Engineering Papers⌕ Search

Engineering topics

Christian, Blair

Publications and source records attributed to Christian, Blair.

Dataset Repository for Investigating Suicide Risk Using Social and Environmental Determinants of Health

Suicide is frequently modeled as a function of genetics and environment, where the latter refers to factors other than direct biological consequences, such as air quality, financial level, social connectivity, transportation and food access, and homelessness status. According to the World Health Organization, clean air, a stable climate, adequate water, sanitation and hygiene, safe chemical use, radiation protection, healthy and safe workplaces, sound agricultural practices, health-supportive cities and built environments, and a preserved natural environment are all prerequisites for good health. Understanding the relationships between these determinants and mental health outcomes requires standardized data that can be included in healthcare programs and health outcome models. There is a wealth of publicly available data on social and environmental factors provided by various US organizations that can benefit the design of health care systems and public health interventions, as well as improve our comprehension of factors that impact health. Such information would not only help improve the understanding of individual and community risk but also identify new risk factors that have not previously been therapeutically targeted, especially in terms of their impact on mental health. However, curating and standardizing such datasets is challenging because they are often recorded at numerous geographical and temporal resolutions and with varying spatial and temporal granularities. To address this challenge, we launched an endeavor in conjunction with the Veterans Health Administration to collect publicly available socioeconomic and environmental determinants of health statistics in the US. In this manuscript, we describe a social and environmental determinants of health (SEDH) datasets repository, data curation documentation, and a pipeline framework for data generation; This effort started in 2020, when we began constructing a scalable pipeline to automate the download, extraction, preparation, analysis, and production of datasets. These datasets have been made available to the VHA and may be shared upon agreement with collaborating organizations.

60 APPLIED LIFE SCIENCES↗

VA EDH Data Curation Documentation – FY2021, Rev. 2

The health and well-being of the Nation’s men and women who have served in uniform is the highest priority for the U.S. Department of Veterans Affairs (VA). VA is committed to providing timely access to high-quality, recovery-oriented, evidence-based mental health care that anticipates and responds to Veterans’ needs and supports the reintegration of returning Service members into their communities. VA is working to eliminate suicide among all Veterans by developing and implementing innovative suicide prevention approaches and resources.

60 APPLIED LIFE SCIENCES↗

CTSA MHRI Datasets

Oak Ridge National Laboratory (ORNL) has collaborated with MedStar Health Research Institute (MHRI) to develop, test, and validate health outcomes using electronic health records (EHRs) from hospitals associated with participating Clinical and Translational Science Awards (CTSA). MHRI, the research organization of MedStar Health (MSH), has a history of initiating projects, both in the laboratory and in the field, that serve the needs of medically underserved and disenfranchised groups. In this document, the ORNL team is providing data curation documentation for the following datasets, which are publicly available: 1. Area Deprivation Index (ADI) 2015 block group; 2. Child Opportunity Index 2015 tract; 3. Low food access 2017 block group; 4. Neighborhood deprivation index 2017 tract; 5. Social Capital Index 2014 county; and, 6. Social Vulnerability Index 2014 tract.

54 ENVIRONMENTAL SCIENCES↗

VA EDH Data Curation Documentation FY22-Q2, Rev. 2

The health and well-being of the Nation’s men and women who have served in uniform is the highest priority for the U.S. Department of Veterans Affairs (VA). VA is committed to providing timely access to high-quality, recovery-oriented, evidence-based mental health care that anticipates and responds to Veterans’ needs and supports the reintegration of returning Service members into their communities. VA is working to eliminate suicide among all Veterans by developing and implementing innovative suicide prevention approaches and resources. Health outcomes, such as suicide are typically modeled as a function of genetics and environment, where environment refers to factors beyond medical, e.g., air quality, access to transportation and food, homelessness status, etc. Mental health outcomes for each individual are considered to be associated with multiple stressors that fall under a variety of categories socioeconomic, economic, physical environment. Understanding the relationships between these stressors, covariates and health outcomes, requires curated, standardized data that can be input into the VA’s Recovery Engagement and Coordination for Health - Veterans Enhanced Treatment (REACH VET) or other health outcomes model. Environmental Determinants of Health (EDH) as defined by the World Health Organization (WHO) is clean air, stable climate, adequate water, sanitation and hygiene, safe use of chemicals, protection from radiation, healthy and safe workplaces, sound agricultural practices, health-supportive cities and built environments, and a preserved nature are all prerequisites for good health.

60 APPLIED LIFE SCIENCES↗

VA EDH Data Curation Documentation FY2022-Q1, Rev. 2

The health and well-being of the Nation’s men and women who have served in uniform is the highest priority for the U.S. Department of Veterans Affairs (VA). VA is committed to providing timely access to high-quality, recovery-oriented, evidence-based mental health care that anticipates and responds to Veterans’ needs and supports the reintegration of returning Service members into their communities. VA is working to eliminate suicide among all Veterans by developing and implementing innovative suicide prevention approaches and resources.

60 APPLIED LIFE SCIENCES↗

Privacy-Preserving Knowledge Transfer with Bootstrap Aggregation of Teacher Ensembles

There is a need to transfer knowledge among institutions and organizations to save effort in annotation and labeling or in enhancing task performance. However, knowledge transfer is difficult because of restrictions that are in place to ensure data security and privacy. Institutions are not allowed to exchange data or perform any activity that may expose personal information. With the leverage of a differential privacy algorithm in a high-performance computing environment, we propose a new training protocol, Bootstrap Aggregation of Teacher Ensembles (BATE), which is applicable to various types of machine learning models. The BATE algorithm is based on and provides enhancements to the PATE algorithm, maintaining competitive task performance scores on complex datasets with underrepresented class labels.We conducted a proof-of-the-concept study of the information extraction from cancer pathology report data from four cancer registries and performed comparisons between four scenarios: no collaboration, no privacy-preserving collaboration, the PATE algorithm, and the proposed BATE algorithm. The results showed that the BATE algorithm maintained competitive macro-averaged F1 scores, demonstrating that the suggested algorithm is an effective yet privacy-preserving method for machine learning and deep learning solutions.

Yoon, Hong-Jun↗

Classifying Cancer Pathology Reports with Hierarchical Self-Attention Networks

We introduce a deep learning architecture, hierarchical self-attention networks (HiSANs), designed for classifying pathology reports and show how its unique architecture leads to a new state-of-the-art in accuracy, faster training, and clear interpretability. We evaluate performance on a corpus of 374,899 pathology reports obtained from the National Cancer Institute's (NCI) Surveillance, Epidemiology, and End Results (SEER) program. Each pathology report is associated with five clinical classification tasks – site, laterality, behavior, histology, and grade. We compare the performance of the HiSAN against other machine learning and deep learning approaches commonly used on medical text data – Naive Bayes, logistic regression, convolutional neural networks, and hierarchical attention networks (the previous state-of-the-art). We show that HiSANs are superior to other machine learning and deep learning text classifiers in both accuracy and macro F-score across all five classification tasks. Compared to the previous state-of-the-art, hierarchical attention networks, HiSANs not only are an order of magnitude faster to train, but also achieve about 1% better relative accuracy and 5% better relative macro F-score.

60 APPLIED LIFE SCIENCES↗

Extraction of Tumor Site from Cancer Pathology Reports using Deep Filters

Purpose: Pathology reports are the primary source of information concerning the millions of cancer cases across the United States. Cancer registries manually process the pathology reports to extract the pertinent information including primary tumor site, behavior, histology, laterality, and grade. Processing a large volume of the pathology reports in a timely manner is a continuing challenge for cancer registries. The purpose of this study is to develop an information extraction pipeline to reliably and efficiently extract reportable information. Method: We have developed a novel inverse-regression (IR) based information extraction pipeline. The inverse-regression based supervised filter has been successfully applied to many application domains. However, its application to the information extraction from unstructured text is hindered primarily by the extreme high-dimensionality of n-gram representations of text. In this study, we attempt to overcome the obstacles by a novel bootstrapping strategy. First, we use an information-theoretic mutual information based filter to discard the excessive and redundant n-gram features. This step reduces the size and improves the condition number of the sample covariance matrix, thus reducing the computational cost and improving the numerical stability of the subsequent inverse-regression step. Then we use localized sliced inverse-regression (LSIR) to learn a low-dimensional discriminatory subspace for information inference. In particular, we use the k-nearest neighbors of an unlabeled pathology report in the learned representation to infer the desired information from the labeled data in a supervised manner. Results: The experiments were conducted on a set of de-identified pathology reports with human expert labels as the ground truth. Our pipeline consistently performed better than or comparable to the best performing state-of-the-art methods while reducing the training and inference times substantially. Conclusion: Our results demonstrate the potential of inverse-regression based information extraction pipeline for reliable and efficient information extraction from unstructured text. The information extracted from the pathology reports can be used along with clinical information, medical imaging, and genomic information to instigate discoveries in cancer research.

Dubey, Abhishek↗

Deep Transfer Learning Across Cancer Registries for Information Extraction from Pathology Reports

Automated text information extraction from cancer pathology reports is an active area of research to support national cancer surveillance. A well-known challenge is how to develop information extraction tools with robust performance across cancer registries. In this study we investigated whether transfer learning (TL) with a convolutional neural network (CNN) can facilitate cross-registry knowledge sharing. Specifically, we performed a series of experiments to determine whether a CNN trained with single-registry data is capable of transferring knowledge to another registry or whether developing a cross-registry knowledge database produces a more effective and generalizable model. Using data from two cancer registries and primary tumor site and topography as the information extraction task of interest, our study showed that TL results in 6.90% and 17.22% improvement of classification m acro F -score o ver the baseline single-registry models. Detailed analysis illustrated that the observed improvement is evident in the low prevalence classes.

Alawad, Mohammed↗

A Knowledge Graph Approach for the Secondary Use of Cancer Registry Data

Population-based central cancer registries collect valuable structured and unstructured data primarily for cancer surveillance and research, enhancing insights into clinical features associated with cancer occurrence, cancer treatment, and cancer outcomes to guide interventions which reduce the cancer burden. Cancer registries primarily collect data on (1) cancer type (case or tumor); (2) patient demographics such as age, gender, and residential address at time of diagnosis; (3) planned first course of treatment; and (4) date of last contact, vital status, and cause of death. Cancer registry data is dynamic, structured data, which is extracted from many unstructured sources such as electronic healthcare records, and consolidated for reporting and other purposes. While available advanced analytic tools such as SEER*Stat have the ability to build SAS queries, we, however, explore an innovative knowledge graph approach to organizing cancer registry data for advanced analytics and visualization, which has unique advantages over approaches of existing tools. This innovative knowledge graph approach semantically enriches the data and easily enables linkage with third-party data, which can better explain variation in outcomes. We have developed a prototype knowledge graph based on data from the Louisiana Tumor Registry and other publicly available datasets including Behavioral Risk Factor Surveillance System, Clinical Trials, DBpedia, GeoNames, Rural-Urban Continuum Codes, and Semantic MEDLINE. The resource description framework (RDF) data model was selected to represent our knowledge graph, which contains more than 25 billion triples and is ~4TB in storage size. To exhibit the benefits of the knowledge graph approach, we used scenario specific queries, which find the relationships between cancer treatment sequences and outcomes. To illustrate its ease of use in iterative analysis, the knowledge graph was linked to external datasets for performing complex queries across multiple datasets. In addition, we used knowledge graphs to identify data discrepancies and to handle schema changes. Finally, we visualized the knowledge graph to discover data patterns. Our results demonstrate this graph-based solution enables cancer researchers to execute complex queries and more easily perform iterative analyses to improve understanding of cancer registry data. In the future, we would like to use high-performance computing (HPC) resources for faster-generating hypotheses with clinical potential from our knowledge graph.

Hasan, S M Shamimul↗

Selective Information Extraction Strategies for Cancer Pathology Reports with Convolutional Neural Networks

To trust model predictions, it is important to ensure new data scored by the model comes from the same population used for model training. If the model is used to score new data different than the model’s training data, then predictions and model performance metrics cannot be trusted. Identifying and excluding these anomalous data points is an important task when using models in the real world. Traditional machine learning algorithms and classifiers don’t have the capability to abstain in this case. Here we propose a data-novelty detection algorithm for the Convolutional Neural Network classifier, yielding a rejection score for each new data point scored. It is a post-modeling procedure which examines the distribution of convolution filters to determine if the prediction should be trusted. We apply this algorithm to an information extraction model for a natural language text corpus. We evaluated the algorithm performance using a primary cancer site classification model applied to cancer pathology reports. Results demonstrate that the algorithm is an effective way to exclude cancer pathology reports from model scoring when they do not contain the expected information necessary to accurately classify the primary cancer type.

Yoon, Hong-Jun↗

CAT: computer aided triage improving upon the Bayes risk through ε-refusal triage rules

Manual extraction of information from electronic pathology (epath) reports to populate the Surveillance, Epidemiology, and End Result (SEER) database is labor intensive. Systematizing the data extraction automatically using machine-learning (ML) and natural language processing (NLP) is desirable to reduce the human labor required to populate the SEER database and to improve the timeliness of the data. This enables scaling up registry efficiency and collection of new data elements. To ensure the integrity, quality, and continuity of the SEER data, the misclassification error of ML and NPL algorithms needs to be negligible. Current algorithms fail to achieve the precision of human experts who can bring additional information in their assessments. Differences in registry format and the desire to develop a common information extraction platform further complicate the ML/NLP tasks. The purpose of our study is to develop triage rules to partially automate registry workflow to improve the precision of the auto-extracted information. This paper presents a mathematical framework to improve the precision of a classifier beyond that of the Bayes classifier by selectively classifying item that are most likely to be correct. This results in a triage rule that only classifies a subset of the item. We characterize the optimal triage rule and demonstrate its usefulness in the problem of classifying cancer site from electronic pathology reports to achieve a desired precision. From the mathematical formalism, we propose a heuristic estimate for triage rule based on post-processing the soft-max output from standard machine learning algorithms. We show, in test cases, that the triage rule significantly improve the classification accuracy.

60 APPLIED LIFE SCIENCES↗

Retrofitting Word Embeddings with the UMLS Metathesaurus for Clinical Information Extraction

Deep learning has surged in popularity and proven to be effective for various artificial intelligence applications including information extraction from cancer pathology reports. Since word representation is a core unit that enables deep learning algorithms to understand words and be able to perform NLP, this representation must include as much information as possible to help these algorithms achieve high classification performance. Therefore, in this work in addition to the distributional information of words in large sized corpora, we use UMLS vocabulary resources to enrich the vector space representation of words with the semantic relations between words. These resources provide many terminologies pertaining to cancer. The refined word embeddings are used with a convolutional neural (CNN) model to extract four data elements from cancer pathology reports; ICD-O-3 tumor topography codes, tumor laterality, behavior, and histological grade. We observed that using UMLS vocabulary resources to enrich word embeddings of CNN models consistently outperformed CNN models without pre-training word embeddings and even with pre-trained word embeddings on a domain specific corpus across all four tasks. The results show marginal improvement on the laterality task, but a significant improvement on the other tasks, especially for the macro-f score. Specifically, the improvements are 3%, 13%, and 15% for tumor site, histological grade, and behavior tasks, respectively. This approach is encouraging to enrich word embeddings with more clinical data resources to be used for information abstraction tasks from clinical pathology reports.

Alawad, Mohammed↗

Scalable deep text comprehension for Cancer surveillance on high-performance computing

Background: Deep Learning (DL) has advanced the state-of-the-art capabilities in bioinformatics applications which has resulted in trends of increasingly sophisticated and computationally demanding models trained by larger and larger data sets. This vastly increased computational demand challenges the feasibility of conducting cutting-edge research. One solution is to distribute the vast computational workload across multiple computing cluster nodes with data parallelism algorithms. In this study, we used a High-Performance Computing environment and implemented the Downpour Stochastic Gradient Descent algorithm for data parallelism to train a Convolutional Neural Network (CNN) for the natural language processing task of information extraction from a massive dataset of cancer pathology reports. We evaluated the scalability improvements using data parallelism training and the Titan supercomputer at Oak Ridge Leadership Computing Facility. To evaluate scalability, we used different numbers of worker nodes and performed a set of experiments comparing the effects of different training batch sizes and optimizer functions.Results: We found that Adadelta would consistently converge at a lower validation loss, though requiring over twice as many training epochs as the fastest converging optimizer, RMSProp. The Adam optimizer consistently achieved a close 2nd place minimum validation loss significantly faster; using a batch size of 16 and 32 allowed the network to converge in only 4.5 training epochs.Conclusions: We demonstrated that the networked training process is scalable across multiple compute nodes communicating with message passing interface while achieving higher classification accuracy compared to a traditional machine learning algorithm.

Qiu, John X.↗

Filter pruning of Convolutional Neural Networks for text classification: A case study of cancer pathology report comprehension

Convolutional Neural Networks (CNN) have recently demonstrated effective performance in many Natural Language Processing tasks. In this study, we explore a novel approach for pruning a CNN's convolution filters using our new data-driven utility score. We have applied this technique to an information extraction task of classifying a dataset of cancer pathology reports by cancer type, a highly imbalanced dataset. Compared to standard CNN training, our new algorithm resulted in a nearly .07 increase in the micro-averaged F1-score and a strong .22 increase in the macro-averaged F1-score using a model with nearly a third fewer network weights. We show how directly utilizing a network's interpretation of data can result in strong performance gains, particularly with severely imbalanced datasets.

Yoon, Hong-Jun↗