Electronic health records: a critical appraisal of strengths and limitations

Digital Neuropsychology beyond Computerized Cognitive Assessment: Applications of Novel Digital Technologies

Compared with other health disciplines, there is a stagnation in technological innovation in the field of clinical neuropsychology. Traditional paper-and-pencil tests have a number of shortcomings, such as low-frequency data collection and limitations in ecological validity. While computerized cognitive assessment may help overcome some of these issues, current computerized paradigms do not address the majority of these limitations. In this paper, we review recent literature on the applications of novel digital health approaches, including ecological momentary assessment, smartphone-based assessment and sensors, wearable devices, passive driving sensors, smart homes, voice biomarkers, and electronic health record mining, in neurological populations. We describe how each digital tool may be applied to neurologic care and overcome limitations of traditional neuropsychological assessment. Ethical considerations, limitations of current research, as well as our proposed future of neuropsychological practice are also discussed.

Factors identified as barriers or facilitators to EMR/EHR based interprofessional primary care: a scoping review

As interprofessional collaboration (IPC) in primary care receives increasing attention, the role of electronic medical and health record (EMR/EHR) systems in supporting IPC is important to consider. A scoping review was conducted to synthesize the current literature on the barriers and facilitators of EMR/EHRs to interprofessional primary care. Four online databases (OVID Medline, EBSCO CINAHL, OVID EMBASE, and OVID PsycINFO) were searched without date restrictions. Twelve studies were included in the review. Of six facilitator and barrier themes identified, the key facilitator was teamwork support and a significant barrier was data management. Other important barriers included usability related mainly to interoperability, and practice support primarily in terms of patient care. Additional themes were organization attributes and user features. Although EMR/EHR systems facilitated teamwork support, there is potential for team features to be strengthened further. Persistent barriers may be partly addressed by advances in software design, particularly if interprofessional perspectives are included. Organizations and teams might also consider strategies for working with existing EMR/EHR systems, for instance by developing guidelines for interprofessional use. Further research concerning the use of electronic records in interprofessional contexts is needed to support IPC in primary care.

Improving Diagnostics with Deep Forest Applied to Electronic Health Records

An electronic health record (EHR) is a vital high-dimensional part of medical concepts. Discovering implicit correlations in the information of this data set and the research and informative aspects can improve the treatment and management process. The challenge of concern is the data sources' limitations in finding a stable model to relate medical concepts and use these existing connections. This paper presents Patient Forest, a novel end-to-end approach for learning patient representations from tree-structured data for readmission and mortality prediction tasks. By leveraging statistical features, the proposed model is able to provide an accurate and reliable classifier for predicting readmission and mortality. Experiments on MIMIC-III and eICU datasets demonstrate Patient Forest outperforms existing machine learning models, especially when the training data are limited. Additionally, a qualitative evaluation of Patient Forest is conducted by visualising the learnt representations in 2D space using the t-SNE, which further confirms the effectiveness of the proposed model in learning EHR representations.

Risk of COVID-19 breakthrough infection and hospitalization in individuals with comorbidities

BACKGROUND

The successful development of multiple COVID-19 vaccines has led to a global vaccination effort to reduce severe COVID-19 infection and mortality. However, the effectiveness of the COVID-19 vaccines wane over time leading to breakthrough infections where vaccinated individuals experience a COVID-19 infection. Here we estimate the risks of breakthrough infection and subsequent hospitalization in individuals with common comorbidities who had completed an initial vaccination series.

METHODS

Our study population included vaccinated patients between January 1, 2021 to March 31, 2022 who are present in the Truveta patient population. Models were developed to describe 1) time from completing primary vaccination series till breakthrough infection; and 2) if a patient was hospitalized within 14 days of breakthrough infection. We adjusted for age, race, ethnicity, sex, and year-month of vaccination.

RESULTS

Of 1,218,630 patients in the Truveta Platform who had completed an initial vaccination sequence between January 1, 2021 and March 31, 2022, 2.85, 3.42, 2.75, and 2.88 percent of patients with CKD, chronic lung disease, diabetes, or are in an immunocompromised state experienced breakthrough infection, respectively, compared to 1.46 percent of the population without any of these four comorbidities. We found an increased risk of breakthrough infection and subsequent hospitalization in individuals with any of the four comorbidities when compared to individuals without these four comorbidities.

CONCLUSIONS

Vaccinated individuals with any of the studied comorbidities experienced an increased risk of breakthrough COVID-19 infection and subsequent hospitalizations compared to the people without any of the studied comorbidities. Individuals with immunocompromising conditions and chronic lung disease were most at risk of breakthrough infection, while people with CKD were most at risk of hospitalization following breakthrough infection. Patients with multiple comorbidities have an even greater risk of breakthrough infection or hospitalization compared to patients with none of the studied comorbidities. Individuals with common comorbidities should remain vigilant against infection even if vaccinated.

Autoimmune haemolytic anaemia due to immunodeficiency

Autoimmune disorders are common presenting manifestations of immunodeficiency syndromes. We present a case of a woman in her late teens, with a history of frequent sinopulmonary tract infections during her childhood, who presented to our hospital with anaemia, jaundice and fatigue. She also had significant physical growth retardation for her age and sex. With this case report, we intend to present the diagnostic and therapeutic challenges faced by the patient and our healthcare system and propose a few feasible solutions to tackle these challenges.

Getting More Out of Large Databases and EHRs with Natural Language Processing and Artificial Intelligence: The Future Is Here

Electronic health records (EHRs) have created great opportunities to collect various information from clinical patient encounters. However, most EHR data are stored in unstructured form (e.g., clinical notes, surgical notes, and medication instructions), and researchers need data to be in computable form (structured) to extract meaningful relationships involving variables that can influence patient outcomes. Clinical natural language processing (NLP) is the field of extracting structured data from unstructured text documents in EHRs. Clinical text has several characteristics that mandate the use of special techniques to extract structured information from them compared with generic NLP methods. In this article, we define clinical NLP models, introduce different methods of information extraction from unstructured data using NLP, and describe the basic technical aspects of how deep learning-based NLP models work. We conclude by noting the challenges of working with clinical NLP models and summarizing the general steps needed to launch an NLP project.

Machine Learning and Deep Learning in Cardiothoracic Imaging: A Scoping Review

Machine-learning (ML) and deep-learning (DL) algorithms are part of a group of modeling algorithms that grasp the hidden patterns in data based on a training process, enabling them to extract complex information from the input data. In the past decade, these algorithms have been increasingly used for image processing, specifically in the medical domain. Cardiothoracic imaging is one of the early adopters of ML/DL research, and the COVID-19 pandemic resulted in more research focus on the feasibility and applications of ML/DL in cardiothoracic imaging. In this scoping review, we systematically searched available peer-reviewed medical literature on cardiothoracic imaging and quantitatively extracted key data elements in order to get a big picture of how ML/DL have been used in the rapidly evolving cardiothoracic imaging field. During this report, we provide insights on different applications of ML/DL and some nuances pertaining to this specific field of research. Finally, we provide general suggestions on how researchers can make their research more than just a proof-of-concept and move toward clinical adoption.

Efficiency and Safety of Electronic Health Records in Switzerland-A Comparative Analysis of 2 Commercial Systems in Hospitals

OBJECTIVES

Differences in efficiency and safety between 2 electronic health record (systems A and B) in Swiss hospitals were investigated.

METHODS

In a scenario-based usability test under experimental conditions, a total of 100 physicians at 4 hospitals were asked to complete typical routine tasks, like medication or imaging orders. Differences in number of mouse clicks and time-on-task as indicators of efficiency and error type, error count, and rate as indicators of patient safety between hospital sites were analyzed. Time-on-task and clicks were correlated with error count.

RESULTS

There were differences in efficiency and safety between hospitals. Overall, physicians working with system B required less clicks (A: 511, B: 442, P = 0.001) and time (A: 2055 seconds, B: 1713 seconds, P = 0.055) and made fewer errors (A: 40%, B: 27%, P < 0.001). No participant completed all tasks correctly. The most frequent error in medication and radiology ordering was a wrong dose and a wrong level, respectively. Time errors were particularly prevalent in laboratory orders. Higher error counts coincided with longer time-on-task (r = 0.50, P < 0.001) and more clicks (r = 0.47, P < 0.001).

CONCLUSIONS

The variations in clicks, time, and errors are likely due to naive functionality and design of the systems and differences in their implementation. The high error rates coincide with inefficiency and jeopardize patient safety and produce economic costs and burden on physicians. The results raise usability concerns with potential for severe patient harm. A deeper understanding of differences as well as regulative guidelines and policy making are needed.

Acceleration of mobile health for monitoring post-transplant in the COVID-19 era: Applications for pediatric settings

BACKGROUND

Since the start of the COVID-19 pandemic and consequent lockdowns, the use of telehealth interventions has rapidly increased both in the general population and among transplant recipients. Among pediatric transplant recipients, this most frequently takes the form of interventions on mobile devices, or mHealth, such as remote visits via video chat or phone, phone-based monitoring, and mobile apps. Telehealth interventions may offer the opportunity to provide care that minimizes many of the barriers of in-person care.

METHODS

The present review followed the PRISMA guidelines. Sources up until October 2020 were initially identified through searches of PsycInfo^® and PubMed^® .

RESULTS

We identified ten papers that reported findings from adult interventions and five studies based in pediatrics. Eight of the adult publications stemmed from the same two trials; within the pediatric subset, this was the case for two papers. Studies that have looked at mHealth interventions have found high acceptability rates over the short run, but there is a general lack of data on long-term use.

CONCLUSIONS

The literature surrounding pediatric trials specifically is sparse with all findings referencing interventions that are in early stages of development, ranging from field tests to small feasibility trials. The lack of research highlights the need for a multi-center RCT that utilizes robust measures of medication adherence and other outcome variables, with longer-term follow-up before telehealth interventions should be fully embraced.

Exploring the relationship between electronic health records and provider burnout: A systematic review

OBJECTIVE

Stress and burnout due to electronic health record (EHR) technology has become a focus for burnout intervention. The aim of this study is to systematically review the relationship between EHR use and provider burnout.

MATERIALS AND METHODS

A systematic literature search was performed on PubMed, EMBASE, PsychInfo, ACM Digital Library in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) statement. Inclusion criterion was original research investigating the association between EHR and provider burnout. Studies that did not measure the association objectively were excluded. Study quality was assessed using the Medical Education Research Study Quality Instrument. Qualitative synthesis was also performed.

RESULTS

Twenty-six studies met inclusion criteria. The median sample size of providers was 810 (total 20 885; 44% male; mean age 53 [range, 34-56] years). Twenty-three (88%) studies were cross-sectional studies and 3 were single-arm cohort studies measuring pre- and postintervention burnout prevalence. Burnout was assessed objectively with various validated instruments. Insufficient time for documentation (odds ratio [OR], 1.40-5.83), high inbox or patient call message volumes (OR, 2.06-6.17), and negative perceptions of EHR by providers (OR, 2.17-2.44) were the 3 most cited EHR-related factors associated with higher rates of provider burnout that was assessed objectively.

CONCLUSIONS

The included studies were mostly observational studies; thus, we were not able to determine a causal relationship. Currently, there are few studies that objectively assessed the relationship between EHR use and provider burnout. The 3 most cited EHR factors associated with burnout were confirmed and should be the focus of efforts to improve EHR-related provider burnout.

A New Dimension of Health Care: The Benefits, Limitations and Implications of Virtual Medicine

Background: Virtual medicine has been rapidly evolving over the past several decades. However, obstacles such as data security, inadequate funding and limited technological resources have hindered its seamless incorporation into the health care system.  The recent pandemic has induced a widespread adoption of virtual care practices to remove the need for physical meetings between patients and health care practitioners. Purpose: This literature review aims to examine the current state of virtual medicine amid the COVID-19 pandemic and evaluate the benefits, limitations and implications of continuing technological advancements in the future. Findings: Most of the available literature suggests that the recent adoption of virtual medicine has allowed practitioners to cut down on costs and secondary expenses while maintaining the quality of medical care services. Due to the growing consumer demand, researchers predict that virtual medicine may be a viable modality for patient care post-pandemic. However, concerns surrounding patient security and digital infrastructure threaten the ability of virtual medicine to provide quality and effective health care. Additionally, rural virtual medicine programs face challenges in expanding services due to the scarcity of information and communication technology specialists and inadequate funding. Comprehensive legislation and governance standards must be implemented to ensure proper data security and privacy. Additional funds may also be required to train staff, reform current digital software and improve the quality of service. The proliferation of advanced technologies and improvements in current platforms will enable more providers to render virtual medical care services.

Role of Artificial Intelligence (AI) in Surgery: Introduction, General Principles, and Potential Applications

AI (Artificial intelligence) is an interdisciplinary field aimed at the development of algorithms to endow machines with the capability of executing cognitive tasks. The number of publications regarding AI and surgery has increased dramatically over the last two decades. This phenomenon can partly be explained by the exponential growth in computing power available to the largest AI training runs. AI can be classified into different sub-domains with extensive potential clinical applications in the surgical setting. AI will increasingly become a major component of clinical practice in surgery. The aim of the present Narrative Review is to give a general introduction and summarized overview of AI, as well as to present additional remarks on potential surgical applications and future perspectives in surgery.