Hemlock Caitlin, Kwong Laura H, Fernald Lia C H, Hubbard Alan E, Colford John M, Tofail Fahmida, Rahman Md Mahbubur, Parvez Sarker, Luby Stephen P, Mertens Andrew N
Department of Environmental and Occupational Health, University of Washington, Seattle, WA, USA.
Division of Epidemiology, School of Public Health, University of California, Berkeley, Berkeley, CA, USA.
medRxiv. 2025 Jun 18:2025.06.17.25329796. doi: 10.1101/2025.06.17.25329796.
Understanding who benefits most from investments in water, sanitation, and hygiene (WaSH) interventions can elucidate causal pathways, uncover complex interactions between population characteristics and interventions, and inform targeted implementation. We applied machine learning to identify and describe households of children that benefited most from WaSH and nutrition interventions.
We used causal forests and baseline characteristics of pregnant women enroled in a trial in Bangladesh (2013-2015) to test for heterogenous treatment effects of the primary trial outcomes at two years (length-for-age Z-score [LAZ-score] and diarrhoea prevalence) and one secondary outcome (child development [EASQ Z-score]) for each treatment-outcome combination. We split households into three groups based on predicted treatment effect magnitude and compared characteristics of those that benefitted the most (Tercile 3) versus the least (Tercile 1).
Heterogeneity was detected in the effect of Sanitation on EASQ Z-score, compared to Control; children in Tercile 3 were estimated to gain 0.51 SD (95% CI: 0.35, 0.67) whereas children in Tercile 1 were estimated to have no benefit. At baseline, households of children in Tercile 3 were more likely to report that chickens always entered the house (85% vs. 4%) and had animal feces observed in the child's play area (84% vs. 18%) when compared with Tercile 1. Tercile 3 households also owned less land and assets and lived further from Dhaka, any population center, or a market. We did not detect heterogeneity for any other treatment-outcome comparison.
We did not detect heterogeneity in any treatment arms for the outcomes of diarrhoea or LAZ-score, showing that children from all backgrounds benefit from effective interventions equally based on household characteristics. We found heterogeneity in the effect of receiving sanitation improvements on child development, where poorer households located in more remote areas and potentially with higher levels of animal fecal contamination had the highest expected benefit.
了解哪些人能从水、环境卫生和个人卫生（WaSH）干预措施的投资中获益最多，有助于阐明因果路径，揭示人口特征与干预措施之间的复杂相互作用，并为有针对性的实施提供信息。我们应用机器学习来识别和描述从WaSH和营养干预措施中获益最多的儿童家庭。
我们利用因果森林和参与孟加拉国一项试验（2013 - 2015年）的孕妇的基线特征，针对每种治疗 - 结果组合，测试两年时主要试验结果（年龄别身长Z评分[LAZ评分]和腹泻患病率）以及一个次要结果（儿童发育[EASQ Z评分]）的异质性治疗效果。我们根据预测的治疗效果大小将家庭分为三组，并比较获益最多（第三分位组）与获益最少（第一分位组）的家庭特征。
与对照组相比，在环境卫生对EASQ Z评分的影响方面检测到异质性；估计第三分位组的儿童获得0.51标准差（95%置信区间：0.35，0.67），而第一分位组的儿童估计没有获益。在基线时，与第一分位组相比，第三分位组儿童的家庭更有可能报告鸡总是进入屋内（85%对4%），并且在儿童游乐区观察到动物粪便（84%对18%）。第三分位组的家庭拥有的土地和资产也较少，居住地点离达卡、任何人口中心或市场更远。对于任何其他治疗 - 结果比较，我们未检测到异质性。
在腹泻或LAZ评分结果的任何治疗组中，我们均未检测到异质性，这表明基于家庭特征，来自所有背景的儿童均能从有效干预措施中平等获益。我们发现改善环境卫生对儿童发育的影响存在异质性，其中位于更偏远地区且可能动物粪便污染水平较高的较贫困家庭预期获益最高。
