Discovering disease associations by integrating electronic clinical data and medical literature

Enhanced disease-disease association with information enriched disease representation

OBJECTIVE

Quantification of disease-disease association (DDA) enables the understanding of disease relationships for discovering disease progression and finding comorbidity. For effective DDA strength calculation, there is a need to address the main challenge of integration of various biomedical aspects of DDA is to obtain an information rich disease representation.

MATERIALS AND METHODS

An enhanced and integrated DDA framework is developed that integrates enriched literature-based with concept-based DDA representation. The literature component of the proposed framework uses PubMed abstracts and consists of improved neural network model that classifies DDAs for an enhanced literature-based DDA representation. Similarly, an ontology-based joint multi-source association embedding model is proposed in the ontology component using Disease Ontology (DO), UMLS, claims insurance, clinical notes etc. Results and Discussion: The obtained information rich disease representation is evaluated on different aspects of DDA datasets such as Gene, Variant, Gene Ontology (GO) and a human rated benchmark dataset. The DDA scores calculated using the proposed method achieved a high correlation mainly in gene-based dataset. The quantified scores also shown better correlation of 0.821, when evaluated on human rated 213 disease pairs. In addition, the generated disease representation is proved to have substantial effect on correlation of DDA scores for different categories of disease pairs.

CONCLUSION

The enhanced context and semantic DDA framework provides an enriched disease representation, resulting in high correlated results with different DDA datasets. We have also presented the biological interpretation of disease pairs. The developed framework can also be used for deriving the strength of other biomedical associations.

Kawasaki disease in childhood and psychiatric disorders: A population-based case-control prospective study in Taiwan

BACKGROUND

Kawasaki disease (KD) is a common childhood acute inflammatory disease and potentially triggers a chronic inflammation. Although some researches have investigated neurodevelopmental consequences following KD, the findings have been inconsistent. This is the first population-based study targeted on KD and common psychiatric disorders.

OBJECTIVES

We aimed to investigate the association between KD and psychiatric disorders and hypothesized that standard anti-inflammatory treatment by intravenous immunoglobulin (IVIG) may protect against development of psychiatric disorders.

METHOD

We retrieved data from Taiwan's National Health Insurance Research database (NHIRD). Patients (n = 282,513) with psychiatric disorders (the case group) during 1997-2013 were included, and the control group was matched with age, sex, income and urbanization (1:1). We calculated the prevalence of KD in both groups and estimated odd ratios (ORs) and 95% confidence intervals (CIs) in the subgroup analyses for KD in conditions of age, severity, and common psychiatric comorbidity.

RESULTS

Numbers of patients with KD were 460 in the cases and 380 in the controls (p = .006), and the crude OR of KD was 1.21 times greater (95% CI = 1.06-1.39, p = .006) in the case than the control groups. KD patients without IVIG treatment (n = 126) were higher in the cases than those in the controls (n = 54), with the OR of 2.33 (95% CI = 1.70-3.21, p < .0001). Subgroup analyses showed that KD survivors were at significant risk for autism spectrum disorders (ASD) (OR = 2.15, 95% CI = 1.27-3.65; p = .005) and attention deficit and hyperactivity disorders (ADHD) (OR = 1.19, 95% CI = 1.02-1.39; p = 0.03), and a trend of increased risk for anxiety disorders (OR = 1.36, 95%CI = 0.99-1.86; p = 0.05).

CONCLUSIONS

Patients with KD were more likely to have comorbid psychiatric disorders, including ASD and ADHD. Moreover, anti-inflammatory treatment with IVIG may have potential prophylactic effects against the development of psychiatric disorders.

Gender-sensitive word embeddings for healthcare

OBJECTIVE

To analyze gender bias in clinical trials, to design an algorithm that mitigates the effects of biases of gender representation on natural-language (NLP) systems trained on text drawn from clinical trials, and to evaluate its performance.

MATERIALS AND METHODS

We analyze gender bias in clinical trials described by 16 772 PubMed abstracts (2008-2018). We present a method to augment word embeddings, the core building block of NLP-centric representations, by weighting abstracts by the number of women participants in the trial. We evaluate the resulting gender-sensitive embeddings performance on several clinical prediction tasks: comorbidity classification, hospital length of stay prediction, and intensive care unit (ICU) readmission prediction.

RESULTS

For female patients, the gender-sensitive model area under the receiver-operator characteristic (AUROC) is 0.86 versus the baseline of 0.81 for comorbidity classification, mean absolute error 4.59 versus the baseline of 4.66 for length of stay prediction, and AUROC 0.69 versus 0.67 for ICU readmission. All results are statistically significant.

DISCUSSION

Women have been underrepresented in clinical trials. Thus, using the broad clinical trials literature as training data for statistical language models could result in biased models, with deficits in knowledge about women. The method presented enables gender-sensitive use of publications as training data for word embeddings. In experiments, the gender-sensitive embeddings show better performance than baseline embeddings for the clinical tasks studied. The results highlight opportunities for recognizing and addressing gender and other representational biases in the clinical trials literature.

CONCLUSION

Addressing representational biases in data for training NLP embeddings can lead to better results on downstream tasks for underrepresented populations.

Long-term hearing and neurodevelopmental outcomes following Kawasaki disease: A population-based cohort study

BACKGROUND

Kawasaki disease (KD) incidence is increasing in Ontario. Cardiovascular sequelae following KD are well-described. However, there are limited data on non-cardiovascular outcomes.

OBJECTIVES

To determine the risk of hearing loss, anxiety, developmental disorders, intellectual disabilities and attention-deficit/hyperactivity disorder (ADHD) among KD survivors vs. non-exposed children.

METHODS

We included all Ontario children (≤18 yr) surviving hospitalization with a KD diagnosis between 1995 and 2018, using population-based health administrative databases. We excluded children with prior KD diagnoses and non-residents. KD cases were matched with 100 non-exposed children by age, sex and year. Follow-up continued until death or March 2019. We calculated the prevalence, incidence and adjusted hazard ratios (aHR [95%CI]) of outcomes between 0-1 yr, 1-5 yr, 5-10 yr and >10 yr follow-up.

RESULTS

Among 4597 KD survivors, 364 (7.9%) were diagnosed with hearing loss, 1213 (26.4%) anxiety disorders, 398 (8.7%) developmental disorders, 51 (1.1%) intellectual disability and 21 (0.5%) ADHD, during median 11 year follow-up. Compared to 459,700 non-exposed children, KD survivors were not at increased risk of hearing loss after adjustment for potential confounders. KD survivors were at increased risk of anxiety disorders between 0-1 yr (aHR 1.75 [1.46-2.10]), 1-5 yr (aHR 1.13 [1.01-1.28]), 5-10 yr (aHR 1.14 [1.03-1.28]) and >10 yr (aHR 1.11 [1.02-1.22]); developmental disorders between 0-1 yr (aHR 1.49 [1.28-1.74]) and 1-5 yr (aHR 1.19 [1.02-1.40]); intellectual disabilities >10 yr (aHR 2.36 [1.36-4.10]); and ADHD >10 yr (aHR 2.01 [1.14-3.57]).

CONCLUSIONS

KD survivors are at increased risk of being diagnosed with anxiety disorders sooner, being diagnosed with developmental disorders between 0 and 5 yr and being diagnosed with intellectual disabilities or ADHD >10 yr after KD diagnosis. This may justify enhanced developmental and audiological surveillance of KD survivors.

Drug-drug similarity measure and its applications

Drug similarities play an important role in modern biology and medicine, as they help scientists gain deep insights into drugs' therapeutic mechanisms and conduct wet labs that may significantly improve the efficiency of drug research and development. Nowadays, a number of drug-related databases have been constructed, with which many methods have been developed for computing similarities between drugs for studying associations between drugs, human diseases, proteins (drug targets) and more. In this review, firstly, we briefly introduce the publicly available drug-related databases. Secondly, based on different drug features, interaction relationships and multimodal data, we summarize similarity calculation methods in details. Then, we discuss the applications of drug similarities in various biological and medical areas. Finally, we evaluate drug similarity calculation methods with common evaluation metrics to illustrate the important roles of drug similarity measures on different applications.

Comorbidity4j: a tool for interactive analysis of disease comorbidities over large patient datasets

SUMMARY

Pushed by the growing availability of Electronic Health Records for data mining, the identification of relevant patterns of co-occurring diseases over a population of individuals-referred to as comorbidity analysis-has become a common practice due to its great impact on life expectancy, quality of life and healthcare costs. In this scenario, the availability of scalable, easy-to-use software frameworks tailored to support the study of comorbidities over large datasets of patients is essential. We introduce Comorbidity4j, an open-source Java tool to perform systematic analyses of comorbidities by generating interactive Web visualizations to explore and refine results. Comorbidity4j processes user-provided clinical data by identifying significant disease co-occurrences and computing a comprehensive set of comorbidity indices. Patients can be stratified by sex, age and user-defined criteria. Comorbidity4j supports the analysis of the temporal directionality and the sex ratio of diseases. The incremental upload and validation of clinical input data and the customization of comorbidity analyses are performed by an interactive Web interface. With a Web browser, the results of such analyses can be filtered with respect to comorbidity indexes and disease names and explored by means of heat maps and network charts of disease associations. Comorbidity4j is optimized to efficiently process large datasets of clinical data. Besides a software tool for local execution, we provide Comorbidity4j as a Web service to enable users to perform online comorbidity analyses.

AVAILABILITY AND IMPLEMENTATION

Doc: http://comorbidity4j.readthedocs.io/; Source code: https://github.com/fra82/comorbidity4j, Web tool: http://comorbidity.eu/comorbidity4web/.

Repositioned Drugs for Inflammatory Diseases such as Sepsis, Asthma, and Atopic Dermatitis

The process of drug discovery and drug development consumes billions of dollars to bring a new drug to the market. Drug development is time consuming and sometimes, the failure rates are high. Thus, the pharmaceutical industry is looking for a better option for new drug discovery. Drug repositioning is a good alternative technology that has demonstrated many advantages over de novo drug development, the most important one being shorter drug development timelines. In the last two decades, drug repositioning has made tremendous impact on drug development technologies. In this review, we focus on the recent advances in drug repositioning technologies and discuss the repositioned drugs used for inflammatory diseases such as sepsis, asthma, and atopic dermatitis.

Discovering novel disease comorbidities using electronic medical records

Increasing reliance on electronic medical records at large medical centers provides unique opportunities to perform population level analyses exploring disease progression and etiology. The massive accumulation of diagnostic, procedure, and laboratory codes in one place has enabled the exploration of co-occurring conditions, their risk factors, and potential prognostic factors. While most of the readily identifiable associations in medical records are (now) well known to the scientific community, there is no doubt many more relationships are still to be uncovered in EMR data. In this paper, we introduce a novel finding index to help with that task. This new index uses data mined from real-time PubMed abstracts to indicate the extent to which empirically discovered associations are already known (i.e., present in the scientific literature). Our methods leverage second-generation p-values, which better identify associations that are truly clinically meaningful. We illustrate our new method with three examples: Autism Spectrum Disorder, Alzheimer’s Disease, and Optic Neuritis. Our results demonstrate wide utility for identifying new associations in EMR data that have the highest priority among the complex web of correlations and causalities. Data scientists and clinicians can work together more effectively to discover novel associations that are both empirically reliable and clinically understudied.

comoRbidity: an R package for the systematic analysis of disease comorbidities

Motivation

The study of comorbidities is a major priority due to their impact on life expectancy, quality of life and healthcare cost. The availability of electronic health records (EHRs) for data mining offers the opportunity to discover disease associations and comorbidity patterns from the clinical history of patients gathered during routine medical care. This opens the need for analytical tools for detection of disease comorbidities, including the investigation of their underlying genetic basis.

Results

We present comoRbidity, an R package aimed at providing a systematic and comprehensive analysis of disease comorbidities from both the clinical and molecular perspectives. comoRbidity leverages from (i) user provided clinical data from EHR databases (the clinical comorbidity analysis) and (ii) genotype-phenotype information of the diseases under study (the molecular comorbidity analysis) for a comprehensive analysis of disease comorbidities. The clinical comorbidity analysis enables identifying significant disease comorbidities from clinical data, including sex and age stratification and temporal directionality analyses, while the molecular comorbidity analysis supports the generation of hypothesis on the underlying mechanisms of the disease comorbidities by exploring shared genes among disorders. The open-source comoRbidity package is a software tool aimed at expediting the integrative analysis of disease comorbidities by incorporating several analytical and visualization functions.

Availability and implementation

https://bitbucket.org/ibi_group/comorbidity

Supplementary information

Supplementary data are available at Bioinformatics online.

An Innovative Framework for Bioimage Annotation and Studies

The collection and analysis of clinical data are needed to investigate diseases and to define medical protocols and treatments. Bioimages, medical annotations and patient history are clinical data acquired and studied to perform a correct diagnosis and to propose an appropriate therapy. Currently, hospital departments manage these data using legacy systems which do not often allow data integration among different departments or health structures. Thus, in many cases clinical information sharing and exchange are difficult to implement. This is also the case for biomedical images for which data integration or data overlapping is usually not available. Image annotations and comparison can be crucial for physicians in many case studies. In this paper, a general purpose framework for bioimage management and annotations is proposed. Moreover, a simple-to-use information system has been developed to integrate clinical and diagnosis codes. The framework allows physicians (1) to integrate DICOM images from different platforms and (2) to report notes and highlights directly on images, thus offering, among the others, to query and compare similar clinical cases. This contribution is the result of a framework aimed to support oncologists in managing DICOM images and clinical data from different departments. Data integration is performed using a here-proposed XML-based module also utilized to trace temporal changes in image annotations.

Big data from electronic health records for early and late translational cardiovascular research: challenges and potential

Aims

Cohorts of millions of people's health records, whole genome sequencing, imaging, sensor, societal and publicly available data present a rapidly expanding digital trace of health. We aimed to critically review, for the first time, the challenges and potential of big data across early and late stages of translational cardiovascular disease research.

Methods and results

We sought exemplars based on literature reviews and expertise across the BigData@Heart Consortium. We identified formidable challenges including: data quality, knowing what data exist, the legal and ethical framework for their use, data sharing, building and maintaining public trust, developing standards for defining disease, developing tools for scalable, replicable science and equipping the clinical and scientific work force with new inter-disciplinary skills. Opportunities claimed for big health record data include: richer profiles of health and disease from birth to death and from the molecular to the societal scale; accelerated understanding of disease causation and progression, discovery of new mechanisms and treatment-relevant disease sub-phenotypes, understanding health and diseases in whole populations and whole health systems and returning actionable feedback loops to improve (and potentially disrupt) existing models of research and care, with greater efficiency. In early translational research we identified exemplars including: discovery of fundamental biological processes e.g. linking exome sequences to lifelong electronic health records (EHR) (e.g. human knockout experiments); drug development: genomic approaches to drug target validation; precision medicine: e.g. DNA integrated into hospital EHR for pre-emptive pharmacogenomics. In late translational research we identified exemplars including: learning health systems with outcome trials integrated into clinical care; citizen driven health with 24/7 multi-parameter patient monitoring to improve outcomes and population-based linkages of multiple EHR sources for higher resolution clinical epidemiology and public health.

Conclusion

High volumes of inherently diverse ('big') EHR data are beginning to disrupt the nature of cardiovascular research and care. Such big data have the potential to improve our understanding of disease causation and classification relevant for early translation and to contribute actionable analytics to improve health and healthcare.

Applications of network analysis to routinely collected health care data: a systematic review

Objective

To survey network analyses of datasets collected in the course of routine operations in health care settings and identify driving questions, methods, needs, and potential for future research.

Materials and Methods

A search strategy was designed to find studies that applied network analysis to routinely collected health care datasets and was adapted to 3 bibliographic databases. The results were grouped according to a thematic analysis of their settings, objectives, data, and methods. Each group received a methodological synthesis.

Results

The search found 189 distinct studies reported before August 2016. We manually partitioned the sample into 4 groups, which investigated institutional exchange, physician collaboration, clinical co-occurrence, and workplace interaction networks. Several robust and ongoing research programs were discerned within (and sometimes across) the groups. Little interaction was observed between these programs, despite conceptual and methodological similarities.

Discussion

We use the literature sample to inform a discussion of good practice at this methodological interface, including the concordance of motivations, study design, data, and tools and the validation and standardization of techniques. We then highlight instances of positive feedback between methodological development and knowledge domains and assess the overall cohesion of the sample.

Inferring new drug indications using the complementarity between clinical disease signatures and drug effects

BACKGROUND

Drug repositioning is the process of finding new indications for existing drugs. Its importance has been dramatically increasing recently due to the enormous increase in new drug discovery cost. However, most of the previous molecular-centered drug repositioning work is not able to reflect the end-point physiological activities of drugs because of the inherent complexity of human physiological systems.

METHODS

Here, we suggest a novel computational framework to make inferences for alternative indications of marketed drugs by using electronic clinical information which reflects the end-point physiological results of drug's effects on the biological activities of humans. In this work, we use the concept of complementarity between clinical disease signatures and clinical drug effects. With this framework, we establish disease-related clinical variable vectors (clinical disease signature vectors) and drug-related clinical variable vectors (clinical drug effect vectors) by applying two methodologies (i.e., statistical analysis and literature mining). Finally, we assign a repositioning possibility score to each disease-drug pair by the calculation of complementarity (anti-correlation) and association between clinical states ("up" or "down") of disease signatures and clinical effects ("up", "down" or "association") of drugs. A total of 717 clinical variables in the electronic clinical dataset (NHANES), are considered in this study.

RESULTS

The statistical significance of our prediction results is supported through two benchmark datasets (Comparative Toxicogenomics Database and Clinical Trials). We discovered not only lots of known relationships between diseases and drugs, but also many hidden disease-drug relationships. For example, glutathione and edetic-acid may be investigated as candidate drugs for asthma treatment. We examined prediction results by using statistical experiments (enrichment verification, hyper-geometric and permutation test P<0.009 in Comparative Toxicogenomics Database and Clinical Trials) and presented evidences for those with already published literature.

CONCLUSION

The results show that electronic clinical information is a feasible data resource and utilizing the complementarity (anti-correlated relationships) between clinical signatures of disease and clinical effects of drugs is a potentially predictive concept in drug repositioning research. It makes the proposed approach useful to identity novel relationships between diseases and drugs that have a high probability of being biologically valid.

Contribution of Electronic Medical Records to the Management of Rare Diseases

Purpose. Electronic health record systems provide great opportunity to study most diseases. Objective of this study was to determine whether electronic medical records (EMR) in ophthalmology contribute to management of rare eye diseases, isolated or in syndromes. Study was designed to identify and collect patients' data with ophthalmology-specific EMR. Methods. Ophthalmology-specific EMR software (Softalmo software Corilus) was used to acquire ophthalmological ocular consultation data from patients with five rare eye diseases. The rare eye diseases and data were selected and collected regarding expertise of eye center. Results. A total of 135,206 outpatient consultations were performed between 2011 and 2014 in our medical center specialized in rare eye diseases. The search software identified 29 congenital aniridia, 6 Axenfeld/Rieger syndrome, 11 BEPS, 3 Nanophthalmos, and 3 Rubinstein-Taybi syndrome. Discussion. EMR provides advantages for medical care. The use of ophthalmology-specific EMR is reliable and can contribute to a comprehensive ocular visual phenotype useful for clinical research. Conclusion. Routinely EMR acquired with specific software dedicated to ophthalmology provides sufficient detail for rare diseases. These software-collected data appear useful for creating patient cohorts and recording ocular examination, avoiding the time-consuming analysis of paper records and investigation, in a University Hospital linked to a National Reference Rare Center Disease.

Birth month affects lifetime disease risk: a phenome-wide method

OBJECTIVE

An individual's birth month has a significant impact on the diseases they develop during their lifetime. Previous studies reveal relationships between birth month and several diseases including atherothrombosis, asthma, attention deficit hyperactivity disorder, and myopia, leaving most diseases completely unexplored. This retrospective population study systematically explores the relationship between seasonal affects at birth and lifetime disease risk for 1688 conditions.

METHODS

We developed a hypothesis-free method that minimizes publication and disease selection biases by systematically investigating disease-birth month patterns across all conditions. Our dataset includes 1 749 400 individuals with records at New York-Presbyterian/Columbia University Medical Center born between 1900 and 2000 inclusive. We modeled associations between birth month and 1688 diseases using logistic regression. Significance was tested using a chi-squared test with multiplicity correction.

RESULTS

We found 55 diseases that were significantly dependent on birth month. Of these 19 were previously reported in the literature (P < .001), 20 were for conditions with close relationships to those reported, and 16 were previously unreported. We found distinct incidence patterns across disease categories.

CONCLUSIONS

Lifetime disease risk is affected by birth month. Seasonally dependent early developmental mechanisms may play a role in increasing lifetime risk of disease.

Development and validation of a classification approach for extracting severity automatically from electronic health records

Background

Electronic Health Records (EHRs) contain a wealth of information useful for studying clinical phenotype-genotype relationships. Severity is important for distinguishing among phenotypes; however other severity indices classify patient-level severity (e.g., mild vs. acute dermatitis) rather than phenotype-level severity (e.g., acne vs. myocardial infarction). Phenotype-level severity is independent of the individual patient’s state and is relative to other phenotypes. Further, phenotype-level severity does not change based on the individual patient. For example, acne is mild at the phenotype-level and relative to other phenotypes. Therefore, a given patient may have a severe form of acne (this is the patient-level severity), but this does not effect its overall designation as a mild phenotype at the phenotype-level.

Methods

We present a method for classifying severity at the phenotype-level that uses the Systemized Nomenclature of Medicine – Clinical Terms. Our method is called the Classification Approach for Extracting Severity Automatically from Electronic Health Records (CAESAR). CAESAR combines multiple severity measures – number of comorbidities, medications, procedures, cost, treatment time, and a proportional index term. CAESAR employs a random forest algorithm and these severity measures to discriminate between severe and mild phenotypes.

Results

Using a random forest algorithm and these severity measures as input, CAESAR differentiates between severe and mild phenotypes (sensitivity = 91.67, specificity = 77.78) when compared to a manually evaluated reference standard (k = 0.716).

Conclusions

CAESAR enables researchers to measure phenotype severity from EHRs to identify phenotypes that are important for comparative effectiveness research.

Network Analysis of Comorbidities: Case Study of HIV/AIDS in Taiwan

Comorbidities are the presence of one or more additional disorders or diseases co-occurring with a primary disease or disorder. The purpose of this study is to identify diseases that co-occur with HIV/AIDS and analyze the gender differences. Data was collected from 536 HIV/AIDS admission medical records out of 1,377,469 admission medical records from 1997 to 2010 in Taiwan. In this study, the comorbidity relationships are presented in the phenotypic disease network (PDN), and φ-correlation is used to measure the distance between two diseases on the network. The results show that there is a high correlation in the following pairs/triad of diseases: human immunodeficiency virus infection with specified conditions (042) and pneumocystosis pneumonia (1363), human immunodeficiency virus infection with specified malignant neoplasms (0422) and kaposi’s sarcoma of other specified sites (1768), human immunodeficiency virus acquired immunodeficiency syndrome, and unspecified (0429) and progressive multifocal leukoencephalopathy (0463), and lastly, human immunodeficiency virus infection with specified infections (0420), meningoencephalitis due to toxoplasmosis (1300), and human immunodeficiency virus infection specified infections causing other specified infections (0421).

Similarity-based modeling applied to signal detection in pharmacovigilance

One of the main objectives in pharmacovigilance is the detection of adverse drug events (ADEs) through mining of healthcare databases, such as electronic health records or administrative claims data. Although different approaches have been shown to be of great value, research is still focusing on the enhancement of signal detection to gain efficiency in further assessment and follow-up. We applied similarity-based modeling techniques, using 2D and 3D molecular structure, ADE, target, and ATC (anatomical therapeutic chemical) similarity measures, to the candidate associations selected previously in a medication-wide association study for four ADE outcomes. Our results showed an improvement in the precision when we ranked the subset of ADE candidates using similarity scorings. This method is simple, useful to strengthen or prioritize signals generated from healthcare databases, and facilitates ADE detection through the identification of the most similar drugs for which ADE information is available.

Building the graph of medicine from millions of clinical narratives

Electronic health records (EHR) represent a rich and relatively untapped resource for characterizing the true nature of clinical practice and for quantifying the degree of inter-relatedness of medical entities such as drugs, diseases, procedures and devices. We provide a unique set of co-occurrence matrices, quantifying the pairwise mentions of 3 million terms mapped onto 1 million clinical concepts, calculated from the raw text of 20 million clinical notes spanning 19 years of data. Co-frequencies were computed by means of a parallelized annotation, hashing, and counting pipeline that was applied over clinical notes from Stanford Hospitals and Clinics. The co-occurrence matrix quantifies the relatedness among medical concepts which can serve as the basis for many statistical tests, and can be used to directly compute Bayesian conditional probabilities, association rules, as well as a range of test statistics such as relative risks and odds ratios. This dataset can be leveraged to quantitatively assess comorbidity, drug-drug, and drug-disease patterns for a range of clinical, epidemiological, and financial applications.

Applying MetaMap to Medline for identifying novel associations in a large clinical dataset: a feasibility analysis

OBJECTIVE

We describe experiments designed to determine the feasibility of distinguishing known from novel associations based on a clinical dataset comprised of International Classification of Disease, V.9 (ICD-9) codes from 1.6 million patients by comparing them to associations of ICD-9 codes derived from 20.5 million Medline citations processed using MetaMap. Associations appearing only in the clinical dataset, but not in Medline citations, are potentially novel.

METHODS

Pairwise associations of ICD-9 codes were independently identified in both the clinical and Medline datasets, which were then compared to quantify their degree of overlap. We also performed a manual review of a subset of the associations to validate how well MetaMap performed in identifying diagnoses mentioned in Medline citations that formed the basis of the Medline associations.

RESULTS

The overlap of associations based on ICD-9 codes in the clinical and Medline datasets was low: only 6.6% of the 3.1 million associations found in the clinical dataset were also present in the Medline dataset. Further, a manual review of a subset of the associations that appeared in both datasets revealed that co-occurring diagnoses from Medline citations do not always represent clinically meaningful associations.

DISCUSSION

Identifying novel associations derived from large clinical datasets remains challenging. Medline as a sole data source for existing knowledge may not be adequate to filter out widely known associations.

CONCLUSIONS

In this study, novel associations were not readily identified. Further improvements in accuracy and relevance for tools such as MetaMap are needed to realize their expected utility.

Data-driven discovery of seasonally linked diseases from an Electronic Health Records system

BACKGROUND

Patterns of disease incidence can identify new risk factors for the disease or provide insight into the etiology. For example, allergies and infectious diseases have been shown to follow periodic temporal patterns due to seasonal changes in environmental or infectious agents. Previous work searching for seasonal or other temporal patterns in disease diagnosis rates has been limited both in the scope of the diseases examined and in the ability to distinguish unexpected seasonal patterns. Electronic Health Records (EHR) compile extensive longitudinal clinical information, constituting a unique source for discovery of trends in occurrence of disease. However, the data suffer from inherent biases that preclude an identification of temporal trends.

METHODS

Motivated by observation of the biases in this data source, we developed a method (Lomb-Scargle periodograms in detrended data, LSP-detrend) to find periodic patterns by adjusting the temporal information for broad trends in incidence, as well as seasonal changes in total hospitalizations. LSP-detrend can sensitively uncover periodic temporal patterns in the corrected data and identify the significance of the trend. We apply LSP-detrend to a compilation of records from 1.5 million patients encoded by ICD-9-CM (International Classification of Diseases, Ninth Revision, Clinical Modification), including 2,805 disorders with more than 500 occurrences across a 12 year period, recorded from 1.5 million patients.

RESULTS AND CONCLUSIONS

Although EHR data, and ICD-9 coded records in particular, were not created with the intention of aggregated use for research, these data can in fact be mined for periodic patterns in incidence of disease, if confounders are properly removed. Of all diagnoses, around 10% are identified as seasonal by LSP-detrend, including many known phenomena. We robustly reproduce previous findings, even for relatively rare diseases. For instance, Kawasaki disease, a rare childhood disease that has been associated with weather patterns, is detected as strongly linked with winter months. Among the novel results, we find a bi-annual increase in exacerbations of myasthenia gravis, a potentially life threatening complication of an autoimmune disease. We dissect the causes of this seasonal incidence and propose that factors predisposing patients to this event vary through the year.

Association between Kawasaki disease and autism: a population-based study in Taiwan

Objective: The association between Kawasaki disease and autism has rarely been studied in Asian populations. By using a nationwide Taiwanese population-based claims database, we tested the hypothesis that Kawasaki disease may increase the risk of autism in Taiwan. Materials and Methods: Our study cohort consisted of patients who had received the diagnosis of Kawasaki disease (ICD-9-CM: 446.1) between 1997 and 2005 (N = 563). For a comparison cohort, five age- and gender-matched control patients for every patient in the study cohort were selected using random sampling (N = 2,815). All subjects were tracked for 5 years from the date of cohort entry to identify whether they had developed autism (ICD-9-CM code 299.0) or not. Cox proportional hazard regressions were then performed to evaluate 5-year autism-free survival rates. Results: The main finding of this study was that patients with Kawasaki disease seem to not be at increased risk of developing autism. Of the total patients, four patients developed autism during the 5-year follow-up period, among whom two were Kawasaki disease patients and two were in the comparison cohort. Further, the adjusted hazard ratios (AHR) (AHR: 4.81; 95% confidence interval: 0.68–34.35; P = 0.117) did not show any statistical significance between the Kawasaki disease group and the control group during the 5-year follow-up. Conclusion: Our study indicated that patients with Kawasaki disease are not at increased risk of autism.

A pipeline to extract drug-adverse event pairs from multiple data sources

BACKGROUND

Pharmacovigilance aims to uncover and understand harmful side-effects of drugs, termed adverse events (AEs). Although the current process of pharmacovigilance is very systematic, the increasing amount of information available in specialized health-related websites as well as the exponential growth in medical literature presents a unique opportunity to supplement traditional adverse event gathering mechanisms with new-age ones.

METHOD

We present a semi-automated pipeline to extract associations between drugs and side effects from traditional structured adverse event databases, enhanced by potential drug-adverse event pairs mined from user-comments from health-related websites and MEDLINE abstracts. The pipeline was tested using a set of 12 drugs representative of two previous studies of adverse event extraction from health-related websites and MEDLINE abstracts.

RESULTS

Testing the pipeline shows that mining non-traditional sources helps substantiate the adverse event databases. The non-traditional sources not only contain the known AEs, but also suggest some unreported AEs for drugs which can then be analyzed further.

CONCLUSION

A semi-automated pipeline to extract the AE pairs from adverse event databases as well as potential AE pairs from non-traditional sources such as text from MEDLINE abstracts and user-comments from health-related websites is presented.

Mining the electronic health record for disease knowledge

The growing amount and availability of electronic health record (EHR) data present enhanced opportunities for discovering new knowledge about diseases. In the past decade, there has been an increasing number of data and text mining studies focused on the identification of disease associations (e.g., disease-disease, disease-drug, and disease-gene) in structured and unstructured EHR data. This chapter presents a knowledge discovery framework for mining the EHR for disease knowledge and describes each step for data selection, preprocessing, transformation, data mining, and interpretation/validation. Topics including natural language processing, standards, and data privacy and security are also discussed in the context of this framework.

SN algorithm: analysis of temporal clinical data for mining periodic patterns and impending augury

BACKGROUND

EHR (Electronic Health Record) system has led to development of specialized form of clinical databases which enable storage of information in temporal prospective. It has been a big challenge for mining this form of clinical data considering varied temporal points. This study proposes a conjoined solution to analyze the clinical parameters akin to a disease. We have used "association rule mining algorithm" to discover association rules among clinical parameters that can be augmented with the disease. Furthermore, we have proposed a new algorithm, SN algorithm, to map clinical parameters along with a disease state at various temporal points.

RESULT

SN algorithm is based on Jacobian approach, which augurs the state of a disease 'Sn' at a given temporal point 'Tn' by mapping the derivatives with the temporal point 'T0', whose state of disease 'S0' is known. The predictive ability of the proposed algorithm is evaluated in a temporal clinical data set of brain tumor patients. We have obtained a very high prediction accuracy of ~97% for a brain tumor state 'Sn' for any temporal point 'Tn'.

CONCLUSION

The results indicate that the methodology followed may be of good value to the diagnostic procedure, especially for analyzing temporal form of clinical data.

Describing the relationship between cat bites and human depression using data from an electronic health record

Data mining approaches have been increasingly applied to the electronic health record and have led to the discovery of numerous clinical associations. Recent data mining studies have suggested a potential association between cat bites and human depression. To explore this possible association in more detail we first used administrative diagnosis codes to identify patients with either depression or bites, drawn from a population of 1.3 million patients. We then conducted a manual chart review in the electronic health record of all patients with a code for a bite to accurately determine which were from cats or dogs. Overall there were 750 patients with cat bites, 1,108 with dog bites, and approximately 117,000 patients with depression. Depression was found in 41.3% of patients with cat bites and 28.7% of those with dog bites. Furthermore, 85.5% of those with both cat bites and depression were women, compared to 64.5% of those with dog bites and depression. The probability of a woman being diagnosed with depression at some point in her life if she presented to our health system with a cat bite was 47.0%, compared to 24.2% of men presenting with a similar bite. The high proportion of depression in patients who had cat bites, especially among women, suggests that screening for depression could be appropriate in patients who present to a clinical provider with a cat bite. Additionally, while no causative link is known to explain this association, there is growing evidence to suggest that the relationship between cats and human mental illness, such as depression, warrants further investigation.

OPIC: Ontology-driven Patient Information Capturing system for epilepsy

The widespread use of paper or document-based forms for capturing patient information in various clinical settings, for example in epilepsy centers, is a critical barrier for large-scale, multi-center research studies that require interoperable, consistent, and error-free data collection. This challenge can be addressed by a web-accessible and flexible patient data capture system that is supported by a common terminological system to facilitate data re-usability, sharing, and integration. We present OPIC, an Ontology-driven Patient Information Capture (OPIC) system that uses a domain-specific epilepsy and seizure ontology (EpSO) to (1) support structured entry of multi-modal epilepsy data, (2) proactively ensure quality of data through use of ontology terms in drop-down menus, and (3) identify and index clinically relevant ontology terms in free-text fields to improve accuracy of subsequent analytical queries (e.g. cohort identification). EpSO, modeled using the Web Ontology Language (OWL), conforms to the recommendations of the International League Against Epilepsy (ILAE) classification and terminological commission. OPIC has been developed using agile software engineering methodology for rapid development cycles in close collaboration with domain expert and end users. We report the result from the initial deployment of OPIC at the University Hospitals Case Medical Center (UH CMC) epilepsy monitoring unit (EMU) as part of the NIH-funded project on Sudden Unexpected Death in Epilepsy (SUDEP). Preliminary user evaluation shows that OPIC has achieved its design objectives to be an intuitive patient information capturing system that also reduces the potential for data entry errors and variability in use of epilepsy terms.

Modeling temporal relationships in large scale clinical associations

OBJECTIVE

We describe an approach for modeling temporal relationships in a large scale association analysis of electronic health record data. The addition of temporal information can inform hypothesis generation and help to explain the relationships. We applied this approach on a dataset containing 41.2 million time-stamped International Classification of Diseases, Ninth Revision (ICD-9) codes from 1.6 million patients.

METHODS

We performed two independent analyses including a pairwise association analysis using a χ(2) test and a temporal analysis using a binomial test. Data were visualized using network diagrams and reviewed for clinical significance.

RESULTS

We found nearly 400 000 highly associated pairs of ICD-9 codes with varying numbers of strong temporal associations ranging from ≥1 day to ≥10 years apart. Most of the findings were not considered clinically novel, although some, such as an association between Helicobacter pylori infection and diabetes, have recently been reported in the literature. The temporal analysis in our large cohort, however, revealed that diabetes usually preceded the diagnoses of H pylori, raising questions about possible cause and effect.

DISCUSSION

Such analyses have significant limitations, some of which are due to known problems with ICD-9 codes and others to potentially incomplete data even at a health system level. Nevertheless, large scale association analyses with temporal modeling can help provide a mechanism for novel discovery in support of hypothesis generation.

CONCLUSIONS

Temporal relationships can provide an additional layer of meaning in identifying and interpreting clinical associations.

Enhancing adverse drug event detection in electronic health records using molecular structure similarity: application to pancreatitis

Background

Adverse drug events (ADEs) detection and assessment is at the center of pharmacovigilance. Data mining of systems, such as FDA’s Adverse Event Reporting System (AERS) and more recently, Electronic Health Records (EHRs), can aid in the automatic detection and analysis of ADEs. Although different data mining approaches have been shown to be valuable, it is still crucial to improve the quality of the generated signals.

Objective

To leverage structural similarity by developing molecular fingerprint-based models (MFBMs) to strengthen ADE signals generated from EHR data.

Methods

A reference standard of drugs known to be causally associated with the adverse event pancreatitis was used to create a MFBM. Electronic Health Records (EHRs) from the New York Presbyterian Hospital were mined to generate structured data. Disproportionality Analysis (DPA) was applied to the data, and 278 possible signals related to the ADE pancreatitis were detected. Candidate drugs associated with these signals were then assessed using the MFBM to find the most promising candidates based on structural similarity.

Results

The use of MFBM as a means to strengthen or prioritize signals generated from the EHR significantly improved the detection accuracy of ADEs related to pancreatitis. MFBM also highlights the etiology of the ADE by identifying structurally similar drugs, which could follow a similar mechanism of action.

Conclusion

The method proposed in this paper provides evidence of being a promising adjunct to existing automated ADE detection and analysis approaches.

Live sequence charts to model medical information

Background

Medical records accumulate data concerning patient health and the natural history of disease progression. However, methods to mine information systematically in a form other than an electronic health record are not yet available. The purpose of this study was to develop an object modeling technique as a first step towards a formal database of medical records.

Method

Live Sequence Charts (LSC) were used to formalize the narrative text obtained during a patient interview. LSCs utilize a visual scenario-based programming language to build object models. LSC extends the classical language of UML message sequence charts (MSC), predominantly through addition of modalities and providing executable semantics. Inter-object scenarios were defined to specify natural history event interactions and different scenarios in the narrative text.

Result

A simulated medical record was specified into LSC formalism by translating the text into an object model that comprised a set of entities and events. The entities described the participating components (i.e., doctor, patient and record) and the events described the interactions between elements. A conceptual model is presented to illustrate the approach. An object model was generated from data extracted from an actual new patient interview, where the individual was eventually diagnosed as suffering from Chronic Fatigue Syndrome (CFS). This yielded a preliminary formal designated vocabulary for CFS development that provided a basis for future formalism of these records.

Conclusions

Translation of medical records into object models created the basis for a formal database of the patient narrative that temporally depicts the events preceding disease, the diagnosis and treatment approach. The LSCs object model of the medical narrative provided an intuitive, visual representation of the natural history of the patient’s disease.

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.

Fractal-like distributions over the rational numbers in high-throughput biological and clinical data

Recent developments in extracting and processing biological and clinical data are allowing quantitative approaches to studying living systems. High-throughput sequencing (HTS), expression profiles, proteomics, and electronic health records (EHR) are some examples of such technologies. Extracting meaningful information from those technologies requires careful analysis of the large volumes of data they produce. In this note, we present a set of fractal-like distributions that commonly appear in the analysis of such data. The first set of examples are drawn from a HTS experiment. Here, the distributions appear as part of the evaluation of the error rate of the sequencing and the identification of tumorogenic genomic alterations. The other examples are obtained from risk factor evaluation and analysis of relative disease prevalence and co-mordbidity as these appear in EHR. The distributions are also relevant to identification of subclonal populations in tumors and the study of quasi-species and intrahost diversity of viral populations.