Sohn, Sunghwan

The concept of optimizing health care by understanding and generating knowledge from previous evidence, ie, the Learning Health-care System (LHS), has gained momentum and now has national prominence. Meanwhile, the rapid adoption of electronic health records (EHRs) enables the data collection required to form the basis for facilitating LHS. A prerequisite for using EHR data within the LHS is an infrastructure that enables access to EHR data longitudinally for health-care analytics and real time for knowledge delivery. Additionally, significant clinical information is embedded in the free text, making natural language processing (NLP) an essential component in implementing an LHS. Herein, we share our institutional implementation of a big data-empowered clinical NLP infrastructure, which not only enables health-care analytics but also has real-time NLP processing capability. The infrastructure has been utilized for multiple institutional projects including the MayoExpertAdvisor, an individualized care recommendation solution for clinical care. We compared the advantages of big data over two other environments. Big data infrastructure significantly outperformed other infrastructure in terms of computing speed, demonstrating its value in making the LHS a possibility in the near future.

Background and Purpose— We investigated whether family history of stroke or coronary heart disease (CHD) is associated with presence of carotid artery stenosis (CAS). Methods— The study cohort included 864 patients (72±8 years; 68% men) with CAS and 1698 controls (61±11 years; 55% men) referred for noninvasive vascular testing. CAS was defined as ≥70% stenosis in the internal carotid artery on ultrasound or history of carotid revascularization. Controls did not have CAS or history of cerebrovascular disease or CHD. Family history of stroke and CHD was defined as having ≥1 first-degree relative who had stroke or CHD before age 65 years. Logistic regression analysis was used to evaluate whether family history of stroke or CHD was associated with presence of CAS, independent of conventional risk factors. Results— Family history of stroke and CHD was present more often in patients with CAS than in controls, with a resulting odds ratios (95% confidence interval) of 2.02 (1.61–2.53) and 2.01 (1.70–2.37), respectively. The associations remained significant after adjustment for age, sex, body mass index, smoking, diabetes mellitus, hypertension, and dyslipidemia; odds ratios: 1.41 (1.06–1.90) and 1.69 (1.35–2.10), respectively. A greater number of affected relatives with stroke or CHD was associated with higher odds of CAS; adjusted odds ratios: 1.25 (0.91–1.72) and 1.46 (1.14–1.89) versus 2.65 (1.35–5.40) and 2.13 (1.57–2.90) for patients with 1 and ≥2 affected relatives with stroke and CHD, respectively. Conclusions— Family history of stroke and of CHD were each associated with CAS, suggesting that shared genetic and environmental factors contribute to the risk of CAS.

A large amount of medication information resides in the unstructured text found in electronic medical records, which requires advanced techniques to be properly mined. In clinical notes, medication information follows certain semantic patterns (eg, medication, dosage, frequency, and mode). Some medication descriptions contain additional word(s) between medication attributes. Therefore, it is essential to understand the semantic patterns as well as the patterns of the context interspersed among them (ie, context patterns) to effectively extract comprehensive medication information. In this paper we examined both semantic and context patterns, and compared those found in Mayo Clinic and i2b2 challenge data. We found that some variations exist between the institutions but the dominant patterns are common.

This paper describes the sentiment classification system developed by the Mayo Clinic team for the 2011 I2B2/VA/Cincinnati Natural Language Processing (NLP) Challenge. The sentiment classification task is to assign any pertinent emotion to each sentence in suicide notes. We have implemented three systems that have been trained on suicide notes provided by the I2B2 challenge organizer–-a machine learning system, a rule-based system, and a system consisting of a combination of both. Our machine learning system was trained on re-annotated data in which apparently inconsistent emotion assignment was adjusted. Then, the machine learning methods by RIPPER and multinomial Naïve Bayes classifiers, manual pattern matching rules, and the combination of the two systems were tested to determine the emotions within sentences. The combination of the machine learning and rule-based system performed best and produced a micro-average F-score of 0.5640.