Liu, Hongfang

Introduction: Proton pump inhibitors (PPIs) are used by an estimated 29 million Americans. PPIs increase the levels of asymmetrical dimethylarginine, a known risk factor for cardiovascular disease (CVD). Data from a select population of patients with CVD suggest that PPI use is associated with an increased risk of stroke, heart failure, and coronary heart disease. The impact of PPI use on incident CVD is largely unknown in the general population. Hypothesis: We hypothesized that PPI users have a higher risk of incident total CVD, coronary heart disease, stroke, and heart failure compared to nonusers. To demonstrate specificity of association, we additionally hypothesized that there is not an association between use of H 2 -blockers - another commonly used class of medications with similar indications as PPIs - and CVD. Methods: We used the Rochester Epidemiology Project’s medical records-linkage system to identify all residents of Olmsted County, MN on our baseline date of January 1, 2004 (N=140217). We excluded persons who did not grant permission for their records to be used for research, were <18 years old, had a history of CVD, had missing data for any variable included in our model, or had evidence of PPI use within the previous year.We followed our final cohort (N=58175) for up to 12 years. The administrative censoring date for CVD was 1/20/2014, for coronary heart disease was 8/3/2016, for stroke was 9/9/2016, and for heart failure was 1/20/2014. Time-varying PPI ever-use was ascertained using 1) natural language processing to capture unstructured text from the electronic health record, and 2) outpatient prescriptions. An incident CVD event was defined as the first occurrence of 1) validated heart failure, 2) validated coronary heart disease, or 3) stroke, defined using diagnostic codes only. As a secondary analysis, we calculated the association between time-varying H 2 -blocker ever-use and CVD among persons not using H 2 -blockers at baseline. Results: After adjustment for age, sex, race, education, hypertension, hyperlipidemia, diabetes, and body-mass-index, PPI use was associated with an approximately 50% higher risk of CVD (hazard ratio [95% CI]: 1.51 [1.37-1.67]; 2187 CVD events), stroke (hazard ratio [95% CI]: 1.49 [1.35-1.65]; 1928 stroke events), and heart failure (hazard ratio [95% CI]: 1.56 [1.23-1.97]; 353 heart failure events) compared to nonusers. Users of PPIs had a 35% greater risk of coronary heart disease than nonusers (95% CI: 1.13-1.61; 626 coronary heart disease events). Use of H 2 -blockers was also associated with a higher risk of CVD (adjusted hazard ratio [95% CI]: 1.23 [1.08-1.41]; 2331 CVD events). Conclusions: PPI use is associated with a higher risk of CVD, coronary heart disease, stroke and heart failure. Use of a drug with no known cardiac toxicity - H 2 -blockers - was also associated with a greater risk of CVD, warranting further study.

Background: Real world studies of silent brain infarction (SBI) and white matter disease (WMD) are impeded by challenges in cohort identification. Natural language processing (NLP) from imaging reports may facilitate future studies. However, electronic health records can be heterogeneous and the process of interpreting neuroimages and generating reports can vary. Understanding knowledge representation and relationships between neuroimages and imaging reports is crucial for using NLP to facilitate disease management and cohort identification. Methods: A balanced sample of head neuroimages (CT, MRI) of patients >50 years without clinical histories of symptomatic stroke, TIA, or dementia were obtained at Mayo Clinic and Tufts Medical Center. A team of 4 radiology residents performed report interpretation (RI) on 1000 reports according to a standardized protocol for the presence of SBIs, the presence of WMD, and WMD grade. A random subsample of 400 was doubly read for interrater reliability. For benchmarking, a team of 4 neuroradiologists directly reviewed and described findings on a subsample of 182 images, each doubly read. We assessed interrater reliability for direct review (DR) and RI, and agreement between these 2 information sources. An NLP algorithm was developed to review and extract findings from 1000 imaging reports. Results: For DR, interrater reliability was moderate for SBIs and WMD (k = 0.53, 95% CI 0.43-0.64 and k = 0.47, 95% CI 0.33-0.61) and good for WMD grade (Spearman 0.71, p<0.001). For RI, interrater reliability for SBIs, WMD and WMD grade was good (k = 0.88, 95% CI 0.80-0.97; k = 0.98, 95% CI 0.97-1.00; and Spearman = 0.985, p<0.001, respectively). Agreement between DR and RI was good for SBIs (k = 0.77, 95% CI 0.67-0.86) and WMD (k = 0.65, 95% CI 0.54-0.77). Spearman rank correlations comparing WMD grade interpretation DR to RI was 0.60 (p<0.001). In identifying the presence of SBIs and WMDs, the accuracy of the NLP algorithm was 0.991 and 0.994, respectively. Conclusion: For the presence of SBI and WMD, and WMD grade, agreement between RI and DR was similar to agreement between 2 neuroradiologists directly reviewing neuroimages. It is highly feasible to use NLP to identify patients with SBIs and WMDs for clinical studies.

Background . Patients increasingly use asynchronous communication platforms to converse with care teams. Natural language processing (NLP) to classify content and automate triage of these messages has great potential to enhance clinical efficiency. We characterize the contents of a corpus of portal messages generated by patients using NLP methods. We aim to demonstrate descriptive analyses of patient text that can contribute to the development of future sophisticated NLP applications. Methods . We collected approximately 3,000 portal messages from the cardiology, dermatology, and gastroenterology departments at Mayo Clinic. After labeling these messages as either Active Symptom, Logistical, Prescription, or Update, we used NER (named entity recognition) to identify medical concepts based on the UMLS library. We hierarchically analyzed the distribution of these messages in terms of departments, message types, medical concepts, and keywords therewithin. Results . Active Symptom and Logistical content types comprised approximately 67% of the message cohort. The “Findings” medical concept had the largest number of keywords across all groupings of content types and departments. “Anatomical Sites” and “Disorders” keywords were more prevalent in Active Symptom messages, while “Drugs” keywords were most prevalent in Prescription messages. Logistical messages tended to have the lower proportions of “Anatomical Sites,”, “Disorders,”, “Drugs,”, and “Findings” keywords when compared to other message content types. Conclusions . This descriptive corpus analysis sheds light on the content and foci of portal messages. The insight into the content and differences among message themes can inform the development of more robust NLP models.

Abstract Objective : Developing clinical natural language processing systems often requires access to many clinical documents, which are not widely available to the public due to privacy and security concerns. To address this challenge, we propose to develop methods to generate synthetic clinical notes and evaluate their utility in real clinical natural language processing tasks. Materials and Methods : We implemented 4 state-of-the-art text generation models, namely CharRNN, SegGAN, GPT-2, and CTRL, to generate clinical text for the History and Present Illness section. We then manually annotated clinical entities for randomly selected 500 History and Present Illness notes generated from the best-performing algorithm. To compare the utility of natural and synthetic corpora, we trained named entity recognition (NER) models from all 3 corpora and evaluated their performance on 2 independent natural corpora. Results : Our evaluation shows GPT-2 achieved the best BLEU (bilingual evaluation understudy) score (with a BLEU-2 of 0.92). NER models trained on synthetic corpus generated by GPT-2 showed slightly better performance on 2 independent corpora: strict F1 scores of 0.709 and 0.748, respectively, when compared with the NER models trained on natural corpus (F1 scores of 0.706 and 0.737, respectively), indicating the good utility of synthetic corpora in clinical NER model development. In addition, we also demonstrated that an augmented method that combines both natural and synthetic corpora achieved better performance than that uses the natural corpus only. Conclusions : Recent advances in text generation have made it possible to generate synthetic clinical notes that could be useful for training NER models for information extraction from natural clinical notes, thus lowering the privacy concern and increasing data availability. Further investigation is needed to apply this technology to practice.

Background: White matter disease (WMD) and silent brain infarction (SBI) are known to be risk markers for stroke. Nevertheless, the predictive value of these changes when seen incidentally on routinely-obtained neuroimages is unknown. Methods: In this retrospective cohort study, Kaiser Permanente-Southern California health plan enrollees aged ≥ 50 years old with a brain CT or MRI scan between 2009-2019 and without a prior history of ischemic stroke, transient ischemic attack, or dementia were identified. Natural language processing (NLP) was used to identify patients with SBI and WMD on the index neuroimaging report. We used Cox proportional hazards to estimate the risk of future ischemic stroke associated with the presence of SBI and of WMD, controlling for major stroke risk factors. Results: Among 262,875 individuals receiving brain neuroimaging, 13,154 (5.0%) and 78,330 (29.8%) had SBI and WMD, respectively. The Table below summarizes the crude stroke incidence rates. The crude hazard ratio (HR) was 3.40 (95% CI 3.25-3.56) for SBI and 2.63 (95% CI 2.54-2.71) for WMD. In the multivariable model controlling for all major stroke risk factors, the effect of SBI was found to be stronger in younger versus older patients and for MRI- versus CT-discovered lesions. With MRI, the average adjusted HR over time was 2.95 (95% CI 2.53-3.44) for those < age 65 and 2.15 (95% CI 1.91-2.41) for those ≥ age 65. With CT scan, the average adjusted HR over time was 2.48 (95%CI 2.19-2.81) for those < age 65 and 1.81 (95% CI 1.71-1.91) for those ≥ age 65. The adjusted HR associated with a finding of WMD was 1.76 (95% CI 1.69-1.82) and was not modified by age or imaging modality. The effect of SBI decreased gradually over time, while the effect of WMD remained constant. Conclusion: Incidentally-discovered SBI and WMD are common in patients ≥ age 50 and are associated with substantial increases in the risk of subsequent symptomatic stroke. The findings may represent an opportunity for stroke prevention.

Background: White matter disease (WMD) and silent brain infarction (SBI) are known to be risk markers for dementia. Nevertheless, the effects of incidentally-discovered WMD and SBI on routinely-obtained neuroimages is unknown. Methods: In the retrospective cohort study, Kaiser Permanente-Southern California (KPSC) health plan enrollees aged ≥ 50 years old with a brain cross-sectional image (CT or MRI) between 2009-2019 and without a prior history of ischemic stroke, transient ischemic attack, or dementia were identified. Natural language processing (NLP) was used to identify patients with SBI and WMD on the first qualifying neuroimaging report. Cox proportional hazards regression model was applied to estimate the effects of WMD and SBI on dementia, controlling for major cardiovascular risk factors. Results: Among 262,875 individuals receiving brain neuroimaging, 13,154 (5.0%) and 78,330 (29.8%) had SBI and WMD, respectively. The table below summarizes the crude dementia incidence rates. The crude hazard ratio (HR) was 3.69 (95% CI 3.58-3.80) for WMD and 2.80 (95% CI 2.68-2.93) for SBI. In the multivariable model controlling for all major cardiovascular risk factors, the effect of WMD on dementia risk was found to be stronger in younger compared to older patients and for CT- compared to MRI-discovered lesions. With CT, the adjusted HR was 3.08 (95% CI 2.84-3.34) for those < age 70 and 1.90 (95% CI 1.83-1.97) for those ≥ age 70. With MRI, the adjusted HR was 2.58 (95% CI 2.31-2.87) for those < age 70 and 1.59 (95% CI 1.45-1.75) for those ≥ age 70. The adjusted HR associated with a finding of SBI was 2.01 (95% CI 1.78-2.32) for patients age <70 and 1.26 (95% CI 1.20-1.32) for patients age ≥70, and was not modified by imaging modality. Conclusion: Incidentally-discovered WMD and SBI are common in patients ≥ age 50 and are associated with substantial increase in the risk of subsequent dementia. The findings may represent an opportunity for dementia prevention.

Introduction: Silent brain infarcts (SBIs) and white matter disease (WMD) are highly prevalent and associated with increased risk of ischemic stroke in patients with traditional stroke risk factors (RFs) in prospective cohort studies. Their frequency and associations with stroke RFs have not been well described in real world populations. Methods: This was a cross-sectional study of patients age ≥ 50 in the Kaiser Permanente-Southern California (KPSC) health system between 2009-2019 with a head CT or MRI for non-stroke indications and no history of ischemic stroke, transient ischemic attack, or dementia. A natural language processing (NLP) algorithm developed at Mayo Clinic and Tufts Medical Center was applied to the KPSC EHR to identify individuals with reported SBIs or WMD. Multivariable Poisson regression with robust error variance was used to estimate risk ratios of demographics, stroke RFs (from the Framingham Stroke Risk Score), and scan modality on the presence of SBIs or WMD. Results: Among 262,875 individuals, the NLP identified 13,154 (5.0%) with SBIs and 78,330 (29.8%) with WMD. Stroke RFs were highly prevalent in this cohort. The majority underwent CTs (74.8%) instead of MRIs as their initial neuroimaging. After adjustment for demographics and RFs, advanced age demonstrated a strong association with increased risk of SBIs and WMD (table). MRI was associated with a reduced risk of reported SBIs (ARR: 0.87, 95% CI 0.83-0.91) and an increased risk of reported WMD (ARR 2.86, 95% CI 2.83-2.90). Despite being prevalent, traditional stroke RFs had weak associations with increased risk of SBIs or increased risk of WMD. Conclusions: Advanced age is strongly associated with incidentally discovered SBIs and WMD on neuroimaging studies obtained in routine care. The development of SBIs and WMD may not be fully attributable to traditional stroke RFs.

335 Background: Systematic reviews are outdated quickly when the evidence is rapidly evolving as the process is laborious and there is little incentive for primary author team of an index SRMA to update the evidence. Consequently, there is an epidemic of redundant SRMAs performed by different teams—sometimes with conflicted results—for treatment of first line mRCC. Methods: We have created a living, interactive systematic review (LISR)and network meta-analysis(LINMA) for the treatment of first line mRCC using an Artificial intelligence (AI) assisted framework for evidence synthesis (Living, Interactive evidence synthesis framework) (LIvE) . The framework is implemented in five-layered architecture (application layer, shared module layer, core service layer, middleware layer, and storage layer) which work together to automate the identification of new studies and analysis and semi-automate the screening and data extraction. Dynamic features such as interactive tables, figures and evidence maps are enabled using Python and JavaScript programming languages. Results: We have maintained a living, interactive evidence profile for the first line treatment mRCC since September 2019 ( LIVING WEBSITE) . Living search strategy identifies new studies as they become available. As of October 13, 2020 LISR, includes data 14 clinical trials ( PRISMA ). Baseline characteristics are summarized in an interactive table ( TABLE) . Cabozantinib& Nivolumab (Cabo-Nivo) is the highest ranked drug for improving Overall Response (OR), Progression Free Survival (PFS) and Overall Survival (OS) whereas Ipilimumab in combination with Nivolumab (Ipi-Nivo) is highest ranked drug for achieving complete response (CR). Ipi-Nivo and Atezolizumab & Bevacizumab (Ate-Bev) ranked highest and Cabo-Nivo ranked lowest for treatment related Adverse events (TRAEs). Results of network meta-analysis are summarized as interactive tables and plots ( NMA ), summary of findings tables ( MULTIPLE COMAPRISONS ) and evidence maps ( MAP ). Conclusions: LISRs can potentially reduce redundancy, increase transparency, reproducibility, enable shared-decision making (at a guideline level, or in a patient-clinician dyad) and support living guidelines.

Abstract Background: DNIV accounts for 6%–10% of newly diagnosed breast cancer cases. Despite widespread mammography screening, its incidence is increasing in the United States and survival of this disease has only modestly improved since the late 1970s. As patient data accumulates in EHR, it’s promising to generate practice-based evidence through utilization of observational data sources. However, assembly of a DNIV cohort based on EHR data is challenging, as key pathologic and staging information are stored in unstructured clinical narratives and not available as structured data. In this study, we developed a rule-based algorithm to phenotype DNIV using natural language processing (NLP) techniques, and implemented the algorithm on our institutional EHR to extract potential DNIV cases. Methods and Results: We defined DNIV as those with either (1) M1 disease identified at time of initial presentation or M1 disease identified within 4 months after definitive surgery. We first developed a reference case list of DNIV verified by physician chart review of the EHR. We next refined the algorithm on a training dataset containing 51 positive and 38 negative reference cases. Next we tested the performance on the testing data containing 23 positive and 55 negative cases. The phenotyping algorithm identified key data elements using NLP, i.e., stage IV breast cancer, definitive surgery, stage 0-III, recurrent breast cancer and associated dates. To identify DNIV cases, phenotyping algorithm integrated temporal relations among the key data elements. The following steps were conducted in the following sequential order: (1) Identification of patients with breast cancer diagnosis using ICD-9 and ICD-10 codes. (2) Patients are positive cases if there are explicit mentions that delineate DNIV from recurrent metastatic breast cancer, such as “de novo stage IV” or “primary intact” detected by NLP at time of diagnosis. (3) Otherwise, patients with definitive surgery are selected if stage IV was within 5 years before definitive surgery or within 4 months after definitive surgery, along with patients with stage IV but without definitive surgery. (4) We further excluded patients with stage 0-III detected within 5 years after stage IV. (5) We further excluded patients with recurrent breast cancer detected before or at time of detection of stage IV. The remaining patients were left as positive cases. Precision of the algorithm was 70%, recall was 87% and F1, the weighted average of precision and recall, was 77%. We implemented our algorithm to interrogate 10 million clinical documents in a cohort of 56,548 patients with breast cancer diagnosis codes who presented to our institution between 2004 and 2018 and had research authorization. We identified 1918 potential DNIV cases. Conclusion: Our future focus is on algorithm refinement. An algorithm-generated cohort could serve as a data source for further study on outcomes related to DNIV and ideally as automated data abstractor and staging process. Citation Format: Liwei Wang, Karthik Giridhar, Kimberly Corbin, Brenda Ernst, Sadia Choudhery, Emmanuel Gabriel, Feichen Shen, Hongfang Liu, James Jakub. Identifying de novo stage IV breast cancer (DNIV) cases in Electronic Health Records (EHR) using natural language processing [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-050.