Dataset Information

Assessing longitudinal housing status using Electronic Health Record data: a comparison of natural language processing, structured data, and patient-reported history.

ABSTRACT:

Introduction

Measuring long-term housing outcomes is important for evaluating the impacts of services for individuals with homeless experience. However, assessing long-term housing status using traditional methods is challenging. The Veterans Affairs (VA) Electronic Health Record (EHR) provides detailed data for a large population of patients with homeless experiences and contains several indicators of housing instability, including structured data elements (e.g., diagnosis codes) and free-text clinical narratives. However, the validity of each of these data elements for measuring housing stability over time is not well-studied.

Methods

We compared VA EHR indicators of housing instability, including information extracted from clinical notes using natural language processing (NLP), with patient-reported housing outcomes in a cohort of homeless-experienced Veterans.

Results

NLP achieved higher sensitivity and specificity than standard diagnosis codes for detecting episodes of unstable housing. Other structured data elements in the VA EHR showed promising performance, particularly when combined with NLP.

Discussion

Evaluation efforts and research studies assessing longitudinal housing outcomes should incorporate multiple data sources of documentation to achieve optimal performance.

SUBMITTER: Chapman AB

PROVIDER: S-EPMC10244644 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Assessing longitudinal housing status using Electronic Health Record data: a comparison of natural language processing, structured data, and patient-reported history.

Chapman Alec B AB Cordasco Kristina K Chassman Stephanie S Panadero Talia T Agans Dylan D Jackson Nicholas N Clair Kimberly K Nelson Richard R Montgomery Ann Elizabeth AE Tsai Jack J Finley Erin E Gabrielian Sonya S

Frontiers in artificial intelligence 20230524

<h4>Introduction</h4>Measuring long-term housing outcomes is important for evaluating the impacts of services for individuals with homeless experience. However, assessing long-term housing status using traditional methods is challenging. The Veterans Affairs (VA) Electronic Health Record (EHR) provides detailed data for a large population of patients with homeless experiences and contains several indicators of housing instability, including structured data elements (e.g., diagnosis codes) and fr ...[more]

PMID: 37293237

Similar Datasets

Project description:BackgroundAbstracting cerebrovascular disease (CeVD) from inpatient electronic medical records (EMRs) through natural language processing (NLP) is pivotal for automated disease surveillance and improving patient outcomes. Existing methods rely on coders' abstraction, which has time delays and under-coding issues. This study sought to develop an NLP-based method to detect CeVD using EMR clinical notes.MethodsCeVD status was confirmed through a chart review on randomly selected hospitalized patients who were 18 years or older and discharged from 3 hospitals in Calgary, Alberta, Canada, between January 1 and June 30, 2015. These patients' chart data were linked to administrative discharge abstract database (DAD) and Sunrise™ Clinical Manager (SCM) EMR database records by Personal Health Number (a unique lifetime identifier) and admission date. We trained multiple natural language processing (NLP) predictive models by combining two clinical concept extraction methods and two supervised machine learning (ML) methods: random forest and XGBoost. Using chart review as the reference standard, we compared the model performances with those of the commonly applied International Classification of Diseases (ICD-10-CA) codes, on the metrics of sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).ResultOf the study sample (n = 3036), the prevalence of CeVD was 11.8% (n = 360); the median patient age was 63; and females accounted for 50.3% (n = 1528) based on chart data. Among 49 extracted clinical documents from the EMR, four document types were identified as the most influential text sources for identifying CeVD disease ("nursing transfer report," "discharge summary," "nursing notes," and "inpatient consultation."). The best performing NLP model was XGBoost, combining the Unified Medical Language System concepts extracted by cTAKES (e.g., top-ranked concepts, "Cerebrovascular accident" and "Transient ischemic attack"), and the term frequency-inverse document frequency vectorizer. Compared with ICD codes, the model achieved higher validity overall, such as sensitivity (25.0% vs 70.0%), specificity (99.3% vs 99.1%), PPV (82.6 vs. 87.8%), and NPV (90.8% vs 97.1%).ConclusionThe NLP algorithm developed in this study performed better than the ICD code algorithm in detecting CeVD. The NLP models could result in an automated EMR tool for identifying CeVD cases and be applied for future studies such as surveillance, and longitudinal studies.

Project description:ImportanceAccurate prediction of outcomes among patients in intensive care units (ICUs) is important for clinical research and monitoring care quality. Most existing prediction models do not take full advantage of the electronic health record, using only the single worst value of laboratory tests and vital signs and largely ignoring information present in free-text notes. Whether capturing more of the available data and applying machine learning and natural language processing (NLP) can improve and automate the prediction of outcomes among patients in the ICU remains unknown.ObjectivesTo evaluate the change in power for a mortality prediction model among patients in the ICU achieved by incorporating measures of clinical trajectory together with NLP of clinical text and to assess the generalizability of this approach.Design, setting, and participantsThis retrospective cohort study included 101 196 patients with a first-time admission to the ICU and a length of stay of at least 4 hours. Twenty ICUs at 2 academic medical centers (University of California, San Francisco [UCSF], and Beth Israel Deaconess Medical Center [BIDMC], Boston, Massachusetts) and 1 community hospital (Mills-Peninsula Medical Center [MPMC], Burlingame, California) contributed data from January 1, 2001, through June 1, 2017. Data were analyzed from July 1, 2017, through August 1, 2018.Main outcomes and measuresIn-hospital mortality and model discrimination as assessed by the area under the receiver operating characteristic curve (AUC) and model calibration as assessed by the modified Hosmer-Lemeshow statistic.ResultsAmong 101 196 patients included in the analysis, 51.3% (n = 51 899) were male, with a mean (SD) age of 61.3 (17.1) years; their in-hospital mortality rate was 10.4% (n = 10 505). A baseline model using only the highest and lowest observed values for each laboratory test result or vital sign achieved a cross-validated AUC of 0.831 (95% CI, 0.830-0.832). In contrast, that model augmented with measures of clinical trajectory achieved an AUC of 0.899 (95% CI, 0.896-0.902; P < .001 for AUC difference). Further augmenting this model with NLP-derived terms associated with mortality further increased the AUC to 0.922 (95% CI, 0.916-0.924; P < .001). These NLP-derived terms were associated with improved model performance even when applied across sites (AUC difference for UCSF: 0.077 to 0.021; AUC difference for MPMC: 0.071 to 0.051; AUC difference for BIDMC: 0.035 to 0.043; P < .001) when augmenting with NLP at each site.Conclusions and relevanceIntensive care unit mortality prediction models incorporating measures of clinical trajectory and NLP-derived terms yielded excellent predictive performance and generalized well in this sample of hospitals. The role of these automated algorithms, particularly those using unstructured data from notes and other sources, in clinical research and quality improvement seems to merit additional investigation.

Project description:IntroductionPeople often experience significant difficulties in receiving mental healthcare due to insufficient resources, stigma and lack of access to care. Remote care technology has the potential to overcome these barriers by reducing travel time and increasing frequency of contact with patients. However, the safe delivery of remote mental healthcare requires evidence on which aspects of care are suitable for remote delivery and which are better served by in-person care. We aim to investigate clinical and demographic associations with remote mental healthcare in a large electronic health record (EHR) dataset and the degree to which remote care is associated with differences in clinical outcomes using natural language processing (NLP) derived EHR data.Methods and analysisDeidentified EHR data, derived from the South London and Maudsley (SLaM) National Health Service Foundation Trust Biomedical Research Centre (BRC) Case Register, will be extracted using the Clinical Record Interactive Search tool for all patients receiving mental healthcare between 1 January 2019 and 31 March 2022. First, data on a retrospective, longitudinal cohort of around 80 000 patients will be analysed using descriptive statistics to investigate clinical and demographic associations with remote mental healthcare and multivariable Cox regression to compare clinical outcomes of remote versus in-person assessments. Second, NLP models that have been previously developed to extract mental health symptom data will be applied to around 5 million documents to analyse the variation in content of remote versus in-person assessments.Ethics and disseminationThe SLaM BRC Case Register and Clinical Record Interactive Search (CRIS) tool have received ethical approval as a deidentified dataset (including NLP-derived data from unstructured free text documents) for secondary mental health research from Oxfordshire REC C (Ref: 18/SC/0372). The study has received approval from the SLaM CRIS Oversight Committee. Study findings will be disseminated through peer-reviewed, open access journal articles and service user and carer advisory groups.

Project description:ObjectiveTo demonstrate that electronic health record (EHR) data can be used in an automated approach to evaluate cataract surgery outcomes.DesignRetrospective analysis.SubjectsResident and faculty surgeons.MethodsElectronic health record data were collected from cataract surgeries performed at the Johns Hopkins Wilmer Eye Institute, and cases were categorized into resident or attending as primary surgeon. Preoperative and postoperative visual acuity (VA) and unplanned return to operating room were extracted from the EHR.Main outcome measuresPostoperative VA and reoperation rate within 90 days.ResultsThis study analyzed 14 537 cataract surgery cases over 32 months. Data were extracted from the EHR using an automated approach to assess surgical outcomes for resident and attending surgeons. Of 337 resident surgeries with both preoperative and postoperative VA data, 248 cases (74%) had better postoperative VA, and 170 cases (51%) had more than 2 lines improvement. There was no statistical difference in the proportion of cases with better postoperative VA or more than 2 lines improvement between resident and attending cases. Attending surgeons had a statistically greater proportion of cases with postoperative VA better than 20/40, but this finding has to be considered in the context that, on average, resident cases started out with poorer baseline VA.A multivariable regression model of VA outcomes vs. resident/attending status that controlled for preoperative VA, patient age, American Society of Anesthesiologists (ASA) score, and estimated income found that resident status, preoperative VA, patient age, ASA score, and estimated income were all significant predictors of VA. The rate of unplanned return to the operating room within 90 days of cataract surgery was not statistically different between resident (1.8%) and attending (1.2%) surgeons.ConclusionsThis study demonstrates that EHR data can be used to evaluate and monitor surgical outcomes in an ongoing way. Analysis of EHR-extracted cataract outcome data showed that preoperative VA, ASA classification, and attending/resident status were important in predicting postoperative VA outcomes. These findings suggest that the utilization of EHR data could enable continuous assessment of surgical outcomes and inform interventions to improve resident training. Financial Disclosure(s): Proprietary or commercial disclosure may be found after the references.

Dataset Information

Assessing longitudinal housing status using Electronic Health Record data: a comparison of natural language processing, structured data, and patient-reported history.

Introduction

Methods

Results

Discussion

Publications

Assessing longitudinal housing status using Electronic Health Record data: a comparison of natural language processing, structured data, and patient-reported history.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets