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.

Identifying Patients With Delirium Based on Unstructured Clinical Notes: Observational Study.

BACKGROUND: Delirium in hospitalized patients is a syndrome of acute brain dysfunction. Diagnostic (International Classification of Diseases [ICD]) codes are often used in studies using electronic health records (EHRs), but they are inaccurate. OBJECTIVE: We sought to develop a more accurate method using natural language processing (NLP) to detect delirium episodes on the basis of unstructured clinical notes. METHODS: We collected 1.5 million notes from >10,000 patients from among 9 hospitals. Seven experts iteratively labeled 200,471 sentences. Using these, we trained three NLP classifiers: Support Vector Machine, Recurrent Neural Networks, and Transformer. Testing was performed using an external data set. We also evaluated associations with delirium billing (ICD) codes, medications, orders for restraints and sitters, direct assessments (Confusion Assessment Method [CAM] scores), and in-hospital mortality. F1 scores, confusion matrices, and areas under the receiver operating characteristic curve (AUCs) were used to compare NLP models. We used the φ coefficient to measure associations with other delirium indicators. RESULTS: The transformer NLP performed best on the following parameters: micro F1=0.978, macro F1=0.918, positive AUC=0.984, and negative AUC=0.992. NLP detections exhibited higher correlations (φ) than ICD codes with deliriogenic medications (0.194 vs 0.073 for ICD codes), restraints and sitter orders (0.358 vs 0.177), mortality (0.216 vs 0.000), and CAM scores (0.256 vs -0.028). CONCLUSIONS: Clinical notes are an attractive alternative to ICD codes for EHR delirium studies but require automated methods. Our NLP model detects delirium with high accuracy, similar to manual chart review. Our NLP approach can provide more accurate determination of delirium for large-scale EHR-based studies regarding delirium, quality improvement, and clinical trails.

Clinical and neuroradiologic characteristics in varicella zoster virus reactivation with central nervous system involvement.

OBJECTIVE: To investigate the clinical and magnetic resonance imaging (MRI) characteristics of patients with varicella zoster virus (VZV) reactivation involving the cranial nerves and central nervous system (CNS). METHODS: This is a retrospective, multi-center case-series of 37 patients with VZV infection affecting the cranial nerves and CNS. RESULTS: The median age was 71 years [IQR 51.5-76]; 21 (57%) were men. Cerebrospinal fluid (CSF) was available in 24/37 (65%); median CSF white blood cell count was 11 [IQR 2-23] cells/µL and protein was 45.5 [IQR 34.5-75.5] mg/dL. VZV polymerase chain reaction (PCR) assays were positive in 6/21 (29%) CSF and 8/9 (89%) ocular samples. Clinical involvement included the optic nerve in 12 (32%), other cranial nerves in 20 (54%), brain parenchyma in 12 (32%) and spinal cord or nerve roots in 4 (11%). Twenty-seven/28 immunocompetent patients' MRIs were available for review (96%). Of the 27, 18 had T1 postcontrast fat saturated sequences without motion artifact to evaluate for cranial nerve enhancement and optic perineuritis (OPN). Eight/18 (44%) demonstrated OPN. All 8 experienced vision loss: 3 optic neuritis, 1 acute retinal necrosis, and 3 CNS vasculitis with 1 central and 1 branch retinal artery occlusion and 1 uveitis. Diplopic patients had cranial nerve and cavernous sinus enhancement. All immunosuppressed patients were imaged. Seven/9 (88%) had extensive neuraxis involvement, including encephalitis, vasculitis and transverse myelitis; one case had OPN. CONCLUSION: OPN is a frequent manifestation in VZV-associated vision loss among immunocompetent patients. Immunosuppressed patients had greater neuraxis involvement. Optimizing MRI protocols may improve early diagnosis in VZV reactivation.

Intrathecal inflammatory responses in the absence of SARS-CoV-2 nucleic acid in the CSF of COVID-19 hospitalized patients.

OBJECTIVE: Little is known about CSF profiles in patients with acute COVID-19 infection and neurological symptoms. Here, CSF was tested for SARS-CoV-2 RNA and inflammatory cytokines and chemokines and compared to controls and patients with known neurotropic pathogens. METHODS: CSF from twenty-seven consecutive patients with COVID-19 and neurological symptoms was assayed for SARS-CoV-2 RNA using quantitative reverse transcription PCR (RT-qPCR) and unbiased metagenomic sequencing. Assays for blood brain barrier (BBB) breakdown (CSF:serum albumin ratio (Q-Alb)), and proinflammatory cytokines and chemokines (IL-6, IL-8, IL-15, IL-16, monocyte chemoattractant protein -1 (MCP-1) and monocyte inhibitory protein - 1ß (MIP-1ß)) were performed in 23 patients and compared to CSF from patients with HIV-1 (16 virally suppressed, 5 unsuppressed), West Nile virus (WNV) (n = 4) and 16 healthy controls (HC). RESULTS: Median CSF cell count for COVID-19 patients was 1 white blood cell/µL; two patients were infected with a second pathogen (Neisseria, Cryptococcus neoformans). No CSF samples had detectable SARS-CoV-2 RNA by either detection method. In patients with COVID-19 only, CSF IL-6, IL-8, IL-15, and MIP-1ß levels were higher than HC and suppressed HIV (corrected-p < 0.05). MCP-1 and MIP-1ß levels were higher, while IL-6, IL-8, IL-15 were similar in COVID-19 compared to WNV patients. Q-Alb correlated with all proinflammatory markers, with IL-6, IL-8, and MIP-1ß (r ≥ 0.6, p < 0.01) demonstrating the strongest associations. CONCLUSIONS: Lack of SARS-CoV-2 RNA in CSF is consistent with pre-existing literature. Evidence of intrathecal proinflammatory markers in a subset of COVID-19 patients with BBB breakdown despite minimal CSF pleocytosis is atypical for neurotropic pathogens.

Skeletal Muscle and Peripheral Nerve Histopathology in COVID-19.

OBJECTIVE: To explore the spectrum of skeletal muscle and nerve pathology of patients who died after severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and to assess for direct viral invasion of these tissues. METHODS: Psoas muscle and femoral nerve sampled from 35 consecutive autopsies of patients who died after SARS-CoV-2 infection and 10 SARS-CoV-2-negative controls were examined under light microscopy. Clinical and laboratory data were obtained by chart review. RESULTS: In SARS-CoV-2-positive patients, mean age at death was 67.8 years (range 43-96 years), and the duration of symptom onset to death ranged from 1 to 49 days. Four patients had neuromuscular symptoms. Peak creatine kinase was elevated in 74% (mean 959 U/L, range 29-8,413 U/L). Muscle showed type 2 atrophy in 32 patients, necrotizing myopathy in 9, and myositis in 7. Neuritis was seen in 9. Major histocompatibility complex-1 (MHC-1) expression was observed in all cases of necrotizing myopathy and myositis and in 8 additional patients. Abnormal expression of myxovirus resistance protein A (MxA) was present on capillaries in muscle in 9 patients and in nerve in 7 patients. SARS-CoV-2 immunohistochemistry was negative in muscle and nerve in all patients. In the 10 controls, muscle showed type 2 atrophy in all patients, necrotic muscle fibers in 1, MHC-1 expression in nonnecrotic/nonregenerating fibers in 3, MxA expression on capillaries in 2, and inflammatory cells in none, and nerves showed no inflammatory cells or MxA expression. CONCLUSIONS: Muscle and nerve tissue demonstrated inflammatory/immune-mediated damage likely related to release of cytokines. There was no evidence of direct SARS-CoV-2 invasion of these tissues. CLASSIFICATION OF EVIDENCE: This study provides Class IV evidence that muscle and nerve biopsies document a variety of pathologic changes in patients dying of coronavirus disease 2019 (COVID-19).

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.

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.

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.

Eastern equine encephalitis and use of IV immunoglobulin therapy and high-dose steroids.

OBJECTIVE: To determine the clinical presentation and patient outcomes after treatment with IV immunoglobulin (IVIG), high-dose steroids, or standard of care alone in Eastern equine encephalitis (EEE), a mosquito-borne viral infection with significant neurologic morbidity and mortality. METHODS: A retrospective observational study of patients admitted to 2 tertiary academic medical centers in Boston, Massachusetts, with EEE from 2005 to 2019. RESULTS: Of 17 patients (median [IQR] age, 63 [36-70] years; 10 (59%) male, and 16 (94%) White race), 17 patients had fever (100%), 15 had encephalopathy (88%), and 12 had headache (71%). Eleven of 14 patients with CSF cell count differential had a neutrophil predominance (mean = 60.6% of white blood cells) with an elevated protein level (median [IQR], 100 mg/dL [75-145]). Affected neuroanatomic regions included the basal ganglia (n = 9/17), thalamus (n = 7/17), and mesial temporal lobe (n = 7/17). A total of 11 patients (65%) received IVIG; 8 (47%) received steroids. Of the patients who received IVIG, increased time from hospital admission to IVIG administration correlated with worse long-term disability as assessed by the modified Rankin Scale (mRS) (r = 0.72, p = 0.02); steroid use was not associated with the mRS score. The mortality was 12%. CONCLUSIONS: Clinicians should suspect EEE in immunocompetent patients with early subcortical neuroimaging abnormalities and CSF neutrophilic predominance. This study suggests a lower mortality than previously reported, but a high morbidity rate in EEE. IVIG as an adjunctive to standard of care may be considered early during hospitalization.

COVID-19 Outpatient Screening: a Prediction Score for Adverse Events.

BACKGROUND: We sought to develop an automatable score to predict hospitalization, critical illness, or death in patients at risk for COVID-19 presenting for urgent care during the Massachusetts outbreak. METHODS: Single-center study of adult outpatients seen in respiratory illness clinics (RICs) or the emergency department (ED), including development (n = 9381, March 7-May 2) and prospective (n = 2205, May 3-14) cohorts. Data was queried from Partners Enterprise Data Warehouse. Outcomes were hospitalization, critical illness or death within 7 days. We developed the COVID-19 Acuity Score (CoVA) using automatically extracted data from the electronic medical record and learning-to-rank ordinal logistic regression modeling. Calibration was assessed using predicted-to-observed event ratio (E/O). Discrimination was assessed by C-statistics (AUC). RESULTS: In the development cohort, 27.3%, 7.2%, and 1.1% of patients experienced hospitalization, critical illness, or death, respectively; and in the prospective cohort, 26.1%, 6.3%, and 0.5%. CoVA showed excellent performance in the development cohort (concurrent validation) for hospitalization (E/O: 1.00, AUC: 0.80); for critical illness (E/O: 1.00, AUC: 0.82); and for death (E/O: 1.00, AUC: 0.87). Performance in the prospective cohort (prospective validation) was similar for hospitalization (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 five were age, diastolic blood pressure, blood oxygen saturation, COVID-19 testing status, and respiratory rate. CONCLUSIONS: CoVA is a prospectively validated automatable score to assessing risk for adverse outcomes related to COVID-19 infection in the outpatient setting.