Background: Clinical records are often unstructured, free-text documents that create information extraction challenges and costs. Healthcare delivery and research organizations, such as the National Mesothelioma Virtual Bank, require the aggregation of both structured and unstructured data types. Natural language processing offers techniques for automatically extracting information from unstructured, free-text documents. Methods: Five hundred and eight history and physical reports from mesothelioma patients were split into development (208) and test sets (300). A reference standard was developed and each report was annotated by experts with regard to the patient's personal history of ancillary cancer and family history of any cancer. The Hx application was developed to process reports, extract relevant features, perform reference resolution and classify them with regard to cancer history. Two methods, Dynamic-Window and ConText, for extracting information were evaluated. Hx's classification responses using each of the two methods were measured against the reference standard. The average Cohen's weighted kappa served as the human benchmark in evaluating the system. Results: Hx had a high overall accuracy, with each method, scoring 96.2%. F-measures using the Dynamic-Window and ConText methods were 91.8% and 91.6%, which were comparable to the human benchmark of 92.8%. For the personal history classification, Dynamic-Window scored highest with 89.2% and for the family history classification, ConText scored highest with 97.6%, in which both methods were comparable to the human benchmark of 88.3% and 97.2%, respectively. Conclusion: We evaluated an automated application's performance in classifying a mesothelioma patient's personal and family history of cancer from clinical reports. To do so, the Hx application must process reports, identify cancer concepts, distinguish the known mesothelioma from ancillary cancers, recognize negation, perform reference resolution and determine the experiencer. Results indicated that both information extraction methods tested were dependant on the domain-specific lexicon and negation extraction. We showed that the more general method, ConText, performed as well as our task-specific method. Although Dynamic-Window could be modified to retrieve other concepts, ConText is more robust and performs better on inconclusive concepts. Hx could greatly improve and expedite the process of extracting data from free-text, clinical records for a variety of research or healthcare delivery organizations.

Background: The Early Detection Research Network (EDRN) colorectal and pancreatic neoplasm virtual biorepository is a bioinformatics-driven system that provides high-quality clinicopathology-rich information for clinical biospecimens. This NCI-sponsored EDRN resource supports translational cancer research. The information model of this biorepository is based on three components: (a) development of common data elements (CDE), (b) a robust data entry tool and (c) comprehensive data query tools. Methods: The aim of the EDRN initiative is to develop and sustain a virtual biorepository for support of translational research. High-quality biospecimens were accrued and annotated with pertinent clinical, epidemiologic, molecular and genomic information. A user-friendly annotation tool and query tool was developed for this purpose. The various components of this annotation tool include: CDEs are developed from the College of American Pathologists (CAP) Cancer Checklists and North American Association of Central Cancer Registries (NAACR) standards. The CDEs provides semantic and syntactic interoperability of the data sets by describing them in the form of metadata or data descriptor. The data entry tool is a portable and flexible Oracle-based data entry application, which is an easily mastered, web-based tool. The data query tool facilitates investigators to search deidentified information within the warehouse through a "point and click" interface thus enabling only the selected data elements to be essentially copied into a data mart using a dimensional-modeled structure from the warehouse's relational structure. Results: The EDRN Colorectal and Pancreatic Neoplasm Virtual Biorepository database contains multimodal datasets that are available to investigators via a web-based query tool. At present, the database holds 2,405 cases and 2,068 tumor accessions. The data disclosure is strictly regulated by user's authorization. The high-quality and well-characterized biospecimens have been used in different translational science research projects as well as to further various epidemiologic and genomics studies. Conclusions: The EDRN Colorectal and Pancreatic Neoplasm Virtual Biorepository with a tangible translational biomedical informatics infrastructure facilitates translational research. The data query tool acts as a central source and provides a mechanism for researchers to efficiently query clinically annotated datasets and biospecimens that are pertinent to their research areas. The tool ensures patient health information protection by disclosing only deidentified data with Institutional Review Board and Health Insurance Portability and Accountability Act protocols.

Background: Radio frequency identification (RFID) tags have potential for use in identifying and tracking biospecimens in anatomic pathology and biorepository laboratories. However, there is little to no data on the tolerance of tags to solutions, solvents, temperatures, and pressures likely to be encountered in the laboratory. The functioning of the Hitachi Mu-chip RFID tag, a candidate for pathology use, was evaluated under such conditions. Methods: The RFID tags were affixed to cryovials containing tissue or media, glass slides, and tissue cassettes. The tags were interrogated for readability before and after each testing condition or cycle. Individual tags were subjected to only one testing condition but for multiple cycles. Testing conditions were: 1) Ten wet autoclave cycles (121˚C, 15 psi); 2) Ten dry autoclave cycles (121˚C, 26 psi); 3) Ten tissue processor cycles; 4) Ten hematoxylin and eosin (H&E) staining cycles; 5) Ten antigen retrieval pressure cooker cycles (125˚C, 15 psi); 6) 75 ^o C for seven days; 7) 75-59 ^o C day/night cycles for 7 days; 8) -80 ^o C, -150 ^o C, or -196 ^o C for 12 months; 9) Fifty freeze-thaw cycles (-196 ^o C to 22 ^o C). Results: One hundred percent of tags exposed to cold temperatures from -80 to -196 ^o C (80 tags, 1120 successful reads), high temperatures from 52 to 75 ^o C (40 tags, 420 reads), H & E staining (20 tags, 200 reads), pressure cooker antigen retrieval (20 tags, 200 reads), and wet autoclaving (20 tags, 200 reads) functioned well throughout and after testing. Of note, all 20 tested tags tolerated 50 freeze-thaw cycles and all 60 tags subjected to sustained freezing temperatures were readable after 1 year. One dry autoclaved tag survived nine cycles but failed after the tenth. The remaining 19 tags were readable after all 10 dry autoclave cycles. One tag failed after the first tissue processing cycle while the remaining 19 tags survived all 10 tissue processing cycles. Conclusions: In this preliminary study, these RFID tags show a high-degree of tolerance to tested solutions, solvents, temperature, and pressure conditions. However, a measurable failure rate is detectable under some circumstances and redundant identification systems such as barcodes may be required with the deployment of RFID systems. We have delineated testing protocols that may be used as a framework for preliminary assessments of candidate RFID tag tolerance to laboratory conditions.