Faculty Bibliography

BACKGROUND:Intrathecal morphine is a popular and effective regional technique for pain control after open liver resection, but its delayed analgesic onset makes it less useful for the intraoperative period. The aim of this retrospective study was to compare the analgesic efficacy and other secondary benefits of the addition of hyperbaric bupivacaine to intrathecal morphine ± fentanyl. We hypothesized that bupivacaine could serve as an analgesic "bridge" prior to the onset of intrathecal morphine/fentanyl thereby lowering opioid consumption and enhancing recovery. METHODS:Cumulative intraoperative and postoperative opioid consumption as well as other intra- and postoperative variables were collected and compared between groups receiving intrathecal morphine alone or intrathecal morphine ± hyperbaric bupivacaine. RESULTS:Sixty-eight patients were selected for inclusion. Cumulative intraoperative morphine consumption was significantly reduced in the bupivacaine group while other intraoperative parameters such as intravenous fluids, blood loss, and vasopressors did not differ. There was a statistically significant improvement in time to first bowel movement in the experimental group. DISCUSSION/CONCLUSIONS:The intraoperative opioid sparing effects and improved time to bowel function with the addition of hyperbaric bupivacaine to intrathecal morphine may make this technique an easy and low risk method of enhancing recovery after open liver resection.

In secondary analysis of electronic health records, a crucial task consists in correctly identifying the patient cohort under investigation. In many cases, the most valuable and relevant information for an accurate classification of medical conditions exist only in clinical narratives. Therefore, it is necessary to use natural language processing (NLP) techniques to extract and evaluate these narratives. The most commonly used approach to this problem relies on extracting a number of clinician-defined medical concepts from text and using machine learning techniques to identify whether a particular patient has a certain condition. However, recent advances in deep learning and NLP enable models to learn a rich representation of (medical) language. Convolutional neural networks (CNN) for text classification can augment the existing techniques by leveraging the representation of language to learn which phrases in a text are relevant for a given medical condition. In this work, we compare concept extraction based methods with CNNs and other commonly used models in NLP in ten phenotyping tasks using 1,610 discharge summaries from the MIMIC-III database. We show that CNNs outperform concept extraction based methods in almost all of the tasks, with an improvement in F1-score of up to 26 and up to 7 percentage points in area under the ROC curve (AUC). We additionally assess the interpretability of both approaches by presenting and evaluating methods that calculate and extract the most salient phrases for a prediction. The results indicate that CNNs are a valid alternative to existing approaches in patient phenotyping and cohort identification, and should be further investigated. Moreover, the deep learning approach presented in this paper can be used to assist clinicians during chart review or support the extraction of billing codes from text by identifying and highlighting relevant phrases for various medical conditions.