A certified de-identification system for all clinical text documents for information extraction at scale.

Objectives: Clinical notes are a veritable treasure trove of information on a patient's disease progression, medical history, and treatment plans, yet are locked in secured databases accessible for research only after extensive ethics review. Removing personally identifying and protected health information (PII/PHI) from the records can reduce the need for additional Institutional Review Boards (IRB) reviews. In this project, our goals were to: (1) develop a robust and scalable clinical text de-identification pipeline that is compliant with the Health Insurance Portability and Accountability Act (HIPAA) Privacy Rule for de-identification standards and (2) share routinely updated de-identified clinical notes with researchers. Materials and Methods: Building on our open-source de-identification software called Philter, we added features to: (1) make the algorithm and the de-identified data HIPAA compliant, which also implies type 2 error-free redaction, as certified via external audit; (2) reduce over-redaction errors; and (3) normalize and shift date PHI. We also established a streamlined de-identification pipeline using MongoDB to automatically extract clinical notes and provide truly de-identified notes to researchers with periodic monthly refreshes at our institution. Results: To the best of our knowledge, the Philter V1.0 pipeline is currently the first and only certified, de-identified redaction pipeline that makes clinical notes available to researchers for nonhuman subjects' research, without further IRB approval needed. To date, we have made over 130 million certified de-identified clinical notes available to over 600 UCSF researchers. These notes were collected over the past 40 years, and represent data from 2757016 UCSF patients.

Lessons learned and recommendations for data coordination in collaborative research: The CSER consortium experience.

Integrating data across heterogeneous research environments is a key challenge in multi-site, collaborative research projects. While it is important to allow for natural variation in data collection protocols across research sites, it is also important to achieve interoperability between datasets in order to reap the full benefits of collaborative work. However, there are few standards to guide the data coordination process from project conception to completion. In this paper, we describe the experiences of the Clinical Sequence Evidence-Generating Research (CSER) consortium Data Coordinating Center (DCC), which coordinated harmonized survey and genomic sequencing data from seven clinical research sites from 2020 to 2022. Using input from multiple consortium working groups and from CSER leadership, we first identify 14 lessons learned from CSER in the categories of communication, harmonization, informatics, compliance, and analytics. We then distill these lessons learned into 11 recommendations for future research consortia in the areas of planning, communication, informatics, and analytics. We recommend that planning and budgeting for data coordination activities occur as early as possible during consortium conceptualization and development to minimize downstream complications. We also find that clear, reciprocal, and continuous communication between consortium stakeholders and the DCC is equally important to maintaining a secure and centralized informatics ecosystem for pooling data. Finally, we discuss the importance of actively interrogating current approaches to data governance, particularly for research studies that straddle the research-clinical divide.

Evaluation of serverless computing for scalable execution of a joint variant calling workflow.

Advances in whole-genome sequencing have greatly reduced the cost and time of obtaining raw genetic information, but the computational requirements of analysis remain a challenge. Serverless computing has emerged as an alternative to using dedicated compute resources, but its utility has not been widely evaluated for standardized genomic workflows. In this study, we define and execute a best-practice joint variant calling workflow using the SWEEP workflow management system. We present an analysis of performance and scalability, and discuss the utility of the serverless paradigm for executing workflows in the field of genomics research. The GATK best-practice short germline joint variant calling pipeline was implemented as a SWEEP workflow comprising 18 tasks. The workflow was executed on Illumina paired-end read samples from the European and African super populations of the 1000 Genomes project phase III. Cost and runtime increased linearly with increasing sample size, although runtime was driven primarily by a single task for larger problem sizes. Execution took a minimum of around 3 hours for 2 samples, up to nearly 13 hours for 62 samples, with costs ranging from $2 to $70.

Variant Classification Concordance using the ACMG-AMP Variant Interpretation Guidelines across Nine Genomic Implementation Research Studies.

Harmonization of variant pathogenicity classification across laboratories is important for advancing clinical genomics. The two CLIA-accredited Electronic Medical Record and Genomics Network sequencing centers and the six CLIA-accredited laboratories and one research laboratory performing genome or exome sequencing in the Clinical Sequencing Evidence-Generating Research Consortium collaborated to explore current sources of discordance in classification. Eight laboratories each submitted 20 classified variants in the ACMG secondary finding v.2.0 genes. After removing duplicates, each of the 158 variants was annotated and independently classified by two additional laboratories using the ACMG-AMP guidelines. Overall concordance across three laboratories was assessed and discordant variants were reviewed via teleconference and email. The submitted variant set included 28 P/LP variants, 96 VUS, and 34 LB/B variants, mostly in cancer (40%) and cardiac (27%) risk genes. Eighty-six (54%) variants reached complete five-category (i.e., P, LP, VUS, LB, B) concordance, and 17 (11%) had a discordance that could affect clinical recommendations (P/LP versus VUS/LB/B). 21% and 63% of variants submitted as P and LP, respectively, were discordant with VUS. Of the 54 originally discordant variants that underwent further review, 32 reached agreement, for a post-review concordance rate of 84% (118/140 variants). This project provides an updated estimate of variant concordance, identifies considerations for LP classified variants, and highlights ongoing sources of discordance. Continued and increased sharing of variant classifications and evidence across laboratories, and the ongoing work of ClinGen to provide general as well as gene- and disease-specific guidance, will lead to continued increases in concordance.

Protected Health Information filter (Philter): accurately and securely de-identifying free-text clinical notes.

There is a great and growing need to ascertain what exactly is the state of a patient, in terms of disease progression, actual care practices, pathology, adverse events, and much more, beyond the paucity of data available in structured medical record data. Ascertaining these harder-to-reach data elements is now critical for the accurate phenotyping of complex traits, detection of adverse outcomes, efficacy of off-label drug use, and longitudinal patient surveillance. Clinical notes often contain the most detailed and relevant digital information about individual patients, the nuances of their diseases, the treatment strategies selected by physicians, and the resulting outcomes. However, notes remain largely unused for research because they contain Protected Health Information (PHI), which is synonymous with individually identifying data. Previous clinical note de-identification approaches have been rigid and still too inaccurate to see any substantial real-world use, primarily because they have been trained with too small medical text corpora. To build a new de-identification tool, we created the largest manually annotated clinical note corpus for PHI and develop a customizable open-source de-identification software called Philter ("Protected Health Information filter"). Here we describe the design and evaluation of Philter, and show how it offers substantial real-world improvements over prior methods.

Evolution of the Highly Repetitive PEVK Region of Titin Across Mammals.

The protein titin plays a key role in vertebrate muscle where it acts like a giant molecular spring. Despite its importance and conservation over vertebrate evolution, a lack of high quality annotations in non-model species makes comparative evolutionary studies of titin challenging. The PEVK region of titin-named for its high proportion of Pro-Glu-Val-Lys amino acids-is particularly difficult to annotate due to its abundance of alternatively spliced isoforms and short, highly repetitive exons. To understand PEVK evolution across mammals, we developed a bioinformatics tool, PEVK_Finder, to annotate PEVK exons from genomic sequences of titin and applied it to a diverse set of mammals. PEVK_Finder consistently outperforms standard annotation tools across a broad range of conditions and improves annotations of the PEVK region in non-model mammalian species. We find that the PEVK region can be divided into two subregions (PEVK-N, PEVK-C) with distinct patterns of evolutionary constraint and divergence. The bipartite nature of the PEVK region has implications for titin diversification. In the PEVK-N region, certain exons are conserved and may be essential, but natural selection also acts on particular codons. In the PEVK-C, exons are more homogenous and length variation of the PEVK region may provide the raw material for evolutionary adaptation in titin function. The PEVK-C region can be further divided into a highly repetitive region (PEVK-CA) and one that is more variable (PEVK-CB). Taken together, we find that the very complexity that makes titin a challenge for annotation tools may also promote evolutionary adaptation.