Natural language processing to identify lupus nephritis phenotype in electronic health records.

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.

Multiarterial vs Single-Arterial Coronary Surgery: 10-Year Follow-up of 1 Million Patients.

BACKGROUND: Although many options exist for multivessel coronary revascularization, controversy persists over whether multiarterial grafting (MAG) confers a survival advantage over single-arterial grafting (SAG) with saphenous vein in coronary artery bypass grafting (CABG). This study sought to compare longitudinal survival between patients undergoing MAG and those undergoing SAG. METHODS: All patients undergoing isolated CABG with ≥2 bypass grafts in The Society of Thoracic Surgeons Adult Cardiac Surgery Database (2008-2019) were linked to the National Death Index. Risk adjustment was performed using inverse probability weighting and multivariable modeling. The primary end point was longitudinal survival. Subpopulation analyses were performed and volume thresholds were analyzed to determine optimal benefit. RESULTS: A total of 1,021,632 patients underwent isolated CABG at 1108 programs (100,419 MAG [9.83%]; 920,943 SAG [90.17%]). Median follow-up was 5.30 years (range, 0-12 years). After risk adjustment, all characteristics were well balanced. At 10 years, MAG was associated with improved unadjusted (hazard ratio, 0.59; 95% CI 0.58-0.61) and adjusted (hazard ratio, 0.86; 95% CI, 0.85-0.88) 10-year survival. Center volume of ≥10 MAG cases/year was associated with benefit. MAG was associated with an overall survival advantage over SAG in all subgroups, including stable coronary disease, acute coronary syndrome, and acute infarction. Survival was equivalent to that with SAG for patients age ≥80 years and those with severe heart failure, renal failure, peripheral vascular disease, or obesity. Only patients with a body mass index ≥40 kg/m2 had superior survival with SAG. CONCLUSIONS: Multiarterial CABG is associated with superior long-term survival and should be the surgical multivessel revascularization strategy of choice for patients with a body mass index of less than 40 kg/m2.

Prediction of Time to Hemodynamic Stabilization of Unstable Injured Patient Encounters Using Electronic Medical Record Data.

BACKGROUND: This study sought to predict time to patient hemodynamic stabilization during trauma resuscitations of hypotensive patient encounters using electronic medical records (EMR) data. METHODS: This observational cohort study leveraged EMR data from a nine-hospital academic system composed of Level I, Level II and non-trauma centers. Injured, hemodynamically unstable (initial systolic blood pressure < 90 mmHg) emergency encounters from 2015-2020 were identified. Stabilization was defined as documented subsequent systolic blood pressure > 90 mmHg. We predicted time to stabilization testing random forests, gradient boosting and ensembles using patient, injury, treatment, EPIC Trauma Narrator and hospital features from the first four hours of care. RESULTS: Of 177,127 encounters, 1347 (0.8%) arrived hemodynamically unstable; 168 (12.5%) presented to Level I trauma centers, 853 (63.3%) to Level II, and 326 (24.2%) to non-trauma centers. Of those, 747 (55.5%) were stabilized with a median of 50 minutes (IQR 21-101 min). Stabilization was documented in 94.6% of unstable patient encounters at Level I, 57.6% at Level II and 29.8% at non-trauma centers (p < 0.001). Time to stabilization was predicted with a C-index of 0.80. The most predictive features were EPIC Trauma Narrator measures; documented patient arrival, provider exam, and disposition decision. In-hospital mortality was highest at Level I, 3.0% vs. 1.2% at Level II, and 0.3% at non-trauma centers (p < 0.001). Importantly, non-trauma centers had the highest re-triage rate to another acute care hospital (12.0%) compared to Level II centers (4.0%, p < 0.001). CONCLUSION: Time to stabilization of unstable injured patients can be predicted with EMR data.

Prediction of intra-abdominal injury using natural language processing of electronic medical record data.

BACKGROUND: This study aimed to use natural language processing to predict the presence of intra-abdominal injury using unstructured data from electronic medical records. METHODS: This was a random-sample retrospective observational cohort study leveraging unstructured data from injured patients taken to one of 9 acute care hospitals in an integrated health system between 2015 and 2021. Patients with International Classification of Diseases External Cause of Morbidity codes were identified. History and physical, consult, progress, and radiology report text from the first 8 hours of care were abstracted. Annotator dyads independently annotated encounters' text files to establish ground truth regarding whether intra-abdominal injury occurred. Features were extracted from text using natural language processing techniques, bag of words, and principal component analysis. We tested logistic regression, random forests, and gradient boosting machine to determine accuracy, recall, and precision of natural language processing to predict intra-abdominal injury. RESULTS: A random sample of 7,000 patient encounters of 177,127 was annotated. Only 2,951 had sufficient information to determine whether an intra-abdominal injury was present. Among those, 84 (2.9%) had an intra-abdominal injury. The concordance between annotators was 0.989. Logistic regression of features identified with bag of words and principal component analysis had the best predictive ability, with an area under the receiver operating characteristic curve of 0.9, recall of 0.73, and precision of 0.17. Text features with greatest importance included "abdomen," "pelvis," "spleen," and "hematoma." CONCLUSION: Natural language processing could be a screening decision support tool, which, if paired with human clinical assessment, can maximize precision of intra-abdominal injury identification.

Rapid identification of inflammatory arthritis and associated adverse events following immune checkpoint therapy: a machine learning approach.

Introduction: Immune checkpoint inhibitor-induced inflammatory arthritis (ICI-IA) poses a major clinical challenge to ICI therapy for cancer, with 13% of cases halting ICI therapy and ICI-IA being difficult to identify for timely referral to a rheumatologist. The objective of this study was to rapidly identify ICI-IA patients in clinical data and assess associated immune-related adverse events (irAEs) and risk factors. Methods: We conducted a retrospective study of the electronic health records (EHRs) of 89 patients who developed ICI-IA out of 2451 cancer patients who received ICI therapy at Northwestern University between March 2011 to January 2021. Logistic regression and random forest machine learning models were trained on all EHR diagnoses, labs, medications, and procedures to identify ICI-IA patients and EHR codes indicating ICI-IA. Multivariate logistic regression was then used to test associations between ICI-IA and cancer type, ICI regimen, and comorbid irAEs. Results: Logistic regression and random forest models identified ICI-IA patients with accuracies of 0.79 and 0.80, respectively. Key EHR features from the random forest model included ICI-IA relevant features (joint pain, steroid prescription, rheumatoid factor tests) and features suggesting comorbid irAEs (thyroid function tests, pruritus, triamcinolone prescription). Compared to 871 adjudicated ICI patients who did not develop arthritis, ICI-IA patients had higher odds of developing cutaneous (odds ratio [OR]=2.66; 95% Confidence Interval [CI] 1.63-4.35), endocrine (OR=2.09; 95% CI 1.15-3.80), or gastrointestinal (OR=2.88; 95% CI 1.76-4.72) irAEs adjusting for demographics, cancer type, and ICI regimen. Melanoma (OR=1.99; 95% CI 1.08-3.65) and renal cell carcinoma (OR=2.03; 95% CI 1.06-3.84) patients were more likely to develop ICI-IA compared to lung cancer patients. Patients on nivolumab+ipilimumab were more likely to develop ICI-IA compared to patients on pembrolizumab (OR=1.86; 95% CI 1.01-3.43). Discussion: Our machine learning models rapidly identified patients with ICI-IA in EHR data and elucidated clinical features indicative of comorbid irAEs. Patients with ICI-IA were significantly more likely to also develop cutaneous, endocrine, and gastrointestinal irAEs during their clinical course compared to ICI therapy patients without ICI-IA.

Privacy-preserving record linkage across disparate institutions and datasets to enable a learning health system: The national COVID cohort collaborative (N3C) experience.

Introduction: Research driven by real-world clinical data is increasingly vital to enabling learning health systems, but integrating such data from across disparate health systems is challenging. As part of the NCATS National COVID Cohort Collaborative (N3C), the N3C Data Enclave was established as a centralized repository of deidentified and harmonized COVID-19 patient data from institutions across the US. However, making this data most useful for research requires linking it with information such as mortality data, images, and viral variants. The objective of this project was to establish privacy-preserving record linkage (PPRL) methods to ensure that patient-level EHR data remains secure and private when governance-approved linkages with other datasets occur. Methods: Separate agreements and approval processes govern N3C data contribution and data access. The Linkage Honest Broker (LHB), an independent neutral party (the Regenstrief Institute), ensures data linkages are robust and secure by adding an extra layer of separation between protected health information and clinical data. The LHB's PPRL methods (including algorithms, processes, and governance) match patient records using "deidentified tokens," which are hashed combinations of identifier fields that define a match across data repositories without using patients' clear-text identifiers. Results: These methods enable three linkage functions: Deduplication, Linking Multiple Datasets, and Cohort Discovery. To date, two external repositories have been cross-linked. As of March 1, 2023, 43 sites have signed the LHB Agreement; 35 sites have sent tokens generated for 9 528 998 patients. In this initial cohort, the LHB identified 135 037 matches and 68 596 duplicates. Conclusion: This large-scale linkage study using deidentified datasets of varying characteristics established secure methods for protecting the privacy of N3C patient data when linked for research purposes. This technology has potential for use with registries for other diseases and conditions.

Northwestern University resource and education development initiatives to advance collaborative artificial intelligence across the learning health system.

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.

Planning the Implementation of a Multilevel Blood Pressure Control Intervention in Chicago: Community and Clinical Perspectives.

Objectives: Hypertension is associated with high morbidity and mortality. The complications of hypertension disproportionately impact African American residents in Chicago's South Side neighborhood. To inform the implementation of an evidence-based multilevel hypertension management intervention, we sought to identify community member- and clinician-level barriers to diagnosing and treating hypertension, and strategies for addressing those barriers. Methods: We conducted 5 focus groups with members of faith-based organizations (FBOs) (n=40) and 8 focus groups with clinicians and administrators (n=26) employed by community health centers (CHCs) located in Chicago's South Side. Results: Participants across groups identified the physical environment, including lack of access to clinics and healthy food, as a risk factor for hypertension. Participants also identified inconsistent results from home blood pressure monitoring and medication side effects as barriers to seeking diagnosis and treatment. Potential strategies raised by participants to address these barriers included (1) addressing patients' unmet social needs, such as food security and transportation; (2) offering education that meaningfully engages patients in discussions about managing hypertension (eg, medication adherence, diet, follow-up care); (3) coordinating referrals via community-based organizations (including FBOs) to CHCs for hypertension management; and (4) establishing a setting where community members managing hypertension diagnosis can support one another. Conclusions: Clinic-level barriers to the diagnosis and treatment of hypertension, such as competing priorities and resource constraints, are exacerbated by community-level stressors. Community members and clinicians agreed that it is important to select implementation strategies that leverage and enhance both community- and clinic-based resources.

Process of Engaging Community and Scientific Partners in the Development of the CIRCL-Chicago Study Protocol.

Objectives: Hypertension affects 1 in 3 adults in the United States and disproportionately affects African Americans. Kaiser Permanente demonstrated that a "bundle" of evidence-based interventions significantly increased blood pressure control rates. This paper describes a multiyear process of developing the protocol for a trial of the Kaiser bundle for implementation in under-resourced urban communities experiencing cardiovascular health disparities during the planning phase of this biphasic award (UG3/UH3). Methods: The protocol was developed by a collaboration of faith-based community members, representatives from community health center practice-based research networks, and academic scientists with expertise in health disparities, implementation science, community-engaged research, social care interventions, and health informatics. Scientists from the National Institutes of Health and the other grantees of the Disparities Elimination through Coordinated Interventions to Prevent and Control Heart and Lung Disease Risk (DECIPHeR) Alliance also contributed to developing our protocol. Results: The protocol is a hybrid type 3 effectiveness-implementation study using a parallel cluster randomized trial to test the impact of practice facilitation on implementation of the Kaiser bundle in community health centers compared with implementation without facilitation. A central strategy to the Kaiser bundle is to coordinate implementation via faith-based and other community organizations for recruitment and navigation of resources for health-related social risks. Conclusions: The proposed research has the potential to improve identification, diagnosis, and control of blood pressure among under-resourced communities by connecting community entities and healthcare organizations in new ways. Faith-based organizations are a trusted voice in African American communities that could be instrumental for eliminating disparities.

Evolving availability and standardization of patient attributes for matching.

Variation in availability, format, and standardization of patient attributes across health care organizations impacts patient-matching performance. We report on the changing nature of patient-matching features available from 2010-2020 across diverse care settings. We asked 38 health care provider organizations about their current patient attribute data-collection practices. All sites collected name, date of birth (DOB), address, and phone number. Name, DOB, current address, social security number (SSN), sex, and phone number were most commonly used for cross-provider patient matching. Electronic health record queries for a subset of 20 participating sites revealed that DOB, first name, last name, city, and postal codes were highly available (>90%) across health care organizations and time. SSN declined slightly in the last years of the study period. Birth sex, gender identity, language, country full name, country abbreviation, health insurance number, ethnicity, cell phone number, email address, and weight increased over 50% from 2010 to 2020. Understanding the wide variation in available patient attributes across care settings in the United States can guide selection and standardization efforts for improved patient matching in the United States.