrate the potential of ‘agile global health’ and reflect on the limitations, trade-offs, and implications of this approach.

Improving the Quality of Point of Care Diagnostics with Real-Time Machine Learning in Low Literacy LMIC Settings

The scalability of medical technology in low resource settings requires a higher level of usability and clear decision support compared to conventional devices, since users often have very limited training. In particular, it is important to provide users with real time feedback on data quality during the patient information acquisition in a manner that enables the user to take immediate corrective action. In this work, we present an example of such a system, which provides real time feedback on the source of noise and interference on a low cost Doppler device connected to a smart-phone used by traditional birth attendants (TBAs) in rural Guatemala. A total of 195 fetal recordings made from 146 singleton pregnancies in the second and third trimester were recorded over 8 months by 19 TBAs. The resulting 33.7 hours of data were segmented into 0.75 s epochs and independently labeled by three trained researchers into one of five noise or quality categories that dominated the data. A two-step classifier, composed of a logistic regression and a multiclass support vector machine, was then trained to classify the data on epochs from 0.75 s to 3.75 s. After feature selection the highest micro-averaged test F1 score was 96.8% and macro-average F1 test score was 94.5% for 3.75 s segments using 23 features. A reduced real time model with 17 features produced comparable micro-and macro-averaged test F1 scores of 96.0% and 94.5% respectively. The code is portable back to a low-end smartphone to run on such a device in real time (under 400 ms) in order to provide an audiovisual cue for the TBAs via the smartphone. Future work will evaluate the classifier presented here as part of a decision support system for data quality improvement in an ongoing randomized control trial in Guatemala.

mHealth intervention to improve the continuum of maternal and perinatal care in rural Guatemala: a pragmatic, randomized controlled feasibility trial

Background/objectiveGuatemala’s indigenous Maya population has one of the highest perinatal and maternal mortality rates in Latin America. In this population most births are delivered at home by traditional birth attendants (TBAs), who have limited support and linkages to public hospitals. The goal of this study was to characterize the detection of maternal and perinatal complications and rates of facility-level referral by TBAs, and to evaluate the impact of a mHealth decision support system on these rates.MethodsA pragmatic one-year feasibility trial of an mHealth decisions support system was conducted in rural Maya communities in collaboration with TBAs. TBAs were individually randomized in an unblinded fashion to either early-access or later-access to the mHealth system. TBAs in the early-access arm used the mHealth system throughout the study. TBAs in the later-access arm provided usual care until crossing over uni-directionally to the mHealth system at the study midpoint. The primary study outcome was the monthly rate of referral to facility-level care, adjusted for birth volume.ResultsForty-four TBAs were randomized, 23 to the early-access arm and 21 to the later-access arm. Outcomes were analyzed for 799 pregnancies (early-access 425, later-access 374). Monthly referral rates to facility-level care were significantly higher among the early-access arm (median 33 referrals per 100 births, IQR 22–58) compared to the later-access arm (median 20 per 100, IQR 0–30) (p = 0.03). At the study midpoint, the later-access arm began using the mHealth platform and its referral rates increased (median 34 referrals per 100 births, IQR 5–50) with no significant difference from the early-access arm (p = 0.58). Rates of complications were similar in both arms, except for hypertensive disorders of pregnancy, which were significantly higher among TBAs in the early-access arm (RR 3.3, 95% CI 1.10–9.86).ConclusionsReferral rates were higher when TBAs had access to the mHealth platform. The introduction of mHealth supportive technologies for TBAs is feasible and can improve detection of complications and timely referral to facility-care within challenging healthcare delivery contexts.Trial registrationClinicaltrials.gov NCT02348840.

Complementary feeding intervention on stunted Guatemalan children: a randomised controlled trial

Objective/background Guatemala’s indigenous Maya population has one of the highest rates of childhood stunting in the world. The goal of this study was to examine the impact of an intensive, individualised approach to complementary feeding education for caregivers on feeding practices and growth over usual care. Design An individually randomised (1:1 allocation ratio), parallel-group superiority trial, with blinding of study staff collecting outcome data. Setting Rural Maya communities in Guatemala. Participants 324 children aged 6–24 months with a height-for-age Z score of less than or equal to −2.5 SD were randomised, 161 to the intervention and 163 to usual care. Interventions Community health workers conducted home visits for 6 months, providing usual care or usual care plus individualised caregiver education. Main outcomes measures The main outcome was change in length/height-for-age Z score. Secondary outcomes were changes in complementary feeding indicators. Results Data were analysed for 296 subjects (intervention 145, usual care 151). There was a non-significant trend to improved growth in the intervention arm (length/height-for-age Z score change difference 0.07(95% CI −0.04 to 0.18)). The intervention led to a 22% improvement in minimum dietary diversity (RR 1.22, 95% CI 1.11 to 1.35) and a 23% improvement in minimal acceptable diet (RR 1.23, 95% CI 1.08 to 1.40) over usual care. Conclusions Complementary feeding outcomes improved in the intervention arm, and a non-significant trend towards improved linear growth was observed. Community health workers in a low-resource rural environment can implement individualised caregiver complementary feeding education with significant improvements in child dietary quality over standard approaches. Clinical trial registration number NCT02509936. Stage: Results

Developmental outcomes of an individualised complementary feeding intervention for stunted children: a substudy from a larger randomised controlled trial in Guatemala

Objective Stunting is a common cause of early child developmental delay; Guatemala has the fourth highest rate of stunting globally. The goal of this study was to examine the impact of an intensive community health worker-led complementary feeding intervention on early child development in Guatemala. We hypothesised that the intervention would improve child development over usual care. Design A substudy from a larger individually randomised (1:1 allocation ratio), parallel-group superiority trial, with blinding of study staff collecting outcomes data. Setting Rural, indigenous Maya communities in Guatemala. Participants 210 stunted children (height-for-age z-score ≤−2.5) aged 6–24 months, previously randomised to usual care (106) or an intensive complementary feeding intervention (104). 84 in the intervention and 91 in the usual care arm agreed to participate. Interventions Community health workers conducted monthly home visits for 6 months, providing usual care or individualised complementary feeding education. Main outcome measures The primary outcomes were change in z-scores for the subscales of the Bayley Scales of Infant Development (BSID), Third Edition. Results 100 individuals were included in the final analysis, 47 in the intervention and 53 in the usual care arm. No statistically significant differences in age-adjusted scores between the arms were observed for any subscale. However, improvements within-subjects in both arms were observed (median duration between measurements 189 days (IQR 182–189)). Mean change for subscales was 0.45 (95% CI 0.23 to 0.67) z-scores in the intervention, and 0.43 (95% CI 0.25 to 0.61) in the usual care arm. Conclusions An intensive complementary feeding intervention did not significantly improve developmental outcomes more than usual care in stunted, indigenous Guatemalan children. However, both interventions had significant positive impacts on developmental outcomes. Trial registration number NCT02509936. Stage Results.

A quality improvement project using statistical process control methods for type 2 diabetes control in a resource-limited setting.

Quality issue Quality improvement (QI) is a key strategy for improving diabetes care in low- and middle-income countries (LMICs). This study reports on a diabetes QI project in rural Guatemala whose primary aim was to improve glycemic control of a panel of adult diabetes patients. Initial assessment Formative research suggested multiple areas for programmatic improvement in ambulatory diabetes care. Choice of solution This project utilized the Model for Improvement and Agile Global Health, our organizations complementary healthcare implementation framework. Implementation A bundle of improvement activities were implemented at the home, clinic and institutional level. Evaluation Control charts of mean hemoglobin A1C (HbA1C) and proportion of patients meeting target HbA1C showed improvement as special cause variation was identified 3 months after the intervention began. Control charts for secondary process measures offered insights into the value of different components of the intervention. Intensity of home-based diabetes education emerged as an important driver of panel glycemic control. Lessons learned Diabetes QI work is feasible in resource-limited settings in LMICs and can improve glycemic control. Statistical process control charts are a promising methodology for use with panels or registries of diabetes patients.

Use of propranolol in a remote region of rural Guatemala to treat a large facial infantile haemangioma.

We present a female infant with a right-sided facial and neck haemangioma, from a remote, resource-poor community in rural Guatemala. She received first-line treatment, propranolol, with marked reduction in tumour size and erythema. Treatment was stopped after 35 weeks due to recurrent diarrhoea and sustained weight loss. Propranolol can be used to safely treat infants with haemangiomas in remote, rural communities if there is adequate follow-up, education and communication. Periocular haemangiomas should be treated promptly to avoid visual impairment. Infants with large facial haemangiomas should be screened for Posterior fossa anomalies, Hemangioma, Arterial anomalies, Cardiac anomalies, and Eye anomalies (PHACE) syndrome, and specialists should be involved. The case also highlights the difficulty of providing treatment for a complex illness when basic health needs, such as food security and water sanitation, are limited.