Electronic medical records (EMRs), epidemiology, and epistemology: reflections on EMRs and future pediatric clinical research

Identifying Precise Targets to Improve Child Mental Health Care Equity: Leveraging Advances in Clinical Research Informatics and Lived Experience

To reduce child mental health disparities, it is imperative to improve the precision of targets and to expand our vision of social determinants of health as modifiable. Advancements in clinical research informatics and please state accurate measurement of child mental health service use and quality. Participatory action research promotes representation of underserved groups in informatics research and practice and may improve the effectiveness of interventions by informing research across all stages, including the identification of key variables, risk and protective factors, and data interpretation.

Digital child health: opportunities and obstacles. A joint statement of European Academy of Paediatrics and European Confederation of Primary Care Paediatricians

The advancement of technology and the increasing digitisation of healthcare systems have opened new opportunities to transform the delivery of child health services. The importance of interoperable electronic health data in enhancing healthcare systems and improving child health care is evident. Interoperability ensures seamless data exchange and communication among healthcare entities, providers, institutions, household and systems. Using standardised data formats, coding systems, and terminologies is crucial in achieving interoperability and overcoming the barriers of different systems, formats, and locations. Paediatricians and other child health stakeholders can effectively address data structure, coding, and terminology inconsistencies by promoting interoperability and improving data quality and accuracy of children and youth, according to guidelines of the World Health Organisation. Thus, ensure comprehensive health assessments and screenings for children, including timely follow-up and communication of results. And implement effective vaccination schedules and strategies, ensuring timely administration of vaccines and prompt response to any concerns or adverse events. Developmental milestones can be continuously monitored. This can improve care coordination, enhance decision-making, and optimise health outcomes for children. In conclusion, using interoperable electronic child health data holds great promise in advancing international child healthcare systems and enhancing the child's care and well-being. By promoting standardised data exchange, interoperability enables timely health assessments, accurate vaccination schedules, continuous monitoring of developmental milestones, coordination of care, and collaboration among child healthcare professionals and the individual or their caregiver. Embracing interoperability is essential for creating a person-centric and data-driven healthcare ecosystem where the potential of digitalisation and innovation can be fully realized.

Comparing the influence of big data resources on medical knowledge recall for staff with and without medical collaboration platform

BACKGROUND

This study aims to examine how big data resources affect the recall of prior medical knowledge by healthcare professionals, and how this differs in environments with and without remote consultation platforms.

METHOD

This study investigated two distinct categories of medical institutions, namely 132 medical institutions with platforms, and 176 medical institutions without the platforms. Big data resources are categorized into two levels-medical institutional level and public level-and three types, namely data, technology, and services. The data are analyzed using SmartPLS2.

RESULTS

(1) In both scenarios, shared big data resources at the public level have a significant direct impact on the recall of prior medical knowledge. However, there is a significant difference in the direct impact of big data resources at the institutional level in both scenarios. (2) In institutions with platforms, for the three big data resources (the medical big data assets and big data deployment technical capacity at the medical institutional level, and policies of medical big data at the public level) without direct impacts, there exist three indirect pathways. (3) In institutions without platforms, for the two big data resources (the service capability and big data technical capacity at the medical institutional level) without direct impacts, there exist three indirect pathways.

CONCLUSIONS

The different interactions between big data, technology, and services, as well as between different levels of big data resources, affect the way clinical doctors recall relevant medical knowledge. These interaction patterns vary between institutions with and without platforms. This study provides a reference for governments and institutions to design big data environments for improving clinical capabilities.

Electronic health records identify timely trends in childhood mental health conditions

BACKGROUND

Electronic health records (EHRs) data provide an opportunity to collect patient information rapidly, efficiently and at scale. National collaborative research networks, such as PEDSnet, aggregate EHRs data across institutions, enabling rapid identification of pediatric disease cohorts and generating new knowledge for medical conditions. To date, aggregation of EHR data has had limited applications in advancing our understanding of mental health (MH) conditions, in part due to the limited research in clinical informatics, necessary for the translation of EHR data to child mental health research.

METHODS

In this cohort study, a comprehensive EHR-based typology was developed by an interdisciplinary team, with expertise in informatics and child and adolescent psychiatry, to query aggregated, standardized EHR data for the full spectrum of MH conditions (disorders/symptoms and exposure to adverse childhood experiences (ACEs), across 13 years (2010-2023), from 9 PEDSnet centers. Patients with and without MH disorders/symptoms (without ACEs), were compared by age, gender, race/ethnicity, insurance, and chronic physical conditions. Patients with ACEs alone were compared with those that also had MH disorders/symptoms. Prevalence estimates for patients with 1+ disorder/symptoms and for specific disorders/symptoms and exposure to ACEs were calculated, as well as risk for developing MH disorder/symptoms.

RESULTS

The EHR study data set included 7,852,081 patients < 21 years of age, of which 52.1% were male. Of this group, 1,552,726 (19.8%), without exposure to ACEs, had a lifetime MH disorders/symptoms, 56.5% being male. Annual prevalence estimates of MH disorders/symptoms (without exposure to ACEs) rose from 10.6% to 2010 to 15.1% in 2023, a 44% relative increase, peaking to 15.4% in 2019, prior to the Covid-19 pandemic. MH categories with the largest increases between 2010 and 2023 were exposure to ACEs (1.7, 95% CI 1.6-1.8), anxiety disorders (2.8, 95% CI 2.8-2.9), eating/feeding disorders (2.1, 95% CI 2.1-2.2), gender dysphoria/sexual dysfunction (43.6, 95% CI 35.8-53.0), and intentional self-harm/suicidality (3.3, 95% CI 3.2-3.5). White youths had the highest rates in most categories, except for disruptive behavior disorders, elimination disorders, psychotic disorders, and standalone symptoms which Black youths had higher rates. Median age of detection was 8.1 years (IQR 3.5-13.5) with all standalone symptoms recorded earlier than the corresponding MH disorder categories.

CONCLUSIONS

These results support EHRs' capability in capturing the full spectrum of MH disorders/symptoms and exposure to ACEs, identifying the proportion of patients and groups at risk, and detecting trends throughout a 13-year period that included the Covid-19 pandemic. Standardized EHR data, which capture MH conditions is critical for health systems to examine past and current trends for future surveillance. Our publicly available EHR-mental health typology codes can be used in other studies to further advance research in this area.

Precision information extraction for rare disease epidemiology at scale

BACKGROUND

The United Nations recently made a call to address the challenges of an estimated 300 million persons worldwide living with a rare disease through the collection, analysis, and dissemination of disaggregated data. Epidemiologic Information (EI) regarding prevalence and incidence data of rare diseases is sparse and current paradigms of identifying, extracting, and curating EI rely upon time-intensive, error-prone manual processes. With these limitations, a clear understanding of the variation in epidemiology and outcomes for rare disease patients is hampered. This challenges the public health of rare diseases patients through a lack of information necessary to prioritize research, policy decisions, therapeutic development, and health system allocations.

METHODS

In this study, we developed a newly curated epidemiology corpus for Named Entity Recognition (NER), a deep learning framework, and a novel rare disease epidemiologic information pipeline named EpiPipeline4RD consisting of a web interface and Restful API. For the corpus creation, we programmatically gathered a representative sample of rare disease epidemiologic abstracts, utilized weakly-supervised machine learning techniques to label the dataset, and manually validated the labeled dataset. For the deep learning framework development, we fine-tuned our dataset and adapted the BioBERT model for NER. We measured the performance of our BioBERT model for epidemiology entity recognition quantitatively with precision, recall, and F1 and qualitatively through a comparison with Orphanet. We demonstrated the ability for our pipeline to gather, identify, and extract epidemiology information from rare disease abstracts through three case studies.

RESULTS

We developed a deep learning model to extract EI with overall F1 scores of 0.817 and 0.878, evaluated at the entity-level and token-level respectively, and which achieved comparable qualitative results to Orphanet's collection paradigm. Additionally, case studies of the rare diseases Classic homocystinuria, GRACILE syndrome, Phenylketonuria demonstrated the adequate recall of abstracts with epidemiology information, high precision of epidemiology information extraction through our deep learning model, and the increased efficiency of EpiPipeline4RD compared to a manual curation paradigm.

CONCLUSIONS

EpiPipeline4RD demonstrated high performance of EI extraction from rare disease literature to augment manual curation processes. This automated information curation paradigm will not only effectively empower development of the NIH Genetic and Rare Diseases Information Center (GARD), but also support the public health of the rare disease community.

Impact of Delayed Time to Antibiotics in Medical and Surgical Necrotizing Enterocolitis

This study investigated whether delayed receipt of antibiotics in infants with necrotizing enterocolitis (NEC) is associated with disease severity. In this retrospective, single-center cohort study of infants diagnosed with NEC over 4 years, we compared the timing of antibiotic administration in infants (time order placed to time of receipt) in medical and surgical NEC. Cases were independently reviewed, then various clinical factors were compared. Of 46 suspected cases, 25 were confirmed by a panel of radiologists with good interrater reliability (ICC 0.657; p < 0.001). Delays in antibiotic receipt were 1.7× greater in surgical than medical NEC cases (p = 0.049). Every hour after order entry increased the adjusted odds of surgical NEC by 2.4 (1.08−5.23; p = 0.032). Delayed antibiotic receipt was more common in infants with surgical than medical NEC. Larger studies will be needed to investigate if optimizing antibiotic expediency could improve intestinal outcomes.

Impact of big data resources on clinicians’ activation of prior medical knowledge

Background

Activating prior medical knowledge in diagnosis and treatment is an important basis for clinicians to improve their care ability. However, it has not been systematically explained whether and how various big data resources affect the activation of prior knowledge in the big data environment faced by clinicians.

Objective

The aim of this study is to contribute to a better understanding on how the activation of prior knowledge of clinicians is affected by a wide range of shared and private big data resources, to reveal the impact of big data resources on clinical competence and professional development of clinicians.

Method

Through the comprehensive analysis of extant research results, big data resources are classified as big data itself, big data technology and big data services at the public and institutional levels. A survey was conducted on clinicians and IT personnel in Chinese hospitals. A total of 616 surveys are completed, involving 308 medical institutions. Each medical institution includes a clinician and an IT personnel. SmartPLS version 2.0 software package was used to test the direct impact of big data resources on the activation of prior knowledge. We further analyze their indirect impact of those big data resources without direct impact.

Results

(1) Big data quality environment at the institutional level and the big data sharing environment at the public level directly affect activation of prior medical knowledge; (2) Big data service environment at the institutional level directly affects activation of prior medical knowledge; (3) Big data deployment environment at the institutional level and big data service environment at the public level have no direct impact on activation of prior knowledge of clinicians, but they have an indirect impact through big data quality environment and service environment at the institutional level and the big data sharing environment at the public level.

Conclusions

Big data technology, big data itself and big data service at the public level and institutional level interact and influence each other to activate prior medical knowledge. This study highlights the implications of big data resources on improvement of clinicians’ diagnosis and treatment ability.

Research on Named Entity Recognition Method of Metro On-Board Equipment Based on Multiheaded Self-Attention Mechanism and CNN-BiLSTM-CRF

Massive and complex unstructured fault text data will be generated during the operation of subway trains. A named entity recognition model of subway on-board equipment based on Multiheaded Self-attention mechanism and CNN-BiLSTM-CRF is proposed to address the issue of low recognition accuracy and incomplete recognition features of unstructured fault data named entity recognition task of subway on-board equipment: BiLSTM-CNN parallel network extracts context feature information and local attention information, respectively; In the MHA layer, the features learned from different dimensions are fused through the Multiheaded Self-attention mechanism, and the dependencies of various ranges in the sequence are captured to yield the internal structure information of the features. The conditional random field CRF is used to learn the internal relationship between tags to ensure their sequence. This model is tested with other named entity recognition models on the marked subway on-board fault data. The experimental results demonstrate that this model is able to recognize 10 kinds of labels in the dataset. Moreover, the recognition effect of each label has a good performance in the three evaluation indexes of P, R, and F1 score. Moreover, the weighted average evaluation indexes Avg − P, Avg − R, and Avg − F₁ of 10 labels in this model reach the highest 95.39%, 95.48%, and 95.37%, which has high evaluation indexes and can be applied to the named entity recognition of Metro on-board equipment.

Extract, transform, load framework for the conversion of health databases to OMOP

Common data models standardize the structures and semantics of health datasets, enabling reproducibility and large-scale studies that leverage the data from multiple locations and settings. The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) is one of the leading common data models. While there is a strong incentive to convert datasets to OMOP, the conversion is time and resource-intensive, leaving the research community in need of tools for mapping data to OMOP. We propose an extract, transform, load (ETL) framework that is metadata-driven and generic across source datasets. The ETL framework uses a new data manipulation language (DML) that organizes SQL snippets in YAML. Our framework includes a compiler that converts YAML files with mapping logic into an ETL script. Access to the ETL framework is available via a web application, allowing users to upload and edit YAML files via web editor and obtain an ETL SQL script for use in development environments. The structure of the DML maximizes readability, refactoring, and maintainability, while minimizing technical debt and standardizing the writing of ETL operations for mapping to OMOP. Our framework also supports transparency of the mapping process and reuse by different institutions.

PercolationDF: A percolation-based medical diagnosis framework

Goal: With the continuing shortage and unequal distribution of medical resources, our objective is to develop a general diagnosis framework that utilizes a smaller amount of electronic medical records (EMRs) to alleviate the problem that the data volume requirement of prevailing models is too vast for medical institutions to afford. Methods: The framework proposed contains network construction, network expansion, and disease diagnosis methods. In the first two stages above, the knowledge extracted from EMRs is utilized to build and expense an EMR-based medical knowledge network (EMKN) to model and represent the medical knowledge. Then, percolation theory is modified to diagnose EMKN. Result: Facing the lack of data, our framework outperforms naïve Bayes networks, neural networks and logistic regression, especially in the top-10 recall. Out of 207 test cases, 51.7% achieved 100% in the top-10 recall, 21% better than what was achieved in one of our previous studies. Conclusion: The experimental results show that the proposed framework may be useful for medical knowledge representation and diagnosis. The framework effectively alleviates the lack of data volume by inferring the knowledge modeled in EMKN. Significance: The proposed framework not only has applications for diagnosis but also may be extended to other domains to represent and model the knowledge and inference on the representation.

Use of electronic medical records to describe the prevalence of allergic diseases in Canada

Background

Leveraging the data management resources of the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) is a viable approach for describing the prevalence of allergic disease documented in primary care settings.

Methods

The dataset used for this study was inclusive of data from EMR initiation up to Dec 31st 2018. The sample included 1235 primary care providers representing 1,556,472 patients across Canada.

Results

In total, there were 536,005 patients with a documented allergy that fit into one of the 10 suggested categories. The allergy table includes 718,032 distinct entries representing 564,242 unique patients, which is 36.3% of the patients within the CPCSSN repository. The most common allergies recorded were drug allergy (39.0%), beta-lactam allergy (14.4%), environmental allergy (11.0%), and food allergy (8.0%). Anticipated upcoming studies include physician-documented drug allergy with a focus on beta-lactam allergy, as well as stinging insect allergy, among others. To our knowledge, these will also be the first such prevalence studies of primary care physician-documented allergic disease done in Canada.

Interpretation

The CPCSSN dataset represents electronic medical records from 1.5 million patients across Canada including documentation of allergic diseases. This dataset provides a national representative population to describe and characterize Canadian patients with common allergic conditions. This robust dataset provides the opportunity for health surveillance, and in particular data to explore the impact of allergic disease on primary care practice.

Trial registration

Not applicable.

Teasing out Artificial Intelligence in Medicine: An Ethical Critique of Artificial Intelligence and Machine Learning in Medicine

The rapid adoption and implementation of artificial intelligence in medicine creates an ontologically distinct situation from prior care models. There are both potential advantages and disadvantages with such technology in advancing the interests of patients, with resultant ontological and epistemic concerns for physicians and patients relating to the instatiation of AI as a dependent, semi- or fully-autonomous agent in the encounter. The concept of libertarian paternalism potentially exercised by AI (and those who control it) has created challenges to conventional assessments of patient and physician autonomy. The unclear legal relationship between AI and its users cannot be settled presently, an progress in AI and its implementation in patient care will necessitate an iterative discourse to preserve humanitarian concerns in future models of care. This paper proposes that physicians should neither uncritically accept nor unreasonably resist developments in AI but must actively engage and contribute to the discourse, since AI will affect their roles and the nature of their work. One's moral imaginative capacity must be engaged in the questions of beneficence, autonomy, and justice of AI and whether its integration in healthcare has the potential to augment or interfere with the ends of medical practice.

Challenges Frequently Encountered in the Secondary Use of Electronic Medical Record Data for Research

The wide adoption of electronic medical records and subsequent availability of large amounts of clinical data provide a rich resource for researchers. However, the secondary use of clinical data for research purposes is not without limitations. In accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we conducted a systematic review to identify current issues related to secondary use of electronic medical record data via MEDLINE and CINAHL databases. All articles published until June 2018 were included. Sixty articles remained after title and abstract review, and four domains of potential limitations were identified: (1) data quality issues, present in 91.7% of the articles reviewed; (2) data preprocessing challenges (53.3%); (3) privacy concerns (18.3%); and (4) potential for limited generalizability (21.7%). Researchers must be aware of the limitations inherent to the use of electronic medical record data for research and consider the potential effects of these limitations throughout the entire study process, from initial conceptualization to the identification of adequate sources that can provide data appropriate for answering the research questions, analysis, and reporting study results. Consideration should also be given to using existing data quality assessment frameworks to facilitate use of standardized data quality definitions and further efforts of standard data quality reporting in publications.

Chinese Clinical Named Entity Recognition in Electronic Medical Records: Development of a Lattice Long Short-Term Memory Model With Contextualized Character Representations

BACKGROUND

Clinical named entity recognition (CNER), whose goal is to automatically identify clinical entities in electronic medical records (EMRs), is an important research direction of clinical text data mining and information extraction. The promotion of CNER can provide support for clinical decision making and medical knowledge base construction, which could then improve overall medical quality. Compared with English CNER, and due to the complexity of Chinese word segmentation and grammar, Chinese CNER was implemented later and is more challenging.

OBJECTIVE

With the development of distributed representation and deep learning, a series of models have been applied in Chinese CNER. Different from the English version, Chinese CNER is mainly divided into character-based and word-based methods that cannot make comprehensive use of EMR information and cannot solve the problem of ambiguity in word representation.

METHODS

In this paper, we propose a lattice long short-term memory (LSTM) model combined with a variant contextualized character representation and a conditional random field (CRF) layer for Chinese CNER: the Embeddings from Language Models (ELMo)-lattice-LSTM-CRF model. The lattice LSTM model can effectively utilize the information from characters and words in Chinese EMRs; in addition, the variant ELMo model uses Chinese characters as input instead of the character-encoding layer of the ELMo model, so as to learn domain-specific contextualized character embeddings.

RESULTS

We evaluated our method using two Chinese CNER datasets from the China Conference on Knowledge Graph and Semantic Computing (CCKS): the CCKS-2017 CNER dataset and the CCKS-2019 CNER dataset. We obtained F1 scores of 90.13% and 85.02% on the test sets of these two datasets, respectively.

CONCLUSIONS

Our results show that our proposed method is effective in Chinese CNER. In addition, the results of our experiments show that variant contextualized character representations can significantly improve the performance of the model.

Data extraction for epidemiological research (DExtER): a novel tool for automated clinical epidemiology studies

The use of primary care electronic health records for research is abundant. The benefits gained from utilising such records lies in their size, longitudinal data collection and data quality. However, the use of such data to undertake high quality epidemiological studies, can lead to significant challenges particularly in dealing with misclassification, variation in coding and the significant effort required to pre-process the data in a meaningful format for statistical analysis. In this paper, we describe a methodology to aid with the extraction and processing of such databases, delivered by a novel software programme; the "Data extraction for epidemiological research" (DExtER). The basis of DExtER relies on principles of extract, transform and load processes. The tool initially provides the ability for the healthcare dataset to be extracted, then transformed in a format whereby data is normalised, converted and reformatted. DExtER has a user interface designed to obtain data extracts specific to each research question and observational study design. There are facilities to input the requirements for; eligible study period, definition of exposed and unexposed groups, outcome measures and important baseline covariates. To date the tool has been utilised and validated in a multitude of settings. There have been over 35 peer-reviewed publications using the tool, and DExtER has been implemented as a validated public health surveillance tool for obtaining accurate statistics on epidemiology of key morbidities. Future direction of this work will be the application of the framework to linked as well as international datasets and the development of standardised methods for conducting electronic pre-processing and extraction from datasets for research purposes.

Education and Training on Electronic Medical Records (EMRs) for health care professionals and students: A Scoping Review

BACKGROUND AND OBJECTIVES

The ability of health care providers and students to use EMRs efficiently can lead to achieving improved clinical outcomes. Training policies and strategies play a major role in successful technology implementation and ongoing use of the EMR systems. To provide evidence-based guidance for developing and implementing educational interventions and training, we reviewed and summarized the current literature on EMR training targeting both healthcare professionals (HCP) and students.

METHODS

We used the Joanna Briggs Institute (JBI) approach for scoping reviews and the PRISMA extension of scoping reviews (PRISMA-ScR) checklist for reporting our review. 46 full-text articles that met the eligibility criteria were selected for the review. Narrative synthesis was performed to summarize the evidence using numerical and descriptive analysis. We used inductive content analysis for categorizing the training methods. Also, the modified version of the Kirkpatrick's levels model was used for abstracting the training outcome.

RESULTS

Five types of training methods were identified: one-on-one training, peer-coach training, classroom training (CRT), computer-based training (CBT), and blended training. A variety of CBT platforms were used, including a prototype academic electronic medical record system (AEMR), AEMR/simulated EMR (Sim-EMR), mobile based AEMR, eLearning, and electronic educational materials. Each training intervention could have resulted in several outcomes. Most outcomes were related to levels 1-3 of the Kirkpatrick model that involves learners (n = 108), followed by level 4a that involves organizations (n = 7), and lastly level 4b that involves patients (n = 1). The outcomes related to participants' knowledge (level 2b) was the most often measured training outcome (n = 44).

CONCLUSIONS

This review presents a comprehensive synthesis of the evidence on EMR training. A variety of training methods, participants, locations, strategies, and outcomes were described in the studies. Training should be aligned with the particular training needs, training objectives, EMR system utilized, and organizational environment. A training plan should include an overall goal and SMART (Specific, Measurable, Achievable, Realistic, Tangible) training objectives, that would allow a more rigorous evaluation of the training outcomes.

Improving the Named Entity Recognition of Chinese Electronic Medical Records by Combining Domain Dictionary and Rules

Electronic medical records are an integral part of medical texts. Entity recognition of electronic medical records has triggered many studies that propose many entity extraction methods. In this paper, an entity extraction model is proposed to extract entities from Chinese Electronic Medical Records (CEMR). In the input layer of the model, we use word embedding and dictionary features embedding as input vectors, where word embedding consists of a character representation and a word representation. Then, the input vectors are fed to the bidirectional long short-term memory to capture contextual features. Finally, a conditional random field is employed to capture dependencies between neighboring tags. We performed experiments on body classification task, and the F1 values reached 90.65%. We also performed experiments on anatomic region recognition task, and the F1 values reached 93.89%. On both tasks, our model had higher performance than state-of-the-art models, such as Bi-LSTM-CRF, Bi-LSTM-Attention, and Vote. Through experiments, our model has a good effect when dealing with small frequency entities and unknown entities; with a small training dataset, our method showed 2–4% improvement on F1 value compared to the basic Bi-LSTM-CRF models. Additionally, on anatomic region recognition task, besides using our proposed entity extraction model, 12 rules we designed and domain dictionary were adopted. Then, in this task, the weighted F1 value of the three specific entities extraction reached 84.36%.

Towards Reliable ARDS Clinical Decision Support: ARDS Patient Analytics with Free-text and Structured EMR Data

In this work, we utilize a combination of free-text and structured data to build Acute Respiratory Distress Syndrome(ARDS) prediction models and ARDS phenotype clusters. We derived 'Patient Context Vectors' representing patientspecific contextual ARDS risk factors, utilizing deep-learning techniques on ICD and free-text clinical notes data. The Patient Context Vectors were combined with structured data from the first 24 hours of admission, such as vital signs and lab results, to build an ARDS patient prediction model and an ARDS patient mortality prediction model achieving AUC of 90.16 and 81.01 respectively. The ability of Patient Context Vectors to summarize patients' medical history and current conditions is also demonstrated by the automatic clustering of ARDS patients into clinically meaningful phenotypes based on comorbidities, patient history, and presenting conditions. To our knowledge, this is the first study to successfully combine free-text and structured data, without any manual patient risk factor curation, to build real-time ARDS prediction models.

Medical Named Entity Extraction from Chinese Resident Admit Notes Using Character and Word Attention-Enhanced Neural Network

The resident admit notes (RANs) in electronic medical records (EMRs) is first-hand information to study the patient’s condition. Medical entity extraction of RANs is an important task to get disease information for medical decision-making. For Chinese electronic medical records, each medical entity contains not only word information but also rich character information. Effective combination of words and characters is very important for medical entity extraction. We propose a medical entity recognition model based on a character and word attention-enhanced (CWAE) neural network for Chinese RANs. In our model, word embeddings and character-based embeddings are obtained through character-enhanced word embedding (CWE) model and Convolutional Neural Network (CNN) model. Then attention mechanism combines the character-based embeddings and word embeddings together, which significantly improves the expression ability of words. The new word embeddings obtained by the attention mechanism are taken as the input to bidirectional long short-term memory (BI-LSTM) and conditional random field (CRF) to extract entities. We extracted nine types of key medical entities from Chinese RANs and evaluated our model. The proposed method was compared with two traditional machine learning methods CRF, support vector machine (SVM), and the related deep learning models. The result shows that our model has better performance, and the result of our model reaches 94.44% in the F1-score.

Perceptions of allied health staff of the implementation of an integrated electronic medical record across regional and metropolitan settings

ObjectiveThe aim of this study was to investigate the perceptions of allied health professionals (AHPs) to implementation of an integrated electronic medical record (EMR) across both regional and metropolitan settings. MethodsThe study was conducted as a cross-sectional electronic survey. AHPs working at three hospital sites within Queensland Health were sent an electronic survey link. Participation was voluntary and recruitment via a snowball sampling technique was encouraged. Responses were analysed descriptively. ResultsIn all, 104 responders completed the survey. Responders were distributed across three sites within the selected health service, with most (75%; n=78) being at the largest site. Physiotherapy accounted for the largest number of responders (22%). Most responders were female (87%; n=90) and between 20 and 40 years of age (68%; n=71). On a scale from 0 (being anxious) to 100 (being excited), at the time EMR implementation was announced, there was a trend towards excitement (mean score 59). The most commonly reported factor hindering EMR implementation was the opportunity to practice with EMR (34%), whereas clinical ‘change champions’ were reported as the most common facilitators (61%). Overall, 60% of responders were very satisfied or satisfied with the EMR, but limited effects on efficiency and patient care were reported. ConclusionsThe results suggest an overall positive response to EMR implementation. Minimal staff reported effects such as stress or anxiety in the workplace related to EMR implementation, and a perception of ‘comfort’ was cited once EMR was part of usual practice. However, responders did not report a significant effect on speed, efficiency or quality of patient care following EMR implementation. What is known about the topic?A growing body of literature exists regarding the perceptions of staff (particularly medical officers) in moving towards EMRs, but there is limited evidence regarding the perceptions of AHPs, and the barriers and facilitators to this change. What does this paper add?This paper presents a novel perspective regarding the perceptions of AHPs regarding the implementation of an EMR and provides a perspective of the barriers and facilitators that supported a smooth transition at three sites. What are the implications for practitioners?Despite being a large-scale service change, the introduction of an EMR did not significantly increase AHPs’ subjective feelings of anxiety. Services considering EMR implementation should invest in the provision of timely information, ‘at-elbow’ support and opportunities to practice the new system.

Identifying the "Blip on the Radar Screen": Leveraging Big Data in Defining Drug Safety and Efficacy in Pediatric Practice

The immense amount of electronic health data (pharmacy and administrative claims, electronic health records, and clinical registries) that is being generated every day in the care of patients has the potential to be leveraged for improving clinical decisions at the point of care, uncovering or validating drug efficacy and drug safety. The potential use of big data for improving safe and effective use of medications is especially important in children because of their low drug exposure relative to adults. Electronic health data is collected primarily for clinical or billing purposes and not for research purposes. The major steps involved in data acquisition, extraction, aggregation, analysis, modeling, and interpretation are discussed. It is important to understand the limitation of big data and utilize appropriate study design and statistical methods. Possible applications are presented along with specific examples of how big data has been used in drug research to find that blip on the radar screen that may give an efficacy or safety signal that can lead to further investigation.

Epidemiology of Pulmonary Fibrosis: A Cohort Study Using Healthcare Data in Sweden

Introduction

Data on the epidemiology of idiopathic pulmonary fibrosis (IPF) in Sweden are lacking. This study estimates the incidence and prevalence of IPF in Sweden, and describes the demographic and clinical characteristics and the overall survival of patients with IPF.

Methods

Two cohorts were studied: a national cohort of 17,247 patients with pulmonary fibrosis (ICD-10 code J84.1 with no competing diagnosis) from the Swedish National Patient Register (cohort 1 [C1]); and an electronic medical record-based regional subset of C1 comprising 1755 patients having pulmonary fibrosis and a radiology procedure (C2).

Results

The incidence of pulmonary fibrosis in C1 ranged from 10.4 to 15.4 cases per 100,000 population per year between 2001 and 2015. The prevalence increased from 15.4 to 68.0 cases per 100,000 population per year. Patients ≥ 70 years and men had a higher incidence and prevalence of pulmonary fibrosis. Common comorbidities included respiratory infections and cardiovascular disorders. Approximately one-third of patients in each cohort were hospitalised with pulmonary fibrosis within a year of diagnosis. The median survival time from disease diagnosis was 2.6 years in C1 and 5.2 years in C2. Older patients had a higher risk of hospitalisation and mortality. Women had a better prognosis than men.

Conclusion

This study underscores the importance of pulmonary fibrosis as a cause of respiratory-related morbidity and mortality in Sweden. The stable incidence and increasing prevalence over time suggests longer survival. The higher morbidity and mortality in older patients highlights the importance of early case detection, diagnosis and management for better prognosis.

Funding

F. Hoffmann-La Roche, Ltd./Genentech, Inc.

Electronic supplementary material

The online version of this article (10.1007/s41030-019-0087-9) contains supplementary material, which is available to authorized users.

Data electronically extracted from the electronic health record require validation

OBJECTIVES

Determine sources of error in electronically extracted data from electronic health records.

STUDY DESIGN

Categorical and continuous variables related to early-onset neonatal hypoglycemia were preselected and electronically extracted from records of 100 randomly selected neonates within 3479 births with laboratory-proven early-onset hypoglycemia. Extraction language was written by an information technologist and data validated by blinded manual chart review. Kappa coefficient assessed categorical variables and percent validity continuous variables.

RESULTS

8/23 (35%) categorical variables had acceptable Κappa (1-0.81); 5/23 (22%) had fair-slight agreement, Κappa < 0.40. Notably, "hypoglycemia" had poor agreement, Κappa 0.16. In contrast, 6/8 continuous variables had validity ≥ 94%. After correcting extraction language, 6/9 variables were corrected and inter-rater validation improved. However, "hypoglycemia" was not corrected, remaining an issue.

CONCLUSIONS

Data extraction without validation procedures, especially categorical variables using International Classification of Diseases-9 (ICD-9) codes, often results in incorrect data identification. Electronically extracted data must incorporate built-in validating processes.

Satisfaction and perceived usefulness with newly-implemented Electronic Health Records System among pediatricians at a university hospital

BACKGROUND

Apposite implementation of Electronic Health Records (EHR) is anchoring standards of care in healthcare settings by reducing long-run operational costs, improving healthcare quality, and enhancing patient safety.

OBJECTIVE

This study aims to explore factors that might influence Pediatricians' satisfaction with an implemented EHR system and its perceived usefulness at a tertiary-care teaching hospital, Riyadh, Saudi Arabia.

METHODS

A cross-sectional survey distributed to all physicians working in the pediatric department of King Saud University Medical City (KSUMC) in the period from June to November 2015, two months after the launch of the EHR system, internally branded as electronic system for integrated health information (eSiHi). Bivariate and multivariate regression were analyzed to examine factors associated with physicians' satisfaction.

RESULTS

Of the 112 physicians who completed the survey, 97 (86.6%) attended training courses before the implementation of new EHR. On average, the participants rated the perceived usefulness of the new system at 6.4/10 for patient care and physicians' satisfaction levels were 5.2/10. The top indicator of EHR usefulness was the system's ability to reduce errors and improve the quality of care [mean 3.31, SD 0.9, RII 82.8%]; the lowest-ranking indicator was the physicians' perceived familiarity with functions and benefits [mean 2.68, SD 0.7, RII 67%]. The top indicator of satisfaction with the EHR system was enhanced "individual performance" [mean 3.04, SD 1, RII 60.9%]; the lowest-ranking perceived indicator was the limited availability of workplace computers [mean 1.91, SD 1.2, RII 38.2%].

CONCLUSIONS

Limited data regarding EHR implementation and end-users satisfaction in the Middle East region necessitates further work on factors affecting levels of satisfaction with the EHR system among different health institutes. Lack of information technology (IT) support, hardware, and time-consuming data entry process are challenging barriers for proper utilization of EHR for pediatric health care services.

Diversity in the emergency care for febrile children in Europe: a questionnaire study

OBJECTIVE

To provide an overview of care in emergency departments (EDs) across Europe in order to interpret observational data and implement interventions regarding the management of febrile children.

DESIGN AND SETTING

An electronic questionnaire was sent to the principal investigators of an ongoing study (PERFORM (Personalised Risk assessment in Febrile illness to Optimise Real-life Management), www.perform2020.eu) in 11 European hospitals in eight countries: Austria, Germany, Greece, Latvia, the Netherlands, Slovenia, Spain and the UK.

OUTCOME MEASURES

The questionnaire covered indicators in three domains: local ED quality (supervision, guideline availability, paper vs electronic health records), organisation of healthcare (primary care, immunisation), and local factors influencing or reflecting resource use (availability of point-of-care tests, admission rates).

RESULTS

Reported admission rates ranged from 4% to 51%. In six settings (Athens, Graz, Ljubljana, Riga, Rotterdam, Santiago de Compostela), the supervising ED physicians were general paediatricians, in two (Liverpool, London) these were paediatric emergency physicians, in two (Nijmegen, Newcastle) supervision could take place by either a general paediatrician or a general emergency physician, and in one (München) this could be either a general paediatrician or a paediatric emergency physician. The supervising physician was present on site in all settings during office hours and in five out of eleven settings during out-of-office hours. Guidelines for fever and sepsis were available in all settings; however, the type of guideline that was used differed. Primary care was available in all settings during office hours and in eight during out-of-office hours. There were differences in routine immunisations as well as in additional immunisations that were offered; immunisation rates varied between and within countries.

CONCLUSION

Differences in local, regional and national aspects of care exist in the management of febrile children across Europe. This variability has to be considered when trying to interpret differences in the use of diagnostic tools, antibiotics and admission rates. Any future implementation of interventions or diagnostic tests will need to be aware of this European diversity.

Presenting predictors and temporal trends of treatment-related outcomes in diabetic ketoacidosis

OBJECTIVE

This study examines temporal trends in treatment-related outcomes surrounding a diabetic ketoacidosis (DKA) performance improvement intervention consisting of mandated intensive care unit admission and implementation of a standardized management pathway, and identifies physical and biochemical characteristics associated with outcomes in this population.

METHODS

A retrospective cohort of 1225 children with DKA were identified in the electronic health record by international classification of diseases codes and a minimum pH less than 7.3 during hospitalization at a quaternary children's hospital between April, 2009 and May, 2016. Multivariable regression examined predictors and trends of hypoglycemia, central venous line placement, severe hyperchloremia, head computed tomography (CT) utilization, treated cerebral edema and hospital length of stay (LOS).

RESULTS

The incidence of severe hyperchloremia and head CT utilization decreased during the study period. Among patients with severe DKA (presenting pH < 7.1), the intervention was associated with decreasing LOS and less variability in LOS. Lower pH at presentation was independently associated with increased risk for all outcomes except hypoglycemia, which was associated with higher pH. Patients treated for cerebral edema had a lower presenting mean systolic blood pressure z score (0.58 [95% confidence interval (CI) -0.02-1.17] vs 1.23 [1.13-1.33]) and a higher maximum mean systolic blood pressure (SBP) z score during hospitalization (3.75 [3.19-4.31] vs 2.48 [2.38-2.58]) compared to patients not receiving cerebral edema treatment. Blood pressure and cerebral edema remained significantly associated after covariate adjustment.

CONCLUSION

Treatment-related outcomes improved over the entire study period and following a performance improvement intervention. The association of SBP with cerebral edema warrants further study.

Developmental Disorders and Medical Complications Among Infants with Subclinical Intrauterine Opioid Exposures

The objective was to compare diagnosis rates representing developmental outcomes and medical complications between infants with intrauterine opioid exposures who did not receive pharmacologic treatment for neonatal abstinence syndrome at the time of birth and infants for whom no exposure to substances of abuse were detected. This retrospective, descriptive study included approximately 95% of Hamilton County, Ohio resident births in 2014 and 2015. Universal maternal drug test results, performed at the time of birth, were documented and linked to electronic health records representing pediatric primary and subspecialty follow-up care as well as urgent care, emergency care, and inpatient services provided by Cincinnati Children's Hospital Medical Center through 2017, when all children were at least 24 months old. Diagnosis rates were compared between drug exposure groups using chi-square tests. Among infants born at >34 weeks gestation and without other complex clinical conditions, infants with subclinical opioid exposures (N = 473) were more likely than infants with no drug exposures (N = 14,933) to be diagnosed with behavioral or emotional disorders (3.0% vs 1.1%, P = 0.0008), developmental delay (15.6% vs 7.6%, P < 0.0001), speech disorder (10.1% vs 6.5%, P = 0.001), or strabismus (3.4% vs 1.0%, P < 0.0001), and more likely to be exposed to the hepatitis C virus (6.8% vs 0.1%, P < 0.0001). Increased diagnosis rates among all opioid exposed infants, regardless of withdrawal severity, may warrant the additional allocation of resources for screening and follow-up. Awareness of the increased risk for certain developmental delays and medical conditions is critical to early intervention and treatment supporting improved outcomes.

Is It Feasible to Use Electronic Health Records for Quality Measurement of Adolescent Care?

OBJECTIVE

To determine the extent to which it is feasible to implement quality measures on electronic health records (EHRs) as currently implemented in pediatric health centers.

METHODS

A survey of information technology professionals at 10 institutions that provide primary care services to adolescents. The survey asked whether data about care was being captured electronically across the nine domains relevant to adolescent well care: Screening, Health Risks, Sexual Health, Diagnosis and History, Laboratory Results, Prescriptions, Referrals, Forms Management, and Patient Demographics. For each domain, we developed a scale of the extent to which the EHR makes quality measurement feasible.

RESULTS

Overall feasibility scores varied across centers from 34% to 85% and from 53% to 80% across care domains. One centre reported 100% feasibility for 8 of 10 care domains.

CONCLUSIONS

Electronic health records can facilitate quality improvement, but the feasibility of such use depends on the presence, validity, and accessibility of the quality data in the EHR. Even among the largest and most sophisticated pediatric EHR systems, quality of care measurement is not possible yet for all aspects of adolescent well care without manual effort to review and code data. Nevertheless, almost all quality measures were reported to be feasible in some systems.

Skin colour assessment of replanted fingers in digital images and its reliability for the incorporation of images in nursing progress notes

AIMS AND OBJECTIVES

To determine whether nurses can accurately assess the skin colour of replanted fingers displayed as digital images on a computer screen.

BACKGROUND

Colour measurement and clinical diagnostic methods for medical digital images have been studied, but reproducing skin colour on a computer screen remains difficult.

DESIGN

The inter-rater reliability of skin colour assessment scores was evaluated. In May 2014, 21 nurses who worked on a trauma ward in Japan participated in testing.

METHODS

Six digital images with different skin colours were used. Colours were scored from both digital images and direct patient's observation. The score from a digital image was defined as the test score, and its difference from the direct assessment score as the difference score. Intraclass correlation coefficients were calculated. Nurses' opinions were classified and summarised.

RESULTS

The intraclass correlation coefficients for the test scores were fair. Although the intraclass correlation coefficients for the difference scores were poor, they improved to good when three images that might have contributed to poor reliability were excluded. Most nurses stated that it is difficult to assess skin colour in digital images; they did not think it could be a substitute for direct visual assessment. However, most nurses were in favour of including images in nursing progress notes.

DISCUSSION

Although the inter-rater reliability was fairly high, the reliability of colour reproduction in digital images as indicated by the difference scores was poor. Nevertheless, nurses expect the incorporation of digital images in nursing progress notes to be useful. This gap between the reliability of digital colour reproduction and nurses' expectations towards it must be addressed.

CONCLUSIONS

High inter-rater reliability for digital images in nursing progress notes was not observed. Assessments of future improvements in colour reproduction technologies are required.

RELEVANCE TO CLINICAL PRACTICE

Further digitisation and visualisation of nursing records might pose challenges.

Challenges in Using Real-world Clinical Practice Records for Validation of Clinical Trial Data in Inflammatory Bowel Disease: Lessons Learned

Electronic medical records (EMRs) have gained widespread use in clinical practice and by default serve as a large patient database with potential for use in clinical research. Although there remains significant interest in leveraging EMRs for research purposes, extraction of data has proven to be complex and with insufficient accuracy. We describe the limitations of an EMR in our attempt to conduct a seemingly simple study aimed at validating variables identified in the PRECiSE 3, a 7-year open label safety and efficacy study of certolizumab pegol in Crohn's disease that identified clinical factors that predicted both short- and long-term efficacy. A multicenter, retrospective cohort study from 8 academic and large community practices was performed, and data were collected from each respective EMR. Significant challenges with reliable capture of key data elements were encountered, and overall a screen fail rate of 91.8% across all sites was seen. We describe these challenges and potential future directions to work together to advance accuracy and implementation of the use of EMRs in inflammatory bowel disease.

A cloud-based framework for large-scale traditional Chinese medical record retrieval

INTRODUCTION

Electronic medical records are increasingly common in medical practice. The secondary use of medical records has become increasingly important. It relies on the ability to retrieve the complete information about desired patient populations. How to effectively and accurately retrieve relevant medical records from large- scale medical big data is becoming a big challenge. Therefore, we propose an efficient and robust framework based on cloud for large-scale Traditional Chinese Medical Records (TCMRs) retrieval.

METHODS

We propose a parallel index building method and build a distributed search cluster, the former is used to improve the performance of index building, and the latter is used to provide high concurrent online TCMRs retrieval. Then, a real-time multi-indexing model is proposed to ensure the latest relevant TCMRs are indexed and retrieved in real-time, and a semantics-based query expansion method and a multi- factor ranking model are proposed to improve retrieval quality. Third, we implement a template-based visualization method for displaying medical reports.

RESULTS

The proposed parallel indexing method and distributed search cluster can improve the performance of index building and provide high concurrent online TCMRs retrieval. The multi-indexing model can ensure the latest relevant TCMRs are indexed and retrieved in real-time. The semantics expansion method and the multi-factor ranking model can enhance retrieval quality. The template-based visualization method can enhance the availability and universality, where the medical reports are displayed via friendly web interface.

CONCLUSIONS

In conclusion, compared with the current medical record retrieval systems, our system provides some advantages that are useful in improving the secondary use of large-scale traditional Chinese medical records in cloud environment. The proposed system is more easily integrated with existing clinical systems and be used in various scenarios.

From hospitalization records to surveillance: The use of local patient profiles to characterize cholera in Vellore, India

Despite availability of high quality medical records, health care systems often do not have the resources or tools to utilize these data efficiently. Yet, hospital-based, laboratory-confirmed records may pave the way for building reliable surveillance systems capable of monitoring temporal trends of emerging infections. In this communication, we present a new tool to compress and visualize medical records with a local population profile (LPP) approach, which transforms information into statistically comparable patterns. We provide a step-by-step tutorial on how to build, interpret, and expand the use of LPP using hospitalization records of laboratory-confirmed cholera. We abstracted case information from the databases maintained by the Department of Clinical Microbiology at Christian Medical College in Vellore, India. We used a single-year age distribution to construct LPPs for O1, O139, and non O1/O139 serotypes of Vibrio cholerae. Disease counts and hospitalization rates were converted into fitted kernel-based probability densities. We formally compared LPPs with the Kolmogorov-Smirnov test, and created multi-panel visuals to depict temporal trend, age distribution, and hospitalization rates simultaneously. Our first implementation of LPPs revealed information that is typically gathered from surveillance systems such as: i) estimates of the demographic distribution of diseases and identification of a population at risk, ii) changes in the dominant pathogen presence; and iii) trends in disease occurrence. The LPP demonstrated the benefit of increased resolution in pattern detection of disease for different Vibrio cholerae serotypes and two demographic categories by showing patterns and anomalies that would be obscured by traditional methods of analysis and visualization. LPP can be used effectively to compile basic patient information such as age, sex, diagnosis, location, and time into compact visuals. Future development of the proposed approach will allow public health researchers and practitioners to broadly utilize and efficiently compress large volumes of medical records without loss of information.

Extracting autism spectrum disorder data from the electronic health record

BACKGROUND

Little is known about the health care utilization patterns of individuals with pediatric autism spectrum disorder (ASD).

OBJECTIVES

Electronic health record (EHR) data provide an opportunity to study medical utilization and track outcomes among children with ASD.  Methods: Using a pediatric, tertiary, academic hospital's Epic EHR, search queries were built to identify individuals aged 2-18 with International Classification of Diseases, Ninth Revision (ICD-9) codes, 299.00, 299.10, and 299.80 in their records. Codes were entered in the EHR using four different workflows: (1) during an ambulatory visit, (2) abstracted by Health Information Management (HIM) for an encounter, (3) recorded on the patient problem list, or (4) added as a chief complaint during an Emergency Department visit. Once individuals were identified, demographics, scheduling, procedures, and prescribed medications were extracted for all patient-related encounters for the period October 2010 through September 2012.

RESULTS

There were 100,000 encounters for more than 4,800 unique individuals. Individuals were most frequently identified with an HIM abstracted code (82.6%) and least likely to be identified by a chief complaint (45.8%). Categorical frequency for reported race (2 = 816.5, p < 0.001); payor type (2 = 354.1, p < 0.001); encounter type (2 = 1497.0, p < 0.001); and department (2 = 3722.8, p < 0.001) differed by search query. Challenges encountered included, locating available discrete data elements and missing data.

CONCLUSIONS

This study identifies challenges inherent in designing inclusive algorithms for identifying individuals with ASD and demonstrates the utility of employing multiple extractions to improve the completeness and quality of EHR data when conducting research.

A study of EMR-based medical knowledge network and its applications

BACKGROUND AND OBJECTIVE

Electronic medical records (EMRs) contain an amount of medical knowledge which can be used for clinical decision support. We attempt to integrate this medical knowledge into a complex network, and then implement a diagnosis model based on this network.

METHODS

The dataset of our study contains 992 records which are uniformly sampled from different departments of the hospital. In order to integrate the knowledge of these records, an EMR-based medical knowledge network (EMKN) is constructed. This network takes medical entities as nodes, and co-occurrence relationships between the two entities as edges. Selected properties of this network are analyzed. To make use of this network, a basic diagnosis model is implemented. Seven hundred records are randomly selected to re-construct the network, and the remaining 292 records are used as test records. The vector space model is applied to illustrate the relationships between diseases and symptoms. Because there may exist more than one actual disease in a record, the recall rate of the first ten results, and the average precision are adopted as evaluation measures.

RESULTS

Compared with a random network of the same size, this network has a similar average length but a much higher clustering coefficient. Additionally, it can be observed that there are direct correlations between the community structure and the real department classes in the hospital. For the diagnosis model, the vector space model using disease as a base obtains the best result. At least one accurate disease can be obtained in 73.27% of the records in the first ten results.

CONCLUSION

We constructed an EMR-based medical knowledge network by extracting the medical entities. This network has the small-world and scale-free properties. Moreover, the community structure showed that entities in the same department have a tendency to be self-aggregated. Based on this network, a diagnosis model was proposed. This model uses only the symptoms as inputs and is not restricted to a specific disease. The experiments conducted demonstrated that EMKN is a simple and universal technique to integrate different medical knowledge from EMRs, and can be used for clinical decision support.

Research on Clinical Preventive Services for Adolescents and Young Adults: Where Are We and Where Do We Need to Go?

We reviewed research regarding system- and visit-level strategies to enhance clinical preventive service delivery and quality for adolescents and young adults. Despite professional consensus on recommended services for adolescents, a strong evidence base for services for young adults, and improved financial access to services with the Affordable Care Act's provisions, receipt of preventive services remains suboptimal. Further research that builds off successful models of linking traditional and community clinics is needed to improve access to care for all youth. To optimize the clinical encounter, promising clinician-focused strategies to improve delivery of preventive services include screening and decision support tools, particularly when integrated into electronic medical record systems and supported by training and feedback. Although results have been mixed, interventions have moved beyond increasing service delivery to demonstrating behavior change. Research on emerging technology-such as gaming platforms, mobile phone applications, and wearable devices-suggests opportunities to expand clinicians' reach; however, existing research is based on limited clinical settings and populations. Improved monitoring systems and further research are needed to examine preventive services facilitators and ensure that interventions are effective across the range of clinical settings where youth receive preventive care, across multiple populations, including young adults, and for more vulnerable populations with less access to quality care.

Use of electronic health records by child primary healthcare providers in Europe

BACKGROUND

There is limited data on the use and functionality level of electronic health records (EHRs) supporting primary child health care in Europe. Our objective was to determine European primary child healthcare providers' use of EHRs, and functionality level of the systems used.

METHODS

European primary care paediatricians, paediatric subspecialists and family doctors were invited by European Academy of Paediatrics Research in Ambulatory Setting Network (EAPRASnet) country coordinators to complete a web-based survey on the use of EHRs and the systems' functionalities. Binomial logistic analysis has been used to evaluate the effect of specialty and type of practice on the use of EHRs.

RESULTS

The survey was completed by 679 child primary healthcare providers (response rate 53%). Five hundred and fifty four responses coming from 10 predominant countries were taken for further analysis. EHR use by respondents varied widely between countries, all electronic type use ranging between 7% and 97%. There was no significant difference in EHR use between group practice and solo practitioners, or between family doctors and primary care paediatricians. History and physical examination can be properly recorded by respondents in most countries. However, growth chart plotting capacity in some countries ranges between 22% and 50%. Vaccination recording capacity varies between 50% and 100%, and data exchange capacity with immunization databases is mostly limited, ranging between 0% and 54%.

CONCLUSIONS

There is marked heterogeneity in the use and functionalities of EHRs used among child primary child healthcare providers in Europe. More importantly, lack of critical paediatric supportive functionalities like growth tracking and vaccination status has been documented in some countries. There is a need to explore the reasons for these findings, and to develop a cross European paediatric EHR standards.

Quality of administrative health databases in Canada: A scoping review

OBJECTIVE

Administrative health databases are increasingly used to conduct population-based health research and surveillance; this has resulted in a corresponding growth in studies about their quality. Our objective was to describe the characteristics of published Canadian studies about administrative health database quality.

METHODS

PubMed, Scopus, and Google Advanced were searched, along with websites of relevant organizations. English-language studies that evaluated the quality of one or more Canadian administrative health databases between 2004 and 2014 were selected for inclusion. Extracted information included data quality concepts and measures, year and type of publication, type of database, and geographic origin.

SYNTHESIS

More than 3,000 publications were identified fromthe search. Twelve reports and 144 peer-reviewed papers were included. The majority (53.5%) of peer-review publications used databases from Ontario and Alberta, while 67% of the non-peer-review publications used data from multiple provinces/ territories. Almost all peer-reviewed papers (97.2%) were validation studies. Hospital discharge abstracts and physician billing claims were the most frequently validated databases. Approximately half of the publications (53.0%) validated case definitions and 37.7% focused on a chronic physical health condition.

CONCLUSION

Gaps in the Canadian administrative data quality literature include a limited number of studies evaluating data from the Maritimes and across multiple jurisdictions, newer data sources, validating methods for identifying individuals with mental illness, and assessing the completeness and serviceability of the data. Data quality studies can aid researchers to understand the strengths and limitations of the data.

Quality of EHR data extractions for studies of preterm birth in a tertiary care center: guidelines for obtaining reliable data

BACKGROUND

The use of Electronic Health Records (EHR) has increased significantly in the past 15 years. This study compares electronic vs. manual data abstractions from an EHR for accuracy. While the dataset is limited to preterm birth data, our work is generally applicable. We enumerate challenges to reliable extraction, and state guidelines to maximize reliability.

METHODS

An Epic™ EHR data extraction of structured data values from 1,772 neonatal records born between the years 2001-2011 was performed. The data were directly compared to a manually-abstracted database. Specific data values important to studies of perinatology were chosen to compare discrepancies between the two databases.

RESULTS

Discrepancy rates between the EHR extraction and the manual database were calculated for gestational age in weeks (2.6 %), birthweight (9.7 %), first white blood cell count (3.2 %), initial hemoglobin (11.9 %), peak total and direct bilirubin (11.4 % and 4.9 %), and patent ductus arteriosus (PDA) diagnosis (12.8 %). Using the discrepancies, errors were quantified in both datasets using chart review. The EHR extraction errors were significantly fewer than manual abstraction errors for PDA and laboratory values excluding neonates transferred from outside hospitals, but significantly greater for birth weight. Reasons for the observed errors are discussed.

CONCLUSIONS

We show that an EHR not modified specifically for research purposes had discrepancy ranges comparable to a manually created database. We offer guidelines to minimize EHR extraction errors in future study designs. As EHRs become more research-friendly, electronic chart extractions should be more efficient and have lower error rates compared to manual abstractions.

Electronic Health Record-Enabled Research in Children Using the Electronic Health Record for Clinical Discovery

Initially described more than 50 years ago, electronic health records (EHRs) are now becoming ubiquitous throughout pediatric health care settings. The confluence of increased EHR implementation and the exponential growth of digital data within them, the development of clinical informatics tools and techniques, and the growing workforce of experienced EHR users presents new opportunities to use EHRs to augment clinical discovery and improve pediatric patient care. This article reviews the basic concepts surrounding EHR-enabled research and clinical discovery, including the types and fidelity of EHR data elements, EHR data validation/corroboration, and the steps involved in analytical interrogation.

Development of a large urban longitudinal HIV clinical cohort using a web-based platform to merge electronically and manually abstracted data from disparate medical record systems: technical challenges and innovative solutions

OBJECTIVE

Electronic medical records (EMRs) are being increasingly utilized to conduct clinical and epidemiologic research in numerous fields. To monitor and improve care of HIV-infected patients in Washington, DC, one of the most severely affected urban areas in the United States, we developed a city-wide database across 13 clinical sites using electronic data abstraction and manual data entry from EMRs.

MATERIALS AND METHODS

To develop this unique longitudinal cohort, a web-based electronic data capture system (Discovere®) was used. An Agile software development methodology was implemented across multiple EMR platforms. Clinical informatics staff worked with information technology specialists from each site to abstract data electronically from each respective site's EMR through an extract, transform, and load process.

RESULTS

Since enrollment began in 2011, more than 7000 patients have been enrolled, with longitudinal clinical data available on all patients. Data sets are produced for scientific analyses on a quarterly basis, and benchmarking reports are generated semi-annually enabling each site to compare their participants' clinical status, treatments, and outcomes to the aggregated summaries from all other sites.

DISCUSSION

Numerous technical challenges were identified and innovative solutions developed to ensure the successful implementation of the DC Cohort. Central to the success of this project was the broad collaboration established between government, academia, clinics, community, information technology staff, and the patients themselves.

CONCLUSIONS

Our experiences may have practical implications for researchers who seek to merge data from diverse clinical databases, and are applicable to the study of health-related issues beyond HIV.

Using Electronic Health Records for Population Health Research: A Review of Methods and Applications

The use and functionality of electronic health records (EHRs) have increased rapidly in the past decade. Although the primary purpose of EHRs is clinical, researchers have used them to conduct epidemiologic investigations, ranging from cross-sectional studies within a given hospital to longitudinal studies on geographically distributed patients. Herein, we describe EHRs, examine their use in population health research, and compare them with traditional epidemiologic methods. We describe diverse research applications that benefit from the large sample sizes and generalizable patient populations afforded by EHRs. These have included reevaluation of prior findings, a range of diseases and subgroups, environmental and social epidemiology, stigmatized conditions, predictive modeling, and evaluation of natural experiments. Although studies using primary data collection methods may have more reliable data and better population retention, EHR-based studies are less expensive and require less time to complete. Future EHR epidemiology with enhanced collection of social/behavior measures, linkage with vital records, and integration of emerging technologies such as personal sensing could improve clinical care and population health.

A security framework for nationwide health information exchange based on telehealth strategy

This study focuses on the situation of health information exchange (HIE) in the context of a nationwide network. It aims to create a security framework that can be implemented to ensure the safe transmission of health information across the boundaries of care providers in Malaysia and other countries. First, a critique of the major elements of nationwide health information networks is presented from the perspective of security, along with such topics as the importance of HIE, issues, and main approaches. Second, a systematic evaluation is conducted on the security solutions that can be utilized in the proposed nationwide network. Finally, a secure framework for health information transmission is proposed within a central cloud-based model, which is compatible with the Malaysian telehealth strategy. The outcome of this analysis indicates that a complete security framework for a global structure of HIE is yet to be defined and implemented. Our proposed framework represents such an endeavor and suggests specific techniques to achieve this goal.

Adapting practice-based intervention research to electronic environments: opportunities and complexities at two institutions

BACKGROUND AND PURPOSE

Primary care practice-based research has become more complex with increased use of electronic health records (EHRs). Little has been reported about changes in study planning and execution that are required as practices change from paper-based to electronic-based environments. We describe the evolution of a pediatric practice-based intervention study as it was adapted for use in the electronic environment, to enable other practice-based researchers to plan efficient, effective studies.

METHODS

We adapted a paper-based pediatric office-level intervention to enhance parent-provider communication about subspecialty referrals for use in two practice-based research networks (PBRNs) with partially and fully electronic environments. We documented the process of adaptation and its effect on study feasibility and efficiency, resource use, and administrative and regulatory complexities, as the study was implemented in the two networks.

RESULTS

Considerable time and money was required to adapt the paper-based study to the electronic environment, requiring extra meetings with institutional EHR-, regulatory-, and administrative teams, and increased practice training. Institutional unfamiliarity with using EHRs in practice-based research, and the consequent need to develop new policies, were major contributors to delays. Adapting intervention tools to the EHR and minimizing practice disruptions was challenging, but resulted in several efficiencies as compared with a paper-based project. In particular, recruitment and tracking of subjects and data collection were easier and more efficient.

CONCLUSIONS

Practice-based intervention research in an electronic environment adds considerable cost and time at the outset of a study, especially for centers unfamiliar with such research. Efficiencies generated have the potential of easing the work of study enrollment, subject tracking, and data collection.

Effect of provider prompts on adolescent immunization rates: a randomized trial

OBJECTIVE

Adolescent immunization rates are suboptimal. Experts recommend provider prompts at health care visits to improve rates. We assessed the impact of either electronic health record (EHR) or nurse- or staff-initiated provider prompts on adolescent immunization rates.

METHODS

We conducted a randomized controlled trial, allocating practices in 1 of 2 practice-based research networks (PBRN) to provider prompts or standard-of-care control. Ten primary care practices participated, 5 intervention and 5 controls, each matched in pairs on urban, suburban, or rural location and practice type (pediatric or family medicine), from a PBRN in Greater Rochester, New York (GR-PBRN); and 12 practices, 6 intervention, 6 controls, similarly matched, from a national pediatric continuity clinic PBRN (CORNET). The study period was 1 year per practice, ranging from June 2011 to January 2013. Study participants were adolescents 11 to 17 years attending these 22 practices; random sample of chart reviews per practice for baseline and postintervention year to assess immunization rates (n = 7,040 total chart reviews for adolescents with >1 visit in a period). The intervention was an EHR prompt (4 GR-PBRN and 5 CORNET practice pairs) (alert) that appeared on providers' computer screens at all office visits, indicating the specific immunizations that adolescents were recommended to receive. Staff prompts (1 GR-PBRN pair and 1 CORNET pair) in the form of a reminder sheet was placed on the provider's desk in the exam room indicating the vaccines due. We compared immunization rates, stratified by PBRN, for routine vaccines (meningococcus, pertussis, human papillomavirus, influenza) at study beginning and end.

RESULTS

Intervention and control practices within each PBRN were similar at baseline for demographics and immunization rates. Immunization rates at the study end for adolescents who were behind on immunizations at study initiation were not significantly different for intervention versus control practices for any vaccine or combination of vaccines. Results were similar for each PBRN and also when only EHR-based prompts was assessed. For example, at study end, 3-dose human papillomavirus vaccination rates for GR-PBRN intervention versus control practices were 51% versus 53% (adjusted odds ratio 0.96; 95% confidence interval 0.64-1.34); CORNET intervention versus control rates were 50% versus 42% (adjusted odds ratio 1.06; 95% confidence interval 0.68-1.88).

CONCLUSIONS AND RELEVANCE

In both a local and national setting, provider prompts failed to improve adolescent immunization rates. More rigorous practice-based changes are needed.

Comparison of a semi-automatic annotation tool and a natural language processing application for the generation of clinical statement entries

BACKGROUND AND OBJECTIVE

Electronic medical records with encoded entries should enhance the semantic interoperability of document exchange. However, it remains a challenge to encode the narrative concept and to transform the coded concepts into a standard entry-level document. This study aimed to use a novel approach for the generation of entry-level interoperable clinical documents.

METHODS

Using HL7 clinical document architecture (CDA) as the example, we developed three pipelines to generate entry-level CDA documents. The first approach was a semi-automatic annotation pipeline (SAAP), the second was a natural language processing (NLP) pipeline, and the third merged the above two pipelines. We randomly selected 50 test documents from the i2b2 corpora to evaluate the performance of the three pipelines.

RESULTS

The 50 randomly selected test documents contained 9365 words, including 588 Observation terms and 123 Procedure terms. For the Observation terms, the merged pipeline had a significantly higher F-measure than the NLP pipeline (0.89 vs 0.80, p<0.0001), but a similar F-measure to that of the SAAP (0.89 vs 0.87). For the Procedure terms, the F-measure was not significantly different among the three pipelines.

CONCLUSIONS

The combination of a semi-automatic annotation approach and the NLP application seems to be a solution for generating entry-level interoperable clinical documents.

Using computer-extracted data from electronic health records to measure the quality of adolescent well-care

OBJECTIVE

To determine whether quality measures based on computer-extracted EHR data can reproduce findings based on data manually extracted by reviewers.

DATA SOURCES

We studied 12 measures of care indicated for adolescent well-care visits for 597 patients in three pediatric health systems.

STUDY DESIGN

Observational study.

DATA COLLECTION/EXTRACTION METHODS

Manual reviewers collected quality data from the EHR. Site personnel programmed their EHR systems to extract the same data from structured fields in the EHR according to national health IT standards.

PRINCIPAL FINDINGS

Overall performance measured via computer-extracted data was 21.9 percent, compared with 53.2 percent for manual data. Agreement measures were high for immunizations. Otherwise, agreement between computer extraction and manual review was modest (Kappa = 0.36) because computer-extracted data frequently missed care events (sensitivity = 39.5 percent). Measure validity varied by health care domain and setting. A limitation of our findings is that we studied only three domains and three sites.

CONCLUSIONS

The accuracy of computer-extracted EHR quality reporting depends on the use of structured data fields, with the highest agreement found for measures and in the setting that had the greatest concentration of structured fields. We need to improve documentation of care, data extraction, and adaptation of EHR systems to practice workflow.

Building a common pediatric research terminology for accelerating child health research

Longitudinal observational clinical data on pediatric patients in electronic format is becoming widely available. A new era of multi-institutional data networks that study pediatric diseases and outcomes across disparate health delivery models and care settings are also enabling an innovative collaborative rapid improvement paradigm called the Learning Health System. However, the potential alignment of routine clinical care, observational clinical research, pragmatic clinical trials, and health systems improvement requires a data infrastructure capable of combining information from systems and workflows that historically have been isolated from each other. Removing barriers to integrating and reusing data collected in different settings will permit new opportunities to develop a more complete picture of a patient's care and to leverage data from related research studies. One key barrier is the lack of a common terminology that provides uniform definitions and descriptions of clinical observations and data. A well-characterized terminology ensures a common meaning and supports data reuse and integration. A common terminology allows studies to build upon previous findings and to reuse data collection tools and data management processes. We present the current state of terminology harmonization and describe a governance structure and mechanism for coordinating the development of a common pediatric research terminology that links to clinical terminologies and can be used to align existing terminologies. By reducing the barriers between clinical care and clinical research, a Learning Health System can leverage and reuse not only its own data resources but also broader extant data resources.

Can we predict a national profile of non-attendance paediatric urology patients: a multi-institutional electronic health record study

BACKGROUND

Non-attendance at paediatric urology outpatient appointments results in the patient's failure to receive medical care and wastes health care resources.

OBJECTIVE

To determine the utility of using routinely collected electronic health record (EHR) data for multi-centre analysis of variables predictive of patient noshows (NS) to identify areas for future intervention.

METHODS

Data were obtained from Children's Hospital Colorado, Rady Children's Hospital San Diego and University of Virginia Hospital paediatric urology practices, which use the Epic® EHR system. Data were extracted for all urology outpatient appointments scheduled from 1 October 2010 to 30 September 2011 using automated electronic data extraction techniques. Data included appointment type; date; provider type and days from scheduling to appointment. All data were de-identified prior to analysis. Predictor variables identified using χ(2) and analysis of variance were modelled using multivariate logistic regression.

RESULTS

A total of 2994 NS patients were identified within a population of 28,715, with a mean NS rate of 10.4%. Multivariate logistic regression determined that an appointment with mid-level provider (odds ratio (OR) 1.70 95% CI (1.56, 1.85)) and an increased number of days between scheduling and appointment (15-28 days OR 1.24 (1.09, 1.41); 29+ days OR 1.70 (1.53, 1.89)) were significantly associated with NS appointments.

CONCLUSION

We demonstrated sufficient interoperability among institutions to obtain data rapidly and efficiently for use in 1) interventions; 2) further study and 3) more complex analysis. Demographic and potentially modifiable clinic characteristics were associated with NS to the outpatient clinic. The analysis also demonstrated that available data are dependent on the clinical data collection systems and practices.

Development and evaluation of a de-identification procedure for a case register sourced from mental health electronic records

Background

Electronic health records (EHRs) provide enormous potential for health research but also present data governance challenges. Ensuring de-identification is a pre-requisite for use of EHR data without prior consent. The South London and Maudsley NHS Trust (SLaM), one of the largest secondary mental healthcare providers in Europe, has developed, from its EHRs, a de-identified psychiatric case register, the Clinical Record Interactive Search (CRIS), for secondary research.

Methods

We describe development, implementation and evaluation of a bespoke de-identification algorithm used to create the register. It is designed to create dictionaries using patient identifiers (PIs) entered into dedicated source fields and then identify, match and mask them (with ZZZZZ) when they appear in medical texts. We deemed this approach would be effective, given high coverage of PI in the dedicated fields and the effectiveness of the masking combined with elements of a security model. We conducted two separate performance tests i) to test performance of the algorithm in masking individual true PIs entered in dedicated fields and then found in text (using 500 patient notes) and ii) to compare the performance of the CRIS pattern matching algorithm with a machine learning algorithm, called the MITRE Identification Scrubber Toolkit – MIST (using 70 patient notes – 50 notes to train, 20 notes to test on). We also report any incidences of potential breaches, defined by occurrences of 3 or more true or apparent PIs in the same patient’s notes (and in an additional set of longitudinal notes for 50 patients); and we consider the possibility of inferring information despite de-identification.

Results

True PIs were masked with 98.8% precision and 97.6% recall. As anticipated, potential PIs did appear, owing to misspellings entered within the EHRs. We found one potential breach. In a separate performance test, with a different set of notes, CRIS yielded 100% precision and 88.5% recall, while MIST yielded a 95.1% and 78.1%, respectively. We discuss how we overcome the realistic possibility – albeit of low probability – of potential breaches through implementation of the security model.

Conclusion

CRIS is a de-identified psychiatric database sourced from EHRs, which protects patient anonymity and maximises data available for research. CRIS demonstrates the advantage of combining an effective de-identification algorithm with a carefully designed security model. The paper advances much needed discussion of EHR de-identification – particularly in relation to criteria to assess de-identification, and considering the contexts of de-identified research databases when assessing the risk of breaches of confidential patient information.