Inter-patient distance metrics using SNOMED CT defining relationships

Applying Natural Language Processing to Textual Data From Clinical Data Warehouses: Systematic Review

BACKGROUND

In recent years, health data collected during the clinical care process have been often repurposed for secondary use through clinical data warehouses (CDWs), which interconnect disparate data from different sources. A large amount of information of high clinical value is stored in unstructured text format. Natural language processing (NLP), which implements algorithms that can operate on massive unstructured textual data, has the potential to structure the data and make clinical information more accessible.

OBJECTIVE

The aim of this review was to provide an overview of studies applying NLP to textual data from CDWs. It focuses on identifying the (1) NLP tasks applied to data from CDWs and (2) NLP methods used to tackle these tasks.

METHODS

This review was performed according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. We searched for relevant articles in 3 bibliographic databases: PubMed, Google Scholar, and ACL Anthology. We reviewed the titles and abstracts and included articles according to the following inclusion criteria: (1) focus on NLP applied to textual data from CDWs, (2) articles published between 1995 and 2021, and (3) written in English.

RESULTS

We identified 1353 articles, of which 194 (14.34%) met the inclusion criteria. Among all identified NLP tasks in the included papers, information extraction from clinical text (112/194, 57.7%) and the identification of patients (51/194, 26.3%) were the most frequent tasks. To address the various tasks, symbolic methods were the most common NLP methods (124/232, 53.4%), showing that some tasks can be partially achieved with classical NLP techniques, such as regular expressions or pattern matching that exploit specialized lexica, such as drug lists and terminologies. Machine learning (70/232, 30.2%) and deep learning (38/232, 16.4%) have been increasingly used in recent years, including the most recent approaches based on transformers. NLP methods were mostly applied to English language data (153/194, 78.9%).

CONCLUSIONS

CDWs are central to the secondary use of clinical texts for research purposes. Although the use of NLP on data from CDWs is growing, there remain challenges in this field, especially with regard to languages other than English. Clinical NLP is an effective strategy for accessing, extracting, and transforming data from CDWs. Information retrieved with NLP can assist in clinical research and have an impact on clinical practice.

HESML: a real-time semantic measures library for the biomedical domain with a reproducible survey

BACKGROUND

Ontology-based semantic similarity measures based on SNOMED-CT, MeSH, and Gene Ontology are being extensively used in many applications in biomedical text mining and genomics respectively, which has encouraged the development of semantic measures libraries based on the aforementioned ontologies. However, current state-of-the-art semantic measures libraries have some performance and scalability drawbacks derived from their ontology representations based on relational databases, or naive in-memory graph representations. Likewise, a recent reproducible survey on word similarity shows that one hybrid IC-based measure which integrates a shortest-path computation sets the state of the art in the family of ontology-based semantic measures. However, the lack of an efficient shortest-path algorithm for their real-time computation prevents both their practical use in any application and the use of any other path-based semantic similarity measure.

RESULTS

To bridge the two aforementioned gaps, this work introduces for the first time an updated version of the HESML Java software library especially designed for the biomedical domain, which implements the most efficient and scalable ontology representation reported in the literature, together with a new method for the approximation of the Dijkstra's algorithm for taxonomies, called Ancestors-based Shortest-Path Length (AncSPL), which allows the real-time computation of any path-based semantic similarity measure.

CONCLUSIONS

We introduce a set of reproducible benchmarks showing that HESML outperforms by several orders of magnitude the current state-of-the-art libraries in the three aforementioned biomedical ontologies, as well as the real-time performance and approximation quality of the new AncSPL shortest-path algorithm. Likewise, we show that AncSPL linearly scales regarding the dimension of the common ancestor subgraph regardless of the ontology size. Path-based measures based on the new AncSPL algorithm are up to six orders of magnitude faster than their exact implementation in large ontologies like SNOMED-CT and GO. Finally, we provide a detailed reproducibility protocol and dataset as supplementary material to allow the exact replication of all our experiments and results.

Use of the Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) for Processing Free Text in Health Care: Systematic Scoping Review

Background

Interoperability and secondary use of data is a challenge in health care. Specifically, the reuse of clinical free text remains an unresolved problem. The Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) has become the universal language of health care and presents characteristics of a natural language. Its use to represent clinical free text could constitute a solution to improve interoperability.

Objective

Although the use of SNOMED and SNOMED CT has already been reviewed, its specific use in processing and representing unstructured data such as clinical free text has not. This review aims to better understand SNOMED CT's use for representing free text in medicine.

Methods

A scoping review was performed on the topic by searching MEDLINE, Embase, and Web of Science for publications featuring free-text processing and SNOMED CT. A recursive reference review was conducted to broaden the scope of research. The review covered the type of processed data, the targeted language, the goal of the terminology binding, the method used and, when appropriate, the specific software used.

Results

In total, 76 publications were selected for an extensive study. The language targeted by publications was 91% (n=69) English. The most frequent types of documents for which the terminology was used are complementary exam reports (n=18, 24%) and narrative notes (n=16, 21%). Mapping to SNOMED CT was the final goal of the research in 21% (n=16) of publications and a part of the final goal in 33% (n=25). The main objectives of mapping are information extraction (n=44, 39%), feature in a classification task (n=26, 23%), and data normalization (n=23, 20%). The method used was rule-based in 70% (n=53) of publications, hybrid in 11% (n=8), and machine learning in 5% (n=4). In total, 12 different software packages were used to map text to SNOMED CT concepts, the most frequent being Medtex, Mayo Clinic Vocabulary Server, and Medical Text Extraction Reasoning and Mapping System. Full terminology was used in 64% (n=49) of publications, whereas only a subset was used in 30% (n=23) of publications. Postcoordination was proposed in 17% (n=13) of publications, and only 5% (n=4) of publications specifically mentioned the use of the compositional grammar.

Conclusions

SNOMED CT has been largely used to represent free-text data, most frequently with rule-based approaches, in English. However, currently, there is no easy solution for mapping free text to this terminology and to perform automatic postcoordination. Most solutions conceive SNOMED CT as a simple terminology rather than as a compositional bag of ontologies. Since 2012, the number of publications on this subject per year has decreased. However, the need for formal semantic representation of free text in health care is high, and automatic encoding into a compositional ontology could be a solution.

Evaluation of standard and semantically-augmented distance metrics for neurology patients

Background

Patient distances can be calculated based on signs and symptoms derived from an ontological hierarchy. There is controversy as to whether patient distance metrics that consider the semantic similarity between concepts can outperform standard patient distance metrics that are agnostic to concept similarity. The choice of distance metric can dominate the performance of classification or clustering algorithms. Our objective was to determine if semantically augmented distance metrics would outperform standard metrics on machine learning tasks.

Methods

We converted the neurological findings from 382 published neurology cases into sets of concepts with corresponding machine-readable codes. We calculated patient distances by four different metrics (cosine distance, a semantically augmented cosine distance, Jaccard distance, and a semantically augmented bipartite distance). Semantic augmentation for two of the metrics depended on concept similarities from a hierarchical neuro-ontology. For machine learning algorithms, we used the patient diagnosis as the ground truth label and patient findings as machine learning features. We assessed classification accuracy for four classifiers and cluster quality for two clustering algorithms for each of the distance metrics.

Results

Inter-patient distances were smaller when the distance metric was semantically augmented. Classification accuracy and cluster quality were not significantly different by distance metric.

Conclusion

Although semantic augmentation reduced inter-patient distances, we did not find improved classification accuracy or improved cluster quality with semantically augmented patient distance metrics when applied to a dataset of neurology patients. Further work is needed to assess the utility of semantically augmented patient distances.

Prediction of Medical Concepts in Electronic Health Records: Similar Patient Analysis

Background

Medicine 2.0—the adoption of Web 2.0 technologies such as social networks in health care—creates the need for apps that can find other patients with similar experiences and health conditions based on a patient’s electronic health record (EHR). Concurrently, there is an increasing number of longitudinal EHR data sets with rich information, which are essential to fulfill this need.

Objective

This study aimed to evaluate the hypothesis that we can leverage similar EHRs to predict possible future medical concepts (eg, disorders) from a patient’s EHR.

Methods

We represented patients’ EHRs using time-based prefixes and suffixes, where each prefix or suffix is a set of medical concepts from a medical ontology. We compared the prefixes of other patients in the collection with the state of the current patient using various interpatient distance measures. The set of similar prefixes yields a set of suffixes, which we used to determine probable future concepts for the current patient’s EHR.

Results

We evaluated our methods on the Multiparameter Intelligent Monitoring in Intensive Care II data set of patients, where we achieved precision up to 56.1% and recall up to 69.5%. For a limited set of clinically interesting concepts, specifically a set of procedures, we found that 86.9% (353/406) of the true-positives are clinically useful, that is, these procedures were actually performed later on the patient, and only 4.7% (19/406) of true-positives were completely irrelevant.

Conclusions

These initial results indicate that predicting patients’ future medical concepts is feasible. Effectively predicting medical concepts can have several applications, such as managing resources in a hospital.

Supporting Translational Research on Inherited Cardiomyopathies through Information Technology

Objectives: The INHERITANCE project, funded by the European Commission, is aimed at studying genetic or inherited Dilated cardiomyopathies (DCM) and at understanding the impact and management of the disease within families that suffer from heart conditions that are caused by DCMs. The biomedical informatics research activity of the project aims at implementing information technology solutions to support the project team in the different phases of their research, in particular in genes screening prioritization and new gene-disease association discovery.

Methods: In order to manage the huge quantity of scientific, clinical and patient data generated by the project several advanced biomedical informatics tools have been developed. The paper describes a layer of software instruments to support translation of the results of the project in clinical practice as well as to support the scientific discovery process. This layer includes data warehousing, intelligent querying of the phenotype data, integrated search of biological data and knowledge repositories, text mining of the relevant literature, and case based reasoning.

Results: At the moment, a set of 1,394 patients and 9,784 observations has been stored into the INHERITANCE data warehouse. The literature database contains more than 1,100,000 articles retrieved from the Pubmed and generically related to cardiac diseases, already analyzed for extracting medical concepts and genes.

Conclusions: After two years of project the data warehouse has been completely set up and the text mining tools for automatic literature analysis have been implemented and tested. A first prototype of the decision support tool for knowledge discovery and gene prioritization is available, but a more complete release is still under development.

Association Patterns of Ontological Features Signify Electronic Health Records in Liver Cancer

Electronic Health Record (EHR) system enables clinical decision support. In this study, a set of 112 abdominal computed tomography imaging examination reports, consisting of 59 cases of hepatocellular carcinoma (HCC) or liver metastases (so-called HCC group for simplicity) and 53 cases with no abnormality detected (NAD group), were collected from four hospitals in Hong Kong. We extracted terms related to liver cancer from the reports and mapped them to ontological features using Systematized Nomenclature of Medicine (SNOMED) Clinical Terms (CT). The primary predictor panel was formed by these ontological features. Association levels between every two features in the HCC and NAD groups were quantified using Pearson's correlation coefficient. The HCC group reveals a distinct association pattern that signifies liver cancer and provides clinical decision support for suspected cases, motivating the inclusion of new features to form the augmented predictor panel. Logistic regression analysis with stepwise forward procedure was applied to the primary and augmented predictor sets, respectively. The obtained model with the new features attained 84.7% sensitivity and 88.4% overall accuracy in distinguishing HCC from NAD cases, which were significantly improved when compared with that without the new features.

Computing semantic similarity between biomedical concepts using new information content approach

The exploitation of heterogeneous clinical sources and healthcare records is fundamental in clinical and translational research. The determination of semantic similarity between word pairs is an important component of text understanding that enables the processing and structuring of textual resources. Some of these measures have been adapted to the biomedical field by incorporating domain information extracted from clinical data or from medical ontologies such as MeSH. This study focuses on Information Content (IC) based measures that exploit the topological parameters of the taxonomy to express the semantics of a concept. A new intrinsic IC computing method based on the taxonomical parameters of the ancestors' subgraph is then assigned to a biomedical concept into the "is a" hierarchy. Moreover, we present a study of the topological parameters through the MeSH taxonomy. This study treats the semantic interpretation and the different ways of expressing the parameters of depth and the descendants' subgraph. Using MeSH as an input ontology, the accuracy of our proposal is evaluated and compared against other IC-based measures according to several widely-used benchmarks of biomedical terms. The correlation between the results obtained for the evaluated measure using the proposed approach and those from the ratings of human' experts shows that our proposal outperforms the previous measures.

Using Semantic Association to Extend and Infer Literature-Oriented Relativity Between Terms

Relative terms often appear together in the literature. Methods have been presented for weighting relativity of pairwise terms by their co-occurring literature and inferring new relationship. Terms in the literature are also in the directed acyclic graph of ontologies, such as Gene Ontology and Disease Ontology. Therefore, semantic association between terms may help for establishing relativities between terms in literature. However, current methods do not use these associations. In this paper, an adjusted R-scaled score (ARSS) based on information content (ARSSIC) method is introduced to infer new relationship between terms. First, set inclusion relationship between terms of ontology was exploited to extend relationships between these terms and literature. Next, the ARSS method was presented to measure relativity between terms across ontologies according to these extensional relationships. Then, the ARSSIC method using ratios of information shared of term's ancestors was designed to infer new relationship between terms across ontologies. The result of the experiment shows that ARSS identified more pairs of statistically significant terms based on corresponding gene sets than other methods. And the high average area under the receiver operating characteristic curve (0.9293) shows that ARSSIC achieved a high true positive rate and a low false positive rate. Data is available at http://mlg.hit.edu.cn/ARSSIC/.

A fuzzy-ontology-oriented case-based reasoning framework for semantic diabetes diagnosis

OBJECTIVE

Case-based reasoning (CBR) is a problem-solving paradigm that uses past knowledge to interpret or solve new problems. It is suitable for experience-based and theory-less problems. Building a semantically intelligent CBR that mimic the expert thinking can solve many problems especially medical ones.

METHODS

Knowledge-intensive CBR using formal ontologies is an evolvement of this paradigm. Ontologies can be used for case representation and storage, and it can be used as a background knowledge. Using standard medical ontologies, such as SNOMED CT, enhances the interoperability and integration with the health care systems. Moreover, utilizing vague or imprecise knowledge further improves the CBR semantic effectiveness. This paper proposes a fuzzy ontology-based CBR framework. It proposes a fuzzy case-base OWL2 ontology, and a fuzzy semantic retrieval algorithm that handles many feature types.

MATERIAL

This framework is implemented and tested on the diabetes diagnosis problem. The fuzzy ontology is populated with 60 real diabetic cases. The effectiveness of the proposed approach is illustrated with a set of experiments and case studies.

RESULTS

The resulting system can answer complex medical queries related to semantic understanding of medical concepts and handling of vague terms. The resulting fuzzy case-base ontology has 63 concepts, 54 (fuzzy) object properties, 138 (fuzzy) datatype properties, 105 fuzzy datatypes, and 2640 instances. The system achieves an accuracy of 97.67%. We compare our framework with existing CBR systems and a set of five machine-learning classifiers; our system outperforms all of these systems.

CONCLUSION

Building an integrated CBR system can improve its performance. Representing CBR knowledge using the fuzzy ontology and building a case retrieval algorithm that treats different features differently improves the accuracy of the resulting systems.

PubMed-supported clinical term weighting approach for improving inter-patient similarity measure in diagnosis prediction

BACKGROUND

Similarity-based retrieval of Electronic Health Records (EHRs) from large clinical information systems provides physicians the evidence support in making diagnoses or referring examinations for the suspected cases. Clinical Terms in EHRs represent high-level conceptual information and the similarity measure established based on these terms reflects the chance of inter-patient disease co-occurrence. The assumption that clinical terms are equally relevant to a disease is unrealistic, reducing the prediction accuracy. Here we propose a term weighting approach supported by PubMed search engine to address this issue.

METHODS

We collected and studied 112 abdominal computed tomography imaging examination reports from four hospitals in Hong Kong. Clinical terms, which are the image findings related to hepatocellular carcinoma (HCC), were extracted from the reports. Through two systematic PubMed search methods, the generic and specific term weightings were established by estimating the conditional probabilities of clinical terms given HCC. Each report was characterized by an ontological feature vector and there were totally 6216 vector pairs. We optimized the modified direction cosine (mDC) with respect to a regularization constant embedded into the feature vector. Equal, generic and specific term weighting approaches were applied to measure the similarity of each pair and their performances for predicting inter-patient co-occurrence of HCC diagnoses were compared by using Receiver Operating Characteristics (ROC) analysis.

RESULTS

The Areas under the curves (AUROCs) of similarity scores based on equal, generic and specific term weighting approaches were 0.735, 0.728 and 0.743 respectively (p < 0.01). In comparison with equal term weighting, the performance was significantly improved by specific term weighting (p < 0.01) but not by generic term weighting. The clinical terms "Dysplastic nodule", "nodule of liver" and "equal density (isodense) lesion" were found the top three image findings associated with HCC in PubMed.

CONCLUSIONS

Our findings suggest that the optimized similarity measure with specific term weighting to EHRs can improve significantly the accuracy for predicting the inter-patient co-occurrence of diagnosis when compared with equal and generic term weighting approaches.

Relational Fuzzy Self-Organizing Maps for Cluster Visualization and Summarization

The notion of Best-Matching Unit (BMU) in the proposed Fuzzy Relational Self-Organizing (FRSOM) algorithm is replaced by a membership function where every neuron has a certain degree of matching to an input object. The FRSOM is an extension of the relational self-organizing map. In the proposed FRSOM we incorporate a monotonically increasing fuzzifier and a monotonically decreasing neighborhood kernel. Initially, FRSOM assigns winning neurons. However, as time progresses adjacent neurons begin communicating and sharing information about the stimulus received. The amount of information being shared at a given time is governed by the fuzzifier and the number of neurons sharing information is controlled by the neighborhood kernel. Additionally, in this paper we show that FRSOM is the relational dual of Fuzzy Batch SOM (FBSOM) followed by experimental results comparing both FBSOM and FRSOM on synthetic datasets. Then we will demonstrate the visualization and summarization capabilities of FRSOM on two real relational datasets, Gene Ontology and a patient data consisting of Activity of Daily Living score trajectories.

Enabling online studies of conceptual relationships between medical terms: developing an efficient web platform

Background

The Unified Medical Language System (UMLS) contains many important ontologies in which terms are connected by semantic relations. For many studies on the relationships between biomedical concepts, the use of transitively associated information from ontologies and the UMLS has been shown to be effective. Although there are a few tools and methods available for extracting transitive relationships from the UMLS, they usually have major restrictions on the length of transitive relations or on the number of data sources.

Objective

Our goal was to design an efficient online platform that enables efficient studies on the conceptual relationships between any medical terms.

Methods

To overcome the restrictions of available methods and to facilitate studies on the conceptual relationships between medical terms, we developed a Web platform, onGrid, that supports efficient transitive queries and conceptual relationship studies using the UMLS. This framework uses the latest technique in converting natural language queries into UMLS concepts, performs efficient transitive queries, and visualizes the result paths. It also dynamically builds a relationship matrix for two sets of input biomedical terms. We are thus able to perform effective studies on conceptual relationships between medical terms based on their relationship matrix.

Results

The advantage of onGrid is that it can be applied to study any two sets of biomedical concept relations and the relations within one set of biomedical concepts. We use onGrid to study the disease-disease relationships in the Online Mendelian Inheritance in Man (OMIM). By crossvalidating our results with an external database, the Comparative Toxicogenomics Database (CTD), we demonstrated that onGrid is effective for the study of conceptual relationships between medical terms.

Conclusions

onGrid is an efficient tool for querying the UMLS for transitive relations, studying the relationship between medical terms, and generating hypotheses.

EHR Big Data Deep Phenotyping. Contribution of the IMIA Genomic Medicine Working Group

OBJECTIVES

Given the quickening speed of discovery of variant disease drivers from combined patient genotype and phenotype data, the objective is to provide methodology using big data technology to support the definition of deep phenotypes in medical records.

METHODS

As the vast stores of genomic information increase with next generation sequencing, the importance of deep phenotyping increases. The growth of genomic data and adoption of Electronic Health Records (EHR) in medicine provides a unique opportunity to integrate phenotype and genotype data into medical records. The method by which collections of clinical findings and other health related data are leveraged to form meaningful phenotypes is an active area of research. Longitudinal data stored in EHRs provide a wealth of information that can be used to construct phenotypes of patients. We focus on a practical problem around data integration for deep phenotype identification within EHR data. The use of big data approaches are described that enable scalable markup of EHR events that can be used for semantic and temporal similarity analysis to support the identification of phenotype and genotype relationships.

CONCLUSIONS

Stead and colleagues' 2005 concept of using light standards to increase the productivity of software systems by riding on the wave of hardware/processing power is described as a harbinger for designing future healthcare systems. The big data solution, using flexible markup, provides a route to improved utilization of processing power for organizing patient records in genotype and phenotype research.

Effectively processing medical term queries on the UMLS Metathesaurus by layered dynamic programming

Background

Mapping medical terms to standardized UMLS concepts is a basic step for leveraging biomedical texts in data management and analysis. However, available methods and tools have major limitations in handling queries over the UMLS Metathesaurus that contain inaccurate query terms, which frequently appear in real world applications.

Methods

To provide a practical solution for this task, we propose a layered dynamic programming mapping (LDPMap) approach, which can efficiently handle these queries. LDPMap uses indexing and two layers of dynamic programming techniques to efficiently map a biomedical term to a UMLS concept.

Results

Our empirical study shows that LDPMap achieves much faster query speeds than LCS. In comparison to the UMLS Metathesaurus Browser and MetaMap, LDPMap is much more effective in querying the UMLS Metathesaurus for inaccurately spelled medical terms, long medical terms, and medical terms with special characters.

Conclusions

These results demonstrate that LDPMap is an efficient and effective method for mapping medical terms to the UMLS Metathesaurus.

Comorbidity clusters in autism spectrum disorders: an electronic health record time-series analysis

OBJECTIVE

The distinct trajectories of patients with autism spectrum disorders (ASDs) have not been extensively studied, particularly regarding clinical manifestations beyond the neurobehavioral criteria from the Diagnostic and Statistical Manual of Mental Disorders. The objective of this study was to investigate the patterns of co-occurrence of medical comorbidities in ASDs.

METHODS

International Classification of Diseases, Ninth Revision codes from patients aged at least 15 years and a diagnosis of ASD were obtained from electronic medical records. These codes were aggregated by using phenotype-wide association studies categories and processed into 1350-dimensional vectors describing the counts of the most common categories in 6-month blocks between the ages of 0 to 15. Hierarchical clustering was used to identify subgroups with distinct courses.

RESULTS

Four subgroups were identified. The first was characterized by seizures (n = 120, subgroup prevalence 77.5%). The second (n = 197) was characterized by multisystem disorders including gastrointestinal disorders (prevalence 24.3%) and auditory disorders and infections (prevalence 87.8%), and the third was characterized by psychiatric disorders (n = 212, prevalence 33.0%). The last group (n = 4316) could not be further resolved. The prevalence of psychiatric disorders was uncorrelated with seizure activity (P = .17), but a significant correlation existed between gastrointestinal disorders and seizures (P < .001). The correlation results were replicated by using a second sample of 496 individuals from a different geographic region.

CONCLUSIONS

Three distinct patterns of medical trajectories were identified by unsupervised clustering of electronic health record diagnoses. These may point to distinct etiologies with different genetic and environmental contributions. Additional clinical and molecular characterizations will be required to further delineate these subgroups.

Challenges and facilitators to adoption of a point-of-care electronic health record in home care

Electronic health records (EHRs), intended to improve the clinical process, are understudied in home care. The researchers assessed clinician satisfaction, informed by workflow and patient outcomes, to identify EHR adoption challenges. The mixed methods study setting was a Philadelphia agency with 137 clinicians. Adoption challenges included: (a) hardware problems coupled with lack of field support; (b) inadequate training; and (c) mismatch of EHR usability/functionality and workflow resulting in decreased efficiency. Adoption facilitators were support for team communication and improved clinical data timeliness. Opportunities for improved adoption included sharing with front-line clinicians EHR data related to patient care and health outcomes.

Patient clustering with uncoded text in electronic medical records

We propose a mixture model for text data designed to capture underlying structure in the history of present illness section of electronic medical records data. Additionally, we propose a method to induce bias that leads to more homogeneous sets of diagnoses for patients in each cluster. We apply our model to a collection of electronic records from an emergency department and compare our results to three other relevant models in order to assess performance. Results using standard metrics demonstrate that patient clusters from our model are more homogeneous when compared to others, and qualitative analyses suggest that our approach leads to interpretable patient sub-populations when applied to real data. Finally, we demonstrate an example of our patient clustering model to identify adverse drug events.

Exploring the frontier of electronic health record surveillance: the case of postoperative complications

BACKGROUND

The aim of this study was to build electronic algorithms using a combination of structured data and natural language processing (NLP) of text notes for potential safety surveillance of 9 postoperative complications.

METHODS

Postoperative complications from 6 medical centers in the Southeastern United States were obtained from the Veterans Affairs Surgical Quality Improvement Program (VASQIP) registry. Development and test datasets were constructed using stratification by facility and date of procedure for patients with and without complications. Algorithms were developed from VASQIP outcome definitions using NLP-coded concepts, regular expressions, and structured data. The VASQIP nurse reviewer served as the reference standard for evaluating sensitivity and specificity. The algorithms were designed in the development and evaluated in the test dataset.

RESULTS

Sensitivity and specificity in the test set were 85% and 92% for acute renal failure, 80% and 93% for sepsis, 56% and 94% for deep vein thrombosis, 80% and 97% for pulmonary embolism, 88% and 89% for acute myocardial infarction, 88% and 92% for cardiac arrest, 80% and 90% for pneumonia, 95% and 80% for urinary tract infection, and 77% and 63% for wound infection, respectively. A third of the complications occurred outside of the hospital setting.

CONCLUSIONS

Computer algorithms on data extracted from the electronic health record produced respectable sensitivity and specificity across a large sample of patients seen in 6 different medical centers. This study demonstrates the utility of combining NLP with structured data for mining the information contained within the electronic health record.

An ontology-based similarity measure for biomedical data-application to radiology reports

BACKGROUND

Determining similarity between two individual concepts or two sets of concepts extracted from a free text document is important for various aspects of biomedicine, for instance, to find prior clinical reports for a patient that are relevant to the current clinical context. Using simple concept matching techniques, such as lexicon based comparisons, is typically not sufficient to determine an accurate measure of similarity.

METHODS

In this study, we tested an enhancement to the standard document vector cosine similarity model in which ontological parent-child (is-a) relationships are exploited. For a given concept, we define a semantic vector consisting of all parent concepts and their corresponding weights as determined by the shortest distance between the concept and parent after accounting for all possible paths. Similarity between the two concepts is then determined by taking the cosine angle between the two corresponding vectors. To test the improvement over the non-semantic document vector cosine similarity model, we measured the similarity between groups of reports arising from similar clinical contexts, including anatomy and imaging procedure. We further applied the similarity metrics within a k-nearest-neighbor (k-NN) algorithm to classify reports based on their anatomical and procedure based groups. 2150 production CT radiology reports (952 abdomen reports and 1128 neuro reports) were used in testing with SNOMED CT, restricted to Body structure, Clinical finding and Procedure branches, as the reference ontology.

RESULTS

The semantic algorithm preferentially increased the intra-class similarity over the inter-class similarity, with a 0.07 and 0.08 mean increase in the neuro-neuro and abdomen-abdomen pairs versus a 0.04 mean increase in the neuro-abdomen pairs. Using leave-one-out cross-validation in which each document was iteratively used as a test sample while excluding it from the training data, the k-NN based classification accuracy was shown in all cases to be consistently higher with the semantics based measure compared with the non-semantic case. Moreover, the accuracy remained steady even as k value was increased - for the two anatomy related classes accuracy for k=41 was 93.1% with semantics compared to 86.7% without semantics. Similarly, for the eight imaging procedures related classes, accuracy (for k=41) with semantics was 63.8% compared to 60.2% without semantics. At the same k, accuracy improved significantly to 82.8% and 77.4% respectively when procedures were logically grouped together into four classes (such as ignoring contrast information in the imaging procedure description). Similar results were seen at other k-values.

CONCLUSIONS

The addition of semantic context into the document vector space model improves the ability of the cosine similarity to differentiate between radiology reports of different anatomical and image procedure-based classes. This effect can be leveraged for document classification tasks, which suggests its potential applicability for biomedical information retrieval.

Next-generation phenotyping of electronic health records

The national adoption of electronic health records (EHR) promises to make an unprecedented amount of data available for clinical research, but the data are complex, inaccurate, and frequently missing, and the record reflects complex processes aside from the patient's physiological state. We believe that the path forward requires studying the EHR as an object of interest in itself, and that new models, learning from data, and collaboration will lead to efficient use of the valuable information currently locked in health records.

Mining electronic health records: towards better research applications and clinical care

Clinical data describing the phenotypes and treatment of patients represents an underused data source that has much greater research potential than is currently realized. Mining of electronic health records (EHRs) has the potential for establishing new patient-stratification principles and for revealing unknown disease correlations. Integrating EHR data with genetic data will also give a finer understanding of genotype-phenotype relationships. However, a broad range of ethical, legal and technical reasons currently hinder the systematic deposition of these data in EHRs and their mining. Here, we consider the potential for furthering medical research and clinical care using EHR data and the challenges that must be overcome before this is a reality.

k-Neighborhood decentralization: a comprehensive solution to index the UMLS for large scale knowledge discovery

The Unified Medical Language System (UMLS) is the largest thesaurus in the biomedical informatics domain. Previous works have shown that knowledge constructs comprised of transitively-associated UMLS concepts are effective for discovering potentially novel biomedical hypotheses. However, the extremely large size of the UMLS becomes a major challenge for these applications. To address this problem, we designed a k-neighborhood Decentralization Labeling Scheme (kDLS) for the UMLS, and the corresponding method to effectively evaluate the kDLS indexing results. kDLS provides a comprehensive solution for indexing the UMLS for very efficient large scale knowledge discovery. We demonstrated that it is highly effective to use kDLS paths to prioritize disease-gene relations across the whole genome, with extremely high fold-enrichment values. To our knowledge, this is the first indexing scheme capable of supporting efficient large scale knowledge discovery on the UMLS as a whole. Our expectation is that kDLS will become a vital engine for retrieving information and generating hypotheses from the UMLS for future medical informatics applications.

A Case-based Retrieval System using Natural Language Processing and Population-based Visualization

Electronic medical records capture large quantities of patient data generated as a result of routine care. Secondary use of this data for clinical research could provide new insights into the evolution of diseases and help assess the effectiveness of available interventions. Unfortunately, the unstructured nature of clinical data hinders a user's ability to understand this data: tools are needed to structure, model, and visualize the data to elucidate patterns in a patient population. We present a case-based retrieval framework that incorporates an extraction tool to identify concepts from clinical reports, a disease model to capture necessary context for interpreting extracted concepts, and a model-driven visualization to facilitate querying and interpretation of the results. We describe how the model is used to group, filter, and retrieve similar cases. We present an application of the framework that aids users in exploring a population of intracranial aneurysm patients.

Towards a framework for developing semantic relatedness reference standards

Our objective is to develop a framework for creating reference standards for functional testing of computerized measures of semantic relatedness. Currently, research on computerized approaches to semantic relatedness between biomedical concepts relies on reference standards created for specific purposes using a variety of methods for their analysis. In most cases, these reference standards are not publicly available and the published information provided in manuscripts that evaluate computerized semantic relatedness measurement approaches is not sufficient to reproduce the results. Our proposed framework is based on the experiences of medical informatics and computational linguistics communities and addresses practical and theoretical issues with creating reference standards for semantic relatedness. We demonstrate the use of the framework on a pilot set of 101 medical term pairs rated for semantic relatedness by 13 medical coding experts. While the reliability of this particular reference standard is in the "moderate" range; we show that using clustering and factor analyses offers a data-driven approach to finding systematic differences among raters and identifying groups of potential outliers. We test two ontology-based measures of relatedness and provide both the reference standard containing individual ratings and the R program used to analyze the ratings as open-source. Currently, these resources are intended to be used to reproduce and compare results of studies involving computerized measures of semantic relatedness. Our framework may be extended to the development of reference standards in other research areas in medical informatics including automatic classification, information retrieval from medical records and vocabulary/ontology development.

Gene prioritization and clustering by multi-view text mining

BACKGROUND

Text mining has become a useful tool for biologists trying to understand the genetics of diseases. In particular, it can help identify the most interesting candidate genes for a disease for further experimental analysis. Many text mining approaches have been introduced, but the effect of disease-gene identification varies in different text mining models. Thus, the idea of incorporating more text mining models may be beneficial to obtain more refined and accurate knowledge. However, how to effectively combine these models still remains a challenging question in machine learning. In particular, it is a non-trivial issue to guarantee that the integrated model performs better than the best individual model.

RESULTS

We present a multi-view approach to retrieve biomedical knowledge using different controlled vocabularies. These controlled vocabularies are selected on the basis of nine well-known bio-ontologies and are applied to index the vast amounts of gene-based free-text information available in the MEDLINE repository. The text mining result specified by a vocabulary is considered as a view and the obtained multiple views are integrated by multi-source learning algorithms. We investigate the effect of integration in two fundamental computational disease gene identification tasks: gene prioritization and gene clustering. The performance of the proposed approach is systematically evaluated and compared on real benchmark data sets. In both tasks, the multi-view approach demonstrates significantly better performance than other comparing methods.

CONCLUSIONS

In practical research, the relevance of specific vocabulary pertaining to the task is usually unknown. In such case, multi-view text mining is a superior and promising strategy for text-based disease gene identification.

Large datasets in biomedicine: a discussion of salient analytic issues

Advances in high-throughput and mass-storage technologies have led to an information explosion in both biology and medicine, presenting novel challenges for analysis and modeling. With regards to multivariate analysis techniques such as clustering, classification, and regression, large datasets present unique and often misunderstood challenges. The authors' goal is to provide a discussion of the salient problems encountered in the analysis of large datasets as they relate to modeling and inference to inform a principled and generalizable analysis and highlight the interdisciplinary nature of these challenges. The authors present a detailed study of germane issues including high dimensionality, multiple testing, scientific significance, dependence, information measurement, and information management with a focus on appropriate methodologies available to address these concerns. A firm understanding of the challenges and statistical technology involved ultimately contributes to better science. The authors further suggest that the community consider facilitating discussion through interdisciplinary panels, invited papers and curriculum enhancement to establish guidelines for analysis and reporting.

Implementation of an onto-wiki toolkit using web services to improve the efficiency and effectiveness of medical ontology co-authoring and analysis

The ICD11 draft was launched by the WHO in order to define ICD ontology by selected experts using a wiki-like structured joint-authoring tool. The challenge of this expert-/community-based ontology co-authoring is how to manage and process the ontology objects in the wiki page. The wiki-tools in the market require lots of time and human effort to organise, process and extract the ontology content from the wiki page for review and analysis. Therefore, this article is to investigate how to apply semantic web technology to improve the efficiency and effectiveness of ontology co-authoring and analysis. An onto-wiki toolkit that provides a set of web services is proposed for ontology creators to create, co-edit, organise, map and relate the wiki-like structured ontology objects on a wiki page for review and analysis. By using the onto-wiki toolkits, the pace of terminology standardisation, e-patient records integration, exchange and sharing can be improved.

Use abstracted patient-specific features to assist an information-theoretic measurement to assess similarity between medical cases

Inter-case similarity metrics can potentially help find similar cases from a case base for evidence-based practice. While several methods to measure similarity between cases have been proposed, developing an effective means for measuring patient case similarity remains a challenging problem. We were interested in examining how abstracting could potentially assist computing case similarity. In this study, abstracted patient-specific features from medical records were used to improve an existing information-theoretic measurement. The developed metric, using a combination of abstracted disease, finding, procedure and medication features, achieved a correlation between 0.6012 and 0.6940 to experts.