Classification of neurologic outcomes from medical notes using natural language processing.

Neurologic disability level at hospital discharge is an important outcome in many clinical research studies. Outside of clinical trials, neurologic outcomes must typically be extracted by labor intensive manual review of clinical notes in the electronic health record (EHR). To overcome this challenge, we set out to develop a natural language processing (NLP) approach that automatically reads clinical notes to determine neurologic outcomes, to make it possible to conduct larger scale neurologic outcomes studies. We obtained 7314 notes from 3632 patients hospitalized at two large Boston hospitals between January 2012 and June 2020, including discharge summaries (3485), occupational therapy (1472) and physical therapy (2357) notes. Fourteen clinical experts reviewed notes to assign scores on the Glasgow Outcome Scale (GOS) with 4 classes, namely 'good recovery', 'moderate disability', 'severe disability', and 'death' and on the Modified Rankin Scale (mRS), with 7 classes, namely 'no symptoms', 'no significant disability', 'slight disability', 'moderate disability', 'moderately severe disability', 'severe disability', and 'death'. For 428 patients' notes, 2 experts scored the cases generating interrater reliability estimates for GOS and mRS. After preprocessing and extracting features from the notes, we trained a multiclass logistic regression model using LASSO regularization and 5-fold cross validation for hyperparameter tuning. The model performed well on the test set, achieving a micro average area under the receiver operating characteristic and F-score of 0.94 (95% CI 0.93-0.95) and 0.77 (0.75-0.80) for GOS, and 0.90 (0.89-0.91) and 0.59 (0.57-0.62) for mRS, respectively. Our work demonstrates that an NLP algorithm can accurately assign neurologic outcomes based on free text clinical notes. This algorithm increases the scale of research on neurological outcomes that is possible with EHR data.

Proteomic analysis of cardiometabolic biomarkers and predictive modeling of severe outcomes in patients hospitalized with COVID-19.

BACKGROUND: The high heterogeneity in the symptoms and severity of COVID-19 makes it challenging to identify high-risk patients early in the disease. Cardiometabolic comorbidities have shown strong associations with COVID-19 severity in epidemiologic studies. Cardiometabolic protein biomarkers, therefore, may provide predictive insight regarding which patients are most susceptible to severe illness from COVID-19. METHODS: In plasma samples collected from 343 patients hospitalized with COVID-19 during the first wave of the pandemic, we measured 92 circulating protein biomarkers previously implicated in cardiometabolic disease. We performed proteomic analysis and developed predictive models for severe outcomes. We then used these models to predict the outcomes of out-of-sample patients hospitalized with COVID-19 later in the surge (N = 194). RESULTS: We identified a set of seven protein biomarkers predictive of admission to the intensive care unit and/or death (ICU/death) within 28 days of presentation to care. Two of the biomarkers, ADAMTS13 and VEGFD, were associated with a lower risk of ICU/death. The remaining biomarkers, ACE2, IL-1RA, IL6, KIM1, and CTSL1, were associated with higher risk. When used to predict the outcomes of the future, out-of-sample patients, the predictive models built with these protein biomarkers outperformed all models built from standard clinical data, including known COVID-19 risk factors. CONCLUSIONS: These findings suggest that proteomic profiling can inform the early clinical impression of a patient's likelihood of developing severe COVID-19 outcomes and, ultimately, accelerate the recognition and treatment of high-risk patients.

Prolonged Intubation in Patients With Prior Cerebrovascular Disease and COVID-19.

Objectives: Patients with comorbidities are at increased risk for poor outcomes in COVID-19, yet data on patients with prior neurological disease remains limited. Our objective was to determine the odds of critical illness and duration of mechanical ventilation in patients with prior cerebrovascular disease and COVID-19. Methods: A observational study of 1,128 consecutive adult patients admitted to an academic center in Boston, Massachusetts, and diagnosed with laboratory-confirmed COVID-19. We tested the association between prior cerebrovascular disease and critical illness, defined as mechanical ventilation (MV) or death by day 28, using logistic regression with inverse probability weighting of the propensity score. Among intubated patients, we estimated the cumulative incidence of successful extubation without death over 45 days using competing risk analysis. Results: Of the 1,128 adults with COVID-19, 350 (36%) were critically ill by day 28. The median age of patients was 59 years (SD: 18 years) and 640 (57%) were men. As of June 2nd, 2020, 127 (11%) patients had died. A total of 177 patients (16%) had a prior cerebrovascular disease. Prior cerebrovascular disease was significantly associated with critical illness (OR = 1.54, 95% CI = 1.14-2.07), lower rate of successful extubation (cause-specific HR = 0.57, 95% CI = 0.33-0.98), and increased duration of intubation (restricted mean time difference = 4.02 days, 95% CI = 0.34-10.92) compared to patients without cerebrovascular disease. Interpretation: Prior cerebrovascular disease adversely affects COVID-19 outcomes in hospitalized patients. Further study is required to determine if this subpopulation requires closer monitoring for disease progression during COVID-19.

The Fast Literature Assessment and Review (FLARE) Initiative. A Collaborative Effort for Timely Literature Appraisal during the Coronavirus Disease Pandemic.

The emergence and worldwide spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused major disruptions to the healthcare system and medical education. In response, the scientific community has been acquiring, releasing, and publishing data at a remarkable pace. At the same time, medical practitioners are taxed with greater professional duties than ever before, making it challenging to stay current with the influx of medical literature.To address the above mismatch between data release and provider capacity and to support our colleagues, physicians at the Massachusetts General Hospital have engaged in an electronic collaborative effort focused on rapid literature appraisal and dissemination regarding SARS-CoV-2 with a focus on critical care.Members of the Division of Pulmonary and Critical Care, the Division of Cardiology, and the Department of Medicine at Massachusetts General Hospital established the Fast Literature Assessment and Review (FLARE) team. This group rapidly compiles, appraises, and synthesizes literature regarding SARS-CoV-2 as it pertains to critical care, relevant clinical questions, and anecdotal reports. Daily, FLARE produces and disseminates highly curated scientific reviews and opinion pieces, which are distributed to readers using an online newsletter platform.Interest in our work has escalated rapidly. FLARE was quickly shared with colleagues outside our division, and, in a short time, our audience has grown to include more than 4,000 readers across the globe.Creating a collaborative group with a variety of expertise represents a feasible and acceptable way of rapidly appraising, synthesizing, and communicating scientific evidence directly to frontline clinicians in this time of great need.

Cardiometabolic risk factors for COVID-19 susceptibility and severity: A Mendelian randomization analysis.

BACKGROUND: Epidemiological studies report associations of diverse cardiometabolic conditions including obesity with COVID-19 illness, but causality has not been established. We sought to evaluate the associations of 17 cardiometabolic traits with COVID-19 susceptibility and severity using 2-sample Mendelian randomization (MR) analyses. METHODS AND FINDINGS: We selected genetic variants associated with each exposure, including body mass index (BMI), at p < 5 × 10-8 from genome-wide association studies (GWASs). We then calculated inverse-variance-weighted averages of variant-specific estimates using summary statistics for susceptibility and severity from the COVID-19 Host Genetics Initiative GWAS meta-analyses of population-based cohorts and hospital registries comprising individuals with self-reported or genetically inferred European ancestry. Susceptibility was defined as testing positive for COVID-19 and severity was defined as hospitalization with COVID-19 versus population controls (anyone not a case in contributing cohorts). We repeated the analysis for BMI with effect estimates from the UK Biobank and performed pairwise multivariable MR to estimate the direct effects and indirect effects of BMI through obesity-related cardiometabolic diseases. Using p < 0.05/34 tests = 0.0015 to declare statistical significance, we found a nonsignificant association of genetically higher BMI with testing positive for COVID-19 (14,134 COVID-19 cases/1,284,876 controls, p = 0.002; UK Biobank: odds ratio 1.06 [95% CI 1.02, 1.10] per kg/m2; p = 0.004]) and a statistically significant association with higher risk of COVID-19 hospitalization (6,406 hospitalized COVID-19 cases/902,088 controls, p = 4.3 × 10-5; UK Biobank: odds ratio 1.14 [95% CI 1.07, 1.21] per kg/m2, p = 2.1 × 10-5). The implied direct effect of BMI was abolished upon conditioning on the effect on type 2 diabetes, coronary artery disease, stroke, and chronic kidney disease. No other cardiometabolic exposures tested were associated with a higher risk of poorer COVID-19 outcomes. Small study samples and weak genetic instruments could have limited the detection of modest associations, and pleiotropy may have biased effect estimates away from the null. CONCLUSIONS: In this study, we found genetic evidence to support higher BMI as a causal risk factor for COVID-19 susceptibility and severity. These results raise the possibility that obesity could amplify COVID-19 disease burden independently or through its cardiometabolic consequences and suggest that targeting obesity may be a strategy to reduce the risk of severe COVID-19 outcomes.

CoVA: An Acuity Score for Outpatient Screening that Predicts Coronavirus Disease 2019 Prognosis.

BACKGROUND: We sought to develop an automatable score to predict hospitalization, critical illness, or death for patients at risk for coronavirus disease 2019 (COVID-19) presenting for urgent care. METHODS: We developed the COVID-19 Acuity Score (CoVA) based on a single-center study of adult outpatients seen in respiratory illness clinics or the emergency department. Data were extracted from the Partners Enterprise Data Warehouse, and split into development (n = 9381, 7 March-2 May) and prospective (n = 2205, 3-14 May) cohorts. Outcomes were hospitalization, critical illness (intensive care unit or ventilation), or death within 7 days. Calibration was assessed using the expected-to-observed event ratio (E/O). Discrimination was assessed by area under the receiver operating curve (AUC). RESULTS: In the prospective cohort, 26.1%, 6.3%, and 0.5% of patients experienced hospitalization, critical illness, or death, respectively. CoVA showed excellent performance in prospective validation for hospitalization (expected-to-observed ratio [E/O]: 1.01; AUC: 0.76), for critical illness (E/O: 1.03; AUC: 0.79), and for death (E/O: 1.63; AUC: 0.93). Among 30 predictors, the top 5 were age, diastolic blood pressure, blood oxygen saturation, COVID-19 testing status, and respiratory rate. CONCLUSIONS: CoVA is a prospectively validated automatable score for the outpatient setting to predict adverse events related to COVID-19 infection.

Classification of the Disposition of Patients Hospitalized with COVID-19: Reading Discharge Summaries Using Natural Language Processing.

BACKGROUND: Medical notes are a rich source of patient data; however, the nature of unstructured text has largely precluded the use of these data for large retrospective analyses. Transforming clinical text into structured data can enable large-scale research studies with electronic health records (EHR) data. Natural language processing (NLP) can be used for text information retrieval, reducing the need for labor-intensive chart review. Here we present an application of NLP to large-scale analysis of medical records at 2 large hospitals for patients hospitalized with COVID-19. OBJECTIVE: Our study goal was to develop an NLP pipeline to classify the discharge disposition (home, inpatient rehabilitation, skilled nursing inpatient facility [SNIF], and death) of patients hospitalized with COVID-19 based on hospital discharge summary notes. METHODS: Text mining and feature engineering were applied to unstructured text from hospital discharge summaries. The study included patients with COVID-19 discharged from 2 hospitals in the Boston, Massachusetts area (Massachusetts General Hospital and Brigham and Women's Hospital) between March 10, 2020, and June 30, 2020. The data were divided into a training set (70%) and hold-out test set (30%). Discharge summaries were represented as bags-of-words consisting of single words (unigrams), bigrams, and trigrams. The number of features was reduced during training by excluding n-grams that occurred in fewer than 10% of discharge summaries, and further reduced using least absolute shrinkage and selection operator (LASSO) regularization while training a multiclass logistic regression model. Model performance was evaluated using the hold-out test set. RESULTS: The study cohort included 1737 adult patients (median age 61 [SD 18] years; 55% men; 45% White and 16% Black; 14% nonsurvivors and 61% discharged home). The model selected 179 from a vocabulary of 1056 engineered features, consisting of combinations of unigrams, bigrams, and trigrams. The top features contributing most to the classification by the model (for each outcome) were the following: "appointments specialty," "home health," and "home care" (home); "intubate" and "ARDS" (inpatient rehabilitation); "service" (SNIF); "brief assessment" and "covid" (death). The model achieved a micro-average area under the receiver operating characteristic curve value of 0.98 (95% CI 0.97-0.98) and average precision of 0.81 (95% CI 0.75-0.84) in the testing set for prediction of discharge disposition. CONCLUSIONS: A supervised learning-based NLP approach is able to classify the discharge disposition of patients hospitalized with COVID-19. This approach has the potential to accelerate and increase the scale of research on patients' discharge disposition that is possible with EHR data.

Lung Histopathology in Coronavirus Disease 2019 as Compared With Severe Acute Respiratory Sydrome and H1N1 Influenza: A Systematic Review.

BACKGROUND: Patients with severe coronavirus disease 2019 (COVID-19) have respiratory failure with hypoxemia and acute bilateral pulmonary infiltrates, consistent with ARDS. Respiratory failure in COVID-19 might represent a novel pathologic entity. RESEARCH QUESTION: How does the lung histopathology described in COVID-19 compare with the lung histopathology described in SARS and H1N1 influenza? STUDY DESIGN AND METHODS: We conducted a systematic review to characterize the lung histopathologic features of COVID-19 and compare them against findings of other recent viral pandemics, H1N1 influenza and SARS. We systematically searched MEDLINE and PubMed for studies published up to June 24, 2020, using search terms for COVID-19, H1N1 influenza, and SARS with keywords for pathology, biopsy, and autopsy. Using PRISMA-Individual Participant Data guidelines, our systematic review analysis included 26 articles representing 171 COVID-19 patients; 20 articles representing 287 H1N1 patients; and eight articles representing 64 SARS patients. RESULTS: In COVID-19, acute-phase diffuse alveolar damage (DAD) was reported in 88% of patients, which was similar to the proportion of cases with DAD in both H1N1 (90%) and SARS (98%). Pulmonary microthrombi were reported in 57% of COVID-19 and 58% of SARS patients, as compared with 24% of H1N1 influenza patients. INTERPRETATION: DAD, the histologic correlate of ARDS, is the predominant histopathologic pattern identified in lung pathology from patients with COVID-19, H1N1 influenza, and SARS. Microthrombi were reported more frequently in both patients with COVID-19 and SARS as compared with H1N1 influenza. Future work is needed to validate this histopathologic finding and, if confirmed, elucidate the mechanistic underpinnings and characterize any associations with clinically important outcomes.

Development and Prospective Validation of a Deep Learning Algorithm for Predicting Need for Mechanical Ventilation.

BACKGROUND: Objective and early identification of hospitalized patients, and particularly those with novel coronavirus disease 2019 (COVID-19), who may require mechanical ventilation (MV) may aid in delivering timely treatment. RESEARCH QUESTION: Can a transparent deep learning (DL) model predict the need for MV in hospitalized patients and those with COVID-19 up to 24 h in advance? STUDY DESIGN AND METHODS: We trained and externally validated a transparent DL algorithm to predict the future need for MV in hospitalized patients, including those with COVID-19, using commonly available data in electronic health records. Additionally, commonly used clinical criteria (heart rate, oxygen saturation, respiratory rate, Fio2, and pH) were used to assess future need for MV. Performance of the algorithm was evaluated using the area under receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value. RESULTS: We obtained data from more than 30,000 ICU patients (including more than 700 patients with COVID-19) from two academic medical centers. The performance of the model with a 24-h prediction horizon at the development and validation sites was comparable (AUC, 0.895 vs 0.882, respectively), providing significant improvement over traditional clinical criteria (P < .001). Prospective validation of the algorithm among patients with COVID-19 yielded AUCs in the range of 0.918 to 0.943. INTERPRETATION: A transparent deep learning algorithm improves on traditional clinical criteria to predict the need for MV in hospitalized patients, including in those with COVID-19. Such an algorithm may help clinicians to optimize timing of tracheal intubation, to allocate resources and staff better, and to improve patient care.