Search

Determining the cause of death of hospitalized patients with cardiovascular disease is of the utmost importance. This is usually recorded in free text form. In this study we aimed to develop a series of supervised natural language processing algorithms to extract cardiovascular causes of hospitalization and final causes of death.

Objectives: To assess the proportion of members of a private health insurance at the Hospital Italiano de Buenos Aires with primary adherence to, 1) bisphosphonates for secondary prevention of osteoporotic fractures, 2) insulin and metformin in type 2 diabetes, and 3) tamoxifen in the context of treatment of breast cancer., Design: Retrospective cohort study to determine the proportion of primary treatment adherence during 2012 and 2013. SITE: Hospital Italiano de Buenos Aires, Argentina., Participants: Members of the Hospital Italiano de Buenos Aires private health insurance, who had received a new electronic prescription (alendronate or ibandronate for secondary prevention of fractures following an osteoporotic fracture; insulin and/or metformin for type 2 diabetes; or tamoxifen as a treatment for breast cancer) during the years 2012 and 2013. An analysis was performed on 1,403 new electronic prescriptions, of which 673 were excluded for not meeting the inclusion criteria., Main Measurements: Primary adherence has been defined as the execution of a first-time treatment after it was agreed with the health care provider. The primary analysis assessed the proportion of primary adherence for the three medications. A bivariate analysis was performed to compare the characteristics and potential predictors of primary adherence., Results: Primary adherence for each drug group was, 93% Bisphosphonates, 88% Metformin, 96% Insulin, and 92% Tamoxifen., Conclusions: To the best of our knowledge, this is the first study that has evaluated primary adherence in Argentina, and the first for Tamoxifen world wide. The primary adherence documented in our study was somewhat higher than that reported in the literature., (Copyright © 2017 Elsevier España, S.L.U. All rights reserved.)

Background and Objective: Recent progression towards precision medicine has encouraged the use of electronic health records (EHRs) as a source for large amounts of data, which is required for studying the effect of treatments or risk factors in more specific subpopulations. Phenotyping algorithms allow to automatically classify patients according to their particular electronic phenotype thus facilitating the setup of retrospective cohorts. Our objective is to compare the performance of different classification strategies (only using standardized problems, rule-based algorithms, statistical learning algorithms (six learners) and stacked generalization (five versions)), for the categorization of patients according to their diabetic status (diabetics, not diabetics and inconclusive; Diabetes of any type) using information extracted from EHRs., Methods: Patient information was extracted from the EHR at Hospital Italiano de Buenos Aires, Buenos Aires, Argentina. For the derivation and validation datasets, two probabilistic samples of patients from different years (2005: n = 1663; 2015: n = 800) were extracted. The only inclusion criterion was age (≥40 & <80 years). Four researchers manually reviewed all records and classified patients according to their diabetic status (diabetic: diabetes registered as a health problem or fulfilling the ADA criteria; non-diabetic: not fulfilling the ADA criteria and having at least one fasting glycemia below 126 mg/dL; inconclusive: no data regarding their diabetic status or only one abnormal value). The best performing algorithms within each strategy were tested on the validation set., Results: The standardized codes algorithm achieved a Kappa coefficient value of 0.59 (95% CI 0.49, 0.59) in the validation set. The Boolean logic algorithm reached 0.82 (95% CI 0.76, 0.88). A slightly higher value was achieved by the Feedforward Neural Network (0.9, 95% CI 0.85, 0.94). The best performing learner was the stacked generalization meta-learner that reached a Kappa coefficient value of 0.95 (95% CI 0.91, 0.98)., Conclusions: The stacked generalization strategy and the feedforward neural network showed the best classification metrics in the validation set. The implementation of these algorithms enables the exploitation of the data of thousands of patients accurately., (Copyright © 2017 Elsevier B.V. All rights reserved.)