Extracting Findings from Narrative Reports: Software Transferability and Sources of Physician Disagreement

1998 ◽  
Vol 37 (01) ◽  
pp. 01-07 ◽  
Author(s):  
G.J. Kuperman ◽  
C. Friedman ◽  
G. Hripcsak
Keyword(s):  
Health Care ◽  
Natural Language ◽  
Language Processing ◽  
Medical Center ◽  
General Purpose ◽  
Clinical Use ◽  
Local Behavior ◽  
Care Community ◽  
And Performance ◽  
Clinical Conditions

Abstract:While natural language processing systems are beginning to see clinical use, it remains unclear whether they can be disseminated effectively through the health care community. MedLEE, a general-purpose natural language processor developed for Columbia-Presbyterian Medical Center, was compared to physicians' ability to detect seven clinical conditions in 200 Brigham and Women's Hospital chest radiograph reports. Using the system on the new institution's reports resulted in a small but measurable drop in performance (it was distinguishable from physicians at p = 0.011). By making adjustments to the interpretation of the processor's coded output (without changing the processor itself), local behavior was better accommodated, and performance improved so that it was indistinguishable from the physicians. Pairs of physicians disagreed on at least one condition for 22% of reports; the source of disagreement appeared to be interpretation of findings, gauging likelihood and degree of disease, and coding errors.

scholarly journals Utility of Natural Language Processing for Clinical Quality Measures Reporting

2017 ◽  
Vol 9 (1) ◽  
Author(s):  
Dino P. Rumoro ◽  
Shital C. Shah ◽  
Gillian S. Gibbs ◽  
Marilyn M. Hallock ◽  
Gordon M. Trenholme ◽  
...  
Keyword(s):  
Health Care ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Medical Center ◽  
Academic Medical Center ◽  
Quality Measures ◽  
Surveillance Program ◽  
Free Text ◽  
Influenza Immunization

ObjectiveTo explain the utility of using an automated syndromic surveillanceprogram with advanced natural language processing (NLP) to improveclinical quality measures reporting for influenza immunization.IntroductionClinical quality measures (CQMs) are tools that help measure andtrack the quality of health care services. Measuring and reportingCQMs helps to ensure that our health care system is deliveringeffective, safe, efficient, patient-centered, equitable, and timely care.The CQM for influenza immunization measures the percentage ofpatients aged 6 months and older seen for a visit between October1 and March 31 who received (or reports previous receipt of) aninfluenza immunization. Centers for Disease Control and Preventionrecommends that everyone 6 months of age and older receive aninfluenza immunization every season, which can reduce influenza-related morbidity and mortality and hospitalizations.MethodsPatients at a large academic medical center who had a visit toan affiliated outpatient clinic during June 1 - 8, 2016 were initiallyidentified using their electronic medical record (EMR). The 2,543patients who were selected did not have documentation of influenzaimmunization in a discrete field of the EMR. All free text notes forthese patients between August 1, 2015 and March 31, 2016 wereretrieved and analyzed using the sophisticated NLP built withinGeographic Utilization of Artificial Intelligence in Real-Timefor Disease Identification and Alert Notification (GUARDIAN)– a syndromic surveillance program – to identify any mention ofinfluenza immunization. The goal was to identify additional cases thatmet the CQM measure for influenza immunization and to distinguishdocumented exceptions. The patients with influenza immunizationmentioned were further categorized by GUARDIAN NLP intoReceived, Recommended, Refused, Allergic, and Unavailable.If more than one category was applicable for a patient, they wereindependently counted in their respective categories. A descriptiveanalysis was conducted, along with manual review of a sample ofcases per each category.ResultsFor the 2,543 patients who did not have influenza immunizationdocumentation in a discrete field of the EMR, a total of 78,642 freetext notes were processed using GUARDIAN. Four hundred fiftythree (17.8%) patients had some mention of influenza immunizationwithin the notes, which could potentially be utilized to meet the CQMinfluenza immunization requirement. Twenty two percent (n=101)of patients mentioned already having received the immunizationwhile 34.7% (n=157) patients refused it during the study time frame.There were 27 patients with the mention of influenza immunization,who could not be differentiated into a specific category. The numberof patients placed into a single category of influenza immunizationwas 351 (77.5%), while 75 (16.6%) were classified into more thanone category. See Table 1.ConclusionsUsing GUARDIAN’s NLP can identify additional patients whomay meet the CQM measure for influenza immunization or whomay be exempt. This tool can be used to improve CQM reportingand improve overall influenza immunization coverage by using it toalert providers. Next steps involve further refinement of influenzaimmunization categories, automating the process of using the NLPto identify and report additional cases, as well as using the NLP forother CQMs.Table 1. Categorization of influenza immunization documentation within freetext notes of 453 patients using NLP

scholarly journals Sentiment Analysis Techniques Applied to Raw-Text Data from a Csq-8 Questionnaire about Mindfulness in Times of COVID-19 to Improve Strategy Generation

2021 ◽  
Vol 18 (12) ◽  
pp. 6408
Author(s):  
Mario Jojoa Acosta ◽  
Gema Castillo-Sánchez ◽  
Begonya Garcia-Zapirain ◽  
Isabel de la Torre Díez ◽  
Manuel Franco-Martín
Keyword(s):  
Health Care ◽  
Natural Language Processing ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Transfer Learning ◽  
Language Processing ◽  
Health Care Professionals ◽  
Ground Truth ◽  
Relevant Information ◽  
Free Text

The use of artificial intelligence in health care has grown quickly. In this sense, we present our work related to the application of Natural Language Processing techniques, as a tool to analyze the sentiment perception of users who answered two questions from the CSQ-8 questionnaires with raw Spanish free-text. Their responses are related to mindfulness, which is a novel technique used to control stress and anxiety caused by different factors in daily life. As such, we proposed an online course where this method was applied in order to improve the quality of life of health care professionals in COVID 19 pandemic times. We also carried out an evaluation of the satisfaction level of the participants involved, with a view to establishing strategies to improve future experiences. To automatically perform this task, we used Natural Language Processing (NLP) models such as swivel embedding, neural networks, and transfer learning, so as to classify the inputs into the following three categories: negative, neutral, and positive. Due to the limited amount of data available—86 registers for the first and 68 for the second—transfer learning techniques were required. The length of the text had no limit from the user’s standpoint, and our approach attained a maximum accuracy of 93.02% and 90.53%, respectively, based on ground truth labeled by three experts. Finally, we proposed a complementary analysis, using computer graphic text representation based on word frequency, to help researchers identify relevant information about the opinions with an objective approach to sentiment. The main conclusion drawn from this work is that the application of NLP techniques in small amounts of data using transfer learning is able to obtain enough accuracy in sentiment analysis and text classification stages.

scholarly journals Development of a Natural Language Processing Algorithm to Identify and Evaluate Transgender Patients in Electronic Health Record System

2019 ◽  
Vol 29 (Supp2) ◽  
pp. 441-450 ◽  
Author(s):  
Jesse M. Ehrenfeld ◽  
Keanan Gabriel Gottlieb ◽  
Lauren Brittany Beach ◽  
Shelby E. Monahan ◽  
Daniel Fabbri
Keyword(s):  
Health Care ◽  
Natural Language ◽  
Language Processing ◽  
Health Care Services ◽  
False Positive Rate ◽  
Health Condition ◽  
Record System ◽  
Care Services ◽  
Electronic Health ◽  
Hormone Use

Objective: To create a natural language pro­cessing (NLP) algorithm to identify transgen­der patients in electronic health records.Design: We developed an NLP algorithm to identify patients (keyword + billing codes). Patients were manually reviewed, and their health care services categorized by billing code.Setting: Vanderbilt University Medical CenterParticipants: 234 adult and pediatric trans­gender patientsMain Outcome Measures: Number of transgender patients correctly identified and categorization of health services utilized.Results: We identified 234 transgender pa­tients of whom 50% had a diagnosed men­tal health condition, 14% were living with HIV, and 7% had diabetes. Largely driven by hormone use, nearly half of patients attended the Endocrinology/Diabetes/Me­tabolism clinic. Many patients also attended the Psychiatry, HIV, and/or Obstetrics/Gyne­cology clinics. The false positive rate of our algorithm was 3%.Conclusions: Our novel algorithm correctly identified transgender patients and provided important insights into health care utiliza­tion among this marginalized population. Ethn Dis. 2019;29(Suppl 2): 441-450. doi:10.18865/ed.29.S2.441

scholarly journals Natural Language Processing-Identified Problem Opioid Use And Its Associated Health Care Costs

2016 ◽  
Vol 19 (3) ◽  
pp. A4 ◽  
Author(s):  
E.T. Masters ◽  
J. Mardekian ◽  
A. Ramaprasan ◽  
K. Saunders ◽  
D.E. Gross ◽  
...  
Keyword(s):  
Health Care ◽  
Natural Language Processing ◽  
Natural Language ◽  
Health Care Costs ◽  
Language Processing ◽  
Opioid Use ◽  
Care Costs

scholarly journals Emerging trends: A gentle introduction to fine-tuning

2021 ◽  
Vol 27 (6) ◽  
pp. 763-778
Author(s):  
Kenneth Ward Church ◽  
Zeyu Chen ◽  
Yanjun Ma
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Question Answering ◽  
General Purpose ◽  
Fine Tuning ◽  
Language Engineering ◽  
Training Models ◽  
Emerging Trends ◽  
Foundation Model ◽  
Programming Skills

AbstractThe previous Emerging Trends article (Church et al., 2021. Natural Language Engineering27(5), 631–645.) introduced deep nets to poets. Poets is an imperfect metaphor, intended as a gesture toward inclusion. The future for deep nets will benefit by reaching out to a broad audience of potential users, including people with little or no programming skills, and little interest in training models. That paper focused on inference, the use of pre-trained models, as is, without fine-tuning. The goal of this paper is to make fine-tuning more accessible to a broader audience. Since fine-tuning is more challenging than inference, the examples in this paper will require modest programming skills, as well as access to a GPU. Fine-tuning starts with a general purpose base (foundation) model and uses a small training set of labeled data to produce a model for a specific downstream application. There are many examples of fine-tuning in natural language processing (question answering (SQuAD) and GLUE benchmark), as well as vision and speech.

Leveraging Natural Language Processing Applications Using Machine Learning

2020 ◽  
pp. 338-360
Author(s):  
Janjanam Prabhudas ◽  
C. H. Pradeep Reddy
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Text Summarization ◽  
Feature Representation ◽  
Learning Models ◽  
Primary Focus ◽  
And Performance

The enormous increase of information along with the computational abilities of machines created innovative applications in natural language processing by invoking machine learning models. This chapter will project the trends of natural language processing by employing machine learning and its models in the context of text summarization. This chapter is organized to make the researcher understand technical perspectives regarding feature representation and their models to consider before applying on language-oriented tasks. Further, the present chapter revises the details of primary models of deep learning, its applications, and performance in the context of language processing. The primary focus of this chapter is to illustrate the technical research findings and gaps of text summarization based on deep learning along with state-of-the-art deep learning models for TS.

scholarly journals Automatic Identification of Information Quality Metrics in Health News Stories

2020 ◽  
Vol 8 ◽  
Author(s):  
Majed Al-Jefri ◽  
Roger Evans ◽  
Joon Lee ◽  
Pietro Ghezzi
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Information Quality ◽  
Evaluation Process ◽  
Health News ◽  
News Stories

Objective: Many online and printed media publish health news of questionable trustworthiness and it may be difficult for laypersons to determine the information quality of such articles. The purpose of this work was to propose a methodology for the automatic assessment of the quality of health-related news stories using natural language processing and machine learning.Materials and Methods: We used a database from the website HealthNewsReview.org that aims to improve the public dialogue about health care. HealthNewsReview.org developed a set of criteria to critically analyze health care interventions' claims. In this work, we attempt to automate the evaluation process by identifying the indicators of those criteria using natural language processing-based machine learning on a corpus of more than 1,300 news stories. We explored features ranging from simple n-grams to more advanced linguistic features and optimized the feature selection for each task. Additionally, we experimented with the use of pre-trained natural language model BERT.Results: For some criteria, such as mention of costs, benefits, harms, and “disease-mongering,” the evaluation results were promising with an F1 measure reaching 81.94%, while for others the results were less satisfactory due to the dataset size, the need of external knowledge, or the subjectivity in the evaluation process.Conclusion: These used criteria are more challenging than those addressed by previous work, and our aim was to investigate how much more difficult the machine learning task was, and how and why it varied between criteria. For some criteria, the obtained results were promising; however, automated evaluation of the other criteria may not yet replace the manual evaluation process where human experts interpret text senses and make use of external knowledge in their assessment.

Text Analysis of Assembly Work Instructions

2015 ◽  
Author(s):  
Rahul Sharan Renu ◽  
Gregory Mocko
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Lead Times ◽  
Parts Of Speech ◽  
Assembly Work ◽  
And Performance ◽  
Quality Of Products ◽  
Speech Tagging

The objective of this research is to investigate the requirements and performance of parts-of-speech tagging of assembly work instructions. Natural Language Processing of assembly work instructions is required to perform data mining with the objective of knowledge reuse. Assembly work instructions are key process engineering elements that allow for predictable assembly quality of products and predictable assembly lead times. Authoring of assembly work instructions is a subjective process. It has been observed that most assembly work instructions are not grammatically complete sentences. It is hypothesized that this can lead to false parts-of-speech tagging (by Natural Language Processing tools). To test this hypothesis, two parts-of-speech taggers are used to tag 500 assembly work instructions (obtained from the automotive industry). The first parts-of-speech tagger is obtained from Natural Language Processing Toolkit (nltk.org) and the second parts-of-speech tagger is obtained from Stanford Natural Language Processing Group (nlp.stanford.edu). For each of these taggers, two experiments are conducted. In the first experiment, the assembly work instructions are input to the each tagger in raw form. In the second experiment, the assembly work instructions are preprocessed to make them grammatically complete, and then input to the tagger. It is found that the Stanford Natural Language Processing tagger with the preprocessed assembly work instructions produced the least number of false parts-of-speech tags.

Sign in / Sign up

Export Citation Format

Share Document