Estimating the global impact of poor quality of care on maternal and neonatal outcomes in 81 low- and middle-income countries: A modeling study

Abstract

Background: In low-resource settings where disease burdens remain high and many health facilities lack essentials such as drugs or commodities, functional equipment, and trained personnel, poor quality of care often results and the impact can be profound. In this paper, we systematically quantify the potential gain of addressing quality of care globally using country-level data about antenatal, childbirth, and postnatal care interventions.

Methods and findings: In this study, we created deterministic models to project health outcomes if quality of care was addressed in a representative sample of 81 low- and middle-income countries (LMICs). First, available data from health facility surveys (e.g., Service Provision Assessment [SPA] and Service Availability and Readiness Assessment [SARA]) conducted 2007-2016 were linked to household surveys (e.g., Demographic and Health Surveys [DHS] and Multiple Indicator Cluster Surveys [MICS]) to estimate baseline coverage for a core subset of 19 maternal and newborn health interventions. Next, models were constructed with the Lives Saved Tool (LiST) using country-specific baseline levels in countries with a linked dataset (n = 17) and sample medians applied as a proxy in countries without linked data. Lastly, these 2016 starting baseline levels were raised to reach targets in 2020 as endline based upon country-specific utilization (e.g., proportion of women who attended 4+ antenatal visits, percentage of births delivered in a health facility) from the latest DHS or MICS population-based reports. Our findings indicate that if high-quality health systems could effectively deliver this subset of evidence-based interventions to mothers and their newborns who are already seeking care, there would be an estimated 28% decrease in maternal deaths, 28% decrease in neonatal deaths, and 22% fewer stillbirths compared to a scenario without any change or improvement in quality of care. Totals of 86,000 (range, 77,800-92,400) maternal and 0.67 million (range, 0.59 million-0.75 million) neonatal lives could be saved, and 0.52 million (range, 0.48 million-0.55 million) stillbirths could be prevented across the 81 countries in the calendar year 2020 when adequate quality care is provided at current levels of utilization. Limitations include the paucity of data to individually assess quality of care for each intervention in all LMICs and the necessary assumption that quality of care being provided among the subset of countries with linked datasets is comparable or representative of LMICs overall.

Conclusions: Our findings suggest that efforts to close the quality gap would still produce substantial benefits at current levels of access or utilization. With estimated mortality rate declines of 21%-32% on average, gains from this first step would be significant if quality was improved for selected antenatal, intrapartum, and postnatal interventions to benefit pregnant women and newborns seeking care. Interventions provided at or around the time of childbirth are most critical and accounted for 64% of the impact overall estimated in this quality improvement analysis.

Fig 1. Framework for evaluation of health systems.

The conceptual model of the LiST depicted with applicable data sources. LiST, Lives Saved Tool.

Fig 2. Impact pathways for the LiST (Version 5.67).

Interventions provided during antenatal, childbirth, and postnatal care are shown with associated risk factors and mortality outcomes. AMTSL, active management of the third stage of labor; IPTp, Intermittent preventive treatment in pregnancy; LiST, Lives Saved Tool; pPRoM, preterm premature rupture of the membranes; SGA, small for gestational age.

Fig 3. Bar graph of estimated impact in 81 LMICs, with 2020 as the target year.

The total number of maternal (tan) and neonatal (orange) lives saved and stillbirths prevented (green) organized by the timing of delivery for the evidence-based intervention. LMIC, low- and middle-income country.

Fig 4. Boxplot of estimated mortality change quantified in 81 LMICs comparing 2020 (endline) to 2016 (baseline).

Bars represent the 25th, 50th (middle), and 75th percentiles for the percent change in MMR, neonatal mortality rate, and stillbirth rate. The outliers include Somalia and South Sudan, which were estimated to have very modest reductions in MMR. LMIC, low- and middle-income country; MMR, maternal mortality ratio.