2018
DOI: 10.1186/s12911-018-0617-7
|View full text |Cite
|
Sign up to set email alerts
|

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

Abstract: BackgroundWe examined the comparative performance of structured, diagnostic codes vs. natural language processing (NLP) of unstructured text for screening suicidal behavior among pregnant women in electronic medical records (EMRs).MethodsWomen aged 10–64 years with at least one diagnostic code related to pregnancy or delivery (N = 275,843) from Partners HealthCare were included as our “datamart.” Diagnostic codes related to suicidal behavior were applied to the datamart to screen women for suicidal behavior. A… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
41
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
5
1
1

Relationship

3
4

Authors

Journals

citations
Cited by 54 publications
(41 citation statements)
references
References 60 publications
0
41
0
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%
“…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%
“…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 . Psychiatrists manually reviewed clinical charts to identify relevant features for suicidal behaviour and to obtain gold‐standard labels.…”
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%
See 2 more Smart Citations