Electronic health records: new opportunities for clinical research

CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks

Electronic Health Records (EHRs) play a crucial role in shaping predictive are models, yet they encounter challenges such as significant data gaps and class imbalances. Traditional Graph Neural Network (GNN) approaches have limitations in fully leveraging neighbourhood data or demanding intensive computational requirements for regularisation. To address this challenge, we introduce CliqueFluxNet, a novel framework that innovatively constructs a patient similarity graph to maximise cliques, thereby highlighting strong inter-patient connections. At the heart of CliqueFluxNet lies its stochastic edge fluxing strategy - a dynamic process involving random edge addition and removal during training. This strategy aims to enhance the model's generalisability and mitigate overfitting. Our empirical analysis, conducted on MIMIC-III and eICU datasets, focuses on the tasks of mortality and readmission prediction. It demonstrates significant progress in representation learning, particularly in scenarios with limited data availability. Qualitative assessments further underscore CliqueFluxNet's effectiveness in extracting meaningful EHR representations, solidifying its potential for advancing GNN applications in healthcare analytics.

Impact of electronic medical records on healthcare delivery in Nigeria: A review

Electronic medical records (EMRs) have great potential to improve healthcare processes and outcomes. They are increasingly available in Nigeria, as in many developing countries. The impact of their introduction has not been well studied. We sought to synthesize the evidence from primary studies of the effect of EMRs on data quality, patient-relevant outcomes and patient satisfaction. We identified and examined five original research articles published up to May 2023 in the following medical literature databases: PUBMED/Medline, EMBASE, Web of Science, African Journals Online and Google Scholar. Four studies examined the influence of the introduction of or improvements in the EMR on data collection and documentation. The pooled percentage difference in data quality after introducing or improving the EMR was 142% (95% CI: 82% to 203%, p-value < 0.001). There was limited heterogeneity in the estimates (I2 = 0%, p-heterogeneity = 0.93) and no evidence suggestive of publication bias. The 5th study assessed patient satisfaction with pharmacy services following the introduction of the EMR but neither had a comparison group nor assessed patient satisfaction before EMR was introduced. We conclude that the introduction of EMR in Nigerian healthcare facilities meaningfully increased the quality of the data.

UK Electronic Healthcare Records for Research: A Scientometric Analysis of Respiratory, Cardiovascular, and COVID-19 Publications

Background

Routinely collected electronic healthcare records (EHRs) document many details of a person's health, including demographics, preventive services, symptoms, tests, disease diagnoses and prescriptions. Although not collected for research purposes, these data provide a wealth of information which can be incorporated into epidemiological investigations, and records can be analysed to understand a range of important health questions. We aimed to understand the use of routinely collected health data in epidemiological studies relating to three of the most common chronic respiratory conditions, namely: asthma, chronic obstructive pulmonary disease (COPD) and interstitial lung disease (ILD). We also characterised studies using EHR data to investigate respiratory diseases more generally, relative to cardiovascular disease and COVID-19, to understand trends in the use of these data.

Methods

We conducted a search of the Scopus database, to identify original research articles (irrespective of date) which used data from one of the following most frequently used UK EHR databases: Clinical Practice Research Datalink (including General Practice Research Database (CPRD's predecessor)), The Health Improvement Network and QResearch, defined through the presence of keywords. These databases were selected as they had been previously included in the works of Vezyridis and Timmons.

Findings

A total of 716 manuscripts were included in the analysis of the three chronic respiratory conditions. The majority investigated either asthma or COPD, whilst only 28 manuscripts investigated ILD. The number of publications has increased for respiratory conditions over the past 10 years (888% increase from 2000 to 2022) but not as much as for cardiovascular diseases (1105%). These data have been used to investigate comorbidities, off-target effects of medication, as well as assessing disease incidence and prevalence. Most papers published across all three domains were in journals with an impact factor less than 10.

Transforming Primary Care Data Into the Observational Medical Outcomes Partnership Common Data Model: Development and Usability Study

Background

Patient-monitoring software generates a large amount of data that can be reused for clinical audits and scientific research. The Observational Health Data Sciences and Informatics (OHDSI) consortium developed the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) to standardize electronic health record data and promote large-scale observational and longitudinal research.

Objective

This study aimed to transform primary care data into the OMOP CDM format.

Methods

We extracted primary care data from electronic health records at a multidisciplinary health center in Wattrelos, France. We performed structural mapping between the design of our local primary care database and the OMOP CDM tables and fields. Local French vocabularies concepts were mapped to OHDSI standard vocabularies. To validate the implementation of primary care data into the OMOP CDM format, we applied a set of queries. A practical application was achieved through the development of a dashboard.

Results

Data from 18,395 patients were implemented into the OMOP CDM, corresponding to 592,226 consultations over a period of 20 years. A total of 18 OMOP CDM tables were implemented. A total of 17 local vocabularies were identified as being related to primary care and corresponded to patient characteristics (sex, location, year of birth, and race), units of measurement, biometric measures, laboratory test results, medical histories, and drug prescriptions. During semantic mapping, 10,221 primary care concepts were mapped to standard OHDSI concepts. Five queries were used to validate the OMOP CDM by comparing the results obtained after the completion of the transformations with the results obtained in the source software. Lastly, a prototype dashboard was developed to visualize the activity of the health center, the laboratory test results, and the drug prescription data.

Conclusions

Primary care data from a French health care facility have been implemented into the OMOP CDM format. Data concerning demographics, units, measurements, and primary care consultation steps were already available in OHDSI vocabularies. Laboratory test results and drug prescription data were mapped to available vocabularies and structured in the final model. A dashboard application provided health care professionals with feedback on their practice.

Integrating clinical research into electronic health record workflows to support a learning health system

Objective

Integrating clinical research into routine clinical care workflows within electronic health record systems (EHRs) can be challenging, expensive, and labor-intensive. This case study presents a large-scale clinical research project conducted entirely within a commercial EHR during the COVID-19 pandemic.

Case Report

The UCSD and UCSDH COVID-19 NeutraliZing Antibody Project (ZAP) aimed to evaluate antibody levels to SARS-CoV-2 virus in a large population at an academic medical center and examine the association between antibody levels and subsequent infection diagnosis.

Results

The project rapidly and successfully enrolled and consented over 2000 participants, integrating the research trial with standing COVID-19 testing operations, staff, lab, and mobile applications. EHR-integration increased enrollment, ease of scheduling, survey distribution, and return of research results at a low cost by utilizing existing resources.

Conclusion

The case study highlights the potential benefits of EHR-integrated clinical research, expanding their reach across multiple health systems and facilitating rapid learning during a global health crisis.

The Role of Robotics in Meeting Institutional Goals: A Unified Strategy to Facilitate Program Excellence

PURPOSE

The rapid expansion of robotic surgical equipment necessitates a review of the needs and challenges faced by hospitals introducing robots for the first time to compete with experienced institutions. The aim of this study was to analyze the impact of robotic surgery on our hospital compared to open and laparoscopic surgery, examine internal transformations, and assess regional, domestic, and international implications.

METHODS

A retrospective review was conducted of electronic medical records (EMRs) from 2019 to 2022 at Inha University Hospital, including patients who underwent common robotic procedures and equivalent open and laparoscopic operations. The study investigated clinical and operational performance changes in the hospital after the introduction of robotic technology. It also evaluated the operational effectiveness of robot implementation in local, national, and international contexts. To facilitate comparison with other hospitals, the data were transmitted to Intuitive Surgical, Inc. for analysis. The study was conducted in compliance with domestic personal information regulations and received approval from our Institutional Review Board.

RESULTS

We analyzed EMR data from 3,147 patients who underwent surgical treatment. Over a period of 3.5 years, the adoption of robotic technology in a hospital setting significantly enhanced the technical skills of all professors involved. The introduction of robotic systems led to increased patient utilization of conventional surgical techniques, as well as a rise in the number of patients choosing robotic surgery. This collective trend contributed to an overall increase in patient numbers. This favorable evaluation of the operational effectiveness of our hospital's robot implementation in the context of local, national, and global factors is expected to positively influence policy changes.

CONCLUSION

Stakeholders should embrace data science and evidence-based techniques to generate valuable insights from objective data, assess the health of robot-assisted surgery programs, and identify opportunities for improvement and excellence.

OHDSI-compliance: a set of document templates facilitating the implementation and operation of a software stack for real-world evidence generation

Introduction

The open-source software offered by the Observational Health Data Science and Informatics (OHDSI) collective, including the OMOP-CDM, serves as a major backbone for many real-world evidence networks and distributed health data analytics platforms. While container technology has significantly simplified deployments from a technical perspective, regulatory compliance can remain a major hurdle for the setup and operation of such platforms. In this paper, we present OHDSI-Compliance, a comprehensive set of document templates designed to streamline the data protection and information security-related documentation and coordination efforts required to establish OHDSI installations.

Methods

To decide on a set of relevant document templates, we first analyzed the legal requirements and associated guidelines with a focus on the General Data Protection Regulation (GDPR). Moreover, we analyzed the software architecture of a typical OHDSI stack and related its components to the different general types of concepts and documentation identified. Then, we created those documents for a prototypical OHDSI installation, based on the so-called Broadsea package, following relevant guidelines from Germany. Finally, we generalized the documents by introducing placeholders and options at places where individual institution-specific content will be needed.

Results

We present four documents: (1) a record of processing activities, (2) an information security concept, (3) an authorization concept, as well as (4) an operational concept covering the technical details of maintaining the stack. The documents are publicly available under a permissive license.

Discussion

To the best of our knowledge, there are no other publicly available sets of documents designed to simplify the compliance process for OHDSI deployments. While our documents provide a comprehensive starting point, local specifics need to be added, and, due to the heterogeneity of legal requirements in different countries, further adoptions might be necessary.

Effect of perioperative ketorolac on postoperative bleeding after pediatric tonsillectomy

INTRODUCTION

Ketorolac is a frequently used anesthetic pain agent which is traditionally avoided during tonsillectomy due to concern for postoperative hemorrhage. Our goal was to assess the degree of risk associated with the use of Ketorolac following pediatric tonsillectomy.

METHODS

The TriNetX electronic health records research database was queried in January 2024 for patients undergoing tonsillectomy with or without adenoidectomy under the age of 18 years and without a diagnosed bleeding disorder. Patients were separated into two cohorts either having received or not having received ketorolac the same day as surgery. Propensity score matching was performed for age at the time of surgery, sex, race, ethnicity, and preoperative diagnoses. The outcomes assessed were postoperative hemorrhage requiring operative control within the first day (primary hemorrhage) and within the first month after surgery (secondary hemorrhage).

RESULTS

17,434 patients were identified who had undergone pediatric tonsillectomy with or without adenoidectomy and had received ketorolac the same day as surgery. 290,373 patients were identified who had undergone pediatric tonsillectomy with or without adenoidectomy and had not received ketorolac the same day as surgery. 1:1 propensity score matching resulted in 17,434 patients within each cohort. Receipt of ketorolac the same day as surgery resulted in an increased risk of primary hemorrhage OR 2.158 (95 % CI 1.354, 3.437) and secondary hemorrhage OR 1.374 (95 % CI 1.057, 1.787) requiring operative control.

CONCLUSION

Ketorolac use during pediatric tonsillectomy with or without adenoidectomy was associated with an increased risk of postoperative primary and secondary bleeding requiring surgery.

Impact of Electronic Health Record Use on Cognitive Load and Burnout Among Clinicians: Narrative Review

The cognitive load theory suggests that completing a task relies on the interplay between sensory input, working memory, and long-term memory. Cognitive overload occurs when the working memory's limited capacity is exceeded due to excessive information processing. In health care, clinicians face increasing cognitive load as the complexity of patient care has risen, leading to potential burnout. Electronic health records (EHRs) have become a common feature in modern health care, offering improved access to data and the ability to provide better patient care. They have been added to the electronic ecosystem alongside emails and other resources, such as guidelines and literature searches. Concerns have arisen in recent years that despite many benefits, the use of EHRs may lead to cognitive overload, which can impact the performance and well-being of clinicians. We aimed to review the impact of EHR use on cognitive load and how it correlates with physician burnout. Additionally, we wanted to identify potential strategies recommended in the literature that could be implemented to decrease the cognitive burden associated with the use of EHRs, with the goal of reducing clinician burnout. Using a comprehensive literature review on the topic, we have explored the link between EHR use, cognitive load, and burnout among health care professionals. We have also noted key factors that can help reduce EHR-related cognitive load, which may help reduce clinician burnout. The research findings suggest that inadequate efforts to present large amounts of clinical data to users in a manner that allows the user to control the cognitive burden in the EHR and the complexity of the user interfaces, thus adding more "work" to tasks, can lead to cognitive overload and burnout; this calls for strategies to mitigate these effects. Several factors, such as the presentation of information in the EHR, the specialty, the health care setting, and the time spent completing documentation and navigating systems, can contribute to this excess cognitive load and result in burnout. Potential strategies to mitigate this might include improving user interfaces, streamlining information, and reducing documentation burden requirements for clinicians. New technologies may facilitate these strategies. The review highlights the importance of addressing cognitive overload as one of the unintended consequences of EHR adoption and potential strategies for mitigation, identifying gaps in the current literature that require further exploration.

Tracking persistent postoperative opioid use: a proof-of-concept study demonstrating a use case for natural language processing

BACKGROUND

Large language models have been gaining tremendous popularity since the introduction of ChatGPT in late 2022. Perioperative pain providers should leverage natural language processing (NLP) technology and explore pertinent use cases to improve patient care. One example is tracking persistent postoperative opioid use after surgery. Since much of the relevant data may be 'hidden' within unstructured clinical text, NLP models may prove to be advantageous. The primary objective of this proof-of-concept study was to demonstrate the ability of an NLP engine to review clinical notes and accurately identify patients who had persistent postoperative opioid use after major spine surgery.

METHODS

Clinical documents from all patients that underwent major spine surgery during July 2015-August 2021 were extracted from the electronic health record. The primary outcome was persistent postoperative opioid use, defined as continued use of opioids greater than or equal to 3 months after surgery. This outcome was ascertained via manual clinician review from outpatient spine surgery follow-up notes. An NLP engine was applied to these notes to ascertain the presence of persistent opioid use-this was then compared with results from clinician manual review.

RESULTS

The final study sample consisted of 965 patients, in which 705 (73.1%) were determined to have persistent opioid use following surgery. The NLP engine correctly determined the patients' opioid use status in 92.9% of cases, in which it correctly identified persistent opioid use in 95.6% of cases and no persistent opioid use in 86.1% of cases.

DISCUSSION

Access to unstructured data within the perioperative history can contextualize patients' opioid use and provide further insight into the opioid crisis, while at the same time improve care directly at the patient level. While these goals are in reach, future work is needed to evaluate how to best implement NLP within different healthcare systems for use in clinical decision support.

Best practices for multimodal clinical data management and integration: An atopic dermatitis research case

BACKGROUND

In clinical research on multifactorial diseases such as atopic dermatitis, data-driven medical research has become more widely used as means to clarify diverse pathological conditions and to realize precision medicine. However, modern clinical data, characterized as large-scale, multimodal, and multi-center, causes difficulties in data integration and management, which limits productivity in clinical data science.

METHODS

We designed a generic data management flow to collect, cleanse, and integrate data to handle different types of data generated at multiple institutions by 10 types of clinical studies. We developed MeDIA (Medical Data Integration Assistant), a software to browse the data in an integrated manner and extract subsets for analysis.

RESULTS

MeDIA integrates and visualizes data and information on research participants obtained from multiple studies. It then provides a sophisticated interface that supports data management and helps data scientists retrieve the data sets they need. Furthermore, the system promotes the use of unified terms such as identifiers or sampling dates to reduce the cost of pre-processing by data analysts. We also propose best practices in clinical data management flow, which we learned from the development and implementation of MeDIA.

CONCLUSIONS

The MeDIA system solves the problem of multimodal clinical data integration, from complex text data such as medical records to big data such as omics data from a large number of patients. The system and the proposed best practices can be applied not only to allergic diseases but also to other diseases to promote data-driven medical research.

Cross-institution natural language processing for reliable clinical association studies: a methodological exploration

OBJECTIVES

Natural language processing (NLP) of clinical notes in electronic medical records is increasingly used to extract otherwise sparsely available patient characteristics, to assess their association with relevant health outcomes. Manual data curation is resource intensive and NLP methods make these studies more feasible. However, the methodology of using NLP methods reliably in clinical research is understudied. The objective of this study is to investigate how NLP models could be used to extract study variables (specifically exposures) to reliably conduct exposure-outcome association studies.

STUDY DESIGN AND SETTING

In a convenience sample of patients admitted to the intensive care unit of a US academic health system, multiple association studies are conducted, comparing the association estimates based on NLP-extracted vs. manually extracted exposure variables. The association studies varied in NLP model architecture (Bidirectional Encoder Decoder from Transformers, Long Short-Term Memory), training paradigm (training a new model, fine-tuning an existing external model), extracted exposures (employment status, living status, and substance use), health outcomes (having a do-not-resuscitate/intubate code, length of stay, and in-hospital mortality), missing data handling (multiple imputation vs. complete case analysis), and the application of measurement error correction (via regression calibration).

RESULTS

The study was conducted on 1,174 participants (median [interquartile range] age, 61 [50, 73] years; 60.6% male). Additionally, up to 500 discharge reports of participants from the same health system and 2,528 reports of participants from an external health system were used to train the NLP models. Substantial differences were found between the associations based on NLP-extracted and manually extracted exposures under all settings. The error in association was only weakly correlated with the overall F1 score of the NLP models.

CONCLUSION

Associations estimated using NLP-extracted exposures should be interpreted with caution. Further research is needed to set conditions for reliable use of NLP in medical association studies.

Automatic de-identification of French electronic health records: a cost-effective approach exploiting distant supervision and deep learning models

BACKGROUND

Electronic health records (EHRs) contain valuable information for clinical research; however, the sensitive nature of healthcare data presents security and confidentiality challenges. De-identification is therefore essential to protect personal data in EHRs and comply with government regulations. Named entity recognition (NER) methods have been proposed to remove personal identifiers, with deep learning-based models achieving better performance. However, manual annotation of training data is time-consuming and expensive. The aim of this study was to develop an automatic de-identification pipeline for all kinds of clinical documents based on a distant supervised method to significantly reduce the cost of manual annotations and to facilitate the transfer of the de-identification pipeline to other clinical centers.

METHODS

We proposed an automated annotation process for French clinical de-identification, exploiting data from the eHOP clinical data warehouse (CDW) of the CHU de Rennes and national knowledge bases, as well as other features. In addition, this paper proposes an assisted data annotation solution using the Prodigy annotation tool. This approach aims to reduce the cost required to create a reference corpus for the evaluation of state-of-the-art NER models. Finally, we evaluated and compared the effectiveness of different NER methods.

RESULTS

A French de-identification dataset was developed in this work, based on EHRs provided by the eHOP CDW at Rennes University Hospital, France. The dataset was rich in terms of personal information, and the distribution of entities was quite similar in the training and test datasets. We evaluated a Bi-LSTM + CRF sequence labeling architecture, combined with Flair + FastText word embeddings, on a test set of manually annotated clinical reports. The model outperformed the other tested models with a significant F1 score of 96,96%, demonstrating the effectiveness of our automatic approach for deidentifying sensitive information.

CONCLUSIONS

This study provides an automatic de-identification pipeline for clinical notes, which can facilitate the reuse of EHRs for secondary purposes such as clinical research. Our study highlights the importance of using advanced NLP techniques for effective de-identification, as well as the need for innovative solutions such as distant supervision to overcome the challenge of limited annotated data in the medical domain.

EHR-BERT: A BERT-based model for effective anomaly detection in electronic health records

OBJECTIVE

Physicians and clinicians rely on data contained in electronic health records (EHRs), as recorded by health information technology (HIT), to make informed decisions about their patients. The reliability of HIT systems in this regard is critical to patient safety. Consequently, better tools are needed to monitor the performance of HIT systems for potential hazards that could compromise the collected EHRs, which in turn could affect patient safety. In this paper, we propose a new framework for detecting anomalies in EHRs using sequence of clinical events. This new framework, EHR-Bidirectional Encoder Representations from Transformers (BERT), is motivated by the gaps in the existing deep-learning related methods, including high false negatives, sub-optimal accuracy, higher computational cost, and the risk of information loss. EHR-BERT is an innovative framework rooted in the BERT architecture, meticulously tailored to navigate the hurdles in the contemporary BERT method; thus, enhancing anomaly detection in EHRs for healthcare applications.

METHODS

The EHR-BERT framework was designed using the Sequential Masked Token Prediction (SMTP) method. This approach treats EHRs as natural language sentences and iteratively masks input tokens during both training and prediction stages. This method facilitates the learning of EHR sequence patterns in both directions for each event and identifies anomalies based on deviations from the normal execution models trained on EHR sequences.

RESULTS

Extensive experiments on large EHR datasets across various medical domains demonstrate that EHR-BERT markedly improves upon existing models. It significantly reduces the number of false positives and enhances the detection rate, thus bolstering the reliability of anomaly detection in electronic health records. This improvement is attributed to the model's ability to minimize information loss and maximize data utilization effectively.

CONCLUSION

EHR-BERT showcases immense potential in decreasing medical errors related to anomalous clinical events, positioning itself as an indispensable asset for enhancing patient safety and the overall standard of healthcare services. The framework effectively overcomes the drawbacks of earlier models, making it a promising solution for healthcare professionals to ensure the reliability and quality of health data.

Prediction of multiclass surgical outcomes in glaucoma using multimodal deep learning based on free-text operative notes and structured EHR data

OBJECTIVE

Surgical outcome prediction is challenging but necessary for postoperative management. Current machine learning models utilize pre- and post-op data, excluding intraoperative information in surgical notes. Current models also usually predict binary outcomes even when surgeries have multiple outcomes that require different postoperative management. This study addresses these gaps by incorporating intraoperative information into multimodal models for multiclass glaucoma surgery outcome prediction.

MATERIALS AND METHODS

We developed and evaluated multimodal deep learning models for multiclass glaucoma trabeculectomy surgery outcomes using both structured EHR data and free-text operative notes. We compare those to baseline models that use structured EHR data exclusively, or neural network models that leverage only operative notes.

RESULTS

The multimodal neural network had the highest performance with a macro AUROC of 0.750 and F1 score of 0.583. It outperformed the baseline machine learning model with structured EHR data alone (macro AUROC of 0.712 and F1 score of 0.486). Additionally, the multimodal model achieved the highest recall (0.692) for hypotony surgical failure, while the surgical success group had the highest precision (0.884) and F1 score (0.775).

DISCUSSION

This study shows that operative notes are an important source of predictive information. The multimodal predictive model combining perioperative notes and structured pre- and post-op EHR data outperformed other models. Multiclass surgical outcome prediction can provide valuable insights for clinical decision-making.

CONCLUSIONS

Our results show the potential of deep learning models to enhance clinical decision-making for postoperative management. They can be applied to other specialties to improve surgical outcome predictions.

Accurate diagnosis of bullous pemphigoid requires multiple health care visits

Introduction

Accurate use of diagnostic codes is crucial for epidemiological and genetic research based on electronic health record (EHR) data.

Methods

This retrospective study validated the International Classification of Diseases (ICD)-10 diagnostic code L12.0 for bullous pemphigoid (BP) using EHR data from two Finnish university hospitals. We found 1225 subjects with at least one EHR entry of L12.0 between 2009 and 2019. BP diagnosis was based on clinical findings characteristic of BP and positive findings on direct immunofluorescence (DIF), BP180-NC16A enzyme-linked immunosorbent assay (ELISA) or indirect immunofluorescence (IIF) assay.

Results

True BP was found in 901 patients; the positive predictive value (PPV) for L12.0 was 73.6% (95% CI 71.0-76.0). L12.0 was more accurately registered in dermatology units than any specialized health care units (p<0.001). Including patients with multiple L12.0 registrations (≥3), increased the accuracy of the L12.0 code in both dermatology units and other settings.

Discussion

One diagnostic code of L12.0 is not enough to recognize BP in a large epidemiological data set; including only L12.0 registered in dermatology units and excluding cases with <3 L12.0 record entries markedly increases the PPV of BP diagnosis.

Eos and OMOCL: Towards a seamless integration of openEHR records into the OMOP Common Data Model

BACKGROUND

The reuse of data from electronic health records (EHRs) for research purposes promises to improve the data foundation for clinical trials and may even support to enable them. Nevertheless, EHRs are characterized by both, heterogeneous structure and semantics. To standardize this data for research, the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) standard has recently seen an increase in use. However, the conversion of these EHRs into the OMOP CDM requires complex and resource intensive Extract Transform and Load (ETL) processes. This hampers the reuse of clinical data for research. To solve the issues of heterogeneity of EHRs and the lack of semantic precision on the care site, the openEHR standard has recently seen wider adoption. A standardized process to integrate openEHR records into the CDM potentially lowers the barriers of making EHRs accessible for research. Yet, a comprehensive approach about the integration of openEHR records into the OMOP CDM has not yet been made.

METHODS

We analyzed both standards and compared their models to identify possible mappings. Based on this, we defined the necessary processes to transform openEHR records into CDM tables. We also discuss the limitation of openEHR with its unspecific demographics model and propose two possible solutions.

RESULTS

We developed the OMOP Conversion Language (OMOCL) which enabled us to define a declarative openEHR archetype-to-CDM mapping language. Using OMOCL, it was possible to define a set of mappings. As a proof-of-concept, we implemented the Eos tool, which uses the OMOCL-files to successfully automatize the ETL from real-world and sample EHRs into the OMOP CDM.

DISCUSSION

Both Eos and OMOCL provide a way to define generic mappings for an integration of openEHR records into OMOP. Thus, it represents a significant step towards achieving interoperability between the clinical and the research data domains. However, the transformation of openEHR data into the less expressive OMOP CDM leads to a loss of semantics.

TransFAIR study: a European multicentre experimental comparison of EHR2EDC technology to the usual manual method for eCRF data collection

PURPOSE

Regulatory authorities including the Food and Drug Administration and the European Medicines Agency are encouraging to conduct clinical trials using routinely collected data. The aim of the TransFAIR experimental comparison was to evaluate, within real-life conditions, the ability of the Electronic Health Records to Electronic Data Capture (EHR2EDC) module to accurately transfer from EHRs to EDC systems patients' data of clinical studies in various therapeutic areas.

METHODS

A prospective study including six clinical trials from three different sponsors running in three hospitals across Europe has been conducted. The same data from the six studies were collected using both traditional manual data entry and the EHR2EDC module. The outcome variable was the percentage of data accurately transferred using the EHR2EDC technology. This percentage was calculated considering all collected data and the data in four domains: demographics (DM), vital signs (VS), laboratories (LB) and concomitant medications (CM).

RESULTS

Overall, 6143 data points (39.6% of the data in the scope of the TransFAIR study and 16.9% when considering all data) were accurately transferred using the platform. LB data represented 65.4% of the data transferred; VS data, 30.8%; DM data, 0.7% and CM data, 3.1%.

CONCLUSIONS

The objective of accurately transferring at least 15% of the manually entered trial datapoints using the EHR2EDC module was achieved. Collaboration and codesign by hospitals, industry, technology company, supported by the Institute of Innovation through Health Data was a success factor in accomplishing these results. Further work should focus on the harmonisation of data standards and improved interoperability to extend the scope of transferable EHR data.

Assessment of implementation barriers of blockchain technology in public healthcare: evidences from developing countries

The widespread use of Blockchain technology (BT) in nations that are developing remains in its early stages, necessitating a more comprehensive evaluation using efficient and adaptable approaches. The need for digitalization to boost operational effectiveness is growing in the healthcare sector. Despite BT's potential as a competitive option for the healthcare sector, insufficient research has prevented it being fully utilised. This study intends to identify the main sociological, economical, and infrastructure obstacles to BT adoption in developing nations' public health systems. To accomplish this goal, the study employs a multi-level analysis of blockchain hurdles using hybrid approach. The study's findings provide decision- makers with guidance on how to proceed, as well as insight into implementation challenges.

The reporting of neuropsychiatric symptoms in electronic health records of individuals with Alzheimer's disease: a natural language processing study

BACKGROUND

Neuropsychiatric symptoms (NPS) are prevalent in the early clinical stages of Alzheimer's disease (AD) according to proxy-based instruments. Little is known about which NPS clinicians report and whether their judgment aligns with proxy-based instruments. We used natural language processing (NLP) to classify NPS in electronic health records (EHRs) to estimate the reporting of NPS in symptomatic AD at the memory clinic according to clinicians. Next, we compared NPS as reported in EHRs and NPS reported by caregivers on the Neuropsychiatric Inventory (NPI).

METHODS

Two academic memory clinic cohorts were used: the Amsterdam UMC (n = 3001) and the Erasmus MC (n = 646). Patients included in these cohorts had MCI, AD dementia, or mixed AD/VaD dementia. Ten trained clinicians annotated 13 types of NPS in a randomly selected training set of n = 500 EHRs from the Amsterdam UMC cohort and in a test set of n = 250 EHRs from the Erasmus MC cohort. For each NPS, a generalized linear classifier was trained and internally and externally validated. Prevalence estimates of NPS were adjusted for the imperfect sensitivity and specificity of each classifier. Intra-individual comparison of the NPS classified in EHRs and NPS reported on the NPI were conducted in a subsample (59%).

RESULTS

Internal validation performance of the classifiers was excellent (AUC range: 0.81-0.91), but external validation performance decreased (AUC range: 0.51-0.93). NPS were prevalent in EHRs from the Amsterdam UMC, especially apathy (adjusted prevalence = 69.4%), anxiety (adjusted prevalence = 53.7%), aberrant motor behavior (adjusted prevalence = 47.5%), irritability (adjusted prevalence = 42.6%), and depression (adjusted prevalence = 38.5%). The ranking of NPS was similar for EHRs from the Erasmus MC, although not all classifiers obtained valid prevalence estimates due to low specificity. In both cohorts, there was minimal agreement between NPS classified in the EHRs and NPS reported on the NPI (all kappa coefficients < 0.28), with substantially more reports of NPS in EHRs than on NPI assessments.

CONCLUSIONS

NLP classifiers performed well in detecting a wide range of NPS in EHRs of patients with symptomatic AD visiting the memory clinic and showed that clinicians frequently reported NPS in these EHRs. Clinicians generally reported more NPS in EHRs than caregivers reported on the NPI.

A drug recommender system for the treatment of hypertension

BACKGROUND

One third (20% to 30%) of patients suffering from hypertension show increased blood pressure resistant to treatment. This resistance often has multifactorial causes, like therapeutic inertia and inappropriate medication but also poor patient adherence. Evidence-based guidelines aim to support appropriate health care decisions. However, (i) research and appraisal of clinical guidelines is often not practicable in daily routine care and (ii) guidelines alone are often insufficient to make suitable and personalized treatment decisions. Shared decision-making (SDM) can significantly improve patient adherence, but is also difficult to implement in routine care due to time constraints.

METHODS

Clinical Decision Support Systems (CDSSs), designed to support clinical decision-making by providing explainable and personalized treatment recommendations, are expected to remedy the aforementioned issues. In this work we describe a digital recommendation system for the pharmaceutical treatment of hypertension and compare its recommendations with clinical experts. The proposed therapy recommender algorithm combines external evidence (knowledge-based) - derived from clinical guidelines and drugs' professional information - with information stored in routine care data (data-based) - derived from 298 medical records and 900 doctor-patient contacts from 7 general practitioners practices. The developed Graphical User Interface (GUI) visualizes recommendations along with personalized treatment information and intents to support SDM. The CDSS was evaluated on 23 artificial test patients (case vignettes), by comparing its output with recommendations from five specialized physicians.

RESULTS

The results show that the proposed algorithm provides personalized treatment recommendations with large agreement with clinical experts. This is true for agreement with all experts (agree_all), with any expert (agree_any), and with the majority vote of all experts (agree_majority). The performance of a solely data-based approach can be additionally improved by applying evidence-based rules (external evidence). When comparing the achieved results (agree_all) with the inter-rater agreement among experts, the CDSS's recommendations partly agree more often with the experts than the experts among each other.

CONCLUSION

Overall, the feasibility and performance of medication recommendation systems for the treatment of hypertension could be shown. The major challenges when developing such a CDSS arise from (i) the availability of sufficient and appropriate training and evaluation data and (ii) the absence of standardized medical knowledge such as computerized guidelines. If these challenges are solved, such treatment recommender systems can support physicians with exploiting knowledge stored in routine care data, help to comply with the best available clinical evidence and increase the adherence of the patient by reducing site-effects and individualizing therapies.

Opportunities and challenges to non-communicable disease (NCD) research and training in Pakistan: a qualitative study from Pakistan

INTRODUCTION

Most of the global non-communicable disease (NCD)-related death burden is borne by low and middle-income countries (LMICs). In LMICs like Pakistan, however, a major gap in responding to NCDs is a lack of high-quality research leading to policy development and implementation of NCDs. To assess institutional opportunities and constraints to NCD research and training we conducted a situational analysis for NCD research and training at Aga Khan University Pakistan.

METHODS

We conducted a descriptive exploratory study using grounded theory as a qualitative approach: semistructured interviews of 16 NCD stakeholders (three excluded) and two focus group discussions with postgraduate and undergraduate trainees were conducted. A simple thematic analysis was done where themes were identified, and then recurring ideas were critically placed in their specific themes and refined based on the consensus of the investigators.

RESULTS

The major themes derived were priority research areas in NCDs; methods to improve NCD research integration; barriers to NCD research in LMICs like Pakistan; design of NCD research programme and career paths; and NCD prevention at mass level, policy and link to the government. In general, participants opined that while there was an appetite for NCD research and training, but few high-quality research training programmes in NCDs existed, such programmes needed to be established. The ideal NCD research and training programmes would have in-built protected time, career guidance and dedicated mentorship. Most participants identified cardiovascular diseases as a priority thematic area and health information technology and data science as key methodological approaches to be introduced into research training.

CONCLUSION

We conclude from this qualitative study on NCD research and training that high-quality research training programmes for NCDs are rare. Such programmes need to be established with in-built protected time, career guidance and mentorship for the trainees to improve their research capacity in Pakistan.

Portability of natural language processing methods to detect suicidality from clinical text in US and UK electronic health records

Background

In the global effort to prevent death by suicide, many academic medical institutions are implementing natural language processing (NLP) approaches to detect suicidality from unstructured clinical text in electronic health records (EHRs), with the hope of targeting timely, preventative interventions to individuals most at risk of suicide. Despite the international need, the development of these NLP approaches in EHRs has been largely local and not shared across healthcare systems.

Methods

In this study, we developed a process to share NLP approaches that were individually developed at King's College London (KCL), UK and Weill Cornell Medicine (WCM), US - two academic medical centers based in different countries with vastly different healthcare systems. We tested and compared the algorithms' performance on manually annotated clinical notes (KCL: n = 4,911 and WCM = 837).

Results

After a successful technical porting of the NLP approaches, our quantitative evaluation determined that independently developed NLP approaches can detect suicidality at another healthcare organization with a different EHR system, clinical documentation processes, and culture, yet do not achieve the same level of success as at the institution where the NLP algorithm was developed (KCL approach: F1-score 0.85 vs. 0.68, WCM approach: F1-score 0.87 vs. 0.72).

Limitations

Independent NLP algorithm development and patient cohort selection at the two institutions comprised direct comparability.

Conclusions

Shared use of these NLP approaches is a critical step forward towards improving data-driven algorithms for early suicide risk identification and timely prevention.

The Holy grail of healthcare analytics: what it takes to get there?

BACKGROUND

Indian healthcare is rapidly growing and needs efficiency more than ever, which can be achieved by leveraging healthcare analytics. National Digital Health Mission has set the stage for digital health and getting the right direction from the very beginning is important. The current study was, therefore, undertaken to find what it takes for an apex tertiary care teaching hospital to leverage healthcare analytics.

AIM

To study the existing Hospital Information System (HIS) at AIIMS, New Delhi and assess the preparedness to leverage healthcare analytics.

METHODOLOGY

A three-pronged approach was used. First, concurrent review and detailed mapping of all running applications was done based on nine parameters by a multidisciplinary team of experts. Second, capability of the current HIS to measure specific management related KPIs was evaluated. Third, user perspective was obtained from 750 participants from all cadres of healthcare workers, using a validated questionnaire based on Delone and McLean model.

RESULTS

Interoperability issues between applications running within the same institute, impaired informational continuity with limited device interface and automation were found on concurrent review. HIS was capturing data to measure only 9 out of 33 management KPIs. User perspective on information quality was very poor which was found to be due to poor system quality of HIS, though some functions were reportedly well supported by the HIS.

CONCLUSION

It is important for hospitals to first evaluate and strengthen their data generation systems/HIS. The three-pronged approach used in this study provides a template for other hospitals.

Developing Automated Computer Algorithms to Phenotype Periodontal Disease Diagnoses in Electronic Dental Records

OBJECTIVE

 Our objective was to phenotype periodontal disease (PD) diagnoses from three different sections (diagnosis codes, clinical notes, and periodontal charting) of the electronic dental records (EDR) by developing two automated computer algorithms.

METHODS

 We conducted a retrospective study using EDR data of patients (n = 27,138) who received care at Temple University Maurice H. Kornberg School of Dentistry from January 1, 2017 to August 31, 2021. We determined the completeness of patient demographics, periodontal charting, and PD diagnoses information in the EDR. Next, we developed two automated computer algorithms to automatically diagnose patients' PD statuses from clinical notes and periodontal charting data. Last, we phenotyped PD diagnoses using automated computer algorithms and reported the improved completeness of diagnosis.

RESULTS

 The completeness of PD diagnosis from the EDR was as follows: periodontal diagnosis codes 36% (n = 9,834), diagnoses in clinical notes 18% (n = 4,867), and charting information 80% (n = 21,710). After phenotyping, the completeness of PD diagnoses improved to 100%. Eleven percent of patients had healthy periodontium, 43% were with gingivitis, 3% with stage I, 36% with stage II, and 7% with stage III/IV periodontitis.

CONCLUSIONS

 We successfully developed, tested, and deployed two automated algorithms on big EDR datasets to improve the completeness of PD diagnoses. After phenotyping, EDR provided 100% completeness of PD diagnoses of 27,138 unique patients for research purposes. This approach is recommended for use in other large databases for the evaluation of their EDR data quality and for phenotyping PD diagnoses and other relevant variables.

CODE-EHR best practice framework for the use of structured electronic healthcare records in clinical research

Big data is central to new developments in global clinical science aiming to improve the lives of patients. Technological advances have led to the routine use of structured electronic healthcare records with the potential to address key gaps in clinical evidence. The covid-19 pandemic has demonstrated the potential of big data and related analytics, but also important pitfalls. Verification, validation, and data privacy, as well as the social mandate to undertake research are key challenges. The European Society of Cardiology and the BigData@Heart consortium have brought together a range of international stakeholders, including patient representatives, clinicians, scientists, regulators, journal editors and industry. We propose the CODE-EHR Minimum Standards Framework as a means to improve the design of studies, enhance transparency and develop a roadmap towards more robust and effective utilisation of healthcare data for research purposes.

The future regulation of artificial intelligence systems in healthcare services and medical research in the European Union

Despite its promising future, the application of artificial intelligence (AI) and automated decision-making in healthcare services and medical research faces several legal and ethical hurdles. The European Union (EU) is tackling these issues with the existing legal framework and drafting new regulations, such as the proposed AI Act. The EU General Data Protection Regulation (GDPR) partly regulates AI systems, with rules on processing personal data and protecting data subjects against solely automated decision-making. In healthcare services, (automated) decisions are made more frequently and rapidly. However, medical research focuses on innovation and efficacy, with less direct decisions on individuals. Therefore, the GDPR’s restrictions on solely automated decision-making apply mainly to healthcare services, and the rights of patients and research participants may significantly differ. The proposed AI Act introduced a risk-based approach to AI systems based on the principles of ethical AI. We analysed the complex connection between the GDPR and AI Act, highlighting the main issues and finding ways to harmonise the principles of data protection and ethical AI. The proposed AI Act may complement the GDPR in healthcare services and medical research. Although several years may pass before the AI Act comes into force, many of its goals will be realised before that.

CODE-EHR best-practice framework for the use of structured electronic health-care records in clinical research

Big data is important to new developments in global clinical science that aim to improve the lives of patients. Technological advances have led to the regular use of structured electronic health-care records with the potential to address key deficits in clinical evidence that could improve patient care. The COVID-19 pandemic has shown this potential in big data and related analytics but has also revealed important limitations. Data verification, data validation, data privacy, and a mandate from the public to conduct research are important challenges to effective use of routine health-care data. The European Society of Cardiology and the BigData@Heart consortium have brought together a range of international stakeholders, including representation from patients, clinicians, scientists, regulators, journal editors, and industry members. In this Review, we propose the CODE-EHR minimum standards framework to be used by researchers and clinicians to improve the design of studies and enhance transparency of study methods. The CODE-EHR framework aims to develop robust and effective utilisation of health-care data for research purposes.

Data capture and sharing in the COVID-19 pandemic: a cause for concern

Routine health care and research have been profoundly influenced by digital-health technologies. These technologies range from primary data collection in electronic health records (EHRs) and administrative claims to web-based artificial-intelligence-driven analyses. There has been increased use of such health technologies during the COVID-19 pandemic, driven in part by the availability of these data. In some cases, this has resulted in profound and potentially long-lasting positive effects on medical research and routine health-care delivery. In other cases, high profile shortcomings have been evident, potentially attenuating the effect of-or representing a decreased appetite for-digital-health transformation. In this Series paper, we provide an overview of how facets of health technologies in routinely collected medical data (including EHRs and digital data sharing) have been used for COVID-19 research and tracking, and how these technologies might influence future pandemics and health-care research. We explore the strengths and weaknesses of digital-health research during the COVID-19 pandemic and discuss how learnings from COVID-19 might translate into new approaches in a post-pandemic era.

Attitudes of Mental Health Service Users Toward Storage and Use of Electronic Health Records

OBJECTIVE

Electronic health records (EHRs) are used for both clinical practice and research. Because mental health service users' views are underrepresented in perspectives on EHR use, the authors examined service users' awareness, attitudes, and opinions about EHR data storage and sharing.

METHODS

A mixed-methods, cross-sectional design was used to examine attitudes of 253 Norwegian mental health service users who were recruited online to complete a quantitative and qualitative (free-text) survey about EHR utilization.

RESULTS

Most participants were aware that EHRs were stored (95%) and shared (58%). Most thought that patients benefited from EHR storage (84%), trusted authorities with EHR sharing (71%), were willing to share their EHRs to help others (75%), felt they benefited from EHR sharing (75%), and thought EHR sharing was ethical for health care and research (71%). Fewer were aware of EHR sharing for research (36%), and 62% were aware that shared data were anonymized. Of the participants, 69% recognized privacy risks associated with sharing. Lack of transparency and skepticism about anonymization and misuse of EHR data were concerns and perceived risks. Mental health service users thought that EHRs should be shared for policy development (81%), education and training (85%), improving care quality (89%), research (91%), and clinical decision support (81%).

CONCLUSIONS

Participants were aware of and supported EHR sharing for research and clinical care. They supported sharing to help others and were willing to fully participate in clinical care and research, as well as to share EHR information for their own care, research, and the care of others.

Impact of time-varying exposure on estimated effects in observational studies using routinely collected data: protocol for a cross-sectional study

INTRODUCTION

Time-varying exposure is an important issue that should be addressed in longitudinal observational studies using routinely collected data (RCD) for drug treatment effects. How well investigators designed, analysed and reported time-varying exposure, and to what extent the divergence that can be observed between different methods used for handling time-varying exposure in these studies remains uncertain. We will conduct a cross-sectional study to comprehensively address this question.

METHODS AND ANALYSIS

We have developed a comprehensive search strategy to identify all studies exploring drug treatment effects including both effectiveness and safety that used RCD and were published in core journals between 2018 and 2020. We will collect information regarding general study characteristics, data source profile, methods for handling time-varying exposure, results and the interpretation of findings from each eligibility. Paired reviewers will screen and extract data, resolving disagreements through discussion. We will describe the characteristics of included studies, and summarise the method used for handling time-varying exposure in primary analysis and sensitivity analysis. We will also compare the divergence between different approaches for handling time-varying exposure using ratio of risk ratios.

ETHICS AND DISSEMINATION

No ethical approval is required because the data we will use do not include individual patient data. Findings will be disseminated through peer-reviewed publications.

A Proposal for Value-Based Managed Entry Agreements in an Environment of Technological Change and Economic Challenge for Publicly Funded Healthcare Systems

Managed entry agreements (MEA) represent one of the main topics of discussion between the European National Payers Authorities. Several initiatives on the subject have been organized over the past few years and the scientific literature is full of publications on the subject. There is currently little international sharing of information between payers, mainly as a result of the confidentiality issues. There are potential benefits from the mutual sharing of information, both about the existence of MEAs and on the outcomes and results. The importance of involving all the players in the decision-making process on market access for a medicinal product (MP) is that it may help to make new therapies available to patients in a shorter time. The aim of this project is to propose a new pathway of value-based MEA (VBMEA), based on the analysis of the current Italian pricing and reimbursement framework. This requires elaboration of a transparent appraisal and MEA details with at least a 24-month contract. The price of the MP is therefore valued based on the analysis of the VBMEA registries of the Italian Medicines Agency. Although the proposal focuses on the Italian context, a similar approach could also be adapted in other nations, considering the particularities of the single health technology assessment (HTA)/payer system.

Measurement of hemorrhage-related severe maternal morbidity with billing versus electronic medical record data

OBJECTIVE

Measurement of obstetric hemorrhage-related morbidity is important for quality assurance purposes but presents logistical challenges in large populations. Billing codes are typically used to track severe maternal morbidity but may be of suboptimal validity. The objective of this study was to evaluate the validity of billing code diagnoses for hemorrhage-related morbidity compared to data obtained from the electronic medical record.

STUDY DESIGN

Deliveries occurring between July 2014 and July 2017 from three hospitals within a single system were analyzed. Three outcomes related to obstetric hemorrhage that are part of the Centers for Disease Control and Prevention definition of severe maternal morbidity (SMM) were evaluated: (i) transfusion, (ii) disseminated intravascular coagulation (DIC), and (iii) acute renal failure (ARF). ICD-9-CM and ICD-10-CM for these conditions were ascertained and compared to blood bank records and laboratory values. Sensitivity, specificity, positive (PPV) and negative predictive values (NPV) with 95% confidence intervals (CI) were calculated. Ancillary analyses were performed comparing codes and outcomes between hospitals and comparing ICD-9-CM to ICD-10-CM codes. Comparisons of categorical variables were performed with the chi-squared test. T-tests were used to compare continuous outcomes.

RESULTS

35,518 deliveries were analyzed. 786 women underwent transfusion, 168 had serum creatinine ≥1.2 mg/dL, and 99, 40, and 16 had fibrinogen ≤200, ≤150, and ≤100 mg/dL, respectively. Transfusion codes were 65% sensitive (95% CI 62-69%) with a 91% PPV (89-94%) for blood bank records of transfusion. DIC codes were 22% sensitive (95% CI 15-32%) for a fibrinogen cutoff of ≤200 mg/dL with 15% PPV (95% CI 10-22%). Sensitivity for ARF was 33% (95% CI 26-41%) for a creatinine of 1.2 mg/dL with a PPV of 63% (95% CI 52-73%). Sensitivity of ICD-9-CM for transfusion was significantly higher than ICD-10-CM (81%, 95% CI 76-86% versus 56%, 95% CI 51-60%, p < .01). Evaluating sensitivity of codes by individual hospitals, sensitivity of diagnosis codes for transfusion varied significantly (Hospital A 47%, 95% CI 36-58% versus Hospital B 63%, 95% CI 58-67% versus Hospital C 80%, 95% CI 74-86%, p < .01).

CONCLUSION

Use of administrative billing codes for postpartum hemorrhage complications may be appropriate for measuring trends related to disease burden and resource utilization, particularly in the case of transfusion, but may be suboptimal for measuring clinical outcomes within and between hospitals.

Using electronic health records to streamline provider recruitment for implementation science studies

Background

Healthcare providers are often targeted as research participants, especially for implementation science studies evaluating provider- or system-level issues. Frequently, provider eligibility is based on both provider and patient factors. Manual chart review and self-report are common provider screening strategies but require substantial time, effort, and resources. The automated use of electronic health record (EHR) data may streamline provider identification for implementation science research. Here, we describe an approach to provider screening for a Veterans Health Administration (VHA)-funded study focused on implementing risk-aligned surveillance for bladder cancer patients.

Methods

Our goal was to identify providers at 6 pre-specified facilities who performed ≥10 surveillance cystoscopy procedures among bladder cancer patients in the 12 months prior to recruitment start on January 16, 2020, and who were currently practicing at 1 of 6 pre-specified facilities. Using VHA EHR data (using CPT, ICD10 procedure, and ICD10 diagnosis codes), we identified cystoscopy procedures performed after an initial bladder cancer diagnosis (i.e., surveillance procedures). Procedures were linked to VHA staff data to determine the provider of record, the number of cystoscopies they performed, and their current location of practice. To validate this approach, we performed a chart review of 105 procedures performed by a random sample of identified providers. The proportion of correctly identified procedures was calculated (Positive Predictive Value (PPV)), along with binomial 95% confidence intervals (CI).

Findings

We identified 1,917,856 cystoscopies performed on 703,324 patients from October 1, 1999—January 16, 2020, across the nationwide VHA. Of those procedures, 40% were done on patients who had a prior record of bladder cancer and were completed by 15,065 distinct providers. Of those, 61 performed ≥ 10 procedures and were currently practicing at 1 of the 6 facilities of interest in the 1 year prior to study recruitment. The random chart review of 7 providers found 101 of 105 procedures (PPV: 96%; 95% CI: 91% to 99%) were surveillance procedures and were performed by the selected provider on the recorded date.

Implications

These results show that EHR data can be used for accurate identification of healthcare providers as research participants when inclusion criteria consist of both patient- (temporal relationship between diagnosis and procedure) and provider-level (frequency of procedure and location of current practice) factors. As administrative codes and provider identifiers are collected in most, if not all, EHRs for billing purposes this approach can be translated from provider recruitment in VHA to other healthcare systems. Implementation studies should consider this method of screening providers.

Establishing a National Cardiovascular Disease Surveillance System in the United States Using Electronic Health Record Data: Key Strengths and Limitations

Cardiovascular disease surveillance involves quantifying the evolving population-level burden of cardiovascular outcomes and risk factors as a data-driven initial step followed by the implementation of interventional strategies designed to alleviate this burden in the target population. Despite widespread acknowledgement of its potential value, a national surveillance system dedicated specifically to cardiovascular disease does not currently exist in the United States. Routinely collected health care data such as from electronic health records (EHRs) are a possible means of achieving national surveillance. Accordingly, this article elaborates on some key strengths and limitations of using EHR data for establishing a national cardiovascular disease surveillance system. Key strengths discussed include the: (1) ubiquity of EHRs and consequent ability to create a more "national" surveillance system, (2) existence of a common data infrastructure underlying the health care enterprise with respect to data domains and the nomenclature by which these data are expressed, (3) longitudinal length and detail that define EHR data when individuals repeatedly patronize a health care organization, and (4) breadth of outcomes capable of being surveilled with EHRs. Key limitations discussed include the: (1) incomplete ascertainment of health information related to health care-seeking behavior and the disconnect of health care data generated at separate health care organizations, (2) suspect data quality resulting from the default information-gathering processes within the clinical enterprise, (3) questionable ability to surveil patients through EHRs in the absence of documented interactions, and (4) the challenge in interpreting temporal trends in health metrics, which can be obscured by changing clinical and administrative processes.

Understanding enterprise data warehouses to support clinical and translational research: enterprise information technology relationships, data governance, workforce, and cloud computing

OBJECTIVE

Among National Institutes of Health Clinical and Translational Science Award (CTSA) hubs, effective approaches for enterprise data warehouses for research (EDW4R) development, maintenance, and sustainability remain unclear. The goal of this qualitative study was to understand CTSA EDW4R operations within the broader contexts of academic medical centers and technology.

MATERIALS AND METHODS

We performed a directed content analysis of transcripts generated from semistructured interviews with informatics leaders from 20 CTSA hubs.

RESULTS

Respondents referred to services provided by health system, university, and medical school information technology (IT) organizations as "enterprise information technology (IT)." Seventy-five percent of respondents stated that the team providing EDW4R service at their hub was separate from enterprise IT; strong relationships between EDW4R teams and enterprise IT were critical for success. Managing challenges of EDW4R staffing was made easier by executive leadership support. Data governance appeared to be a work in progress, as most hubs reported complex and incomplete processes, especially for commercial data sharing. Although nearly all hubs (n = 16) described use of cloud computing for specific projects, only 2 hubs reported using a cloud-based EDW4R. Respondents described EDW4R cloud migration facilitators, barriers, and opportunities.

DISCUSSION

Descriptions of approaches to how EDW4R teams at CTSA hubs work with enterprise IT organizations, manage workforces, make decisions about data, and approach cloud computing provide insights for institutions seeking to leverage patient data for research.

CONCLUSION

Identification of EDW4R best practices is challenging, and this study helps identify a breadth of viable options for CTSA hubs to consider when implementing EDW4R services.

Using a Patient Portal to Increase Enrollment in a Newborn Screening Research Study: Observational Study

BACKGROUND

Many research studies fail to enroll enough research participants. Patient-facing electronic health record applications, known as patient portals, may be used to send research invitations to eligible patients.

OBJECTIVE

The first aim was to determine if receipt of a patient portal research recruitment invitation was associated with enrollment in a large ongoing study of newborns (Early Check). The second aim was to determine if there were differences in opening the patient portal research recruitment invitation and study enrollment by race and ethnicity, age, or rural/urban home address.

METHODS

We used a computable phenotype and queried the health care system's clinical data warehouse to identify women whose newborns would likely be eligible. Research recruitment invitations were sent through the women's patient portals. We conducted logistic regressions to test whether women enrolled their newborns after receipt of a patient portal invitation and whether there were differences by race and ethnicity, age, and rural/urban home address.

RESULTS

Research recruitment invitations were sent to 4510 women not yet enrolled through their patient portals between November 22, 2019, through March 5, 2020. Among women who received a patient portal invitation, 3.6% (161/4510) enrolled their newborns within 27 days. The odds of enrolling among women who opened the invitation was nearly 9 times the odds of enrolling among women who did not open their invitation (SE 3.24, OR 8.86, 95% CI 4.33-18.13; P<.001). On average, it took 3.92 days for women to enroll their newborn in the study, with 64% (97/161) enrolling their newborn within 1 day of opening the invitation. There were disparities by race and urbanicity in enrollment in the study after receipt of a patient portal research invitation but not by age. Black women were less likely to enroll their newborns than White women (SE 0.09, OR 0.29, 95% CI 0.16-0.55; P<.001), and women in urban zip codes were more likely to enroll their newborns than women in rural zip codes (SE 0.97, OR 3.03, 95% CI 1.62-5.67; P=.001). Black women (SE 0.05, OR 0.67, 95% CI 0.57-0.78; P<.001) and Hispanic women (SE 0.07, OR 0.73, 95% CI 0.60-0.89; P=.002) were less likely to open the research invitation compared to White women.

CONCLUSIONS

Patient portals are an effective way to recruit participants for research studies, but there are substantial racial and ethnic disparities and disparities by urban/rural status in the use of patient portals, the opening of a patient portal invitation, and enrollment in the study.

TRIAL REGISTRATION

ClinicalTrials.gov NCT03655223; https://clinicaltrials.gov/ct2/show/NCT03655223.

Constructing Epidemiologic Cohorts from Electronic Health Record Data

In the United States, electronic health records (EHR) are increasingly being incorporated into healthcare organizations to document patient health and services rendered. EHRs serve as a vast repository of demographic, diagnostic, procedural, therapeutic, and laboratory test data generated during the routine provision of health care. The appeal of using EHR data for epidemiologic research is clear: EHRs generate large datasets on real-world patient populations in an easily retrievable form permitting the cost-efficient execution of epidemiologic studies on a wide array of topics. Constructing epidemiologic cohorts from EHR data involves as a defining feature the development of data machinery, which transforms raw EHR data into an epidemiologic dataset from which appropriate inference can be drawn. Though data machinery includes many features, the current report focuses on three aspects of machinery development of high salience to EHR-based epidemiology: (1) selecting study participants; (2) defining “baseline” and assembly of baseline characteristics; and (3) follow-up for future outcomes. For each, the defining features and unique challenges with respect to EHR-based epidemiology are discussed. An ongoing example illustrates key points. EHR-based epidemiology will become more prominent as EHR data sources continue to proliferate. Epidemiologists must continue to improve the methods of EHR-based epidemiology given the relevance of EHRs in today’s healthcare ecosystem.

Identifying family and unpaid caregivers in the electronic health record: A descriptive analysis (Preprint)

Background

Most efforts to identify caregivers for research use passive approaches such as self-nomination. We describe an approach in which electronic health records (EHRs) can help identify, recruit, and increase diverse representations of family and other unpaid caregivers.

Objective

Few health systems have implemented systematic processes for identifying caregivers. This study aimed to develop and evaluate an EHR-driven process for identifying veterans likely to have unpaid caregivers in a caregiver survey study. We additionally examined whether there were EHR-derived veteran characteristics associated with veterans having unpaid caregivers.

Methods

We selected EHR home- and community-based referrals suggestive of veterans’ need for supportive care from friends or family. We identified veterans with these referrals across the 8 US Department of Veteran Affairs medical centers enrolled in our study. Phone calls to a subset of these veterans confirmed whether they had a caregiver, specifically an unpaid caregiver. We calculated the screening contact rate for unpaid caregivers of veterans using attempted phone screening and for those who completed phone screening. The veteran characteristics from the EHR were compared across referral and screening groups using descriptive statistics, and logistic regression was used to compare the likelihood of having an unpaid caregiver among veterans who completed phone screening.

Results

During the study period, our EHR-driven process identified 12,212 veterans with home- and community-based referrals; 2134 (17.47%) veteran households were called for phone screening. Among the 2134 veterans called, 1367 (64.06%) answered the call, and 813 (38.1%) veterans had a caregiver based on self-report of the veteran, their caregiver, or another person in the household. The unpaid caregiver identification rate was 38.1% and 59.5% among those with an attempted phone screening and completed phone screening, respectively. Veterans had increased odds of having an unpaid caregiver if they were married (adjusted odds ratio [OR] 2.69, 95% CI 1.68-4.34), had respite care (adjusted OR 2.17, 95% CI 1.41-3.41), or had adult day health care (adjusted OR 3.69, 95% CI 1.60-10.00). Veterans with a dementia diagnosis (adjusted OR 1.37, 95% CI 1.00-1.89) or veteran-directed care referral (adjusted OR 1.95, 95% CI 0.97-4.20) were also suggestive of an association with having an unpaid caregiver.

Conclusions

The EHR-driven process to identify veterans likely to have unpaid caregivers is systematic and resource intensive. Approximately 60% (813/1367) of veterans who were successfully screened had unpaid caregivers. In the absence of discrete fields in the EHR, our EHR-driven process can be used to identify unpaid caregivers; however, incorporating caregiver identification fields into the EHR would support a more efficient and systematic identification of caregivers.

Trial Registration

ClincalTrials.gov NCT03474380; https://clinicaltrials.gov/ct2/show/NCT03474380

Multigenerational health research using population-based linked databases: an international review

Family health history is a well-established risk factor for many health conditions but the systematic collection of health histories, particularly for multiple generations and multiple family members, can be challenging. Routinely-collected electronic databases in a select number of sites worldwide offer a powerful tool to conduct multigenerational health research for entire populations. At these sites, administrative and healthcare records are used to construct familial relationships and objectively-measured health histories. We review and synthesize published literature to compare the attributes of routinely-collected, linked databases for three European sites (Denmark, Norway, Sweden) and three non-European sites (Canadian province of Manitoba, Taiwan, Australian state of Western Australia) with the capability to conduct population-based multigenerational health research. Our review found that European sites primarily identified family structures using population registries, whereas non-European sites used health insurance registries (Manitoba and Taiwan) or linked data from multiple sources (Western Australia). Information on familial status was reported to be available as early as 1947 (Sweden); Taiwan had the fewest years of data available (1995 onwards). All centres reported near complete coverage of familial relationships for their population catchment regions. Challenges in working with these data include differentiating biological and legal relationships, establishing accurate familial linkages over time, and accurately identifying health conditions. This review provides important insights about the benefits and challenges of using routinely-collected, population-based linked databases for conducting population-based multigenerational health research, and identifies opportunities for future research within and across the data-intensive environments at these six sites.

Epidemiology of adult chronic cough: disease burden, regional issues, and recent findings

Chronic cough is a common medical condition that has a significant impact on patients' quality of life. Although it was previously considered a symptom of other disorders, it is now regarded as a pathologic state that is characterized by a deviation from the intrinsic protective functions of the cough reflex, especially in adults. There are several factors that may underlie the cough reflex hypersensitivity and its persistence, such as age, sex, comorbidities, viral infection, exposure to irritants or environmental pollutants, and their interactions may determine the epidemiology of chronic cough in different countries. With a deeper understanding of disease pathophysiology and advanced research methodology, there are more attempts to investigate cough epidemiology using a large cohort of healthcare population data. This is a narrative overview of recent findings on the disease burden, risk factors, Asia-Pacific issues, and longitudinal outcomes in adults with chronic cough. This paper also discusses the approaches utilizing routinely collected data in cough research.

Drug repurposing for opioid use disorders: integration of computational prediction, clinical corroboration, and mechanism of action analyses

Morbidity and mortality from opioid use disorders (OUD) and other substance use disorders (SUD) is a major public health crisis, yet there are few medications to treat them. There is an urgency to accelerate SUD medication development. We present an integrated drug repurposing strategy that combines computational prediction, clinical corroboration using electronic health records (EHRs) of over 72.9 million patients and mechanisms of action analysis. Among top-ranked repurposed candidate drugs, tramadol, olanzapine, mirtazapine, bupropion, and atomoxetine were associated with increased odds of OUD remission (adjusted odds ratio: 1.51 [1.38-1.66], 1.90 [1.66-2.18], 1.38 [1.31-1.46], 1.37 [1.29-1.46], 1.48 [1.25-1.76], p value < 0.001, respectively). Genetic and functional analyses showed these five candidate drugs directly target multiple OUD-associated genes including BDNF, CYP2D6, OPRD1, OPRK1, OPRM1, HTR1B, POMC, SLC6A4 and OUD-associated pathways, including opioid signaling, G-protein activation, serotonin receptors, and GPCR signaling. In summary, we developed an integrated drug repurposing approach and identified five repurposed candidate drugs that might be of value for treating OUD patients, including those suffering from comorbid conditions.

Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumonia

Background

Chest radiograph (CXR) is a basic diagnostic test in community-acquired pneumonia (CAP) with prognostic value. We developed a CXR-based artificial intelligence (AI) model (CAP AI predictive Engine: CAPE) and prospectively evaluated its discrimination for 30-day mortality.

Methods

Deep-learning model using convolutional neural network (CNN) was trained with a retrospective cohort of 2235 CXRs from 1966 unique adult patients admitted for CAP from 1 January 2019 to 31 December 2019. A single-centre prospective cohort between 11 May 2020 and 15 June 2020 was analysed for model performance. CAPE mortality risk score based on CNN analysis of the first CXR performed for CAP was used to determine the area under the receiver operating characteristic curve (AUC) for 30-day mortality.

Results

315 inpatient episodes for CAP occurred, with 30-day mortality of 19.4% (n=61/315). Non-survivors were older than survivors (mean (SD)age, 80.4 (10.3) vs 69.2 (18.7)); more likely to have dementia (n=27/61 vs n=58/254) and malignancies (n=16/61 vs n=18/254); demonstrate higher serum C reactive protein (mean (SD), 109 mg/L (98.6) vs 59.3 mg/L (69.7)) and serum procalcitonin (mean (SD), 11.3 (27.8) μg/L vs 1.4 (5.9) μg/L). The AUC for CAPE mortality risk score for 30-day mortality was 0.79 (95% CI 0.73 to 0.85, p<0.001); Pneumonia Severity Index (PSI) 0.80 (95% CI 0.74 to 0.86, p<0.001); Confusion of new onset, blood Urea nitrogen, Respiratory rate, Blood pressure, 65 (CURB-65) score 0.76 (95% CI 0.70 to 0.81, p<0.001), respectively. CAPE combined with CURB-65 model has an AUC of 0.83 (95% CI 0.77 to 0.88, p<0.001). The best performing model was CAPE incorporated with PSI, with an AUC of 0.84 (95% CI 0.79 to 0.89, p<0.001).

Conclusion

CXR-based CAPE mortality risk score was comparable to traditional pneumonia severity scores and improved its discrimination when combined.

A Framework for Methodological Choice and Evidence Assessment for Studies Using External Comparators from Real-World Data

Several approaches have been proposed recently to accelerate the pathway from drug discovery to patient access. These include novel designs such as using controls external to the clinical trial where standard randomised controls are not feasible. In parallel, there has been rapid growth in the application of routinely collected healthcare ‘real-world’ data for post-market safety and effectiveness studies. Thus, using real-world data to establish an external comparator arm in clinical trials is a natural next step. Regulatory authorities have begun to endorse the use of external comparators in certain circumstances, with some positive outcomes for new drug approvals. Given the potential to introduce bias associated with observational studies, there is a need for recommendations on how external comparators should be best used. In this article, we propose an evaluation framework for real-world data external comparator studies that enables full assessment of available evidence and related bias. We define the principle of exchangeability and discuss the applicability of criteria described by Pocock for consideration of the exchangeability of the external and trial populations. We explore how trial designs using real-world data external comparators fit within the evidence hierarchy and propose a four-step process for good conduct of external comparator studies. This process is intended to maximise the quality of evidence based on careful study design and the combination of covariate balancing, bias analysis and combining outcomes.

COVID-19 and dementia: Analyses of risk, disparity, and outcomes from electronic health records in the US

INTRODUCTION

At present, there is limited data on the risks, disparity, and outcomes for COVID-19 in patients with dementia in the United States.

METHODS

This is a retrospective case-control analysis of patient electronic health records (EHRs) of 61.9 million adult and senior patients (age ≥ 18 years) in the United States up to August 21, 2020.

RESULTS

Patients with dementia were at increased risk for COVID-19 compared to patients without dementia (adjusted odds ratio [AOR]: 2.00 [95% confidence interval (CI), 1.94-2.06], P < .001), with the strongest effect for vascular dementia (AOR: 3.17 [95% CI, 2.97-3.37], P < .001), followed by presenile dementia (AOR: 2.62 [95% CI, 2.28-3.00], P < .001), Alzheimer's disease (AOR: 1.86 [95% CI, 1.77-1.96], P < .001), senile dementia (AOR: 1.99 [95% CI, 1.86-2.13], P < .001) and post-traumatic dementia (AOR: 1.67 [95% CI, 1.51-1.86] P < .001). Blacks with dementia had higher risk of COVID-19 than Whites (AOR: 2.86 [95% CI, 2.67-3.06], P < .001). The 6-month mortality and hospitalization risks in patients with dementia and COVID-19 were 20.99% and 59.26%, respectively.

DISCUSSION

These findings highlight the need to protect patients with dementia as part of the strategy to control the COVID-19 pandemic.

EMR2vec: Bridging the gap between patient data and clinical trial

The human suffering from diseases caused by life-threatening viruses such as SARS, Ebola, and COVID-19 motivated many of us to study and discover the best means to harness the potential of data integration to assist clinical researchers to curb these viruses. Integrating patients data with clinical trials data is enormously promising as it provides a comprehensive knowledge base that accelerates the clinical research response-ability to tackle emerging infectious disease outbreaks. This work introduces EMR2vec, a platform that customises advanced NLP, machine learning and semantic web techniques to link potential patients to suitable clinical trials. Linking these two different but complementary datasets allows clinicians and researchers to compare patients to clinical research opportunities or to automatically select patients for personalized clinical care. The platform derives a 'bag of medical terms' (BoMT) from eligibility criteria by normalizing extracted entities through SNOMED-CT ontology. With the usage of BoMT, an ontological reasoning method is proposed to represent EMR and clinical trials in a vector space model. The platform presents a matching process that reduces vector dimensionality using a neural network, then applies orthogonality projection to measure the similarity between vectors. Finally, the proposed EMR2vec platform is evaluated with an extendable prototype based on Big data tools.

Improving Current Glycated Hemoglobin Prediction in Adults: Use of Machine Learning Algorithms With Electronic Health Records

Background

Predicting the risk of glycated hemoglobin (HbA_1c) elevation can help identify patients with the potential for developing serious chronic health problems, such as diabetes. Early preventive interventions based upon advanced predictive models using electronic health records data for identifying such patients can ultimately help provide better health outcomes.

Objective

Our study investigated the performance of predictive models to forecast HbA_1c elevation levels by employing several machine learning models. We also examined the use of patient electronic health record longitudinal data in the performance of the predictive models. Explainable methods were employed to interpret the decisions made by the black box models.

Methods

This study employed multiple logistic regression, random forest, support vector machine, and logistic regression models, as well as a deep learning model (multilayer perceptron) to classify patients with normal (<5.7%) and elevated (≥5.7%) levels of HbA_1c. We also integrated current visit data with historical (longitudinal) data from previous visits. Explainable machine learning methods were used to interrogate the models and provide an understanding of the reasons behind the decisions made by the models. All models were trained and tested using a large data set from Saudi Arabia with 18,844 unique patient records.

Results

The machine learning models achieved promising results for predicting current HbA_1c elevation risk. When coupled with longitudinal data, the machine learning models outperformed the multiple logistic regression model used in the comparative study. The multilayer perceptron model achieved an accuracy of 83.22% for the area under receiver operating characteristic curve when used with historical data. All models showed a close level of agreement on the contribution of random blood sugar and age variables with and without longitudinal data.

Conclusions

This study shows that machine learning models can provide promising results for the task of predicting current HbA_1c levels (≥5.7% or less). Using patients’ longitudinal data improved the performance and affected the relative importance for the predictors used. The models showed results that are consistent with comparable studies.