Employing AI with NLP to Combine EHR’s Structured and Free Text Data to Identify NVAF to Decrease Strokes and Death (Preprint)

2021 ◽  
Author(s):  
Peter Elkin ◽  
Sarah Mullin ◽  
Jack Mardekian ◽  
Chris Crowner ◽  
Sylvester Sakilay ◽  
...  
Keyword(s):  
Language Processing ◽  
Oral Anticoagulants ◽  
Unstructured Data ◽  
Free Text ◽  
Text Data ◽  
Clinical Notes ◽  
The Us ◽  
Text Information ◽  
Icd Codes ◽  
The University

BACKGROUND Non-Valvular Atrial Fibrillation (NVAF), affects almost 6 million Americans and is a major contributor to strokes; but is significantly undiagnosed and undertreated despite explicit guidelines for oral anticoagulation. OBJECTIVE We investigate if use of semi-supervised natural language processing (NLP) of electronic health record’s (EHRs’) free-text information combined with structured EHR data improves NVAF discovery and treatment--perhaps offering a method to prevent thousands of deaths and save billions of dollars. METHODS We abstracted a set of 96,681 participants from the University at Buffalo’s faculty practice’s EHR. NLP was used to index the notes and compare the ability to identify NVAF, CHA2DS2 VASc and HAS-BLED scores using unstructured data (ICD codes) vs. Structured plus Unstructured data from clinical notes. Additionally, we analyzed data from 63,296,120 participants in the Optum and Truven databases to determine the NVAF’s frequency, rates of CHA2DS2 VASc ≥ 2 and no contraindications to oral anticoagulants (OAC), rates of stroke and death in the untreated population, and first year’s costs after stroke. 16,17 RESULTS The structured-plus-unstructured method would have identified 3,976,056 additional true NVAF cases (p<0.001) and improved sensitivity for CHA2DS2-VASc and HAS-BLED scores compared to the structured data alone (P=0.00195, and P<0.001 respectively), a 32.1% improvement. For the US this method would prevent an estimated 176,537 strokes, save 10,575 lives, and save over $13.5 billion. CONCLUSIONS AI-informed bio-surveillance combining NLP of free-text information with structured EHR data improves data completeness, could prevent thousands of strokes, and save lives and funds. This method is applicable to many disorders, with profound public health consequences. CLINICALTRIAL None

scholarly journals Ascertaining Framingham heart failure phenotype from inpatient electronic health record data using natural language processing: a multicentre Atherosclerosis Risk in Communities (ARIC) validation study

BMJ Open ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. e047356
Author(s):  
Carlton R Moore ◽  
Saumya Jain ◽  
Stephanie Haas ◽  
Harish Yadav ◽  
Eric Whitsel ◽  
...  
Keyword(s):  
Language Processing ◽  
Validation Dataset ◽  
Free Text ◽  
Electronic Health Record Data ◽  
Atherosclerosis Risk In Communities ◽  
Clinical Notes ◽  
Atherosclerosis Risk ◽  
Record Data ◽  
Sensitivity Specificity ◽  
Aric Study

ObjectivesUsing free-text clinical notes and reports from hospitalised patients, determine the performance of natural language processing (NLP) ascertainment of Framingham heart failure (HF) criteria and phenotype.Study designA retrospective observational study design of patients hospitalised in 2015 from four hospitals participating in the Atherosclerosis Risk in Communities (ARIC) study was used to determine NLP performance in the ascertainment of Framingham HF criteria and phenotype.SettingFour ARIC study hospitals, each representing an ARIC study region in the USA.ParticipantsA stratified random sample of hospitalisations identified using a broad range of International Classification of Disease, ninth revision, diagnostic codes indicative of an HF event and occurring during 2015 was drawn for this study. A randomly selected set of 394 hospitalisations was used as the derivation dataset and 406 hospitalisations was used as the validation dataset.InterventionUse of NLP on free-text clinical notes and reports to ascertain Framingham HF criteria and phenotype.Primary and secondary outcome measuresNLP performance as measured by sensitivity, specificity, positive-predictive value (PPV) and agreement in ascertainment of Framingham HF criteria and phenotype. Manual medical record review by trained ARIC abstractors was used as the reference standard.ResultsOverall, performance of NLP ascertainment of Framingham HF phenotype in the validation dataset was good, with 78.8%, 81.7%, 84.4% and 80.0% for sensitivity, specificity, PPV and agreement, respectively.ConclusionsBy decreasing the need for manual chart review, our results on the use of NLP to ascertain Framingham HF phenotype from free-text electronic health record data suggest that validated NLP technology holds the potential for significantly improving the feasibility and efficiency of conducting large-scale epidemiologic surveillance of HF prevalence and incidence.

scholarly journals Natural language processing methods for knowledge management—Applying document clustering for fast search and grouping of engineering documents

2021 ◽  
pp. 1063293X2098297
Author(s):  
Ivar Örn Arnarsson ◽  
Otto Frost ◽  
Emil Gustavsson ◽  
Mats Jirstrand ◽  
Johan Malmqvist
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Domain Knowledge ◽  
Clustering Algorithms ◽  
Document Clustering ◽  
Unstructured Data ◽  
Free Text ◽  
Engineering Change ◽  
Engineering Documents

Product development companies collect data in form of Engineering Change Requests for logged design issues, tests, and product iterations. These documents are rich in unstructured data (e.g. free text). Previous research affirms that product developers find that current IT systems lack capabilities to accurately retrieve relevant documents with unstructured data. In this research, we demonstrate a method using Natural Language Processing and document clustering algorithms to find structurally or contextually related documents from databases containing Engineering Change Request documents. The aim is to radically decrease the time needed to effectively search for related engineering documents, organize search results, and create labeled clusters from these documents by utilizing Natural Language Processing algorithms. A domain knowledge expert at the case company evaluated the results and confirmed that the algorithms we applied managed to find relevant document clusters given the queries tested.

Assessing the Difficulty and Time Cost of De-identification in Clinical Narratives

2006 ◽  
Vol 45 (03) ◽  
pp. 246-252 ◽  
Author(s):  
W. F. Phillips ◽  
S. Phansalkar ◽  
S. A. Sims ◽  
J. F. Hurdle ◽  
D. A. Dorr
Keyword(s):  
Regular Expression ◽  
Free Text ◽  
Time Cost ◽  
Clinical Notes ◽  
The Us ◽  
Important Challenge ◽  
Automated Technique ◽  
Manual Review ◽  
Simple Search ◽  
Selection Of

Summary Objective: To characterize the difficulty confronting investigators in removing protected health information (PHI) from cross-discipline, free-text clinical notes, an important challenge to clinical informatics research as recalibrated by the introduction of the US Health Insurance Portability and Accountability Act (HIPAA) and similar regulations. Methods: Randomized selection of clinical narratives from complete admissions written by diverse providers, reviewed using a two-tiered rater system and simple automated regular expression tools. For manual review, two independent reviewers used simple search and replace algorithms and visual scanning to find PHI as defined by HIPAA, followed by an independent second review to detect any missed PHI. Simple automated review was also performed for the “easy” PHI that are number- or date-based. Results: From 262 notes, 2074 PHI, or 7.9 ± 6.1 per note, were found. The average recall (or sensitivity) was 95.9% while precision was 99.6% for single reviewers. Agreement between individual reviewers was strong (ICC = 0.99), although some asymmetry in errors was seen between reviewers (p = 0.001). The automated technique had better recall (98.5%) but worse precision (88.4%) for its subset of identifiers. Manually de-identifying a note took 87.3 ± 61 seconds on average. Conclusions: Manual de-identification of free-text notes is tedious and time-consuming, but even simple PHI is difficult to automatically identify with the exactitude required under HIPAA.

scholarly journals Identifying Medication-related Intents from a Bidirectional Text Messaging Platform for Hypertension Management: An Unsupervised Learning Approach

2021 ◽  
Author(s):  
Anahita Davoudi ◽  
Natalie Lee ◽  
Thaibinh Luong ◽  
Timothy Delaney ◽  
Elizabeth Asch ◽  
...  
Keyword(s):  
Blood Pressure ◽  
Unsupervised Learning ◽  
Language Processing ◽  
Text Messaging ◽  
Latent Dirichlet Allocation ◽  
Clinical Care ◽  
Hypertension Management ◽  
Free Text ◽  
Significant Heterogeneity ◽  
Text Data

Background: Free-text communication between patients and providers is playing an increasing role in chronic disease management, through platforms varying from traditional healthcare portals to more novel mobile messaging applications. These text data are rich resources for clinical and research purposes, but their sheer volume render them difficult to manage. Even automated approaches such as natural language processing require labor-intensive manual classification for developing training datasets, which is a rate-limiting step. Automated approaches to organizing free-text data are necessary to facilitate the use of free-text communication for clinical care and research. Objective: We applied unsupervised learning approaches to 1) understand the types of topics discussed and 2) to learn medication-related intents from messages sent between patients and providers through a bi-directional text messaging system for managing participant blood pressure. Methods: This study was a secondary analysis of de-identified messages from a remote mobile text-based employee hypertension management program at an academic institution. In experiment 1, we trained a Latent Dirichlet Allocation (LDA) model for each message type (inbound-patient and outbound-provider) and identified the distribution of major topics and significant topics (probability >0.20) across message types. In experiment 2, we annotated all medication-related messages with a single medication intent. Then, we trained a second LDA model (medLDA) to assess how well the unsupervised method could identify more fine-grained medication intents. We encoded each medication message with n-grams (n-1-3 words) using spaCy, clinical named entities using STANZA, and medication categories using MedEx, and then applied Chi-square feature selection to learn the most informative features associated with each medication intent. Results: A total of 253 participants and 5 providers engaged in the program generating 12,131 total messages: 47% patient messages and 53% provider messages. Most patient messages correspond to blood pressure (BP) reporting, BP encouragement, and appointment scheduling. In contrast, most provider messages correspond to BP reporting, medication adherence, and confirmatory statements. In experiment 1, for both patient and provider messages, most messages contained 1 topic and few with more than 3 topics identified using LDA. However, manual review of some messages within topics revealed significant heterogeneity even within single-topic messages as identified by LDA. In experiment 2, among the 534 medication messages annotated with a single medication intent, most of the 282 patient medication messages referred to medication request (48%; n=134) and medication taking (28%; n=79); most of the 252 provider medication messages referred to medication question (69%; n=173). Although medLDA could identify a majority intent within each topic, the model could not distinguish medication intents with low prevalence within either patient or provider messages. Richer feature engineering identified informative lexical-semantic patterns associated with each medication intent class. Conclusion: LDA can be an effective method for generating subgroups of messages with similar term usage and facilitate the review of topics to inform annotations. However, few training cases and shared vocabulary between intents precludes the use of LDA for fully automated deep medication intent classification.

scholarly journals Incorporating natural language processing to improve classification of axial spondyloarthritis using electronic health records

Rheumatology ◽  
2019 ◽  
Vol 59 (5) ◽  
pp. 1059-1065 ◽  
Author(s):  
Sizheng Steven Zhao ◽  
Chuan Hong ◽  
Tianrun Cai ◽  
Chang Xu ◽  
Jie Huang ◽  
...  
Keyword(s):  
Electronic Health Records ◽  
Predictive Value ◽  
Area Under The Curve ◽  
Free Text ◽  
Text Data ◽  
Health Records ◽  
Disease Concepts ◽  
Icd Codes ◽  
Electronic Health

Abstract Objectives To develop classification algorithms that accurately identify axial SpA (axSpA) patients in electronic health records, and compare the performance of algorithms incorporating free-text data against approaches using only International Classification of Diseases (ICD) codes. Methods An enriched cohort of 7853 eligible patients was created from electronic health records of two large hospitals using automated searches (⩾1 ICD codes combined with simple text searches). Key disease concepts from free-text data were extracted using NLP and combined with ICD codes to develop algorithms. We created both supervised regression-based algorithms—on a training set of 127 axSpA cases and 423 non-cases—and unsupervised algorithms to identify patients with high probability of having axSpA from the enriched cohort. Their performance was compared against classifications using ICD codes only. Results NLP extracted four disease concepts of high predictive value: ankylosing spondylitis, sacroiliitis, HLA-B27 and spondylitis. The unsupervised algorithm, incorporating both the NLP concept and ICD code for AS, identified the greatest number of patients. By setting the probability threshold to attain 80% positive predictive value, it identified 1509 axSpA patients (mean age 53 years, 71% male). Sensitivity was 0.78, specificity 0.94 and area under the curve 0.93. The two supervised algorithms performed similarly but identified fewer patients. All three outperformed traditional approaches using ICD codes alone (area under the curve 0.80–0.87). Conclusion Algorithms incorporating free-text data can accurately identify axSpA patients in electronic health records. Large cohorts identified using these novel methods offer exciting opportunities for future clinical research.

scholarly journals Extracting Clinical Features From Dictated Ambulatory Consult Notes Using a Commercially Available Natural Language Processing Tool: Pilot, Retrospective, Cross-Sectional Validation Study (Preprint)

2018 ◽  
Author(s):  
Jeremy Petch ◽  
Jane Batt ◽  
Joshua Murray ◽  
Muhammad Mamdani
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Clinical Features ◽  
Language Processing ◽  
A Priori ◽  
Cross Sectional Study ◽  
Free Text ◽  
Cross Sectional ◽  
Text Data ◽  
Complex Features

BACKGROUND The increasing adoption of electronic health records (EHRs) in clinical practice holds the promise of improving care and advancing research by serving as a rich source of data, but most EHRs allow clinicians to enter data in a text format without much structure. Natural language processing (NLP) may reduce reliance on manual abstraction of these text data by extracting clinical features directly from unstructured clinical digital text data and converting them into structured data. OBJECTIVE This study aimed to assess the performance of a commercially available NLP tool for extracting clinical features from free-text consult notes. METHODS We conducted a pilot, retrospective, cross-sectional study of the accuracy of NLP from dictated consult notes from our tuberculosis clinic with manual chart abstraction as the reference standard. Consult notes for 130 patients were extracted and processed using NLP. We extracted 15 clinical features from these consult notes and grouped them a priori into categories of simple, moderate, and complex for analysis. RESULTS For the primary outcome of overall accuracy, NLP performed best for features classified as simple, achieving an overall accuracy of 96% (95% CI 94.3-97.6). Performance was slightly lower for features of moderate clinical and linguistic complexity at 93% (95% CI 91.1-94.4), and lowest for complex features at 91% (95% CI 87.3-93.1). CONCLUSIONS The findings of this study support the use of NLP for extracting clinical features from dictated consult notes in the setting of a tuberculosis clinic. Further research is needed to fully establish the validity of NLP for this and other purposes.

scholarly journals Discovering Monogenic Patients with a Confirmed Molecular Diagnosis in Millions of Clinical Notes with MonoMiner

2021 ◽  
Author(s):  
David Wei Wu ◽  
Jon A Bernstein ◽  
Gill Bejerano
Keyword(s):  
Molecular Diagnosis ◽  
Language Processing ◽  
Clinical Care ◽  
Disease Diagnosis ◽  
Monogenic Disease ◽  
Free Text ◽  
Causal Gene ◽  
Hospital System ◽  
Clinical Notes ◽  
Monogenic Diseases

Purpose: Cohort building is a powerful foundation for improving clinical care, performing research, clinical trial recruitment, and many other applications. We set out to build a cohort of all patients with monogenic conditions who have received a definitive causal gene diagnosis in a 3 million patient hospital system. Methods: We define a subset of half (4,461) of OMIM curated diseases for which at least one monogenic causal gene is definitively known. We then introduce MonoMiner, a natural language processing framework to identify molecularly confirmed monogenic patients from free-text clinical notes. Results: We show that ICD-10-CM codes cover only a fraction of known monogenic diseases, and even where available, code-based patient retrieval offers 0.12 precision. Searching by causal gene symbol offers great recall but an even worse 0.09 precision. MonoMiner achieves 7-9 times higher precision (0.82), with 0.88 precision on disease diagnosis alone, tagging 4,259 patients with 560 monogenic diseases and 534 causal genes, at 0.48 recall. Conclusion: MonoMiner enables the discovery of a large, high-precision cohort of monogenic disease patients with an established molecular diagnosis, empowering numerous downstream uses. Because it relies only on clinical notes, MonoMiner is highly portable, and its approach is adaptable to other domains and languages.

Highly accurate classification of chest radiographic reports using a deep learning natural language model pre-trained on 3.8 million text reports

2020 ◽  
Author(s):  
Keno K Bressem ◽  
Lisa C Adams ◽  
Robert A Gaudin ◽  
Daniel Tröltzsch ◽  
Bernd Hamm ◽  
...  
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Language Model ◽  
Fine Tuning ◽  
Supplementary Information ◽  
Free Text ◽  
Clinical Workflow ◽  
Text Data ◽  
Unlabelled Data ◽  
Medical Reports

Abstract Motivation The development of deep, bidirectional transformers such as Bidirectional Encoder Representations from Transformers (BERT) led to an outperformance of several Natural Language Processing (NLP) benchmarks. Especially in radiology, large amounts of free-text data are generated in daily clinical workflow. These report texts could be of particular use for the generation of labels in machine learning, especially for image classification. However, as report texts are mostly unstructured, advanced NLP methods are needed to enable accurate text classification. While neural networks can be used for this purpose, they must first be trained on large amounts of manually labelled data to achieve good results. In contrast, BERT models can be pre-trained on unlabelled data and then only require fine tuning on a small amount of manually labelled data to achieve even better results. Results Using BERT to identify the most important findings in intensive care chest radiograph reports, we achieve areas under the receiver operation characteristics curve of 0.98 for congestion, 0.97 for effusion, 0.97 for consolidation and 0.99 for pneumothorax, surpassing the accuracy of previous approaches with comparatively little annotation effort. Our approach could therefore help to improve information extraction from free-text medical reports. Availability and implementation We make the source code for fine-tuning the BERT-models freely available at https://github.com/fast-raidiology/bert-for-radiology. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Towards a symbiotic relationship between big data, artificial intelligence, and hospital pharmacy

2020 ◽  
Vol 13 (1) ◽  
Author(s):  
Carlos Del Rio-Bermudez ◽  
Ignacio H. Medrano ◽  
Laura Yebes ◽  
Jose Luis Poveda
Keyword(s):  
Artificial Intelligence ◽  
Big Data ◽  
Language Processing ◽  
Big Data Analytics ◽  
Improve Patient Care ◽  
Free Text ◽  
Medication History ◽  
Medical Databases ◽  
Therapeutic Outcomes ◽  
Text Information

Abstract The digitalization of health and medicine and the growing availability of electronic health records (EHRs) has encouraged healthcare professionals and clinical researchers to adopt cutting-edge methodologies in the realms of artificial intelligence (AI) and big data analytics to exploit existing large medical databases. In Hospital and Health System pharmacies, the application of natural language processing (NLP) and machine learning to access and analyze the unstructured, free-text information captured in millions of EHRs (e.g., medication safety, patients’ medication history, adverse drug reactions, interactions, medication errors, therapeutic outcomes, and pharmacokinetic consultations) may become an essential tool to improve patient care and perform real-time evaluations of the efficacy, safety, and comparative effectiveness of available drugs. This approach has an enormous potential to support share-risk agreements and guide decision-making in pharmacy and therapeutics (P&T) Committees.

Identifying patients with delirium based on unstructured clinical notes (Preprint)

2021 ◽  
Author(s):  
Wendong Ge ◽  
Haitham Alabsi ◽  
Aayushee Jain ◽  
Elissa Ye ◽  
Haoqi Sun ◽  
...  
Keyword(s):  
Language Processing ◽  
Large Scale ◽  
Accurate Determination ◽  
Accurate Method ◽  
Confusion Assessment Method ◽  
Assessment Method ◽  
Support Vector ◽  
Attractive Alternative ◽  
Clinical Notes ◽  
Icd Codes

UNSTRUCTURED Objective: Delirium in hospitalized patients is a syndrome of acute brain dysfunction. Diagnostic (ICD) codes are often used in studies using electronic health records (EHR), but are inaccurate. We sought to develop a more accurate method using Natural Language Processing (NLP) to detect delirium episodes based on unstructured clinical notes. Materials and Methods We collected 1.5M notes from >10K patients spanning 9 hospitals. Seven experts iteratively labeled 200,471 sentences. Using these, we trained three NLP classifiers: Support Vector Machine, Recurrent Neural Networks, and Transformer. Testing was performed on an external dataset. We also evaluated associations with delirium billing (ICD) codes, medications, orders for restraints and sitters, direct assessments (Confusion Assessment Method (CAM) scores), and in-hospital mortality. F1 scores, confusion matrices and AUC were used to compare NLP models. We used the Phi coefficient to measure associations with other delirium indicators. Results: The transformer NLP performed best: micro F1: 0.978, macro F1 0.918, positive AUC 0.984, negative AUC 0.992. NLP detections exhibited higher correlations (Phi) than ICD codes with deliriogenic medications (0.194], vs 0.073 for ICD codes); restraints and sitter orders (0.358 vs 0.177); mortality (0.216 vs 0.000); and CAM scores (0.256 vs -0.028). Discussion. Clinical notes are an attractive alternative to ICD codes for EHR delirium studies, but require automated methods. Our NLP model detects delirium with high accuracy, similar to manual chart review. Conclusion. Our NLP model can provide more accurate determination of delirium for large-scale EHR-based studies.

Sign in / Sign up

Export Citation Format

Share Document