AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
-
AMIA Annu Symp Proc · Jan 2015
Automated Grading of Gliomas using Deep Learning in Digital Pathology Images: A modular approach with ensemble of convolutional neural networks.
Brain glioma is the most common primary malignant brain tumors in adults with different pathologic subtypes: Lower Grade Glioma (LGG) Grade II, Lower Grade Glioma (LGG) Grade III, and Glioblastoma Multiforme (GBM) Grade IV. The survival and treatment options are highly dependent of this glioma grade. We propose a deep learning-based, modular classification pipeline for automated grading of gliomas using digital pathology images. ⋯ Our modular pipeline provides diagnostic quality statistics, such as precision, sensitivity and specificity, of the individual deep learning modules, and (1) facilitates training given the limited data in this domain, (2) enables exploration of different deep learning structures for each module, (3) leads to developing less complex modules that are simpler to analyze, and (4) provides flexibility, permitting use of single modules within the framework or use of other modeling or machine learning applications, such as probabilistic graphical models or support vector machines. Our modular approach helps us meet the requirements of minimum accuracy levels that are demanded by the context of different decision points within a multi-class classification scheme. Convolutional Neural Networks are trained for each module for each sub-task with more than 90% classification accuracies on validation data set, and achieved classification accuracy of 96% for the task of GBM vs LGG classification, 71% for further identifying the grade of LGG into Grade II or Grade III on independent data set coming from new patients from the multi-institutional repository.
-
Discharge summaries (DCS) frequently fail to improve the continuity of care. A chart review of 188 DCS was performed to identify specific components that could be improved through health information technology. Medication reconciliations were analyzed for completeness and for medical reasoning. ⋯ Patient preferences, patient goals, and lessons learned were rarely included. A handover tone was in only 17% of the DCS. Evaluating the DCS as a clinical handover is novel but information for safe handovers is frequently missing.
-
AMIA Annu Symp Proc · Jan 2014
Characterization of a handoff documentation tool through usage log data.
Handoffs are a critical component of coordinated patient care; however, poor handoffs have been associated with near misses and adverse events. To address this, national agencies have recommended standardizing handoffs, for example through the use of handoff documentation tools. Recent research suggests that handoff tools, typically designed for physicians, are often used by non-physician providers as information sources. ⋯ This further reiterates the view of electronic handoff tools as facilitators of team communication and coordination. However, the study also showed considerable variability in the frequency of updates between different units and across different patients. Further research is required to understand what factors drive such diversity in the use of electronic handoff tool and whether this diversity can be used to make inferences about patients' conditions.
-
AMIA Annu Symp Proc · Jan 2014
An evaluation of a natural language processing tool for identifying and encoding allergy information in emergency department clinical notes.
Emergency department (ED) visits due to allergic reactions are common. Allergy information is often recorded in free-text provider notes; however, this domain has not yet been widely studied by the natural language processing (NLP) community. We developed an allergy module built on the MTERMS NLP system to identify and encode food, drug, and environmental allergies and allergic reactions. ⋯ We developed an annotation schema and annotated 400 ED notes that served as a gold standard for comparison to MTERMS output. MTERMS achieved an F-measure of 87.6% for the detection of allergen names and no known allergies, 90% for identifying true reactions in each allergy statement where true allergens were also identified, and 69% for linking reactions to their allergen. These preliminary results demonstrate the feasibility using NLP to extract and encode allergy information from clinical notes.
-
Being a hospital patient can be isolating and anxiety-inducing. We conducted two experiments to better understand clinician and patient perceptions about giving patients access to their medical records during hospital encounters. The first experiment, a survey of physicians, nurses, and other care providers (N=53), showed that most respondents were comfortable with the idea of providing patients with their clinical information. ⋯ In the second experiment, we provided eight hospital patients with a daily copy of their full medical record-including physician notes and diagnostic test results. From semi-structured interviews with seven of these patients, we found that they perceived the information as highly useful even if they did not fully understand complex medical terms. Our results suggest that increased patient information sharing in the inpatient setting is beneficial and desirable to patients, and generally acceptable to clinicians.