Search

BackgroundStrokes represent a leading cause of mortality globally. The evolution of developing new therapies is subject to safety and efficacy testing in clinical trials, which operate in a limited timeframe. To maximize the impact of these trials, patient cohorts for whom ischemic stroke is likely during that designated timeframe should be identified. Machine learning may improve upon existing candidate identification methods in order to maximize the impact of clinical trials for stroke prevention and treatment and improve patient safety.MethodsA retrospective study was performed using 41,970 qualifying patient encounters with ischemic stroke from inpatient visits recorded from over 700 inpatient and ambulatory care sites. Patient data were extracted from electronic health records and used to train and test a gradient boosted machine learning algorithm (MLA) to predict the patients' risk of experiencing ischemic stroke from the period of 1 day up to 1 year following the patient encounter. The primary outcome of interest was the occurrence of ischemic stroke.ResultsAfter training for optimization, XGBoost obtained a specificity of 0.793, a positive predictive value (PPV) of 0.194, and a negative predictive value (NPV) of 0.985. The MLA further obtained an area under the receiver operating characteristic (AUROC) of 0.88. The Logistic Regression and multilayer perceptron models both achieved AUROCs of 0.862. Among features that significantly impacted the prediction of ischemic stroke were previous stroke history, age, and mean systolic blood pressure.ConclusionMLAs have the potential to more accurately predict the near risk of ischemic stroke within a 1-year prediction window for individuals who have been hospitalized. This risk stratification tool can be used to design clinical trials to test stroke prevention treatments in high-risk populations by identifying subjects who would be more likely to benefit from treatment.

Abstract Background Pulmonary embolisms (PE) are life‐threatening medical events, and early identification of patients experiencing a PE is essential to optimizing patient outcomes. Current tools for risk stratification of PE patients are limited and unable to predict PE events before their occurrence. Objective We developed a machine learning algorithm (MLA) designed to identify patients at risk of PE before the clinical detection of onset in an inpatient population. Materials and Methods Three machine learning (ML) models were developed on electronic health record data from 63,798 medical and surgical inpatients in a large US medical center. These models included logistic regression, neural network, and gradient boosted tree (XGBoost) models. All models used only routinely collected demographic, clinical, and laboratory information as inputs. All were evaluated for their ability to predict PE at the first time patient vital signs and lab measures required for the MLA to run were available. Performance was assessed with regard to the area under the receiver operating characteristic (AUROC), sensitivity, and specificity. Results The model trained using XGBoost demonstrated the strongest performance for predicting PEs. The XGBoost model obtained an AUROC of 0.85, a sensitivity of 81%, and a specificity of 70%. The neural network and logistic regression models obtained AUROCs of 0.74 and 0.67, sensitivity of 81% and 81%, and specificity of 44% and 35%, respectively. Conclusions This algorithm may improve patient outcomes through earlier recognition and prediction of PE, enabling earlier diagnosis and treatment of PE.

Deep venous thrombosis (DVT) is associated with significant morbidity, mortality, and increased healthcare costs. Standard scoring systems for DVT risk stratification often provide insufficient stratification of hospitalized patients and are unable to accurately predict which inpatients are most likely to present with DVT. There is a continued need for tools which can predict DVT in hospitalized patients. We performed a retrospective study on a database collected from a large academic hospital, comprised of 99,237 total general ward or ICU patients, 2,378 of whom experienced a DVT during their hospital stay. Gradient boosted machine learning algorithms were developed to predict a patient’s risk of developing DVT at 12- and 24-hour windows prior to onset. The primary outcome of interest was diagnosis of in-hospital DVT. The machine learning predictors obtained AUROCs of 0.83 and 0.85 for DVT risk prediction on hospitalized patients at 12- and 24-hour windows, respectively. At both 12 and 24 hours before DVT onset, the most important features for prediction of DVT were cancer history, VTE history, and internal normalized ratio (INR). Improved risk stratification may prevent unnecessary invasive testing in patients for whom DVT cannot be ruled out using existing methods. Improved risk stratification may also allow for more targeted use of prophylactic anticoagulants, as well as earlier diagnosis and treatment, preventing the development of pulmonary emboli and other sequelae of DVT.

Age is the greatest risk factor for Parkinson's disease (PD) which causes progressive loss of dopamine (DA) neurons, with males at greater risk than females. Intriguingly, some DA neurons are more resilient to degeneration than others. Increasing evidence suggests that vesicular glutamate transporter (VGLUT) expression in DA neurons plays a role in this selective vulnerability. We investigated the role of DA neuron VGLUT in sex- and age-related differences in DA neuron vulnerability using the genetically tractable Drosophila model. We found sex differences in age-related DA neurodegeneration and its associated locomotor behavior, where males exhibit significantly greater decreases in both DA neuron number and locomotion during aging compared with females. We discovered that dynamic changes in DA neuron VGLUT expression mediate these age- and sex-related differences, as a potential compensatory mechanism for diminished DA neurotransmission during aging. Importantly, female Drosophila possess higher levels of VGLUT expression in DA neurons compared with males, and this finding is conserved across flies, rodents, and humans. Moreover, we showed that diminishing VGLUT expression in DA neurons eliminates females' greater resilience to DA neuron loss across aging. This offers a new mechanism for sex differences in selective DA neuron vulnerability to age-related DA neurodegeneration. Finally, in mice, we showed that the ability of DA neurons to achieve optimal control over VGLUT expression is essential for DA neuron survival. These findings lay the groundwork for the manipulation of DA neuron VGLUT expression as a novel therapeutic strategy to boost DA neuron resilience to age- and PD-related neurodegeneration.

Ontogenetic changes in area use, habitat use, and trophic interactions play an important role in the ecology, demography, and ultimately population dynamics of many species. Assumed to be driven by shifting life‐history requirements, trophic niche shifts in white sharks (Carcharodon carcharias) are well documented, but the timing of the spatial niche shift that is hypothesized to occur with the trophic niche shift remains poorly understood. To document how fine‐scale area use varies as sharks age and the timing of the ontogenetic spatial shift of this top predator, we tracked individual white sharks tagged as young‐of‐the‐year or young juveniles over multiple years. Using data from juvenile white sharks detected over multiple years in a nursery habitat with a high‐density receiver array, we found no difference in area use with age. However, using a coast‐wide receiver array including nursery and adult habitat, we found the probability of detecting a juvenile white shark in nursery habitat decreased with age, with a concurrent increasing probability of detection in adult habitat. As the conservation and management of this species relies on understanding nursery habitat use and age‐related movements, data presented here address an important knowledge gap for the understudied juvenile to subadult life stages and the ontogenetic habitat shift of this species. [ABSTRACT FROM AUTHOR]

Despite being a heavily fished species, little is known about the movements of silky sharks (Carcharhinus falciformis). In this study, we report the longest (in duration and distance traveled) and most spatially extensive recorded migration for a silky shark. This shark, tagged with a fin‐mount satellite transmitter at the Galapagos Islands, traveled >27,666 km over 546 days, making two westerly migrations into international waters as far as 4755 km from the tagging location. These extensive movements in an area with high international fishing effort highlights the importance of understanding silky shark migrations to inform management practices. [ABSTRACT FROM AUTHOR]