Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture,component evaluation and applications

We aim to build and evaluate an open-source natural language processing system for information extraction from electronic medical record clinical free-text. We describe and evaluate our system, the clinical Text Analysis and Knowledge Extraction System (cTAKES), released open-source at http://www.ohnlp.org. The cTAKES builds on existing open-source technologies—the Unstructured Information Management Architecture framework and OpenNLP natural language processing toolkit. Its components, specifically trained for the clinical domain, create rich linguistic and semantic annotations. Performance of individual components: sentence boundary detector accuracy=0.949; tokenizer accuracy=0.949; part-of-speech tagger accuracy=0.936; shallow parser F-score=0.924; named entity recognizer and system-level evaluation F-score=0.715 for exact and 0.824 for overlapping spans, and accuracy for concept mapping, negation, and status attributes for exact and overlapping spans of 0.957, 0.943, 0.859, and 0.580, 0.939, and 0.839, respectively. Overall performance is discussed against five applications. The cTAKES annotations are the foundation for methods and modules for higher-level semantic processing of clinical free-text.     

Automatically extracting cancer disease characteristics from pathology reports into a Disease Knowledge Representation Model

We introduce an extensible and modifiable knowledge representation model to represent cancer disease characteristics in a comparable and consistent fashion. We describe a system, MedTAS/P which automatically instantiates the knowledge representation model from free-text pathology reports. MedTAS/P is based on an open-source framework and its components use natural language processing principles, machine learning and rules to discover and populate elements of the model. To validate the model and measure the accuracy of MedTAS/P, we developed a gold-standard corpus of manually annotated colon cancer pathology reports. MedTAS/P achieves F1-scores of 0.97–1.0 for instantiating classes in the knowledge representation model such as histologies or anatomical sites, and F1-scores of 0.82–0.93 for primary tumors or lymph nodes, which require the extractions of relations. An F1-score of 0.65 is reported for metastatic tumors, a lower score predominantly due to a very small number of instances in the training and test sets.     

Potential Impact of Initial Clinical Data on Adjustment of Pediatric Readmission Rates

ObjectiveComparison of readmission rates requires adjustment for case-mix (ie, differences in patient populations), but previously only claims data were available for this purpose. We examined whether incorporation of relatively readily available clinical data improves prediction of pediatric readmissions and thus might enhance case-mix adjustment.MethodsWe examined 30-day readmissions using claims and electronic health record data for patients ≤18 years and 29 days of age who were admitted to 3 children's hospitals from February 2011 to February 2014. Using the Pediatric All-Condition Readmission Measure and starting with a model including age, gender, chronic conditions, and primary diagnosis, we examined whether the addition of initial vital sign and laboratory data improved model performance. We employed machine learning to evaluate the same variables, using the L2-regularized logistic regression with cost-sensitive learning and convolutional neural network.ResultsControlling for the core model variables, low red blood cell count and mean corpuscular hemoglobin concentration and high red cell distribution width were associated with greater readmission risk, as were certain interactions between laboratory and chronic condition variables. However, the C-statistic (0.722 vs 0.713) and McFadden's pseudo R² (0.085 vs 0.076) for this and the core model were similar, suggesting minimal improvement in performance. In machine learning analyses, the F-measure (harmonic mean of sensitivity and positive predictive value) was similar for the best-performing model (containing all variables) and core model (0.250 vs 0.243).ConclusionsReadily available clinical variables do not meaningfully improve the prediction of pediatric readmissions and would be unlikely to enhance case-mix adjustment unless their distributions varied widely across hospitals.     

Expanding indications for liver transplantation in the era of liver transplant oncology

Despite numerous advances and emerging data, liver transplantation in the setting of gastrointestinal malignancies remains controversial outside of certain accepted indications. In an era of persistent organ shortage and increasing organ demand, allocation of liver grafts must be considered carefully. While hepatocellular carcinoma and hilar cholangiocarcinoma have become accepted indications for transplantation, tumor size and standardized multi-disciplinary treatment protocols are necessary to ensure optimal patient outcomes. As more studies seeking to expand the oncologic indications for liver transplantation are emerging, it is becoming increasingly clear that tumor biology and response to therapy are key factors for optimal oncologic outcomes. In addition, time from diagnosis to transplantation appears to correlate with survival, as stable disease over time portends better outcomes post-operatively. Identifying aggressive disease pre-transplant remains difficult with current imaging and tissue sampling techniques. While tumor size and stage are important prognostic predictors for most malignancies, patient and tumor selection protocols are necessary. As the fields of medical and surgical oncology continue to evolve, it is clear that a protocolized interdisciplinary treatment approach is necessary for combatting any cancer effectively. Disease stability over time and response to neoadjuvant therapy may be the best predictors for successful patient outcomes and can be easily incorporated in our treatment paradigms. Current data evaluating liver transplantation for expanded oncologic indications such as: expanded criteria hepatocellular carcinoma, intrahepatic cholangiocarcinoma, mixed tumors, and liver limited metastatic colorectal carcinomas, incorporate multi-modal therapies and evaluation of tumor treatment response. While further investigation is necessary, initial results suggest there is an expanded role for transplant surgery in malignancy in a new era of liver transplant oncology.     

Anaphoric reference in clinical reports: characteristics of an annotated corpus

MotivationExpressions that refer to a real-world entity already mentioned in a narrative are often considered anaphoric. For example, in the sentence “The pain comes and goes,” the expression “the pain” is probably referring to a previous mention of pain. Interpretation of meaning involves resolving the anaphoric reference: deciding which expression in the text is the correct antecedent of the referring expression, also called an anaphor. We annotated a set of 180 clinical reports (surgical pathology, radiology, discharge summaries, and emergency department) from two institutions to indicate all anaphor–antecedent pairs.ObjectiveThe objective of this study is to describe the characteristics of the corpus in terms of the frequency of anaphoric relations, the syntactic and semantic nature of the members of the pairs, and the types of anaphoric relations that occur. Understanding how anaphoric reference is exhibited in clinical reports is critical to developing reference resolution algorithms and to identifying peculiarities of clinical text that may alter the features and methodologies that will be successful for automated anaphora resolution.ResultsWe found that anaphoric reference is prevalent in all types of clinical reports, that annotations of noun phrases, semantic type, and section headings may be especially important for automated resolution of anaphoric reference, and that separate modules for reference resolution may be required for different report types, different institutions, and different types of anaphors. Accurate resolution will probably require extensive domain knowledge—especially for pathology and radiology reports with more part/whole and set/subset relations.ConclusionWe hope researchers will leverage the annotations in this corpus to develop automated algorithms and will add to the annotations to generate a more extensive corpus.     

Cyclin D1 inhibits mitochondrial activity in B cells

Cyclin D1 is a cell cycle regulatory protein that acts at the G1-S transition, following its binding to and activation by the cyclin-dependent kinases 4 or 6. Cyclin D1 is absent from the entire B-cell lineage but is present in a large percentage of 2 types of malignant B-cell hemopathy--mantle cell lymphoma and multiple myeloma--suggesting a major role of this protein in the malignancy process. We show here, in an experimental model of cyclin D1 fusion protein transduction in mature B cells, that, cyclin D1 inhibits total mitochondrial activity. Cyclin D1 is localized at the outer mitochondrial membrane, bound to a voltage-dependent anion channel through its central domain, and it competes with hexokinase 2 for binding to this channel. The bound cyclin D1 decreases the supply of ADP, ATP, and metabolites, thereby reducing energy production. This function of cyclin D1 was also reported by others in normal and transformed mammary epithelial cells, suggesting that it may be ubiquitous.