Context: Text-based reporting and manual arbitration for whole slide imaging (WSI) validation studies are labor intensive and do not allow for consistent, scalable, and repeatable data collection or analysis. Objective: The objective of this study was to establish a method of data capture and analysis using standardized codified checklists and predetermined synoptic discordance tables and to use these methods in a pilot multisite validation study. Methods and Study Design: Fifteen case report form checklists were generated from the College of American Pathology cancer protocols. Prior to data collection, all hypothetical pairwise comparisons were generated, and a level of harm was determined for each possible discordance. Four sites with four pathologists each generated 264 independent reads of 33 cases. Preestablished discordance tables were applied to determine site by site and pooled accuracy, intrareader/intramodality, and interreader intramodality error rates. Results: Over 10,000 hypothetical pairwise comparisons were evaluated and assigned harm in discordance tables. The average difference in error rates between WSI and glass, as compared to ground truth, was 0.75% with a lower bound of 3.23% (95% confidence interval). Major discordances occurred on challenging cases, regardless of modality. The average inter-reader agreement across sites for glass was 76.5% (weighted kappa of 0.68) and for digital it was 79.1% (weighted kappa of 0.72). Conclusion: These results demonstrate the feasibility and utility of employing standardized synoptic checklists and predetermined discordance tables to gather consistent, comprehensive diagnostic data for WSI validation studies. This method of data capture and analysis can be applied in large-scale multisite WSI validations.

Background: Endometrial carcinoma (EC) is the most common extracolonic malignant neoplasm associated with Lynch syndrome (LS). LS is caused by autosomal dominant germline mutations in DNA mismatch repair (MMR) genes. Screening for LS in EC is often evaluated by loss of immunohistochemical (IHC) expression of DNA MMR enzymes MLH1, MSH2, MSH6, and PMS2 (MMR IHC). In July 2013, our clinicians asked that we screen all EC in patients ≤60 for loss of MMR IHC expression. Despite this policy, several cases were not screened or screening was delayed. We implemented an informatics-based approach to ensure that all women who met criteria would have timely screening. Subjects and Methods: Reports are created in PowerPath (Sunquest Information Systems, Tucson, AZ) with custom synoptic templates. We implemented an algorithm on March 6, 2014 requiring pathologists to address MMR IHC in patients ≤60 with EC before sign out (S/O). Pathologists must answer these questions: is patient ≤60 (yes/no), if yes, follow-up questions (IHC done previously, ordered with addendum to follow, results included in report, N/A, or not ordered), if not ordered, one must explain. We analyzed cases from July 18, 2013 to August 31, 2016 preimplementation (PreImp) and postimplementation (PostImp) that met criteria. Data analysis was performed using the standard data package included with GraphPad Prism^® 7.00 (GraphPad Software, Inc., La Jolla, CA, USA). Results: There were 147 patients who met criteria (29 PreImp and 118 PostImp). IHC was ordered in a more complete and timely fashion PostImp than PreImp. PreImp, 4/29 (13.8%) cases did not get any IHC, but PostImp, only 4/118 (3.39%) were missed (P = 0.0448). Of cases with IHC ordered, 60.0% (15/25) were ordered before or at S/O PreImp versus 91.2% (104/114) PostImp (P = 0.0004). Relative to day of S/O, the mean days of order delay were longer and more variable PreImp versus PostImp (12.9 ± 40.7 vs. -0.660 ± 1.15; P = 0.0227), with the average being before S/O PostImp. Conclusion: This algorithm ensures MMR IHC ordering in women ≤60 with EC and can be applied to similar scenarios. Ancillary tests for management are increasing, especially genetic and molecular-based methods. The burden of managing orders and results remains with the pathologist and relying on human intervention alone is ineffective. Ordering IHC before or at S/O prevents oversight and the additional work of retrospective ordering and reporting.

Background: Measures of spatial intratumor heterogeneity are potentially important diagnostic biomarkers for cancer progression, proliferation, and response to therapy. Spatial relationships among cells including cancer and stromal cells in the tumor microenvironment (TME) are key contributors to heterogeneity. Methods: We demonstrate how to quantify spatial heterogeneity from immunofluorescence pathology samples, using a set of 3 basic breast cancer biomarkers as a test case. We learn a set of dominant biomarker intensity patterns and map the spatial distribution of the biomarker patterns with a network. We then describe the pairwise association statistics for each pattern within the network using pointwise mutual information (PMI) and visually represent heterogeneity with a two-dimensional map. Results: We found a salient set of 8 biomarker patterns to describe cellular phenotypes from a tissue microarray cohort containing 4 different breast cancer subtypes. After computing PMI for each pair of biomarker patterns in each patient and tumor replicate, we visualize the interactions that contribute to the resulting association statistics. Then, we demonstrate the potential for using PMI as a diagnostic biomarker, by comparing PMI maps and heterogeneity scores from patients across the 4 different cancer subtypes. Estrogen receptor positive invasive lobular carcinoma patient, AL13-6, exhibited the highest heterogeneity score among those tested, while estrogen receptor negative invasive ductal carcinoma patient, AL13-14, exhibited the lowest heterogeneity score. Conclusions: This paper presents an approach for describing intratumor heterogeneity, in a quantitative fashion (via PMI), which departs from the purely qualitative approaches currently used in the clinic. PMI is generalizable to highly multiplexed/hyperplexed immunofluorescence images, as well as spatial data from complementary in situ methods including FISSEQ and CyTOF, sampling many different components within the TME. We hypothesize that PMI will uncover key spatial interactions in the TME that contribute to disease proliferation and progression.

Background: Celiac disease (CD) is a common autoimmune disorder. Efficient identification of patients may improve chronic management of the disease. Prior studies have shown searching International Classification of Diseases-9 (ICD-9) codes alone is inaccurate for identifying patients with CD. In this study, we developed automated classification algorithms leveraging pathology reports and other clinical data in Electronic Health Records (EHRs) to refine the subset population preselected using ICD-9 code (579.0). Materials and Methods: EHRs were searched for established ICD-9 code (579.0) suggesting CD, based on which an initial identification of cases was obtained. In addition, laboratory results for tissue transglutaminse were extracted. Using natural language processing we analyzed pathology reports from upper endoscopy. Twelve machine learning classifiers using different combinations of variables related to ICD-9 CD status, laboratory result status, and pathology reports were experimented to find the best possible CD classifier. Ten-fold cross-validation was used to assess the results. Results: A total of 1498 patient records were used including 363 confirmed cases and 1135 false positive cases that served as controls. Logistic model based on both clinical and pathology report features produced the best results: Kappa of 0.78, F1 of 0.92, and area under the curve (AUC) of 0.94, whereas in contrast using ICD-9 only generated poor results: Kappa of 0.28, F1 of 0.75, and AUC of 0.63. Conclusion: Our automated classification system presented an efficient and reliable way to improve the performance of CD patient identification.

Objective: Within the information technology (IT) industry, best practices and standards are constantly evolving and being refined. In contrast, computer technology utilized within the healthcare industry often evolves at a glacial pace, with reduced opportunities for justified innovation. Although the use of timely technology refreshes within an enterprise's overall technology stack can be costly, thoughtful adoption of select technologies with a demonstrated return on investment can be very effective in increasing productivity and at the same time, reducing the burden of maintenance often associated with older and legacy systems. In this brief technical communication, we introduce the concept of microservices as applied to the ecosystem of data analysis pipelines. Microservice architecture is a framework for dividing complex systems into easily managed parts. Each individual service is limited in functional scope, thereby conferring a higher measure of functional isolation and reliability to the collective solution. Moreover, maintenance challenges are greatly simplified by virtue of the reduced architectural complexity of each constitutive module. This fact notwithstanding, rendered overall solutions utilizing a microservices-based approach provide equal or greater levels of functionality as compared to conventional programming approaches. Bioinformatics, with its ever-increasing demand for performance and new testing algorithms, is the perfect use-case for such a solution. Moreover, if promulgated within the greater development community as an open-source solution, such an approach holds potential to be transformative to current bioinformatics software development. Context: Bioinformatics relies on nimble IT framework which can adapt to changing requirements. Aims: To present a well-established software design and deployment strategy as a solution for current challenges within bioinformatics Conclusions: Use of the microservices framework is an effective methodology for the fabrication and implementation of reliable and innovative software, made possible in a highly collaborative setting.