Feichen Shen

David Oniani, Chen Wang, Yiqing Zhao et al.

Cancer is responsible for millions of deaths worldwide every year. Although significant progress has been achieved in cancer medicine, many issues remain to be addressed for improving cancer therapy. Appropriate cancer patient stratification is the prerequisite for selecting appropriate treatment plan, as cancer patients are of known heterogeneous genetic make-ups and phenotypic differences. In this study, built upon deep phenotypic characterizations extractable from Mayo Clinic electronic health records (EHRs) and genetic test reports for a collection of cancer patients, we developed a system leveraging a joint of phenotypic and genetic features for cancer patient subgrouping. The workflow is roughly divided into three parts: feature preprocessing, cancer patient classification, and cancer patient clustering based. In feature preprocessing step, we performed filtering, retaining the most relevant features. In cancer patient classification, we utilized joint categorical features to build a patient-feature matrix and applied nine different machine learning models, Random Forests (RF), Decision Tree (DT), Support Vector Machine (SVM), Naive Bayes (NB), Logistic Regression (LR), Multilayer Perceptron (MLP), Gradient Boosting (GB), Convolutional Neural Network (CNN), and Feedforward Neural Network (FNN), for classification purposes. Finally, in the cancer patient clustering step, we leveraged joint embeddings features and patient-feature associations to build an undirected feature graph and then trained the cancer feature node embeddings.

David Oniani, Chen Wang, Yiqing Zhao et al.

Cancer is responsible for millions of deaths worldwide every year. Although significant progress hasbeen achieved in cancer medicine, many issues remain to be addressed for improving cancer therapy.Appropriate cancer patient stratification is the prerequisite for selecting appropriate treatment plan, ascancer patients are of known heterogeneous genetic make-ups and phenotypic differences. In thisstudy, built upon deep phenotypic characterizations extractable from Mayo Clinic electronic healthrecords (EHRs) and genetic test reports for a collection of cancer patients, we evaluated variousgraph neural networks (GNNs) leveraging a joint of phenotypic and genetic features for cancer typeclassification. Models were applied and fine-tuned on the Mayo Clinic cancer disease dataset. Theassessment was done through the reported accuracy, precision, recall, and F1 values as well as throughF1 scores based on the disease class. Per our evaluation results, GNNs on average outperformed thebaseline models with mean statistics always being higher that those of the baseline models (0.849 vs0.772 for accuracy, 0.858 vs 0.794 for precision, 0.843 vs 0.759 for recall, and 0.843 vs 0.855 for F1score). Among GNNs, ChebNet, GraphSAGE, and TAGCN showed the best performance, while GATshowed the worst. We applied and compared eight GNN models including AGNN, ChebNet, GAT,GCN, GIN, GraphSAGE, SGC, and TAGCN on the Mayo Clinic cancer disease dataset and assessedtheir performance as well as compared them with each other and with more conventional machinelearning models such as decision tree, gradient boosting, multi-layer perceptron, naive bayes, andrandom forest which we used as the baselines.

Sunyang Fu, David Chen, Huan He et al.

Background Concept extraction, a subdomain of natural language processing (NLP) with a focus on extracting concepts of interest, has been adopted to computationally extract clinical information from text for a wide range of applications ranging from clinical decision support to care quality improvement. Objectives In this literature review, we provide a methodology review of clinical concept extraction, aiming to catalog development processes, available methods and tools, and specific considerations when developing clinical concept extraction applications. Methods Based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a literature search was conducted for retrieving EHR-based information extraction articles written in English and published from January 2009 through June 2019 from Ovid MEDLINE In-Process & Other Non-Indexed Citations, Ovid MEDLINE, Ovid EMBASE, Scopus, Web of Science, and the ACM Digital Library. Results A total of 6,686 publications were retrieved. After title and abstract screening, 228 publications were selected. The methods used for developing clinical concept extraction applications were discussed in this review.

Sijia Liu, Yanshan Wang, Andrew Wen et al.

Background: Widespread adoption of electronic health records (EHRs) has enabled secondary use of EHR data for clinical research and healthcare delivery. Natural language processing (NLP) techniques have shown promise in their capability to extract the embedded information in unstructured clinical data, and information retrieval (IR) techniques provide flexible and scalable solutions that can augment the NLP systems for retrieving and ranking relevant records. Methods: In this paper, we present the implementation of Cohort Retrieval Enhanced by Analysis of Text from EHRs (CREATE), a cohort retrieval system that can execute textual cohort selection queries on both structured and unstructured EHR data. CREATE is a proof-of-concept system that leverages a combination of structured queries and IR techniques on NLP results to improve cohort retrieval performance while adopting the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) to enhance model portability. The NLP component empowered by cTAKES is used to extract CDM concepts from textual queries. We design a hierarchical index in Elasticsearch to support CDM concept search utilizing IR techniques and frameworks. Results: Our case study on 5 cohort identification queries evaluated using the IR metric, P@5 (Precision at 5) at both the patient-level and document-level, demonstrates that CREATE achieves an average P@5 of 0.90, which outperforms systems using only structured data or only unstructured data with average P@5s of 0.54 and 0.74, respectively.

Yanshan Wang, Naveed Afzal, Sunyang Fu et al.

The wide adoption of electronic health records (EHRs) has enabled a wide range of applications leveraging EHR data. However, the meaningful use of EHR data largely depends on our ability to efficiently extract and consolidate information embedded in clinical text where natural language processing (NLP) techniques are essential. Semantic textual similarity (STS) that measures the semantic similarity between text snippets plays a significant role in many NLP applications. In the general NLP domain, STS shared tasks have made available a huge collection of text snippet pairs with manual annotations in various domains. In the clinical domain, STS can enable us to detect and eliminate redundant information that may lead to a reduction in cognitive burden and an improvement in the clinical decision-making process. This paper elaborates our efforts to assemble a resource for STS in the medical domain, MedSTS. It consists of a total of 174,629 sentence pairs gathered from a clinical corpus at Mayo Clinic. A subset of MedSTS (MedSTS_ann) containing 1,068 sentence pairs was annotated by two medical experts with semantic similarity scores of 0-5 (low to high similarity). We further analyzed the medical concepts in the MedSTS corpus, and tested four STS systems on the MedSTS_ann corpus. In the future, we will organize a shared task by releasing the MedSTS_ann corpus to motivate the community to tackle the real world clinical problems.

Yanshan Wang, Sunghwan Sohn, Sijia Liu et al.

Objective: To automatically create large labeled training datasets and reduce the efforts of feature engineering for training accurate machine learning models for clinical information extraction. Materials and Methods: We propose a distant supervision paradigm empowered by deep representation for extracting information from clinical text. In this paradigm, the rule-based NLP algorithms are utilized to generate weak labels and create large training datasets automatically. Additionally, we use pre-trained word embeddings as deep representation to eliminate the need of task-specific feature engineering for machine learning. We evaluated the effectiveness of the proposed paradigm on two clinical information extraction tasks: smoking status extraction and proximal femur (hip) fracture extraction. We tested three prevalent machine learning models, namely, Convolutional Neural Networks (CNN), Support Vector Machine (SVM), and Random Forrest (RF). Results: The results indicate that CNN is the best fit to the proposed distant supervision paradigm. It outperforms the rule-based NLP algorithms given large datasets by capturing additional extraction patterns. We also verified the advantage of word embedding feature representation in the paradigm over term frequency-inverse document frequency (tf-idf) and topic modeling representations. Discussion: In the clinical domain, the limited amount of labeled data is always a bottleneck for applying machine learning. Additionally, the performance of machine learning approaches highly depends on task-specific feature engineering. The proposed paradigm could alleviate those problems by leveraging rule-based NLP algorithms to automatically assign weak labels and eliminating the need of task-specific feature engineering using word embedding feature representation.

Feichen Shen, David W Larson, James M. Naessens et al.

Postsurgical complications (PSCs) are known as a deviation from the normal postsurgical course and categorized by severity and treatment requirements. Surgical site infection (SSI) is one of major PSCs and the most common healthcare-associated infection, resulting in increased length of hospital stay and cost. In this work, we assessed an automated way to generate lexicon (i.e., keyword features) from clinical narratives using sublanguage analysis with heuristics to detect SSI and evaluated these keywords with medical experts. To further validate our approach, we also conducted decision tree algorithm on cohort using automatically generated keywords. The results show that our framework was able to identify SSI keywords from clinical narratives and to support search-based natural language processing (NLP) approaches by augmenting search queries.

Feichen Shen, Yugyung Lee

Biomedical ontology refers to a shared conceptualization for a biomedical domain of interest that has vastly improved data management and data sharing through the open data movement. The rapid growth and availability of biomedical data make it impractical and computationally expensive to perform manual analysis and query processing with the large scale ontologies. The lack of ability in analyzing ontologies from such a variety of sources, and supporting knowledge discovery for clinical practice and biomedical research should be overcome with new technologies. In this study, we developed a Medical Topic discovery and Query generation framework (MedTQ), which was composed by a series of approaches and algorithms. A predicate neighborhood pattern-based approach introduced has the ability to compute the similarity of predicates (relations) in ontologies. Given a predicate similarity metric, machine learning algorithms have been developed for automatic topic discovery and query generation. The topic discovery algorithm, called the hierarchical K-Means algorithm was designed by extending an existing supervised algorithm (K-means clustering) for the construction of a topic hierarchy. In the hierarchical K-Means algorithm, a level-by-level optimization strategy was selected for consistent with the strongly association between elements within a topic. Automatic query generation was facilitated for discovered topic that could be guided users for interactive query design and processing. Evaluation was conducted to generate topic hierarchy for DrugBank ontology as a case study. Results demonstrated that the MedTQ framework can enhance knowledge discovery by capturing underlying structures from domain specific data and ontologies.

Yanshan Wang, Sijia Liu, Naveed Afzal et al.

Word embeddings have been widely used in biomedical Natural Language Processing (NLP) applications as they provide vector representations of words capturing the semantic properties of words and the linguistic relationship between words. Many biomedical applications use different textual resources (e.g., Wikipedia and biomedical articles) to train word embeddings and apply these word embeddings to downstream biomedical applications. However, there has been little work on evaluating the word embeddings trained from these resources.In this study, we provide an empirical evaluation of word embeddings trained from four different resources, namely clinical notes, biomedical publications, Wikipedia, and news. We performed the evaluation qualitatively and quantitatively. For the qualitative evaluation, we manually inspected five most similar medical words to a given set of target medical words, and then analyzed word embeddings through the visualization of those word embeddings. For the quantitative evaluation, we conducted both intrinsic and extrinsic evaluation. Based on the evaluation results, we can draw the following conclusions. First, the word embeddings trained on clinical notes and biomedical publications can capture the semantics of medical terms better, and find more relevant similar medical terms, and are closer to human experts' judgments, compared to these trained on Wikipedia and news. Second, there does not exist a consistent global ranking of word embedding quality for downstream biomedical NLP applications. However, adding word embeddings as extra features will improve results on most downstream tasks. Finally, the word embeddings trained on biomedical domain corpora do not necessarily have better performance than those trained on other general domain corpora for any downstream biomedical NLP tasks.