Use of electronic health records in U.S. hospitals

Users' perception on factors contributing to electronic medical records systems use: a focus group discussion study in healthcare facilities setting in Kenya

Background

Electronic medical records systems (EMRs) adoption in healthcare to facilitate work processes have become common in many countries. Although EMRs are associated with quality patient care, patient safety, and cost reduction, their adoption rates are comparatively low. Understanding factors associated with the use of the implemented EMRs are critical for advancing successful implementations and scale-up sustainable initiatives. The aim of this study was to explore end users’ perceptions and experiences on factors facilitating and hindering EMRs use in healthcare facilities in Kenya, a low- and middle-income country.

Methods

Two focus group discussions were conducted with EMRs users (n = 20) each representing a healthcare facility determined by the performance of the EMRs implementation. Content analysis was performed on the transcribed data and relevant themes derived.

Results

Six thematic categories for both facilitators and barriers emerged, and these related to (1) system functionalities; (2) training; (3) technical support; (4) human factors; (5) infrastructure, and (6) EMRs operation mode. The identified facilitators included: easiness of use and learning of the system complemented by EMRs upgrades, efficiency of EMRs in patient data management, responsive information technology (IT) and collegial support, and user training. The identified barriers included: frequent power blackouts, inadequate computers, retrospective data entry EMRs operation mode, lack of continuous training on system upgrades, and delayed IT support.

Conclusions

Users generally believed that the EMRs improved the work process, with multiple factors identified as facilitators and barriers to their use. Most users perceived system functionalities and training as motivators to EMRs use, while infrastructural issues posed as the greatest barrier. No specific EMRs use facilitators and/or barriers could be attributed to facility performance levels. Continuous evaluations are necessary to assess improvements of the identified factors as well as determine emerging issues.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-021-01737-x.

Digital health in oncology in Africa: A scoping review and cross-sectional survey

BACKGROUND

Low- and middle-income countries, especially in Africa, face a growing cancer burden. Adoption of digital health solutions has the potential to improve cancer care delivery and research in these countries. However, the extent of implementation and the impact of digital health interventions across the cancer continuum in Africa have not been studied.

AIMS

To describe the current landscape of digital health interventions in oncology in Africa.

METHODS

We conducted a scoping literature review and supplemented this with a survey. Following the PRISMA for Scoping Reviews guidelines, we searched literature in PubMed and Embase for keywords and synonyms for cancer, digital health, and African countries, and abstracted data using a structured form. For the survey, participants were delegates of the 2019 conference of the African Organization for Research and Training in Cancer.

RESULTS

The literature review identified 57 articles describing 40 digital health interventions or solutions from 17 African countries, while the survey included 111 respondents from 18 African countries, and these reported 25 different digital health systems. Six articles (10.5%) reported randomized controlled trials. The other 51 articles (89.5%) were descriptive or quasi-experimental studies. The interventions mostly targeted cancer prevention (28 articles, 49.1%) or diagnosis and treatment (23 articles, 40.4%). Four articles (7.0%) targeted survivorship and end of life, and the rest were cross-cutting. Cervical cancer was the most targeted cancer (25 articles, 43.9%). Regarding WHO classification of digital interventions, most were for providers (35 articles, 61.4%) or clients (13, 22.8%), while the others were for data services or cut across these categories. The interventions were mostly isolated pilots using basic technologies such as SMS and telephone calls for notifying patients of their appointments or results, or for cancer awareness; image capture apps for cervical cancer screening, and tele-conferencing for tele-pathology and mentorship. Generally positive results were reported, but evaluation focused on structure and process measures such as ease of use, infrastructure requirements, and acceptability of intervention; or general benefits e.g. supporting training and mentorship of providers, communication among providers and clients, and improving data collection and management. No studies evaluated individualized clinical outcomes, and there were no interventions in literature for health system managers although the systems identified in the survey had such functionality, e.g. inventory management. The survey also indicated that none of the digital health systems had all the functionalities for a comprehensive EHR, and major barriers for digital health were initial and ongoing costs, resistance from clinical staff, and lack of fit between the EHR and the clinical workflows.

CONCLUSION

Digital health interventions in oncology in Africa are at early maturity stages but promising. Barriers such as funding, fit between digital health tools and clinical workflows, and inertia towards technology, shall need to be addressed to allow for advancement of digital health solutions to support all parts of the cancer continuum. Future research should investigate the impact of digital health solutions on long-term cancer outcomes such as cancer mortality, morbidity and quality of life.

Use of Electronic Health Information Technology in a National Sample of Hospitals That Provide Specialty Substance Use Care

OBJECTIVE

Most U.S. acute care hospitals have adopted basic electronic health record (EHR) functionality and health information exchange (HIE) (84% and 88%, respectively, in 2017). This study examined whether rates of EHR and HIE adoption by hospital-based substance use disorder programs are lower than rates by acute care hospitals.

METHODS

Data from the 2017 National Survey on Substance Abuse Treatment Services were analyzed to examine adoption of basic EHR functionality (i.e., assessment, progress monitoring, discharge, labs, and prescription dispensing) and use of HIE by hospital-based programs. Analyses used weighted multivariable models of EHR and HIE outcomes, adjusted for nonresponse.

RESULTS

Of 894 hospital-based substance use disorder programs with EHR information, two-thirds (N=606, 68%) reported use of basic EHR functionality. Psychiatric hospitals were less likely than acute care hospitals to have adopted EHR (odds ratio [OR]=0.49, 95% confidence interval [CI]=0.35-0.71). Compared with nonprofit hospitals, for-profit (OR=0.23, 95% CI=0.16-0.35) and government-owned (OR=0.52, 95% CI=0.33-0.83) hospitals were less likely to use basic EHR functionality. Hospital-based programs providing medications for alcohol or opioid use disorders were more likely than those not providing such medications to use basic EHR (OR=1.95, 95% CI=1.31-2.90). Of 839 hospitals with information on HIE use, 598 (71%) reported using electronic HIE. Adoption of basic EHR functionality was the strongest predictor of HIE use (OR=4.73, 95% CI=3.29-6.79).

CONCLUSIONS

Hospital-based substance use disorder programs trail behind U.S. acute care hospitals in adoption of basic EHR and electronic HIE. Findings raise concerns about missed opportunities to improve hospital-based substance use disorder care quality and performance measurement.

Online patient portal use by caregivers in pediatric oncology: Are we widening sociodemographic disparities?

BACKGROUND

Financial and regulatory incentives have encouraged and increased the availability of online patient portals that provide caregivers access to their child's electronic health records (EHR). Such access is believed to promote better engagement and outcomes of care. Little is known about the use of portals by caregivers of children with cancer. This study sought to examine whether sociodemographic and clinical care variables are associated with portal activation in a pediatric oncology sample.

METHODS

Sociodemographic and clinical characteristics were extracted from the EHR of pediatric oncology patients treated for their first cancer in the Nemours Center for Cancer and Blood Disorders between 2012 and 2017. A Child Opportunity Index (COI) was calculated based on home zip code. Characteristics of children whose caregivers did and did not activate the portal were compared.

RESULTS

Sixty-six percent of caregivers activated a portal account with a peak within 90 days of diagnosis. In logistic regression, caregivers with a younger aged child, spoke English, lived closer to the hospital, lived in higher COI area, with longer treatment length, and more radiology tests had greater odds of portal activation. Those with private health insurance or White race were overrepresented among those who activated an account in univariate analysis.

CONCLUSION

The majority of caregivers of children with cancer activate portal accounts; however, differences in sociodemographic and clinical variables across those who did and did not activate accounts emerged. As portals become ubiquitous, we must understand how they are used and mitigate widening inequities caused by disparate portal use.

Getting on track for digital work: Digital transformation in an administrative court before and during COVID-19

This article analyses organizational change and new ways of working in one of our most institutionalized and professionalized contexts—the courts. Here, digital technologies and the implementation of digital work practices carry great promise as they enable more accessible and qualitative services to be produced more efficiently and effectively. While prior studies have shown that institutionalized and professionalized actors are reluctant to respond to change, attempts to change work practices through digital technologies remain understudied. In particular, we do not know how COVID-19 has influenced the motivation and implementation of digitalized work. This article draws on a large Swedish administrative court and its attempts to digitalize its work starting in 2018. We find that several barriers first inhibited a successful transformation of work practices. These barriers were connected to the institution of the court and the institutionalized profession of judges, which worked together in preventing organizational change. However, COVID-19 radically accelerated the digital implementation of work practices and gave rise to two separate re-assessment processes. The first established new motivations for digitalized work, and the second allowed for a new perception of value in digital work. These processes effectively broke down perceived barriers and substantially facilitated a more successful digital transformation of working practices.

Adoption of health technologies for effective health information system: Need of the hour for Pakistan

Health information technology systems have the capacity to improve health outcomes for the patients thus ensuring quality and efficient services. Health information systems (HIS) are important tools in guidance towards patient safety and better outcomes. However, still, morbidity and mortality attributed to medical errors remain an important issue that needs to be addressed. The objective of the present study was to assess the health information system in terms of technological, environmental, organizational and human factors affecting the adoption as well as the perceptions of stakeholders along with barriers and constraints related to successful implementation. A descriptive cross-sectional study design was used. Prospective data was collected from primary sources by self-administering the pre-validated questionnaires as well as by physical verification of the availability of equipment. After data collection, data was analyzed to assess the health information management systems. The results of the present study showed that the health information system in Pakistan is not up to the mark. The equipment was mostly unavailable at the primary healthcare facilities. The staff was also unsatisfied with the available services. Administrative, financial and human constraints were identified as the major barriers towards successful implementation and management of HIS. The present study concluded that the health information system of Pakistan needs to be revamped. Health information management system partially existed at district and sub-district offices, while was completely absent at tertiary, secondary and primary healthcare levels. The poor adoption of health information technology systems at healthcare facilities might largely be attributed to insufficient human resources with limited resources and budget allocation for health in Pakistan. Effective and timely strategies involving all important stakeholders and healthcare professionals must be designed and implemented at the National level to restructure an affordable, resilient and quality healthcare system.

Examining How Internet Users Trust and Access Electronic Health Record Patient Portals: Survey Study

Background

Electronic health record (EHR) patient portals are designed to provide medical health records to patients. Using an EHR portal is expected to contribute to positive health outcomes and facilitate patient-provider communication.

Objective

Our objective was to examine how portal users report using their portals and the factors associated with obtaining health information from the internet. We also examined the desired portal features, factors impacting users’ trust in portals, and barriers to using portals.

Methods

An internet-based survey study was conducted using Amazon Mechanical Turk. All the participants were adults in the United States who used patient portals. The survey included questions about how the participants used their portals, what factors acted as barriers to using their portals, and how they used and how much they trusted other web-based health information sources as well as their portals. A logistic regression model was used to examine the factors influencing the participants’ trust in their portals. Additionally, the desired features and design characteristics were identified to support the design of future portals.

Results

A total of 394 participants completed the survey. Most of the participants were less than 35 years old (212/394, 53.8%), with 36.3% (143/394) aged between 35 and 55 years, and 9.9% (39/394) aged above 55 years. Women accounted for 48.5% (191/394) of the survey participants. More than 78% (307/394) of the participants reported using portals at least monthly. The most common portal features used were viewing lab results, making appointments, and paying bills. Participants reported some barriers to portal use including data security and limited access to the internet. The results of a logistic regression model used to predict the trust in their portals suggest that those comfortable using their portals (odds ratio [OR] 7.97, 95% CI 1.11-57.32) thought that their portals were easy to use (OR 7.4, 95% CI 1.12-48.84), and frequent internet users (OR 43.72, 95% CI 1.83-1046.43) were more likely to trust their portals. Participants reporting that the portals were important in managing their health (OR 28.13, 95% CI 5.31-148.85) and that their portals were a valuable part of their health care (OR 6.75, 95% CI 1.51-30.11) were also more likely to trust their portals.

Conclusions

There are several factors that impact the trust of EHR patient portal users in their portals. Designing easily usable portals and considering these factors may be the most effective approach to improving trust in patient portals. The desired features and usability of portals are critical factors that contribute to users’ trust in EHR portals.

Resource-based view on safety culture's influence on hospital performance: The moderating role of electronic health record implementation

BACKGROUND

Patient safety and safety culture have received increasing attention from agencies such as the Agency of Healthcare Research and Quality and the Institute of Medicine. Safety culture refers to the fundamental values, attitudes, and perceptions that provide a unique source of competitive advantage to improve performance. This study contributes to the literature and expands understanding of safety culture and hospital performance outcomes when considering electronic health record (EHR) usage.

PURPOSE

Based on the resource-based view of the firm, this study examined the association between safety culture and hospital quality and financial performance in the presence of EHR.

METHODOLOGY/APPROACH

Data consist of the 2016 Hospital Survey on Patient Safety, Hospital Compare, American Hospital Association's annual survey, and the American Hospital Association's Information Technology supplement. Our final analytic sample consisted of 154 hospitals. We used a two-part nested regression model approach.

RESULTS/CONCLUSION

Safety culture has a direct positive relationship with financial performance (operating margin). Furthermore, having basic EHR as compared to not having EHR further enhances this positive relationship. On the other hand, safety culture does not have a direct association with quality performance (readmissions) in most cases. However, safety culture coupled with basic EHR functionalities, compared to not having EHR, is associated with lower readmissions.

PRACTICE IMPLICATIONS

Hospitals should strive to improve patient safety culture as part of their strategic plan for quality improvement. In addition, hospital managers should consider implementing EHR as a resource that can support safety culture's effect on outcomes such as financial and quality performance indicators. Future studies can examine the differences between basic and advanced EHR presence in relation to safety culture.

The Role of Health Information Technology in Pneumococcal Vaccination Uptake Among Adults with Heart Disease

Background: Health information technology (HIT) may influence pneumococcal vaccination uptake in high-risk populations. This study assessed the association of HIT utilization on pneumococcal vaccine (PCV) uptake among adults ≥40 years with heart disease. Methods: This was a cross-sectional study of 2,134 individuals representing 16,813,593 United States adults ≥40 years with heart disease using the National Health Interview Survey data. The independent variables were use of the Internet to (1) look up health information, (2) fill a prescription, and (3) schedule a medical appointment, and use of an e-mail (4) communicate with a health care provider. The dependent variable was PCV uptake. Chi-square analysis was used to evaluate group differences, and a multiple logistic regression was used to analyze the association between HIT utilization and PCV uptake. Results: Those who use the Internet to fill up a prescription and to communicate with their health care provider were more likely to take up the PCV (adjusted odds ratio [AOR] 1.56; 95% confidence interval [CI] 1.03-2.37, p = 0.035) and (AOR 1.95; 95% CI 1.23-3.10, p = 0.005) respectively. Compared with those who did not use HIT in any form, those who used HIT in at least three or four forms had a higher PCV uptake (AORs 1.93; 95% CI 1.19-3.13, p = 0.008) and (AOR 2.33 95% CI 1.22-4.47, p = 0.011) respectively. Conclusion: Our analysis shows a positive association of HIT utilization and PCV uptake. It further stresses the importance of electronic health in preventive medicine. This implies that HIT can be used purposively in other aspects of preventive health. Larger studies should evaluate the relationship between different uses of HIT and the uptake of different vaccines.

Network Theory and Switching Behaviors: A User Guide for Analyzing Electronic Records Databases

As part of studies that employ health electronic records databases, this paper advocates the employment of graph theory for investigating drug-switching behaviors. Unlike the shared approach in this field (comparing groups that have switched with control groups), network theory can provide information about actual switching behavior patterns. After a brief and simple introduction to fundamental concepts of network theory, here we present (i) a Python script to obtain an adjacency matrix from a records database and (ii) an illustrative example of the application of network theory basic concepts to investigate drug-switching behaviors. Further potentialities of network theory (weighted matrices and the use of clustering algorithms), along with the generalization of these methods to other kinds of switching behaviors beyond drug switching, are discussed.

A decade post-HITECH: Critical access hospitals have electronic health records but struggle to keep up with other advanced functions

OBJECTIVE

Despite broad electronic health record (EHR) adoption in U.S. hospitals, there is concern that an "advanced use" digital divide exists between critical access hospitals (CAHs) and non-CAHs. We measured EHR adoption and advanced use over time to analyzed changes in the divide.

MATERIALS AND METHODS

We used 2008 to 2018 American Hospital Association Information Technology survey data to update national EHR adoption statistics. We stratified EHR adoption by CAH status and measured advanced use for both patient engagement (PE) and clinical data analytics (CDA) domains. We used a linear probability regression for each domain with year-CAH interactions to measure temporal changes in the relationship between CAH status and advanced use.

RESULTS

In 2018, 98.3% of hospitals had adopted EHRs; there were no differences by CAH status. A total of 58.7% and 55.6% of hospitals adopted advanced PE and CDA functions, respectively. In both domains, CAHs were less likely to be advanced users: 46.6% demonstrated advanced use for PE and 32.0% for CDA. Since 2015, the advanced use divide has persisted for PE and widened for CDA.

DISCUSSION

EHR adoption among hospitals is essentially ubiquitous; however, CAHs still lag behind in advanced use functions critical to improving care quality. This may be rooted in different advanced use needs among CAH patients and lack of access to technical expertise.

CONCLUSIONS

The advanced use divide prevents CAH patients from benefitting from a fully digitized healthcare system. To close the widening gap in CDA, policymakers should consider partnering with vendors to develop implementation guides and standards for functions like dashboards and high-risk patient identification algorithms to better support CAH adoption.

Using electronic health records to develop and validate a machine-learning tool to predict type 2 diabetes outcomes: a study protocol

INTRODUCTION

Type 2 diabetes mellitus (T2DM) is a major cause of blindness, kidney failure, myocardial infarction, stroke and lower limb amputation. We are still unable, however, to accurately predict or identify which patients are at a higher risk of deterioration. Most risk stratification tools do not account for novel factors such as sociodemographic determinants, self-management ability or access to healthcare. Additionally, most tools are based in clinical trials, with limited external generalisability.

OBJECTIVE

The aim of this work is to design and validate a machine learning-based tool to identify patients with T2DM at high risk of clinical deterioration, based on a comprehensive set of patient-level characteristics retrieved from a population health linked dataset.

SAMPLE AND DESIGN

Retrospective cohort study of patients with diagnosis of T2DM on 1 January 2015, with a 5-year follow-up. Anonymised electronic healthcare records from the Whole System Integrated Care (WSIC) database will be used.

PRELIMINARY OUTCOMES

Outcome variables of clinical deterioration will include retinopathy, chronic renal disease, myocardial infarction, stroke, peripheral arterial disease or death. Predictor variables will include sociodemographic and geographic data, patients' ability to self-manage disease, clinical and metabolic parameters and healthcare service usage. Prognostic models will be defined using multidependence Bayesian networks. The derivation cohort, comprising 80% of the patients, will be used to define the prognostic models. Model parameters will be internally validated by comparing the area under the receiver operating characteristic curve in the derivation cohort with those calculated from a leave-one-out and a 10 times twofold cross-validation.

ETHICS AND DISSEMINATION

The study has received approvals from the Information Governance Committee at the WSIC. Results will be made available to people with T2DM, their caregivers, the funders, diabetes care societies and other researchers.

5G Edge Computing Enabled Directional Data Collection for Medical Community Electronic Health Records

It is important to promote the development and application of hospital information system, community health service system, etc. However, it is difficult to realize the intercommunication between various information systems because it is not enough to realize the in-depth management of health information. To address these issues, we design the 5G edge computing-assisted architecture for medical community. Then, we formulate the directional data collection (DDC) problem to gather the EMR/HER data from the medical community to minimize the service error under the deadline constraint of data collection deadline. Moreover, we design the data direction prediction algorithm (DDPA) to predict the data collection direction and propose the data collection planning algorithm (DCPA) to minimize the data collecting time cost. Through the numerical simulation experiments, we demonstrate that our proposed algorithms can decrease the total time cost by 62.48% and improve the data quality by 36.47% through the designed system, respectively.

Electronic charting of radiation therapy planning and treatment: Report of Task Group 262

While most Radiation Oncology clinics have adopted electronic charting in one form or another, no consensus document exists that provides guidelines for safe and effective use of the Radiation Oncology electronic medical records (RO-EMR). Task Group 262 was formed to provide these guidelines as well as to provide recommendations to vendors for improving electronic charting functionality in future. Guidelines are provided in the following areas: Implementation and training for the RO-EMR, acceptance testing and quality assurance (QA) of the RO-EMR, use of the RO-EMR as an information repository, use of the RO-EMR as a workflow manager, electronic charting for brachytherapy and nonstandard treatments, and information technology (IT) considerations associated with the RO-EMR. The report was based on a literature search by the task group, an extensive survey of task group members on their respective RO-EMR practices, an AAPM membership survey on electronic charting, as well as group consensus.

Factors associated with nurses' user resistance to change of electronic health record systems

Background

Electronic health record (EHR) systems often face user resistance in hospitals, which results in a failure to acquire their full benefits. To implement the EHR successfully, it is crucial to reduce nurses’ resistance to use the system. This study aimed to investigate the factors associated with nurses’ resistance to use the EHR system.

Methods

A descriptive correlational study was conducted with nurses working at four university hospitals in Korea using self-administered questionnaires to measure user resistance behavior, resistance to change, perceived usefulness, perceived ease of use, perceived value, colleagues’ opinions, self-efficacy for change, and organizational support for change. Path analysis was performed to examine direct and indirect association with user resistance behavior.

Results

A total of 223 nurses completed the questionnaires. All seven factors were found to be significantly associated with user resistance, either directly or indirectly. The total effect on user resistance behavior was highest in resistance to change (0.65), followed by perceived usefulness (− 0.33); both had direct but no indirect effects. Conversely, self-efficacy for change (− 0.25), perceived value (− 0.21), colleagues’ opinions (− 0.16), perceived ease of use (− 0.16), and organizational support for change (− 0.05) had indirect but no direct effects.

Conclusions

The study examined the factors associated with nurses’ user resistance behavior after the implementation of a new EHR system. These findings could help hospitals develop better EHR implementation strategies to reduce user resistance behavior among the nursing staff.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-021-01581-z.

Biomedical and clinical English model packages for the Stanza Python NLP library

Objective

The study sought to develop and evaluate neural natural language processing (NLP) packages for the syntactic analysis and named entity recognition of biomedical and clinical English text.

Materials and Methods

We implement and train biomedical and clinical English NLP pipelines by extending the widely used Stanza library originally designed for general NLP tasks. Our models are trained with a mix of public datasets such as the CRAFT treebank as well as with a private corpus of radiology reports annotated with 5 radiology-domain entities. The resulting pipelines are fully based on neural networks, and are able to perform tokenization, part-of-speech tagging, lemmatization, dependency parsing, and named entity recognition for both biomedical and clinical text. We compare our systems against popular open-source NLP libraries such as CoreNLP and scispaCy, state-of-the-art models such as the BioBERT models, and winning systems from the BioNLP CRAFT shared task.

Results

For syntactic analysis, our systems achieve much better performance compared with the released scispaCy models and CoreNLP models retrained on the same treebanks, and are on par with the winning system from the CRAFT shared task. For NER, our systems substantially outperform scispaCy, and are better or on par with the state-of-the-art performance from BioBERT, while being much more computationally efficient.

Conclusions

We introduce biomedical and clinical NLP packages built for the Stanza library. These packages offer performance that is similar to the state of the art, and are also optimized for ease of use. To facilitate research, we make all our models publicly available. We also provide an online demonstration (http://stanza.run/bio).

Factors that Determine Comprehensive Categorical Classification of EHR Implementation Levels

Electronic Health Records (EHRs) have the potential to alleviate patient safety mistakes. Of the various levels of EHR, advanced or higher-level functionalities of EHR are designed to improve patient safety. Certain organizational and environmental factors may pose as barriers toward implementing all of the functionalities, leaving certain hospitals intermediate between basic and comprehensive levels of implementation. This study identifies a comprehensive categorical classification that includes hospitals that have functionalities between basic and comprehensive levels of EHR and determines the organizational and environmental factors that may influence hospitals to implement one or more combinations of these categories. A longitudinal panel design was used. Ordinal logistic regression with random effects model was fitted with robust cluster standard errors. Our sample consisted of non-federal general acute care hospitals utilizing a panel design from 2010 to 2016 with 17 586 hospital-year observations (or an average of 2600 hospitals per year). Larger size hospitals, ones with higher total margin, metropolitan and urban hospitals, system affiliated hospitals, and those in higher managed care penetration areas have higher odds of belonging in one of the higher categories of EHR implementation. Hospitals that can access a greater amount of human resources and financial assets from their environments, may implement higher levels of EHR. Initial and maintenance costs of EHR, interoperability issues, and inability to distribute high costs of training across facilities may stymie implementation of higher EHR functionalities. Policymaking to encourage competition among vendors may possibly lower the implementation price for hospitals with limited resources.

Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction

Deep learning (DL)-based predictive models from electronic health records (EHRs) deliver impressive performance in many clinical tasks. Large training cohorts, however, are often required by these models to achieve high accuracy, hindering the adoption of DL-based models in scenarios with limited training data. Recently, bidirectional encoder representations from transformers (BERT) and related models have achieved tremendous successes in the natural language processing domain. The pretraining of BERT on a very large training corpus generates contextualized embeddings that can boost the performance of models trained on smaller datasets. Inspired by BERT, we propose Med-BERT, which adapts the BERT framework originally developed for the text domain to the structured EHR domain. Med-BERT is a contextualized embedding model pretrained on a structured EHR dataset of 28,490,650 patients. Fine-tuning experiments showed that Med-BERT substantially improves the prediction accuracy, boosting the area under the receiver operating characteristics curve (AUC) by 1.21-6.14% in two disease prediction tasks from two clinical databases. In particular, pretrained Med-BERT obtains promising performances on tasks with small fine-tuning training sets and can boost the AUC by more than 20% or obtain an AUC as high as a model trained on a training set ten times larger, compared with deep learning models without Med-BERT. We believe that Med-BERT will benefit disease prediction studies with small local training datasets, reduce data collection expenses, and accelerate the pace of artificial intelligence aided healthcare.

HITECH to 21st century cures: clinician burden and evolving health IT policy

Adoption and use of health information technology (IT) was identified as 1 solution to quality and safety issues that permeate the United States health care system. Implementation of health IT has accelerated across the US over the past decade, in part, as a result of legislative and regulatory requirements and incentives. However, adoption of these systems has burdened clinician users due to design, configuration, and implementation issues, resulting in poor usability, challenges to workflow integration, and cumbersome documentation requirements. The path to alleviating these clinician burdens requires a clear understanding of the intent and evolution of pertinent regulations and the context in which they exist. This article reviews the Office of the National Coordinator of Health Information Technology's efforts, documents current regulatory actions, and discusses additional policy opportunities that can further improve clinician satisfaction and effectiveness in providing health care with health IT that is an asset, not an obstacle.

Hospital organizational strategies associated with advanced EHR adoption

OBJECTIVE

To identify organizational complementarities of adoption and use of electronic health records (EHRs) and assess what organizational strategies were associated with more advanced EHR use.

DATA SOURCES

Primary survey data of US hospitals combined with secondary data from the American Hospital Association Annual Survey and IT Supplement.

STUDY DESIGN

In this cross-sectional study, we describe hospital organizational practices around EHR adoption and use and identify how these practices coalesce into distinct strategies. We then assess the association between those organizational strategies and adoption of advanced EHR functions.

DATA COLLECTION

Primary data collection consisted of surveys sent to 797 US acute care hospitals in 2018-2019, with 451 complete respondents.

PRINCIPAL FINDINGS

There was significant variation in hospital organizational practices for EHR adoption and use. Factor analysis identified practices in three domains: leadership engagement, human capital, and systems integration. Hospitals in the top quartile of the leadership engagement factor were 14 percentage points more likely to have adopted patient engagement EHR functions (P = 0.01) while hospitals in the top quartile of human capital were 14 percentage points less likely to have adopted these functions (P = 0.02). Hospitals in the top quartile of systems integration were 12 percentage points more likely to have adopted patient engagement functions (P = 0.02) and 14 percentage points more likely to have adopted EHR data analytics functions (P = 0.02).

CONCLUSIONS

Our findings suggest that specific organizational strategies are associated with more advanced EHR adoption. Hospital leaders interested in realizing more value from their EHR investment may find it useful to know that there is an association between adoption of more advanced EHR functions, and engaging senior leadership as well as building connectivity between clinical and administrative systems.

Reconsidering hospital EHR adoption at the dawn of HITECH: implications of the reported 9% adoption of a "basic" EHR

Objective

In 2009, a prominent national report stated that 9% of US hospitals had adopted a “basic” electronic health record (EHR) system. This statistic was widely cited and became a memetic anchor point for EHR adoption at the dawn of HITECH. However, its calculation relies on specific treatment of the data; alternative approaches may have led to a different sense of US hospitals’ EHR adoption and different subsequent public policy.

Materials and Methods

We reanalyzed the 2008 American Heart Association Information Technology supplement and complementary sources to produce a range of estimates of EHR adoption. Estimates included the mean and median number of EHR functionalities adopted, figures derived from an item response theory-based approach, and alternative estimates from the published literature. We then plotted an alternative definition of national progress toward hospital EHR adoption from 2008 to 2018.

Results

By 2008, 73% of hospitals had begun the transition to an EHR, and the majority of hospitals had adopted at least 6 of the 10 functionalities of a basic system. In the aggregate, national progress toward basic EHR adoption was 58% complete, and, when accounting for measurement error, we estimate that 30% of hospitals may have adopted a basic EHR.

Discussion

The approach used to develop the 9% figure resulted in an estimate at the extreme lower bound of what could be derived from the available data and likely did not reflect hospitals’ overall progress in EHR adoption.

Conclusion

The memetic 9% figure shaped nationwide thinking and policy making about EHR adoption; alternative representations of the data may have led to different policy.

Adoption of Electronic Health Records (EHRs) in China During the Past 10 Years: Consecutive Survey Data Analysis and Comparison of Sino-American Challenges and Experiences

Background

The adoption rate of electronic health records (EHRs) in hospitals has become a main index to measure digitalization in medicine in each country.

Objective

This study summarizes and shares the experiences with EHR adoption in China and in the United States.

Methods

Using the 2007-2018 annual hospital survey data from the Chinese Health Information Management Association (CHIMA) and the 2008-2017 United States American Hospital Association Information Technology Supplement survey data, we compared the trends in EHR adoption rates in China and the United States. We then used the Bass model to fit these data and to analyze the modes of diffusion of EHRs in these 2 countries. Finally, using the 2007, 2010, and 2014 CHIMA and Healthcare Information and Management Systems Services survey data, we analyzed the major challenges faced by hospitals in China and the United States in developing health information technology.

Results

From 2007 to 2018, the average adoption rates of the sampled hospitals in China increased from 18.6% to 85.3%, compared to the increase from 9.4% to 96% in US hospitals from 2008 to 2017. The annual average adoption rates in Chinese and US hospitals were 6.1% and 9.6%, respectively. However, the annual average number of hospitals adopting EHRs was 1500 in China and 534 in the US, indicating that the former might require more effort. Both countries faced similar major challenges for hospital digitalization.

Conclusions

The adoption rates of hospital EHRs in China and the United States have both increased significantly in the past 10 years. The number of hospitals that adopted EHRs in China exceeded 16,000, which was 3.3 times that of the 4814 nonfederal US hospitals. This faster adoption outcome may have been a benefit of top-level design and government-led policies, particularly the inclusion of EHR adoption as an important indicator for performance evaluation and the appointment of public hospitals.

A Bespoke Electronic Health Record for Epilepsy Care (EpiToMe): Development and Qualitative Evaluation

BACKGROUND

While electronic health records (EHR) bring various benefits to health care, EHR systems are often criticized as cumbersome to use, failing to fulfill the promise of improved health care delivery with little more than a means of meeting regulatory and billing requirements. EHR has also been recognized as one of the contributing factors for physician burnout.

OBJECTIVE

Specialty-specific EHR systems have been suggested as an alternative approach that can potentially address challenges associated with general-purpose EHRs. We introduce the Epilepsy Tracking and optimized Management engine (EpiToMe), an exemplar bespoke EHR system for epilepsy care. EpiToMe uses an agile, physician-centered development strategy to optimize clinical workflow and patient care documentation. We present the design and implementation of EpiToMe and report the initial feedback on its utility for physician burnout.

METHODS

Using collaborative, asynchronous data capturing interfaces anchored to a domain ontology, EpiToMe distributes reporting and documentation workload among technicians, clinical fellows, and attending physicians. Results of documentation are transmitted to the parent EHR to meet patient care requirements with a push of a button. An HL7 (version 2.3) messaging engine exchanges information between EpiToMe and the parent EHR to optimize clinical workflow tasks without redundant data entry. EpiToMe also provides live, interactive patient tracking interfaces to ease the burden of care management.

RESULTS

Since February 2019, 15,417 electroencephalogram reports, 2635 Epilepsy Monitoring Unit daily reports, and 1369 Epilepsy Monitoring Unit phase reports have been completed in EpiToMe for 6593 unique patients. A 10-question survey was completed by 11 (among 16 invited) senior clinical attending physicians. Consensus was found that EpiToMe eased the burden of care documentation for patient management, a contributing factor to physician burnout.

CONCLUSIONS

EpiToMe offers an exemplar bespoke EHR system developed using a physician-centered design and latest advancements in information technology. The bespoke approach has the potential to ease the burden of care management in epilepsy. This approach is applicable to other clinical specialties.

The Potential for Health Information Technology Tools to Reduce Racial Disparities in Maternal Morbidity and Mortality

Health information technology (health IT) potentially is a promising vital lever to address racial and ethnic, socioeconomic, and geographic disparities in maternal morbidity and mortality (MMM). This is especially relevant given that approximately 60% of maternal deaths are considered preventable.1-36 Interventions that leverage health IT tools to target the underlying drivers of disparities at the patient, clinician, and health care system levels potentially could reduce disparities in quality of care throughout the continuum (antepartum, intrapartum, and postpartum) of maternity care. This article presents an overview of the research (and gaps) on the potential of health IT tools to document SDoH and community-level geocoded data in EHR-based CDS systems, minimize implicit bias, and improve adherence to clinical guidelines and coordinated care to inform multilevel (patient, clinician, system) interventions throughout the continuum of maternity care for health disparity populations impacted by MMM. Telemedicine models for improving access in rural areas and new technologies for risk assessment and disease management (e.g., regarding preeclampsia) also are discussed.

Modeling multivariate clinical event time-series with recurrent temporal mechanisms

In this work, we propose a novel autoregressive event time-series model that can predict future occurrences of multivariate clinical events. Our model represents multivariate event time-series using different temporal mechanisms aimed to fit different temporal characteristics of the time-series. In particular, information about distant past is modeled through the hidden state space defined by an LSTM-based model, information on recently observed clinical events is modeled through discriminative projections, and information about periodic (repeated) events is modeled using a special recurrent mechanism based on probability distributions of inter-event gaps compiled from past data. We evaluate our proposed model on electronic health record (EHRs) data derived from MIMIC-III dataset. We show that our new model equipped with the above temporal mechanisms leads to improved prediction performance compared to multiple baselines.

Optimizing clinical decision support alerts in electronic medical records: a systematic review of reported strategies adopted by hospitals

OBJECTIVE

To identify and summarize the current internal governance processes adopted by hospitals, as reported in the literature, for selecting, optimizing, and evaluating clinical decision support (CDS) alerts in order to identify effective approaches.

MATERIALS AND METHODS

Databases (Medline, Embase, CINAHL, Scopus, Web of Science, IEEE Xplore Digital Library, CADTH, and WorldCat) were searched to identify relevant papers published from January 2010 to April 2020. All paper types published in English that reported governance processes for selecting and/or optimizing CDS alerts in hospitals were included.

RESULTS

Eight papers were included in the review. Seven papers focused specifically on medication-related CDS alerts. All papers described the use of a multidisciplinary committee to optimize alerts. Other strategies included the use of clinician feedback, alert data, literature and drug references, and a visual dashboard. Six of the 8 papers reported evaluations of their CDS alert modifications following the adoption of optimization strategies, and of these, 5 reported a reduction in alert rate.

CONCLUSIONS

A multidisciplinary committee, often in combination with other approaches, was the most frequent strategy reported by hospitals to optimize their CDS alerts. Due to the limited number of published processes, variation in system changes, and evaluation results, we were unable to compare the effectiveness of different strategies, although employing multiple strategies appears to be an effective approach for reducing CDS alert numbers. We recommend hospitals report on descriptions and evaluations of governance processes to enable identification of effective strategies for optimization of CDS alerts in hospitals.

Towards the Use of Blockchain in Mobile Health Services and Applications

With the advent of cryptocurrencies and blockchain, the growth and adaptation of cryptographic features and capabilities were quickly extended to new and underexplored areas, such as healthcare. Currently, blockchain is being implemented mainly as a mechanism to secure Electronic Health Records (EHRs). However, new studies have shown that this technology can be a powerful tool in empowering patients to control their own health data, as well for enabling a fool-proof health data history and establishing medical responsibility. Additionally, with the proliferation of mobile health (m-Health) sustained on service-oriented architectures, the adaptation of blockchain mechanisms into m-Health applications creates the possibility for a more decentralized and available healthcare service. Hence, this paper presents a review of the current security best practices for m-Health and the most used and widely known implementations of the blockchain protocol, including blockchain technologies in m-Health. The main goal of this comprehensive review is to further discuss and elaborate on identified open-issues and potential use cases regarding the uses of blockchain in this area. Finally, the paper presents the major findings, challenges and advantages on future blockchain implementations for m-Health services and applications.

Predictive value of indicators for identifying child maltreatment and intimate partner violence in coded electronic health records: a systematic review and meta-analysis

OBJECTIVE

Electronic health records (EHRs) are routinely used to identify family violence, yet reliable evidence of their validity remains limited. We conducted a systematic review and meta-analysis to evaluate the positive predictive values (PPVs) of coded indicators in EHRs for identifying intimate partner violence (IPV) and child maltreatment (CM), including prenatal neglect.

METHODS

We searched 18 electronic databases between January 1980 and May 2020 for studies comparing any coded indicator of IPV or CM including prenatal neglect defined as neonatal abstinence syndrome (NAS) or fetal alcohol syndrome (FAS), against an independent reference standard. We pooled PPVs for each indicator using random effects meta-analyses.

RESULTS

We included 88 studies (3 875 183 individuals) involving 15 indicators for identifying CM in the prenatal period and childhood (0-18 years) and five indicators for IPV among women of reproductive age (12-50 years). Based on the International Classification of Disease system, the pooled PPV was over 80% for NAS (16 studies) but lower for FAS (<40%; seven studies). For young children, primary diagnoses of CM, specific injury presentations (eg, rib fractures and retinal haemorrhages) and assaults showed a high PPV for CM (pooled PPVs: 55.9%-87.8%). Indicators of IPV in women had a high PPV, with primary diagnoses correctly identifying IPV in >85% of cases.

CONCLUSIONS

Coded indicators in EHRs have a high likelihood of correctly classifying types of CM and IPV across the life course, providing a useful tool for assessment, support and monitoring of high-risk groups in health services and research.

Adoption rates of electronic health records in Turkish Hospitals and the relation with hospital sizes

BACKGROUND

Nation-wide adoption of electronic health records (EHRs) in hospitals has become a Turkish policy priority in recognition of their benefits in maintaining the overall quality of clinical care. The electronic medical record maturity model (EMRAM) is a widely used survey tool developed by the Healthcare Information and Management Systems Society (HIMSS) to measure the rate of adoption of EHR functions in a hospital or a secondary care setting. Turkey completed many standardizations and infrastructural improvement initiatives in the health information technology (IT) domain during the first phase of the Health Transformation Program between 2003 and 2017. Like the United States of America (USA), the Turkish Ministry of Health (MoH) applied a bottom-up approach to adopting EHRs in state hospitals. This study aims to measure adoption rates and levels of EHR use in state hospitals in Turkey and investigate any relationship between adoption and use and hospital size.

METHODS

EMRAM surveys were completed by 600 (68.9%) state hospitals in Turkey between 2014 and 2017. The availability and prevalence of medical information systems and EHR functions and their use were measured. The association between hospital size and the availability/prevalence of EHR functions was also calculated.

RESULTS

We found that 63.1% of all hospitals in Turkey have at least basic EHR functions, and 36% have comprehensive EHR functions, which compares favourably to the results of Korean hospitals in 2017, but unfavorably to the results of US hospitals in 2015 and 2017. Our findings suggest that smaller hospitals are better at adopting certain EHR functions than larger hospitals.

CONCLUSION

Measuring the overall adoption rates of EHR functions is an emerging approach and a beneficial tool for the strategic management of countries. This study is the first one covering all state hospitals in a country using EMRAM. The bottom-up approach to adopting EHR in state hospitals that was successful in the USA has also been found to be successful in Turkey. The results are used by the Turkish MoH to disseminate the nation-wide benefits of EHR functions.

Computerised clinical decision support systems and absolute improvements in care: meta-analysis of controlled clinical trials

OBJECTIVE

To report the improvements achieved with clinical decision support systems and examine the heterogeneity from pooling effects across diverse clinical settings and intervention targets.

DESIGN

Systematic review and meta-analysis.

DATA SOURCES

Medline up to August 2019.

ELIGIBILITY CRITERIA FOR SELECTING STUDIES AND METHODS

Randomised or quasi-randomised controlled trials reporting absolute improvements in the percentage of patients receiving care recommended by clinical decision support systems. Multilevel meta-analysis accounted for within study clustering. Meta-regression was used to assess the degree to which the features of clinical decision support systems and study characteristics reduced heterogeneity in effect sizes. Where reported, clinical endpoints were also captured.

RESULTS

In 108 studies (94 randomised, 14 quasi-randomised), reporting 122 trials that provided analysable data from 1 203 053 patients and 10 790 providers, clinical decision support systems increased the proportion of patients receiving desired care by 5.8% (95% confidence interval 4.0% to 7.6%). This pooled effect exhibited substantial heterogeneity (I2=76%), with the top quartile of reported improvements ranging from 10% to 62%. In 30 trials reporting clinical endpoints, clinical decision support systems increased the proportion of patients achieving guideline based targets (eg, blood pressure or lipid control) by a median of 0.3% (interquartile range -0.7% to 1.9%). Two study characteristics (low baseline adherence and paediatric settings) were associated with significantly larger effects. Inclusion of these covariates in the multivariable meta-regression, however, did not reduce heterogeneity.

CONCLUSIONS

Most interventions with clinical decision support systems appear to achieve small to moderate improvements in targeted processes of care, a finding confirmed by the small changes in clinical endpoints found in studies that reported them. A minority of studies achieved substantial increases in the delivery of recommended care, but predictors of these more meaningful improvements remain undefined.

Impact of Trust and Privacy Concerns on Technology Acceptance in Healthcare: An Indian Perspective

This paper augments the technology acceptance model (TAM) by empirically investigating the influence of behavioral traits (privacy concerns and trust) and cognitive beliefs (perceived usefulness and perceived ease of use) on patients' behavioral intention to accept technology in healthcare service delivery. Despite increased emphasis on healthcare service delivery, there has been limited studies as to how various behavioral constructs are related to adoption of new technology in healthcare sector. To this end, and to develop meaningful insights, a conceptual model integrating behavioral constructs with constructs related to technology acceptance model is devised. The aim here is essentially to understand relationships that predict patients' acceptance of technology in healthcare services. The devised model is tested on responses obtained from survey of 416 patients availing healthcare service at various primary health centers in New Delhi, India. Structural equation modeling (SEM) is employed to conceptualize the model and validate nine hypotheses entailing key constructs. The results indicate that perceived usefulness, perceived ease of use, trust and privacy concern are direct predictors of patients' behavior to accept technology in availing healthcare services. In summary, this research provides an empirical contribution to the literature on effect of trust and privacy concerns on acceptance of technology in healthcare.

Telemedicine is an important aspect of healthcare services amid COVID-19 outbreak: Its barriers in Bangladesh and strategies to overcome

The current pandemic of coronavirus disease 19 (COVID-19) has been a global concern since early 2020, where the number of COVID-19 cases is also on a rapid surge in Bangladesh with the report of a total of 276,549 cases after the detection of the first three cases in this country on 8 March 2020. The COVID-19 pandemic has made a seismic shift in the healthcare delivery system, where physician offices have accelerated digital health solutions at record speed, putting telemedicine (i.e., telehealth) at centre stage. Amid the severely contagious COVID-19, telemedicine has moved from being an optional service to an essential one. As the developing country, there are some barriers to get evenly distributed advantages of this approach due to the digital divides and disparities. In this commentary, we have described the importance of telemedicine service amid the outbreak of COVID-19 in Bangladesh, the barriers and challenges that the country is facing to implement this approach and the strategies to overcome these barriers in this developing country.

Hospital adoption of electronic health record functions to support age-friendly care: results from a national survey

OBJECTIVE

To measure US hospitals' adoption of electronic health record (EHR) functions that support care for older adults, focusing on structured documentation of the 4Ms (What Matters, Medication, Mentation, and Mobility) and electronic health information exchange/communication with patients, caregivers, and long-term care providers.

MATERIALS AND METHODS

In an online survey of a national, random sample of 797 US acute-care hospitals in 2018-2019, 479 (60.1%) responded. We calculated nationally representative measures of the percentages of hospitals with EHRs that include structured documentation of the 4Ms and exchange/communications functions.

RESULTS

Structured EHR documentation of the 4Ms was fully implemented in at least 1 unit in 64.0% of hospitals and across all units in 41.5% of hospitals. Of the 4Ms, structured documentation was the highest for medications (91.3% in at least 1 unit) and the lowest for mentation (70.3% in at least 1 unit). All exchange/communication functions had been implemented in at least 1 unit in 16.2% of facilities and across all units in 7.6% of hospitals. Less than half of the hospitals had an EHR portal for long-term care facilities to access hospital information (45.4% in at least 1 unit), sent information electronically to long-term care facilities (44.6%), and had training for adults/caregivers on the patient portal (32.1%).

DISCUSSION

Despite significant national investment in EHRs, hospital EHRs do not yet include key documentation, exchange, and communication functions needed to support evidence-based care for the older adults who comprise the majority of the inpatient population. Additional policy efforts are likely needed to promote the expansion of EHR capabilities into these high-value domains.

CONCLUSIONS

US acute-care hospital EHRs are lacking key functions that support care for older adults.

Generalizable Layered Blockchain Architecture for Health Care Applications: Development, Case Studies, and Evaluation

Background

Data coordination across multiple health care facilities has become increasingly important for many emerging health care applications. Distrust has been recognized as a key barrier to the success of such applications. Leveraging blockchain technology could provide potential solutions tobuild trust between data providers and receivers by taking advantage of blockchain properties such as security, immutability, anonymity, decentralization, and smart contracts. Many health technologies have empirically proven that blockchain designs fit well with the needs of health care applications with certain degrees of success. However, there is a lack of robust architecture to provide a practical framework for developers to implement applications and test the performance of stability, efficiency, and scalability using standard blockchain designs. A generalized blockchain model is needed for the health care community to adopt blockchain technology and develop applications in a timely fashion.

Objective

This study aimed at building a generalized blockchain architecture that provides data coordination functions, including data requests, permission granting, data exchange, and usage tracking, for a wide spectrum of health care application developments.

Methods

An augmented, 3-layered blockchain architecture was built on a private blockchain network. The 3 layers, from bottom to top, are as follows: (1) incorporation of fundamental blockchain settings and smart contract design for data collection; (2) interactions between the blockchain and health care application development environment using Node.js and web3.js; and (3) a flexible development platform that supports web technologies such as HTML, https, and various programing languages. Two example applications, health information exchange (HIE) and clinical trial recruitment, were developed in our design to demonstrate the feasibility of the layered architecture. Case studies were conducted to test the performance in terms of stability, efficiency, and scalability of the blockchain system.

Results

A total of 331,142 simulated HIE requests from accounts of 40,000 patients were successfully validated through this layered blockchain architecture with an average exchange time of 11.271 (SD 2.208) seconds. We also simulated a clinical trial recruitment scenario with the same set of patients and various recruitment criteria to match potential subjects using the same architecture. Potential subjects successfully received the clinical trial recruitment information and granted permission to the trial sponsors to access their health records with an average time of 3.07 seconds.

Conclusions

This study proposes a generalized layered blockchain architecture that offers health technology community blockchain features for application development without requiring developers to have extensive experience with blockchain technology. The case studies tested the performance of our design and empirically proved the feasibility of the architecture in 2 relevant health application domains.

Generalized Regression Estimators with High-Dimensional Covariates

Data from a large number of covariates with known population totals are frequently observed in survey studies. These auxiliary variables contain valuable information that can be incorporated into estimation of the population total of a survey variable to improve the estimation precision. We consider the generalized regression estimator formulated under the model-assisted framework in which a regression model is utilized to make use of the available covariates while the estimator still has basic design-based properties. The generalized regression estimator has been shown to improve the efficiency of the design-based Horvitz-Thompson estimator when the number of covariates is fixed. In this study, we investigate the performance of the generalized regression estimator when the number of covariates p is allowed to diverge as the sample size n increases. We examine two approaches where the model parameter is estimated using the weighted least squares method when p < n and the LASSO method when the model parameter is sparse. We show that under an assisted model and certain conditions on the joint distribution of the covariates as well as the divergence rates of n and p, the generalized regression estimator is asymptotically more efficient than the Horvitz-Thompson estimator, and is robust against model misspecification. We also study the consistency of variance estimation for the generalized regression estimator. Our theoretical results are corroborated by simulation studies and an example.

Evaluating people's concern about their health information privacy based on power-responsibility equilibrium model: A case of Taiwan

To address the issue of rising expenditure of healthcare service and to fulfill the skyrocketing demand for quality healthcare, the electronic medical records (EMR) exchange has become a vital and indispensable solution for healthcare facilities in terms of being able to share medical information among healthcare providers. Hence, EMR exchange was expected to improve the quality of healthcare and reduce the cost of repetitive medical check-ups and unnecessary treatments. However, recent reports affirming EMR data leaks and compromises have ignited major worldwide privacy concerns over the security of the EMR systems. How to effectively diminish patients' concern for EMR privacy has thus become an important issue that healthcare institution managers/stakeholders have to address urgently. This study leverages the power-responsibility equilibrium perspective to investigate the antecedents and consequences of concerns for the EMR exchange. A survey using 391 responses collected from medical centers, regional and district hospitals in Taiwan was used to conduct this study. The results show that government regulations have a positive effect on hospital privacy policies. Furthermore, both government regulations and hospital privacy policy are negatively associated with concern for EMR information privacy. Additional reports gathered from this study also showed that concern for EMR information privacy could result in patients' protective responses including refusal to provide personal health information (PHI), removal of PHI, negative word of mouth, complaining directly to the hospital, or complaining indirectly to third-party organizations. These findings demonstrate the need for healthcare facilities to formulate robust privacy policies in order to alleviate patients' concern for EMR information privacy based on governmental regulations. This regulation is top-priority as the incapability of reducing patients' concern for EMR information privacy may lead to the collapse of the campaign for the full-adoption of EMR or possibly jeopardize the promotion and application of EMR among healthcare facilities.

National Trends in the Safety Performance of Electronic Health Record Systems From 2009 to 2018

IMPORTANCE

Despite the broad adoption of electronic health record (EHR) systems across the continuum of care, safety problems persist.

OBJECTIVE

To measure the safety performance of operational EHRs in hospitals across the country during a 10-year period.

DESIGN, SETTING, AND PARTICIPANTS

This case series included all US adult hospitals nationwide that used the National Quality Forum Health IT Safety Measure EHR computerized physician order entry safety test administered by the Leapfrog Group between 2009 and 2018. Data were analyzed from July 1, 2018 to December 1, 2019.

EXPOSURE

The Health IT Safety Measure test, which uses simulated medication orders that have either injured or killed patients previously to evaluate how well hospital EHRs could identify medication errors with potential for patient harm.

MAIN OUTCOMES AND MEASURES

Descriptive statistics for performance on the assessment test over time were calculated at the overall test score level, type of decision support category level, and EHR vendor level.

RESULTS

Among 8657 hospital-years observed during the study, mean (SD) scores on the overall test increased from 53.9% (18.3%) in 2009 to 65.6% (15.4%) in 2018. Mean (SD) hospital score for the categories representing basic clinical decision support increased from 69.8% (20.8%) in 2009 to 85.6% (14.9%) in 2018. For the categories representing advanced clinical decision support, the mean (SD) score increased from 29.6% (22.4%) in 2009 to 46.1% (21.6%) in 2018. There was considerable variation in test performance by EHR.

CONCLUSIONS AND RELEVANCE

These findings suggest that despite broad adoption and optimization of EHR systems in hospitals, wide variation in the safety performance of operational EHR systems remains across a large sample of hospitals and EHR vendors. Hospitals using some EHR vendors had significantly higher test scores. Overall, substantial safety risk persists in current hospital EHR systems.

Competency Assessment in Simulation of Electronic Health Records Tool Development

Rapid deployment of electronic health records has resulted in a need for simulation centers to integrate the use of electronic health records into simulation-based learning activities within the clinical workflow. To assess the quality of the documentation in the electronic health record, the Competency Assessment in Simulation of Electronic Health Records Tool was developed. Lynn's method of content validity, combined with nominal group and Delphi techniques, was used to identify 15 domains of best practice in documentation. Participants with expertise in academic education, simulation, and informatics provided input into the development of the tool. The tool evolved over three rounds of Delphi that refined the language and provided anchors to promote accurate assessment of student and nurse documentation. The results of the Delphi narrowed the 15 domains down to 10 domains for scoring best practices in electronic documentation within simulation-based learning activities. The Competency Assessment in Simulation of Electronic Health Records Tool was developed to address the electronic health record competencies of both nursing students and practicing nurses in a simulation environment.

Overcoming barriers to the adoption and implementation of predictive modeling and machine learning in clinical care: what can we learn from US academic medical centers?

There is little known about how academic medical centers (AMCs) in the US develop, implement, and maintain predictive modeling and machine learning (PM and ML) models. We conducted semi-structured interviews with leaders from AMCs to assess their use of PM and ML in clinical care, understand associated challenges, and determine recommended best practices. Each transcribed interview was iteratively coded and reconciled by a minimum of 2 investigators to identify key barriers to and facilitators of PM and ML adoption and implementation in clinical care. Interviews were conducted with 33 individuals from 19 AMCs nationally. AMCs varied greatly in the use of PM and ML within clinical care, from some just beginning to explore their utility to others with multiple models integrated into clinical care. Informants identified 5 key barriers to the adoption and implementation of PM and ML in clinical care: (1) culture and personnel, (2) clinical utility of the PM and ML tool, (3) financing, (4) technology, and (5) data. Recommendation to the informatics community to overcome these barriers included: (1) development of robust evaluation methodologies, (2) partnership with vendors, and (3) development and dissemination of best practices. For institutions developing clinical PM and ML applications, they are advised to: (1) develop appropriate governance, (2) strengthen data access, integrity, and provenance, and (3) adhere to the 5 rights of clinical decision support. This article highlights key challenges of implementing PM and ML in clinical care at AMCs and suggests best practices for development, implementation, and maintenance at these institutions.

Use of electronic medical records in development and validation of risk prediction models of hospital readmission: systematic review

OBJECTIVE

To provide focused evaluation of predictive modeling of electronic medical record (EMR) data to predict 30 day hospital readmission.

DESIGN

Systematic review.

DATA SOURCE

Ovid Medline, Ovid Embase, CINAHL, Web of Science, and Scopus from January 2015 to January 2019.

ELIGIBILITY CRITERIA FOR SELECTING STUDIES

All studies of predictive models for 28 day or 30 day hospital readmission that used EMR data.

OUTCOME MEASURES

Characteristics of included studies, methods of prediction, predictive features, and performance of predictive models.

RESULTS

Of 4442 citations reviewed, 41 studies met the inclusion criteria. Seventeen models predicted risk of readmission for all patients and 24 developed predictions for patient specific populations, with 13 of those being developed for patients with heart conditions. Except for two studies from the UK and Israel, all were from the US. The total sample size for each model ranged between 349 and 1 195 640. Twenty five models used a split sample validation technique. Seventeen of 41 studies reported C statistics of 0.75 or greater. Fifteen models used calibration techniques to further refine the model. Using EMR data enabled final predictive models to use a wide variety of clinical measures such as laboratory results and vital signs; however, use of socioeconomic features or functional status was rare. Using natural language processing, three models were able to extract relevant psychosocial features, which substantially improved their predictions. Twenty six studies used logistic or Cox regression models, and the rest used machine learning methods. No statistically significant difference (difference 0.03, 95% confidence interval -0.0 to 0.07) was found between average C statistics of models developed using regression methods (0.71, 0.68 to 0.73) and machine learning (0.74, 0.71 to 0.77).

CONCLUSIONS

On average, prediction models using EMR data have better predictive performance than those using administrative data. However, this improvement remains modest. Most of the studies examined lacked inclusion of socioeconomic features, failed to calibrate the models, neglected to conduct rigorous diagnostic testing, and did not discuss clinical impact.