Search

Providing an accurate prediction of mortality risk for patients in the health care system as early as possible could help improve care quality and reduce costs. The recent adoption of Electronic Health Records (EHRs) has created an opportunity to improve prediction accuracy by obtaining more detailed data and applying more advanced algorithms. In this work, we applied gradient boosted trees and deep neural networks to estimate the mortality risk of patients admitted to a single institution’s Intensive Care Units (ICUs). Unlike the prior studies that utilize a rich set of features usually available at discharge, we used commonly available data in EHRs at the time of admission. We used a subset of MIMIC III of 4,440 admissions between 2001 and 2012 to extract demographic information (age, gender, marital status, etc.), diagnosis and medical (ICD) codes. The model achieved 87.30 AUC on the 10% test set. The excellent performance of the model highlights the usability of models with few features for building real-world prediction engines.

Heatwaves are one of the deadliest natural disasters that occur annually with thousands of people seeking medical attention. The spatio-temporal synchronization between peaks in disease manifestation and high temperature provides important insights into the seasonal timing of the heatwave and the response it may cause with respect to emergence, severity, and duration. The objectives of this study are to examine the association between hospitalizations due to heat stroke in older adults and heat in the United States (US) and explore synchronization with respect to heatwave sequence, time of arrival, and regional climate. Three large data sets were utilized: daily hospitalization records of the US elderly between 1991 and 2006, annual demographic summaries on Medicare beneficiaries maintained by the Centers for Medicare and Medicaid Services (CMS), and nationwide daily meteorological observations. We modeled seasonal fluctuations in health outcomes, such as the timing and intensity of the seasonal peak in hospitalizations using refined harmonic GLM for eight climatically similar regions. During the 16-year study period, there were 40,019 heat-related hospitalizations (HRH) in the conterminous US. The rates of HRH varied substantially across eight climatic regions: with the highest rate of 7.05 cases per million residents observed in areas with temperate arid summers and winters (TaTa) and the lowest rate of 0.67-in areas with cold moderately dry summers and arid winters (CdCa), where summer temperatures are about 18.3 °C and 12.1 °C, respectively. We detected 400 heatwaves defined as any day when the night time temperature is above its 90th percentile for the current and previous nights. The first seasonal heatwave in a season resulted in 4274 hospitalizations over 342 heatwave-days: 34.3% of 12,442 hospitalizations occurred in 26% of 1308 heatwave-days. The relative risks of increased HRH associated with the first and second heatwaves were 10.4 (95%CI: 8.5; 12.3) and 11.4 (95%CI: 9.6; 13.3), respectively, indicating the disproportional effects of early heatwave arrivals. The seasonal spike in heat stroke hospitalizations in regions with relatively similar annual temperatures, e.g. in areas with temperate moderately dry summers and winters (TdTa: 12.8 °C) and (TaTa: 11.1 °C) ranged between 4.5 (95%CI: 3.3; 5.5) and 11.0 (95%CI: 8.2; 14.9) cases per million residents, respectively, indicating substantial regional differences. The differences in heat-related hospitalizations and response to heatwaves are substantial among older adults residing in different climate regions of the conterminous US. The disproportionally high response to the early seasonal heatwave deserves special attention, especially in the context of prevention and decision support frameworks.

Schistosoma haematobium transmission is influenced by environmental conditions that determine the suitability of the parasite and intermediate host snail habitats, as well as by socioeconomic conditions, access to water and sanitation infrastructure, and human behaviors. Remote sensing is a demonstrated valuable tool to characterize environmental conditions that support schistosomiasis transmission. Socioeconomic and behavioral conditions that propagate repeated domestic and recreational surface water contact are more difficult to quantify at large spatial scales. We present a mixed-methods approach that builds on the remotely sensed ecological variables by exploring water and sanitation related community characteristics as independent risk factors of schistosomiasis transmission.

The Flint Water Crisis-due to changes of water source and treatment procedures-has revealed many unsolved social, environmental, and public health problems for US drinking water, including opportunistic premise plumbing pathogens (OPPP). The true health impact of OPPP, especially in vulnerable populations such as the elderly, is largely unknown. We explored 108 claims in the largest US national uniformly collected data repository to determine rates and costs of OPPP-related hospitalizations. In 1991-2006, 617,291 cases of three selected OPPP infections resulted in the elderly alone of $0.6 billion USD per year of payments. Antibiotic resistance significantly increased OPPP illness costs that are likely to be underreported. More precise estimates for OPPP burdens could be obtained if better clinical, microbiological, administrative, and environmental monitoring data were cross-linked. An urgent dialog across governmental and disciplinary divides, and studies on preventing OPPP through drinking water exposure, are warranted.

Older adults are highly vulnerable to the detriment of extreme weather. The rapid non-linear increase in heat-related morbidity is difficult to quantify, hindering the attribution of direct effects of exposure on severe health outcomes. We examine the effects of ambient temperatures on heat-related hospitalizations (HH) among the elderly in presence of strong seasonality and by assessing the effects caused by the first and subsequent seasonal heatwaves. We empirically derived the thresholds for a heatwave episode in Boston MSA based on 16 years of daily observations. We compared the health risks of heatwaves using the proposed and four alternative definitions. 701 cases of HH in older residents of Boston area were examined using harmonic regression models, designed to capture the non-linear effects of ambient temperatures and heatwave episodes when the night-time temperature is above 65.5 °F for 3 consecutive nights. The overall relative risk of HH associated with a heatwave episode was 6.9 [95%CI:4.8–9.8]. The relative risk of HH associated with the first heatwave increases up to 13.3 [95%CI:7.4–24.0]. The risk declined to 3.7 [95%CI:2.4–5.8] for the subsequent heatwave. Four other commonly used heatwave definitions confirmed these findings. Public health actions have to target the first heatwave to maximize the impact of preventive measures.

Continuous access to adequate quantities of safe water is essential for human health and socioeconomic development. Piped water systems (PWSs) are an increasingly common type of water supply in rural African small towns. Despite providing the highest and most flexible level of service with better microbiological water quality to their users, these systems remain vulnerable to rural water sustainability challenges. We assessed temporal and spatial patterns in water consumption from public standpipes of four PWSs in Ghana in order to assess clean water demand relative to other available water sources. Low water consumption was evident in all study towns, which manifested temporally and spatially. Temporal variability in water consumption that is negatively correlated with rainfall is an indicator of rainwater preference when it is available. Furthermore, our findings show that standpipes in close proximity to alternative water sources such as streams and hand-dug wells suffer further reductions in water consumption. Qualitative data suggest that consumer demand in the study towns appears to be driven more by water quantity, accessibility, and perceived aesthetic water quality, as compared to microbiological water quality or price. In settings with chronic under-utilization of improved water sources, increasing water demand through household connections, improving water quality with respect to taste and appropriateness for laundry, and educating residents about health benefits of using piped water should be prioritized. Continued consumer demand and sufficient revenue generation are important attributes of a water service that ensure its function over time. Our findings suggest that analyzing water consumption of existing metered PWSs in combination with qualitative approaches may enable more efficient planning of community-based water supplies and support sustainable development.

Climate change and increasing urbanization have intensified scientific interest in understanding the impact of vegetation cover on human health. While the elderly population (persons 65+y.o.) continues to grow, environmental determinants for asthma in this group remain poorly understood. Using spatial and time series analysis we investigated the effect of vegetation cover as measured by the Normalized Difference Vegetation Index (NDVI) on asthma hospitalization rates (AHR)(ICD-9 codes 493.0-9) among Medicare recipients in seven northeastern United States. We considered potential confounders, including income, land cover category, seasonal influenza activity, and population density, classified as urban, suburban, and rural. Time-series analysis identified seasonal patterns in elderly asthma hospitalizations as counter-phase with NDVI: when vegetation vigor increases, AHR decreases (R 2 =0.59, p=0.001). Winter peaks of influenza correlated with an increase in AHR (R 2 =0.43, p=0.001). Spatial multivariate analysis found HRs increased significantly (RR=1.048, 95% CI:1.072-1.086, p=0.001) as population density increased. Regardless of location, living in poverty increased AHR (RR=1.014, 95% CI:1.026-1.018, p=0.001). After adjusting for income and percent elderly population, evergreen vegetation in urban areas demonstrated a small, yet protective effect (RR=0.998, 95% CI:0.993-0.997, p=0.02). These results suggest that urban evergreen vegetation cover could be an important factor for reducing the risk of elderly asthma hospitalizations.