Refine
Year of publication
Language
- English (43)
Is part of the Bibliography
- yes (43)
Keywords
- gamma rays: galaxies (9)
- BL Lacertae objects: general (8)
- galaxies: active (8)
- gamma rays: general (7)
- astroparticle physics (6)
- radiation mechanisms: non-thermal (6)
- acceleration of particles (3)
- BL Lacertae objects: individual: Mrk 421 (2)
- BL Lacertae objects: individual: Mrk 501 (2)
- Galaxy: center (2)
We present a search for magnetically broadened gamma-ray emission around active galactic nuclei (AGNs), using VERITAS observations of seven hard-spectrum blazars. A cascade process occurs when multi-TeV gamma-rays from an AGN interact with extragalactic background light (EBL) photons to produce electron-positron pairs, which then interact with cosmic microwave background photons via inverse-Compton scattering to produce gamma-rays. Due to the deflection of the electron- positron pairs, a non-zero intergalactic magnetic field (IGMF) would potentially produce detectable effects on the angular distribution of the cascade emission. In particular, an angular broadening compared to the unscattered emission could occur. Through non-detection of angularly broadened emission from 1ES 1218 vertical bar 304, the source with the largest predicted cascade fraction, we exclude a range of IGMF strengths around 10(-14) G at the 95% confidence level. The extent of the exclusion range varies with the assumptions made about the intrinsic spectrum of 1ES. 1218+304 and the EBL model used in the simulation of the cascade process. All of the sources are used to set limits on the flux due to extended emission.
Background:
COVID-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.
Objective:
The 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.
Methods:
We 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.
Results:
Upon 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.
Conclusions:
We 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.
Phe2vec
(2021)
Robust phenotyping of patients from electronic health records (EHRs) at scale is a challenge in clinical informatics. Here, we introduce Phe2vec, an automated framework for disease phenotyping from EHRs based on unsupervised learning and assess its effectiveness against standard rule-based algorithms from Phenotype KnowledgeBase (PheKB). Phe2vec is based on pre-computing embeddings of medical concepts and patients' clinical history. Disease phenotypes are then derived from a seed concept and its neighbors in the embedding space. Patients are linked to a disease if their embedded representation is close to the disease phenotype. Comparing Phe2vec and PheKB cohorts head-to-head using chart review, Phe2vec performed on par or better in nine out of ten diseases. Differently from other approaches, it can scale to any condition and was validated against widely adopted expert-based standards. Phe2vec aims to optimize clinical informatics research by augmenting current frameworks to characterize patients by condition and derive reliable disease cohorts.