Toward a Learning Health-care System - Knowledge Delivery at the Point of Care Empowered by Big Data and NLP

Near Real-time Natural Language Processing for the Extraction of Abdominal Aortic Aneurysm Diagnoses From Radiology Reports: Algorithm Development and Validation Study

BACKGROUND

Management of abdominal aortic aneurysms (AAAs) requires serial imaging surveillance to evaluate the aneurysm dimension. Natural language processing (NLP) has been previously developed to retrospectively identify patients with AAA from electronic health records (EHRs). However, there are no reported studies that use NLP to identify patients with AAA in near real-time from radiology reports.

OBJECTIVE

This study aims to develop and validate a rule-based NLP algorithm for near real-time automatic extraction of AAA diagnosis from radiology reports for case identification.

METHODS

The AAA-NLP algorithm was developed and deployed to an EHR big data infrastructure for near real-time processing of radiology reports from May 1, 2019, to September 2020. NLP extracted named entities for AAA case identification and classified subjects as cases and controls. The reference standard to assess algorithm performance was a manual review of processed radiology reports by trained physicians following standardized criteria. Reviewers were blinded to the diagnosis of each subject. The AAA-NLP algorithm was refined in 3 successive iterations. For each iteration, the AAA-NLP algorithm was modified based on performance compared to the reference standard.

RESULTS

A total of 360 reports were reviewed, of which 120 radiology reports were randomly selected for each iteration. At each iteration, the AAA-NLP algorithm performance improved. The algorithm identified AAA cases in near real-time with high positive predictive value (0.98), sensitivity (0.95), specificity (0.98), F1 score (0.97), and accuracy (0.97).

CONCLUSIONS

Implementation of NLP for accurate identification of AAA cases from radiology reports with high performance in near real time is feasible. This NLP technique will support automated input for patient care and clinical decision support tools for the management of patients with AAA.  .

Transforming epilepsy research: A systematic review on natural language processing applications

Despite improved ancillary investigations in epilepsy care, patients' narratives remain indispensable for diagnosing and treatment monitoring. This wealth of information is typically stored in electronic health records and accumulated in medical journals in an unstructured manner, thereby restricting complete utilization in clinical decision-making. To this end, clinical researchers increasing apply natural language processing (NLP)-a branch of artificial intelligence-as it removes ambiguity, derives context, and imbues standardized meaning from free-narrative clinical texts. This systematic review presents an overview of the current NLP applications in epilepsy and discusses the opportunities and drawbacks of NLP alongside its future implications. We searched the PubMed and Embase databases with a "natural language processing" and "epilepsy" query (March 4, 2022) and included original research articles describing the application of NLP techniques for textual analysis in epilepsy. Twenty-six studies were included. Fifty-eight percent of these studies used NLP to classify clinical records into predefined categories, improving patient identification and treatment decisions. Other applications of NLP had structured clinical information retrieval from electronic health records, scientific papers, and online posts of patients. Challenges and opportunities of NLP applications for enhancing epilepsy care and research are discussed. The field could further benefit from NLP by replicating successes in other health care domains, such as NLP-aided quality evaluation for clinical decision-making, outcome prediction, and clinical record summarization.

Natural language processing for identification of hypertrophic cardiomyopathy patients from cardiac magnetic resonance reports

Background

Cardiac magnetic resonance (CMR) imaging is important for diagnosis and risk stratification of hypertrophic cardiomyopathy (HCM) patients. However, collection of information from large numbers of CMR reports by manual review is time-consuming, error-prone and costly. Natural language processing (NLP) is an artificial intelligence method for automated extraction of information from narrative text including text in CMR reports in electronic health records (EHR). Our objective was to assess whether NLP can accurately extract diagnosis of HCM from CMR reports.

Methods

An NLP system with two tiers was developed for information extraction from narrative text in CMR reports; the first tier extracted information regarding HCM diagnosis while the second extracted categorical and numeric concepts for HCM classification. We randomly allocated 200 HCM patients with CMR reports from 2004 to 2018 into training (100 patients with 185 CMR reports) and testing sets (100 patients with 206 reports).

Results

NLP algorithms demonstrated very high performance compared to manual annotation. The algorithm to extract HCM diagnosis had accuracy of 0.99. The accuracy for categorical concepts included HCM morphologic subtype 0.99, systolic anterior motion of the mitral valve 0.96, mitral regurgitation 0.93, left ventricular (LV) obstruction 0.94, location of obstruction 0.92, apical pouch 0.98, LV delayed enhancement 0.93, left atrial enlargement 0.99 and right atrial enlargement 0.98. Accuracy for numeric concepts included maximal LV wall thickness 0.96, LV mass 0.99, LV mass index 0.98, LV ejection fraction 0.98 and right ventricular ejection fraction 0.99.

Conclusions

NLP identified and classified HCM from CMR narrative text reports with very high performance.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-022-02017-y.

Quality assessment of functional status documentation in EHRs across different healthcare institutions

The secondary use of electronic health records (EHRs) faces challenges in the form of varying data quality-related issues. To address that, we retrospectively assessed the quality of functional status documentation in EHRs of persons participating in Mayo Clinic Study of Aging (MCSA). We used a convergent parallel design to collect quantitative and qualitative data and independently analyzed the findings. We discovered a heterogeneous documentation process, where the care practice teams, institutions, and EHR systems all play an important role in how text data is documented and organized. Four prevalent instrument-assisted documentation (iDoc) expressions were identified based on three distinct instruments: Epic smart form, questionnaire, and occupational therapy and physical therapy templates. We found strong differences in the usage, information quality (intrinsic and contextual), and naturality of language among different type of iDoc expressions. These variations can be caused by different source instruments, information providers, practice settings, care events and institutions. In addition, iDoc expressions are context specific and thus shall not be viewed and processed uniformly. We recommend conducting data quality assessment of unstructured EHR text prior to using the information.

PO2RDF: representation of real-world data for precision oncology using resource description framework

Background

Next-generation sequencing provides comprehensive information about individuals’ genetic makeup and is commonplace in precision oncology practice. Due to the heterogeneity of individual patient’s disease conditions and treatment journeys, not all targeted therapies were initiated despite actionable mutations. To better understand and support the clinical decision-making process in precision oncology, there is a need to examine real-world associations between patients’ genetic information and treatment choices.

Methods

To fill the gap of insufficient use of real-world data (RWD) in electronic health records (EHRs), we generated a single Resource Description Framework (RDF) resource, called PO2RDF (precision oncology to RDF), by integrating information regarding genes, variants, diseases, and drugs from genetic reports and EHRs.

Results

There are a total 2,309,014 triples contained in the PO2RDF. Among them, 32,815 triples are related to Gene, 34,695 triples are related to Variant, 8,787 triples are related to Disease, 26,154 triples are related to Drug. We performed two use case analyses to demonstrate the usability of the PO2RDF: (1) we examined real-world associations between EGFR mutations and targeted therapies to confirm existing knowledge and detect off-label use. (2) We examined differences in prognosis for lung cancer patients with/without TP53 mutations.

Conclusions

In conclusion, our work proposed to use RDF to organize and distribute clinical RWD that is otherwise inaccessible externally. Our work serves as a pilot study that will lead to new clinical applications and could ultimately stimulate progress in the field of precision oncology.

The Impact of Big Data Management Capabilities on the Performance of Manufacturing Firms in Asian Economy During COVID-19: The Mediating Role of Organizational Agility and Moderating Role of Information Technology Capability

The main purpose of this study is to examine the impact of the big data management capabilities on the performance of manufacturing firms in the Asian Economy during coronavirus disease 2019 (COVID-19). In addition to this, this study is also planned to examine the mediating role of organizational agility in the relationship between the big data management capabilities and the performance of Chinese manufacturing firms during COVID-19. Last, this study has examined the moderating role of information technology capability in the relationship between the big data management capabilities and performance of Chinese manufacturing firms during COVID-19. This study adopted the quantitative method of research with a cross-sectional technique. This study employed a questionnaire to gather the data as a research instrument. This study has used the purposive sampling method by keeping in mind the context of this study. Employees of the Chinese SMEs that were at least 10 years old were the population of this study. The research model was being analyzed by employing the "partial least squares" technique through statistical software the Smart PLS version 3. The results are in line with the proposed hypothesis. This study contributed to the literature by suggesting characteristics that promote or prevent the organization from successfully implementing big data and pointed out that showing resistance in information management system implementation may have different effects on the organization. Besides, the study also discussed the relationship between such information systems and the organization. Findings of these two factors provide insights for the practitioners and researchers in assessing the success or failure of organizations for using big data.

Impact of Different Approaches to Preparing Notes for Analysis With Natural Language Processing on the Performance of Prediction Models in Intensive Care

Supplemental Digital Content is available in the text.

OBJECTIVES:

To evaluate whether different approaches in note text preparation (known as preprocessing) can impact machine learning model performance in the case of mortality prediction ICU.

DESIGN:

Clinical note text was used to build machine learning models for adults admitted to the ICU. Preprocessing strategies studied were none (raw text), cleaning text, stemming, term frequency-inverse document frequency vectorization, and creation of n-grams. Model performance was assessed by the area under the receiver operating characteristic curve. Models were trained and internally validated on University of California San Francisco data using 10-fold cross validation. These models were then externally validated on Beth Israel Deaconess Medical Center data.

SETTING:

ICUs at University of California San Francisco and Beth Israel Deaconess Medical Center.

SUBJECTS:

Ten thousand patients in the University of California San Francisco training and internal testing dataset and 27,058 patients in the external validation dataset, Beth Israel Deaconess Medical Center.

INTERVENTIONS:

None.

MEASUREMENTS AND MAIN RESULTS:

Mortality rate at Beth Israel Deaconess Medical Center and University of California San Francisco was 10.9% and 7.4%, respectively. Data are presented as area under the receiver operating characteristic curve (95% CI) for models validated at University of California San Francisco and area under the receiver operating characteristic curve for models validated at Beth Israel Deaconess Medical Center. Models built and trained on University of California San Francisco data for the prediction of inhospital mortality improved from the raw note text model (AUROC, 0.84; CI, 0.80–0.89) to the term frequency-inverse document frequency model (AUROC, 0.89; CI, 0.85–0.94). When applying the models developed at University of California San Francisco to Beth Israel Deaconess Medical Center data, there was a similar increase in model performance from raw note text (area under the receiver operating characteristic curve at Beth Israel Deaconess Medical Center: 0.72) to the term frequency-inverse document frequency model (area under the receiver operating characteristic curve at Beth Israel Deaconess Medical Center: 0.83).

CONCLUSIONS:

Differences in preprocessing strategies for note text impacted model discrimination. Completing a preprocessing pathway including cleaning, stemming, and term frequency-inverse document frequency vectorization resulted in the preprocessing strategy with the greatest improvement in model performance. Further study is needed, with particular emphasis on how to manage author implicit bias present in note text, before natural language processing algorithms are implemented in the clinical setting.

Leveraging Genetic Reports and Electronic Health Records for the Prediction of Primary Cancers: Algorithm Development and Validation Study

BACKGROUND

Precision oncology has the potential to leverage clinical and genomic data in advancing disease prevention, diagnosis, and treatment. A key research area focuses on the early detection of primary cancers and potential prediction of cancers of unknown primary in order to facilitate optimal treatment decisions.

OBJECTIVE

This study presents a methodology to harmonize phenotypic and genetic data features to classify primary cancer types and predict cancers of unknown primaries.

METHODS

We extracted genetic data elements from oncology genetic reports of 1011 patients with cancer and their corresponding phenotypical data from Mayo Clinic's electronic health records. We modeled both genetic and electronic health record data with HL7 Fast Healthcare Interoperability Resources. The semantic web Resource Description Framework was employed to generate the network-based data representation (ie, patient-phenotypic-genetic network). Based on the Resource Description Framework data graph, Node2vec graph-embedding algorithm was applied to generate features. Multiple machine learning and deep learning backbone models were compared for cancer prediction performance.

RESULTS

With 6 machine learning tasks designed in the experiment, we demonstrated the proposed method achieved favorable results in classifying primary cancer types (area under the receiver operating characteristic curve [AUROC] 96.56% for all 9 cancer predictions on average based on the cross-validation) and predicting unknown primaries (AUROC 80.77% for all 8 cancer predictions on average for real-patient validation). To demonstrate the interpretability, 17 phenotypic and genetic features that contributed the most to the prediction of each cancer were identified and validated based on a literature review.

CONCLUSIONS

Accurate prediction of cancer types can be achieved with existing electronic health record data with satisfactory precision. The integration of genetic reports improves prediction, illustrating the translational values of incorporating genetic tests early at the diagnosis stage for patients with cancer.

Usability of a Digital Registry to Promote Secondary Prevention for Peripheral Artery Disease Patients

Objective

To evaluate usability of a quality improvement tool that promotes guideline-based care for patients with peripheral arterial disease (PAD).

Patients and Methods

The study was conducted from July 19, 2018, to August 21, 2019. We compared the usability of a PAD cohort knowledge solution (CKS) with standard management supported by an electronic health record (EHR). Two scenarios were developed for usability evaluation; the first for the PAD-CKS while the second evaluated standard EHR workflow. Providers were asked to provide opinions about the PAD-CKS tool and to generate a System Usability Scale (SUS) score. Metrics analyzed included time required, number of mouse clicks, and number of keystrokes.

Results

Usability evaluations were completed by 11 providers. SUS for the PAD-CKS was excellent at 89.6. Time required to complete 21 tasks in the CKS was 4 minutes compared with 12 minutes for standard EHR workflow (median, P = .002). Completion of CKS tasks required 34 clicks compared with 148 clicks for the EHR (median, P = .002). Keystrokes for CKS task completion was 8 compared with 72 for EHR (median, P = .004). Providers indicated that overall they found the tool easy to use and the PAD mortality risk score useful.

Conclusions

Usability evaluation of the PAD-CKS tool demonstrated time savings, a high SUS score, and a reduction of mouse clicks and keystrokes for task completion compared to standard workflow using the EHR. Provider feedback regarding the strengths and weaknesses also created opportunities for iterative improvement of the PAD-CKS tool.

Development and application of a high throughput natural language processing architecture to convert all clinical documents in a clinical data warehouse into standardized medical vocabularies

OBJECTIVE

Natural language processing (NLP) engines such as the clinical Text Analysis and Knowledge Extraction System are a solution for processing notes for research, but optimizing their performance for a clinical data warehouse remains a challenge. We aim to develop a high throughput NLP architecture using the clinical Text Analysis and Knowledge Extraction System and present a predictive model use case.

MATERIALS AND METHODS

The CDW was comprised of 1 103 038 patients across 10 years. The architecture was constructed using the Hadoop data repository for source data and 3 large-scale symmetric processing servers for NLP. Each named entity mention in a clinical document was mapped to the Unified Medical Language System concept unique identifier (CUI).

RESULTS

The NLP architecture processed 83 867 802 clinical documents in 13.33 days and produced 37 721 886 606 CUIs across 8 standardized medical vocabularies. Performance of the architecture exceeded 500 000 documents per hour across 30 parallel instances of the clinical Text Analysis and Knowledge Extraction System including 10 instances dedicated to documents greater than 20 000 bytes. In a use-case example for predicting 30-day hospital readmission, a CUI-based model had similar discrimination to n-grams with an area under the curve receiver operating characteristic of 0.75 (95% CI, 0.74-0.76).

DISCUSSION AND CONCLUSION

Our health system's high throughput NLP architecture may serve as a benchmark for large-scale clinical research using a CUI-based approach.

Generating real-world evidence from unstructured clinical notes to examine clinical utility of genetic tests: use case in BRCAness

Background

Next-generation sequencing provides comprehensive information about individuals’ genetic makeup and is commonplace in oncology clinical practice. However, the utility of genetic information in the clinical decision-making process has not been examined extensively from a real-world, data-driven perspective. Through mining real-world data (RWD) from clinical notes, we could extract patients’ genetic information and further associate treatment decisions with genetic information.

Methods

We proposed a real-world evidence (RWE) study framework that incorporates context-based natural language processing (NLP) methods and data quality examination before final association analysis. The framework was demonstrated in a Foundation-tested women cancer cohort (N = 196). Upon retrieval of patients’ genetic information using NLP system, we assessed the completeness of genetic data captured in unstructured clinical notes according to a genetic data-model. We examined the distribution of different topics regarding BRCA1/2 throughout patients’ treatment process, and then analyzed the association between BRCA1/2 mutation status and the discussion/prescription of targeted therapy.

Results

We identified seven topics in the clinical context of genetic mentions including: Information, Evaluation, Insurance, Order, Negative, Positive, and Variants of unknown significance. Our rule-based system achieved a precision of 0.87, recall of 0.93 and F-measure of 0.91. Our machine learning system achieved a precision of 0.901, recall of 0.899 and F-measure of 0.9 for four-topic classification and a precision of 0.833, recall of 0.823 and F-measure of 0.82 for seven-topic classification. We found in result-containing sentences, the capture of BRCA1/2 mutation information was 75%, but detailed variant information (e.g. variant types) is largely missing. Using cleaned RWD, significant associations were found between BRCA1/2 positive mutation and targeted therapies.

Conclusions

In conclusion, we demonstrated a framework to generate RWE using RWD from different clinical sources. Rule-based NLP system achieved the best performance for resolving contextual variability when extracting RWD from unstructured clinical notes. Data quality issues such as incompleteness and discrepancies exist thus manual data cleaning is needed before further analysis can be performed. Finally, we were able to use cleaned RWD to evaluate the real-world utility of genetic information to initiate a prescription of targeted therapy.

Developing an FHIR-Based Computational Pipeline for Automatic Population of Case Report Forms for Colorectal Cancer Clinical Trials Using Electronic Health Records

PURPOSE

The Fast Healthcare Interoperability Resources (FHIR) is emerging as a next-generation standards framework developed by HL7 for exchanging electronic health care data. The modeling capability of FHIR in standardizing cancer data has been gaining increasing attention by the cancer research informatics community. However, few studies have been conducted to examine the capability of FHIR in electronic data capture (EDC) applications for effective cancer clinical trials. The objective of this study was to design, develop, and evaluate an FHIR-based method that enables the automation of the case report forms (CRFs) population for cancer clinical trials using real-world electronic health records (EHRs).

MATERIALS AND METHODS

We developed an FHIR-based computational pipeline of EDC with a case study for modeling colorectal cancer trials. We first leveraged an existing FHIR-based cancer profile to represent EHR data of patients with colorectal cancer, and then we used the FHIR Questionnaire and QuestionnaireResponse resources to represent the CRFs and their data population. To test the accuracy of and overall quality of the computational pipeline, we used synoptic reports of 287 Mayo Clinic patients with colorectal cancer from 2013 to 2019 with standard measures of precision, recall, and F1 score.

RESULTS

Using the computational pipeline, a total of 1,037 synoptic reports were successfully converted as the instances of the FHIR-based cancer profile. The average accuracy for converting all data elements (excluding tumor perforation) of the cancer profile was 0.99, using 200 randomly selected records. The average F1 score for populating nine questions of the CRFs in a real-world colorectal cancer trial was 0.95, using 100 randomly selected records.

CONCLUSION

We demonstrated that it is feasible to populate CRFs with EHR data in an automated manner with satisfactory performance. The outcome of the study provides helpful insight into future directions in implementing FHIR-based EDC applications for modern cancer clinical trials.

Phenotyping severity of patient-centered outcomes using clinical notes: A prostate cancer use case

Introduction

A learning health system (LHS) must improve care in ways that are meaningful to patients, integrating patient‐centered outcomes (PCOs) into core infrastructure. PCOs are common following cancer treatment, such as urinary incontinence (UI) following prostatectomy. However, PCOs are not systematically recorded because they can only be described by the patient, are subjective and captured as unstructured text in the electronic health record (EHR). Therefore, PCOs pose significant challenges for phenotyping patients. Here, we present a natural language processing (NLP) approach for phenotyping patients with UI to classify their disease into severity subtypes, which can increase opportunities to provide precision‐based therapy and promote a value‐based delivery system.

Methods

Patients undergoing prostate cancer treatment from 2008 to 2018 were identified at an academic medical center. Using a hybrid NLP pipeline that combines rule‐based and deep learning methodologies, we classified positive UI cases as mild, moderate, and severe by mining clinical notes.

Results

The rule‐based model accurately classified UI into disease severity categories (accuracy: 0.86), which outperformed the deep learning model (accuracy: 0.73). In the deep learning model, the recall rates for mild and moderate group were higher than the precision rate (0.78 and 0.79, respectively). A hybrid model that combined both methods did not improve the accuracy of the rule‐based model but did outperform the deep learning model (accuracy: 0.75).

Conclusion

Phenotyping patients based on indication and severity of PCOs is essential to advance a patient centered LHS. EHRs contain valuable information on PCOs and by using NLP methods, it is feasible to accurately and efficiently phenotype PCO severity. Phenotyping must extend beyond the identification of disease to provide classification of disease severity that can be used to guide treatment and inform shared decision‐making. Our methods demonstrate a path to a patient centered LHS that could advance precision medicine.

Modeling cancer clinical trials using HL7 FHIR to support downstream applications: A case study with colorectal cancer data

BACKGROUND AND OBJECTIVE

Identification and Standardization of data elements used in clinical trials may control and reduce the cost and errors during the operational process, and enable seamless data exchange between the electronic data capture (EDC) systems and Electronic Health Record (EHR) systems. This study presents a methodology to comprehensively capture the clinical trial data element needs.

MATERIALS AND METHODS

Case report forms (CRF) for clinical trial data collection were used to approximate the clinical information need, whereby these information needs were then mapped to a semantically equivalent field within an existing FHIR cancer profile. For items without a semantically equivalent field, we considered these items to be information needs that cannot be represented in current standards and proposed extensions to support these needs.

RESULTS

We successfully identified 62 discrete items from a preliminary survey of 43 base questions in four CRFs used in colorectal cancer clinical trials, in which 28 items are modeled with FHIR extensions and their associated responses for colorectal cancer. We achieved promising results in the data population of the CRFs with average Precision 98.5 %, Recall 96.2 %, and F-measure 96.8 % for all base questions. We also demonstrated the auto-filled answers in CRFs can be used to discover patient subgroups using a topic modeling approach.

CONCLUSION

CRFs can be considered as a proxy for representing information needs for their respective cancer types. Mining the information needs can serve as a valuable resource for expanding existing standards to ensure they can comprehensively represent relevant clinical data without loss of granularity.

Pragmatic cluster randomized trial to evaluate effectiveness and implementation of enhanced EHR-facilitated cancer symptom control (E2C2)

Background

The prevalence of inadequate symptom control among cancer patients is quite high despite the availability of definitive care guidelines and accurate and efficient assessment tools.

Methods

We will conduct a hybrid type 2 stepped wedge pragmatic cluster randomized clinical trial to evaluate a guideline-informed enhanced, electronic health record (EHR)-facilitated cancer symptom control (E2C2) care model. Teams of clinicians at five hospitals that care for patients with various cancers will be randomly assigned in steps to the E2C2 intervention. The E2C2 intervention will have two levels of care: level 1 will offer low-touch, automated self-management support for patients reporting moderate sleep disturbance, pain, anxiety, depression, and energy deficit symptoms or limitations in physical function (or both). Level 2 will offer nurse-managed collaborative care for patients reporting more intense (severe) symptoms or functional limitations (or both). By surveying and interviewing clinical staff, we will also evaluate whether the use of a multifaceted, evidence-based implementation strategy to support adoption and use of the E2C2 technologies improves patient and clinical outcomes. Finally, we will conduct a mixed methods evaluation to identify disparities in the adoption and implementation of the E2C2 intervention among elderly and rural-dwelling patients with cancer.

Discussion

The E2C2 intervention offers a pragmatic, scalable approach to delivering guideline-based symptom and function management for cancer patients. Since discrete EHR-imbedded algorithms drive defining aspects of the intervention, the approach can be efficiently disseminated and updated by specifying and modifying these centralized EHR algorithms.

Trial registration

ClinicalTrials.gov, NCT03892967. Registered on 25 March 2019.

Developing a FHIR-based Framework for Phenome Wide Association Studies: A Case Study with A Pan-Cancer Cohort

Phenome Wide Association Studies (PheWAS) enables phenome-wide scans to discover novel associations between genotype and clinical phenotypes via linking available genomic reports and large-scale Electronic Health Record (EHR). Data heterogeneity from different EHR systems and genetic reports has been a critical challenge that hinders meaningful validation. To address this, we propose an FHIR-based framework to model the PheWAS study in a standard manner. We developed an FHIR-based data model profile to enable the standard representation of data elements from genetic reports and EHR data that are used in the PheWAS study. As a proof-of-concept, we implemented the proposed method using a cohort of 1,595 pan-cancer patients with genetic reports from Foundation Medicine as well as the corresponding lab tests and diagnosis from Mayo EHRs. A PheWAS study is conducted and 81 significant genotype-phenotype associations are identified, in which 36 significant associations for cancers are validated based on a literature review.

Patient Preferences Regarding Informed Consent Models for Participation in a Learning Health Care System for Oncology

PURPOSE

The expansion of learning health care systems (LHSs) promises to bolster research and quality improvement endeavors. Stewards of patient data have a duty to respect the preferences of the patients from whom, and for whom, these data are being collected and consolidated.

METHODS

We conducted democratic deliberations with a diverse sample of 217 patients treated at 4 sites to assess views about LHSs, using the example of CancerLinQ, a real-world LHS, to stimulate discussion. In small group discussions, participants deliberated about different policies for how to provide information and to seek consent regarding the inclusion of patient data. These discussions were recorded, transcribed, and de-identified for thematic analysis.

RESULTS

Of participants, 67% were female, 61% were non-Hispanic Whites, and the mean age was 60 years. Patients' opinions about sharing their data illuminated 2 spectra: trust/distrust and individualism/collectivism. Positions on these spectra influenced the weight placed on 3 priorities: promoting societal altruism, ensuring respect for persons, and protecting themselves. In turn, consideration of these priorities seemed to inform preferences regarding patient choices and system transparency. Most advocated for a policy whereby patients would receive notification and have the opportunity to opt out of including their medical records in the LHS. Participants reasoned that such a policy would balance personal protections and societal welfare.

CONCLUSION

System transparency and patient choice are vital if patients are to feel respected and to trust LHS endeavors. Those responsible for LHS implementation should ensure that all patients receive an explanation of their options, together with standardized, understandable, comprehensive materials.

Assessment of the impact of EHR heterogeneity for clinical research through a case study of silent brain infarction

Background

The rapid adoption of electronic health records (EHRs) holds great promise for advancing medicine through practice-based knowledge discovery. However, the validity of EHR-based clinical research is questionable due to poor research reproducibility caused by the heterogeneity and complexity of healthcare institutions and EHR systems, the cross-disciplinary nature of the research team, and the lack of standard processes and best practices for conducting EHR-based clinical research.

Method

We developed a data abstraction framework to standardize the process for multi-site EHR-based clinical studies aiming to enhance research reproducibility. The framework was implemented for a multi-site EHR-based research project, the ESPRESSO project, with the goal to identify individuals with silent brain infarctions (SBI) at Tufts Medical Center (TMC) and Mayo Clinic. The heterogeneity of healthcare institutions, EHR systems, documentation, and process variation in case identification was assessed quantitatively and qualitatively.

Result

We discovered a significant variation in the patient populations, neuroimaging reporting, EHR systems, and abstraction processes across the two sites. The prevalence of SBI for patients over age 50 for TMC and Mayo is 7.4 and 12.5% respectively. There is a variation regarding neuroimaging reporting where TMC are lengthy, standardized and descriptive while Mayo’s reports are short and definitive with more textual variations. Furthermore, differences in the EHR system, technology infrastructure, and data collection process were identified.

Conclusion

The implementation of the framework identified the institutional and process variations and the heterogeneity of EHRs across the sites participating in the case study. The experiment demonstrates the necessity to have a standardized process for data abstraction when conducting EHR-based clinical studies.

Desiderata for delivering NLP to accelerate healthcare AI advancement and a Mayo Clinic NLP-as-a-service implementation

Data is foundational to high-quality artificial intelligence (AI). Given that a substantial amount of clinically relevant information is embedded in unstructured data, natural language processing (NLP) plays an essential role in extracting valuable information that can benefit decision making, administration reporting, and research. Here, we share several desiderata pertaining to development and usage of NLP systems, derived from two decades of experience implementing clinical NLP at the Mayo Clinic, to inform the healthcare AI community. Using a framework, we developed as an example implementation, the desiderata emphasize the importance of a user-friendly platform, efficient collection of domain expert inputs, seamless integration with clinical data, and a highly scalable computing infrastructure.

Automated extraction of sudden cardiac death risk factors in hypertrophic cardiomyopathy patients by natural language processing

BACKGROUND

The management of hypertrophic cardiomyopathy (HCM) patients requires the knowledge of risk factors associated with sudden cardiac death (SCD). SCD risk factors such as syncope and family history of SCD (FH-SCD) as well as family history of HCM (FH-HCM) are documented in electronic health records (EHRs) as clinical narratives. Automated extraction of risk factors from clinical narratives by natural language processing (NLP) may expedite management workflow of HCM patients. The aim of this study was to develop and deploy NLP algorithms for automated extraction of syncope, FH-SCD, and FH-HCM from clinical narratives.

METHODS AND RESULTS

We randomly selected 200 patients from the Mayo HCM registry for development (n = 100) and testing (n = 100) of NLP algorithms for extraction of syncope, FH-SCD as well as FH-HCM from clinical narratives of EHRs. The clinical reference standard was manually abstracted by 2 independent annotators. Performance of NLP algorithms was compared to aggregation and summarization of data entries in the HCM registry for syncope, FH-SCD, and FH-HCM. We also compared the NLP algorithms with billing codes for syncope as well as responses to patient survey questions for FH-SCD and FH-HCM. These analyses demonstrated NLP had superior sensitivity (0.96 vs 0.39, p < 0.001) and comparable specificity (0.90 vs 0.92, p = 0.74) and PPV (0.90 vs 0.83, p = 0.37) compared to billing codes for syncope. For FH-SCD, NLP outperformed survey responses for all parameters (sensitivity: 0.91 vs 0.59, p = 0.002; specificity: 0.98 vs 0.50, p < 0.001; PPV: 0.97 vs 0.38, p < 0.001). NLP also achieved superior sensitivity (0.95 vs 0.24, p < 0.001) with comparable specificity (0.95 vs 1.0, p-value not calculable) and positive predictive value (PPV) (0.92 vs 1.0, p = 0.09) compared to survey responses for FH-HCM.

CONCLUSIONS

Automated extraction of syncope, FH-SCD and FH-HCM using NLP is feasible and has promise to increase efficiency of workflow for providers managing HCM patients.

Using Electronic Health Records To Generate Phenotypes For Research

Electronic health records contain patient-level data collected during and for clinical care. Data within the electronic health record include diagnostic billing codes, procedure codes, vital signs, laboratory test results, clinical imaging, and physician notes. With repeated clinic visits, these data are longitudinal, providing important information on disease development, progression, and response to treatment or intervention strategies. The near universal adoption of electronic health records nationally has the potential to provide population-scale real-world clinical data accessible for biomedical research, including genetic association studies. For this research potential to be realized, high-quality research-grade variables must be extracted from these clinical data warehouses. We describe here common and emerging electronic phenotyping approaches applied to electronic health records, as well as current limitations of both the approaches and the biases associated with these clinically collected data that impact their use in research. © 2018 by John Wiley & Sons, Inc.

Association of Ankle-Brachial Indices With Limb Revascularization or Amputation in Patients With Peripheral Artery Disease

IMPORTANCE

The prevalence and morbidity of peripheral artery disease (PAD) are high, with limb outcomes including revascularization and amputation. In community-dwelling patients with PAD, the role of noninvasive evaluation for risk assessment and rates of limb outcomes have not been established to date.

OBJECTIVE

To evaluate whether ankle-brachial indices are associated with limb outcomes in community-dwelling patients with PAD.

DESIGN, SETTING, AND PARTICIPANTS

A population-based, observational, test-based cohort study of patients was performed from January 1, 1998, to December 31, 2014. Data analysis was conducted from July 15 to December 15, 2017. Participants included a community-based cohort of 1413 patients with PAD from Olmsted County, Minnesota, identified by validated algorithms deployed to electronic health records. Automated algorithms identified limb outcomes used to build Cox proportional hazards regression models. Ankle-brachial indices and presence of poorly compressible arteries were electronically identified from digital data sets. Guideline-recommended management strategies within 6 months of diagnosis were also electronically retrieved, including therapy with statins, antiplatelet agents, angiotensin-converting enzyme inhibitors or angiotensin-receptor blockers, and smoking abstention.

MAIN OUTCOMES AND MEASURES

Ankle-brachial index (index ≤0.9 indicates PAD; <.05, severe PAD; and ≥1.40, poorly compressible arteries) and limb revascularization or amputation.

RESULTS

Of 1413 patients, 633 (44.8%) were women; mean (SD) age was 70.8 (13.3) years. A total of 283 patients (20.0%) had severe PAD (ankle-brachial indices <0.5) and 350 (24.8%) had poorly compressible arteries (ankle-brachial indices ≥1.4); 780 (55.2%) individuals with less than severe disease formed the reference group. Only 32 of 283 patients (11.3%) with severe disease and 68 of 350 patients (19.4%) with poorly compressible arteries were receiving 4 guideline-recommended management strategies. In the severe disease subgroup, the 1-year event rate for revascularization was 32.4% (90 events); in individuals with poorly compressible arteries, the 1-year amputation rate was 13.9% (47 events). In models adjusted for age, sex, and critical limb ischemia, poorly compressible arteries were associated with amputation (hazard ratio [HR], 3.12; 95% CI, 2.16-4.50; P < .001) but not revascularization (HR, 0.91; 95% CI, 0.69-1.20; P = .49). In contrast, severe disease was associated with revascularization (HR, 2.69; 95% CI, 2.15-3.37; P < .001) but not amputation (HR, 1.30; 95% CI, 0.82-2.07; P = .27).

CONCLUSIONS AND RELEVANCE

Community-dwelling patients with severe PAD or poorly compressible arteries have high rates of revascularization or limb loss, respectively. Guideline-recommended management strategies for secondary risk prevention are underused in the community.

Leveraging the Electronic Health Record to Create an Automated Real-Time Prognostic Tool for Peripheral Arterial Disease

Background Automated individualized risk prediction tools linked to electronic health records ( EHR s) are not available for management of patients with peripheral arterial disease. The goal of this study was to create a prognostic tool for patients with peripheral arterial disease using data elements automatically extracted from an EHR to enable real-time and individualized risk prediction at the point of care. Methods and Results A previously validated phenotyping algorithm was deployed to an EHR linked to the Rochester Epidemiology Project to identify peripheral arterial disease cases from Olmsted County, MN, for the years 1998 to 2011. The study cohort was composed of 1676 patients: 593 patients died over 5-year follow-up. The c-statistic for survival in the overall data set was 0.76 (95% confidence interval [CI], 0.74-0.78), and the c-statistic across 10 cross-validation data sets was 0.75 (95% CI, 0.73-0.77). Stratification of cases demonstrated increasing mortality risk by subgroup (low: hazard ratio, 0.35 [95% CI, 0.21-0.58]; intermediate-high: hazard ratio, 2.98 [95% CI, 2.37-3.74]; high: hazard ratio, 8.44 [95% CI, 6.66-10.70], all P<0.0001 versus the reference subgroup). An equation for risk calculation was derived from Cox model parameters and β estimates. Big data infrastructure enabled deployment of the real-time risk calculator to the point of care via the EHR . Conclusions This study demonstrates that electronic tools can be deployed to EHR s to create automated real-time risk calculators to predict survival of patients with peripheral arterial disease. Moreover, the prognostic model developed may be translated to patient care as an automated and individualized real-time risk calculator deployed at the point of care.

The role of telemedicine in postoperative care

Telemedicine has become one of the most rapidly-expanding components of the health care system. Its adoption has afforded improved access to care, greater resource efficiency, and decreased costs associated with traditional office visits and has been well established in a wide array of fields. Telemedicine has been adopted in several domains of surgical care. In recent years, the role of telemedicine in postoperative care has caught attention as it has demonstrated excellent clinical outcomes, enhanced patient satisfaction, increased accessibility along with reduced wait times, and cost savings for patients and health care systems. In this narrative review, we describe the history of telemedicine, its adoption in the field of surgery and its various modalities, its use in the postoperative setting, and the potential benefits to both patients and healthcare systems. As telemedicine continues to emerge as a powerful tool for health care delivery, we also discuss several barriers to its widespread adoption as well as the future utility of telemedicine in postoperative care.

Digital maturity: are we ready to use technology in the NHS?

Digital maturity assessments (DMAs) are a self-assessment mechanism for organisations. They can be effectively utilised to generate local digital roadmaps. In their simplest form, these allow organisations to understand their state of readiness to integrate digital technologies. This is achieved by assessing the capability and compatibility of their information systems to communicate or interface both within and across organisations. Through utilising and responding to the findings of DMAs, it is thought that the NHS will be better able to provide a patient-centred service to meet local needs within a national framework. It is this exchange and integration of information across health and social care systems that will drive innovation and transformation in the NHS.

Making Sense of Big Textual Data for Health Care: Findings from the Section on Clinical Natural Language Processing

Objectives: To summarize recent research and present a selection of the best papers published in 2016 in the field of clinical Natural Language Processing (NLP). Method: A survey of the literature was performed by the two section editors of the IMIA Yearbook NLP section. Bibliographic databases were searched for papers with a focus on NLP efforts applied to clinical texts or aimed at a clinical outcome. Papers were automatically ranked and then manually reviewed based on titles and abstracts. A shortlist of candidate best papers was first selected by the section editors before being peer-reviewed by independent external reviewers. Results: The five clinical NLP best papers provide a contribution that ranges from emerging original foundational methods to transitioning solid established research results to a practical clinical setting. They offer a framework for abbreviation disambiguation and coreference resolution, a classification method to identify clinically useful sentences, an analysis of counseling conversations to improve support to patients with mental disorder and grounding of gradable adjectives. Conclusions: Clinical NLP continued to thrive in 2016, with an increasing number of contributions towards applications compared to fundamental methods. Fundamental work addresses increasingly complex problems such as lexical semantics, coreference resolution, and discourse analysis. Research results translate into freely available tools, mainly for English.