RESUMO
ObjectivesLung ultrasound (LUS) is a portable, low cost respiratory imaging tool but is challenged by user dependence and lack of diagnostic specificity. It is unknown whether the advantages of LUS implementation could be paired with deep learning techniques to match or exceed human-level, diagnostic specificity among similar appearing, pathological LUS images. DesignA convolutional neural network was trained on LUS images with B lines of different etiologies. CNN diagnostic performance, as validated using a 10% data holdback set was compared to surveyed LUS-competent physicians. SettingTwo tertiary Canadian hospitals. Participants600 LUS videos (121,381 frames) of B lines from 243 distinct patients with either 1) COVID-19, Non-COVID acute respiratory distress syndrome (NCOVID) and 3) Hydrostatic pulmonary edema (HPE). ResultsThe trained CNN performance on the independent dataset showed an ability to discriminate between COVID (AUC 1.0), NCOVID (AUC 0.934) and HPE (AUC 1.0) pathologies. This was significantly better than physician ability (AUCs of 0.697, 0.704, 0.967 for the COVID, NCOVID and HPE classes, respectively), p < 0.01. ConclusionsA deep learning model can distinguish similar appearing LUS pathology, including COVID-19, that cannot be distinguished by humans. The performance gap between humans and the model suggests that subvisible biomarkers within ultrasound images could exist and multi-center research is merited.
RESUMO
OBJECTIVES: The risk of drowning is reported to be 15-19 times greater in people with epilepsy compared to the general population. Despite this disproportionate burden, there is limited data about the circumstances surrounding drowning deaths in people with epilepsy. This population-based case series characterizes drowning deaths in people with epilepsy. METHODS: Postmortem data from coroner-ordered autopsies conducted in Ontario between 2014 and 2016 were screened for cases of drowning in people with a history of seizures. Demographic information, epilepsy characteristics, and circumstances surrounding death were extracted from post mortem reports. The incidence of drowning in people with epilepsy was calculated using government estimates of the Ontario population and the number of people with epilepsy. RESULTS: Twenty-five people with epilepsy drowned during the three-year study period, giving an estimated incidence of 1.5 per 10,000 epilepsy person-years (95% CI: 0.98, 2.23). Decedents were mostly young (mean age 36 years) and without physical or developmental disability. Approximately one-third had psychiatric comorbidities. Epilepsy severity ranged from well-controlled to drug refractory. Only 3 people had alcohol or illicit drugs detected on toxicological analysis. Forty-four percent of deaths were the result of an unwitnessed drowning in a bathtub. CONCLUSIONS: This population-based case series confirms people with epilepsy drown at a rate nearly ten times greater than the general population (1.5 per 10,000 epilepsy person-years compared to the estimated provincial average of 0.13 per 10,000). Drowning deaths in people with epilepsy most often occur in the bathtub. These deaths are only rarely associated with intoxication. People with epilepsy should receive counseling on the increased risk of drowning, including information regarding the significant risk associated with bathtub use, the potential protective roles of anti-epileptic drug (AED) adherence and supervision when in or around water, and the fact that all people with epilepsy remain at an increased risk of drowning regardless of their apparent seizure control.
