Clinical decision support with natural language processing facilitates determination of colonoscopy surveillance intervals

Natural Language Processing Can Automate Extraction of Barrett's Esophagus Endoscopy Quality Metrics

Objectives

To develop an automated natural language processing (NLP) method for extracting high-fidelity Barrett's Esophagus (BE) endoscopic surveillance and treatment data from the electronic health record (EHR).

Methods

Patients who underwent BE-related endoscopies between 2016 and 2020 at a single medical center were randomly assigned to a development or validation set. Those not aged 40 to 80 and those without confirmed BE were excluded. For each patient, free text pathology reports and structured procedure data were obtained. Gastroenterologists assigned ground truth labels. An NLP method leveraging MetaMap Lite generated endoscopy-level diagnosis and treatment data. Performance metrics were assessed for this data. The NLP methodology was then adapted to label key endoscopic eradication therapy (EET)-related endoscopy events and thereby facilitate calculation of patient-level pre-EET diagnosis, endotherapy time, and time to CE-IM.

Results

99 patients (377 endoscopies) and 115 patients (399 endoscopies) were included in the development and validation sets respectively. When assigning high-fidelity labels to the validation set, NLP achieved high performance (recall: 0.976, precision: 0.970, accuracy: 0.985, and F1-score: 0.972). 77 patients initiated EET and underwent 554 endoscopies. Key EET-related clinical event labels had high accuracy (EET start: 0.974, CE-D: 1.00, and CE-IM: 1.00), facilitating extraction of pre-treatment diagnosis, endotherapy time, and time to CE-IM.

Conclusions

High-fidelity BE endoscopic surveillance and treatment data can be extracted from routine EHR data using our automated, transparent NLP method. This method produces high-level clinical datasets for clinical research and quality metric assessment.

Deep learning approach to detection of colonoscopic information from unstructured reports

BACKGROUND

Colorectal cancer is a leading cause of cancer deaths. Several screening tests, such as colonoscopy, can be used to find polyps or colorectal cancer. Colonoscopy reports are often written in unstructured narrative text. The information embedded in the reports can be used for various purposes, including colorectal cancer risk prediction, follow-up recommendation, and quality measurement. However, the availability and accessibility of unstructured text data are still insufficient despite the large amounts of accumulated data. We aimed to develop and apply deep learning-based natural language processing (NLP) methods to detect colonoscopic information.

METHODS

This study applied several deep learning-based NLP models to colonoscopy reports. Approximately 280,668 colonoscopy reports were extracted from the clinical data warehouse of Samsung Medical Center. For 5,000 reports, procedural information and colonoscopic findings were manually annotated with 17 labels. We compared the long short-term memory (LSTM) and BioBERT model to select the one with the best performance for colonoscopy reports, which was the bidirectional LSTM with conditional random fields. Then, we applied pre-trained word embedding using large unlabeled data (280,668 reports) to the selected model.

RESULTS

The NLP model with pre-trained word embedding performed better for most labels than the model with one-hot encoding. The F1 scores for colonoscopic findings were: 0.9564 for lesions, 0.9722 for locations, 0.9809 for shapes, 0.9720 for colors, 0.9862 for sizes, and 0.9717 for numbers.

CONCLUSIONS

This study applied deep learning-based clinical NLP models to extract meaningful information from colonoscopy reports. The method in this study achieved promising results that demonstrate it can be applied to various practical purposes.

Artificial Intelligence and Machine Learning Based Intervention in Medical Infrastructure: A Review and Future Trends

People in the life sciences who work with Artificial Intelligence (AI) and Machine Learning (ML) are under increased pressure to develop algorithms faster than ever. The possibility of revealing innovative insights and speeding breakthroughs lies in using large datasets integrated on several levels. However, even if there is more data at our disposal than ever, only a meager portion is being filtered, interpreted, integrated, and analyzed. The subject of this technology is the study of how computers may learn from data and imitate human mental processes. Both an increase in the learning capacity and the provision of a decision support system at a size that is redefining the future of healthcare are enabled by AI and ML. This article offers a survey of the uses of AI and ML in the healthcare industry, with a particular emphasis on clinical, developmental, administrative, and global health implementations to support the healthcare infrastructure as a whole, along with the impact and expectations of each component of healthcare. Additionally, possible future trends and scopes of the utilization of this technology in medical infrastructure have also been discussed.

Combining text mining with clinical decision support in clinical practice: a scoping review

OBJECTIVE

Combining text mining (TM) and clinical decision support (CDS) could improve diagnostic and therapeutic processes in clinical practice. This review summarizes current knowledge of the TM-CDS combination in clinical practice, including their intended purpose, implementation in clinical practice, and barriers to such implementation.

MATERIALS AND METHODS

A search was conducted in PubMed, EMBASE, and Cochrane Library databases to identify full-text English language studies published before January 2022 with TM-CDS combination in clinical practice.

RESULTS

Of 714 identified and screened unique publications, 39 were included. The majority of the included studies are related to diagnosis (n = 26) or prognosis (n = 11) and used a method that was developed for a specific clinical domain, document type, or application. Most of the studies selected text containing parts of the electronic health record (EHR), such as reports (41%, n = 16) and free-text narratives (36%, n = 14), and 23 studies utilized a tool that had software "developed for the study". In 15 studies, the software source was openly available. In 79% of studies, the tool was not implemented in clinical practice. Barriers to implement these tools included the complexity of natural language, EHR incompleteness, validation and performance of the tool, lack of input from an expert team, and the adoption rate among professionals.

DISCUSSION/CONCLUSIONS

The available evidence indicates that the TM-CDS combination may improve diagnostic and therapeutic processes, contributing to increased patient safety. However, further research is needed to identify barriers to implementation and the impact of such tools in clinical practice.

Assessment of Electronic Health Record for Cancer Research and Patient Care Through a Scoping Review of Cancer Natural Language Processing

PURPOSE

The advancement of natural language processing (NLP) has promoted the use of detailed textual data in electronic health records (EHRs) to support cancer research and to facilitate patient care. In this review, we aim to assess EHR for cancer research and patient care by using the Minimal Common Oncology Data Elements (mCODE), which is a community-driven effort to define a minimal set of data elements for cancer research and practice. Specifically, we aim to assess the alignment of NLP-extracted data elements with mCODE and review existing NLP methodologies for extracting said data elements.

METHODS

Published literature studies were searched to retrieve cancer-related NLP articles that were written in English and published between January 2010 and September 2020 from main literature databases. After the retrieval, articles with EHRs as the data source were manually identified. A charting form was developed for relevant study analysis and used to categorize data including four main topics: metadata, EHR data and targeted cancer types, NLP methodology, and oncology data elements and standards.

RESULTS

A total of 123 publications were selected finally and included in our analysis. We found that cancer research and patient care require some data elements beyond mCODE as expected. Transparency and reproductivity are not sufficient in NLP methods, and inconsistency in NLP evaluation exists.

CONCLUSION

We conducted a comprehensive review of cancer NLP for research and patient care using EHRs data. Issues and barriers for wide adoption of cancer NLP were identified and discussed.

Novel technical and privacy-preserving technology for artificial intelligence in ophthalmology

PURPOSE OF REVIEW

The application of artificial intelligence (AI) in medicine and ophthalmology has experienced exponential breakthroughs in recent years in diagnosis, prognosis, and aiding clinical decision-making. The use of digital data has also heralded the need for privacy-preserving technology to protect patient confidentiality and to guard against threats such as adversarial attacks. Hence, this review aims to outline novel AI-based systems for ophthalmology use, privacy-preserving measures, potential challenges, and future directions of each.

RECENT FINDINGS

Several key AI algorithms used to improve disease detection and outcomes include: Data-driven, imagedriven, natural language processing (NLP)-driven, genomics-driven, and multimodality algorithms. However, deep learning systems are susceptible to adversarial attacks, and use of data for training models is associated with privacy concerns. Several data protection methods address these concerns in the form of blockchain technology, federated learning, and generative adversarial networks.

SUMMARY

AI-applications have vast potential to meet many eyecare needs, consequently reducing burden on scarce healthcare resources. A pertinent challenge would be to maintain data privacy and confidentiality while supporting AI endeavors, where data protection methods would need to rapidly evolve with AI technology needs. Ultimately, for AI to succeed in medicine and ophthalmology, a balance would need to be found between innovation and privacy.

A scoping review of ethics considerations in clinical natural language processing

Objectives

To review through an ethics lens the state of research in clinical natural language processing (NLP) for the study of bias and fairness, and to identify gaps in research.

Methods

We queried PubMed and Google Scholar for articles published between 2015 and 2021 concerning clinical NLP, bias, and fairness. We analyzed articles using a framework that combines the machine learning (ML) development process (ie, design, data, algorithm, and critique) and bioethical concepts of beneficence, nonmaleficence, autonomy, justice, as well as explicability. Our approach further differentiated between biases of clinical text (eg, systemic or personal biases in clinical documentation towards patients) and biases in NLP applications.

Results

Out of 1162 articles screened, 22 met criteria for full text review. We categorized articles based on the design (N = 2), data (N = 12), algorithm (N = 14), and critique (N = 17) phases of the ML development process.

Discussion

Clinical NLP can be used to study bias in applications reliant on clinical text data as well as explore biases in the healthcare setting. We identify 3 areas of active research that require unique ethical considerations about the potential for clinical NLP to address and/or perpetuate bias: (1) selecting metrics that interrogate bias in models; (2) opportunities and risks of identifying sensitive patient attributes; and (3) best practices in reconciling individual autonomy, leveraging patient data, and inferring and manipulating sensitive information of subgroups. Finally, we address the limitations of current ethical frameworks to fully address concerns of justice. Clinical NLP is a rapidly advancing field, and assessing current approaches against ethical considerations can help the discipline use clinical NLP to explore both healthcare biases and equitable NLP applications.

Implementation of App-Based Diabetes Medication Management: Outpatient and Perioperative Clinical Decision Support

PURPOSE OF REVIEW

Outpatient and perioperative therapeutic decision making for patients with diabetes involves increasingly complex medical-decision making due to rapid advances in knowledge and treatment modalities. We sought to review mobile decision support tools available to clinicians for this essential and increasingly difficult task, and to highlight the development and implementation of novel mobile applications for these purposes.

RECENT FINDINGS

We found 211 mobile applications related to diabetes from the search, but only five were found to provide clinical decision support for outpatient diabetes management and none for perioperative decision support. We found a dearth of tools for clinicians to navigate these tasks. We highlight key aspects for effective development of future diabetes decision support. These include just-in-time availability, respect for the five rights of clinical decision support, and integration with clinical workflows including the electronic medical record.

Development of a Natural Language Processing System for Assessing Quality Indicators from Free-Text Colonoscopy and Pathology Reports: Methodology Development and Applications (Preprint)

Background

Manual data extraction of colonoscopy quality indicators is time and labor intensive. Natural language processing (NLP), a computer-based linguistics technique, can automate the extraction of important clinical information, such as adverse events, from unstructured free-text reports. NLP information extraction can facilitate the optimization of clinical work by helping to improve quality control and patient management.

Objective

We developed an NLP pipeline to analyze free-text colonoscopy and pathology reports and evaluated its ability to automatically assess adenoma detection rate (ADR), sessile serrated lesion detection rate (SDR), and postcolonoscopy surveillance intervals.

Methods

The NLP tool for extracting colonoscopy quality indicators was developed using a data set of 2000 screening colonoscopy reports from a single health care system, with an associated 1425 pathology reports. The NLP system was then tested on a data set of 1000 colonoscopy reports and its performance was compared with that of 5 human annotators. Additionally, data from 54,562 colonoscopies performed between 2010 and 2019 were analyzed using the NLP pipeline.

Results

The NLP pipeline achieved an overall accuracy of 0.99-1.00 for identifying polyp subtypes, 0.99-1.00 for identifying the anatomical location of polyps, and 0.98 for counting the number of neoplastic polyps. The NLP pipeline achieved performance similar to clinical experts for assessing ADR, SDR, and surveillance intervals. NLP analysis of a 10-year colonoscopy data set identified great individual variance in colonoscopy quality indicators among 25 endoscopists.

Conclusions

The NLP pipeline could accurately extract information from colonoscopy and pathology reports and demonstrated clinical efficacy for assessing ADR, SDR, and surveillance intervals in these reports. Implementation of the system enabled automated analysis and feedback on quality indicators, which could motivate endoscopists to improve the quality of their performance and improve clinical decision-making in colorectal cancer screening programs.

Automated identification and assignment of colonoscopy surveillance recommendations for individuals with colorectal polyps

BACKGROUND AND AIMS

Determining surveillance intervals for patients with colorectal polyps is critical but time-consuming and challenging to do reliably. We present the development and assessment of a pipeline that leverages natural language processing techniques to automatically extract and analyze relevant polyp findings from free-text colonoscopy and pathology reports. Using this information, we categorized individual patients into 6 postcolonoscopy surveillance intervals defined by the U.S. Multi-Society Task Force on Colorectal Cancer.

METHODS

Using a set of 546 randomly selected colonoscopy and pathology reports from 324 patients in a single health system, we used a combination of statistical classifiers and rule-based methods to extract polyp properties from each report type, associate properties with unique polyps, and classify a patient into 1 of 6 risk categories by integrating information from both report types. We then assessed the pipeline's performance by determining the positive predictive value (PPV), sensitivity, and F-score of the algorithm, compared with the determination of surveillance intervals by a gastroenterologist.

RESULTS

The pipeline was developed using 346 reports (224 colonoscopy and 122 pathology) from 224 patients and evaluated on an independent test set of 200 reports (100 colonoscopy and 100 pathology) from 100 patients. We achieved an average PPV, sensitivity, and F-score of .92, .95, and .93, respectively, across targeted entities for colonoscopy. Pathology extraction achieved a PPV, sensitivity, and F-score of .95, .97, and .96. The system achieved an overall accuracy of 92% in assigning the recommended interval for surveillance colonoscopy.

CONCLUSIONS

This study demonstrates the feasibility of using machine learning to automatically extract findings and classify patients to appropriate risk categories and corresponding surveillance intervals. Incorporating this system can facilitate proactive and timely follow-up after screening colonoscopy and enable real-time quality assessment of prevention programs and providers.

Simplifying Measurement of Adenoma Detection Rates for Colonoscopy

BACKGROUND

Adenoma detection rate (ADR) is the colonoscopy quality metric with the strongest association to interval or "missed" cancer. Accurate measurement of ADR can be laborious and costly.

AIMS

Our aim was to determine if administrative procedure codes for colonoscopy and text searches of pathology results for adenoma mentions could estimate ADR.

METHODS

We identified US Veterans with a colonoscopy using Current Procedure Terminology (CPT) codes between January 2013 and December 2016 at ten Veterans Affairs sites. We applied simple text searches using Microsoft SQL Server full-text searches to query all pathology notes for "adenoma(s)" or "adenomatous" text mentions to calculate ADRs. To validate our identification of colonoscopy procedures, endoscopists of record, and adenoma detection from the electronic health record, we manually reviewed a random sample of 2000 procedure and pathology notes from the 10 sites.

RESULTS

Structured data fields were accurate in identification of colonoscopies being performed (PPV = 0.99; 95% CI 0.99-1.00) and identifying the endoscopist of record (PPV of 0.95; 95% CI 0.94-0.96) for ADR measurement. Simple text searches of pathology notes for adenoma mentions had excellent performance statistics as follows: sensitivity 0.99 (95% CI 0.98-1.00), specificity 0.93 (95% CI 0.92-0.95), NPV 0.99 (95% CI 0.98-1.00), and PPV 0.93 (0.91-0.94) for measurement of ADR. There was no clinically significant difference in the estimates of overall ADR vs. screening ADR (p > 0.05).

CONCLUSIONS

Measuring ADR using administrative codes and text searches from pathology results is an efficient method to broadly survey colonoscopy quality.

Clinically relevant pretraining is all you need

Clinical notes present a wealth of information for applications in the clinical domain, but heterogeneity across clinical institutions and settings presents challenges for their processing. The clinical natural language processing field has made strides in overcoming domain heterogeneity, while pretrained deep learning models present opportunities to transfer knowledge from one task to another. Pretrained models have performed well when transferred to new tasks; however, it is not well understood if these models generalize across differences in institutions and settings within the clinical domain. We explore if institution or setting specific pretraining is necessary for pretrained models to perform well when transferred to new tasks. We find no significant performance difference between models pretrained across institutions and settings, indicating that clinically pretrained models transfer well across such boundaries. Given a clinically pretrained model, clinical natural language processing researchers may forgo the time-consuming pretraining step without a significant performance drop.

The Impact of Pretrained Language Models on Negation and Speculation Detection in Cross-Lingual Medical Text: Comparative Study

Background

Negation and speculation are critical elements in natural language processing (NLP)-related tasks, such as information extraction, as these phenomena change the truth value of a proposition. In the clinical narrative that is informal, these linguistic facts are used extensively with the objective of indicating hypotheses, impressions, or negative findings. Previous state-of-the-art approaches addressed negation and speculation detection tasks using rule-based methods, but in the last few years, models based on machine learning and deep learning exploiting morphological, syntactic, and semantic features represented as spare and dense vectors have emerged. However, although such methods of named entity recognition (NER) employ a broad set of features, they are limited to existing pretrained models for a specific domain or language.

Objective

As a fundamental subsystem of any information extraction pipeline, a system for cross-lingual and domain-independent negation and speculation detection was introduced with special focus on the biomedical scientific literature and clinical narrative. In this work, detection of negation and speculation was considered as a sequence-labeling task where cues and the scopes of both phenomena are recognized as a sequence of nested labels recognized in a single step.

Methods

We proposed the following two approaches for negation and speculation detection: (1) bidirectional long short-term memory (Bi-LSTM) and conditional random field using character, word, and sense embeddings to deal with the extraction of semantic, syntactic, and contextual patterns and (2) bidirectional encoder representations for transformers (BERT) with fine tuning for NER.

Results

The approach was evaluated for English and Spanish languages on biomedical and review text, particularly with the BioScope corpus, IULA corpus, and SFU Spanish Review corpus, with F-measures of 86.6%, 85.0%, and 88.1%, respectively, for NeuroNER and 86.4%, 80.8%, and 91.7%, respectively, for BERT.

Conclusions

These results show that these architectures perform considerably better than the previous rule-based and conventional machine learning–based systems. Moreover, our analysis results show that pretrained word embedding and particularly contextualized embedding for biomedical corpora help to understand complexities inherent to biomedical text.

Development of an Automated Algorithm to Generate Guideline-based Recommendations for Follow-up Colonoscopy

BACKGROUND AND AIMS

Physician adherence to published colonoscopy surveillance guidelines varies. We aimed to develop and validate an automated clinical decision support algorithm that can extract procedure and pathology data from the electronic medical record (EMR) and generate surveillance intervals congruent with guidelines, which might increase physician adherence.

METHODS

We constructed a clinical decision support (CDS) algorithm based on guidelines from the United States Multi-Society Task Force on Colorectal Cancer. We used a randomly generated validation dataset of 300 outpatient colonoscopies performed at the Cleveland Clinic from 2012 through 2016 to evaluate the accuracy of extracting data from reports stored in the EMR using natural language processing (NLP). We compared colonoscopy follow-up recommendations from the CDS algorithm, endoscopists, and task force guidelines. Using a testing dataset of 2439 colonoscopies, we compared endoscopist recommendations with those of the algorithm.

RESULTS

Manual review of the validation dataset confirmed the NLP program accurately extracted procedure and pathology data for all cases. Recommendations made by endoscopists and the CDS algorithm were guideline-concordant in 62% and 99% of cases, respectively. Discrepant recommendations by endoscopists were earlier than recommended in 94% of the cases. In the testing dataset, 69% of endoscopist and NLP-CDS algorithm recommendations were concordant. Discrepant recommendations by endoscopists were earlier than guidelines in 91% of cases.

CONCLUSIONS

We constructed and tested an automated CDS algorithm that can use NLP-extracted data from the EMR to generate follow-up colonoscopy surveillance recommendations based on published guidelines.

Designing, Conducting, and Reporting Clinical Decision Support Studies: Recommendations and Call to Action

By enabling more efficient and effective medical decision making, computer-based clinical decision support (CDS) could unlock widespread benefits from the significant investment in electronic health record (EHR) systems in the United States. Evidence from high-quality CDS studies is needed to enable and support this vision of CDS-facilitated care optimization, but limited guidance is available in the literature for designing and reporting CDS studies. To address this research gap, this article provides recommendations for designing, conducting, and reporting CDS studies to: 1) ensure that EHR data to inform the CDS are available; 2) choose decision rules that are consistent with local care processes; 3) target the right users and workflows; 4) make the CDS easy to access and use; 5) minimize the burden placed on users; 6) incorporate CDS success factors identified in the literature, in particular the automatic provision of CDS as a part of clinician workflow; 7) ensure that the CDS rules are adequately tested; 8) select meaningful evaluation measures; 9) use as rigorous a study design as is feasible; 10) think about how to deploy the CDS beyond the original host organization; 11) report the study in context; 12) help the audience understand why the intervention succeeded or failed; and 13) consider the financial implications. If adopted, these recommendations should help advance the vision of more efficient, effective care facilitated by useful and widely available CDS.

Impact of a Clinical Decision Support System on Guideline Adherence of Surveillance Recommendations for Colonoscopy After Polypectomy

Background: Surveillance colonoscopy is required in patients with polyps due to an elevated colorectal cancer (CRC) risk; however, studies suggest substantial overuse and underuse of surveillance colonoscopy. The goal of this study was to characterize guideline adherence of surveillance recommendations after implementation of an electronic medical record (EMR)-based Colonoscopy Pathology Reporting and Clinical Decision Support System (CoRS). Methods: We performed a retrospective cohort study of patients who underwent colonoscopy with polypectomy at a safety-net healthcare system before (n=1,822) and after (n=1,320) implementation of CoRS in December 2013. Recommendations were classified as guideline-adherent or nonadherent according to the US Multi-Society Task Force on CRC. We defined surveillance recommendations shorter and longer than guideline recommendations as potential overuse and underuse, respectively. We used multivariable generalized linear mixed models to identify correlates of guideline-adherent recommendations. Results: The proportion of guideline-adherent surveillance recommendations was significantly higher post-CoRS than pre-CoRS (84.6% vs 77.4%; P<.001), with fewer recommendations for potential overuse and underuse. In the post-CoRS period, CoRS was used for 89.8% of cases and, compared with cases for which it was not used, was associated with a higher proportion of guideline-adherent recommendations (87.0% vs 63.4%; RR, 1.34; 95% CI, 1.23-1.42). In multivariable analysis, surveillance recommendations were also more likely to be guideline-adherent in patients with adenomas but less likely among those with fair bowel preparation and those with family history of CRC. Of 203 nonadherent recommendations, 70.4% were considered potential overuse, 20.2% potential underuse, and 9.4% were not provided surveillance recommendations. Conclusions: An EMR-based CoRS was widely used and significantly improved guideline adherence of surveillance recommendations.

Facilitating accurate health provider directories using natural language processing

BACKGROUND

Accurate information in provider directories are vital in health care including health information exchange, health benefits exchange, quality reporting, and in the reimbursement and delivery of care. Maintaining provider directory data and keeping it up to date is challenging. The objective of this study is to determine the feasibility of using natural language processing (NLP) techniques to combine disparate resources and acquire accurate information on health providers.

METHODS

Publically available state licensure lists in Connecticut were obtained along with National Plan and Provider Enumeration System (NPPES) public use files. Connecticut licensure lists textual information of each health professional who is licensed to practice within the state. A NLP-based system was developed based on healthcare provider taxonomy code, location, name and address information to identify textual data within the state and federal records. Qualitative and quantitative evaluation were performed, and the recall and precision were calculated.

RESULTS

We identified nurse midwives, nurse practitioners, and dentists in the State of Connecticut. The recall and precision were 0.95 and 0.93 respectively. Using the system, we were able to accurately acquire 6849 of the 7177 records of health provider directory information.

CONCLUSIONS

The authors demonstrated that the NLP- based approach was effective at acquiring health provider information. Furthermore, the NLP-based system can always be applied to update information further reducing processing burdens as data changes.

The Role of Artificial Intelligence in Clinical Decision Support Systems and a Classification Framework

Clinical decision support systems are meant to improve the quality of decision-making in healthcare. Artificial intelligence is the science of creating intelligent systems that solve complex problems at the level of or better than human experts. Combining artificial intelligence methods into clinical decision support will enable the utilization of large quantities of data to produce relevant decision-making information to practitioners. This article examines various artificial intelligence methodologies and shows how they may be incorporated into clinical decision-making systems. A framework for describing artificial intelligence applications in clinical decision support systems is presented.

Population Health Management for Inflammatory Bowel Disease

Inflammatory bowel diseases (IBDs) are chronic and impose significant, multidimensional burdens on patients and health care systems. The increasing prevalence of IBD will only worsen this problem globally-population health management (PHM) strategies are needed to increase quality of care and population health outcomes while reducing health care costs. We discuss the key components of PHM in IBD. Effective implementation of PHM strategies requires accurate identification of at-risk patients and key areas of variability in care. Improving outcomes of the at-risk population requires implementation of a multicomponent chronic care model designed to shift delivery of ambulatory care from acute, episodic, and reactive encounters, to proactive, planned, long-term care. This is achieved through team care of an activated patient with the help of remote monitoring, clinical information systems, and integrated decision support, with accompanying changes in delivery systems. Performance measurement is integral to any PHM strategy. This involves developing and implementing meaningful metrics of different phases of quality of IBD care and measuring them efficiently using modern clinical information systems. Such an integrated framework of PHM in IBD will facilitate the delivery of high-value care to patients.

Using Electronic Health Records for Quality Measurement and Accountability in Care of the Seriously Ill: Opportunities and Challenges

BACKGROUND

As our population ages and the burden of chronic illness rises, there is increasing need to implement quality metrics that measure and benchmark care of the seriously ill, including the delivery of both primary care and specialty palliative care. Such metrics can be used to drive quality improvement, value-based payment, and accountability for population-based outcomes.

METHODS

In this article, we examine use of the electronic health record (EHR) as a tool to assess quality of serious illness care through narrative review and description of a palliative care quality metrics program in a large healthcare system.

RESULTS

In the search for feasible, reliable, and valid palliative care quality metrics, the EHR is an attractive option for collecting quality data on large numbers of seriously ill patients. However, important challenges to using EHR data for quality improvement and accountability exist, including understanding the validity, reliability, and completeness of the data, as well as acknowledging the difference between care documented and care delivered. Challenges also include developing achievable metrics that are clearly linked to patient and family outcomes and addressing data interoperability across sites as well as EHR platforms and vendors. This article summarizes the strengths and weakness of the EHR as a data source for accountability of community- and population-based programs for serious illness, describes the implementation of EHR data in the palliative care quality metrics program at the University of Washington, and, based on that experience, discusses opportunities and challenges. Our palliative care metrics program was designed to serve as a resource for other healthcare systems.

DISCUSSION

Although the EHR offers great promise for enhancing quality of care provided for the seriously ill, significant challenges remain to operationalizing this promise on a national scale and using EHR data for population-based quality and accountability.

Most Premature Surveillance Colonoscopy Is Not Attributable to Bowel Preparation or New Clinical Indications

BACKGROUND AND AIMS

Surveillance colonoscopy frequently occurs prior to recommended intervals. Studies delineating the reasons why premature surveillance occurs are limited. We sought to define the frequency in which premature surveillance colonoscopy occurs in the setting of an inadequate bowel preparation or with a provided patient clinical indication versus when premature surveillance colonoscopy occurs without any provided discernible rationale in the setting of adequate bowel preparation.

METHODS

A retrospective cross-sectional cohort study of 700 patients undergoing colonoscopy for an indication of "surveillance of polyps" from 2008 to 2014 at two tertiary-care referral centers was carried out. Patients were deemed either "adherent" or "premature" based on US Multi-Society Task Force guideline intervals for surveillance colonoscopy. A documented decision-making rationale for premature surveillance was determined through review of the electronic medical record with assessment of clinical notes and endoscopy order and report.

RESULTS

Premature surveillance occurred in 43.0 % (n = 301) of all surveillance colonoscopies performed. Among the premature cases, rationale was attributed to inadequate bowel preparation in 17.3 % (n = 52) and due to a new clinical indication in 21.6 % (n = 65). Most commonly, in 61.1 % (n = 184) of premature cases, no rationale was documented for the early colonoscopy.

CONCLUSIONS

Documented decision-making rationale for premature surveillance colonoscopy is usually absent in premature cases with inadequate bowel preparation and new clinical indications explaining only a minority of the occurrences.

Editorial: On the Quality of Quality Metrics: Rethinking What Defines a Good Colonoscopy

The colonoscopy quality assurance movement has focused on a variety of process metrics, including the adenoma detection rate (ADR). However, the ADR only ascertains whether or not at least one adenoma is identified. Supplemental measures that quantify all neoplasia have been proposed. In this issue of the American Journal of Gastroenterology, Aniwan and colleagues performed tandem screening colonoscopies to determine the adenoma miss rate among high-ADR endoscopists. This permitted validation of supplemental colonoscopy quality metrics. This study highlights potential limitations of ADR and the need for further refinement of colonoscopy quality metrics, although logistic challenges abound.

A natural language processing program effectively extracts key pathologic findings from radical prostatectomy reports

INTRODUCTION AND OBJECTIVE

Natural language processing (NLP) software programs have been widely developed to transform complex free text into simplified organized data. Potential applications in the field of medicine include automated report summaries, physician alerts, patient repositories, electronic medical record (EMR) billing, and quality metric reports. Despite these prospects and the recent widespread adoption of EMR, NLP has been relatively underutilized. The objective of this study was to evaluate the performance of an internally developed NLP program in extracting select pathologic findings from radical prostatectomy specimen reports in the EMR.

METHODS

An NLP program was generated by a software engineer to extract key variables from prostatectomy reports in the EMR within our healthcare system, which included the TNM stage, Gleason grade, presence of a tertiary Gleason pattern, histologic subtype, size of dominant tumor nodule, seminal vesicle invasion (SVI), perineural invasion (PNI), angiolymphatic invasion (ALI), extracapsular extension (ECE), and surgical margin status (SMS). The program was validated by comparing NLP results to a gold standard compiled by two blinded manual reviewers for 100 random pathology reports.

RESULTS

NLP demonstrated 100% accuracy for identifying the Gleason grade, presence of a tertiary Gleason pattern, SVI, ALI, and ECE. It also demonstrated near-perfect accuracy for extracting histologic subtype (99.0%), PNI (98.9%), TNM stage (98.0%), SMS (97.0%), and dominant tumor size (95.7%). The overall accuracy of NLP was 98.7%. NLP generated a result in <1 second, whereas the manual reviewers averaged 3.2 minutes per report.

CONCLUSIONS

This novel program demonstrated high accuracy and efficiency identifying key pathologic details from the prostatectomy report within an EMR system. NLP has the potential to assist urologists by summarizing and highlighting relevant information from verbose pathology reports. It may also facilitate future urologic research through the rapid and automated creation of large databases.

Using natural language processing to provide personalized learning opportunities from trainee clinical notes

OBJECTIVE

Assessment of medical trainee learning through pre-defined competencies is now commonplace in schools of medicine. We describe a novel electronic advisor system using natural language processing (NLP) to identify two geriatric medicine competencies from medical student clinical notes in the electronic medical record: advance directives (AD) and altered mental status (AMS).

MATERIALS AND METHODS

Clinical notes from third year medical students were processed using a general-purpose NLP system to identify biomedical concepts and their section context. The system analyzed these notes for relevance to AD or AMS and generated custom email alerts to students with embedded supplemental learning material customized to their notes. Recall and precision of the two advisors were evaluated by physician review. Students were given pre and post multiple choice question tests broadly covering geriatrics.

RESULTS

Of 102 students approached, 66 students consented and enrolled. The system sent 393 email alerts to 54 students (82%), including 270 for AD and 123 for AMS. Precision was 100% for AD and 93% for AMS. Recall was 69% for AD and 100% for AMS. Students mentioned ADs for 43 patients, with all mentions occurring after first having received an AD reminder. Students accessed educational links 34 times from the 393 email alerts. There was no difference in pre (mean 62%) and post (mean 60%) test scores.

CONCLUSIONS

The system effectively identified two educational opportunities using NLP applied to clinical notes and demonstrated a small change in student behavior. Use of electronic advisors such as these may provide a scalable model to assess specific competency elements and deliver educational opportunities.

Effectiveness, training and quality assurance of colonoscopy screening for colorectal cancer

Screening for colorectal cancer has been proven to be effective in reducing colorectal cancer incidence and mortality. While the precise benefit of screening exclusively by colonoscopy is not yet known, unarguably, the exam is central to the success of any screening programme. The test affords the opportunity to detect and resect neoplasia across the entire large bowel and is the definitive examination when other screening tests are positive. However, colonoscopy is invasive and often requires sedation as well as extensive bowel preparation, all of which puts the patient at risk. Furthermore, the test can technically be demanding and, unarguably, there is variation in how it is performed. This variation in performance has now been definitively linked to important outcome measures. For example, interval cancers are more common in low adenoma detectors as compared with high adenoma detectors. This review outlines the most current thinking regarding the effectiveness of colonoscopy as a screening tool. It also outlines key concepts to optimise its performance through robust quality assurance programmes and high-quality training.

Multi-center colonoscopy quality measurement utilizing natural language processing

BACKGROUND

An accurate system for tracking of colonoscopy quality and surveillance intervals could improve the effectiveness and cost-effectiveness of colorectal cancer (CRC) screening and surveillance. The purpose of this study was to create and test such a system across multiple institutions utilizing natural language processing (NLP).

METHODS

From 42,569 colonoscopies with pathology records from 13 centers, we randomly sampled 750 paired reports. We trained (n=250) and tested (n=500) an NLP-based program with 19 measurements that encompass colonoscopy quality measures and surveillance interval determination, using blinded, paired, annotated expert manual review as the reference standard. The remaining 41,819 nonannotated documents were processed through the NLP system without manual review to assess performance consistency. The primary outcome was system accuracy across the 19 measures.

RESULTS

A total of 176 (23.5%) documents with 252 (1.8%) discrepant content points resulted from paired annotation. Error rate within the 500 test documents was 31.2% for NLP and 25.4% for the paired annotators (P=0.001). At the content point level within the test set, the error rate was 3.5% for NLP and 1.9% for the paired annotators (P=0.04). When eight vaguely worded documents were removed, 125 of 492 (25.4%) were incorrect by NLP and 104 of 492 (21.1%) by the initial annotator (P=0.07). Rates of pathologic findings calculated from NLP were similar to those calculated by annotation for the majority of measurements. Test set accuracy was 99.6% for CRC, 95% for advanced adenoma, 94.6% for nonadvanced adenoma, 99.8% for advanced sessile serrated polyps, 99.2% for nonadvanced sessile serrated polyps, 96.8% for large hyperplastic polyps, and 96.0% for small hyperplastic polyps. Lesion location showed high accuracy (87.0-99.8%). Accuracy for number of adenomas was 92%.

CONCLUSIONS

NLP can accurately report adenoma detection rate and the components for determining guideline-adherent colonoscopy surveillance intervals across multiple sites that utilize different methods for reporting colonoscopy findings.

Nursing identity and patient-centredness in scholarly health services research: a computational text analysis of PubMed abstracts 1986-2013

BACKGROUND

The most important and contested element of nursing identity may be the patient-centredness of nursing, though this concept is not well-treated in the nursing identity literature. More conceptually-based mapping of nursing identity constructs are needed to help nurses shape their identity. The field of computational text analytics offers new opportunities to scrutinise how growing disciplines such as health services research construct nursing identity. This paper maps the conceptual content of scholarly health services research in PubMed as it relates to the patient-centeredness of nursing.

METHODS

Computational text analytics software was used to analyse all health services abstracts in the database PubMed since 1986. Abstracts were treated as indicative of the content of health services research. The database PubMed was searched for all research papers using the term "service" or "services" in the abstract or keywords for the period 01/01/1986 to 30/06/2013. A total of 234,926 abstracts were obtained. Leximancer software was used in 1) mapping of 4,144,458 instances of 107 concepts; 2) analysis of 106 paired concept co-occurrences for the nursing concept; and 3) sentiment analysis of the nursing concept versus patient, family and community concepts, and clinical concepts.

RESULTS

Nursing is constructed within quality assurance or service implementation or workforce development concepts. It is relatively disconnected from patient, family or community care concepts.

CONCLUSIONS

For those who agree that patient-centredness should be a part of nursing identity in practice, this study suggests that there is a need for development of health services research into both the nature of the caring construct in nursing identity and its expression in practice. More fundamentally, the study raises questions about whether health services research cultures even value the politically popular idea of nurses as patient-centred caregivers and whether they should.

Current and future applications of natural language processing in the field of digestive diseases

Natural language processing (NLP) is a technology that uses computer-based linguistics and artificial intelligence to identify and extract information from free-text data sources such as progress notes, procedure and pathology reports, and laboratory and radiologic test results. With the creation of large databases and the trajectory of health care reform, NLP holds the promise of enhancing the availability, quality, and utility of clinical information with the goal of improving documentation, quality, and efficiency of health care in the United States. To date, NLP has shown promise in automatically determining appropriate colonoscopy intervals and identifying cases of inflammatory bowel disease from electronic health records. The objectives of this review are to provide background on NLP and its associated terminology, to describe how NLP has been used thus far in the field of digestive diseases, and to identify its potential future uses.