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.

ConceptWAS: A high-throughput method for early identification of COVID-19 presenting symptoms and characteristics from clinical notes.

OBJECTIVE: Identifying symptoms and characteristics highly specific to coronavirus disease 2019 (COVID-19) would improve the clinical and public health response to this pandemic challenge. Here, we describe a high-throughput approach - Concept-Wide Association Study (ConceptWAS) - that systematically scans a disease's clinical manifestations from clinical notes. We used this method to identify symptoms specific to COVID-19 early in the course of the pandemic. METHODS: We created a natural language processing pipeline to extract concepts from clinical notes in a local ER corresponding to the PCR testing date for patients who had a COVID-19 test and evaluated these concepts as predictors for developing COVID-19. We identified predictors from Firth's logistic regression adjusted by age, gender, and race. We also performed ConceptWAS using cumulative data every two weeks to identify the timeline for recognition of early COVID-19-specific symptoms. RESULTS: We processed 87,753 notes from 19,692 patients subjected to COVID-19 PCR testing between March 8, 2020, and May 27, 2020 (1,483 COVID-19-positive). We found 68 concepts significantly associated with a positive COVID-19 test. We identified symptoms associated with increasing risk of COVID-19, including "anosmia" (odds ratio [OR] = 4.97, 95% confidence interval [CI] = 3.21-7.50), "fever" (OR = 1.43, 95% CI = 1.28-1.59), "cough with fever" (OR = 2.29, 95% CI = 1.75-2.96), and "ageusia" (OR = 5.18, 95% CI = 3.02-8.58). Using ConceptWAS, we were able to detect loss of smell and loss of taste three weeks prior to their inclusion as symptoms of the disease by the Centers for Disease Control and Prevention (CDC). CONCLUSION: ConceptWAS, a high-throughput approach for exploring specific symptoms and characteristics of a disease like COVID-19, offers a promise for enabling EHR-powered early disease manifestations identification.

Enhancing Postmarketing Surveillance of Medical Products With Large Language Models.

Importance: The Sentinel System is a key component of the US Food and Drug Administration (FDA) postmarketing safety surveillance commitment and uses clinical health care data to conduct analyses to inform drug labeling and safety communications, FDA advisory committee meetings, and other regulatory decisions. However, observational data are frequently deemed insufficient for reliable evaluation of safety concerns owing to limitations in underlying data or methodology. Advances in large language models (LLMs) provide new opportunities to address some of these limitations. However, careful consideration is necessary for how and where LLMs can be effectively deployed for these purposes. Observations: LLMs may provide new avenues to support signal-identification activities to identify novel adverse event signals from narrative text of electronic health records. These algorithms may be used to support epidemiologic investigations examining the causal relationship between exposure to a medical product and an adverse event through development of probabilistic phenotyping of health outcomes of interest and extraction of information related to important confounding factors. LLMs may perform like traditional natural language processing tools by annotating text with controlled vocabularies with additional tailored training activities. LLMs offer opportunities for enhancing information extraction from adverse event reports, medical literature, and other biomedical knowledge sources. There are several challenges that must be considered when leveraging LLMs for postmarket surveillance. Prompt engineering is needed to ensure that LLM-extracted associations are accurate and specific. LLMs require extensive infrastructure to use, which many health care systems lack, and this can impact diversity, equity, and inclusion, and result in obscuring significant adverse event patterns in some populations. LLMs are known to generate nonfactual statements, which could lead to false positive signals and downstream evaluation activities by the FDA and other entities, incurring substantial cost. Conclusions and Relevance: LLMs represent a novel paradigm that may facilitate generation of information to support medical product postmarket surveillance activities that have not been possible. However, additional work is required to ensure LLMs can be used in a fair and equitable manner, minimize false positive findings, and support the necessary rigor of signal detection needed for regulatory activities.

Data-driven automated classification algorithms for acute health conditions: applying PheNorm to COVID-19 disease.

OBJECTIVES: Automated phenotyping algorithms can reduce development time and operator dependence compared to manually developed algorithms. One such approach, PheNorm, has performed well for identifying chronic health conditions, but its performance for acute conditions is largely unknown. Herein, we implement and evaluate PheNorm applied to symptomatic COVID-19 disease to investigate its potential feasibility for rapid phenotyping of acute health conditions. MATERIALS AND METHODS: PheNorm is a general-purpose automated approach to creating computable phenotype algorithms based on natural language processing, machine learning, and (low cost) silver-standard training labels. We applied PheNorm to cohorts of potential COVID-19 patients from 2 institutions and used gold-standard manual chart review data to investigate the impact on performance of alternative feature engineering options and implementing externally trained models without local retraining. RESULTS: Models at each institution achieved AUC, sensitivity, and positive predictive value of 0.853, 0.879, 0.851 and 0.804, 0.976, and 0.885, respectively, at quantiles of model-predicted risk that maximize F1. We report performance metrics for all combinations of silver labels, feature engineering options, and models trained internally versus externally. DISCUSSION: Phenotyping algorithms developed using PheNorm performed well at both institutions. Performance varied with different silver-standard labels and feature engineering options. Models developed locally at one site also worked well when implemented externally at the other site. CONCLUSION: PheNorm models successfully identified an acute health condition, symptomatic COVID-19. The simplicity of the PheNorm approach allows it to be applied at multiple study sites with substantially reduced overhead compared to traditional approaches.

Prognostic clinical decision support for pneumonia in the emergency department: A randomized trial.

BACKGROUND: Hospitalization rates for childhood pneumonia vary widely. Risk-based clinical decision support (CDS) interventions may reduce unwarranted variation. METHODS: We conducted a pragmatic randomized trial in two US pediatric emergency departments (EDs) comparing electronic health record (EHR)-integrated prognostic CDS versus usual care for promoting appropriate ED disposition in children (<18 years) with pneumonia. Encounters were randomized 1:1 to usual care versus custom CDS featuring a validated pneumonia severity score predicting risk for severe in-hospital outcomes. Clinicians retained full decision-making authority. The primary outcome was inappropriate ED disposition, defined as early transition to lower- or higher-level care. Safety and implementation outcomes were also evaluated. RESULTS: The study enrolled 536 encounters (269 usual care and 267 CDS). Baseline characteristics were similar across arms. Inappropriate disposition occurred in 3% of usual care encounters and 2% of CDS encounters (adjusted odds ratio: 0.99, 95% confidence interval: [0.32, 2.95]). Length of stay was also similar and adverse safety outcomes were uncommon in both arms. The tool's custom user interface and content were viewed as strengths by surveyed clinicians (>70% satisfied). Implementation barriers include intrinsic (e.g., reaching the right person at the right time) and extrinsic factors (i.e., global pandemic). CONCLUSIONS: EHR-based prognostic CDS did not improve ED disposition decisions for children with pneumonia. Although the intervention's content was favorably received, low subject accrual and workflow integration problems likely limited effectiveness. Clinical Trials Registration: NCT06033079.

A Proposed Approach to Allegations of Sexual Boundary Violation in Health Care.

BACKGROUND: Sexual boundary violations in the health care setting cause harm for victims, threaten an organization's culture, and create extraordinary organizational risk. The inherent complexities of health care organizations present unique challenges for the initial triage and response to reports of alleged violations. METHODS: A group of experts with experience in law, leadership, human resources, medicine, and health care operations identified processes for organizations to triage and implement an early response to allegations of sexual boundary violations. The group reviewed a series of 100 reports of alleged violations described by patients and coworkers from a 200-hospital professional accountability collaborative to identify the elements of an ideal initial triage and management approach. RESULTS: The group identified three domains to guide early triage and response to reports of boundary violations: (1) severity and acuity of the alleged violation; (2) roles and relationship(s) of the complainant, respondent, and other affected individuals; and (3) contextual information such as prior activity or other mitigating factors. The group identified leadership engagement; coordinated responses; clear articulation of values, policies, and procedures; aligned data reporting; thoughtful reviews; and securing appropriate resources as essential elements of an organization's response. CONCLUSION: A structured systematic approach to classify and respond to allegations of sexual boundary violation is described. The initial response should be guided by assessment of the severity and timing of the reported behavior, followed by assessment of roles and responsibilities with involvement of all relevant stakeholders. Contextual issues and special circumstances of relevance should be identified and incorporated into the response. Systems to identify, store, and retrieve behavior of concern should be improved and integrated.

Use of Electronic Health Record Data for Drug Safety Signal Identification: A Scoping Review.

INTRODUCTION: Pharmacovigilance programs protect patient health and safety by identifying adverse event signals through postmarketing surveillance of claims data and spontaneous reports. Electronic health records (EHRs) provide new opportunities to address limitations of traditional approaches and promote discovery-oriented pharmacovigilance. METHODS: To evaluate the current state of EHR-based medication safety signal identification, we conducted a scoping literature review of studies aimed at identifying safety signals from routinely collected patient-level EHR data. We extracted information on study design, EHR data elements utilized, analytic methods employed, drugs and outcomes evaluated, and key statistical and data analysis choices. RESULTS: We identified 81 eligible studies. Disproportionality methods were the predominant analytic approach, followed by data mining and regression. Variability in study design makes direct comparisons difficult. Studies varied widely in terms of data, confounding adjustment, and statistical considerations. CONCLUSION: Despite broad interest in utilizing EHRs for safety signal identification, current efforts fail to leverage the full breadth and depth of available data or to rigorously control for confounding. The development of best practices and application of common data models would promote the expansion of EHR-based pharmacovigilance.

Antibiotic clinical decision support for pneumonia in the ED: A randomized trial.

BACKGROUND: Electronic health record-based clinical decision support (CDS) is a promising antibiotic stewardship strategy. Few studies have evaluated the effectiveness of antibiotic CDS in the pediatric emergency department (ED). OBJECTIVE: To compare the effectiveness of antibiotic CDS vs. usual care for promoting guideline-concordant antibiotic prescribing for pneumonia in the pediatric ED. DESIGN: Pragmatic randomized clinical trial. SETTING AND PARTICIPANTS: Encounters for children (6 months-18 years) with pneumonia presenting to two tertiary care children s hospital EDs in the United States. INTERVENTION: CDS or usual care was randomly assigned during 4-week periods within each site. The CDS intervention provided antibiotic recommendations tailored to each encounter and in accordance with national guidelines. MAIN OUTCOME AND MEASURES: The primary outcome was exclusive guideline-concordant antibiotic prescribing within the first 24 h of care. Safety outcomes included time to first antibiotic order, encounter length of stay, delayed intensive care, and 3- and 7-day revisits. RESULTS: 1027 encounters were included, encompassing 478 randomized to usual care and 549 to CDS. Exclusive guideline-concordant prescribing did not differ at 24 h (CDS, 51.7% vs. usual care, 53.3%; odds ratio [OR] 0.94 [95% confidence interval [CI]: 0.73, 1.20]). In pre-specified stratified analyses, CDS was associated with guideline-concordant prescribing among encounters discharged from the ED (74.9% vs. 66.0%; OR 1.53 [95% CI: 1.01, 2.33]), but not among hospitalized encounters. Mean time to first antibiotic was shorter in the CDS group (3.0 vs 3.4 h; p = .024). There were no differences in safety outcomes. CONCLUSIONS: Effectiveness of ED-based antibiotic CDS was greatest among those discharged from the ED. Longitudinal interventions designed to target both ED and inpatient clinicians and to address common implementation challenges may enhance the effectiveness of CDS as a stewardship tool.

Evaluation of the portability of computable phenotypes with natural language processing in the eMERGE network.

The electronic Medical Records and Genomics (eMERGE) Network assessed the feasibility of deploying portable phenotype rule-based algorithms with natural language processing (NLP) components added to improve performance of existing algorithms using electronic health records (EHRs). Based on scientific merit and predicted difficulty, eMERGE selected six existing phenotypes to enhance with NLP. We assessed performance, portability, and ease of use. We summarized lessons learned by: (1) challenges; (2) best practices to address challenges based on existing evidence and/or eMERGE experience; and (3) opportunities for future research. Adding NLP resulted in improved, or the same, precision and/or recall for all but one algorithm. Portability, phenotyping workflow/process, and technology were major themes. With NLP, development and validation took longer. Besides portability of NLP technology and algorithm replicability, factors to ensure success include privacy protection, technical infrastructure setup, intellectual property agreement, and efficient communication. Workflow improvements can improve communication and reduce implementation time. NLP performance varied mainly due to clinical document heterogeneity; therefore, we suggest using semi-structured notes, comprehensive documentation, and customization options. NLP portability is possible with improved phenotype algorithm performance, but careful planning and architecture of the algorithms is essential to support local customizations.

Do electronic health record systems "dumb down" clinicians?

A panel sponsored by the American College of Medical Informatics (ACMI) at the 2021 AMIA Symposium addressed the provocative question: "Are Electronic Health Records dumbing down clinicians?" After reviewing electronic health record (EHR) development and evolution, the panel discussed how EHR use can impair care delivery. Both suboptimal functionality during EHR use and longer-term effects outside of EHR use can reduce clinicians' efficiencies, reasoning abilities, and knowledge. Panel members explored potential solutions to problems discussed. Progress will require significant engagement from clinician-users, educators, health systems, commercial vendors, regulators, and policy makers. Future EHR systems must become more user-focused and scalable and enable providers to work smarter to deliver improved care.