There is growing evidence that racial and ethnic minorities bear a disproportionate burden from COVID-19. Temporal changes in the pandemic epidemiology and diversity in the clinical course require ...careful study to identify determinants of poor outcomes. We analyzed 6255 hospitalized individuals with PCR-confirmed SARS-CoV-2 infection from one of 5 hospitals in the University of Pennsylvania Health System between March 2020 and March 2021, using electronic health records to assess risk factors and outcomes through 8 weeks post-admission. Discharge, readmission and mortality outcomes were analyzed in a multi-state model with multivariable Cox models for each transition. Mortality varied markedly over time, with cumulative incidence (95% CI) 30 days post-admission of 19.1% (16.9, 21.3) in March-April 2020, 5.7% (4.2, 7.5) in July-October 2020 and 10.5% (9.1,12.0) in January-March 2021; 26% of deaths occurred after discharge. Average age (SD) at admission varied from 62.7 (17.6) to 54.8 (19.9) to 60.5 (18.1); mechanical ventilation use declined from 21.3% to 9-11%. Compared to Caucasian, Black race was associated with more severe disease at admission, higher rates of co-morbidities and residing in a low-income zip code. Between-race risk differences in mortality risk diminished in multivariable models; while admitting hospital, increasing age, admission early in the pandemic, and severe disease and low blood pressure at admission were associated with increased mortality hazard. Hispanic ethnicity was associated with fewer baseline co-morbidities and lower mortality hazard (0.57, 95% CI: 0.37, .087). Multi-state modeling allows for a unified framework to analyze multiple outcomes throughout the disease course. Morbidity and mortality for hospitalized COVID-19 patients varied over time but post-discharge mortality remained non-trivial. Black race was associated with more risk factors for morbidity and with treatment at hospitals with lower mortality. Multivariable models suggest there are not between-race differences in outcomes. Future work is needed to better understand the identified between-hospital differences in mortality.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
•Electronic health record data can identify patients at risk of suicide ideation.•Univariate analysis found twenty-two risk factors associated with suicide ideation.•Multivariable logistic analysis ...highlighted specific suicide ideation risk factors.•High-risk suicide patients can be flagged using electronic health record data.
Suicide is the tenth leading cause of death in the United States. Several studies have leveraged electronic health record (EHR) data to predict suicide risk in veteran and military samples; however, few studies have investigated suicide risk factors in a large-scale community health population.
Clinical data was queried for 9,811 patients from the Penn Medicine Health System who had completed a Patient Health Questionnaire-9 (PHQ-9) documented in the EHR between January 2017 and June 2019. Patient demographics, PHQ-9 scores, and psychiatric comorbidities were extracted from the EHR. Univariate and multivariable logistic regressions were applied to determine significant risk factors associated with suicide ideation responses from the PHQ-9.
One-quarter (25.8%% of patients endorsed suicide ideation. Univariate analysis found 22 risk factors of suicide ideation. Multivariable logistic regression found significant positive associations (Odds Ratio, (95% Confidence Interval)) with the following: younger ages less than 18 years: 2.1, (1.69, 2.60) and 19-24 years: 1.55, (1.29, 1.87)), single marital status (1.22, (1.08, 1.38)), African American (1.22, (1.08, 1.38)), non-commercial insurance (1.16, (1.03, 1.31)), multiple comorbidities (1 comorbidity (1.65, (1.32, 2.07); 2 comorbidities (2.07, (1.61, 2.64)), 3+ comorbidities (2.49, (1.87, 3.33))), bipolar disorders (Type I: 1.38, (1.14, 1.67) and Type II: 1.94, (1.52, 2.49)), depressive disorders (1.70, (1.49, 1.94)), obsessive compulsive disorder (OCD) (1.43, (1.08, 1.90)), and stress disorders (1.53, (1.33, 1.76)).
Community EHR information can be used to predict suicidal ideation. This information can be used to design tools for identifying patients at risk for suicide in real-time.
Age and time information stored within the histories of clinical notes can provide valuable insights for assessing a patient's disease risk, understanding disease progression, and studying ...therapeutic outcomes. However, details of age and temporally-specified clinical events are not well captured, consistently codified, and readily available to research databases for study.
We expanded upon existing annotation schemes to capture additional age and temporal information, conducted an annotation study to validate our expanded schema, and developed a prototypical, rule-based Named Entity Recognizer to extract our novel clinical named entities (NE). The annotation study was conducted on 138 discharge summaries from the pre-annotated 2014 ShARe/CLEF eHealth Challenge corpus. In addition to existing NE classes (TIMEX3, SUBJECT_CLASS, DISEASE_DISORDER), our schema proposes 3 additional NEs (AGE, PROCEDURE, OTHER_EVENTS). We also propose new attributes, e.g., "degree_relation" which captures the degree of biological relation for subjects annotated under SUBJECT_CLASS. As a proof of concept, we applied the schema to 49 H&P notes to encode pertinent history information for a lung cancer cohort study.
An abundance of information was captured under the new OTHER_EVENTS, PROCEDURE and AGE classes, with 23%, 10% and 8% of all annotated NEs belonging to the above classes, respectively. We observed high inter-annotator agreement of >80% for AGE and TIMEX3; the automated NLP system achieved F1 scores of 86% (AGE) and 86% (TIMEX3). Age and temporally-specified mentions within past medical, family, surgical, and social histories were common in our lung cancer data set; annotation is ongoing to support this translational research study.
Our annotation schema and NLP system can encode historical events from clinical notes to support clinical and translational research studies.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Social risk factors are important dimensions of health and are linked to access to care, quality of life, health outcomes and life expectancy. However, in the Electronic Health Record, data related ...to many social risk factors are primarily recorded in free-text clinical notes, rather than as more readily computable structured data, and hence cannot currently be easily incorporated into automated assessments of health. In this paper, we present Moonstone, a new, highly configurable rule-based clinical natural language processing system designed to automatically extract information that requires inferencing from clinical notes. Our initial use case for the tool is focused on the automatic extraction of social risk factor information - in this case, housing situation, living alone, and social support - from clinical notes. Nursing notes, social work notes, emergency room physician notes, primary care notes, hospital admission notes, and discharge summaries, all derived from the Veterans Health Administration, were used for algorithm development and evaluation.
An evaluation of Moonstone demonstrated that the system is highly accurate in extracting and classifying the three variables of interest (housing situation, living alone, and social support). The system achieved positive predictive value (i.e. precision) scores ranging from 0.66 (homeless/marginally housed) to 0.98 (lives at home/not homeless), accuracy scores ranging from 0.63 (lives in facility) to 0.95 (lives alone), and sensitivity (i.e. recall) scores ranging from 0.75 (lives in facility) to 0.97 (lives alone).
The Moonstone system is - to the best of our knowledge - the first freely available, open source natural language processing system designed to extract social risk factors from clinical text with good (lives in facility) to excellent (lives alone) performance. Although developed with the social risk factor identification task in mind, Moonstone provides a powerful tool to address a range of clinical natural language processing tasks, especially those tasks that require nuanced linguistic processing in conjunction with inference capabilities.
Information regarding opioid use disorder (OUD) status and severity is important for patient care. Clinical notes provide valuable information for detecting and characterizing problematic opioid use, ...necessitating development of natural language processing (NLP) tools, which in turn requires reliably labeled OUD-relevant text and understanding of documentation patterns.
To inform automated NLP methods, we aimed to develop and evaluate an annotation schema for characterizing OUD and its severity, and to document patterns of OUD-relevant information within clinical notes of heterogeneous patient cohorts.
We developed an annotation schema to characterize OUD severity based on criteria from the Diagnostic and Statistical Manual of Mental Disorders, 5th edition. In total, 2 annotators reviewed clinical notes from key encounters of 100 adult patients with varied evidence of OUD, including patients with and those without chronic pain, with and without medication treatment for OUD, and a control group. We completed annotations at the sentence level. We calculated severity scores based on annotation of note text with 18 classes aligned with criteria for OUD severity and determined positive predictive values for OUD severity.
The annotation schema contained 27 classes. We annotated 1436 sentences from 82 patients; notes of 18 patients (11 of whom were controls) contained no relevant information. Interannotator agreement was above 70% for 11 of 15 batches of reviewed notes. Severity scores for control group patients were all 0. Among noncontrol patients, the mean severity score was 5.1 (SD 3.2), indicating moderate OUD, and the positive predictive value for detecting moderate or severe OUD was 0.71. Progress notes and notes from emergency department and outpatient settings contained the most and greatest diversity of information. Substance misuse and psychiatric classes were most prevalent and highly correlated across note types with high co-occurrence across patients.
Implementation of the annotation schema demonstrated strong potential for inferring OUD severity based on key information in a small set of clinical notes and highlighting where such information is documented. These advancements will facilitate NLP tool development to improve OUD prevention, diagnosis, and treatment.
Opioid use disorder (OUD) is underdiagnosed in health system settings, limiting research on OUD using electronic health records (EHRs). Medical encounter notes can enrich structured EHR data with ...documented signs and symptoms of OUD and social risks and behaviors. To capture this information at scale, natural language processing (NLP) tools must be developed and evaluated. We developed and applied an annotation schema to deeply characterize OUD and related clinical, behavioral, and environmental factors, and automated the annotation schema using machine learning and deep learning-based approaches.
Using the MIMIC-III Critical Care Database, we queried hospital discharge summaries of patients with
(ICD-9) OUD diagnostic codes. We developed an annotation schema to characterize problematic opioid use, identify individuals with potential OUD, and provide psychosocial context. Two annotators reviewed discharge summaries from 100 patients. We randomly sampled patients with their associated annotated sentences and divided them into training (66 patients; 2,127 annotated sentences) and testing (29 patients; 1,149 annotated sentences) sets. We used the training set to generate features, employing three NLP algorithms/knowledge sources. We trained and tested prediction models for classification with a traditional machine learner (logistic regression) and deep learning approach (Autogluon based on ELECTRA's replaced token detection model). We applied a five-fold cross-validation approach to reduce bias in performance estimates.
The resulting annotation schema contained 32 classes. We achieved moderate inter-annotator agreement, with F
-scores across all classes increasing from 48 to 66%. Five classes had a sufficient number of annotations for automation; of these, we observed consistently high performance (F
-scores) across training and testing sets for
(training: 91-96; testing: 91-94) and
(training: 86-96; testing: 86-99). Performance dropped from training and to testing sets for
(training: 52-65; testing: 40-48),
(training: 72-78; testing: 61-78) and
(training: 73-80; testing: 72). Autogluon achieved the highest performance.
This pilot study demonstrated that rich information regarding problematic opioid use can be manually identified by annotators. However, more training samples and features would improve our ability to reliably identify less common classes from clinical text, including text from outpatient settings.
One core measure of healthcare quality set forth by the Institute of Medicine is whether care decisions match patient goals. High-quality "serious illness communication" about patient goals and ...prognosis is required to support patient-centered decision-making, however current methods are not sensitive enough to measure the quality of this communication or determine whether care delivered matches patient priorities. Natural language processing (NLP) offers an efficient method for identification and evaluation of documented serious illness communication, which could serve as the basis for future quality metrics in oncology and other forms of serious illness. In this study, we trained NLP algorithms to identify and characterize serious illness communication with oncology patients.
Abstract
Objective
The Consortium for Clinical Characterization of COVID-19 by EHR (4CE) is an international collaboration addressing coronavirus disease 2019 (COVID-19) with federated analyses of ...electronic health record (EHR) data. We sought to develop and validate a computable phenotype for COVID-19 severity.
Materials and Methods
Twelve 4CE sites participated. First, we developed an EHR-based severity phenotype consisting of 6 code classes, and we validated it on patient hospitalization data from the 12 4CE clinical sites against the outcomes of intensive care unit (ICU) admission and/or death. We also piloted an alternative machine learning approach and compared selected predictors of severity with the 4CE phenotype at 1 site.
Results
The full 4CE severity phenotype had pooled sensitivity of 0.73 and specificity 0.83 for the combined outcome of ICU admission and/or death. The sensitivity of individual code categories for acuity had high variability—up to 0.65 across sites. At one pilot site, the expert-derived phenotype had mean area under the curve of 0.903 (95% confidence interval, 0.886-0.921), compared with an area under the curve of 0.956 (95% confidence interval, 0.952-0.959) for the machine learning approach. Billing codes were poor proxies of ICU admission, with as low as 49% precision and recall compared with chart review.
Discussion
We developed a severity phenotype using 6 code classes that proved resilient to coding variability across international institutions. In contrast, machine learning approaches may overfit hospital-specific orders. Manual chart review revealed discrepancies even in the gold-standard outcomes, possibly owing to heterogeneous pandemic conditions.
Conclusions
We developed an EHR-based severity phenotype for COVID-19 in hospitalized patients and validated it at 12 international sites.
Automated texting platforms have emerged as a tool to facilitate communication between patients and health care providers with variable effects on achieving target blood pressure (BP). Understanding ...differences in the way patients interact with these communication platforms can inform their use and design for hypertension management.
Our primary aim was to explore the unique phenotypes of patient interactions with an automated text messaging platform for BP monitoring. Our secondary aim was to estimate associations between interaction phenotypes and BP control.
This study was a secondary analysis of data from a randomized controlled trial for adults with poorly controlled hypertension. A total of 201 patients with established primary care were assigned to the automated texting platform; messages exchanged throughout the 4-month program were analyzed. We used the k-means clustering algorithm to characterize two different interaction phenotypes: program conformity and engagement style. First, we identified unique clusters signifying differences in program conformity based on the frequency over time of error alerts, which were generated to patients when they deviated from the requested text message format (eg, ###/## for BP). Second, we explored overall engagement styles, defined by error alerts and responsiveness to text prompts, unprompted messages, and word count averages. Finally, we applied the chi-square test to identify associations between each interaction phenotype and achieving the target BP.
We observed 3 categories of program conformity based on their frequency of error alerts: those who immediately and consistently submitted texts without system errors (perfect users, 51/201), those who did so after an initial learning period (adaptive users, 66/201), and those who consistently submitted messages generating errors to the platform (nonadaptive users, 38/201). Next, we observed 3 categories of engagement style: the enthusiast, who tended to submit unprompted messages with high word counts (17/155); the student, who inconsistently engaged (35/155); and the minimalist, who engaged only when prompted (103/155). Of all 6 phenotypes, we observed a statistically significant association between patients demonstrating the minimalist communication style (high adherence, few unprompted messages, limited information sharing) and achieving target BP (P<.001).
We identified unique interaction phenotypes among patients engaging with an automated text message platform for remote BP monitoring. Only the minimalist communication style was associated with achieving target BP. Identifying and understanding interaction phenotypes may be useful for tailoring future automated texting interactions and designing future interventions to achieve better BP control.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
Display omitted
To evaluate the technical feasibility and potential value of a digital assistant that prompts intensive care unit (ICU) rounding teams to use evidence-based practices based on ...analysis of their real-time discussions.
We evaluated a novel voice-based digital assistant which audio records and processes the ICU care team’s rounding discussions to determine which evidence-based practices are applicable to the patient but have yet to be addressed by the team. The system would then prompt the team to consider indicated but not yet delivered practices, thereby reducing cognitive burden compared to traditional rigid rounding checklists. In a retrospective analysis, we applied automatic transcription, natural language processing, and a rule-based expert system to generate personalized prompts for each patient in 106 audio-recorded ICU rounding discussions. To assess technical feasibility, we compared the system’s prompts to those created by experienced critical care nurses who directly observed rounds. To assess potential value, we also compared the system’s prompts to a hypothetical paper checklist containing all evidence-based practices.
The positive predictive value, negative predictive value, true positive rate, and true negative rate of the system’s prompts were 0.45 ± 0.06, 0.83 ± 0.04, 0.68 ± 0.07, and 0.66 ± 0.04, respectively. If implemented in lieu of a paper checklist, the system would generate 56% fewer prompts per patient, with 50%±17% greater precision.
A voice-based digital assistant can reduce prompts per patient compared to traditional approaches for improving evidence uptake on ICU rounds. Additional work is needed to evaluate field performance and team acceptance.