Advanced Data Analytics for Clinical Research Part I: What are the Tools?

Abstract

<jats:p> The concept of Big Data is changing the way that clinical research can be performed. Cardiothoracic surgeons need to understand the dynamic digital transformation taking place in the healthcare industry. In the last decade, technological advances and Big Data analytics have become powerful tools for businesses. In healthcare, rapid expansion of Big Data infrastructure has occurred in parallel with attempts to reduce cost and improve outcomes. Many hospitals around the country are augmenting traditional relational databases with Big Data infrastructure. Advanced data capture and categorization tools such as natural language processing and optical character recognition are being developed for clinical and research use, while Internet of Things in the form of wearable technology serves as an additional source of data usable for research. As cardiothoracic surgeons seek ways to innovate, novel approaches to data acquisition and analysis enable a more rigorous level of investigatory efforts. </jats:p>

Importance of resection for locoregional disease control in Masaoka stage IVA thymic neoplasms

“…Patients with thymic neuroendocrine tumors were excluded. Using natural language processing techniques which have been previously described, patients found to have a Masaoka stage IVA thymic neoplasm at the time of initial diagnosis were identified 11‐13 . The truncated search terms of pleura, diaphragm, pericardium, and dropped were used to specify metastatic disease location, and variations of the terms mass, nodule, lesion, and metastasis were employed to specifically identify stage IVA disease.…”

Esophageal adenocarcinoma with any component of signet ring cells portends poor prognosis and response to neoadjuvant therapy

“…Using natural language-processing methods, which have been previously described, we further evaluated the records of patients for the presence of the non-negated term "signet" in pathology reports within the electronic medical record. [13][14][15] This method of key word search is definitive, with 100% sensitivity and 100% specificity. Dates of such pathology reports were recorded and described in relation to the dates of both diagnosis and esophagectomy to better understand the change in the proportion of SRC noted in pathology specimens before and following treatment with neoadjuvant chemoradiation.…”

Advanced Data Analytics for Clinical Research Part II: Application to Cardiothoracic Surgery

“…Both groups of specialists have very different languages in their respective fields, the data scientist will not understand the nuances and complex definitions that exist in medicine and vice versa; nevertheless, familiarity and expertise in both areas are essential for quality results. Our introductory manuscript 1 aimed to provide initial exposure to the language of Big Data and a basic understanding of how these technologies were built and designed, so that communication can be facilitated. For institutions with available data analytic teams and advanced tools such as NLP, early interaction with these teams allows consideration of the full armamentarium of available tools into a possible data retrieval methodology.…”

“…We have previously described a variety of tools related to Big Data analytics that may be implemented in clinical research for the benefit of the cardiothoracic surgeon. 1 In addition to having an infrastructure to gather and merge data from unrelated, independent databases, additional tools help turn unstructured data into usable research data points. Advanced analytics can be helpful in selecting patient groups of interest among the tens of thousands of patients treated over decades at a given institution, as well as coalescing information from pharmacy, radiology, perioperative documentation, cancer registries, billing and coding data, and more.…”