RESUMEN

BACKGROUND: Incidental radiographic findings, such as adrenal nodules, are commonly identified in imaging studies and documented in radiology reports. However, patients with such findings frequently do not receive appropriate follow-up, partially due to the lack of tools for the management of such findings and the time required to maintain up-to-date lists. Natural language processing (NLP) is capable of extracting information from free-text clinical documents and could provide the basis for software solutions that do not require changes to clinical workflows. OBJECTIVES: In this manuscript we present (1) a machine learning algorithm we trained to identify radiology reports documenting the presence of a newly discovered adrenal incidentaloma, and (2) the web application and results database we developed to manage these clinical findings. METHODS: We manually annotated a training corpus of 4,090 radiology reports from across our institution with a binary label indicating whether or not a report contains a newly discovered adrenal incidentaloma. We trained a convolutional neural network to perform this text classification task. Over the NLP backbone we built a web application that allows users to coordinate clinical management of adrenal incidentalomas in real time. RESULTS: The annotated dataset included 404 positive (9.9%) and 3,686 (90.1%) negative reports. Our model achieved a sensitivity of 92.9% (95% confidence interval: 80.9-97.5%), a positive predictive value of 83.0% (69.9-91.1)%, a specificity of 97.8% (95.8-98.9)%, and an F1 score of 87.6%. We developed a front-end web application based on the model's output. CONCLUSION: Developing an NLP-enabled custom web application for tracking and management of high-risk adrenal incidentalomas is feasible in a resource constrained, safety net hospital. Such applications can be used by an institution's quality department or its primary care providers and can easily be generalized to other types of clinical findings.

Asunto(s)

RESUMEN

T-box (TBX) transcription factors are evolutionary conserved genes and master transcriptional regulators. In mammals, TBX2 subfamily (TBX2, TBX3, TBX4, and TBX5) genes are expressed in the developing lung bud and tracheae. Our group previously showed that the expression of TBX2 subfamily was significantly high in human normal lungs, but markedly suppressed in lung adenocarcinoma (LUAD). To further elucidate their role in LUAD pathogenesis, we first confirmed abundant expression of protein products of the four members by immunostaining in adult human normal lung tissues. We also found overall suppressed expression of these genes and their corresponding proteins in a panel of human LUAD cell lines. Transient over-expression of each of the genes in human (NCI-H1299), and mouse (MDA-F471) derived lung cancer cells was found to significantly inhibit growth and proliferation as well as induce apoptosis. Genome-wide transcriptomic analyses on NCI-H1299 cells, overexpressing TBX2 gene subfamily, unraveled novel regulatory pathways. These included, among others, inhibition of cell cycle progression but more importantly activation of the histone demethylase pathway. When using a pattern-matching algorithm, we showed that TBX's overexpression mimic molecular signatures from azacitidine treated NCI-H1299 cells which in turn are inversely correlated to expression profiles of both human and murine lung tumors relative to matched normal lung. In conclusion, we showed that the TBX2 subfamily genes play a critical tumor suppressor role in lung cancer pathogenesis through regulating its methylating pattern, making them putative candidates for epigenetic therapy in LUAD.