Liu, Hongfang

Background: Concerns for side-effects makes the identification of treatment targets of hypertension in the very elderly challenging. We sought to utilize natural language processing (NLP) to evaluate the prevalence of prespecified side-effects in a cohort of very elderly (≥80 years) patients. Methods and Results: We conducted a two-year, cross-sectional study involving 5169 very elderly patients with and without hypertension seen by primary or specialist providers. Hypertension patients had to have a prior hypertension ICD-9 code in the electronic medical records problem list and ≥2 office visits in 2008 and 2009. We used NLP to analyze extracted free text reports from last clinic visits between 2008 and 2009. Of the 10 prespecified side-effects, hypotension, fatigue, and dizziness were the commonest three conditions and hypotension was significantly higher in the HTN patients. Of the 2835 patients with no prior hypertension history and 2334 hypertension patients identified, the prevalence of each prespecified item in both groups were: acute renal failure (0.3% v 0.6%, p=0.13); syncope (2.8% v 2.2%, p = 0.17), dizziness (3.1% v 4.0%, p=0.09), history of fall (1.0% v 0.9%, p=0.65), fatigue (5.4% v 4.5%, p=0.19), femoral neck fracture (0.18% v 0.04%, p=0.16), palpitations (1.2% v 1.5%, p=0.35), hypotension (4.1% v 6.6%, p<0.001), hyperkalemia (1.1% v 1.7%, p=0.04), hypokalemia (0.4% v 0.9%, p=0.01). At least one presumed side-effect was present in 17.5% of all 5169 patients. Among hypertension patients, there was no significant difference in the prevalence of the side-effects among patients with BP above (578) or below 140/90 (1756) except for acute renal failure (1.21% vs 0.40%, p = 0.03). Conclusion: Analysis of free-text outpatient notes using NLP showed that hypotension and potassium abnormalities were significantly more prevalent in very elderly patients with hypertension compared to similarly aged patients with no hypertension history.

Background Inhaled corticosteroids (ICSs) are important in asthma management, but there are concerns regarding associated risk of pneumonia. While studies in asthmatic adults have shown inconsistent results, this risk in asthmatic children is unclear. Objective Our aim was to determine the association of ICS use with pneumonia risk in asthmatic children. Methods A nested case-control study was performed in the Mayo Clinic Birth Cohort. Asthmatic children (<18 years) with a physician diagnosis of asthma were identified from electronic medical records of children born at Mayo Clinic from 1997 to 2016 and followed until 31 December 2017. Pneumonia cases defined by Infectious Disease Society of America were 1:1 matched with controls without pneumonia by age, sex and asthma index date. Exposure was defined as ICS prescription at least 90 days prior to pneumonia. Associations of ICS use, type and dose (low, medium and high) with pneumonia risk were analysed using conditional logistic regression. Results Of the 2108 asthmatic children eligible for the study (70% mild intermittent and 30% persistent asthma), 312 children developed pneumonia during the study period. ICS use overall was not associated with risk of pneumonia (adjusted OR: 0.94, 95% CI: 0.62 to 1.41). Poorly controlled asthma was significantly associated with the risk of pneumonia (OR: 2.03, 95% CI: 1.35 to 3.05; p<0.001). No ICS type or dose was associated with risk of pneumonia. Conclusion ICS use in asthmatic children was not associated with risk of pneumonia but poorly controlled asthma was. Future asthma studies may need to include pneumonia as a potential outcome of asthma management.

Abstract Objective Accurate extraction of breast cancer patients’ phenotypes is important for clinical decision support and clinical research. This study developed and evaluated cancer domain pretrained CancerBERT models for extracting breast cancer phenotypes from clinical texts. We also investigated the effect of customized cancer-related vocabulary on the performance of CancerBERT models. Materials and Methods A cancer-related corpus of breast cancer patients was extracted from the electronic health records of a local hospital. We annotated named entities in 200 pathology reports and 50 clinical notes for 8 cancer phenotypes for fine-tuning and evaluation. We kept pretraining the BlueBERT model on the cancer corpus with expanded vocabularies (using both term frequency-based and manually reviewed methods) to obtain CancerBERT models. The CancerBERT models were evaluated and compared with other baseline models on the cancer phenotype extraction task. Results All CancerBERT models outperformed all other models on the cancer phenotyping NER task. Both CancerBERT models with customized vocabularies outperformed the CancerBERT with the original BERT vocabulary. The CancerBERT model with manually reviewed customized vocabulary achieved the best performance with macro F1 scores equal to 0.876 (95% CI, 0.873–0.879) and 0.904 (95% CI, 0.902–0.906) for exact match and lenient match, respectively. Conclusions The CancerBERT models were developed to extract the cancer phenotypes in clinical notes and pathology reports. The results validated that using customized vocabulary may further improve the performances of domain specific BERT models in clinical NLP tasks. The CancerBERT models developed in the study would further help clinical decision support.

AbstractPurposeRural populations are disproportionately affected by the COVID‐19 pandemic. We characterized urban‐rural disparities in patient portal messaging utilization for COVID‐19, and, of those who used the portal during its early stage in the Midwest.MethodsWe collected over 1 million portal messages generated by midwestern Mayo Clinic patients from February to August 2020. We analyzed patient‐generated messages (PGMs) on COVID‐19 by urban‐rural locality and incorporated patients’ sociodemographic factors into the analysis.FindingsThe urban‐rural ratio of portal users, message senders, and COVID‐19 message senders was 1.18, 1.31, and 1.79, indicating greater use among urban patients. The urban‐rural ratio (1.69) of PGMs on COVID‐19 was higher than that (1.43) of general PGMs. The urban‐rural ratios of messaging were 1.72‐1.85 for COVID‐19‐related care and 1.43‐1.66 for other health care issues on COVID‐19. Compared with urban patients, rural patients sent fewer messages for COVID‐19 diagnosis and treatment but more messages for other reasons related to COVID‐19‐related health care (eg, isolation and anxiety). The frequent senders of COVID‐19‐related messages among rural patients were 40+ years old, women, married, and White.ConclusionsIn this Midwest health system, rural patients were less likely to use patient online services during a pandemic and their reasons for its use differ from urban patients. Results suggest opportunities for increasing equity in rural patient engagement in patient portals (in particular, minority populations) for COVID‐19. Public health intervention strategies could target reasons why rural patients might seek health care in a pandemic, such as social isolation and anxiety.

AbstractSummaryBuilding a high-quality annotation corpus requires expenditure of considerable time and expertise, particularly for biomedical and clinical research applications. Most existing annotation tools provide many advanced features to cover a variety of needs where the installation, integration and difficulty of use present a significant burden for actual annotation tasks. Here, we present MedTator, a serverless annotation tool, aiming to provide an intuitive and interactive user interface that focuses on the core steps related to corpus annotation, such as document annotation, corpus summarization, annotation export and annotation adjudication.Availability and implementationMedTator and its tutorial are freely available from https://ohnlp.github.io/MedTator. MedTator source code is available under the Apache 2.0 license: https://github.com/OHNLP/MedTator.Supplementary informationSupplementary data are available at Bioinformatics online.

AbstractObjectiveWith COVID-19, there was a need for a rapidly scalable annotation system that facilitated real-time integration with clinical decision support systems (CDS). Current annotation systems suffer from a high-resource utilization and poor scalability limiting real-world integration with CDS. A potential solution to mitigate these issues is to use the rule-based gazetteer developed at our institution.Materials and MethodsPerformance, resource utilization, and runtime of the rule-based gazetteer were compared with five annotation systems: BioMedICUS, cTAKES, MetaMap, CLAMP, and MedTagger.ResultsThis rule-based gazetteer was the fastest, had a low resource footprint, and similar performance for weighted microaverage and macroaverage measures of precision, recall, and f1-score compared to other annotation systems.DiscussionOpportunities to increase its performance include fine-tuning lexical rules for symptom identification. Additionally, it could run on multiple compute nodes for faster runtime.ConclusionThis rule-based gazetteer overcame key technical limitations facilitating real-time symptomatology identification for COVID-19 and integration of unstructured data elements into our CDS. It is ideal for large-scale deployment across a wide variety of healthcare settings for surveillance of acute COVID-19 symptoms for integration into prognostic modeling. Such a system is currently being leveraged for monitoring of postacute sequelae of COVID-19 (PASC) progression in COVID-19 survivors. This study conducted the first in-depth analysis and developed a rule-based gazetteer for COVID-19 symptom extraction with the following key features: low processor and memory utilization, faster runtime, and similar weighted microaverage and macroaverage measures for precision, recall, and f1-score compared to industry-standard annotation systems.

AbstractIntroductionThe efficacy of cardiac resynchronization therapy (CRT) has been widely studied in the medical literature; however, about 30% of candidates fail to respond to this treatment strategy. Smart computational approaches based on clinical data can help expose hidden patterns useful for identifying CRT responders.MethodsWe retrospectively analyzed the electronic health records of 1664 patients who underwent CRT procedures from January 1, 2002 to December 31, 2017. An ensemble of ensemble (EoE) machine learning (ML) system composed of a supervised and an unsupervised ML layers was developed to generate a prediction model for CRT response.ResultsWe compared the performance of EoE against traditional ML methods and the state‐of‐the‐art convolutional neural network (CNN) model trained on raw electrocardiographic (ECG) waveforms. We observed that the models exhibited improvement in performance as more features were incrementally used for training. Using the most comprehensive set of predictors, the performance of the EoE model in terms of the area under the receiver operating characteristic curve and F1‐score were 0.76 and 0.73, respectively. Direct application of the CNN model on the raw ECG waveforms did not generate promising results.ConclusionThe proposed CRT risk calculator effectively discriminates which heart failure (HF) patient is likely to respond to CRT significantly better than using clinical guidelines and traditional ML methods, thus suggesting that the tool can enhanced care management of HF patients by helping to identify high‐risk patients.

Background: Familial hypercholesterolemia (FH) is an important public health burden as it is a relatively common Mendelian genetic disorder which is associated with dramatically increased lifetime risk for premature atherosclerotic cardiovascular disease (ASCVD) due to elevated plasma low-density lipoprotein cholesterol (LDL-C) levels. Little is known about prevalence and control of FH in the US. Objective: To develop an electronic phenotyping algorithm for rapid identification of FH in electronic health records (EHRs) and thereby address knowledge gaps in prevalence and control of FH. Methods: We identified patients in the Mayo Employee and Community Health (ECH) system who met the following inclusion criteria: 1) gave research authorization, 2) any LDL-C in EHR ≥190 mg/dL; 2) triglycerides <400 mg/dL; 3) absence of secondary causes of hyperlipidemia (hypothyroidism, cholestatic liver diseases, nephrotic syndrome, renal failure, and pregnancy). Next we applied the Dutch Lipid Clinic Network (DLCN) criteria to ascertain FH cases. ASCVD-related diagnosis codes, laboratory data, and medications were obtained from structured EHR datasets. We used the Mayo natural language processing (NLP) system to ascertain presence of family and personal history of premature ASCVD, xanthomas and corneal arcus from clinical text notes. Results: Of a total of 131,000 patients seen in ECH clinics between July 1993 and December 2014, 6018 met the inclusion criteria. Implementing the electronic phenotyping algorithm for FH in these patients identified 178 definite and 369 probable cases (DLCN score >8 and 6-8 points, respectively) with an overall FH prevalence of 0.4% (1:240). Blinded expert review of 160 randomly chosen patients showed positive and negative predictive values for electronic phenotyping algorithm at 85% and 90%, respectively. Only 40% of these patients achieved LDL-C ≤100 mg/dL on treatment. Conclusions: 1) An EHR-based phenotyping algorithm that included NLP had reasonable accuracy in ascertaining FH cases. 2) Implementing this algorithm revealed the prevalence of FH in the study cohort to be nearly twice the current estimate of 1:500 in the general population. 3) Less than half of the FH patients had optimal LDL-C levels on treatment.