Building longitudinal medication dose data using medication information extracted from clinical notes in electronic health records

ObjectiveTo develop an algorithm for building longitudinal medication dose datasets using information extracted from clinical notes in electronic health records (EHRs).Materials and MethodsWe developed an algorithm that converts medication information extracted using natural language processing (NLP) into a usable format and builds longitudinal medication dose datasets. We evaluated the algorithm on 2 medications extracted from clinical notes of Vanderbilt’s EHR and externally validated the algorithm using clinical notes from the MIMIC-III clinical care database.ResultsFor the evaluation using Vanderbilt’s EHR data, the performance of our algorithm was excellent; F1-measures were ≥0.98 for both dose intake and daily dose. For the external validation using MIMIC-III, the algorithm achieved F1-measures ≥0.85 for dose intake and ≥0.82 for daily dose.DiscussionOur algorithm addresses the challenge of building longitudinal medication dose data using information extracted from clinical notes. Overall performance was excellent, but the algorithm can perform poorly when incorrect information is extracted by NLP systems. Although it performed reasonably well when applied to the external data source, its performance was worse due to differences in the way the drug information was written. The algorithm is implemented in the R package, “EHR,” and the extracted data from Vanderbilt’s EHRs along with the gold standards are provided so that users can reproduce the results and help improve the algorithm.ConclusionOur algorithm for building longitudinal dose data provides a straightforward way to use EHR data for medication-based studies. The external validation results suggest its potential for applicability to other systems.     

Breast Cancer Treatment of Women with Schizophrenia and Bipolar Disorder from Philadelphia, PA: Lessons Learned and Suggestions for Improvement

Treating cancer in patients with concurrent severe mental illness is complex and challenging for patients, families, and health care providers. Two such illnesses include schizophrenia and bipolar disorder. In this review, cases of women with breast cancer and severe mental illness from Philadelphia, PA illustrate the obstacles these women face in maintaining adequate cancer care. Barriers to receiving cancer treatment include understanding their disease, continuing medications and appointments, and experiencing complications of their psychiatric disorders. Learning from these cases is critical for health care providers and allows for innovation in treating and educating this difficult population. Increasing patient visit time, using social support services, and psychiatrist and psychiatrist-liaisons are necessary to improve care. In addition, family or caregivers should be included in discussions when possible. These techniques will assist in educating patients, improve insight into their disease and treatment, and allow them to benefit from cancer therapy.     

Metabolic effects of low dose angiotensin converting enzyme inhibitor in dietary obesity in the rat

Background and aimsGiven the recent observation of a local renin-angiotensin system (RAS) in adipose tissue, and its association with obesity-related hypertension, the metabolic effects of treatment with a low dose angiotensin converting enzyme inhibitor (ACEI) were investigated in a rodent model of diet-induced obesity.Methods and resultsMale Sprague Dawley rats were exposed to either standard laboratory chow (12% calories as fat) or palatable high fat (30% calories as fat) diet for 12 weeks. A subset from both dietary groups was given low dose ACEI in drinking water (perindopril, 0.3 mg/kg/day) throughout the study. The high fat diet increased body weight, adiposity, circulating leptin and insulin and in the liver we observed fat accumulation and increased tissue ACE activity. Treatment with perindopril decreased food intake and circulating insulin in both diet groups, and hepatic ACE activity in high fat fed animals only. Decreased plasma leptin concentration with ACE inhibition was only evident in chow fed animals. These effects were independent of any blood pressure lowering effect of ACE inhibition.ConclusionChronic low dose ACEI treatment reduced circulating insulin and leptin levels with some reduction in food intake in chow fed rats. Fewer beneficial effects were observed in obesity, and further work is required to investigate higher ACEI doses. Our data suggest a reduction in hepatic ACE activity may affect lipid accumulation and other inflammatory responses, as well as improving insulin resistance. Our findings may have implications for maximizing the clinical benefit of ACEI in patients without overt cardiovascular complications.     

Brain injury: Analysis of outcome in a post-acute rehabilitation system. Part 2: Subanalyses

The basic findings of brain-injured patients who underwent treatment within a co-ordinated system of post-acute brain-injury rehabilitation programmes have already been reported. The changes in function during the course of treatment by this post-acute sequence of rehabilitation were obtained and reported. A defined total population of N=192 was examined, with exclusions for appropriate causes (e.g. patients seen only for evaluation) producing a study population of N=173; of these, follow-up was achieved in 145 cases, a follow-up rate of 83.8%. Time from date of injury to date of admission, severity of deficit at time of admission to programme, and other appropriate independent variables were used to characterize the population. A single-blind interview methodology was employed in obtaining dependent measures of outcome at 6, 12 or 24 month periods post-discharge. Measures of outcome included residential status, level of productivity activity, and hours per day of attendant care or supervision required. In the work reported in this paper dependent variables are analysed for various subgroups of the total population. The subgroups analysed are: patients with traumatic brain injury only; mild moderate and severe grades of disability; and comparisons of outcomes at 6 months, 1 year, and 2 years post-discharge from treatment. The results are presented in terms of percentage change in dependent measures from point of admission to follow-up. Appropriate parametric and non-parametric statistical analyses of significance are carried out. Additionally, an analysis of cost associated with treatment, and some analysis of cost-benefit is provided. The results document substantial improvements in function during post-acute rehabilitation for both traumatic brain injury and brain dysfunction of other etiologies. Significant improvements are seen to occur in all grades of severity of dysfunction examined, and such improvements are robust and persist without evidence of decrement over the 2-year follow-up period. In addition, economic considerations suggest the potential for the recouping of costs of treatment within a reasonable period of time.