First Confirmed Case of Canine Mortality Due to Dihydroanatoxin-a in Central Texas, USA.

The frequency of dogs becoming ill or dying from accidental exposure to cyanotoxins, produced by cyanobacteria, is increasing throughout the United States. In January and February of 2021, two dogs died and five dogs became ill after swimming in Lake Travis, central Texas, USA; one deceased dog (C1) was subjected to pathological testing. Algal materials, sediment samples, zebra mussel viscera, periphyton from shells, as well as fluids and tissues from the digestive tract of C1 were investigated for the following cyanotoxins: anatoxin-a, homoanatoxin-a, dihydroanatoxin-a (dhATX), cylindrospermopsin, saxitoxin, and microcystins. Necropsy results of C1 indicated neurotoxicosis with significant levels of dhATX in the duodenum tissues (10.51 ng/g dry weight (DW)), jejunum tissue (6.076 ng/g DW), and stomach contents (974.88 ng/g DW). Algae collected near the site of C1's death contained levels of dhATX, ranging from 13 to 33 µg/g. By comparison, dhATX was detected at much lower concentrations in sediment samples (310.23 ng/g DW) and the periphyton on zebra mussel shells (38.45 ng/g DW). While dhATX was suspected in the deaths of canines from an event in Texas in 2019, this is the first report linking dhATX neurotoxicosis through pathological findings in Texas and potentially in the United States.

Risk compensation and face mask mandates during the COVID-19 pandemic.

Face masks are an important component in controlling COVID-19, and policy orders to wear masks are common. However, behavioral responses are seldom additive, and exchanging one protective behavior for another could undermine the COVID-19 policy response. We use SafeGraph smart device location data and variation in the date that US states and counties issued face mask mandates as a set of natural experiments to investigate risk compensation behavior. We compare time at home and the number of visits to public locations before and after face mask orders conditional on multiple statistical controls. We find that face mask orders lead to risk compensation behavior. Americans subject to the mask orders spend 11-24 fewer minutes at home on average and increase visits to some commercial locations-most notably restaurants, which are a high-risk location. It is unclear if this would lead to a net increase or decrease in transmission. However, it is clear that mask orders would be an important part of an economic recovery if people otherwise overestimate the risk of visiting public places.

Efficient learning from big data for cancer risk modeling: A case study with melanoma.

BACKGROUND: Building cancer risk models from real-world data requires overcoming challenges in data preprocessing, efficient representation, and computational performance. We present a case study of a cloud-based approach to learning from de-identified electronic health record data and demonstrate its effectiveness for melanoma risk prediction. METHODS: We used a hybrid distributed and non-distributed approach to computing in the cloud: distributed processing with Apache Spark for data preprocessing and labeling, and non-distributed processing for machine learning model training with scikit-learn. Moreover, we explored the effects of sampling the training dataset to improve computational performance. Risk factors were evaluated using regression weights as well as tree SHAP values. RESULTS: Among 4,061,172 patients who did not have melanoma through the 2016 calendar year, 10,129 were diagnosed with melanoma within one year. A gradient-boosted classifier achieved the best predictive performance with cross-validation (AUC = 0.799, Sensitivity = 0.753, Specificity = 0.688). Compared to a model built on the original data, a dataset two orders of magnitude smaller could achieve statistically similar or better performance with less than 1% of the training time and cost. CONCLUSIONS: We produced a model that can effectively predict melanoma risk for a diverse dermatology population in the U.S. by using hybrid computing infrastructure and data sampling. For this de-identified clinical dataset, sampling approaches significantly shortened the time for model building while retaining predictive accuracy, allowing for more rapid machine learning model experimentation on familiar computing machinery. A large number of risk factors (>300) were required to produce the best model.

A review of statistical and machine learning methods for modeling cancer risk using structured clinical data.

Advancements are constantly being made in oncology, improving prevention and treatment of cancers. To help reduce the impact and deadliness of cancers, they must be detected early. Additionally, there is a risk of cancers recurring after potentially curative treatments are performed. Predictive models can be built using historical patient data to model the characteristics of patients that developed cancer or relapsed. These models can then be deployed into clinical settings to determine if new patients are at high risk for cancer development or recurrence. For large-scale predictive models to be built, structured data must be captured for a wide range of diverse patients. This paper explores current methods for building cancer risk models using structured clinical patient data. Trends in statistical and machine learning techniques are explored, and gaps are identified for future research. The field of cancer risk prediction is a high-impact one, and research must continue for these models to be embraced for clinical decision support of both practitioners and patients.