Searcharxiv⌕ Search

arXiv subjects

Yuan Luo

Publications and source records attributed to Yuan Luo.

At least 91 records · Page 5Linked to original sources
arXiv2021

Natural language processing to identify lupus nephritis phenotype in electronic health records

Systemic lupus erythematosus (SLE) is a rare autoimmune disorder characterized by an unpredictable course of flares and remission with diverse manifestations. Lupus nephritis, one of the major disease manifestations of SLE for organ damage and mortality, is a key component of lupus classification criteria. Accurately identifying lupus nephritis in electronic health records (EHRs) would therefore benefit large cohort observational studies and clinical trials where characterization of the patient population is critical for recruitment, study design, and analysis. Lupus nephritis can be recognized through procedure codes and structured data, such as laboratory tests. However, other critical information documenting lupus nephritis, such as histologic reports from kidney biopsies and prior medical history narratives, require sophisticated text processing to mine information from pathology reports and clinical notes. In this study, we developed algorithms to identify lupus nephritis with and without natural language processing (NLP) using EHR data. We developed four algorithms: a rule-based algorithm using only structured data (baseline algorithm) and three algorithms using different NLP models. The three NLP models are based on regularized logistic regression and use different sets of features including positive mention of concept unique identifiers (CUIs), number of appearances of CUIs, and a mixture of three components respectively. The baseline algorithm and the best performed NLP algorithm were external validated on a dataset from Vanderbilt University Medical Center (VUMC). Our best performing NLP model incorporating features from both structured data, regular expression concepts, and mapped CUIs improved F measure in both the NMEDW (0.41 vs 0.79) and VUMC (0.62 vs 0.96) datasets compared to the baseline lupus nephritis algorithm.

cs.LG↗
arXiv2021

Disparities in Social Determinants among Performances of Mortality Prediction with Machine Learning for Sepsis Patients

Background Sepsis is one of the most life-threatening circumstances for critically ill patients in the US, while a standardized criteria for sepsis identification is still under development. Disparities in social determinants of sepsis patients can interfere with the risk prediction performances using machine learning. Methods Disparities in social determinants, including race, gender, marital status, insurance types and languages, among patients identified by six available sepsis criteria were revealed by forest plots. Sixteen machine learning classifiers were trained to predict in-hospital mortality for sepsis patients. The performance of the trained model was tested on the entire randomly conducted test set and each sub-population built based on each of the following social determinants: race, gender, marital status, insurance type, and language. Results We analyzed a total of 11,791 critical care patients from the MIMIC-III database. Within the population identified by each sepsis identification method, significant differences were observed among sub-populations regarding race, marital status, insurance type, and language. On the 5,783 sepsis patients identified by the Sepsis-3 criteria statistically significant performance decreases for mortality prediction were observed when applying the trained machine learning model on Asian and Hispanic patients. With pairwise comparison, we detected performance discrepancies in mortality prediction between Asian and White patients, Asians and patients of other races, as well as English-speaking and Spanish-speaking patients. Conclusions Disparities in proportions of patients identified by various sepsis criteria were detected among the different social determinant groups. To achieve accurate diagnosis, a versatile diagnostic system for sepsis is needed to overcome the social determinant disparities of patients.

cs.LG↗
arXiv2021

Development and Validation of MicrobEx: an Open-Source Package for Microbiology Culture Concept Extraction

Microbiology culture reports contain critical information for important clinical and public health applications. However, microbiology reports often have complex, semi-structured, free-text data that present a barrier for secondary use. Here we present the development and validation of an open-source package designed to ingest free-text microbiology reports, determine whether the culture is positive, and return a list of SNOMED-CT mapped bacteria. Our rule-based natural language processing algorithm was developed using microbiology reports from two different electronic health record systems in a large healthcare organization, and then externally validated on the reports of two other institutions with manually-extracted results as a benchmark. Our algorithm achieved F-1 scores >0.95 on all classification tasks across both validation sets. Our concept extraction Python package, MicrobEx, is designed to be reused and adapted to individual institutions as an upstream process for other clinical applications, such as machine learning studies, clinical decision support, and disease surveillance systems.

q-bio.QM↗
arXiv2021

SNPs Filtered by Allele Frequency Improve the Prediction of Hypertension Subtypes

Hypertension is the leading global cause of cardiovascular disease and premature death. Distinct hypertension subtypes may vary in their prognoses and require different treatments. An individual's risk for hypertension is determined by genetic and environmental factors as well as their interactions. In this work, we studied 911 African Americans and 1,171 European Americans in the Hypertension Genetic Epidemiology Network (HyperGEN) cohort. We built hypertension subtype classification models using both environmental variables and sets of genetic features selected based on different criteria. The fitted prediction models provided insights into the genetic landscape of hypertension subtypes, which may aid personalized diagnosis and treatment of hypertension in the future.

q-bio.QM↗
arXiv2021

Assessing Social Determinants-Related Performance Bias of Machine Learning Models: A case of Hyperchloremia Prediction in ICU Population

Machine learning in medicine leverages the wealth of healthcare data to extract knowledge, facilitate clinical decision-making, and ultimately improve care delivery. However, ML models trained on datasets that lack demographic diversity could yield suboptimal performance when applied to the underrepresented populations (e.g. ethnic minorities, lower social-economic status), thus perpetuating health disparity. In this study, we evaluated four classifiers built to predict Hyperchloremia - a condition that often results from aggressive fluids administration in the ICU population - and compared their performance in racial, gender, and insurance subgroups. We observed that adding social determinants features in addition to the lab-based ones improved model performance on all patients. The subgroup testing yielded significantly different AUC scores in 40 out of the 44 model-subgroup, suggesting disparities when applying ML models to social determinants subgroups. We urge future researchers to design models that proactively adjust for potential biases and include subgroup reporting in their studies.

cs.LG↗
arXiv2021

Early Prediction of Mortality in Critical Care Setting in Sepsis Patients Using Structured Features and Unstructured Clinical Notes

Sepsis is an important cause of mortality, especially in intensive care unit (ICU) patients. Developing novel methods to identify early mortality is critical for improving survival outcomes in sepsis patients. Using the MIMIC-III database, we integrated demographic data, physiological measurements and clinical notes. We built and applied several machine learning models to predict the risk of hospital mortality and 30-day mortality in sepsis patients. From the clinical notes, we generated clinically meaningful word representations and embeddings. Supervised learning classifiers and a deep learning architecture were used to construct prediction models. The configurations that utilized both structured and unstructured clinical features yielded competitive F-measure of 0.512. Our results showed that the approaches integrating both structured and unstructured clinical features can be effectively applied to assist clinicians in identifying the risk of mortality in sepsis patients upon admission to the ICU.

cs.CY↗
arXiv2021

Unsupervised Learning to Subphenotype Delirium Patients from Electronic Health Records

Delirium is a common acute onset brain dysfunction in the emergency setting and is associated with higher mortality. It is difficult to detect and monitor since its presentations and risk factors can be different depending on the underlying medical condition of patients. In our study, we aimed to identify subtypes within the delirium population and build subgroup-specific predictive models to detect delirium using Medical Information Mart for Intensive Care IV (MIMIC-IV) data. We showed that clusters exist within the delirium population. Differences in feature importance were also observed for subgroup-specific predictive models. Our work could recalibrate existing delirium prediction models for each delirium subgroup and improve the precision of delirium detection and monitoring for ICU or emergency department patients who had highly heterogeneous medical conditions.

cs.LG↗
arXiv2021

Aggregation Delayed Federated Learning

Federated learning is a distributed machine learning paradigm where multiple data owners (clients) collaboratively train one machine learning model while keeping data on their own devices. The heterogeneity of client datasets is one of the most important challenges of federated learning algorithms. Studies have found performance reduction with standard federated algorithms, such as FedAvg, on non-IID data. Many existing works on handling non-IID data adopt the same aggregation framework as FedAvg and focus on improving model updates either on the server side or on clients. In this work, we tackle this challenge in a different view by introducing redistribution rounds that delay the aggregation. We perform experiments on multiple tasks and show that the proposed framework significantly improves the performance on non-IID data.

cs.LG↗
arXiv2021

A simulation study of a windowless gas stripping room in an E//B neutral particle analyzer

Neutral Particle Analyzer (NPA) is one of the crucial diagnostic devices on Tokamak facilities. Stripping unit is one of the main parts of the NPA. A windowless gas stripping room with two differential pipes is adopted in a parallel direction of electric and magnetic fields (E//B) NPA. The pressure distributions in the stripping chamber are simulated by Ansys Fluent together with MolFlow+. Based on the pressure distributions extracted from the simulation, the stripping efficiency of the E//B NPA is studied with GEANT4. The hadron reaction physics is modified to track the charge state of each particle in a cross section base method in GEANT4. The transmission rates ($R$) and the stripping efficiencies $f_{+1}$ are examined for the particle energy ranging from 20 to 200 keV at the input pressure ($P_0$) ranging from 20 to 400 Pa. According to the combined global efficiency, $R \times f_{+1}$, $P_0$ = 240 Pa is obtained as the optimum pressure for the maximum global efficiency in the incident energy range investigated.

physics.ins-det↗
arXiv2021

Deep Learning-Based Anomaly Detection in Cyber-Physical Systems: Progress and Opportunities

Anomaly detection is crucial to ensure the security of cyber-physical systems (CPS). However, due to the increasing complexity of CPSs and more sophisticated attacks, conventional anomaly detection methods, which face the growing volume of data and need domain-specific knowledge, cannot be directly applied to address these challenges. To this end, deep learning-based anomaly detection (DLAD) methods have been proposed. In this paper, we review state-of-the-art DLAD methods in CPSs. We propose a taxonomy in terms of the type of anomalies, strategies, implementation, and evaluation metrics to understand the essential properties of current methods. Further, we utilize this taxonomy to identify and highlight new characteristics and designs in each CPS domain. Also, we discuss the limitations and open problems of these methods. Moreover, to give users insights into choosing proper DLAD methods in practice, we experimentally explore the characteristics of typical neural models, the workflow of DLAD methods, and the running performance of DL models. Finally, we discuss the deficiencies of DL approaches, our findings, and possible directions to improve DLAD methods and motivate future research.

cs.CR↗
arXiv2020

PANTHER: Pathway Augmented Nonnegative Tensor factorization for HighER-order feature learning

Genetic pathways usually encode molecular mechanisms that can inform targeted interventions. It is often challenging for existing machine learning approaches to jointly model genetic pathways (higher-order features) and variants (atomic features), and present to clinicians interpretable models. In order to build more accurate and better interpretable machine learning models for genetic medicine, we introduce Pathway Augmented Nonnegative Tensor factorization for HighER-order feature learning (PANTHER). PANTHER selects informative genetic pathways that directly encode molecular mechanisms. We apply genetically motivated constrained tensor factorization to group pathways in a way that reflects molecular mechanism interactions. We then train a softmax classifier for disease types using the identified pathway groups. We evaluated PANTHER against multiple state-of-the-art constrained tensor/matrix factorization models, as well as group guided and Bayesian hierarchical models. PANTHER outperforms all state-of-the-art comparison models significantly (p<0.05). Our experiments on large scale Next Generation Sequencing (NGS) and whole-genome genotyping datasets also demonstrated wide applicability of PANTHER. We performed feature analysis in predicting disease types, which suggested insights and benefits of the identified pathway groups.

q-bio.QM↗
arXiv2020

Decentralized Source Localization without Sensor Parameters in Wireless Sensor Networks

This paper studies the source (event) localization problem in decentralized wireless sensor networks (WSNs) under the fault model without knowing the sensor parameters. Event localizations have many applications such as localizing intruders, Wifi hotspots and users, and faults in power systems. Previous studies assume the true knowledge (or good estimates) of sensor parameters (e.g., fault model probability or Region of Influence (ROI) of the source) for source localization. However, we propose two methods to estimate the source location in this paper under the fault model: hitting set approach and feature selection method, which only utilize the noisy data set at the fusion center for estimation of the source location without knowing the sensor parameters. The proposed methods have been shown to localize the source effectively. We also study the lower bound on the sample complexity requirement for hitting set method. These methods have also been extended for multiple sources localizations. In addition, we modify the proposed feature selection approach to use maximum likelihood. Finally, extensive simulations are carried out for different settings (i.e., the number of sensor nodes and sample complexity) to validate our proposed methods in comparison to centroid, maximum likelihood, FTML, SNAP estimators.

cs.LG↗
arXiv2020

Finite Blocklength Analysis of Gaussian Random Coding in AWGN Channels under Covert Constraint

This paper considers the achievability and converse bounds on the maximal channel coding rate at a given blocklength and error probability over AWGN channels. The problem stems from covert communication with Gaussian codewords. By re-visiting [18], we first present new and more general achievability bounds for random coding schemes under maximal or average probability of error requirements. Such general bounds are then applied to covert communication in AWGN channels where codewords are generated from Gaussian distribution while meeting the maximal power constraint. Further comparison is made between the new achievability bounds and existing one with deterministic codebooks.

cs.IT↗
arXiv2020

Towards Expressive Graph Representation

Graph Neural Network (GNN) aggregates the neighborhood of each node into the node embedding and shows its powerful capability for graph representation learning. However, most existing GNN variants aggregate the neighborhood information in a fixed non-injective fashion, which may map different graphs or nodes to the same embedding, reducing the model expressiveness. We present a theoretical framework to design a continuous injective set function for neighborhood aggregation in GNN. Using the framework, we propose expressive GNN that aggregates the neighborhood of each node with a continuous injective set function, so that a GNN layer maps similar nodes with similar neighborhoods to similar embeddings, different nodes to different embeddings and the equivalent nodes or isomorphic graphs to the same embeddings. Moreover, the proposed expressive GNN can naturally learn expressive representations for graphs with continuous node attributes. We validate the proposed expressive GNN (ExpGNN) for graph classification on multiple benchmark datasets including simple graphs and attributed graphs. The experimental results demonstrate that our model achieves state-of-the-art performances on most of the benchmarks.

cs.LG↗
arXiv2020

A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports

Joint image-text embedding extracted from medical images and associated contextual reports is the bedrock for most biomedical vision-and-language (V+L) tasks, including medical visual question answering, clinical image-text retrieval, clinical report auto-generation. In this study, we adopt four pre-trained V+L models: LXMERT, VisualBERT, UNIER and PixelBERT to learn multimodal representation from MIMIC-CXR radiographs and associated reports. The extrinsic evaluation on OpenI dataset shows that in comparison to the pioneering CNN-RNN model, the joint embedding learned by pre-trained V+L models demonstrate performance improvement in the thoracic findings classification task. We conduct an ablation study to analyze the contribution of certain model components and validate the advantage of joint embedding over text-only embedding. We also visualize attention maps to illustrate the attention mechanism of V+L models.

cs.CV↗
arXiv2020

Total Variation Distance Based Performance Analysis of Covert Communication over AWGN Channels in Non-asymptotic Regime

This paper investigates covert communication over an additive white Gaussian noise (AWGN) channel in finite block length regime on the assumption of Gaussian codebooks. We first review some achievability and converse bounds on the throughput under maximal power constraint. From these bounds and the analysis of TVD at the adversary, the first and second asymptotics of covert communication are investigated by the help of some divergences inequalities. Furthermore, the analytic solution of TVD, and approximation expansions which can be easily evaluated with given snr (signal noise ratio) are presented. In this way, the proper power level for covert communication can be approximated with given covert constraint of TVD, which leads to more accurate estimation of the power compared with preceding bounds. Further elaboration on the effect of such asymptotic characteristics on the primary channels's throughput in finite block regime is also provided. The results will be very helpful for understanding the behavior of the total variation distance and practical covert communication.

cs.IT↗
arXiv2020

Open-Set Recognition with Gaussian Mixture Variational Autoencoders

In inference, open-set classification is to either classify a sample into a known class from training or reject it as an unknown class. Existing deep open-set classifiers train explicit closed-set classifiers, in some cases disjointly utilizing reconstruction, which we find dilutes the latent representation's ability to distinguish unknown classes. In contrast, we train our model to cooperatively learn reconstruction and perform class-based clustering in the latent space. With this, our Gaussian mixture variational autoencoder (GMVAE) achieves more accurate and robust open-set classification results, with an average F1 improvement of 29.5%, through extensive experiments aided by analytical results.

cs.LG↗