Natural Language Processing Software Research Articles

Implementation of Peer Messengers to Deliver Feedback: An Observational Study to Promote Professionalism in Nursing.

The Co-Worker Observation System (CORS) is a tool and a process to address disrespectful behavior through feedback from trained peer messengers. First used by physicians and advanced practice providers (APPs), CORS has been shown to decrease instances of unprofessional behaviors among physicians and APPs. The research team assessed the feasibility and fidelity of implementing CORS for staff nurses. CORS was implemented at three academic medical centers using a project bundle with 10 essential implementation elements. Reports of unprofessional behavior among staff nurses that were submitted through the institution's electronic reporting system were screened through natural language processing software, coded by trained CORS coders using the Martinez taxonomy, and referred to a trained peer messenger to share the observations with the nurse. A mixed methods, observational design assessed feasibility and fidelity. A total of 590 reports from three sites were identified by the Center for Patient and Professional Advocacy from September 1, 2019, through August 31, 2021. Most reports included more than one problematic behavior, each of which was coded. Of the peer messages, 76.5% were successfully documented using the debriefing survey as complete, 2.2% as awaiting messenger feedback, and 0.2% as awaiting messenger assignments (total of 78.9 % considered delivered). A total of 21.1% were not shared; 4.7% of reports were intentionally not shared because the issue stemmed from a new system or policy implementation (4.0%) or because of known factors affecting the nurse (0.7%). CORS can be implemented with staff nurses efficiently when nursing infrastructure is adequate.

The Development of a Comprehensive Clinicopathologic Registry for Glomerular Diseases Using Natural Language Processing.

Glomerulonephritis (GN) represents a common cause of chronic kidney disease, and treatment to slow or prevent progression of GN is associated with significant morbidity. Large patient registries have improved the understanding of risk stratification, treatment selection, and definitions of treatment response in GN, but can be resource-intensive, with incomplete patient capture. To describe the creation of a comprehensive clinicopathologic registry for all patients undergoing kidney biopsy in Manitoba, using natural language processing software for data extraction from pathology reports, as well as to describe cohort characteristics and outcomes. Retrospective population-based cohort study. Tertiary care center in the province of Manitoba. All patients undergoing a kidney biopsy in the province of Manitoba from 2002 to 2019. Descriptive statistics are presented for the most common glomerular diseases, along with outcomes of kidney failure and mortality for the individual diseases. Data from native kidney biopsy reports from January 2002 to December 2019 were extracted into a structured database using a natural language processing algorithm employing regular expressions. The pathology database was then linked with population-level clinical, laboratory, and medication data, creating a comprehensive clinicopathologic registry. Kaplan-Meier curves and Cox models were constructed to assess the relationship between type of GN and outcomes of kidney failure and mortality. Of 2421 available biopsies, 2103 individuals were linked to administrative data, of which 1292 had a common glomerular disease. The incidence of yearly biopsies increased almost 3-fold over the study period. Among common glomerular diseases, immunoglobulin A (IgA) nephropathy was the most common (28.6%), whereas infection-related GN had the highest proportions of kidney failure (70.3%) and all-cause mortality (42.3%). Predictors of kidney failure included urine albumin-to-creatinine ratio at the time of biopsy (adjusted hazard ratio [HR] = 1.43, 95% confidence interval [CI] = 1.24-1.65), whereas predictors of mortality included age at the time of biopsy (adjusted HR = 1.05, 95% CI = 1.04-1.06) and infection-related GN (adjusted HR = 1.85, 95% CI = 1.14-2.99, compared with the reference category of IgA nephropathy). Retrospective, single-center study with a relatively small number of biopsies. Creation of a comprehensive glomerular diseases registry is feasible and can be facilitated through the use of novel data extraction methods. This registry will facilitate further epidemiological research in GN.

The use of natural language processing in palliative care research: A scoping review

Background: Natural language processing has been increasingly used in palliative care research over the last 5 years for its versatility and accuracy. Aim: To evaluate and characterize natural language processing use in palliative care research, including the most commonly used natural language processing software and computational methods, data sources, trends in natural language processing use over time, and palliative care topics addressed. Design: A scoping review using the framework by Arksey and O’Malley and the updated recommendations proposed by Levac et al. was conducted. Sources: PubMed, Web of Science, Embase, Scopus, and IEEE Xplore databases were searched for palliative care studies that utilized natural language processing tools. Data on study characteristics and natural language processing instruments used were collected and relevant palliative care topics were identified. Results: 197 relevant references were identified. Of these, 82 were included after full-text review. Studies were published in 48 different journals from 2007 to 2022. The average sample size was 21,541 (median 435). Thirty-two different natural language processing software and 33 machine-learning methods were identified. Nine main sources for data processing and 15 main palliative care topics across the included studies were identified. The most frequent topic was mortality and prognosis prediction. We also identified a trend where natural language processing was frequently used in analyzing clinical serious illness conversations extracted from audio recordings. Conclusions: We found 82 papers on palliative care using natural language processing methods for a wide-range of topics and sources of data that could expand the use of this methodology. We encourage researchers to consider incorporating this cutting-edge research methodology in future studies to improve published palliative care data.

User‐led Design of a Self‐administered Smartphone‐based Learning and Memory Assessment

AbstractBackgroundThe International Shopping List test (ISLT) is a verbal word list learning assessment set within a realistic shopping list context, supporting ease of cultural adaptation, and addressing content validity and patient relevance. Improvements to and the wide adoption of natural language processing (NLP) software has enabled the possibility for self‐administered tests of verbal learning. A beta version of a self‐administered, smartphone‐application (app) was developed, using the virtual assistant and NLP: the “List Learning and Memory Assessment (LilaTM)”.MethodTo ensure usability of the app, a user led design process was followed. A beta version was created via several rounds of focus group development in older adults. 12 older adults were then recruited for interviews (8 healthy and 4 with Mild Cognitive Impairment). Participants were pseudo‐randomly assigned to participate in interviews during test performance, using either iPhone or Nokia devices. Each participant completed the test and provided concept elicitation feedback. Qualitative analysis of the interview results was performed using thematic coding.ResultKey positive themes included the ease with which the app could be navigated, and the clarity of visual display and instructions, whilst an important negative theme was the length of time between different components of the test.ConclusionQualitative analysis of concept elicitation interviews has suggested several areas of improvement to the beta‐app, including improvements to performance that shorten processing and wait times between test components. The clarity of the visual display and test instructions were well supported.

S818 An Insight into the Patient’s Perspective of Ulcerative Colitis Flares via Analysis of Online Public Forum Posts: Key Triggers and Symptoms of Flares

Introduction: Prediction of flares in UC remains a challenge, with limited analyses on patient (pt)-reported themes associated with onset. The aim of this analysis was to identify the most common pt-reported triggers and symptoms of UC flares. Methods: We reviewed online posts written by pts with UC on 8 public forums in 6 countries between January 1, 2019 and February 14, 2021. Flare-related posts (identified by keywords; Table), including pre- and post-flare posts from the same pts, were captured using Netbase Quid™ artificial intelligence text analytics and natural language processing software. Once identified, all flare-related posts were analyzed and mapped semantically to uncover the most prevalent conversational topics and themes regarding flares to outline the unmet needs and challenges discussed and to examine self-reported triggers of flares. Results: Of > 27,000 pt posts, 12,900 were identified as flare-related. The most common themes identified were treatment experiences, side-effects (28%), and flare symptoms (22%; Figure a). Of the top topics discussed, the most common was emotional / peer support (9.4% of posts), followed by posts on the individual experiences and recommendations of mesalamine (and other oral / rectal suppositories; 8.0% of posts), the most common treatment option discussed, and dietary recommendations (6.0% of posts; Figure b). Pain was a high-impact topic (fatigue and joint pain, 2.4% of posts; Figure b). Stress and anxiety were the most reported triggers of flares (38% of posts), followed by diet (28% of posts; Table), with discussions suggesting pts with UC had difficulty managing external stressors. Depression, anxiety, and fatigue were frequently identified as both triggers for and symptoms of flares. Initial symptoms of flares (e.g., blood in stool; diarrhea and loose stool; stool frequency) were often not distinguished from full flares. Blood in the stool was the most discussed flare indicator (58%; Table). Conclusion: The results of this analysis of pt posts suggest that some frequently discussed triggers and / or symptoms of UC flares, such as depression, anxiety, pain, and sleep disturbances, are not always captured using traditional clinical disease activity measures.1,2 Physicians should consider additional pt-reported outcomes, including emotional and psychological aspects, during the assessment of pts.Figure 1.: a) Top themes and b) top topics in UC patient forum flare-related posts. Flare-related posts, including those from the same author pre- and post-flare, were identified from online posts written by patients with UC on 8 public forums (Afa Crohn RCH, Carenity, Crohn Club Forum, Crohn’s Forum, Deutsche Morbus Crohn/Colitis ulcerosa Vereinigung; Educainflamatoria, HealingWell, Patient) in 6 countries (France, Germany, Italy, Spain, United Kingdom, and United States) between January 1, 2019 and February 14, 2021. Flare-related posts were identified as those containing relevant keywords, including flare, remission, inflammation, cramps, attack, relapse, symptoms, and bloody stool. Flare-related post data were color-coded by a) themes and b) topics; each node represents a post, and connections represent similar language used across the posts. Centrally located nodes represent core concepts, and peripheral nodes represent niche concepts. UC, ulcerative colitis Table 1. - Most discussed flare triggers and initial flare symptoms in patients with UC Ranking Flare triggers (percentage of posts), (N=1,161) Initial flare symptoms (percentage of posts), (N=645) 1 Stress and anxiety (38%) Blood in stool / passing blood (58%) 2 Diet (28%) Diarrhea and loose stool (19%) 3 Smoking cessation (9%) Stool frequency (19%) 4 Antibiotics (9%) Mucus in stool / passing mucus (17%) 5 Bacterial or viral infection (7%)a Pain and cramping (14%) 6 NSAID usage (6%) Fatigue (7%) Flare-related posts, including those from the same author pre- and post-flare, were identified from online posts written by patients with UC on 8 public forums (Afa Crohn RCH, Carenity, Crohn Club Forum, Crohn’s Forum, Deutsche Morbus Crohn / Colitis ulcerosa Vereinigung, Educainflamatoria, HealingWell, and Patient) in 6 countries (France, Germany, Italy, Spain, United Kingdom, United States) between January 1, 2019 and February 14, 2021. Flare-related posts were identified as those containing relevant keywords, including flare, remission, inflammation, cramps, attack, relapse, symptoms, and bloody stool.aPatients who identified bacterial or viral infections as a flare trigger had uniquely low confidence and were unsure about infections being the cause of their triggers.NSAID, nonsteroidal anti-inflammatory drug; UC, ulcerative colitis.

Экспериментальное моделирование базы данных сбалансированного лингвистического корпуса

The research aims to build a functioning experimental model of a relational database for operating with a balanced linguistic corpus of a fiction work. Scientific novelty lies in the fact that for the first time within the framework of a humanities study, a database of a linguistic corpus is being modeled with a thorough description and taking into account technical details and based on the provisions of the author’s concept of professionally oriented programming. The work involved three stages: forming a technical task (the structure of two tables of a relational database was developed, the SQLite format was selected, additional columns of the tables were provided for the subsequent expansion of the content of research), writing the source code for creating and filling the database (the Python programming language and the spaCy natural language processing module were used) and testing it based on the material of the texts of three F. Kafka’s novels “The Castle”, “Amerika” and “The Trial” (three functioning databases were created). The research findings have shown that modern natural language processing software tools allow one to create automatically full-fledged databases for processing SQL queries, which can be further expanded manually or automatically.

Prevalence and Correlates of Obsessive-Compulsive Symptoms in Individuals With Schizophrenia, Schizoaffective Disorder, or Bipolar Disorder.

Objective: Although frequently reported in psychosis, obsessive-compulsive symptoms (OCS) are often not recognized and thus undertreated. We aimed to estimate the prevalence of OCS and obsessive-compulsive disorder (OCD) in patients with schizophrenia, schizoaffective disorder, or bipolar disorder in clinical records and identify clinical associations of OCS co-occurrence.Methods: Data were retrieved from the South London and Maudsley NHS Foundation Trust Biomedical Research Centre case register. The study population was restricted to individuals diagnosed with schizophrenia (ICD F20.x), schizoaffective disorder (ICD F25.x), or bipolar disorder (ICD F31.x) between 2007 and 2015. OCS and OCD were ascertained from structural fields and via Natural Language Processing software applied to free-text records. Clinical characteristics were obtained from Health of the Nation Outcome Scales for the analyses on associations between clinical characteristics and OCS/OCD status using logistic regressions with confounders considered.Results: 22,551 cases of schizophrenia, schizoaffective disorder, or bipolar disorder were identified in the observation window. Among these, 5,179 (24.0%) were identified as having OCS (including an OCD diagnosis) and 2,574 (11.9%) specifically with comorbid OCD. OCS/OCD was associated with an increased likelihood of recorded aggressive behavior (OR = 1.18; 95% CI, 1.10-1.26), cognitive problems (OR = 1.21; 95% CI, 1.13-1.30), hallucinations and delusions (OR = 1.11; 95% CI, 1.04-1.20), and physical problems (OR = 1.17; 95% CI, 1.09-1.26).Conclusions: OCS and OCD are frequently recorded for patients with schizophrenia, schizoaffective disorder, and bipolar disorder and are associated with more severe psychiatric clinical characteristics. Automated information extraction tools hold potential to improve recognition and treatment of co-occurring OCS/OCD for psychosis.

Prevalence of delayed puberty and low bone density in patients with epidermolysis bullosa: Insight from a large single center's experience.

Epidermolysis bullosa (EB) is a group of rare genetic skin conditions that result in skin fragility. EB can be quite severe with chronic inflammation and malnutrition impairing growth and pubertal development. These factors have potential consequences for skeletal health. We aimed to determine the prevalence of delayed puberty and low bone mineral density (BMD) for age in children and young adults with EB. Electronic medical records (EMR) of patients with confirmed EB <30 years of age at time of initial encounter at Cincinnati Children's Hospital Medical Center between January 1, 2010 and September 30, 2020 were reviewed. Natural language processing software was used to categorize pubertal status of patients with EB as early, normal or delayed. BMD was measured by dual energy x-ray absorptiometry and categorized as low if height adjusted Z-score was <-2.0 using age, sex and race specific reference ranges. 29% of individuals with EB had low BMD with most cases occurring prior to 10 years of age. Of patients who reached adolescence, 23% failed to develop any signs of puberty in the normal range (before age 13 in females or 14 in males) and BMD Z-scores further declined in these individuals. Delayed puberty is an under-recognized comorbidity of individuals with EB, especially in those with recessive dystrophic EB, and can have a significant impact on BMD.

Using Natural Language Processing to Automatically Identify Dysplasia in Pathology Reports for Patients With Barrett’s Esophagus

Identifying dysplasia of Barrett's esophagus (BE) in the electronic medical record (EMR) requires manual abstraction of unstructured data. Natural language processing (NLP) creates structure to unstructured free text. We aimed to develop and validate an NLP algorithm to identify dysplasia in BE patients on histopathology reports with varying report formats in a large integrated EMR system. We randomly selected 600 pathology reports for NLP development and 400 reports for validation from patients with suspected BE in the national Veterans Affairs databases. BE and dysplasia were verified by manual review of the pathology reports. We used NLP software (Clinical Language Annotation, Modeling, and Processing Toolkit; Melax Tech, Houston, TX) to develop an algorithm to identify dysplasia using findings. The algorithm performance characteristics were calculated as recall, precision, accuracy, and F-measure. In the development set of 600 patients, 457 patients had confirmed BE (60 with dysplasia). The NLP identified dysplasia with 98.0% accuracy, 91.7% recall, and 93.2% precision, with an F-measure of 92.4%. All 7 patients with confirmed high-grade dysplasia were classified by the algorithm as having dysplasia. Among the 400 patients in the validation cohort, 230 had confirmed BE (39 with dysplasia). Compared with manual review, the NLP algorithm identified dysplasia with 98.7% accuracy, 92.3% recall, and 100.0% precision, with an F-measure of 96.0%. NLP yielded a high degree of sensitivity and accuracy for identifying dysplasia from diverse types of pathology reports for patients with BE. The application of this algorithm would facilitate research and clinical care in an EMR system with text reports in large data repositories.

ASO Visual Abstract: Utilization of Natural Language Processing Software to Identify Worrisome Pancreatic Lesions.

ASO Visual Abstract: Utilization of Natural Language Processing Software to Identify Worrisome Pancreatic Lesions.

A Multimethod Evaluation of Tobacco Treatment Trial Recruitment Messages for Current Smokers Recently Diagnosed With Cancer: Pilot Factorial Randomized Controlled Trial.

BackgroundA cancer diagnosis can catalyze motivation to quit smoking. Tobacco treatment trials offer cessation resources but have low accrual rates. Digital outreach may improve accrual, but knowledge of how best to recruit smokers with recent diagnoses is limited.ObjectiveThis study aims to identify the message frames that were most effective in promoting intent to talk to a physician about participating in a tobacco treatment trial for smokers recently diagnosed with cancer.MethodsFrom February to April 2019, current smokers diagnosed within the past 24 months were recruited from a national web-based panel for a multimethod pilot randomized trial (N=99). Participants were randomized to a 2×3 plus control factorial design that tested 3 unique message frames: proximal versus distal threats of smoking, costs of continued smoking versus benefits of quitting, and gains of participating versus losses of not participating in a tobacco treatment trial. The primary outcome was intent to talk to a physician about participating in a tobacco treatment trial. In phase 1, the main effect within each message factor level was examined using ANOVA and compared with the control condition. Other message evaluation and effectiveness measures were collected and explored in a multivariable model predicting intent to talk to a physician. In phase 2, open-text evaluations of the messages were analyzed using natural language processing software (Leximancer) to generate a thematic concept map and Linguistic Inquiry Word Count to identify and compare the prevalence of linguistic markers among message factors.ResultsOf the 99 participants, 76 (77%) completed the intervention. Participants who received the cost of continued smoking frame were significantly more likely to intend to talk to their physician about participating in a tobacco treatment trial than those who received the benefits of the quitting frame (mean costs 5.13, SD 1.70 vs mean benefits 4.23, SD 1.86; P=.04). Participants who received the proximal risks of continued smoking frame were significantly more likely to seek more information about participating (mean distal 4.83, SD 1.61 vs mean proximal 5.55, SD 1.15; P=.04), and those who received the losses of not participating frame reported significantly improved perceptions of smoking cessation research (mean gain 3.98, SD 0.83 vs mean loss 4.38, SD 0.78; P=.01). Male participants (P=.006) and those with greater message relevancy (P=.001) were significantly more likely to intend to talk to their physician. Participants’ perceptions of their smoking habits, as well as their motivation to quit smoking, were prevalent themes in the open-text data. Differences in the percentages of affective words across message frames were identified.ConclusionsMultimethod approaches are needed to develop evidence-based recruitment messages for patients recently diagnosed with cancer. Future tobacco treatment trials should evaluate the effectiveness of different message frames on smoker enrollment rates.Trial RegistrationClinicaltrials.gov NCT05471284; https://clinicaltrials.gov/ct2/show/NCT05471284

Utilization of Natural Language Processing Software to Identify Worrisome Pancreatic Lesions.

Computed tomography (CT) imaging is routinely obtained for diagnostics, especially in trauma and emergency rooms, often identifying incidental findings. We utilized a natural language processing (NLP) algorithm to quantify the incidence of clinically relevant pancreatic lesions in CT imaging. We utilized the electronic medical record to perform a retrospective chart review of adult patients admitted for trauma to a level 1 tertiary care center between 2010 and 2020 who underwent abdominal CT imaging. An open-source NLP software was used to identify patients with intrapapillary mucinous neoplasms (IPMN), pancreatic cysts, pancreatic ductal dilation, or pancreatic masses after optimizing the algorithm using a test group of patients who underwent pancreatic surgery. The algorithm identified pancreatic lesions in 27 of 28 patients who underwent pancreatic surgery and excluded 1 patient who had a pure ampullary mass. The study cohort consisted of 18,769 patients who met our inclusion criteria admitted to the hospital. Of this population, 232 were found to have pancreatic lesions of interest. There were 48 (20.7%) patients with concern for IPMN, pancreatic cysts in 36 (15.5%), concerning masses in 30 (12.9%), traumatic findings in 44 (19.0%), pancreatitis in 41 (17.7%), and ductal abnormalities in 19 (18.2%) patients. Prior pancreatic surgery and other findings were identified in 14 (6.0%) patients. In this study, we propose a novel use of NLP software to identify potentially malignant pancreatic lesions annotated in CT imaging performed for other purposes. This methodology can significantly increase the screening and automated referral for the management of precancerous lesions.

How Differing Audiences Were Associated with User Emotional Expression on a Well-Being App.

In the last five years there has been an explosion of mobile apps that aim to impact emotional well-being, yet limited research has examined the ways that users interact, and specifically write to develop a therapeutic alliance within these apps. Writing is a developmental practice in which a narrator transforms amorphous thoughts and emotions into expressions, and according to narrative theory, the linguistic characteristics of writing can be understood as a physical manifestation of a narrator's affect. Informed by literacy theorists who have argued convincingly that narrators address different audiences in different ways, we used IBM Watson's Natural Language Processing software (IBM Watson NLP) to examine how users' expression of emotion on a well-being app differed depending on the audience. Our findings demonstrate that audience was strongly associated with the way users' expressed emotions in writing. When writing to an explicit audience users wrote longer narratives, with less sadness, less anger, less disgust, less fear and more joy. These findings have direct relevance for researchers and well-being app design.

Development and Validation of a Machine Learning Model for Automated Assessment of Resident Clinical Reasoning Documentation.

Residents receive infrequent feedback on their clinical reasoning (CR) documentation. While machine learning (ML) and natural language processing (NLP) have been used to assess CR documentation in standardized cases, no studies have described similar use in the clinical environment. The authors developed and validated using Kane's framework a ML model for automated assessment of CR documentation quality in residents' admission notes. Internal medicine residents' and subspecialty fellows' admission notes at one medical center from July 2014 to March 2020 were extracted from the electronic health record. Using a validated CR documentation rubric, the authors rated 414 notes for the ML development dataset. Notes were truncated to isolate the relevant portion; an NLP software (cTAKES) extracted disease/disorder named entities and human review generated CR terms. The final model had three input variables and classified notes as demonstrating low- or high-quality CR documentation. The ML model was applied to a retrospective dataset (9591 notes) for human validation and data analysis. Reliability between human and ML ratings was assessed on 205 of these notes with Cohen's kappa. CR documentation quality by post-graduate year (PGY) was evaluated by the Mantel-Haenszel test of trend. The top-performing logistic regression model had an area under the receiver operating characteristic curve of 0.88, a positive predictive value of 0.68, and an accuracy of 0.79. Cohen's kappa was 0.67. Of the 9591 notes, 31.1% demonstrated high-quality CR documentation; quality increased from 27.0% (PGY1) to 31.0% (PGY2) to 39.0% (PGY3) (p < .001 for trend). Validity evidence was collected in each domain of Kane's framework (scoring, generalization, extrapolation, and implications). The authors developed and validated a high-performing ML model that classifies CR documentation quality in resident admission notes in the clinical environment-a novel application of ML and NLP with many potential use cases.

NeuroBlu: a natural language processing (NLP) electronic health record (EHR) data analytic tool to generate real-world evidence in mental healthcare

Introduction EHRs contain a rich source of real-world data that can support evidence generation to better understand mental disorders and improve treatment outcomes. However, EHR datasets are complex and include unstructured free text data that are time consuming to manually review and analyse. We present NeuroBlu, a secure, cloud-based analytic tool that includes bespoke NLP software to enable users to analyse large volumes of EHR data to generate real-world evidence in mental healthcare.Objectives(i) To assemble a large mental health EHR dataset in a secure, cloud-based environment.(ii) To apply NLP software to extract data on clinical features as part of the Mental State Examination (MSE).(iii) To analyse the distribution of NLP-derived MSE features by psychiatric diagnosis.MethodsEHR data from 25 U.S. mental healthcare providers were de-identified and transformed into a common data model. NLP models were developed to extract 241 MSE features using a deep learning, long short-term memory (LSTM) approach. The NeuroBlu tool (https://www.neuroblu.ai/) was used to analyse the associations of MSE features in 543,849 patients.ResultsThe figure below illustrates the percentage of patients in each diagnostic category with at least one recorded MSE feature.ConclusionsDelusions and hallucinations were more likely to be recorded in people with schizophrenia and schizoaffective disorder, and cognitive features were more likely to be recorded in people with dementia. However, mood symptoms were frequently recorded across all diagnoses illustrating their importance as a transdiagnostic clinical feature. NLP-derived clinical information could enhance the potential of EHR data to generate real-world evidence in mental healthcare.DisclosureThis study was funded in full by Holmusk.

Facilitating clinical research through automation: Combining optical character recognition with natural language processing.

Performance status is crucial for most clinical research, as an eligibility criterion, a comorbidity covariate, or a trial endpoint. Yet information on performance status often is embedded as free text within a patient's electronic medical record, rather than coded directly, thereby making this concept extremely difficult to extract for research. Furthermore, performance status information frequently resides in outside reports, which are scanned into the electronic medical record along with thousands of clinic notes. The image format of scanned documents also is a major obstacle to the search and retrieval of information, as natural language processing cannot be applied to unstructured text within an image. We, therefore, utilized optical character recognition software to convert images to a searchable format, allowing the application of natural language processing to identify pertinent performance status data elements within scanned electronic medical records. Our study cohort consisted of 189 subjects diagnosed with diffuse large B-cell lymphoma for whom performance status was a required data element for analysis of prognostic factors related to recurrence and survival. Manual abstraction of performance status was previously conducted by a clinical Subject Matter Expert, serving as the gold standard. Leveraging our data warehouse, we extracted relevant scanned electronic medical record documents and applied optical character recognition to these images using the ABBYY FineReader software. The Linguamatics i2e natural language processing software was then used to run queries for performance status against the corpus of electronic medical record documents. We evaluated our optical character recognition/natural language processing pipeline for accuracy and reduction in data extraction effort. We found that there was high accuracy and reduced time for extraction of performance status data by applying our optical character recognition/natural language processing pipeline. The transformed scanned documents from a random sample of patients yielded excellent precision, recall, and F score, with <1% incorrect results. Time savings from a second cohort showed that median time to review documents for patients with performance status data present was reduced by a third. The major time savings was in the review of those documents that in fact did not contain performance status information: median of 18 minutes versus 108 minutes for manual review, an 83% reduction in data abstraction effort. By applying this optical character recognition/natural language processing pipeline, we achieved significant operational improvement and reduced time for information retrieval to support clinical research. Our study demonstrated that optical character recognition software provides an effective mechanism to transform scanned electronic medical record images to allow the application of natural language processing, yielding highly accurate data abstraction. We conclude that our optical character recognition/natural language processing pipeline can greatly facilitate research data abstraction by providing a highly focused data review, eliminating unnecessary manual review of the entire chart, and thus freeing time for abstracting other data elements requiring more human interpretation.

Regular feedback to individual endoscopists is associated with improved adenoma detection rate and other key performance indicators for colonoscopy

ObjectiveMonitoring of key performance indicators (KPIs) is a vital element of endoscopy quality improvement. Adenoma detection rate (ADR) is considered the best marker for colonoscopic quality as it inversely correlates...

A database of refractive indices and dielectric constants auto-generated using ChemDataExtractor

The ability to auto-generate databases of optical properties holds great potential for advancing optical research, especially with regards to the data-driven discovery of optical materials. An optical property database of refractive indices and dielectric constants is presented, which comprises a total of 49,076 refractive index and 60,804 dielectric constant data records on 11,054 unique chemicals. The database was auto-generated using the state-of-the-art natural language processing software, ChemDataExtractor, using a corpus of 388,461 scientific papers. The data repository offers a representative overview of the information on linear optical properties that resides in scientific papers from the past 30 years. Public availability of these data will enable a quick search for the optical property of certain materials. The large size of this repository will accelerate data-driven research on the design and prediction of optical materials and their properties. To the best of our knowledge, this is the first auto-generated database of optical properties from a large number of scientific papers. We provide a web interface to aid the use of our database.

A survey on extremism analysis using natural language processing: definitions, literature review, trends and challenges

Extremism has grown as a global problem for society in recent years, especially after the apparition of movements such as jihadism. This and other extremist groups have taken advantage of different approaches, such as the use of Social Media, to spread their ideology, promote their acts and recruit followers. The extremist discourse, therefore, is reflected on the language used by these groups. Natural language processing (NLP) provides a way of detecting this type of content, and several authors make use of it to describe and discriminate the discourse held by these groups, with the final objective of detecting and preventing its spread. Following this approach, this survey aims to review the contributions of NLP to the field of extremism research, providing the reader with a comprehensive picture of the state of the art of this research area. The content includes a first conceptualization of the term extremism, the elements that compose an extremist discourse and the differences with other terms. After that, a review description and comparison of the frequently used NLP techniques is presented, including how they were applied, the insights they provided, the most frequently used NLP software tools, descriptive and classification applications, and the availability of datasets and data sources for research. Finally, research questions are approached and answered with highlights from the review, while future trends, challenges and directions derived from these highlights are suggested towards stimulating further research in this exciting research area.

Evaluation of patterns of progression on poly (ADP-ribose) polymerase inhibitor (PARPi) maintenance in ovarian cancer: a cross-sectional study

IntroductionDespite improvement in progression-free survival with poly (ADP-ribose) polymerase inhibitors (PARPi) as maintenance therapy for ovarian cancer, many patients will eventually progress on therapy. Oligoprogression is uniquely suited to considerations...