Person:
McCray, Alexa

Profile Picture

Email Address

AA Acceptance Date

Birth Date

Research Projects

Organizational Units

Job Title

Last Name

McCray

First Name

Alexa

Name

McCray, Alexa

Filters

2012 - 20174

Settings

Author's Publications: search.filters.isAuthorOfPublication.068bc676-099e-420d-aa68-d3660330037b

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Publication
    Research Strategies for Biomedical and Health Informatics: Some Thought-provoking and Critical Proposals to Encourage Scientific Debate on the Nature of Good Research in Medical Informatics
    (Schattauer, 2017) Haux, Reinhold; Kulikowski, Casimir A.; Bakken, Suzanne; de Lusignan, Simon; Kimura, Michio; Koch, Sabine; Mantas, John; Maojo, Victor; Marschollek, Michael; Martin-Sanchez, Fernando; Moen, Anne; Park, Hyeoun-Ae; Sarkar, Indra Neil; Leong, Tze Yun; McCray, Alexa
    Summary Background: Medical informatics, or biomedical and health informatics (BMHI), has become an established scientific discipline. In all such disciplines there is a certain inertia to persist in focusing on well-established research areas and to hold on to well-known research methodologies rather than adopting new ones, which may be more appropriate. Objectives: To search for answers to the following questions: What are research fields in informatics, which are not being currently adequately addressed, and which methodological approaches might be insufficiently used? Do we know about reasons? What could be consequences of change for research and for education? Methods: Outstanding informatics scientists were invited to three panel sessions on this topic in leading international conferences (MIE 2015, Medinfo 2015, HEC 2016) in order to get their answers to these questions. Results: A variety of themes emerged in the set of answers provided by the panellists. Some panellists took the theoretical foundations of the field for granted, while several questioned whether the field was actually grounded in a strong theoretical foundation. Panellists proposed a range of suggestions for new or improved approaches, methodologies, and techniques to enhance the BMHI research agenda. Conclusions: The field of BMHI is on the one hand maturing as an academic community and intellectual endeavour. On the other hand vendor-supplied solutions may be too readily and uncritically accepted in health care practice. There is a high chance that BMHI will continue to flourish as an important discipline; its innovative interventions might then reach the original objectives of advancing science and improving health care outcomes.
  • Thumbnail Image
    Publication
    Identifying Gender-Preferred Communication Styles within Online Cancer Communities: A Retrospective, Longitudinal Analysis
    (Public Library of Science, 2012) Durant, Kathleen T.; McCray, Alexa; Safran, Charles
    Background: The goal of this research is to determine if different gender-preferred social styles can be observed within the user interactions at an online cancer community. To achieve this goal, we identify and measure variables that pertain to each gender-specific social style. Methods and Findings: We perform social network and statistical analysis on the communication flow of 8,388 members at six different cancer forums over eight years. Kruskal-Wallis tests were conducted to measure the difference between the number of intimate (and highly intimate) dyads, relationship length, and number of communications. We determine that two patients are more likely to form an intimate bond on a gender-specific cancer forum (ovarian P = <0.0001, breast P = 0.0089, prostate P = 0.0021). Two female patients are more likely to form a highly intimate bond on a female-specific cancer forum (Ovarian P<0.0001, Breast P<0.01). Typically a male patient communicates with more members than a female patient (Ovarian forum P = 0.0406, Breast forum P = 0.0013). A relationship between two patients is longer on the gender-specific cancer forums than a connection between two members not identified as patients (ovarian forum P = 0.00406, breast forum P = 0.00013, prostate forum P = .0.0003). Conclusion: The high level of interconnectedness among the prostate patients supports the hypothesis that men prefer to socialize in large, interconnected, less-intimate groups. A female patient is more likely to form a highly intimate connection with another female patient; this finding is consistent with the hypothesis that woman prefer fewer, more intimate connections. The relationships of same-gender cancer patients last longer than other relationships; this finding demonstrates homophily within these online communities. Our findings regarding online communication preferences are in agreement with research findings from person-to-person communication preference studies. These findings should be considered when designing online communities as well as designing and evaluating psychosocial and educational interventions for cancer patients.
  • Thumbnail Image
    Publication
    Markov Chain Ontology Analysis (MCOA)
    (BioMed Central, 2012) Frost, Hildreth Robert; McCray, Alexa
    Background: Biomedical ontologies have become an increasingly critical lens through which researchers analyze the genomic, clinical and bibliographic data that fuels scientific research. Of particular relevance are methods, such as enrichment analysis, that quantify the importance of ontology classes relative to a collection of domain data. Current analytical techniques, however, remain limited in their ability to handle many important types of structural complexity encountered in real biological systems including class overlaps, continuously valued data, inter-instance relationships, non-hierarchical relationships between classes, semantic distance and sparse data. Results: In this paper, we describe a methodology called Markov Chain Ontology Analysis (MCOA) and illustrate its use through a MCOA-based enrichment analysis application based on a generative model of gene activation. MCOA models the classes in an ontology, the instances from an associated dataset and all directional inter-class, class-to-instance and inter-instance relationships as a single finite ergodic Markov chain. The adjusted transition probability matrix for this Markov chain enables the calculation of eigenvector values that quantify the importance of each ontology class relative to other classes and the associated data set members. On both controlled Gene Ontology (GO) data sets created with Escherichia coli, Drosophila melanogaster and Homo sapiens annotations and real gene expression data extracted from the Gene Expression Omnibus (GEO), the MCOA enrichment analysis approach provides the best performance of comparable state-of-the-art methods. Conclusion: A methodology based on Markov chain models and network analytic metrics can help detect the relevant signal within large, highly interdependent and noisy data sets and, for applications such as enrichment analysis, has been shown to generate superior performance on both real and simulated data relative to existing state-of-the-art approaches.
  • Thumbnail Image
    Publication
    Medical subdomain classification of clinical notes using a machine learning-based natural language processing approach
    (BioMed Central, 2017) Weng, Wei-Hung; Wagholikar, Kavishwar; McCray, Alexa; Szolovits, Peter; Chueh, Henry
    Background: The medical subdomain of a clinical note, such as cardiology or neurology, is useful content-derived metadata for developing machine learning downstream applications. To classify the medical subdomain of a note accurately, we have constructed a machine learning-based natural language processing (NLP) pipeline and developed medical subdomain classifiers based on the content of the note. Methods: We constructed the pipeline using the clinical NLP system, clinical Text Analysis and Knowledge Extraction System (cTAKES), the Unified Medical Language System (UMLS) Metathesaurus, Semantic Network, and learning algorithms to extract features from two datasets — clinical notes from Integrating Data for Analysis, Anonymization, and Sharing (iDASH) data repository (n = 431) and Massachusetts General Hospital (MGH) (n = 91,237), and built medical subdomain classifiers with different combinations of data representation methods and supervised learning algorithms. We evaluated the performance of classifiers and their portability across the two datasets. Results: The convolutional recurrent neural network with neural word embeddings trained-medical subdomain classifier yielded the best performance measurement on iDASH and MGH datasets with area under receiver operating characteristic curve (AUC) of 0.975 and 0.991, and F1 scores of 0.845 and 0.870, respectively. Considering better clinical interpretability, linear support vector machine-trained medical subdomain classifier using hybrid bag-of-words and clinically relevant UMLS concepts as the feature representation, with term frequency-inverse document frequency (tf-idf)-weighting, outperformed other shallow learning classifiers on iDASH and MGH datasets with AUC of 0.957 and 0.964, and F1 scores of 0.932 and 0.934 respectively. We trained classifiers on one dataset, applied to the other dataset and yielded the threshold of F1 score of 0.7 in classifiers for half of the medical subdomains we studied. Conclusion: Our study shows that a supervised learning-based NLP approach is useful to develop medical subdomain classifiers. The deep learning algorithm with distributed word representation yields better performance yet shallow learning algorithms with the word and concept representation achieves comparable performance with better clinical interpretability. Portable classifiers may also be used across datasets from different institutions. Electronic supplementary material The online version of this article (10.1186/s12911-017-0556-8) contains supplementary material, which is available to authorized users.