PMH52 Use of a Natural Language Processing-Based Approach to Extract Suicide Ideation and Behavior from Clinical Notes to Support Depression Research

2021 ◽  
Vol 24 ◽  
pp. S137
Author(s):  
N. Palmon ◽  
S. Momen ◽  
M. Leavy ◽  
G. Curhan ◽  
C. Boussios ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Suicide Ideation ◽  
Clinical Notes ◽  
And Behavior

The Use of Natural Language Processing to Ascertain Suicide Ideation/Attempt from Clinical Notes Within a Large Integrated Healthcare System (Preprint)

2021 ◽  
Author(s):  
Fagen Xie ◽  
Deborah S Ling-Grant ◽  
John Chang ◽  
Britta I Amundsen ◽  
Rulin C Hechter
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Electronic Health Record ◽  
Language Processing ◽  
Suicide Ideation ◽  
Validation Dataset ◽  
Health Record ◽  
Integrated Healthcare ◽  
Entire Study ◽  
Clinical Notes

UNSTRUCTURED Purpose: Identifying risk factors for suicide using progress notes and administrative data is time consuming and usually requires manual case review. In this study, a natural language processing computerized algorithm was developed and implemented to automatically ascertain suicide ideation/attempt from clinical notes in a large integrated healthcare system, Kaiser Permanente Southern California. Methods: Clinical notes containing prespecified relevant keywords and phrases related to suicidal ideation/attempt between 2010 and 2018 were extracted from our organization’s electronic health record system. A random sample of 864 clinical notes was selected and equally divided into four subsets. These subsets were reviewed and classified as one of the following three suicide ideation/attempt categories: “Current”, “Historical” and “No” for each note by experienced research chart abstractors. The first three training datasets were used to develop the rule-based computerized algorithm sequentially and the fourth validation dataset was used to evaluate the algorithm performance. The validated algorithm was then applied to the entire study sample of clinical notes. Results: The computerized algorithm ascertained 23 of the 26 confirmed “Current” suicide ideation/attempt events and all 10 confirmed “Historical” suicide ideation/attempt events in the validation dataset. This algorithm produced a 88.5% sensitivity and 100.0% positive predictive value (PPV) for “Current” suicide ideation/attempt, and a 100.0% sensitivity and 100.0% PPV for “Historical” suicide ideation/attempt. After applying the computerized process to the entire study population sample, we identified a total of 1,050,289 “Current” ideation/attempt events and 293,038 “Historical” ideation/attempt events during the study period. Among the 400,436 individuals who were identified as having a “Current” suicide ideation/attempt event, 115,197 (28.8%) were 15-24 years old at the first event, 234,924 (58.7%) were female, 165,084 (41.7%) were Hispanic, and 150,645 (37.6%) had two or more events in the study period. Conclusions: Our study demonstrated that a natural language processing computerized algorithm can effectively ascertain suicide ideation/attempt from the free-text clinical notes in the electronic health record of a diverse patient population. This algorithm can be utilized in support of suicide prevention programs and patient care management.

Systematic review of current natural language processing methods and applications in cardiology

Heart ◽  
2021 ◽  
pp. heartjnl-2021-319769
Author(s):  
Meghan Reading Turchioe ◽  
Alexander Volodarskiy ◽  
Jyotishman Pathak ◽  
Drew N Wright ◽  
James Enlou Tcheng ◽  
...  
Keyword(s):  
Systematic Review ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Clinical Care ◽  
Real World Data ◽  
Clinical Text ◽  
Clinical Notes ◽  
Artery Disease ◽  
Automated Methods

Natural language processing (NLP) is a set of automated methods to organise and evaluate the information contained in unstructured clinical notes, which are a rich source of real-world data from clinical care that may be used to improve outcomes and understanding of disease in cardiology. The purpose of this systematic review is to provide an understanding of NLP, review how it has been used to date within cardiology and illustrate the opportunities that this approach provides for both research and clinical care. We systematically searched six scholarly databases (ACM Digital Library, Arxiv, Embase, IEEE Explore, PubMed and Scopus) for studies published in 2015–2020 describing the development or application of NLP methods for clinical text focused on cardiac disease. Studies not published in English, lacking a description of NLP methods, non-cardiac focused and duplicates were excluded. Two independent reviewers extracted general study information, clinical details and NLP details and appraised quality using a checklist of quality indicators for NLP studies. We identified 37 studies developing and applying NLP in heart failure, imaging, coronary artery disease, electrophysiology, general cardiology and valvular heart disease. Most studies used NLP to identify patients with a specific diagnosis and extract disease severity using rule-based NLP methods. Some used NLP algorithms to predict clinical outcomes. A major limitation is the inability to aggregate findings across studies due to vastly different NLP methods, evaluation and reporting. This review reveals numerous opportunities for future NLP work in cardiology with more diverse patient samples, cardiac diseases, datasets, methods and applications.

Development of algorithm for classification smoking status from unstructured bilingual electronic health records based on natural language processing (Preprint)

2021 ◽  
Author(s):  
Ye Seul Bae ◽  
Kyung Hwan Kim ◽  
Han Kyul Kim ◽  
Sae Won Choi ◽  
Taehoon Ko ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Electronic Health Records ◽  
Natural Language ◽  
Language Processing ◽  
Smoking Status ◽  
Svm Classifier ◽  
Keyword Extraction ◽  
Health Records ◽  
Clinical Notes ◽  
Electronic Health

BACKGROUND Smoking is a major risk factor and important variable for clinical research, but there are few studies regarding automatic obtainment of smoking classification from unstructured bilingual electronic health records (EHR). OBJECTIVE We aim to develop an algorithm to classify smoking status based on unstructured EHRs using natural language processing (NLP). METHODS With acronym replacement and Python package Soynlp, we normalize 4,711 bilingual clinical notes. Each EHR notes was classified into 4 categories: current smokers, past smokers, never smokers, and unknown. Subsequently, SPPMI (Shifted Positive Point Mutual Information) is used to vectorize words in the notes. By calculating cosine similarity between these word vectors, keywords denoting the same smoking status are identified. RESULTS Compared to other keyword extraction methods (word co-occurrence-, PMI-, and NPMI-based methods), our proposed approach improves keyword extraction precision by as much as 20.0%. These extracted keywords are used in classifying 4 smoking statuses from our bilingual clinical notes. Given an identical SVM classifier, the extracted keywords improve the F1 score by as much as 1.8% compared to those of the unigram and bigram Bag of Words. CONCLUSIONS Our study shows the potential of SPPMI in classifying smoking status from bilingual, unstructured EHRs. Our current findings show how smoking information can be easily acquired and used for clinical practice and research.

Identifying Heart Failure Symptoms and Poor Self-Management in Home Healthcare: A Natural Language Processing Study

2021 ◽  
Author(s):  
Sena Chae ◽  
Jiyoun Song ◽  
Marietta Ojo ◽  
Maxim Topaz
Keyword(s):  
Heart Failure ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Symptom Management ◽  
Home Healthcare ◽  
Self Management ◽  
Clinical Notes ◽  
Patients With Heart Failure

The goal of this natural language processing (NLP) study was to identify patients in home healthcare with heart failure symptoms and poor self-management (SM). The preliminary lists of symptoms and poor SM status were identified, NLP algorithms were used to refine the lists, and NLP performance was evaluated using 2.3 million home healthcare clinical notes. The overall precision to identify patients with heart failure symptoms and poor SM status was 0.86. The feasibility of methods was demonstrated to identify patients with heart failure symptoms and poor SM documented in home healthcare notes. This study facilitates utilizing key symptom information and patients’ SM status from unstructured data in electronic health records. The results of this study can be applied to better individualize symptom management to support heart failure patients’ quality-of-life.

scholarly journals A Natural Language Processing Approach to Automated Highlighting of New Information in Clinical Notes

2020 ◽  
Vol 10 (8) ◽  
pp. 2824
Author(s):  
Yu-Hsiang Su ◽  
Ching-Ping Chao ◽  
Ling-Chien Hung ◽  
Sheng-Feng Sung ◽  
Pei-Ju Lee
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Task Performance ◽  
Language Processing ◽  
Automated Identification ◽  
Clinical Notes ◽  
New Information ◽  
Perceived Workload ◽  
The Impact ◽  
User Experiment

Electronic medical records (EMRs) have been used extensively in most medical institutions for more than a decade in Taiwan. However, information overload associated with rapid accumulation of large amounts of clinical narratives has threatened the effective use of EMRs. This situation is further worsened by the use of “copying and pasting”, leading to lots of redundant information in clinical notes. This study aimed to apply natural language processing techniques to address this problem. New information in longitudinal clinical notes was identified based on a bigram language model. The accuracy of automated identification of new information was evaluated using expert annotations as the reference standard. A two-stage cross-over user experiment was conducted to evaluate the impact of highlighting of new information on task demands, task performance, and perceived workload. The automated method identified new information with an F1 score of 0.833. The user experiment found a significant decrease in perceived workload associated with a significantly higher task performance. In conclusion, automated identification of new information in clinical notes is feasible and practical. Highlighting of new information enables healthcare professionals to grasp key information from clinical notes with less perceived workload.

scholarly journals Using Clinical Notes and Natural Language Processing for Automated HIV Risk Assessment

2018 ◽  
Vol 77 (2) ◽  
pp. 160-166 ◽  
Author(s):  
Daniel J. Feller ◽  
Jason Zucker ◽  
Michael T. Yin ◽  
Peter Gordon ◽  
Noémie Elhadad
Keyword(s):  
Risk Assessment ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Hiv Risk ◽  
Clinical Notes ◽  
Hiv Risk Assessment

scholarly journals The 2019 n2c2/OHNLP Track on Clinical Semantic Textual Similarity: Overview (Preprint)

2020 ◽  
Author(s):  
Yanshan Wang ◽  
Sunyang Fu ◽  
Feichen Shen ◽  
Sam Henry ◽  
Ozlem Uzuner ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
State Of The Art ◽  
Shared Task ◽  
Data Set ◽  
Clinical Text ◽  
Clinical Notes ◽  
Clinical Domain ◽  
Semantic Textual Similarity

BACKGROUND Semantic textual similarity is a common task in the general English domain to assess the degree to which the underlying semantics of 2 text segments are equivalent to each other. Clinical Semantic Textual Similarity (ClinicalSTS) is the semantic textual similarity task in the clinical domain that attempts to measure the degree of semantic equivalence between 2 snippets of clinical text. Due to the frequent use of templates in the Electronic Health Record system, a large amount of redundant text exists in clinical notes, making ClinicalSTS crucial for the secondary use of clinical text in downstream clinical natural language processing applications, such as clinical text summarization, clinical semantics extraction, and clinical information retrieval. OBJECTIVE Our objective was to release ClinicalSTS data sets and to motivate natural language processing and biomedical informatics communities to tackle semantic text similarity tasks in the clinical domain. METHODS We organized the first BioCreative/OHNLP ClinicalSTS shared task in 2018 by making available a real-world ClinicalSTS data set. We continued the shared task in 2019 in collaboration with National NLP Clinical Challenges (n2c2) and the Open Health Natural Language Processing (OHNLP) consortium and organized the 2019 n2c2/OHNLP ClinicalSTS track. We released a larger ClinicalSTS data set comprising 1642 clinical sentence pairs, including 1068 pairs from the 2018 shared task and 1006 new pairs from 2 electronic health record systems, GE and Epic. We released 80% (1642/2054) of the data to participating teams to develop and fine-tune the semantic textual similarity systems and used the remaining 20% (412/2054) as blind testing to evaluate their systems. The workshop was held in conjunction with the American Medical Informatics Association 2019 Annual Symposium. RESULTS Of the 78 international teams that signed on to the n2c2/OHNLP ClinicalSTS shared task, 33 produced a total of 87 valid system submissions. The top 3 systems were generated by IBM Research, the National Center for Biotechnology Information, and the University of Florida, with Pearson correlations of <i>r</i>=.9010, <i>r</i>=.8967, and <i>r</i>=.8864, respectively. Most top-performing systems used state-of-the-art neural language models, such as BERT and XLNet, and state-of-the-art training schemas in deep learning, such as pretraining and fine-tuning schema, and multitask learning. Overall, the participating systems performed better on the Epic sentence pairs than on the GE sentence pairs, despite a much larger portion of the training data being GE sentence pairs. CONCLUSIONS The 2019 n2c2/OHNLP ClinicalSTS shared task focused on computing semantic similarity for clinical text sentences generated from clinical notes in the real world. It attracted a large number of international teams. The ClinicalSTS shared task could continue to serve as a venue for researchers in natural language processing and medical informatics communities to develop and improve semantic textual similarity techniques for clinical text.

Abstract P259: Using Natural Language Processing and Machine Learning to Identify Incident Stroke From Electronic Health Records

Circulation ◽  
2020 ◽  
Vol 141 (Suppl_1) ◽  
Author(s):  
Yiqing Zhao ◽  
Sunyang Fu ◽  
Suzette J Bielinski ◽  
Paul Decker ◽  
Alanna M Chamberlain ◽  
...  
Keyword(s):  
Machine Learning ◽  
Atrial Fibrillation ◽  
Natural Language Processing ◽  
Random Forest ◽  
Natural Language ◽  
Language Processing ◽  
Stroke Incidence ◽  
Clinical Notes ◽  
Feature Sets ◽  
Electronic Health

Background: The focus of most existing phenotyping algorithms based on electronic health record (EHR) data has been to accurately identify cases and non-cases of specific diseases. However, a more challenging task is to accurately identify disease incidence, as identifying the first occurrence of disease is more important for efficient and valid clinical and epidemiological research. Moreover, stroke is a challenging phenotype due to diagnosis difficulty and common miscoding. This task generally requires utilization of multiple types of EHR data (e.g., diagnoses and procedure codes, unstructured clinical notes) and a more robust algorithm integrating both natural language processing and machine learning. In this study, we developed and validated an EHR-based classifier to accurately identify stroke incidence among a cohort of atrial fibrillation (AF) patients Methods: We developed a stroke phenotyping algorithm using International Classification of Diseases, Ninth Revision (ICD-9) codes, Current Procedural Terminology (CPT) codes, and expert-provided keywords as model features. Structured data was extracted from Rochester Epidemiology Project (REP) database. Natural Language Processing (NLP) was used to extract and validate keyword occurrence in clinical notes. A window of ±30 days was considered when including/excluding keywords/codes into the input vector. Frequencies of keywords/codes were used as input feature sets for model training. Multiple competing models were trained using various combinations of feature sets and two machine learning algorithms: logistic regression and random forest. Training data were provided by two nurse abstractors and included validated stroke incidences from a previously established atrial fibrillation cohort. Precision, recall, and F-score of the algorithm were calculated to assess and compare model performances. Results: Among 4,914 patients with atrial fibrillation, 1,773 patients were screened. 3,141 patients had no stroke-related codes or keywords and were presumed to be free of stroke during follow-up. Among the screened patients, 740 had validated strokes and 1,033 did not have a stroke based on review of the EHR by trained nurse abstractors. The best performing stroke incidence phenotyping classifier utilized Keywords+ICD-9+CPT features using a random forest classifier, achieving a precision of 0.942, recall of 0.943, and F-score of 0.943. Conclusion: In conclusion, we developed and validated a stroke algorithm that performed well for identifying stroke incidence in an enriched population (AF cohort), which extends beyond the typical binary case/non-case stroke identification problem. Future work will involve testing the generalizability of this algorithm in a general population.

Sign in / Sign up

Export Citation Format

Share Document