Search

BackgroundMachine learning models require large datasets that may be siloed across different health care institutions. Machine learning studies that focus on COVID-19 have been limited to single-hospital data, which limits model generalizability. ObjectiveWe aimed to use federated learning, a machine learning technique that avoids locally aggregating raw clinical data across multiple institutions, to predict mortality in hospitalized patients with COVID-19 within 7 days. MethodsPatient data were collected from the electronic health records of 5 hospitals within the Mount Sinai Health System. Logistic regression with L1 regularization/least absolute shrinkage and selection operator (LASSO) and multilayer perceptron (MLP) models were trained by using local data at each site. We developed a pooled model with combined data from all 5 sites, and a federated model that only shared parameters with a central aggregator. ResultsThe LASSOfederated model outperformed the LASSOlocal model at 3 hospitals, and the MLPfederated model performed better than the MLPlocal model at all 5 hospitals, as determined by the area under the receiver operating characteristic curve. The LASSOpooled model outperformed the LASSOfederated model at all hospitals, and the MLPfederated model outperformed the MLPpooled model at 2 hospitals. ConclusionsThe federated learning of COVID-19 electronic health record data shows promise in developing robust predictive models without compromising patient privacy.

BackgroundCOVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking. ObjectiveThe aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points. MethodsWe used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19–positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions. ResultsUpon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction. ConclusionsWe externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.

Providing assessment validity information to decision makers in a clear and useful format is an ongoing challenge for the educational and psychological measurement community. We identify issues with a previous approach to a graphical presentation, noting that it is mislabeled as presenting incremental validity, when in fact it displays the effects of using predictors in a multiple hurdle fashion. We offer a straightforward technique for displaying incremental validity among predictors in reference to a criterion measure.

Students bring with them rich cultural and linguistic ways of knowing and communicating when engaged in figuring out explanations of phenomena. However, it is a challenge for teachers to support bi/multilingual learners in language-intensive science and engineering practices when they don't share a common language. When we position students' bi/multilingualism as an asset rather than an obstacle, we can support bi/multilingual students' equitable sensemaking. To support bi/multilingual learners' equitable sensemaking, we offer two tools: language surveys and the multiple ways of communicating strategies sheet. We describe how a teacher (second author) used these resources to adapt an investigation about air resistance and contact forces for his bi/multilingual students. The tools and examples provided can help educators better understand their students and make principled changes to science instruction, to expand how we use language in science. We hope the tools aid teachers in this challenging work but also reframe how educators see what students are saying and doing as assets for developing their ideas and learning. [ABSTRACT FROM AUTHOR]

Binocular diplopia limits quality of life by hampering visual function. There are several treatment options with individual advantages and drawbacks. Contact lenses have recently emerged as an attractive treatment delivery mechanism due to advances in lens manufacturing and imaging modalities. Contact lenses can offer better comfort, efficacy, and cosmetic appeal compared to alternative treatments such as spectacles. They also present unique challenges due to risks of inflammation, infection, and intolerability. This review will explore the management of binocular diplopia using several types of contact lenses including base down prism in contact lenses, scleral lenses, occlusive lenses, and monovision lenses. Increased awareness of differing contact lens will help providers and patients make better informed decisions about diplopia management. [ABSTRACT FROM AUTHOR]

This study describes decentralized recruitment and enrollment for a COVID-19 treatment trial, while comparing 5 primary recruitment methods: search engine ads, paid advertising within a national testing company, paid advertising within a regional testing company, electronic health record messages, and word of mouth. These are compared across patient demographics, efficiency, and cost. Clinical Trials Registration NCT04510194. [ABSTRACT FROM AUTHOR]

This article explores the electrocardiographic manifestations of cardiac disorders in rheumatological conditions, focusing on two case studies of patients with systemic lupus erythematosus (SLE) and rheumatoid arthritis (RA). It emphasizes the importance of early recognition and diagnosis of cardiac involvement in autoimmune diseases to enable appropriate interventions. The article provides an overview of common rhythm and conduction disorders seen in systemic autoimmune diseases and suggests that ECG abnormalities should prompt further cardiac imaging for treatment guidance. Managing cardiac involvement in autoimmune diseases requires a multidisciplinary approach, including reducing inflammation, optimizing cardiovascular risk factors, and following evidence-based guidelines. Early detection and intervention can have prognostic implications for patients with cardiac involvement in autoimmune diseases. [Extracted from the article]

Lafora disease (LD) is a syndrome of progressive myoclonic epilepsy and cumulative neurocognitive deterioration caused by recessively inherited genetic lesions of EPM2A (laforin) or NHLRC1 (malin). Neuropsychiatric symptomatology in LD is thought to be directly downstream of neuronal and astrocytic polyglucosan aggregates, termed Lafora bodies (LBs), which faithfully accumulate in an age‐dependent manner in all mouse models of LD. In this study, we applied home‐cage monitoring to examine the extent of neurobehavioral deterioration in a model of malin‐deficient LD as a means to identify robust preclinical endpoints that may guide the selection of novel genetic treatments. At 6 weeks, ∼6–7 months, and ∼12 months of age, malin‐deficient mice ("KO") and wild‐type (WT) littermates underwent a standardized home‐cage behavioral assessment designed to non‐obtrusively appraise features of rest/arousal, consumptive behaviors, risk aversion, and voluntary wheel‐running. At all timepoints, and over a range of metrics that we report transparently, WT and KO mice were essentially indistinguishable. In contrast, within WT mice compared across the same timepoints, we identified age‐related nocturnal hypoactivity, diminished sucrose preference, and reduced wheel‐running. Neuropathological examinations in subsets of the same mice revealed expected age‐dependent LB accumulation, gliosis, and microglial activation in cortical and subcortical brain regions. At 12 months of age, despite the burden of neocortical LBs, we did not identify spontaneous seizures during an electroencephalographic (EEG) survey, and KO and WT mice exhibited similar spectral EEG features. However, in an in vitro assay of neocortical function, paroxysmal bursts of network activity (UP states) in KO slices were more prolonged at 3 and 6 months of age, but similar to WT at 12 months. KO mice displayed a distinct response to pentylenetetrazole, with a greater incidence of clonic seizures and a more pronounced postictal suppression of movement, feeding, and drinking behavior. Together, these results highlight the clinicopathologic dissociation in a mouse model of LD, where the accrual of LBs may latently modify cortical circuit function and seizure threshold without clinically meaningful changes in home‐cage behavior. Our findings allude to a delay between LB accumulation and neurobehavioral decline in LD: one that may provide a window for treatment, and whose precise duration may be difficult to ascertain within the typical lifespan of a laboratory mouse. [ABSTRACT FROM AUTHOR]

The parenting practices of both transracially adopted Korean American adults and multiracial families are often overlooked in developmental science, yet are important to address, given that the majority of Korean adoptees are now adults with families of their own and given rapid increases in the multiracial population. This qualitative study examined the cultural socialization beliefs and practices among transracially adopted Korean Americans who are parents of multiracial Asian-White children. Drawing upon interviews with 31 Korean adoptee parents (29 female; M[subscript age] = 41.26), we identified four themes that capture parents' understanding of their children's multiracial identities, how that understanding subsequently shapes their cultural socialization practices, and how parents' socialization beliefs and practices vary by developmental stage. These themes described the ways that parents' cultural socialization practices were shaped by their children's phenotypes, parents' understanding of their children's multiracial identities, geographic location, and the multiracial family context. This study also demonstrated how multiracial couples in our sample engaged in cultural socialization together. Results suggest that Korean adoptee parents largely acknowledged their children's multiracial identities through labels, but primarily socialized children as monoracial minorities.