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.

Network autonomic analysis of post-acute sequelae of COVID-19 and postural tachycardia syndrome.

BACKGROUND: The autonomic nervous system (ANS) is a complex network where sympathetic and parasympathetic domains interact inside and outside of the network. Correlation-based network analysis (NA) is a novel approach enabling the quantification of these interactions. The aim of this study is to assess the applicability of NA to assess relationships between autonomic, sensory, respiratory, cerebrovascular, and inflammatory markers on post-acute sequela of COVID-19 (PASC) and postural tachycardia syndrome (POTS). METHODS: In this retrospective study, datasets from PASC (n = 15), POTS (n = 15), and matched controls (n = 11) were analyzed. Networks were constructed from surveys (autonomic and sensory), autonomic tests (deep breathing, Valsalva maneuver, tilt, and sudomotor test) results using heart rate, blood pressure, cerebral blood flow velocity (CBFv), capnography, skin biopsies for assessment of small fiber neuropathy (SFN), and various inflammatory markers. Networks were characterized by clusters and centrality metrics. RESULTS: Standard analysis showed widespread abnormalities including reduced orthostatic CBFv in 100%/88% (PASC/POTS), SFN 77%/88%, mild-to-moderate dysautonomia 100%/100%, hypocapnia 87%/100%, and elevated inflammatory markers. NA showed different signatures for both disorders with centrality metrics of vascular and inflammatory variables playing prominent roles in differentiating PASC from POTS. CONCLUSIONS: NA is suitable for a relationship analysis between autonomic and nonautonomic components. Our preliminary analyses indicate that NA can expand the value of autonomic testing and provide new insight into the functioning of the ANS and related systems in complex disease processes such as PASC and POTS.

Multisystem Involvement in Post-Acute Sequelae of Coronavirus Disease 19.

OBJECTIVE: The purpose of this study was to describe cerebrovascular, neuropathic, and autonomic features of post-acute sequelae of coronavirus disease 2019 ((COVID-19) PASC). METHODS: This retrospective study evaluated consecutive patients with chronic fatigue, brain fog, and orthostatic intolerance consistent with PASC. Controls included patients with postural tachycardia syndrome (POTS) and healthy participants. Analyzed data included surveys and autonomic (Valsalva maneuver, deep breathing, sudomotor, and tilt tests), cerebrovascular (cerebral blood flow velocity [CBFv] monitoring in middle cerebral artery), respiratory (capnography monitoring), and neuropathic (skin biopsies for assessment of small fiber neuropathy) testing and inflammatory/autoimmune markers. RESULTS: Nine patients with PASC were evaluated 0.8 ± 0.3 years after a mild COVID-19 infection, and were treated as home observations. Autonomic, pain, brain fog, fatigue, and dyspnea surveys were abnormal in PASC and POTS (n = 10), compared with controls (n = 15). Tilt table test reproduced the majority of PASC symptoms. Orthostatic CBFv declined in PASC (-20.0 ± 13.4%) and POTS (-20.3 ± 15.1%), compared with controls (-3.0 ± 7.5%, p = 0.001) and was independent of end-tidal carbon dioxide in PASC, but caused by hyperventilation in POTS. Reduced orthostatic CBFv in PASC included both subjects without (n = 6) and with (n = 3) orthostatic tachycardia. Dysautonomia was frequent (100% in both PASC and POTS) but was milder in PASC (p = 0.002). PASC and POTS cohorts diverged in frequency of small fiber neuropathy (89% vs 60%) but not in inflammatory markers (67% vs 70%). Supine and orthostatic hypocapnia was observed in PASC. INTERPRETATION: PASC following mild COVID-19 infection is associated with multisystem involvement including: (1) cerebrovascular dysregulation with persistent cerebral arteriolar vasoconstriction; (2) small fiber neuropathy and related dysautonomia; (3) respiratory dysregulation; and (4) chronic inflammation. ANN NEUROL 2022;91:367-379.

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.