Deep learning for identifying personal and family history of suicidal thoughts and behaviors from EHRs.

Personal and family history of suicidal thoughts and behaviors (PSH and FSH, respectively) are significant risk factors associated with suicides. Research is limited in automatic identification of such data from clinical notes in Electronic Health Records. This study developed deep learning (DL) tools utilizing transformer models (Bio_ClinicalBERT and GatorTron) to detect PSH and FSH in clinical notes derived from three academic medical centers, and compared their performance with a rule-based natural language processing tool. For detecting PSH, the rule-based approach obtained an F1-score of 0.75 ± 0.07, while the Bio_ClinicalBERT and GatorTron DL tools scored 0.83 ± 0.09 and 0.84 ± 0.07, respectively. For detecting FSH, the rule-based approach achieved an F1-score of 0.69 ± 0.11, compared to 0.89 ± 0.10 for Bio_ClinicalBERT and 0.92 ± 0.07 for GatorTron. Across sites, the DL tools identified more than 80% of patients at elevated risk for suicide who remain undiagnosed and untreated.

Community-Based Participatory Research and System Dynamics Modeling for Improving Retention in Hypertension Care.

Importance: The high prevalence of hypertension calls for broad, multisector responses that foster prevention and care services, with the goal of leveraging high-quality treatment as a means of reducing hypertension incidence. Health care system improvements require stakeholder input from across the care continuum to identify gaps and inform interventions that improve hypertension care service, delivery, and retention; system dynamics modeling offers a participatory research approach through which stakeholders learn about system complexity and ways to model sustainable system-level improvements. Objective: To assess the association of simulated interventions with hypertension care retention rates in the Nigerian primary health care system using system dynamics modeling. Design, Setting, and Participants: This decision analytical model used a participatory research approach involving stakeholder workshops conducted in July and October 2022 to gather insights and inform the development of a system dynamics model designed to simulate the association of various interventions with retention in hypertension care. The study focused on the primary health care system in Nigeria, engaging stakeholders from various sectors involved in hypertension care, including patients, community health extension workers, nurses, pharmacists, researchers, administrators, policymakers, and physicians. Exposure: Simulated intervention packages. Main Outcomes and Measures: Retention rate in hypertension care at 12, 24, and 36 months, modeled to estimate the effectiveness of the interventions. Results: A total of 16 stakeholders participated in the workshops (mean [SD] age, 46.5 [8.6] years; 9 [56.3%] male). Training of health care workers was estimated to be the most effective single implementation strategy for improving retention in hypertension care in Nigeria, with estimated retention rates of 29.7% (95% CI, 27.8%-31.2%) at 12 months and 27.1% (95% CI, 26.0%-28.3%) at 24 months. Integrated intervention packages were associated with the greatest improvements in hypertension care retention overall, with modeled retention rates of 72.4% (95% CI, 68.4%-76.4%), 68.1% (95% CI, 64.5%-71.7%), and 67.1% (95% CI, 64.5%-71.1%) at 12, 24, and 36 months, respectively. Conclusions and Relevance: This decision analytical model study showed that community-based participatory research could be used to estimate the potential effectiveness of interventions for improving retention in hypertension care. Integrated intervention packages may be the most promising strategies.

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.

Multiplicative Impact of Adverse Social Determinants of Health on Outcomes in Lupus Nephritis: A Meta-analysis and Systematic Review.

OBJECTIVE: Social determinants of health (SDoH) likely contribute to outcome disparities in lupus nephritis (LN). Understanding the overall burden and contribution of each domain could guide future health equity-focused interventions to improve outcomes and reduce disparities in LN. Objectives of this meta-analysis were to 1) determine the association of overall SDoH and specific SDoH domains on LN outcomes and 2) develop a framework for the multidimensional impact of SDoH on LN outcomes. METHODS: We performed a comprehensive search of studies measuring associations between SDoH and LN outcomes. We examined pooled odds of poor LN outcomes including death, end-stage kidney disease, or cardiovascular disease in patients with and without adverse SDoH. Additionally, we calculated the pooled odds ratios of outcomes by four SDoH domains: individual (eg, insurance), health care (eg, fragmented care), community (eg, neighborhood socioeconomic status), and health behaviors (eg, smoking). RESULTS: Among 531 screened studies, 31 meeting inclusion criteria and 13 with raw data were included in meta-analysis. Pooled odds of poor outcomes were 1.47-fold higher in patients with any adverse SDoH. Patients with adverse SDoH in individual and health care domains had 1.64-fold and 1.77-fold higher odds of poor outcomes. We found a multiplicative impact of having two or more adverse SDoH on LN outcomes. Black patients with public insurance and fragmented care had 12-fold higher odds of poor LN outcomes. CONCLUSION: Adverse SDoH is associated with poor LN outcomes. Having two or more adverse SDoH, specifically in different SDoH domains, had a multiplicative impact leading to worse LN outcomes, widening disparities.

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.

Detection of Personal and Family History of Suicidal Thoughts and Behaviors using Deep Learning and Natural Language Processing: A Multi-Site Study.

Objective: Personal and family history of suicidal thoughts and behaviors (PSH and FSH, respectively) are significant risk factors associated with future suicide events. These are often captured in narrative clinical notes in electronic health records (EHRs). Collaboratively, Weill Cornell Medicine (WCM), Northwestern Medicine (NM), and the University of Florida (UF) developed and validated deep learning (DL)-based natural language processing (NLP) tools to detect PSH and FSH from such notes. The tool's performance was further benchmarked against a method relying exclusively on ICD-9/10 diagnosis codes. Materials and Methods: We developed DL-based NLP tools utilizing pre-trained transformer models Bio_ClinicalBERT and GatorTron, and compared them with expert-informed, rule-based methods. The tools were initially developed and validated using manually annotated clinical notes at WCM. Their portability and performance were further evaluated using clinical notes at NM and UF. Results: The DL tools outperformed the rule-based NLP tool in identifying PSH and FHS. For detecting PSH, the rule-based system obtained an F1-score of 0.75 ± 0.07, while the Bio_ClinicalBERT and GatorTron DL tools scored 0.83 ± 0.09 and 0.84 ± 0.07, respectively. For detecting FSH, the rule-based NLP tool's F1-score was 0.69 ± 0.11, compared to 0.89 ± 0.10 for Bio_ClinicalBERT and 0.92 ± 0.07 for GatorTron. For the gold standard corpora across the three sites, only 2.2% (WCM), 9.3% (NM), and 7.8% (UF) of patients reported to have an ICD-9/10 diagnosis code for suicidal thoughts and behaviors prior to the clinical notes report date. The best performing GatorTron DL tool identified 93.0% (WCM), 80.4% (NM), and 89.0% (UF) of patients with documented PSH, and 85.0%(WCM), 89.5%(NM), and 100%(UF) of patients with documented FSH in their notes. Discussion: While PSH and FSH are significant risk factors for future suicide events, little effort has been made previously to identify individuals with these history. To address this, we developed a transformer based DL method and compared with conventional rule-based NLP approach. The varying effectiveness of the rule-based tools across sites suggests a need for improvement in its dictionary-based approach. In contrast, the performances of the DL tools were higher and comparable across sites. Furthermore, DL tools were fine-tuned using only small number of annotated notes at each site, underscores its greater adaptability to local documentation practices and lexical variations. Conclusion: Variations in local documentation practices across health care systems pose challenges to rule-based NLP tools. In contrast, the developed DL tools can effectively extract PSH and FSH information from unstructured clinical notes. These tools will provide clinicians with crucial information for assessing and treating patients at elevated risk for suicide who are rarely been diagnosed.

Age-stratified comorbid and pharmacologic analysis of patients with glioblastoma.

Background: Increased age is a strong and unfavorable prognostic factor for patients with glioblastoma (GBM). However, the relationships between stratified patient age, comorbidities, and medications have yet to be explored in GBM patient survival analyses. Objective: To evaluate co-morbid conditions, tumor-related symptoms, medication prescriptions, and subject age for patients with GBM and to establish potential targets for prospective studies. Methods: Electronic health records for 565 patients with IDHwt GBM were evaluated at a single center between January 1, 2000 and August 9, 2021 were retrospectively assessed. Data were stratified by MGMT promoter methylation status when available and were used to construct multivariable time-dependent cox models and intra-cohort hazards. Results: Younger (<65 years of age) but not older (≥65 years) GBM patients demonstrated a worse prognosis with movement related disabilities (P < 0.0001), gait/balance difficulty (P = 0.04) and weakness (P = 0.007), as well as psychiatric conditions, mental health disorders (P = 0.002) and anxiety (P = 0.001). In contrast, older but not younger GBM patients demonstrated a worse prognosis with epilepsy (P = 0.039). Both groups had worse survival with confusion/altered mental status (P = 0.023 vs < 0.000) and an improved survival with a Temozolomide prescription. Older but not younger GBM patients experienced an improved hazard with a prescription of ace-inhibitor medications (P = 0.048). Conclusion: Age-dependent novel associations between clinical symptoms and medications prescribed for co-morbid conditions were demonstrated in patients with GBM. The results of the current work support future mechanistic studies that investigate the negative relationship(s) between increased age, comorbidities, and drug therapies for differential clinical decision-making across the lifespan of patients with GBM.

Clinical associations with a polygenic predisposition to benign lower white blood cell counts.

Polygenic variation unrelated to disease contributes to interindividual variation in baseline white blood cell (WBC) counts, but its clinical significance is uncharacterized. We investigated the clinical consequences of a genetic predisposition toward lower WBC counts among 89,559 biobank participants from tertiary care centers using a polygenic score for WBC count (PGSWBC) comprising single nucleotide polymorphisms not associated with disease. A predisposition to lower WBC counts was associated with a decreased risk of identifying pathology on a bone marrow biopsy performed for a low WBC count (odds-ratio = 0.55 per standard deviation increase in PGSWBC [95%CI, 0.30-0.94], p = 0.04), an increased risk of leukopenia (a low WBC count) when treated with a chemotherapeutic (n = 1724, hazard ratio [HR] = 0.78 [0.69-0.88], p = 4.0 × 10-5) or immunosuppressant (n = 354, HR = 0.61 [0.38-0.99], p = 0.04). A predisposition to benign lower WBC counts was associated with an increased risk of discontinuing azathioprine treatment (n = 1,466, HR = 0.62 [0.44-0.87], p = 0.006). Collectively, these findings suggest that there are genetically predisposed individuals who are susceptible to escalations or alterations in clinical care that may be harmful or of little benefit.

Risk factors affecting polygenic score performance across diverse cohorts.

Apart from ancestry, personal or environmental covariates may contribute to differences in polygenic score (PGS) performance. We analyzed effects of covariate stratification and interaction on body mass index (BMI) PGS (PGSBMI) across four cohorts of European (N=491,111) and African (N=21,612) ancestry. Stratifying on binary covariates and quintiles for continuous covariates, 18/62 covariates had significant and replicable R2 differences among strata. Covariates with the largest differences included age, sex, blood lipids, physical activity, and alcohol consumption, with R2 being nearly double between best and worst performing quintiles for certain covariates. 28 covariates had significant PGSBMI-covariate interaction effects, modifying PGSBMI effects by nearly 20% per standard deviation change. We observed overlap between covariates that had significant R2 differences among strata and interaction effects - across all covariates, their main effects on BMI were correlated with their maximum R2 differences and interaction effects (0.56 and 0.58, respectively), suggesting high-PGSBMI individuals have highest R2 and increase in PGS effect. Using quantile regression, we show the effect of PGSBMI increases as BMI itself increases, and that these differences in effects are directly related to differences in R2 when stratifying by different covariates. Given significant and replicable evidence for context-specific PGSBMI performance and effects, we investigated ways to increase model performance taking into account non-linear effects. Machine learning models (neural networks) increased relative model R2 (mean 23%) across datasets. Finally, creating PGSBMI directly from GxAge GWAS effects increased relative R2 by 7.8%. These results demonstrate that certain covariates, especially those most associated with BMI, significantly affect both PGSBMI performance and effects across diverse cohorts and ancestries, and we provide avenues to improve model performance that consider these effects.

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.

Interventions and contextual factors to improve retention in care for patients with hypertension in primary care: Hermeneutic systematic review.

BACKGROUND: Regular engagement over time in hypertension care, or retention, is a crucial but understudied step in optimizing patient outcomes. This systematic review leverages a hermeneutic methodology to identify, evaluate, and quantify the effects of interventions and contextual factors for improving retention for patients with hypertension. METHODS: We searched for articles that were published between 2000 and 2022 from multiple electronic databases, including MEDLINE, EMBASE, Cochrane Central Register of Controlled Trials, clinicaltrials.gov, and WHO International Trials Registry. We followed the latest version of the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guideline to report the findings for this review. We also synthesized the findings using a hermeneutic methodology for systematic reviews, which used an iterative process to review, integrate, analyze, and interpret evidence. RESULTS: From 4686 screened titles and abstracts, 18 unique studies from 9 countries were identified, including 10 (56%) randomized controlled trials (RCTs), 3 (17%) cluster RCTs, and 5 (28%) non-RCT studies. The number of participants ranged from 76 to 1562. The overall mean age range was 41-67 years, and the proportion of female participants ranged from 0% to 100%. Most (n = 17, 94%) studies used non-physician personnel to implement the proposed interventions. Fourteen studies (78%) implemented multilevel combinations of interventions. Education and training, team-based care, consultation, and Short Message Service reminders were the most common interventions tested. CONCLUSIONS: This review presents the most comprehensive findings on retention in hypertension care to date and fills the gaps in the literature, including the effectiveness of interventions, their components, and contextual factors. Adaptation of and implementing HIV care models, such differentiated service delivery, may be more effective and merit further study. REGISTRATION: CRD42021291368. PROTOCOL REGISTRATION: PROSPERO 2021 CRD42021291368. Available at: https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=291368.

Identification and assessment of classification criteria attributes for systemic lupus erythematosus in a regional medical record data network.

OBJECTIVE: To assess the application and utility of algorithms designed to detect features of SLE in electronic health record (EHR) data in a multisite, urban data network. METHODS: Using the Chicago Area Patient-Centered Outcomes Research Network (CAPriCORN), a Clinical Data Research Network (CDRN) containing data from multiple healthcare sites, we identified patients with at least one positively identified criterion from three SLE classification criteria sets developed by the American College of Rheumatology (ACR) in 1997, the Systemic Lupus International Collaborating Clinics (SLICC) in 2012, and the European Alliance of Associations for Rheumatology and the ACR in 2019 using EHR-based algorithms. To measure the algorithms' performance in this data setting, we first evaluated whether the number of clinical encounters for SLE was associated with a greater quantity of positively identified criteria domains using Poisson regression. We next quantified the amount of SLE criteria identified at a single healthcare institution versus all sites to assess the amount of SLE-related information gained from implementing the algorithms in a CDRN. RESULTS: Patients with three or more SLE encounters were estimated to have documented 2.77 (2.73 to 2.80) times the number of positive SLE attributes from the 2012 SLICC criteria set than patients without an SLE encounter via Poisson regression. Patients with three or more SLE-related encounters and with documented care from multiple institutions were identified with more SLICC criteria domains when data were included from all CAPriCORN sites compared with a single site (p<0.05). CONCLUSIONS: The positive association observed between amount of SLE-related clinical encounters and the number of criteria domains detected suggests that the algorithms used in this study can be used to help describe SLE features in this data environment. This work also demonstrates the benefit of aggregating data across healthcare institutions for patients with fragmented care.

Rationale and design for Healthy Hearts for Michigan (HH4M): A pragmatic single-arm hybrid effectiveness-implementation study.

Background: The burden of cardiovascular disease (CVD) is particularly high in several US states, which include the state of Michigan. Hypertension and smoking are two major risk factors for mortality due to CVD. Rural Michigan is disproportionally affected by CVD and by primary care shortages. The Healthy Hearts for Michigan (HH4M) study aims to promote hypertension management and smoking cessation through practice facilitation and quality improvement efforts and is part of the multi-state EvidenceNOW: Building State Capacity initiative to provide external support to primary care practices to improve care delivery. Methods: Primary care practices in rural and underserved areas of Michigan were recruited to join HH4M, a pragmatic, single-arm hybrid Type 2 effectiveness-implementation study during which practice facilitation was delivered at the practice level for 12 months, followed by a 3-month maintenance period. Results: Fifty-four practices were enrolled over a 12-month recruitment period. At baseline, the mean proportion (standard deviation) of patients at the practice level meeting the clinical quality measures were: blood pressure, 0.72 (0.12); tobacco screening, 0.80 (0.30); tobacco cessation intervention, 0.57 (0.28); tobacco screening and cessation intervention: 0.78 (0.26). Conclusion: This three-year research program will evaluate the ability of rural and medically underserved primary care practices to implement the quality improvement model by identifying drivers of and barriers to sustainable implementation, and test whether the model improves (a) blood pressure control and (b) tobacco use screening and cessation.

Declining Participation in Primary Care Quality Improvement Research: A Qualitative Study.

PURPOSE: There are numerous supportive quality improvement (QI) projects to facilitate the implementation of evidence-based practices in primary care, but recruiting physician practices to join these projects is challenging, costly, and time consuming. We aimed to identify factors leading primary care practices to decline participation in QI projects, and strategies to improve the feasibility and attractiveness of QI projects in the future. METHODS: For this qualitative study, we contacted 109 representatives of practices that had declined participation in 1 of 4 Agency for Healthcare Research and Quality-funded EvidenceNOW projects. The representatives were invited to participate in a 15-minute interview or complete a 5-question questionnaire. Thematic analysis was used to organize and characterize findings. RESULTS: Representatives from 31 practices (28.4% of those contacted) responded. Overwhelmingly, respondents indicated that staff turnover, staffing shortages, and general time constraints, exacerbated by the pandemic, prevented participation in the QI projects. Challenges with electronic health records, an expectation of greater financial compensation for participation, and confidence in the practices' current care practices were secondary reasons for declining participation. Tying participation to value-based programs and offering greater compensation were identified as strategies to facilitate recruitment. None of the respondents' recommendations, however, addressed the primary issues of staffing challenges and time constraints. CONCLUSIONS: Staffing challenges and general time constraints, exacerbated by the pandemic, are compromising primary care practices' ability to engage in QI research projects. To encourage participation, policy makers should consider direct supports for primary care, which may also help to alleviate burnout.

Clinical consequences of a polygenic predisposition to benign lower white blood cell counts: Consequences of benign WBC count genetics.

Polygenic variation unrelated to disease contributes to interindividual variation in baseline white blood cell (WBC) counts, but its clinical significance is undefined. We investigated the clinical consequences of a genetic predisposition toward lower WBC counts among 89,559 biobank participants from tertiary care centers using a polygenic score for WBC count (PGSWBC) comprising single nucleotide polymorphisms not associated with disease. A predisposition to lower WBC counts was associated with a decreased risk of identifying pathology on a bone marrow biopsy performed for a low WBC count (odds-ratio=0.55 per standard deviation increase in PGSWBC [95%CI, 0.30 - 0.94], p=0.04), an increased risk of leukopenia (a low WBC count) when treated with a chemotherapeutic (n=1,724, hazard ratio [HR]=0.78 [0.69 - 0.88], p=4.0×10-5) or immunosuppressant (n=354, HR=0.61 [0.38 - 0.99], p=0.04). A predisposition to benign lower WBC counts was associated with an increased risk of discontinuing azathioprine treatment (n=1,466, HR=0.62 [0.44 - 0.87], p=0.006). Collectively, these findings suggest that a WBC count polygenic score identifies individuals who are susceptible to escalations or alterations in clinical care that may be harmful or of little benefit.

Advanced Age in Humans and Mouse Models of Glioblastoma Show Decreased Survival from Extratumoral Influence.

PURPOSE: Glioblastoma (GBM) is the most common aggressive primary malignant brain tumor in adults with a median age of onset of 68 to 70 years old. Although advanced age is often associated with poorer GBM patient survival, the predominant source(s) of maladaptive aging effects remains to be established. Here, we studied intratumoral and extratumoral relationships between adult patients with GBM and mice with brain tumors across the lifespan. EXPERIMENTAL DESIGN: Electronic health records at Northwestern Medicine and the NCI SEER databases were evaluated for GBM patient age and overall survival. The commercial Tempus and Caris databases, as well as The Cancer Genome Atlas were profiled for gene expression, DNA methylation, and mutational changes with varying GBM patient age. In addition, gene expression analysis was performed on the extratumoral brain of younger and older adult mice with or without a brain tumor. The survival of young and old wild-type or transgenic (INK-ATTAC) mice with a brain tumor was evaluated after treatment with or without senolytics and/or immunotherapy. RESULTS: Human patients with GBM ≥65 years of age had a significantly decreased survival compared with their younger counterparts. While the intra-GBM molecular profiles were similar between younger and older patients with GBM, non-tumor brain tissue had a significantly different gene expression profile between young and old mice with a brain tumor and the eradication of senescent cells improved immunotherapy-dependent survival of old but not young mice. CONCLUSIONS: This work suggests a potential benefit for combining senolytics with immunotherapy in older patients with GBM.

A metadata framework for computational phenotypes.

With the burgeoning development of computational phenotypes, it is increasingly difficult to identify the right phenotype for the right tasks. This study uses a mixed-methods approach to develop and evaluate a novel metadata framework for retrieval of and reusing computational phenotypes. Twenty active phenotyping researchers from 2 large research networks, Electronic Medical Records and Genomics and Observational Health Data Sciences and Informatics, were recruited to suggest metadata elements. Once consensus was reached on 39 metadata elements, 47 new researchers were surveyed to evaluate the utility of the metadata framework. The survey consisted of 5-Likert multiple-choice questions and open-ended questions. Two more researchers were asked to use the metadata framework to annotate 8 type-2 diabetes mellitus phenotypes. More than 90% of the survey respondents rated metadata elements regarding phenotype definition and validation methods and metrics positively with a score of 4 or 5. Both researchers completed annotation of each phenotype within 60 min. Our thematic analysis of the narrative feedback indicates that the metadata framework was effective in capturing rich and explicit descriptions and enabling the search for phenotypes, compliance with data standards, and comprehensive validation metrics. Current limitations were its complexity for data collection and the entailed human costs.

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.

An Approach to Evaluating Multisector Partnerships to Support Evidence-Based Quality Improvement in Primary Care.

BACKGROUND: Quality improvement (QI) interventions in primary care are increasingly designed and implemented by multisector partnerships, yet little guidance exists on how to best monitor or evaluate these partnerships. The goal of this project was to describe an approach for evaluating the development and effectiveness of a multisector partnership using data from the first year of the Healthy Hearts for Michigan (HH4M) Cooperative, a multisector partnership of nine organizations tasked with designing and implementing evidence-based QI strategies for hypertension management and tobacco cessation in 50 rural primary care practices. METHODS: The researchers developed a 49-item online survey focused on factors that facilitate or hinder multisector partnerships, drawing on implementation science and partnership, engagement, and collaboration research. The team surveyed all 44 members of the HH4M Cooperative (79.5% response rate) and conducted interviews with 14 members. The interviews focused on implementation phase-specific goals, accomplishments, and challenges. Descriptive analysis was used for the survey results, and thematic analysis for the interview data. RESULTS: Respondents reported strong overall performance by the Cooperative during its first year, which facilitated the successful completion of several intervention design tasks. Strengths included having a clear purpose and trust and respect among members. Areas for improvement included a need for common terminology, clarification of roles and functions, and improvement in communication across workgroups. Lack of engagement from physician practices due to capacity constraints, exacerbated by the COVID-19 pandemic, was the Cooperative's biggest challenge. CONCLUSION: This multimethod approach to evaluating the development and effectiveness of a multisector partnership yielded practical, actionable feedback to program leaders.