Search tips
Search criteria

Results 1-6 (6)

Clipboard (0)

Select a Filter Below

more »
Year of Publication
Document Types
1.  Validity and reliability of a pressure ulcer monitoring tool for persons with spinal cord impairment 
The purpose was to provide support for validity and reliability of the spinal cord impairment pressure ulcer monitoring tool (SCI-PUMT) to assess pressure ulcer (PrU) healing.
Expert panels developed a 30-item pool, including new items and items from two established PrU healing tools, to represent potential variables for monitoring PrU healing. Subjects were prospectively assessed weekly for each variable over a 12-week period.
Data collection was conducted on a cohort of inpatients and outpatients in one Spinal Cord Injury/Disorders Center in the Veterans’ Health Administration.
A convenience sample of Veterans (n = 66) with spinal cord impairment (SCI) was recruited. Eligible subjects had at least one PrU (n = 167) and a history of SCI for longer than 1 year.
Not applicable.
Outcome Measure
A change in PrU volume was calculated using VeV Measurement Documentation software and a digital imaging camera.
Content validity was established for a pool of items designed to gauge PrU healing. Exploratory factor analysis (construct validity) identified a parsimonious set of seven items for inclusion in the SCI-PUMT to assess PrU healing. The SCI-PUMT was found to explain 59% of the variance of the volume across the study. Inter-rater reliability was 0.79 and intra-rater reliability ranged from 0.81 to 0.99 among research assistants. Similar levels of reliability were subsequently established among registered nurses, who used the SCI-PUMT in the clinical setting.
The final version of the SCI-PUMT was determined to be valid, reliable, and sensitive in detecting PrU healing over time in Veterans with SCI.
PMCID: PMC4064581  PMID: 24621044
Pressure ulcer; Decubitus ulcer; Pressure sore; Bedsore; Spinal cord injuries
2.  Using Information from the Electronic Health Record to Improve Measurement of Unemployment in Service Members and Veterans with mTBI and Post-Deployment Stress 
PLoS ONE  2014;9(12):e115873.
The purpose of this pilot study is 1) to develop an annotation schema and a training set of annotated notes to support the future development of a natural language processing (NLP) system to automatically extract employment information, and 2) to determine if information about employment status, goals and work-related challenges reported by service members and Veterans with mild traumatic brain injury (mTBI) and post-deployment stress can be identified in the Electronic Health Record (EHR).
Retrospective cohort study using data from selected progress notes stored in the EHR.
Post-deployment Rehabilitation and Evaluation Program (PREP), an in-patient rehabilitation program for Veterans with TBI at the James A. Haley Veterans' Hospital in Tampa, Florida.
Service members and Veterans with TBI who participated in the PREP program (N = 60).
Main Outcome Measures
Documentation of employment status, goals, and work-related challenges reported by service members and recorded in the EHR.
Two hundred notes were examined and unique vocational information was found indicating a variety of self-reported employment challenges. Current employment status and future vocational goals along with information about cognitive, physical, and behavioral symptoms that may affect return-to-work were extracted from the EHR. The annotation schema developed for this study provides an excellent tool upon which NLP studies can be developed.
Information related to employment status and vocational history is stored in text notes in the EHR system. Information stored in text does not lend itself to easy extraction or summarization for research and rehabilitation planning purposes. Development of NLP systems to automatically extract text-based employment information provides data that may improve the understanding and measurement of employment in this important cohort.
PMCID: PMC4277395  PMID: 25541956
3.  TagLine: Information Extraction for Semi-Structured Text in Medical Progress Notes 
Statistical text mining and natural language processing have been shown to be effective for extracting useful information from medical documents. However, neither technique is effective at extracting the information stored in semi-structure text elements. A prototype system (TagLine) was developed to extract information from the semi-structured text using machine learning and a rule based annotator. Features for the learning machine were suggested by prior work, and by examining text, and selecting attributes that help distinguish classes of text lines. Classes were derived empirically from text and guided by an ontology developed by the VHA’s Consortium for Health Informatics Research (CHIR). Decision trees were evaluated for class predictions on 15,103 lines of text achieved an overall accuracy of 98.5 percent. The class labels applied to the lines were then used for annotating semi-structured text elements. TagLine achieved F-measure over 0.9 for each of the structures, which included tables, slots and fillers.
PMCID: PMC4419992  PMID: 25954358
4.  Finding falls in ambulatory care clinical documents using statistical text mining 
To determine how well statistical text mining (STM) models can identify falls within clinical text associated with an ambulatory encounter.
Materials and Methods
2241 patients were selected with a fall-related ICD-9-CM E-code or matched injury diagnosis code while being treated as an outpatient at one of four sites within the Veterans Health Administration. All clinical documents within a 48-h window of the recorded E-code or injury diagnosis code for each patient were obtained (n=26 010; 611 distinct document titles) and annotated for falls. Logistic regression, support vector machine, and cost-sensitive support vector machine (SVM-cost) models were trained on a stratified sample of 70% of documents from one location (dataset Atrain) and then applied to the remaining unseen documents (datasets Atest–D).
All three STM models obtained area under the receiver operating characteristic curve (AUC) scores above 0.950 on the four test datasets (Atest–D). The SVM-cost model obtained the highest AUC scores, ranging from 0.953 to 0.978. The SVM-cost model also achieved F-measure values ranging from 0.745 to 0.853, sensitivity from 0.890 to 0.931, and specificity from 0.877 to 0.944.
The STM models performed well across a large heterogeneous collection of document titles. In addition, the models also generalized across other sites, including a traditionally bilingual site that had distinctly different grammatical patterns.
The results of this study suggest STM-based models have the potential to improve surveillance of falls. Furthermore, the encouraging evidence shown here that STM is a robust technique for mining clinical documents bodes well for other surveillance-related topics.
PMCID: PMC3756258  PMID: 23242765
Text Mining; Accidental Falls; Electronic Health Records; Ambulatory Care
5.  A Comparison of Patient Outcomes and Quality of Life in Persons With Neurogenic Bowel: Standard Bowel Care Program Vs Colostomy 
The purpose of this study was to compare patient outcomes and quality of life for people with neurogenic bowel using either a standard bowel care program or colostomy.
We analyzed survey data from a national sample, comparing outcomes between veterans with spinal cord injury (SCI) who perform bowel care programs vs individuals with colostomies. This study is part of a larger study to evaluate clinical practice guideline implementation in SCI. The sample included 1,503 veterans with SCI. The response rate was 58.4%. For comparison, we matched the respondents with colostomies to matched controls from the remainder of the survey cohort. A total of 74 veterans with SCI and colostomies were matched with 296 controls, using propensity scores. Seven items were designed to elicit information about the respondent's satisfaction with their bowel care program, whereas 7 other items were designed to measure bowel-related quality of life.
No statistically significant differences in satisfaction or quality of life were found between the responses from veterans with colostomies and those with traditional bowel care programs. Both respondents with colostomies and those without colostomies indicated that they had received training for their bowel care program, that they experienced relatively few complications, such as falls as a result of their bowel care program, and that their quality of life related to bowel care was generally good. However, large numbers of respondents with colostomies (n = 39; 55.7%) and without colostomies (n = 113; 41.7%) reported that they were very unsatisfied with their bowel care program.
Satisfaction with bowel care is a major problem for veterans with SCI.
PMCID: PMC1808270  PMID: 16869085
Colostomy; Spinal cord injuries; Neurogenic bowel; Bowel care; Quality of Life; Life satisfaction; Activities of daily life
6.  Using Ontology Network Structure in Text Mining 
Statistical text mining treats documents as bags of words, with a focus on term frequencies within documents and across document collections. Unlike natural language processing (NLP) techniques that rely on an engineered vocabulary or a full-featured ontology, statistical approaches do not make use of domain-specific knowledge. The freedom from biases can be an advantage, but at the cost of ignoring potentially valuable knowledge. The approach proposed here investigates a hybrid strategy based on computing graph measures of term importance over an entire ontology and injecting the measures into the statistical text mining process. As a starting point, we adapt existing search engine algorithms such as PageRank and HITS to determine term importance within an ontology graph. The graph-theoretic approach is evaluated using a smoking data set from the i2b2 National Center for Biomedical Computing, cast as a simple binary classification task for categorizing smoking-related documents, demonstrating consistent improvements in accuracy.
PMCID: PMC3041319  PMID: 21346937

Results 1-6 (6)