Adaptation of an NLP system to a new healthcare environment to identify social determinants of health

Reeves, Ruth; Christensen, Lee M.; Brown, Jeremiah R.; Conway, Michael; Levis, Maxwell; Gobbel, Glenn T.; Shah, Rashmee U.; Goodrich, Christine A.; Ricket, Iben; Minter, Freneka F.; Bohm, Andrew; Bray, Bruce E.; Matheny, Michael E.; Chapman, Wendy W.

doi:10.1016/j.jbi.2021.103851

Cited by 32 publications

(33 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Methods related to this NLP programming model are described elsewhere. 13 Briefly, the rule‐based NLP tool, Moonstone, was applied to a corpus of clinical notes dated between the index AMI hospitalization and 30 days after discharge of the AMI cohorts at both sites. All notes were processed for 7 measures of social risk, mapping to the following classifications: living alone, instrumental support, medication noncompliance (called medication compliance), impaired activity of daily living (ADL) or impaired instrumental activities of daily living, medical condition affecting ADL/instrumental activities of daily living, dementia, and depression.…”

Section: Methodsmentioning

confidence: 99%

“…Performance metrics for Moonstone include 0.83, 0.74, and 0.78 for precision, recall, and F1 measure, respectively. 13 Definitions for each social risk factor classification are found in Table S1 . The social risk factor data derived by Moonstone's processing of all notes in both facilities’ corpora was rolled up to the encounter level, denoting a presence or absence of a social risk factor for each classification.…”

Section: Methodsmentioning

confidence: 99%

“… 6 , 7 , 8 , 9 In addition, social risk factors are rarely included in readmission prediction models, despite their established role in health outcomes and hospital readmissions. 5 , 10 , 11 , 12 , 13 …”

mentioning

confidence: 99%

“…Computational advances allow us to ascertain structured and unstructured textual data from clinical documentation that were previously difficult to extract, including social risk factors (eg, medication adherence, homelessness, and at‐home support). 13 , 18 These factors have promise for improving risk prediction, dependent on successful data ascertainment. 3 , 4 Moreover, social risk factors are disproportionately seen among vulnerable and high‐need populations, a group that experiences higher risk for readmissions.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Information Extraction From Electronic Health Records to Predict Readmission Following Acute Myocardial Infarction: Does Natural Language Processing Using Clinical Notes Improve Prediction of Readmission?

Brown

Ricket

Reeves

et al. 2022

JAHA

Self Cite

View full text Add to dashboard Cite

Background Social risk factors influence rehospitalization rates yet are challenging to incorporate into prediction models. Integration of social risk factors using natural language processing (NLP) and machine learning could improve risk prediction of 30‐day readmission following an acute myocardial infarction. Methods and Results Patients were enrolled into derivation and validation cohorts. The derivation cohort included inpatient discharges from Vanderbilt University Medical Center between January 1, 2007, and December 31, 2016, with a primary diagnosis of acute myocardial infarction, who were discharged alive, and not transferred from another facility. The validation cohort included patients from Dartmouth‐Hitchcock Health Center between April 2, 2011, and December 31, 2016, meeting the same eligibility criteria described above. Data from both sites were linked to Centers for Medicare & Medicaid Services administrative data to supplement 30‐day hospital readmissions. Clinical notes from each cohort were extracted, and an NLP model was deployed, counting mentions of 7 social risk factors. Five machine learning models were run using clinical and NLP‐derived variables. Model discrimination and calibration were assessed, and receiver operating characteristic comparison analyses were performed. The 30‐day rehospitalization rates among the derivation (n=6165) and validation (n=4024) cohorts were 15.1% (n=934) and 10.2% (n=412), respectively. The derivation models demonstrated no statistical improvement in model performance with the addition of the selected NLP‐derived social risk factors. Conclusions Social risk factors extracted using NLP did not significantly improve 30‐day readmission prediction among hospitalized patients with acute myocardial infarction. Alternative methods are needed to capture social risk factors.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Information Extraction From Electronic Health Records to Predict Readmission Following Acute Myocardial Infarction: Does Natural Language Processing Using Clinical Notes Improve Prediction of Readmission?

Brown

Ricket

Reeves

et al. 2022

JAHA

Self Cite

View full text Add to dashboard Cite

show abstract

“…The use of large datasets with detailed information about therapeutic activities and outcomes including SDH, functional assessment scores, and patient-reported outcome measures could improve treatment precision and optimize patient success. Natural language processing (NLP), language modeling and word embedding techniques could be used on provider notes to find items from patient interactions or audio files that are related to SDH and functionality ( 66 ). For example, NLP can be used to identify which patients are more likely to miss therapy, or functional recovery time could be predicted for resource allocation and treatment planning ( 67 ), as well as identify SDH impact on functional progress among physiatric patients.…”

Section: Leveraging Big Data and Expanding Machine Learning In Physiatrymentioning

confidence: 99%

Social Determinants of Health in Physiatry: Challenges and Opportunities for Clinical Decision Making and Improving Treatment Precision

Conic

Geis

Vincent

2021

Front. Public Health

View full text Add to dashboard Cite

Physiatry is a medical specialty focused on improving functional outcomes in patients with a variety of medical conditions that affect the brain, spinal cord, peripheral nerves, muscles, bones, joints, ligaments, and tendons. Social determinants of health (SDH) play a key role in determining therapeutic process and patient functional outcomes. Big data and precision medicine have been used in other fields and to some extent in physiatry to predict patient outcomes, however many challenges remain. The interplay between SDH and physiatry outcomes is highly variable depending on different phases of care, and more favorable patient profiles in acute care may be less favorable in the outpatient setting. Furthermore, SDH influence which treatments or interventional procedures are accessible to the patient and thus determine outcomes. This opinion paper describes utility of existing datasets in combination with novel data such as movement, gait patterning and patient perceived outcomes could be analyzed with artificial intelligence methods to determine the best treatment plan for individual patients in order to achieve maximal functional capacity.

show abstract

Classifying Individuals With Rheumatic Conditions as Financially Insecure Using Electronic Health Record Data and Natural Language Processing: Algorithm Derivation and Validation

Chandler,

Cai,

Santacroce

et al. 2024

ACR Open Rheumatology

View full text Add to dashboard Cite

ObjectiveWe aimed to examine the feasibility of applying natural language processing (NLP) to unstructured electronic health record (EHR) documents to detect the presence of financial insecurity among patients with rheumatologic disease enrolled in an integrated care management program (iCMP).MethodsWe incorporated supervised, rule‐based NLP and statistical methods to identify financial insecurity among patients with rheumatic conditions enrolled in an iCMP (n = 20,395) in a multihospital EHR system. We constructed a lexicon for financial insecurity using data from available knowledge sources and then reviewed EHR notes from 538 randomly selected individuals (training cohort n = 366, validation cohort n = 172). We manually categorized records as having “definite,” “possible,” or “no” mention of financial insecurity. All available notes were processed using Narrative Information Linear Extraction, a rule‐based version of NLP. Models were trained using the NLP features for financial insecurity using logistic, least absolute shrinkage operator (LASSO), and random forest performance characteristic and were compared with the reference standard.ResultsA total of 245,142 notes were processed from 538 individual patient records. Financial insecurity was present among 100 (27%) individuals in the training cohort and 63 (37%) in the validation cohort. The LASSO and random forest models performed identically and slightly better than logistic regression, with positive predictive values of 0.90, sensitivities of 0.29, and specificities of 0.98.ConclusionThe development of a context‐driven lexicon used with rule‐based NLP to extract data that identify financial insecurity is feasible for use and improved the capture for presence of financial insecurity with high accuracy. In the absence of a standard lexicon and construct definition for financial insecurity status, additional studies are needed to optimize the sensitivity of algorithms to categorize financial insecurity with construct validity.

show abstract

Adaptation of an NLP system to a new healthcare environment to identify social determinants of health

Cited by 32 publications

References 24 publications

Information Extraction From Electronic Health Records to Predict Readmission Following Acute Myocardial Infarction: Does Natural Language Processing Using Clinical Notes Improve Prediction of Readmission?

Information Extraction From Electronic Health Records to Predict Readmission Following Acute Myocardial Infarction: Does Natural Language Processing Using Clinical Notes Improve Prediction of Readmission?

Social Determinants of Health in Physiatry: Challenges and Opportunities for Clinical Decision Making and Improving Treatment Precision

Classifying Individuals With Rheumatic Conditions as Financially Insecure Using Electronic Health Record Data and Natural Language Processing: Algorithm Derivation and Validation

Contact Info

Product

Resources

About