Search

The aim of this study was to evaluate the performance of a computable phenotype for systemic lupus erythematosus (SLE) patients when it is ported from a local data warehouse to the i2b2, OMOP, and PCORnet CDMs. We adapted the SLE phenotype to the Northwestern Medicine (NM) Enterprise Data Warehouse (EDW) and NU i2b2, OMOP, and PCORnet instances. Each of the phenotype’s 17 components were determined by a rules-based algorithm built on diagnosis, medication, lab, and procedure codes. We assessed the phenotype over 168 clinician-confirmed SLE patients and 100 healthy controls and calculated agreement between the EDW and CDMs for overall SLE classification, individual SLICC criteria membership, and individual code occurrence level aggregates - count, first and last date, lab values using Cohen’s kappa (Cκ) and intraclass correlation coefficients (ICC). For overall SLE classification, agreement of the OMOP and PCORnet datamarts with the EDW was high (Cκ 0.928, 0.802, respectively) while that of i2b2 was low (Cκ 0.328). For the panel of SLICC criteria, OMOP had high agreement for 14/17 SLICC criteria (Cκ 0.792-1.000). PCORnet had high agreement for 13/17 criteria (Cκ 0.708-1.000). i2b2 had high agreement for 10/17 criteria (Cκ 0.813-1.000) with the exception of lab-based criteria. While agreement between the EDW and CDMs at the level of individual codes was relatively poor, agreement at the levels of overall SLE classification and individual SLICC criteria were reasonably high for OMOP and PCORnet, suggesting that inconsistencies at a micro, code level become less apparent at the macro, phenotype level.

Abstract Background Systemic lupus erythematosus (SLE) is a rare autoimmune disorder characterized by an unpredictable course of flares and remission with diverse manifestations. Lupus nephritis, one of the major disease manifestations of SLE for organ damage and mortality, is a key component of lupus classification criteria. Accurately identifying lupus nephritis in electronic health records (EHRs) would therefore benefit large cohort observational studies and clinical trials where characterization of the patient population is critical for recruitment, study design, and analysis. Lupus nephritis can be recognized through procedure codes and structured data, such as laboratory tests. However, other critical information documenting lupus nephritis, such as histologic reports from kidney biopsies and prior medical history narratives, require sophisticated text processing to mine information from pathology reports and clinical notes. In this study, we developed algorithms to identify lupus nephritis with and without natural language processing (NLP) using EHR data from the Northwestern Medicine Enterprise Data Warehouse (NMEDW). Methods We developed five algorithms: a rule-based algorithm using only structured data (baseline algorithm) and four algorithms using different NLP models. The first NLP model applied simple regular expression for keywords search combined with structured data. The other three NLP models were based on regularized logistic regression and used different sets of features including positive mention of concept unique identifiers (CUIs), number of appearances of CUIs, and a mixture of three components (i.e. a curated list of CUIs, regular expression concepts, structured data) respectively. The baseline algorithm and the best performing NLP algorithm were externally validated on a dataset from Vanderbilt University Medical Center (VUMC). Results Our best performing NLP model incorporated features from both structured data, regular expression concepts, and mapped concept unique identifiers (CUIs) and showed improved F measure in both the NMEDW (0.41 vs 0.79) and VUMC (0.52 vs 0.93) datasets compared to the baseline lupus nephritis algorithm. Conclusion Our NLP MetaMap mixed model improved the F-measure greatly compared to the structured data only algorithm in both internal and external validation datasets. The NLP algorithms can serve as powerful tools to accurately identify lupus nephritis phenotype in EHR for clinical research and better targeted therapies.

Abstract Introduction The rapid development of artificial intelligence (AI) in healthcare has exposed the unmet need for growing a multidisciplinary workforce that can collaborate effectively in the learning health systems. Maximizing the synergy among multiple teams is critical for Collaborative AI in Healthcare. Methods We have developed a series of data, tools, and educational resources for cultivating the next generation of multidisciplinary workforce for Collaborative AI in Healthcare. We built bulk‐natural language processing pipelines to extract structured information from clinical notes and stored them in common data models. We developed multimodal AI/machine learning (ML) tools and tutorials to enrich the toolbox of the multidisciplinary workforce to analyze multimodal healthcare data. We have created a fertile ground to cross‐pollinate clinicians and AI scientists and train the next generation of AI health workforce to collaborate effectively. Results Our work has democratized access to unstructured health information, AI/ML tools and resources for healthcare, and collaborative education resources. From 2017 to 2022, this has enabled studies in multiple clinical specialties resulting in 68 peer‐reviewed publications. In 2022, our cross‐discipline efforts converged and institutionalized into the Center for Collaborative AI in Healthcare. Conclusions Our Collaborative AI in Healthcare initiatives has created valuable educational and practical resources. They have enabled more clinicians, scientists, and hospital administrators to successfully apply AI methods in their daily research and practice, develop closer collaborations, and advanced the institution‐level learning health system.

BackgroundThe past decade has seen increasing opportunities and efforts to integrate quality improvement into health care. Practice facilitation is a proven strategy to support redesign and improvement in primary care practices that focuses on building organizational capacity for continuous improvement. Practice leadership, staff, and practice facilitators all play important roles in supporting quality improvement in primary care. However, little is known about their perspectives on the context, enablers, barriers, and strategies that impact quality improvement initiatives. ObjectiveThis study aimed to develop a framework to enable assessment of contextual factors, challenges, and strategies that impact practice facilitation, clinical measure performance, and the implementation of quality improvement interventions. We also illustrated the application of the framework using a real-world case study. MethodsWe developed the TITO (task, individual, technology, and organization) framework by conducting participatory stakeholder workshops and incorporating their perspectives to identify enablers and barriers to quality improvement and practice facilitation. We conducted a case study using a mixed methods approach to demonstrate the use of the framework and describe practice facilitation and factors that impact quality improvement in a primary care practice that participated in the Healthy Hearts in the Heartland study. ResultsThe proposed framework was used to organize and analyze different stakeholders’ perspectives and key factors based on framework domains. The case study showed that practice leaders, staff, and practice facilitators all influenced the success of the quality improvement program. However, these participants faced different challenges and used different strategies. The framework showed that barriers stemmed from patients’ social determinants of health, a lack of staff and time, and unsystematic facilitation resources, while enablers included practice culture, staff buy-in, implementation of effective practice facilitation strategies, practice capacity for change, and shared complementary resources from similar, ongoing programs. ConclusionsOur framework provided a useful and generalizable structure to guide and support assessment of future practice facilitation projects, quality improvement initiatives, and health care intervention implementation studies. The practice leader, staff, and practice facilitator all saw value in the quality improvement program and practice facilitation. Practice facilitators are key liaisons to help the quality improvement program; they help all stakeholders work toward a shared target and leverage tailored strategies. Taking advantage of resources from competing, yet complementary, programs as additional support may accelerate the effective achievement of quality improvement goals. Practice facilitation–supported quality improvement programs may be opportunities to assist primary care practices in achieving improved quality of care through focused and targeted efforts. The case study demonstrated how our framework can support a better understanding of contextual factors for practice facilitation, which could enable well-prepared and more successful quality improvement programs for primary care practices. Combining implementation science and informatics thinking, our TITO framework may facilitate interdisciplinary research in both fields.

An 8× draft genome was obtained and annotated for Ralstonia solanacearum race 3 biovar 2 (R3B2) strain UW551, a United States Department of Agriculture Select Agent isolated from geranium. The draft UW551 genome consisted of 80,169 reads resulting in 582 contigs containing 5,925,491 base pairs, with an average 64.5% GC content. Annotation revealed a predicted 4,454 protein coding open reading frames (ORFs), 43 tRNAs, and 5 rRNAs; 2,793 (or 62%) of the ORFs had a functional assignment. The UW551 genome was compared with the published genome of R. solanacearum race 1 biovar 3 tropical tomato strain GMI1000. The two phylogenetically distinct strains were at least 71% syntenic in gene organization. Most genes encoding known pathogenicity determinants, including predicted type III secreted effectors, appeared to be common to both strains. A total of 402 unique UW551 ORFs were identified, none of which had a best hit or >45% amino acid sequence identity with any R. solanacearum predicted protein; 16 had strong (E < 10-13) best hits to ORFs found in other bacterial plant pathogens. Many of the 402 unique genes were clustered, including 5 found in the hrp region and 38 contiguous, potential prophage genes. Conservation of some UW551 unique genes among R3B2 strains was examined by polymerase chain reaction among a group of 58 strains from different races and biovars, resulting in the identification of genes that may be potentially useful for diagnostic detection and identification of R3B2 strains. One 22-kb region that appears to be present in GMI1000 as a result of horizontal gene transfer is absent from UW551 and encodes enzymes that likely are essential for utilization of the three sugar alcohols that distinguish biovars 3 and 4 from biovars 1 and 2.