Browsing by Subject "public health reporting"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Evaluating Methods for Identifying Cancer in Free-Text Pathology Reports Using Various Machine Learning and Data Preprocessing Approaches
    (IOS, 2015) Kasthurirathne, Suranga Nath; Dixon, Brian E.; Grannis, Shaun J.; Department of BioHealth Informatics, School of Informatics and Computing
    Automated detection methods can address delays and incompleteness in cancer case reporting. Existing automated efforts are largely dependent on complex dictionaries and coded data. Using a gold standard of manually reviewed pathology reports, we evaluated the performance of alternative input formats and decision models on a convenience sample of free-text pathology reports. Results showed that the input format significantly impacted performance, and specific algorithms yielded better results for presicion, recall and accuracy. We conclude that our approach is sufficiently accurate for practical purposes and represents a generalized process.
  • Thumbnail Image
    Item
    Measuring the impact of a health information exchange intervention on provider-based notifiable disease reporting using mixed methods: a study protocol
    (2013-10) Dixon, Brian E.; Grannis, Shaun J; Revere, Debra
    Background Health information exchange (HIE) is the electronic sharing of data and information between clinical care and public health entities. Previous research has shown that using HIE to electronically report laboratory results to public health can improve surveillance practice, yet there has been little utilization of HIE for improving provider-based disease reporting. This article describes a study protocol that uses mixed methods to evaluate an intervention to electronically pre-populate provider-based notifiable disease case reporting forms with clinical, laboratory and patient data available through an operational HIE. The evaluation seeks to: (1) identify barriers and facilitators to implementation, adoption and utilization of the intervention; (2) measure impacts on workflow, provider awareness, and end-user satisfaction; and (3) describe the contextual factors that impact the effectiveness of the intervention within heterogeneous clinical settings and the HIE. Methods/Design The intervention will be implemented over a staggered schedule in one of the largest and oldest HIE infrastructures in the U.S., the Indiana Network for Patient Care. Evaluation will be conducted utilizing a concurrent design mixed methods framework in which qualitative methods are embedded within the quantitative methods. Quantitative data will include reporting rates, timeliness and burden and report completeness and accuracy, analyzed using interrupted time-series and other pre-post comparisons. Qualitative data regarding pre-post provider perceptions of report completeness, accuracy, and timeliness, reporting burden, data quality, benefits, utility, adoption, utilization and impact on reporting workflow will be collected using semi-structured interviews and open-ended survey items. Data will be triangulated to find convergence or agreement by cross-validating results to produce a contextualized portrayal of the facilitators and barriers to implementation and use of the intervention. Discussion By applying mixed research methods and measuring context, facilitators and barriers, and individual, organizational and data quality factors that may impact adoption and utilization of the intervention, we will document whether and how the intervention streamlines provider-based manual reporting workflows, lowers barriers to reporting, increases data completeness, improves reporting timeliness and captures a greater portion of communicable disease burden in the community.
  • Thumbnail Image
    Item
    Toward better public health reporting using existing off the shelf approaches: The value of medical dictionaries in automated cancer detection using plaintext medical data
    (Elsevier, 2017-05) Kasthurirathne, Suranga N.; Dixon, Brian E.; Gichoya, Judy; Xu, Huiping; Xia, Yuni; Mamlin, Burke; Grannis, Shaun J.; Department of Epidemiology, Richard M. Fairbanks School of Public Health
    Objectives Existing approaches to derive decision models from plaintext clinical data frequently depend on medical dictionaries as the sources of potential features. Prior research suggests that decision models developed using non-dictionary based feature sourcing approaches and “off the shelf” tools could predict cancer with performance metrics between 80% and 90%. We sought to compare non-dictionary based models to models built using features derived from medical dictionaries. Materials and methods We evaluated the detection of cancer cases from free text pathology reports using decision models built with combinations of dictionary or non-dictionary based feature sourcing approaches, 4 feature subset sizes, and 5 classification algorithms. Each decision model was evaluated using the following performance metrics: sensitivity, specificity, accuracy, positive predictive value, and area under the receiver operating characteristics (ROC) curve. Results Decision models parameterized using dictionary and non-dictionary feature sourcing approaches produced performance metrics between 70 and 90%. The source of features and feature subset size had no impact on the performance of a decision model. Conclusion Our study suggests there is little value in leveraging medical dictionaries for extracting features for decision model building. Decision models built using features extracted from the plaintext reports themselves achieve comparable results to those built using medical dictionaries. Overall, this suggests that existing “off the shelf” approaches can be leveraged to perform accurate cancer detection using less complex Named Entity Recognition (NER) based feature extraction, automated feature selection and modeling approaches.