Local data commons: the sleeping beauty in the community of data commons.

BACKGROUND: Public Data Commons (PDC) have been highlighted in the scientific literature for their capacity to collect and harmonize big data. On the other hand, local data commons (LDC), located within an institution or organization, have been underrepresented in the scientific literature, even though they are a critical part of research infrastructure. Being closest to the sources of data, LDCs provide the ability to collect and maintain the most up-to-date, high-quality data within an organization, closest to the sources of the data. As a data provider, LDCs have many challenges in both collecting and standardizing data, moreover, as a consumer of PDC, they face problems of data harmonization stemming from the monolithic harmonization pipeline designs commonly adapted by many PDCs. Unfortunately, existing guidelines and resources for building and maintaining data commons exclusively focus on PDC and provide very little information on LDC. RESULTS: This article focuses on four important observations. First, there are three different types of LDC service models that are defined based on their roles and requirements. These can be used as guidelines for building new LDC or enhancing the services of existing LDC. Second, the seven core services of LDC are discussed, including cohort identification and facilitation of genomic sequencing, the management of molecular reports and associated infrastructure, quality control, data harmonization, data integration, data sharing, and data access control. Third, instead of commonly developed monolithic systems, we propose a new data sharing method for data harmonization that combines both divide-and-conquer and bottom-up approaches. Finally, an end-to-end LDC implementation is introduced with real-world examples. CONCLUSIONS: Although LDCs are an optimal place to identify and address data quality issues, they have traditionally been relegated to the role of passive data provider for much larger PDC. Indeed, many LDCs limit their functions to only conducting routine data storage and transmission tasks due to a lack of information on how to design, develop, and improve their services using limited resources. We hope that this work will be the first small step in raising awareness among the LDCs of their expanded utility and to publicize to a wider audience the importance of LDC.

Automatic Extraction of ICD-O-3 Primary Sites from Cancer Pathology Reports.

Although registry specific requirements exist, cancer registries primarily identify reportable cases using a combination of particular ICD-O-3 topography and morphology codes assigned to cancer case abstracts of which free text pathology reports form a main component. The codes are generally extracted from pathology reports by trained human coders, sometimes with the help of software programs. Here we present results that improve on the state-of-the-art in automatic extraction of 57 generic sites from pathology reports using three representative machine learning algorithms in text classification. We use a dataset of 56,426 reports arising from 35 labs that report to the Kentucky Cancer Registry. Employing unigrams, bigrams, and named entities as features, our methods achieve a class-based micro F-score of 0.9 and macro F-score of 0.72. To our knowledge, this is the best result on extracting ICD-O-3 codes from pathology reports using a large number of possible codes. Given the large dataset we use (compared to other similar efforts) with reports from 35 different labs, we also expect our final models to generalize better when extracting primary sites from previously unseen reports.