Search

Your search keyword '"Ge, WenDong"' showing total 202 results
Start Over Author "Ge, WenDong"
202 results on '"Ge, WenDong"'

1. Classification of the Disposition of Patients Hospitalized with COVID-19: Reading Discharge Summaries Using Natural Language Processing

Author

Fernandes, Marta, Sun, Haoqi, Jain, Aayushee, Alabsi, Haitham S, Brenner, Laura N, Ye, Elissa, Ge, Wendong, Collens, Sarah I, Leone, Michael J, Das, Sudeshna, Robbins, Gregory K, Mukerji, Shibani S, and Westover, M Brandon

Subjects
Computer applications to medicine. Medical informatics, R858-859.7
Abstract

BackgroundMedical notes are a rich source of patient data; however, the nature of unstructured text has largely precluded the use of these data for large retrospective analyses. Transforming clinical text into structured data can enable large-scale research studies with electronic health records (EHR) data. Natural language processing (NLP) can be used for text information retrieval, reducing the need for labor-intensive chart review. Here we present an application of NLP to large-scale analysis of medical records at 2 large hospitals for patients hospitalized with COVID-19. ObjectiveOur study goal was to develop an NLP pipeline to classify the discharge disposition (home, inpatient rehabilitation, skilled nursing inpatient facility [SNIF], and death) of patients hospitalized with COVID-19 based on hospital discharge summary notes. MethodsText mining and feature engineering were applied to unstructured text from hospital discharge summaries. The study included patients with COVID-19 discharged from 2 hospitals in the Boston, Massachusetts area (Massachusetts General Hospital and Brigham and Women’s Hospital) between March 10, 2020, and June 30, 2020. The data were divided into a training set (70%) and hold-out test set (30%). Discharge summaries were represented as bags-of-words consisting of single words (unigrams), bigrams, and trigrams. The number of features was reduced during training by excluding n-grams that occurred in fewer than 10% of discharge summaries, and further reduced using least absolute shrinkage and selection operator (LASSO) regularization while training a multiclass logistic regression model. Model performance was evaluated using the hold-out test set. ResultsThe study cohort included 1737 adult patients (median age 61 [SD 18] years; 55% men; 45% White and 16% Black; 14% nonsurvivors and 61% discharged home). The model selected 179 from a vocabulary of 1056 engineered features, consisting of combinations of unigrams, bigrams, and trigrams. The top features contributing most to the classification by the model (for each outcome) were the following: “appointments specialty,” “home health,” and “home care” (home); “intubate” and “ARDS” (inpatient rehabilitation); “service” (SNIF); “brief assessment” and “covid” (death). The model achieved a micro-average area under the receiver operating characteristic curve value of 0.98 (95% CI 0.97-0.98) and average precision of 0.81 (95% CI 0.75-0.84) in the testing set for prediction of discharge disposition. ConclusionsA supervised learning–based NLP approach is able to classify the discharge disposition of patients hospitalized with COVID-19. This approach has the potential to accelerate and increase the scale of research on patients’ discharge disposition that is possible with EHR data.

Published
2021
Full Text
View/download PDF

2. Improving Clinician Performance in Classification of EEG Patterns on the Ictal-Interictal-Injury Continuum using Interpretable Machine Learning

Author

Barnett, Alina Jade, Guo, Zhicheng, Jing, Jin, Ge, Wendong, Kaplan, Peter W., Kong, Wan Yee, Karakis, Ioannis, Herlopian, Aline, Jayagopal, Lakshman Arcot, Taraschenko, Olga, Selioutski, Olga, Osman, Gamaleldin, Goldenholz, Daniel, Rudin, Cynthia, and Westover, M. Brandon

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, I.2.6, I.4.9, I.5.4
Abstract

In intensive care units (ICUs), critically ill patients are monitored with electroencephalograms (EEGs) to prevent serious brain injury. The number of patients who can be monitored is constrained by the availability of trained physicians to read EEGs, and EEG interpretation can be subjective and prone to inter-observer variability. Automated deep learning systems for EEG could reduce human bias and accelerate the diagnostic process. However, black box deep learning models are untrustworthy, difficult to troubleshoot, and lack accountability in real-world applications, leading to a lack of trust and adoption by clinicians. To address these challenges, we propose a novel interpretable deep learning model that not only predicts the presence of harmful brainwave patterns but also provides high-quality case-based explanations of its decisions. Our model performs better than the corresponding black box model, despite being constrained to be interpretable. The learned 2D embedded space provides the first global overview of the structure of ictal-interictal-injury continuum brainwave patterns. The ability to understand how our model arrived at its decisions will not only help clinicians to diagnose and treat harmful brain activities more accurately but also increase their trust and adoption of machine learning models in clinical practice; this could be an integral component of the ICU neurologists' standard workflow., Comment: 24 pages including appendices, 9 figures, published at NEJM AI

Published
2022
Full Text
View/download PDF

4. Effects of Epileptiform Activity on Discharge Outcome in Critically Ill Patients

Author

Parikh, Harsh, Hoffman, Kentaro, Sun, Haoqi, Ge, Wendong, Jing, Jin, Amerineni, Rajesh, Liu, Lin, Sun, Jimeng, Zafar, Sahar, Struck, Aaron, Volfovsky, Alexander, Rudin, Cynthia, and Westover, M. Brandon

Subjects
Statistics - Methodology, Computer Science - Machine Learning
Abstract

Epileptiform activity (EA) is associated with worse outcomes including increased risk of disability and death. However, the effect of EA on the neurologic outcome is confounded by the feedback between treatment with anti-seizure medications (ASM) and EA burden. A randomized clinical trial is challenging due to the sequential nature of EA-ASM feedback, as well as ethical reasons. However, some mechanistic knowledge is available, e.g., how drugs are absorbed. This knowledge together with observational data could provide a more accurate effect estimate using causal inference. We performed a retrospective cross-sectional study with 995 patients with the modified Rankin Scale (mRS) at discharge as the outcome and the EA burden defined as the mean or maximum proportion of time spent with EA in six-hour windows in the first 24 hours of electroencephalography as the exposure. We estimated the change in discharge mRS if everyone in the dataset had experienced a certain EA burden and were untreated. We combined pharmacological modeling with an interpretable matching method to account for confounding and EA-ASM feedback. Our matched groups' quality was validated by the neurologists. Having a maximum EA burden greater than 75% when untreated had a 22% increased chance of a poor outcome (severe disability or death), and mild but long-lasting EA increased the risk of a poor outcome by 14%. The effect sizes were heterogeneous depending on pre-admission profile, e.g., patients with hypoxic-ischemic encephalopathy (HIE) or acquired brain injury (ABI) were more affected. Interventions should put a higher priority on patients with an average EA burden higher than 10%, while treatment should be more conservative when the maximum EA burden is low., Comment: 4 Figures

Published
2022
Full Text
View/download PDF

5. NeuraHealth: An Automated Screening Pipeline to Detect Undiagnosed Cognitive Impairment in Electronic Health Records with Deep Learning and Natural Language Processing

Author

Tyagi, Tanish, Magdamo, Colin G., Noori, Ayush, Li, Zhaozhi, Liu, Xiao, Deodhar, Mayuresh, Hong, Zhuoqiao, Ge, Wendong, Ye, Elissa M., Sheu, Yi-han, Alabsi, Haitham, Brenner, Laura, Robbins, Gregory K., Zafar, Sahar, Benson, Nicole, Moura, Lidia, Hsu, John, Serrano-Pozo, Alberto, Prokopenko, Dimitry, Tanzi, Rudolph E., Hyman, Bradley T., Blacker, Deborah, Mukerji, Shibani S., Westover, M. Brandon, and Das, Sudeshna

Subjects
Computer Science - Computation and Language
Abstract

Dementia related cognitive impairment (CI) is a neurodegenerative disorder, affecting over 55 million people worldwide and growing rapidly at the rate of one new case every 3 seconds. 75% cases go undiagnosed globally with up to 90% in low-and-middle-income countries, leading to an estimated annual worldwide cost of USD 1.3 trillion, forecasted to reach 2.8 trillion by 2030. With no cure, a recurring failure of clinical trials, and a lack of early diagnosis, the mortality rate is 100%. Information in electronic health records (EHR) can provide vital clues for early detection of CI, but a manual review by experts is tedious and error prone. Several computational methods have been proposed, however, they lack an enhanced understanding of the linguistic context in complex language structures of EHR. Therefore, I propose a novel and more accurate framework, NeuraHealth, to identify patients who had no earlier diagnosis. In NeuraHealth, using patient EHR from Mass General Brigham BioBank, I fine-tuned a bi-directional attention-based deep learning natural language processing model to classify sequences. The sequence predictions were used to generate structured features as input for a patient level regularized logistic regression model. This two-step framework creates high dimensionality, outperforming all existing state-of-the-art computational methods as well as clinical methods. Further, I integrate the models into a real-world product, a web app, to create an automated EHR screening pipeline for scalable and high-speed discovery of undetected CI in EHR, making early diagnosis viable in medical facilities and in regions with scarce health services.

Published
2022

6. Using Deep Learning to Identify Patients with Cognitive Impairment in Electronic Health Records

Author

Tyagi, Tanish, Magdamo, Colin G., Noori, Ayush, Li, Zhaozhi, Liu, Xiao, Deodhar, Mayuresh, Hong, Zhuoqiao, Ge, Wendong, Ye, Elissa M., Sheu, Yi-han, Alabsi, Haitham, Brenner, Laura, Robbins, Gregory K., Zafar, Sahar, Benson, Nicole, Moura, Lidia, Hsu, John, Serrano-Pozo, Alberto, Prokopenko, Dimitry, Tanzi, Rudolph E., Hyman, Bradley T., Blacker, Deborah, Mukerji, Shibani S., Westover, M. Brandon, and Das, Sudeshna

Subjects
Computer Science - Computation and Language, Computer Science - Machine Learning
Abstract

Dementia is a neurodegenerative disorder that causes cognitive decline and affects more than 50 million people worldwide. Dementia is under-diagnosed by healthcare professionals - only one in four people who suffer from dementia are diagnosed. Even when a diagnosis is made, it may not be entered as a structured International Classification of Diseases (ICD) diagnosis code in a patient's charts. Information relevant to cognitive impairment (CI) is often found within electronic health records (EHR), but manual review of clinician notes by experts is both time consuming and often prone to errors. Automated mining of these notes presents an opportunity to label patients with cognitive impairment in EHR data. We developed natural language processing (NLP) tools to identify patients with cognitive impairment and demonstrate that linguistic context enhances performance for the cognitive impairment classification task. We fine-tuned our attention based deep learning model, which can learn from complex language structures, and substantially improved accuracy (0.93) relative to a baseline NLP model (0.84). Further, we show that deep learning NLP can successfully identify dementia patients without dementia-related ICD codes or medications., Comment: Machine Learning for Health (ML4H) - Extended Abstract

Published
2021

7. Natural Language Processing to Detect Cognitive Concerns in Electronic Health Records Using Deep Learning

Author

Hong, Zhuoqiao, Magdamo, Colin G., Sheu, Yi-han, Mohite, Prathamesh, Noori, Ayush, Ye, Elissa M., Ge, Wendong, Sun, Haoqi, Brenner, Laura, Robbins, Gregory, Mukerji, Shibani, Zafar, Sahar, Benson, Nicole, Moura, Lidia, Hsu, John, Hyman, Bradley T., Westover, Michael B., Blacker, Deborah, and Das, Sudeshna

Subjects
Computer Science - Computation and Language, I.2.7
Abstract

Dementia is under-recognized in the community, under-diagnosed by healthcare professionals, and under-coded in claims data. Information on cognitive dysfunction, however, is often found in unstructured clinician notes within medical records but manual review by experts is time consuming and often prone to errors. Automated mining of these notes presents a potential opportunity to label patients with cognitive concerns who could benefit from an evaluation or be referred to specialist care. In order to identify patients with cognitive concerns in electronic medical records, we applied natural language processing (NLP) algorithms and compared model performance to a baseline model that used structured diagnosis codes and medication data only. An attention-based deep learning model outperformed the baseline model and other simpler models., Comment: Machine Learning for Health (ML4H) at NeurIPS 2020 - Extended Abstract

Published
2020

12. Contribution of Data Categories to Readmission Prediction Accuracy

Author

Ge, Wendong, Kim, Hee Yeun, Desai, Sonali, Perlovsky, Leonid, and Turchin, Alexander

Subjects
Quantitative Biology - Quantitative Methods
Abstract

Identification of patients at high risk for readmission could help reduce morbidity and mortality as well as healthcare costs. Most of the existing studies on readmission prediction did not compare the contribution of data categories. In this study we analyzed relative contribution of 90,101 variables across 398,884 admission records corresponding to 163,468 patients, including patient demographics, historical hospitalization information, discharge disposition, diagnoses, procedures, medications and laboratory test results. We established an interpretable readmission prediction model based on Logistic Regression in scikit-learn, and added the available variables to the model one by one in order to analyze the influences of individual data categories on readmission prediction accuracy. Diagnosis related groups (c-statistic increment of 0.0933) and discharge disposition (c-statistic increment of 0.0269) were the strongest contributors to model accuracy. Additionally, we also identified the top ten contributing variables in every data category.

Published
2018

14. EEG-based grading of immune effector cell-associated neurotoxicity syndrome

Author

Jones, Daniel K., Eckhardt, Christine A., Sun, Haoqi, Tesh, Ryan A., Malik, Preeti, Quadri, Syed, Firme, Marcos Santana, van Sleuwen, Meike, Jain, Aayushee, Fan, Ziwei, Jing, Jin, Ge, Wendong, Nascimento, Fábio A., Sheikh, Irfan S., Jacobson, Caron, Frigault, Matthew, Kimchi, Eyal Y., Cash, Sydney S., Lee, Jong Woo, Dietrich, Jorg, and Westover, M. Brandon

Published
2022
Full Text
View/download PDF

17. Deep active learning for interictal ictal injury continuum EEG patterns

Author

Ge, Wendong, Jing, Jin, An, Sungtae, Herlopian, Aline, Ng, Marcus, Struck, Aaron F., Appavu, Brian, Johnson, Emily L., Osman, Gamaleldin, Haider, Hiba A., Karakis, Ioannis, Kim, Jennifer A., Halford, Jonathan J., Dhakar, Monica B., Sarkis, Rani A., Swisher, Christa B., Schmitt, Sarah, Lee, Jong Woo, Tabaeizadeh, Mohammad, Rodriguez, Andres, Gaspard, Nicolas, Gilmore, Emily, Herman, Susan T., Kaplan, Peter W., Pathmanathan, Jay, Hong, Shenda, Rosenthal, Eric S., Zafar, Sahar, Sun, Jimeng, and Brandon Westover, M.

Published
2021
Full Text
View/download PDF

18. Improving Clinician Performance in Classifying EEG Patterns on the Ictal–Interictal Injury Continuum Using Interpretable Machine Learning

Author

Barnett, Alina Jade, primary, Guo, Zhicheng, additional, Jing, Jin, additional, Ge, Wendong, additional, Kaplan, Peter W., additional, Kong, Wan Yee, additional, Karakis, Ioannis, additional, Herlopian, Aline, additional, Jayagopal, Lakshman Arcot, additional, Taraschenko, Olga, additional, Selioutski, Olga, additional, Osman, Gamaleldin, additional, Goldenholz, Daniel, additional, Rudin, Cynthia, additional, and Westover, M. Brandon, additional

Published
2024
Full Text
View/download PDF

24. Automated detection of immune effector cell‐associated neurotoxicity syndrome via quantitative EEG

Author

Eckhardt, Christine A., primary, Sun, Haoqi, additional, Malik, Preeti, additional, Quadri, Syed, additional, Santana Firme, Marcos, additional, Jones, Daniel K., additional, van Sleuwen, Meike, additional, Jain, Aayushee, additional, Fan, Ziwei, additional, Jing, Jin, additional, Ge, Wendong, additional, Danish, Husain H., additional, Jacobson, Caron A., additional, Rubin, Daniel B., additional, Kimchi, Eyal Y., additional, Cash, Sydney S., additional, Frigault, Matthew J., additional, Lee, Jong Woo, additional, Dietrich, Jorg, additional, and Westover, M. Brandon, additional

Published
2023
Full Text
View/download PDF

25. Effects of epileptiform activity on discharge outcome in critically ill patients in the USA: a retrospective cross-sectional study

Author

Parikh, Harsh, primary, Hoffman, Kentaro, additional, Sun, Haoqi, additional, Zafar, Sahar F, additional, Ge, Wendong, additional, Jing, Jin, additional, Liu, Lin, additional, Sun, Jimeng, additional, Struck, Aaron, additional, Volfovsky, Alexander, additional, Rudin, Cynthia, additional, and Westover, M Brandon, additional

Published
2023
Full Text
View/download PDF

27. Interrater Reliability of Expert Electroencephalographers Identifying Seizures and Rhythmic and Periodic Patterns in EEGs.

Author

Jing, Jin, Ge, Wendong, Struck, Aaron F, Fernandes, Marta Bento, Hong, Shenda, An, Sungtae, Fatima, Safoora, Herlopian, Aline, Karakis, Ioannis, Halford, Jonathan J.J., Ng, Marcus C, Johnson, Emily L, Appavu, Brian L, Sarkis, Rani A, Osman, Gamaleldin, Kaplan, Peter W, Dhakar, Monica B, Jayagopal, Lakshman Arcot, Sheikh, Zubeda, Taraschenko, Olga, Schmitt, Sarah S.E., Haider, Hiba Arif, Kim, Jennifer Ahjin, Swisher, Christa B, Gaspard, Nicolas, Cervenka, Mackenzie MC, Rodriguez Ruiz, Andres A, Lee, Jong Woo, Tabaeizadeh, Mohammad, Gilmore, Emily Jean, Nordstrom, Kristy, Yoo, Ji Yeoun, Holmes, Manisha G, Herman, Susan T, Williams, Jennifer A, Pathmanathan, Jay, Nascimento, Fábio A, Fan, Ziwei, Nasiri, Samaneh, Shafi, Mouhsin M.M., Cash, Sydney S.S., Hoch, Daniel Brian, Cole, Andrew J, Rosenthal, Eric S, Zafar, Sahar F, Sun, Jimeng, Westover, Michael Brandon, Jing, Jin, Ge, Wendong, Struck, Aaron F, Fernandes, Marta Bento, Hong, Shenda, An, Sungtae, Fatima, Safoora, Herlopian, Aline, Karakis, Ioannis, Halford, Jonathan J.J., Ng, Marcus C, Johnson, Emily L, Appavu, Brian L, Sarkis, Rani A, Osman, Gamaleldin, Kaplan, Peter W, Dhakar, Monica B, Jayagopal, Lakshman Arcot, Sheikh, Zubeda, Taraschenko, Olga, Schmitt, Sarah S.E., Haider, Hiba Arif, Kim, Jennifer Ahjin, Swisher, Christa B, Gaspard, Nicolas, Cervenka, Mackenzie MC, Rodriguez Ruiz, Andres A, Lee, Jong Woo, Tabaeizadeh, Mohammad, Gilmore, Emily Jean, Nordstrom, Kristy, Yoo, Ji Yeoun, Holmes, Manisha G, Herman, Susan T, Williams, Jennifer A, Pathmanathan, Jay, Nascimento, Fábio A, Fan, Ziwei, Nasiri, Samaneh, Shafi, Mouhsin M.M., Cash, Sydney S.S., Hoch, Daniel Brian, Cole, Andrew J, Rosenthal, Eric S, Zafar, Sahar F, Sun, Jimeng, and Westover, Michael Brandon

Abstract

The validity of brain monitoring using electroencephalography (EEG), particularly to guide care in patients with acute or critical illness, requires that experts can reliably identify seizures and other potentially harmful rhythmic and periodic brain activity, collectively referred to as "ictal-interictal-injury continuum" (IIIC). Previous interrater reliability (IRR) studies are limited by small samples and selection bias. This study was conducted to assess the reliability of experts in identifying IIIC., SCOPUS: ar.j, info:eu-repo/semantics/published

Published
2023

28. Development of Expert-Level Classification of Seizures and Rhythmic and Periodic Patterns During EEG Interpretation

Author

Jing, Jin, primary, Ge, Wendong, additional, Hong, Shenda, additional, Fernandes, Marta Bento, additional, Lin, Zhen, additional, Yang, Chaoqi, additional, An, Sungtae, additional, Struck, Aaron F., additional, Herlopian, Aline, additional, Karakis, Ioannis, additional, Halford, Jonathan J., additional, Ng, Marcus C., additional, Johnson, Emily L., additional, Appavu, Brian L., additional, Sarkis, Rani A., additional, Osman, Gamaleldin, additional, Kaplan, Peter W., additional, Dhakar, Monica B., additional, Arcot Jayagopal, Lakshman, additional, Sheikh, Zubeda, additional, Taraschenko, Olga, additional, Schmitt, Sarah, additional, Haider, Hiba A., additional, Kim, Jennifer A., additional, Swisher, Christa B., additional, Gaspard, Nicolas, additional, Cervenka, Mackenzie C., additional, Rodriguez Ruiz, Andres A., additional, Lee, Jong Woo, additional, Tabaeizadeh, Mohammad, additional, Gilmore, Emily J., additional, Nordstrom, Kristy, additional, Yoo, Ji Yeoun, additional, Holmes, Manisha G., additional, Herman, Susan T., additional, Williams, Jennifer A., additional, Pathmanathan, Jay, additional, Nascimento, Fábio A., additional, Fan, Ziwei, additional, Nasiri, Samaneh, additional, Shafi, Mouhsin M., additional, Cash, Sydney S., additional, Hoch, Daniel B., additional, Cole, Andrew J., additional, Rosenthal, Eric S., additional, Zafar, Sahar F., additional, Sun, Jimeng, additional, and Westover, M. Brandon, additional

Published
2023
Full Text
View/download PDF

31. Obtaining Better Word Representations via Language Transfer

Author

Li, Changliang, Xu, Bo, Wu, Gaowei, Wang, Xiuying, Ge, Wendong, Li, Yan, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, and Gelbukh, Alexander, editor

Published
2014
Full Text
View/download PDF

32. Dialogue Management in Spoken Dialogue System with Visual Feedback

Author

Ge, Wendong, Xu, Bo, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Kobsa, Alfred, Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, Series editor, Tanaka, Yuzuru, Series editor, Wahlster, Wolfgang, Series editor, Siekmann, Jörg, Series editor, Pham, Duc-Nghia, editor, and Park, Seong-Bae, editor

Published
2014
Full Text
View/download PDF

33. Improving Word Embeddings via Combining with Complementary Languages

Author

Li, Changliang, Xu, Bo, Wu, Gaowei, Zhuang, Tao, Wang, Xiuying, Ge, Wendong, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Kobsa, Alfred, editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Weikum, Gerhard, editor, Goebel, Randy, editor, Tanaka, Yuzuru, editor, Wahlster, Wolfgang, editor, Siekmann, Jörg, editor, Sokolova, Marina, editor, and van Beek, Peter, editor

Published
2014
Full Text
View/download PDF

35. Interrater Reliability of Expert Electroencephalographers Identifying Seizures and Rhythmic and Periodic Patterns in EEGs

Author

Jing, Jin, primary, Ge, Wendong, additional, Struck, Aaron F., additional, Fernandes, Marta Bento, additional, Hong, Shenda, additional, An, Sungtae, additional, Fatima, Safoora, additional, Herlopian, Aline, additional, Karakis, Ioannis, additional, Halford, Jonathan J., additional, Ng, Marcus C., additional, Johnson, Emily L., additional, Appavu, Brian L., additional, Sarkis, Rani A., additional, Osman, Gamaleldin, additional, Kaplan, Peter W., additional, Dhakar, Monica B., additional, Jayagopal, Lakshman Arcot, additional, Sheikh, Zubeda, additional, Taraschenko, Olga, additional, Schmitt, Sarah, additional, Haider, Hiba A., additional, Kim, Jennifer A., additional, Swisher, Christa B., additional, Gaspard, Nicolas, additional, Cervenka, Mackenzie C., additional, Rodriguez Ruiz, Andres A., additional, Lee, Jong Woo, additional, Tabaeizadeh, Mohammad, additional, Gilmore, Emily J., additional, Nordstrom, Kristy, additional, Yoo, Ji Yeoun, additional, Holmes, Manisha G., additional, Herman, Susan T., additional, Williams, Jennifer A., additional, Pathmanathan, Jay, additional, Nascimento, Fábio A., additional, Fan, Ziwei, additional, Nasiri, Samaneh, additional, Shafi, Mouhsin M., additional, Cash, Sydney S., additional, Hoch, Daniel B., additional, Cole, Andrew J., additional, Rosenthal, Eric S., additional, Zafar, Sahar F., additional, Sun, Jimeng, additional, and Westover, M. Brandon, additional

Published
2022
Full Text
View/download PDF

36. Influence of atmospheric in-cloud aqueous-phase chemistry on the global simulation of SO2 in CESM2

Author

Ge, Wendong, Liu, Junfeng, Yi, Kan, Xu, Jiayu, Zhang, Yizhou, Hu, Xiurong, Ma, Jianmin, Wang, Xuejun, Wan, Yi, Hu, Jianying, Zhang, Zhaobin, Wang, Xilong, and Tao, Shu

Subjects
Chemistry, TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES, Physics, QC1-999, QD1-999
Abstract

Sulfur dioxide (SO2) is a major atmospheric pollutant and precursor of sulfate aerosols, which influences air quality, cloud microphysics, and climate. Therefore, better understanding the conversion of SO2 to sulfate is essential to simulate and predict sulfur compounds more accurately. This study evaluates the effects of in-cloud aqueous-phase chemistry on SO2 oxidation in the Community Earth System Model version 2 (CESM2). We replaced the default parameterized SO2 aqueous-phase reactions with detailed HOx, Fe, N, and carbonate chemistry in cloud droplets and performed a global simulation for 2014–2015. Compared with the observations, the results incorporating detailed cloud aqueous-phase chemistry greatly reduced SO2 overestimation. This overestimation was reduced by 0.1–10 ppbv (parts per billion by volume) in most of Europe, North America, and Asia and more than 10 ppbv in parts of China. The biases in annual simulated SO2 mixing ratios decreased by 46 %, 41 %, and 22 % in Europe, the USA, and China, respectively. Fe chemistry and HOx chemistry contributed more to SO2 oxidation than N chemistry. Higher concentrations of soluble Fe and higher pH values could further enhance the oxidation capacity. This study emphasizes the importance of detailed in-cloud aqueous-phase chemistry for the oxidation of SO2. These mechanisms can improve SO2 simulation in CESM2 and deepen understanding of SO2 oxidation and sulfate formation.

Published
2021

38. Interpretable Machine Learning System to EEG Patterns on the Ictal-Interictal-Injury Continuum

Author

Barnett, Alina Jade, Guo, Zhicheng, Jing, Jin, Ge, Wendong, Rudin, Cynthia, and Westover, M. Brandon

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, I.2.6, Computer Vision and Pattern Recognition (cs.CV), I.5.4, Computer Science - Computer Vision and Pattern Recognition, I.4.9, Machine Learning (cs.LG)
Abstract

In intensive care units (ICUs), critically ill patients are monitored with electroencephalograms (EEGs) to prevent serious brain injury. The number of patients who can be monitored is constrained by the availability of trained physicians to read EEGs, and EEG interpretation can be subjective and prone to inter-observer variability. Automated deep learning systems for EEG could reduce human bias and accelerate the diagnostic process. However, black box deep learning models are untrustworthy, difficult to troubleshoot, and lack accountability in real-world applications, leading to a lack of trust and adoption by clinicians. To address these challenges, we propose a novel interpretable deep learning model that not only predicts the presence of harmful brainwave patterns but also provides high-quality case-based explanations of its decisions. Our model performs better than the corresponding black box model, despite being constrained to be interpretable. The learned 2D embedded space provides the first global overview of the structure of ictal-interictal-injury continuum brainwave patterns. The ability to understand how our model arrived at its decisions will not only help clinicians to diagnose and treat harmful brain activities more accurately but also increase their trust and adoption of machine learning models in clinical practice; this could be an integral component of the ICU neurologists' standard workflow., 20 pages including appendices, 7 figures, submitted for peer review

Published
2022

40. Quantitative epileptiform burden and electroencephalography background features predict post-traumatic epilepsy

Author

Chen, Yilun, primary, Li, Songlu, additional, Ge, Wendong, additional, Jing, Jin, additional, Chen, Hsin Yi, additional, Doherty, Daniel, additional, Herman, Alison, additional, Kaleem, Safa, additional, Ding, Kan, additional, Osman, Gamaleldin, additional, Swisher, Christa B, additional, Smith, Christine, additional, Maciel, Carolina B, additional, Alkhachroum, Ayham, additional, Lee, Jong Woo, additional, Dhakar, Monica B, additional, Gilmore, Emily J, additional, Sivaraju, Adithya, additional, Hirsch, Lawrence J, additional, Omay, Sacit B, additional, Blumenfeld, Hal, additional, Sheth, Kevin N, additional, Struck, Aaron F, additional, Edlow, Brian L, additional, Westover, M Brandon, additional, and Kim, Jennifer A, additional

Published
2022
Full Text
View/download PDF

42. Measuring expertise in identifying interictal epileptiform discharges

Author

Harid, Nitish M., Jing, Jin, Hogan, Jacob, Nascimento, Fábio A., Ouyang, An, Zheng, Wei-Long, Ge, Wendong, Zafar, Sahar F., Kim, Jennifer A., Lam, Alice D., Herlopian, Aline, Maus, Douglas, Karakis, Ioannis, Ng, Marcus, Hong, Shenda, Zhu, Yu, Kaplan, Peter W., Cash, Sydney, Shafi, Mouhsin, Martz, Gabriel, Halford, Jonathan J., and Westover, Michael Brandon

Subjects
Epilepsy, Neurology, Humans, Electroencephalography, Neurology (clinical), General Medicine, Article, Time
Abstract

OBJECTIVE. Interictal epileptiform discharges on EEG are integral to diagnosing epilepsy. However, EEGs are interpreted by readers with and without specialty training, and there is no accepted method to assess skill in interpretation. We aimed to develop a test to quantify IED recognition skills. METHODS. A total of 13,262 candidate IEDs were selected from EEGs and scored by eight fellowship-trained reviewers to establish a gold standard. An online test was developed to assess how well readers with different training levels could distinguish candidate waveforms. Sensitivity, false positive rate and calibration were calculated for each reader. A simple mathematical model was developed to estimate each reader’s skill and threshold in identifying an IED, and to develop receiver operating characteristics curves for each reader. We investigated the number of IEDs needed to measure skill level with acceptable precision. RESULTS. Twenty-nine raters completed the test; nine experts, seven experienced non-experts and thirteen novices. Median calibration errors for experts, experienced non-experts and novices were −0.056, 0.012, 0.046; median sensitivities were 0.800, 0.811, 0.715; and median false positive rates were 0.177, 0.272, 0.396, respectively. The number of test questions needed to measure those scores was 549. Our analysis identified that novices had a higher noise level (uncertainty) compared to experienced non-experts and experts. Using calculated noise and threshold levels, receiver operating curves were created, showing increasing median area under the curve from novices (0.735), to experienced non-experts (0.852) and experts (0.891). SIGNIFICANCE. Expert and non-expert readers can be distinguished based on ability to identify IEDs. This type of assessment could also be used to identify and correct differences in thresholds in identifying IEDs.

Published
2022

44. Identifying Patients With Delirium Based on Unstructured Clinical Notes: Observational Study

Author

Ge, Wendong, primary, Alabsi, Haitham, additional, Jain, Aayushee, additional, Ye, Elissa, additional, Sun, Haoqi, additional, Fernandes, Marta, additional, Magdamo, Colin, additional, Tesh, Ryan A, additional, Collens, Sarah I, additional, Newhouse, Amy, additional, MVR Moura, Lidia, additional, Zafar, Sahar, additional, Hsu, John, additional, Akeju, Oluwaseun, additional, Robbins, Gregory K, additional, Mukerji, Shibani S, additional, Das, Sudeshna, additional, and Westover, M Brandon, additional

Published
2022
Full Text
View/download PDF

45. Genome-wide identification and expression analysis of the WRKY gene family in cabbage (Brassica oleracea var. capitata L.)

Author

Yang, Xuyan, Zhao, Shuang, Ge, Wendong, Wang, Tenghui, Fan, Zhenyu, and Wang, Yushu

Subjects
Biotechnology
Abstract

WRKY proteins are a class of transcription factors involved in plant growth and development, biotic and abiotic stress, and other biological processes. In order to systematically study the structure and function of WRKY proteins in cabbage, we used the whole genome sequence of cabbage in the Brassica database (BRAD) and bioinformatics methods. A total of 150 WRKY genes were identified in cabbage, named BolWRKY1-BolWRKY150. These genes were unevenly distributed on 9 chromosomes. In this study, the WRKY proteins were classified into three classes: I, II and III. Cis-acting elements analysis showed that the BolWRKY gene was involved in multiple hormone and stress responses. The protein interaction network analysis suggested that BolWRKY19/100/105 genes might play similar functions in the same stress response. Based on transcriptome data analysis, we found that different BolWRKY genes showed tissue-specific expression. Quantitative real-time PCR analysis showed that several BolWRKY genes were strongly induced by drought stress and ABA (abscisic acid) treatment, indicating members of BolWRKY gene family were closely related to the stress responses such as drought. Our study lays a foundation for further understanding the regulatory mechanism and function of the WRKY gene in response to abiotic stress.

Published
2022
Full Text
View/download PDF

46. Effects of Epileptiform Activity on Discharge Outcome in Critically Ill Patients: A Retrospective Cross-Sectional Study

Author

Parikh, Harsh, primary, Hoffman, Kentaro, additional, Sun, Haoqi, additional, Zafar, Sahar F., additional, Ge, Wendong, additional, Jing, Jin, additional, Liu, Lin, additional, Sun, Jimeng, additional, Struck, Aaron F., additional, Volfovksy, Alexander, additional, Rudin, Cynthia, additional, and Westover, M. Brandon, additional

Published
2022
Full Text
View/download PDF

47. Why Interpretable Causal Inference is Important for High-Stakes Medical Decision Making in Neurology and How to Do it

Author

Parikh, Harsh, primary, Hoffman, Kentaro, additional, Sun, Haoqi, additional, Ge, Wendong, additional, Jing, Jin, additional, Liu, Lin, additional, Sun, Jimeng, additional, Zafar, Sahar F., additional, Struck, Aaron F., additional, Volfovksy, Alexander, additional, Rudin, Cynthia, additional, and Westover, M. Brandon, additional

Published
2022
Full Text
View/download PDF

48. Active deep learning to detect cognitive concerns in electronic health records

Author

Magdamo, Colin G., primary, Hong, Zhuoqiao Mia, additional, Noori, Ayush, additional, Sheu, Yi‐Han, additional, Deodhar, Mayuresh, additional, Ye, Elissa M, additional, Ge, Wendong, additional, Sun, Haoqi, additional, Brenner, Laura, additional, Robbins, Gregory K., additional, Mukerji, Shibani, additional, Zafar, Sahar F., additional, Benson, Nicole, additional, Moura, Lidia Maria V., additional, Hsu, John, additional, Arnold, Steven E., additional, Hyman, Bradley T., additional, Serrano‐Pozo, Alberto, additional, Westover, M Brandon, additional, Blacker, Deborah, additional, and Das, Sudeshna, additional

Published
2021
Full Text
View/download PDF

49. Influence of atmospheric in-cloud aqueous-phase chemistry on global simulation of SO2 in CESM2

Author

Ge, Wendong, Liu, Junfeng, Yi, Kan, Xu, Jiayu, Zhang, Yizhou, Hu, Xiurong, Ma, Jianmin, Wang, Xuejun, Wan, Yi, Hu, Jianying, Zhang, Zhaobin, Wang, Xilong, and Tao, Shu

Abstract

Sulfur dioxide (SO2) is a major atmospheric pollutant and precursor of sulfate aerosols, which influences air quality, cloud microphysics and climate. Therefore, better understanding the conversion of SO2 to sulfate is essential to simulate and predict sulfur compounds more accurately. This study evaluates the effects of in-cloud aqueous-phase chemistry on SO2 oxidation in the Community Earth System Model version 2 (CESM2). We replaced the default aqueous-phase reactions with detailed HOx-, Fe-, N- and carbonate chemistry and performed a global simulation for 2014–2015. Compared with the observations, the results incorporating detailed aqueous-phase chemistry greatly reduced SO2 overestimation. This overestimation was reduced by 0.1–10 ppbv in most of Europe, North America and Asia and more than 10 ppbv in parts of China. The biases in annual simulated SO2 concentrations decreased by 46 %, 41 %, and 22 % in Europe, the United States and China, respectively. Fe-chemistry and HOx-chemistry contributed more to SO2 oxidation than N-chemistry. Higher concentrations of soluble Fe and higher pH values could further enhance the oxidation capacity. This study emphasizes the importance of detailed aqueous-phase chemistry for the oxidation of SO2. These mechanisms can improve SO2 simulation in CESM2 and deepen understanding of SO2 oxidation and sulfate formation.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results