Screening pregnant women for suicidal behavior in electronic medical records: diagnostic codes vs. clinical notes processed by natural language processing

Zhong, Qiu‐Yue; Karlson, Elizabeth W.; Gelaye, Bizu; Finan, Sean; Avillach, Paul; Smoller, Jordan W.; Cai, Tianxi; Williams, Michelle A.

doi:10.1186/s12911-018-0617-7

Cited by 49 publications

(39 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many institutions have established clinical data repositories (CDRs) in conjunction with cohort discovery tools, such as i2b2, to enable investigators to use EHR data for cohort identification in clinical trials and retrospective clinical studies. As much of the detailed patient information is embedded in clinical narratives, cohort identification using only structured data such as diagnosis codes or procedure codes has limited retrieval performance [2][3][4][5]. Natural Language Processing (NLP) techniques have shown promise to be leveraged for various applications in clinical research [6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Implementation of a Cohort Retrieval System for Clinical Data Repositories Using the Observational Medical Outcomes Partnership Common Data Model: Proof-of-Concept System Validation (Preprint)

Liu¹,

Wang²,

Wen³

et al. 2019

Preprint

View full text Add to dashboard Cite

150-250 words)Background: Widespread adoption of electronic health records (EHRs) has enabled secondary use of EHR data for clinical research and healthcare delivery. Natural language processing (NLP) techniques have shown promise in their capability to extract the embedded information in unstructured clinical data, and information retrieval (IR) techniques provide flexible and scalable solutions that can augment the NLP systems for retrieving and ranking relevant records. Methods:In this paper, we present the implementation of Cohort Retrieval Enhanced by Analysis of Text from EHRs (CREATE), a cohort retrieval system that can execute textual cohort selection queries on both structured and unstructured EHR data. CREATE is a proof-of-concept system that leverages a combination of structured queries and IR techniques on NLP results to improve cohort retrieval performance while adopting the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) to enhance model portability. The NLP component empowered by cTAKES is used to extract CDM concepts from textual queries. We design a hierarchical index in Elasticsearch to support CDM concept search utilizing IR techniques and frameworks.Results: Our case study on 5 cohort identification queries evaluated using the IR metric, P@5 (Precision at 5) at both the patient-level and document-level, demonstrates that CREATE achieves an average P@5 of 0.90, which outperforms systems using only structured data or only unstructured data with average P@5s of 0.54 and 0.74, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Implementation of a Cohort Retrieval System for Clinical Data Repositories Using the Observational Medical Outcomes Partnership Common Data Model: Proof-of-Concept System Validation (Preprint)

Liu¹,

Wang²,

Wen³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

“…This algorithm combined information from codified billing data (ICD codes related to suicidal behaviour), clinical notes processed by natural language processing (NLP), and medications in electronic prescriptions. The process of NLP has been described in detail elsewhere . In brief, we first screened for suicidal behaviour using diagnostic codes.…”

Section: Methodsmentioning

confidence: 99%

“…Since suicidal behaviour is not well coded in the EMRs, we previously trained a machine learning algorithm (adaptive elastic net) to classify the presence of suicidal behaviour during pregnancy leveraging additional information embedded in the clinical notes. 21,22 Psychiatrists manually reviewed clinical charts to identify relevant features for suicidal behaviour and to obtain gold-standard labels. This algorithm combined information from codified billing data (ICD codes related to suicidal behaviour), clinical notes processed by natural language processing (NLP), and medications in electronic prescriptions.…”

Section: Suicidal Behaviour During Pregnancymentioning

confidence: 99%

“…The process of NLP has been described in detail elsewhere. 21,22 In brief, we first screened for suicidal behaviour using diagnostic codes. Among the women without any diagnostic codes related to suicidal behaviour, we searched clinical notes and identified women with at least one mention of the terms related to suicidal behaviour (suicide, suicidal, suicidality, self harm, self-harm, harm to self, intentional self-harm, deliberate self-harm, self poison, self-poison, passive SI, kill herself, kill myself, killing herself, killing myself, self-injurious, self injurious, self injury, self-inflicted, self inflicted, self mutilation self cutting, deliberate self-cutting).…”

Section: Suicidal Behaviour During Pregnancymentioning

confidence: 99%

See 2 more Smart Citations

Associations of antepartum suicidal behaviour with adverse infant and obstetric outcomes

Zhong

Gelaye

Karlson

et al. 2019

Paediatric Perinatal Epid

Self Cite

View full text Add to dashboard Cite

Background Relatively little is known about antepartum suicidal behaviour and pregnancy outcomes. We examined associations of antepartum suicidal behaviour, alone and in combination with psychiatric disorders, with adverse infant and obstetric outcomes. Methods We included 188 925 singleton livebirths from a retrospective cohort (1996‐2016). Suicidal behaviour, psychiatric disorders, and outcomes were derived from electronic medical records. We performed multivariable logistic regressions with generalised estimating equations to estimate adjusted odds ratios (aOR) with 95% confidence intervals (95%CI). Results The prevalence of antepartum suicidal behaviour was 152.44 per 100 000 singleton livebirths. Nearly two‐thirds (64.24%) of women with suicidal behaviour also had psychiatric disorders. Compared to women without psychiatric disorders and suicidal behaviour, women with psychiatric disorders alone had 1.3‐fold to 1.4‐fold increased odds of delivering low birthweight or preterm infants and 1.2‐fold increased odds of experiencing obstetric complications. Women with suicidal behaviour alone had increased odds of preterm labour (aOR 2.05, 95% CI 1.16, 3.62). Women with both suicidal behaviour and psychiatric disorders had > twofold increased odds of delivering low birthweight (aOR 2.52, 95% CI 1.40, 4.54), preterm birth (aOR 2.44, 95% CI 1.63, 3.66), and low birthweight/preterm birth (aOR 2.30, 95% CI 1.54, 3.44) infants; the odds of preterm labour (aOR 1.62, 95% CI 1.06, 2.47), placental abruption (aOR 2.33, 95% CI 1.20, 4.51), preterm rupture of membranes (aOR 1.63, 95% CI 1.08, 2.46), and postpartum haemorrhage (aOR 1.93, 95%CI 1.09, 3.40) were elevated. Conclusions Antepartum suicidal behaviour, when co‐occurring with psychiatric disorders, is associated with increased odds of adverse infant and obstetric outcomes. Future studies are warranted to understand the causal roles of suicidal behaviour and psychiatric disorders in pregnancy.

show abstract

Validation of an Electronic Health Record–Based Suicide Risk Prediction Modeling Approach Across Multiple Health Care Systems

Barak–Corren

Castro²,

Nock

et al. 2020

JAMA Netw Open

Self Cite

View full text Add to dashboard Cite

IMPORTANCE Suicide is a leading cause of mortality, with suicide-related deaths increasing in recent years. Automated methods for individualized risk prediction have great potential to address this growing public health threat. To facilitate their adoption, they must first be validated across diverse health care settings.OBJECTIVE To evaluate the generalizability and cross-site performance of a risk prediction method using readily available structured data from electronic health records in predicting incident suicide attempts across multiple, independent, US health care systems. DESIGN, SETTING, AND PARTICIPANTSFor this prognostic study, data were extracted from longitudinal electronic health record data comprising International Classification of Diseases, Ninth Revision diagnoses, laboratory test results, procedures codes, and medications for more than 3.7 million patients from 5 independent health care systems participating in the Accessible Research Commons for Health network. Across sites, 6 to 17 years' worth of data were available, up to 2018. Outcomes were defined by International Classification of Diseases, Ninth Revision codes reflecting incident suicide attempts (with positive predictive value >0.70 according to expert clinician medical record review). Models were trained using naive Bayes classifiers in each of the 5 systems. Models were cross-validated in independent data sets at each site, and performance metrics were calculated. Data analysis was performed from November 2017 to August 2019. MAIN OUTCOMES AND MEASURES The primary outcome was suicide attempt as defined by a previously validated case definition using International Classification of Diseases, Ninth Revision codes. The accuracy and timeliness of the prediction were measured at each site. RESULTS Across the 5 health care systems, of the 3 714 105 patients (2 130 454 female [57.2%])included in the analysis, 39 162 cases (1.1%) were identified. Predictive features varied by site but, as expected, the most common predictors reflected mental health conditions (eg, borderline personality disorder, with odds ratios of 8.1-12.9, and bipolar disorder, with odds ratios of 0.9-9.1) and substance use disorders (eg, drug withdrawal syndrome, with odds ratios of 7.0-12.9). Despite variation in geographical location, demographic characteristics, and population health characteristics, model performance was similar across sites, with areas under the curve ranging from 0.71 (95% CI, 0.70-0.72) to 0.76 (95% CI, 0.75-0.77). Across sites, at a specificity of 90%, the models detected a mean of 38% of cases a mean of 2.1 years in advance. CONCLUSIONS AND RELEVANCEAcross 5 diverse health care systems, a computationally efficient approach leveraging the full spectrum of structured electronic health record data was able to detect (continued) Key Points Question Can a process for training machine-learning algorithms based on electronic health records identify individuals at increased risk of suicide attempts across independent health care systems? Abstract (contin...

show abstract

Screening pregnant women for suicidal behavior in electronic medical records: diagnostic codes vs. clinical notes processed by natural language processing

Cited by 49 publications

References 60 publications

Implementation of a Cohort Retrieval System for Clinical Data Repositories Using the Observational Medical Outcomes Partnership Common Data Model: Proof-of-Concept System Validation (Preprint)

Implementation of a Cohort Retrieval System for Clinical Data Repositories Using the Observational Medical Outcomes Partnership Common Data Model: Proof-of-Concept System Validation (Preprint)

Associations of antepartum suicidal behaviour with adverse infant and obstetric outcomes

Validation of an Electronic Health Record–Based Suicide Risk Prediction Modeling Approach Across Multiple Health Care Systems

Contact Info

Product

Resources

About