Simulating federated learning for steatosis detection using ultrasound images.

We aimed to implement four data partitioning strategies evaluated with four federated learning (FL) algorithms and investigate the impact of data distribution on FL model performance in detecting steatosis using B-mode US images. A private dataset (153 patients; 1530 images) and a public dataset (55 patient; 550 images) were included in this retrospective study. The datasets contained patients with metabolic dysfunction-associated fatty liver disease (MAFLD) with biopsy-proven steatosis grades and control individuals without steatosis. We employed four data partitioning strategies to simulate FL scenarios and we assessed four FL algorithms. We investigated the impact of class imbalance and the mismatch between the global and local data distributions on the learning outcome. Classification performance was assessed with area under the receiver operating characteristic curve (AUC) on a separate test set. AUCs were 0.93 (95% CI 0.92, 0.94) for source-based partitioning scenario with FedAvg, 0.90 (95% CI 0.89, 0.91) for a centralized model, and 0.83 (95% CI 0.81, 0.85) for a model trained in a single-center scenario. When data was perfectly balanced on the global level and each site had an identical data distribution, the model yielded an AUC of 0.90 (95% CI 0.88, 0.92). When each site contained data exclusively from one single class, irrespective of the global data distribution, the AUC fell in the range of 0.34-0.70. FL applied to B-mode US images provide performance comparable to a centralized model and higher than single-center scenario. Global data imbalance and local data heterogeneity influenced the learning outcome.

Automated screening of potential organ donors using a temporal machine learning model.

Organ donation is not meeting demand, and yet 30-60% of potential donors are potentially not identified. Current systems rely on manual identification and referral to an Organ Donation Organization (ODO). We hypothesized that developing an automated screening system based on machine learning could reduce the proportion of missed potentially eligible organ donors. Using routine clinical data and laboratory time-series, we retrospectively developed and tested a neural network model to automatically identify potential organ donors. We first trained a convolutive autoencoder that learned from the longitudinal changes of over 100 types of laboratory results. We then added a deep neural network classifier. This model was compared to a simpler logistic regression model. We observed an AUROC of 0.966 (CI 0.949-0.981) for the neural network and 0.940 (0.908-0.969) for the logistic regression model. At a prespecified cutoff, sensitivity and specificity were similar between both models at 84% and 93%. Accuracy of the neural network model was robust across donor subgroups and remained stable in a prospective simulation, while the logistic regression model performance declined when applied to rarer subgroups and in the prospective simulation. Our findings support using machine learning models to help with the identification of potential organ donors using routinely collected clinical and laboratory data.

Association between obesity and hospital mortality in critical COVID-19: a retrospective cohort study.

BACKGROUND: The impact of obesity on outcomes in acute respiratory distress syndrome (ARDS) is not well understood and remains controversial. Recent studies suggest that obesity might be associated with higher morbidity and mortality in respiratory disease caused by SARS-CoV-2 (COVID-19 disease). Our objective was to evaluate the association between obesity and hospital mortality in critical COVID-19 patients. METHODS: We conducted a retrospective cohort study in a tertiary academic center located in Montréal between March and August 2020. We included all consecutive adult patients admitted to the ICU for COVID-19-confirmed respiratory disease. Our main outcome was hospital mortality. We estimated the association between obesity, using the body mass index as a continuous variable, and hospital survival by fitting a multivariable Cox proportional hazards model. RESULTS: We included 94 patients. Median [q1, q3] body mass index (BMI) was 29 [26-32] kg/m2 and 37% of patients were obese (defined as BMI > 30 kg/m2). Hospital mortality for the entire cohort was 33%. BMI was significantly associated with hospital mortality (hazard ratio [HR] = 2.49 per 10 units BMI; 95% CI, from 1.69 to 3.70; p < 0.001) even after adjustment for sex, age and obesity-related comorbidities (adjusted HR = 3.50; 95% CI from 2.03 to 6.02; p < 0.001). CONCLUSIONS: Obesity was prevalent in hospitalized patients with critical illness secondary to COVID-19 disease and a higher BMI was associated with higher hospital mortality. Further studies are needed to validate this association and to better understand its underlying mechanisms.