Public health agencies face critical challenges in identifying high-risk neighborhoods for childhood lead exposure with limited resources for outreach and intervention programs. To address this, we develop a Priority Score integrating untested children proportions, elevated blood lead prevalence, and public health coverage patterns to support optimized resource allocation decisions across 136 neighborhoods in Chicago, New York City, and Washington, D.C. We leverage these allocation tasks, which require integrating multiple vulnerability indicators and interpreting empirical evidence, to evaluate whether large language models (LLMs) with agentic reasoning and deep research capabilities can effectively allocate public health resources when presented with structured allocation scenarios. LLMs were tasked with distributing 1,000 test kits within each city based on neighborhood vulnerability indicators. Results reveal significant limitations: LLMs frequently overlooked neighborhoods with highest lead prevalence and largest proportions of untested children, such as West Englewood in Chicago, while allocating disproportionate resources to lower-priority areas like Hunts Point in New York City. Overall accuracy averaged 0.46, reaching a maximum of 0.66 with ChatGPT 5 Deep Research. Despite their marketed deep research capabilities, LLMs struggled with fundamental limitations in information retrieval and evidence-based reasoning, frequently citing outdated data and allowing non-empirical narratives about neighborhood conditions to override quantitative vulnerability indicators.

The toxic metal may have rewired early human brains--and sealed the Neanderthals' fate. Lead exposure may have negatively affected Neanderthal abilities for language and speech development. Breakthroughs, discoveries, and DIY tips sent every weekday. Today, lead exposure directly correlates to a post-industrialized world. However, new evidence indicates that exposure to the poisonous element is not necessarily a new issue.

We present an approach for modeling and imputation of nonignorable missing data under Gaussian copulas. The analyst posits a set of quantiles of the marginal distributions of the study variables, for example, reflecting information from external data sources or elicited expert opinion. When these quantiles are accurately specified, we prove it is possible to consistently estimate the copula correlation and perform multiple imputation in the presence of nonignorable missing data. We develop algorithms for estimation and imputation that are computationally efficient, which we evaluate in simulation studies of multiple imputation inferences. We apply the model to analyze associations between lead exposure levels and end-of-grade test scores for 170,000 students in North Carolina. These measurements are not missing at random, as children deemed at-risk for high lead exposure are more likely to be measured. We construct plausible marginal quantiles for lead exposure using national statistics provided by the Centers for Disease Control and Prevention. Complete cases and missing at random analyses appear to underestimate the relationships between certain variables and end-of-grade test scores, while multiple imputation inferences under our model support stronger adverse associations between lead exposure and educational outcomes.

The more lead that people are exposed to in childhood or in the uterus, the more likely they are to engage in criminal behaviour as teenagers or adults, according to a review of 17 studies. "The evidence shows an excess risk for criminal behaviour years later," says Maria Jose Talayero at the George Washington University in Washington DC. Lead exposure has fallen in many countries, mainly due to the removal of lead additives from petrol (gasoline). However, there is no safe level – any amount of exposure is thought to be harmful. It is estimated that 1 in 3 children globally have blood lead levels above 5 micrograms per decilitre, which can result in decreased intelligence, behavioural difficulties and learning problems.