Clinical IE has been used for a wide range of applications, however, there is a considerable gap between clinical studies using EHR data and studies using clinical IE. This study enabled us to gain a more concrete understanding of the gap and to provide potential solutions to bridge this gap.

Based on the evaluation results, we can draw the following conclusions. First, the word embeddings trained from EHR and MedLit can capture the semantics of medical terms better, and find semantically relevant medical terms closer to human experts' judgments than those trained from GloVe and Google News. Second, there does not exist a consistent global ranking of word embeddings for all downstream biomedical NLP applications. However, adding word embeddings as extra features will improve results on most downstream tasks. Finally, the word embeddings trained from the biomedical domain corpora do not necessarily have better performance than those trained from the general domain corpora for any downstream biomedical NLP task.

Epidermal growth factor receptor tyrosine kinase inhibitors gefitinib and erlotinib have been widely used in patients with non-small-cell lung cancer. Unfortunately, the efficacy of EGFR-TKIs is limited because of natural and acquired resistance. As a novel cytoprotective mechanism for tumor cell to survive under unfavorable conditions, autophagy has been proposed to play a role in drug resistance of tumor cells. Whether autophagy can be activated by gefitinib or erlotinib and thereby impair the sensitivity of targeted therapy to lung cancer cells remains unknown. Here, we first report that gefitinib or erlotinib can induce a high level of autophagy, which was accompanied by the inhibition of the PI3K/Akt/mTOR signaling pathway. Moreover, cytotoxicity induced by gefitinib or erlotinib was greatly enhanced after autophagy inhibition by the pharmacological inhibitor chloroquine (CQ) and siRNAs targeting ATG5 and ATG7, the most important components for the formation of autophagosome. Interestingly, EGFR-TKIs can still induce cell autophagy even after EGFR expression was reduced by EGFR specific siRNAs. In conclusion, we found that autophagy can be activated by EGFR-TKIs in lung cancer cells and inhibition of autophagy augmented the growth inhibitory effect of EGFR-TKIs. Autophagy inhibition thus represents a promising approach to improve the efficacy of EGFR-TKIs in the treatment of patients with advanced non-small-cell lung cancer.

BackgroundAutomatic clinical text classification is a natural language processing (NLP) technology that unlocks information embedded in clinical narratives. Machine learning approaches have been shown to be effective for clinical text classification tasks. However, a successful machine learning model usually requires extensive human efforts to create labeled training data and conduct feature engineering. In this study, we propose a clinical text classification paradigm using weak supervision and deep representation to reduce these human efforts.MethodsWe develop a rule-based NLP algorithm to automatically generate labels for the training data, and then use the pre-trained word embeddings as deep representation features for training machine learning models. Since machine learning is trained on labels generated by the automatic NLP algorithm, this training process is called weak supervision. We evaluat the paradigm effectiveness on two institutional case studies at Mayo Clinic: smoking status classification and proximal femur (hip) fracture classification, and one case study using a public dataset: the i2b2 2006 smoking status classification shared task. We test four widely used machine learning models, namely, Support Vector Machine (SVM), Random Forest (RF), Multilayer Perceptron Neural Networks (MLPNN), and Convolutional Neural Networks (CNN), using this paradigm. Precision, recall, and F1 score are used as metrics to evaluate performance.ResultsCNN achieves the best performance in both institutional tasks (F1 score: 0.92 for Mayo Clinic smoking status classification and 0.97 for fracture classification). We show that word embeddings significantly outperform tf-idf and topic modeling features in the paradigm, and that CNN captures additional patterns from the weak supervision compared to the rule-based NLP algorithms. We also observe two drawbacks of the proposed paradigm that CNN is more sensitive to the size of training data, and that the proposed paradigm might not be effective for complex multiclass classification tasks.ConclusionThe proposed clinical text classification paradigm could reduce human efforts of labeled training data creation and feature engineering for applying machine learning to clinical text classification by leveraging weak supervision and deep representation. The experimental experiments have validated the effectiveness of paradigm by two institutional and one shared clinical text classification tasks.