Identifying Patients With Delirium Based on Unstructured Clinical Notes: Observational Study.
Ontology highlight
ABSTRACT: 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.
SUBMITTER: Ge W
PROVIDER: S-EPMC9270709 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BACKGROUND:Acute and chronic low back pain (LBP) are different conditions with different treatments. However, they are coded in electronic health records with the same International Classification of Diseases, 10th revision (ICD-10) code (M54.5) and can be differentiated only by retrospective chart reviews. This prevents an efficient definition of data-driven guidelines for billing and therapy recommendations, such as return-to-work options. OBJECTIVE:The objective of this study was to evaluate the feasibility of automatically distinguishing acute LBP episodes by analyzing free-text clinical notes. METHODS:We used a dataset of 17,409 clinical notes from different primary care practices; of these, 891 documents were manually annotated as acute LBP and 2973 were generally associated with LBP via the recorded ICD-10 code. We compared different supervised and unsupervised strategies for automated identification: keyword search, topic modeling, logistic regression with bag of n-grams and manual features, and deep learning (a convolutional neural network-based architecture [ConvNet]). We trained the supervised models using either manual annotations or ICD-10 codes as positive labels. RESULTS:ConvNet trained using manual annotations obtained the best results with an area under the receiver operating characteristic curve of 0.98 and an F score of 0.70. ConvNet's results were also robust to reduction of the number of manually annotated documents. In the absence of manual annotations, topic models performed better than methods trained using ICD-10 codes, which were unsatisfactory for identifying LBP acuity. CONCLUSIONS:This study uses clinical notes to delineate a potential path toward systematic learning of therapeutic strategies, billing guidelines, and management options for acute LBP at the point of care.
| S-EPMC7068466 | biostudies-literature
Project description:IntroductionWe tested the ability of our natural language processing (NLP) algorithm to identify delirium episodes in a large-scale study using real-world clinical notes.MethodsWe used the Rochester Epidemiology Project to identify persons ≥ 65 years who were hospitalized between 2011 and 2017. We identified all persons with an International Classification of Diseases code for delirium within ±14 days of a hospitalization. We independently applied our NLP algorithm to all clinical notes for this same population. We calculated rates using number of delirium episodes as the numerator and number of hospitalizations as the denominator. Rates were estimated overall, by demographic characteristics, and by year of episode, and differences were tested using Poisson regression.ResultsIn total, 14,255 persons had 37,554 hospitalizations between 2011 and 2017. The code-based delirium rate was 3.02 per 100 hospitalizations (95% CI: 2.85, 3.20). The NLP-based rate was 7.36 per 100 (95% CI: 7.09, 7.64). Rates increased with age (both p < 0.0001). Code-based rates were higher in men compared to women (p = 0.03), but NLP-based rates were similar by sex (p = 0.89). Code-based rates were similar by race and ethnicity, but NLP-based rates were higher in the White population compared to the Black and Asian populations (p = 0.001). Both types of rates increased significantly over time (both p values < 0.001).ConclusionsThe NLP algorithm identified more delirium episodes compared to the ICD code method. However, NLP may still underestimate delirium cases because of limitations in real-world clinical notes, including incomplete documentation, practice changes over time, and missing clinical notes in some time periods.
| S-EPMC10514685 | biostudies-literature
Project description:Mortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes and efficient utilization of resources. Accessibility of electronic health records (EHR) has enabled data-driven predictive modeling using machine learning. However, very few studies rely solely on unstructured clinical notes from the EHR for mortality prediction. In this work, we propose a framework to predict short, mid, and long-term mortality in adult ICU patients using unstructured clinical notes from the MIMIC III database, natural language processing (NLP), and machine learning (ML) models. Depending on the statistical description of the patients' length of stay, we define the short-term as 48-hour and 4-day period, the mid-term as 7-day and 10-day period, and the long-term as 15-day and 30-day period after admission. We found that by only using clinical notes within the 24 hours of admission, our framework can achieve a high area under the receiver operating characteristics (AU-ROC) score for short, mid and long-term mortality prediction tasks. The test AU-ROC scores are 0.87, 0.83, 0.83, 0.82, 0.82, and 0.82 for 48-hour, 4-day, 7-day, 10-day, 15-day, and 30-day period mortality prediction, respectively. We also provide a comparative study among three types of feature extraction techniques from NLP: frequency-based technique, fixed embedding-based technique, and dynamic embedding-based technique. Lastly, we provide an interpretation of the NLP-based predictive models using feature-importance scores.
| S-EPMC8735614 | biostudies-literature
Project description:ObjectivesThis study sets out to ascertain if recognition of delirium impacts on patient outcomes.DesignRetrospective cohort study.SettingUnscheduled admissions to acute care trust/secondary care UK hospitals.ParticipantsSix hundred and fifty-six older adults aged ≥65 years admitted on 14 September 2018.MeasurementsDelirium was ascertained retrospectively from case notes using medical notes. Documented delirium was classified as recognised delirium and retrospectively ascertained delirium was classified as unrecognised delirium.Primary and secondary outcome measuresPrimary outcome measure: inpatient mortality.Secondary outcome measureslength of stay, discharge destination.ResultsDelirium was present in 21.1% (132/626) of patients at any point during admission. The presence of delirium was associated with increased mortality (HR 2.65, CI 1.40 to 5.01). Recognition of delirium did not significantly impact on outcomes.ConclusionsDelirium is associated with adverse outcomes in hospitalised older adults. However, there is insufficient evidence that recognition of delirium affects outcomes. However, delirium recognition presents an opportunity to discuss a person's overall prognosis and discuss this with the patient and their family. Further research is needed to assess the pathophysiology of delirium to enable development of targeted interventions towards improved outcomes in patients with delirium.
| S-EPMC8166612 | biostudies-literature
Project description:BackgroundElectronic health records (EHRs) in unstructured formats are valuable sources of information for research in both the clinical and biomedical domains. However, before such records can be used for research purposes, sensitive health information (SHI) must be removed in several cases to protect patient privacy. Rule-based and machine learning-based methods have been shown to be effective in deidentification. However, very few studies investigated the combination of transformer-based language models and rules.ObjectiveThe objective of this study is to develop a hybrid deidentification pipeline for Australian EHR text notes using rules and transformers. The study also aims to investigate the impact of pretrained word embedding and transformer-based language models.MethodsIn this study, we present a hybrid deidentification pipeline called OpenDeID, which is developed using an Australian multicenter EHR-based corpus called OpenDeID Corpus. The OpenDeID corpus consists of 2100 pathology reports with 38,414 SHI entities from 1833 patients. The OpenDeID pipeline incorporates a hybrid approach of associative rules, supervised deep learning, and pretrained language models.ResultsThe OpenDeID achieved a best F1-score of 0.9659 by fine-tuning the Discharge Summary BioBERT model and incorporating various preprocessing and postprocessing rules. The OpenDeID pipeline has been deployed at a large tertiary teaching hospital and has processed over 8000 unstructured EHR text notes in real time.ConclusionsThe OpenDeID pipeline is a hybrid deidentification pipeline to deidentify SHI entities in unstructured EHR text notes. The pipeline has been evaluated on a large multicenter corpus. External validation will be undertaken as part of our future work to evaluate the effectiveness of the OpenDeID pipeline.
| S-EPMC10733816 | biostudies-literature
Project description:BackgroundNext-generation sequencing provides comprehensive information about individuals' genetic makeup and is commonplace in oncology clinical practice. However, the utility of genetic information in the clinical decision-making process has not been examined extensively from a real-world, data-driven perspective. Through mining real-world data (RWD) from clinical notes, we could extract patients' genetic information and further associate treatment decisions with genetic information.MethodsWe proposed a real-world evidence (RWE) study framework that incorporates context-based natural language processing (NLP) methods and data quality examination before final association analysis. The framework was demonstrated in a Foundation-tested women cancer cohort (N = 196). Upon retrieval of patients' genetic information using NLP system, we assessed the completeness of genetic data captured in unstructured clinical notes according to a genetic data-model. We examined the distribution of different topics regarding BRCA1/2 throughout patients' treatment process, and then analyzed the association between BRCA1/2 mutation status and the discussion/prescription of targeted therapy.ResultsWe identified seven topics in the clinical context of genetic mentions including: Information, Evaluation, Insurance, Order, Negative, Positive, and Variants of unknown significance. Our rule-based system achieved a precision of 0.87, recall of 0.93 and F-measure of 0.91. Our machine learning system achieved a precision of 0.901, recall of 0.899 and F-measure of 0.9 for four-topic classification and a precision of 0.833, recall of 0.823 and F-measure of 0.82 for seven-topic classification. We found in result-containing sentences, the capture of BRCA1/2 mutation information was 75%, but detailed variant information (e.g. variant types) is largely missing. Using cleaned RWD, significant associations were found between BRCA1/2 positive mutation and targeted therapies.ConclusionsIn conclusion, we demonstrated a framework to generate RWE using RWD from different clinical sources. Rule-based NLP system achieved the best performance for resolving contextual variability when extracting RWD from unstructured clinical notes. Data quality issues such as incompleteness and discrepancies exist thus manual data cleaning is needed before further analysis can be performed. Finally, we were able to use cleaned RWD to evaluate the real-world utility of genetic information to initiate a prescription of targeted therapy.
| S-EPMC7789545 | biostudies-literature
Project description:BackgroundSymptoms are a core concept of nursing interest. Large-scale secondary data reuse of notes in electronic health records (EHRs) has the potential to increase the quantity and quality of symptom research. However, the symptom language used in clinical notes is complex. A need exists for methods designed specifically to identify and study symptom information from EHR notes.ObjectivesWe aim to describe a method that combines standardized vocabularies, clinical expertise, and natural language processing to generate comprehensive symptom vocabularies and identify symptom information in EHR notes. We piloted this method with five diverse symptom concepts: constipation, depressed mood, disturbed sleep, fatigue, and palpitations.MethodsFirst, we obtained synonym lists for each pilot symptom concept from the Unified Medical Language System. Then, we used two large bodies of text (clinical notes from Columbia University Irving Medical Center and PubMed abstracts containing Medical Subject Headings or key words related to the pilot symptoms) to further expand our initial vocabulary of synonyms for each pilot symptom concept. We used NimbleMiner, an open-source natural language processing tool, to accomplish these tasks and evaluated NimbleMiner symptom identification performance by comparison to a manually annotated set of nurse- and physician-authored common EHR note types.ResultsCompared to the baseline Unified Medical Language System synonym lists, we identified up to 11 times more additional synonym words or expressions, including abbreviations, misspellings, and unique multiword combinations, for each symptom concept. Natural language processing system symptom identification performance was excellent.DiscussionUsing our comprehensive symptom vocabularies and NimbleMiner to label symptoms in clinical notes produced excellent performance metrics. The ability to extract symptom information from EHR notes in an accurate and scalable manner has the potential to greatly facilitate symptom science research.
| S-EPMC9109773 | biostudies-literature
Project description:BackgroundWith the increased sharing of electronic health information as required by the US 21st Century Cures Act, there is an increased risk of breaching patient, parent, or guardian confidentiality. The prevalence of sensitive terms in clinical notes is not known.ObjectiveThe aim of this study is to define sensitive terms that represent the documentation of content that may be private and determine the prevalence and characteristics of provider notes that contain sensitive terms.MethodsUsing keyword expansion, we defined a list of 781 sensitive terms. We searched all provider history and physical, progress, consult, and discharge summary notes for patients aged 0-21 years written between January 1, 2019, and December 31, 2019, for a direct string match of sensitive terms. We calculated the prevalence of notes with sensitive terms and characterized clinical encounters and patient characteristics.ResultsSensitive terms were present in notes from every clinical context in all pediatric ages. Terms related to the mental health category were most used overall (254,975/1,338,297, 19.5%), but terms related to substance abuse and reproductive health were most common in patients aged 0-3 years. History and physical notes (19,854/34,771, 57.1%) and ambulatory progress notes (265,302/563,273, 47.1%) were most likely to include sensitive terms. The highest prevalence of notes with sensitive terms was found in pain management (950/1112, 85.4%) and child abuse (1092/1282, 85.2%) clinics.ConclusionsNotes containing sensitive terms are not limited to adolescent patients, specific note types, or certain specialties. Recognition of sensitive terms across all ages and clinical settings complicates efforts to protect patient and caregiver privacy in the era of information-blocking regulations.
| S-EPMC9233261 | biostudies-literature
Project description:IntroductionPeople with Parkinson disease (PD) may be at increased risk of delirium and associated adverse outcomes. Delirium is an acute neuropsychiatric syndrome defined by confusion and inattention and is common in older adults. Previous studies may have underestimated the prevalence of delirium in PD because of overlapping symptoms, lack of awareness, and poorly defined criteria. We aimed to identify the prevalence and incidence of delirium in inpatients with PD.MeasurementsParticipants were inpatients with PD admitted over a 4-month period. Delirium prevalence was classified using a standardised assessment at a single visit on the basis of the Diagnostic and Statistical Manual of Mental Disorders fifth edition (DSM-5) criteria. To capture remaining time in hospital, incident delirium was diagnosed using detailed clinical vignettes and a validated consensus method.ResultsForty-four PD patients consented to take part in the study, accounting for 53 admissions. Delirium prevalence was 34.0% (n = 18); reviewing participants over the duration of their hospital stay identified 30 (56.6%) incident delirium cases. The admitting team screened 24.5% for delirium, and delirium was documented in eight (14.8%) patients' medical notes. Patients with delirium were significantly older, had higher frailty scores, and had a longer hospital stay (P < .05 for all).ConclusionsDelirium is common in PD inpatients at admission and incidence increases during hospital stay, but delirium is commonly missed. Our results highlight the importance of screening for delirium throughout patients' stay in hospital. Future studies should consider frequent evaluation over the duration of hospital stay to identify emergent delirium during the admission.
| S-EPMC7186820 | biostudies-literature
Project description:BackgroundIdentifying caregiver availability, particularly for patients with dementia or those with a disability, is critical to informing the appropriate care planning by the health systems, hospitals, and providers. This information is not readily available, and there is a paucity of pragmatic approaches to automatically identifying caregiver availability and type.ObjectiveOur main objective was to use medical notes to assess caregiver availability and type for hospitalized patients with dementia. Our second objective was to identify whether the patient lived at home or resided at an institution.MethodsIn this retrospective cohort study, we used 2016-2019 telephone-encounter medical notes from a single institution to develop a rule-based natural language processing (NLP) algorithm to identify the patient's caregiver availability and place of residence. Using note-level data, we compared the results of the NLP algorithm with human-conducted chart abstraction for both training (749/976, 77%) and test sets (227/976, 23%) for a total of 223 adults aged 65 years and older diagnosed with dementia. Our outcomes included determining whether the patients (1) reside at home or in an institution, (2) have a formal caregiver, and (3) have an informal caregiver.ResultsTest set results indicated that our NLP algorithm had high level of accuracy and reliability for identifying whether patients had an informal caregiver (F1=0.94, accuracy=0.95, sensitivity=0.97, and specificity=0.93), but was relatively less able to identify whether the patient lived at an institution (F1=0.64, accuracy=0.90, sensitivity=0.51, and specificity=0.98). The most common explanations for NLP misclassifications across all categories were (1) incomplete or misspelled facility names; (2) past, uncertain, or undecided status; (3) uncommon abbreviations; and (4) irregular use of templates.ConclusionsThis innovative work was the first to use medical notes to pragmatically determine caregiver availability. Our NLP algorithm identified whether hospitalized patients with dementia have a formal or informal caregiver and, to a lesser extent, whether they lived at home or in an institutional setting. There is merit in using NLP to identify caregivers. This study serves as a proof of concept. Future work can use other approaches and further identify caregivers and the extent of their availability.
| S-EPMC9539648 | biostudies-literature