Early Warning Systems for Critical Illness Outside the Intensive Care Unit

Early warning systems (EWSs) are designed and deployed to create a rapid assessment and response for patients with clinical deterioration outside the intensive care unit (ICU). These models incorporate patient-level data such as vital signs and laboratory values to detect or prevent adverse clinical events, such as vital signs and laboratories to allow detection and prevention of adverse clinical events such as cardiac arrest, intensive care transfer, or sepsis. The applicability, development, clinical utility, and general perception of EWS in clinical practice vary widely. Here, we review the field as it has grown from early vital sign-based scoring systems to contemporary multidimensional algorithms and predictive technologies for clinical decompensation outside the ICU.

Calculated Medicine: Seven Decades of Accelerating Growth

The field of Calculated Medicine has grown substantially over the last 7 decades. Comprised of objective, evidence-based medical decision tools, Calculated Medicine has broad application in medical practice, medical research, and health care management. This article reviews the history and varied methodologies of Calculated Medicine, starting with the 1953 Apgar score and concluding with a look into modern computational tools of the field: machine learning, natural language processing, artificial intelligence, and in silico research techniques. We'll also review and quantify the rapidly accelerating growth of Calculated Medicine in the medical literature. Our database of journal articles referring to the field has accumulated over 1.8 million citations, with more than 460 new citations (on average) posted every day. Using natural language processing, we examine and analyze this burgeoning database. Lastly, we examine an important new direction of Calculated Medicine: self-reflection on its potential effect on racial and ethnic disparities in health care. Our field is making great strides promoting health care egality, and some of the most prominent contributions will be reviewed.

Training pediatric physicians and staff to obtain data from the electronic health record

Electronic health records (EHRs) have provided physicians with user-friendly self-service reporting tools to extract patient data from the EHR. Despite such benefits, physician training on how to use these tools has been limited. At our institution, physicians were faced with prolonged wait time for EHR data extraction requests and were unaware of self-service reporting tool availability in the EHR. Our goal was to develop an EHR data reporting curriculum for physicians and staff and examine the effectiveness of such training. In 2019, physician informaticists developed two interactive sessions to train physicians and staff on self-service reporting tools (Epic® SlicerDicer and Reporting Workbench (RWB)) available in our tertiary children's hospital EHR. We assessed participants' knowledge, confidence, and tool utilization before, after, and 3-months post training via survey. Training sessions occurred between April and August 2021. Thirty-six participants completed the study, with 25 surveys collected immediately post and 22 surveys collected at 3-months post training. Data literacy knowledge pre-test average score improved from 62% to 93% (p < 0.05) immediately post-session and 74% at 3-months post assessment (p = 0.05). Regular tool utilization increased from 29% (RWB) and 34% (SlicerDicer) pre-session to 56% and 44% at 3-months post, respectively. Participants reported increased confidence in performing SlicerDicer model selection, criteria selection, and data visualization as well as RWB report navigation, report creation, report visualization, and describing report's benefits/limitations. Ultimately, physician and staff self-service reporting tools training were effective in increasing data literacy knowledge, tool utilization, and confidence.

Diabetes and artificial intelligence beyond the closed loop: a review of the landscape, promise and challenges

The discourse amongst diabetes specialists and academics regarding technology and artificial intelligence (AI) typically centres around the 10% of people with diabetes who have type 1 diabetes, focusing on glucose sensors, insulin pumps and, increasingly, closed-loop systems. This focus is reflected in conference topics, strategy documents, technology appraisals and funding streams. What is often overlooked is the wider application of data and AI, as demonstrated through published literature and emerging marketplace products, that offers promising avenues for enhanced clinical care, health-service efficiency and cost-effectiveness. This review provides an overview of AI techniques and explores the use and potential of AI and data-driven systems in a broad context, covering all diabetes types, encompassing: (1) patient education and self-management; (2) clinical decision support systems and predictive analytics, including diagnostic support, treatment and screening advice, complications prediction; and (3) the use of multimodal data, such as imaging or genetic data. The review provides a perspective on how data- and AI-driven systems could transform diabetes care in the coming years and how they could be integrated into daily clinical practice. We discuss evidence for benefits and potential harms, and consider existing barriers to scalable adoption, including challenges related to data availability and exchange, health inequality, clinician hesitancy and regulation. Stakeholders, including clinicians, academics, commissioners, policymakers and those with lived experience, must proactively collaborate to realise the potential benefits that AI-supported diabetes care could bring, whilst mitigating risk and navigating the challenges along the way.

AI-Enhanced Healthcare: Not a new Paradigm for Informed Consent

With the increasing prevalence of artificial intelligence (AI) and other digital technologies in healthcare, the ethical debate surrounding their adoption is becoming more prominent. Here I consider the issue of gaining informed patient consent to AI-enhanced care from the vantage point of the United Kingdom's National Health Service setting. I build my discussion around two claims from the World Health Organization: that healthcare services should not be denied to individuals who refuse AI-enhanced care and that there is no precedence to seeking patient consent to AI-enhanced care. I discus U.K. law relating to patient consent and the General Data Protection Regulation to show that current standards relating to patient consent are adequate for AI-enhanced care. I then suggest that in the future it may not be possible to guarantee patient access to non-AI-enhanced healthcare, in a similar way to how we do not offer patients manual alternatives to automated healthcare processes. Throughout my discussion I focus on the issues of patient choice and veracity in the patient-clinician relationship. Finally, I suggest that the best way to protect patients from potential harms associated with the introduction of AI to patient care is not via an overly burdensome patient consent process but via evaluation and regulation of AI technologies.

Imaging Wisely Campaign: Initiative to Reduce Imaging for Low Back Pain Across a Large Safety Net System

OBJECTIVES

Low back pain is a common clinical presentation that often results in expensive and unnecessary imaging that may lead to undue patient harm, including unnecessary procedures. We present an initiative in a safety net system to reduce imaging for low back pain.

METHODS

This quality improvement study was conducted across 70 ambulatory clinics and 11 teaching hospitals. Three electronic health record changes, using the concept of a nudge, were introduced into orders for lumbar radiography (x-ray), lumbar CT, and lumbar MRI. The primary outcome was the number of orders per 1,000 patient-days or encounters for each imaging test in the inpatient, ambulatory, and emergency department (ED) settings. Variation across facilities was assessed, along with selected indications.

RESULTS

Across all clinical environments, there were statistically significant decreases in level differences pre- and postintervention for lumbar x-ray (-52.9% for inpatient encounters, P < .001; -23.7% for ambulatory encounters, P < .001; and -17.3% for ED only encounters, P < .01). There was no decrease in ordering of lumbar CTs in the inpatient and ambulatory settings, although there was an increase in lumbar CTs in ED-only encounters. There was no difference in lumbar MRI ordering. Variation was seen across all hospitals and clinics.

DISCUSSION

Our intervention successfully decreased lumbar radiography across all clinical settings, with a reduction in lumbar CTs in the inpatient and ambulatory settings. There were no changes for lumbar MRI orders.

Predictive Modeling Using Artificial Intelligence and Machine Learning Algorithms on Electronic Health Record Data: Advantages and Challenges

The rapid adoption of electronic health record (EHR) systems in US hospitals from 2008 to 2014 produced novel data elements for analysis. Concurrent innovations in computing architecture and machine learning (ML) algorithms have made rapid consumption of health data feasible and a powerful engine for clinical innovation. In critical care research, the net convergence of these trends has resulted in an exponential increase in outcome prediction research. In the following article, we explore the history of outcome prediction in the intensive care unit (ICU), the growing use of EHR data, and the rise of artificial intelligence and ML (AI) in critical care.

Overview of the 2022 n2c2 shared task on contextualized medication event extraction in clinical notes

BACKGROUND

An accurate medication history, foundational for providing quality medical care, requires understanding of medication change events documented in clinical notes. However, extracting medication changes without the necessary clinical context is insufficient for real-world applications.

METHODS

To address this need, Track 1 of the 2022 National NLP Clinical Challenges focused on extracting the context for medication changes documented in clinical notes using the Contextualized Medication Event Dataset. Track 1 consisted of 3 subtasks: extracting medication mentions from clinical notes (NER), determining whether a medication change is being discussed (Event), and determining the action, negation, temporality, certainty, and actor for any change events (Context). Participants were allowed to participate in any one or more of the subtasks.

RESULTS

A total of 32 teams with participants from 19 countries submitted a total of 211 systems across all subtasks. Most teams formulated NER as a token classification task and Event and Context as multi-class classification tasks, using transformer-based large language models. Overall, performance for NER was high across submitted systems. However, performance for Event and Context were much lower, often due to indirectly stated change events with no clear action verb, events requiring farther textual clues for understanding, and medication mentions with multiple change events.

CONCLUSIONS

This shared task showed that while NLP research on medication extraction is relatively mature, understanding of contextual information surrounding medication events in clinical notes is still an open problem requiring further research to achieve the end goal of supporting real-world clinical applications.

Capacity-Building for Collecting Patient-Reported Outcomes and Experiences (PRO) Data Across Hospitals

PURPOSE

Patient-reported outcomes and experiences (PRO) data are an integral component of health care quality measurement and PROs are now being collected by many healthcare systems. However, hospital organizational capacity-building for the collection and sharing of PROs is a complex process. We sought to identify the factors that facilitated capacity-building for PRO data collection in a nascent quality improvement learning collaborative of 16 hospitals that has the goal of improving the childbirth experience.

DESCRIPTION

We used standard qualitative case study methodologies based on a conceptual framework that hypothesizes that adequate organizational incentives and capacities allow successful achievement of project milestones in a collaborative setting. The 4 project milestones considered in this study were: (1) Agreements; (2) System Design; (3) System Development and Operations; and (4) Implementation. To evaluate the success of reaching each milestone, critical incidents were logged and tracked to determine the capacities and incentives needed to resolve them.

ASSESSMENT

The pace of the implementation of PRO data collection through the 4 milestones was uneven across hospitals and largely dependent on limited hospital capacities in the following 8 dimensions: (1) Incentives; (2) Leadership; (3) Policies; (4) Operating systems; (5) Information technology; (6) Legal aspects; (7) Cross-hospital collaboration; and (8) Patient engagement. From this case study, a trajectory for capacity-building in each dimension is discussed.

CONCLUSION

The implementation of PRO data collection in a quality improvement learning collaborative was dependent on multiple organizational capacities for the achievement of project milestones.

The Electronic Health Record as a Quality Improvement Tool: Exceptional Potential with Special Considerations

The electronic health record (EHR) offers an exciting opportunity for quality improvement efforts. An understanding of the nuances of a site's EHR landscape including the best practices in clinical decision support design, basics of data capture, and acknowledgment of the potential unintended consequences of technology change is essential to ensuring effective usage of this powerful tool.

A method for comparing multiple imputation techniques: A case study on the U.S. national COVID cohort collaborative

Healthcare datasets obtained from Electronic Health Records have proven to be extremely useful for assessing associations between patients' predictors and outcomes of interest. However, these datasets often suffer from missing values in a high proportion of cases, whose removal may introduce severe bias. Several multiple imputation algorithms have been proposed to attempt to recover the missing information under an assumed missingness mechanism. Each algorithm presents strengths and weaknesses, and there is currently no consensus on which multiple imputation algorithm works best in a given scenario. Furthermore, the selection of each algorithm's parameters and data-related modeling choices are also both crucial and challenging. In this paper we propose a novel framework to numerically evaluate strategies for handling missing data in the context of statistical analysis, with a particular focus on multiple imputation techniques. We demonstrate the feasibility of our approach on a large cohort of type-2 diabetes patients provided by the National COVID Cohort Collaborative (N3C) Enclave, where we explored the influence of various patient characteristics on outcomes related to COVID-19. Our analysis included classic multiple imputation techniques as well as simple complete-case Inverse Probability Weighted models. Extensive experiments show that our approach can effectively highlight the most promising and performant missing-data handling strategy for our case study. Moreover, our methodology allowed a better understanding of the behavior of the different models and of how it changed as we modified their parameters. Our method is general and can be applied to different research fields and on datasets containing heterogeneous types.

Sex Differences in Health Conditions Associated with Sexual Assault in a Large Hospital Population

Introduction

Sexual assault is an urgent public health concern with both immediate and long-lasting health consequences, affecting 44% of women and 25% of men during their lifetimes. Large studies are needed to understand the unique healthcare needs of this patient population.

Methods

We mined clinical notes to identify patients with a history of sexual assault in the electronic health record (EHR) at Vanderbilt University Medical Center (VUMC), a large university hospital in the Southeastern USA, from 1989 to 2021 (N = 3,376,424). Using a phenome-wide case-control study, we identified diagnoses co-occurring with disclosures of sexual assault. We performed interaction tests to examine whether sex modified any of these associations. Association analyses were restricted to a subset of patients receiving regular care at VUMC (N = 833,185).

Results

The phenotyping approach identified 14,496 individuals (0.43%) across the VUMC-EHR with documentation of sexual assault and achieved a positive predictive value of 93.0% (95% confidence interval = 85.6-97.0%), determined by manual patient chart review. Out of 1,703 clinical diagnoses tested across all subgroup analyses, 465 were associated with sexual assault. Sex-by-trauma interaction analysis revealed 55 sex-differential associations and demonstrated increased odds of psychiatric diagnoses in male survivors.

Discussion

This case-control study identified associations between disclosures of sexual assault and hundreds of health conditions, many of which demonstrated sex-differential effects. The findings of this study suggest that patients who have experienced sexual assault are at risk for developing wide-ranging medical and psychiatric comorbidities and that male survivors may be particularly vulnerable to developing mental illness.

Bringing student health and Well-Being onto a health system EHR: the benefits of integration in the COVID-19 era

ObjectiveTo detail the implementation, benefits and challenges of onboarding campus-based health services onto a health system's electronic health record.ParticipantsUC San Diego Student Health and Well-Being offers medical services to over 39,000 students. UC San Diego Health is an academic medical center.Methods20 workstreams and 9 electronic modules, systems, or interfaces were converted to new electronic systems.Results36,023 student-patient medical records were created. EHR-integration increased security while creating visibility to 19,700 shared patient visits and records from 236 health systems across the country over 6 months. Benefits for the COVID-19 response included access to screening tools, decision support, telehealth, patient alerting system, reporting and analytics, COVID-19 dashboard, and increased testing capabilities.ConclusionIntegration of an interoperable EHR between neighboring campus-based health services and an affiliated academic medical center can streamline case management, improve quality and safety, and increase access to valuable health resources in times of need. Pertinent examples during the COVID-19 pandemic included uninterrupted and safe provision of clinical services through access to existing telehealth platforms and increased testing capacity.

Identifying and adapting interventions to reduce documentation burden and improve nurses' efficiency in using electronic health record systems (The IDEA Study): protocol for a mixed methods study

Background

Although EHR systems have become a critical part of clinical care, nurses are experiencing a growing burden due to documentation requirements, taking time away from other important clinical activities. There is a need to address the inefficiencies and challenges that nurses face when documenting in and using EHRs. The objective of this study is to engage nurses in generating ideas on how organizations can support and optimize nurses’ experiences with their EHR systems, thereby improving efficiency and reducing EHR-related burden. This work will ensure the identified solutions are grounded in nurses’ perspectives and experiences and will address their specific EHR-related needs.

Methods

This mixed methods study will consist of three phases. Phase 1 will evaluate the accuracy of the EHR system’s analytics platform in capturing how nurses utilize the system in real-time for tasks such as documentation, chart review, and medication reconciliation. Phase 2 consists of a retrospective analysis of the nursing-specific analytics platform and focus groups with nurses to understand and contextualize their usage patterns. These focus groups will also be used to identify areas for improvement in the utilization of the EHR. Phase 3 will include focus groups with nurses to generate and adapt potential interventions to address the areas for improvement and assess the perceived relevance, feasibility, and impact of the potential interventions.

Discussion

This work will generate insights on addressing nurses’ EHR-related burden and burnout. By understanding and contextualizing inefficiencies and current practices, opportunities to improve EHR systems for nursing professional practice will be identified. The study findings will inform the co-design and implementation of interventions that will support adoption and impact. Future work will include the evaluation of the developed interventions, and research on scaling and disseminating the interventions for use in different organizations, EHR systems, and jurisdictions in Canada.

Clinical Informatics and Quality Improvement in the Pediatric Intensive Care Unit

Clinical informatics can support quality improvement and patient safety in the pediatric intensive care unit (PICU) in several ways including data extraction, analysis, and decision support enabled by electronic health records (EHRs), and databases and registries. Clinical decision support (CDS), embedded in EHRs, now an integral part of the workflow in the PICU, includes several tools and is increasingly leveraging artificial intelligence (AI). Understanding the opportunities and challenges can improve the engagement of clinicians with the design, validation, and implementation of CDS, improve satisfaction with CDS, and improve patient safety, care quality, and value.

Social Determinants of Health Data Availability for Patients with Eye Conditions

Purpose

To quantify and characterize social determinants of health (SDoH) data coverage using single-center electronic health records (EHRs) and the National Institutes of Health All of Us research program.

Design

Retrospective cohort study from June 2014 through June 2021.

Participants

Adults 18 years of age or older with a diagnosis of diabetic retinopathy, glaucoma, cataracts, or age-related macular degeneration.

Methods

For All of Us, research participants completed online survey forms as part of a nationwide prospective cohort study. In local EHRs, patients were selected based on diagnosis codes.

Main Outcome Measures

Social determinants of health data coverage, characterized by the proportion of each disease cohort with available data regarding demographics and socioeconomic factors.

Results

In All of Us, we identified 23 806 unique adult patients, of whom 2246 had a diagnosis of diabetic retinopathy, 13 448 had a diagnosis of glaucoma, 6634 had a diagnosis of cataracts, and 1478 had a diagnosis of age-related macular degeneration. Survey completion rates were high (99.5%-100%) across all cohorts for demographic information, overall health, income, education, and lifestyle. However, health care access (12.7%-29.4%), housing (0.7%-1.1%), social isolation (0.2%-0.3%), and food security (0-0.1%) showed significantly lower response rates. In local EHRs, we identified 80 548 adult patients, of whom 6616 had a diagnosis of diabetic retinopathy, 26 793 had a diagnosis of glaucoma, 40 427 had a diagnosis of cataracts, and 6712 had a diagnosis of age-related macular degeneration. High data coverage was found across all cohorts for variables related to tobacco use (82.84%-89.07%), alcohol use (77.45%-83.66%), and intravenous drug use (84.76%-93.14%). However, low data coverage (< 50% completion) was found for all other variables, including education, finances, social isolation, stress, physical activity, food insecurity, and transportation. We used chi-square testing to assess whether the data coverage varied across different disease cohorts and found that all fields varied significantly (P < 0.001).

Conclusions

The limited and highly variable data coverage in both local EHRs and All of Us highlights the need for researchers and providers to develop SDoH data collection strategies and to assemble complete datasets.

Reuniting Long Lost Cousins: a Novel Curriculum in Imaging Informatics for Clinical Informatics Fellows

We developed a curriculum of imaging informatics for clinical informatics fellows. While imaging informatics and clinical informatics are related fields, they have distinct bodies of knowledge. The aim of this curriculum is to prepare clinical informatics fellows for questions regarding imaging informatics on the clinical informatics board certification examination, prepare fellows to handle issues and requests involving imaging informatics in their future roles as clinical informaticists, and develop sufficient knowledge and skills in order to interface with imaging and radiology domain experts. We mapped ACGME core competencies for clinical informatics and the clinical informatics skills and attributes to topics covered in this curriculum. Topics covered included orders vs. encounter-based workflow, understanding imaging informatics operations and the differences between an IT department leading digital image management and the radiology department, clinical decision support for radiology, procuring and integrating new modalities into a PACS system, troubleshooting slow application performance in a PACS environment, imaging sharing, artificial intelligence (AI) in imaging including AI bias, validation of models within home institution and regulatory issues, and structured reporting vs. Natural Language Processing to mine radiology report data. These topics were covered in interactive didactic sessions as well as a journal club. Future work will expand to include hands-on learning and a formal evaluation of this curriculum with current fellows and recent graduates.

Leveraging structured and unstructured electronic health record data to detect reasons for suboptimal statin therapy use in patients with atherosclerotic cardiovascular disease

OBJECTIVE

To determine whether natural language processing (NLP) of unstructured medical text can improve identification of ASCVD patients not using high-intensity statin therapy (HIST) due to statin-associated side effects (SASEs) and other reasons.

METHODS

Reviewers annotated reasons for not prescribing HIST in notes of 1152 randomly selected patients from across the VA healthcare system treated for ASCVD but not receiving HIST. Developers used reviewer annotations to train the Canary NLP tool to detect and extract notes containing one or more of these reasons. Negative predictive value (NPV), sensitivity, specificity and Area Under the Curve (AUC) were used to assess accuracy at detecting documents containing reasons when using structured data, NLP-extracted unstructured data, or both data sources combined.

RESULTS

At least one documented reason for not prescribing HIST occurred in 47% of notes. The most frequent reasons were SASEs (41%) and general intolerance (20%). When identifying notes containing any documented reason for not using HIST, adding NLP-extracted, unstructured data significantly (p<0.05) increased sensitivity (0.69 (95% confidence interval [CI] 0.60-0.76) to 0.89 (95% CI 0.81-0.93)), NPV (0.90 (95% CI 0.87 to 0.93) to 0.96 (95% CI 0.93-0.98)), and AUC (0.84 (95% confidence interval [CI] 0.81-0.88) to 0.91 (95% CI 0.90-0.93)) compared to structured data alone.

CONCLUSIONS

NLP extraction of data from unstructured text can improve identification of reasons for patients not being on HIST over structured data alone. The additional information provided through NLP of unstructured free text should help in tailoring and implementing system-level interventions to improve HIST use in patients with ASCVD.

Enhancing Diagnosis Through Technology: Decision Support, Artificial Intelligence, and Beyond

Patient care in intensive care environments is complex, time-sensitive, and data-rich, factors that make these settings particularly well-suited to clinical decision support (CDS). A wide range of CDS interventions have been used in intensive care unit environments. The field needs well-designed studies to identify the most effective CDS approaches. Evolving artificial intelligence and machine learning models may reduce information-overload and enable teams to take better advantage of the large volume of patient data available to them. It is vital to effectively integrate new CDS into clinical workflows and to align closely with the cognitive processes of frontline clinicians.

Word embeddings trained on published case reports are lightweight, effective for clinical tasks, and free of protected health information

OBJECTIVE

Quantify tradeoffs in performance, reproducibility, and resource demands across several strategies for developing clinically relevant word embeddings.

MATERIALS AND METHODS

We trained separate embeddings on all full-text manuscripts in the Pubmed Central (PMC) Open Access subset, case reports therein, the English Wikipedia corpus, the Medical Information Mart for Intensive Care (MIMIC) III dataset, and all notes in the University of Pennsylvania Health System (UPHS) electronic health record. We tested embeddings in six clinically relevant tasks including mortality prediction and de-identification, and assessed performance using the scaled Brier score (SBS) and the proportion of notes successfully de-identified, respectively.

RESULTS

Embeddings from UPHS notes best predicted mortality (SBS 0.30, 95% CI 0.15 to 0.45) while Wikipedia embeddings performed worst (SBS 0.12, 95% CI -0.05 to 0.28). Wikipedia embeddings most consistently (78% of notes) and the full PMC corpus embeddings least consistently (48%) de-identified notes. Across all six tasks, the full PMC corpus demonstrated the most consistent performance, and the Wikipedia corpus the least. Corpus size ranged from 49 million tokens (PMC case reports) to 10 billion (UPHS).

DISCUSSION

Embeddings trained on published case reports performed as least as well as embeddings trained on other corpora in most tasks, and clinical corpora consistently outperformed non-clinical corpora. No single corpus produced a strictly dominant set of embeddings across all tasks and so the optimal training corpus depends on intended use.

CONCLUSION

Embeddings trained on published case reports performed comparably on most clinical tasks to embeddings trained on larger corpora. Open access corpora allow training of clinically relevant, effective, and reproducible embeddings.

PhD Nursing Students' Perceptions Towards Clinical Informatics Course

This paper aims to investigate PhD nursing students' perceptions regarding a clinical informatics course. Open-ended questionnaires and reviews were used to explore the students' perception of the course. A total of 84.62% (11/13) students responded to the survey. Only four respondents had an understanding of clinical informatics and others did not. All the respondents considered clinical informatics to be a very important and useful course for PhD nursing students.

A statistical quality assessment method for longitudinal observations in electronic health record data with an application to the VA million veteran program

Background

To describe an automated method for assessment of the plausibility of continuous variables collected in the electronic health record (EHR) data for real world evidence research use.

Methods

The most widely used approach in quality assessment (QA) for continuous variables is to detect the implausible numbers using prespecified thresholds. In augmentation to the thresholding method, we developed a score-based method that leverages the longitudinal characteristics of EHR data for detection of the observations inconsistent with the history of a patient. The method was applied to the height and weight data in the EHR from the Million Veteran Program Data from the Veteran’s Healthcare Administration (VHA). A validation study was also conducted.

Results

The receiver operating characteristic (ROC) metrics of the developed method outperforms the widely used thresholding method. It is also demonstrated that different quality assessment methods have a non-ignorable impact on the body mass index (BMI) classification calculated from height and weight data in the VHA’s database.

Conclusions

The score-based method enables automated and scaled detection of the problematic data points in health care big data while allowing the investigators to select the high-quality data based on their need. Leveraging the longitudinal characteristics in EHR will significantly improve the QA performance.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-021-01643-2.

Simulation-derived best practices for clustering clinical data

INTRODUCTION

Clustering analyses in clinical contexts hold promise to improve the understanding of patient phenotype and disease course in chronic and acute clinical medicine. However, work remains to ensure that solutions are rigorous, valid, and reproducible. In this paper, we evaluate best practices for dissimilarity matrix calculation and clustering on mixed-type, clinical data.

METHODS

We simulate clinical data to represent problems in clinical trials, cohort studies, and EHR data, including single-type datasets (binary, continuous, categorical) and 4 data mixtures. We test 5 single distance metrics (Jaccard, Hamming, Gower, Manhattan, Euclidean) and 3 mixed distance metrics (DAISY, Supersom, and Mercator) with 3 clustering algorithms (hierarchical (HC), k-medoids, self-organizing maps (SOM)). We quantitatively and visually validate by Adjusted Rand Index (ARI) and silhouette width (SW). We applied our best methods to two real-world data sets: (1) 21 features collected on 247 patients with chronic lymphocytic leukemia, and (2) 40 features collected on 6000 patients admitted to an intensive care unit.

RESULTS

HC outperformed k-medoids and SOM by ARI across data types. DAISY produced the highest mean ARI for mixed data types for all mixtures except unbalanced mixtures dominated by continuous data. Compared to other methods, DAISY with HC uncovered superior, separable clusters in both real-world data sets.

DISCUSSION

Selecting an appropriate mixed-type metric allows the investigator to obtain optimal separation of patient clusters and get maximum use of their data. Superior metrics for mixed-type data handle multiple data types using multiple, type-focused distances. Better subclassification of disease opens avenues for targeted treatments, precision medicine, clinical decision support, and improved patient outcomes.

Machine Learning and Clinical Informatics for Improving HIV Care Continuum Outcomes

PURPOSE OF REVIEW

This manuscript reviews the use of electronic medical record (EMR) data for HIV care and research along the HIV care continuum with a specific focus on machine learning methods and clinical informatics interventions.

RECENT FINDINGS

EMR-based clinical decision support tools and electronic alerts have been effectively utilized to improve HIV care continuum outcomes. Accurate EMR-based machine learning models have been developed to predict HIV diagnosis, retention in care, and viral suppression. Natural language processing (NLP) of clinical notes and data sharing between healthcare systems and public health agencies can enhance models for identifying people living with HIV who are undiagnosed or in need of relinkage to care. Challenges related to using these technologies include inconsistent EMR documentation, alert fatigue, and the potential for bias. Clinical informatics and machine learning models are promising tools for improving HIV care continuum outcomes. Future research should focus on methods for combining EMR data with additional data sources (e.g., social media, geospatial data) and studying how to effectively implement predictive models for HIV care into clinical practice.

Electronic medical record implementation in tertiary care: factors influencing adoption of an electronic medical record in a cancer centre

Background

Electronic Medical Records (EMRs) are one of a range of digital health solutions that are key enablers of the data revolution transforming the health sector. They offer a wide range of benefits to health professionals, patients, researchers and other key stakeholders. However, effective implementation has proved challenging.

Methods

A qualitative methodology was used in the study. Interviews were conducted with 12 clinical and administrative staff of a cancer centre at one-month pre-launch and eight clinical and administrative staff at 12-months post-launch of an EMR. Data from the interviews was collected via audio recording. Audio recordings were transcribed, de-identified and analysed to identify staff experiences with the EMR.

Results

Data from the pre-implementation interviews were grouped into four categories: 1) Awareness and understanding of EMR; 2) Engagement in launch process; 3) Standardisation and completeness of data; 4) Effect on workload. Data from the post-launch interviews were grouped into six categories: 1) Standardisation and completeness of data; 2) Effect on workload; 3) Feature completeness and functionality; 4) Interaction with technical support; 5) Learning curve; 6) Buy-in from staff. Two categories: Standardisation and completeness of data and effect on workload were common across pre and post-implementation interviews.

Conclusion

Findings from this study contribute new knowledge on barriers and enablers to the implementation of EMRs in complex clinical settings. Barriers to successful implementation include lack of technical support once the EMR has launched, health professional perception the EMR increases workload, and the learning curve for staff adequately familiarize themselves with using the EMR.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12913-020-06015-6.

Development and Optimization of Clinical Informatics Infrastructure to Support Bioinformatics at an Oncology Center

Translational bioinformatics for therapeutic discovery requires the infrastructure of clinical informatics. In this chapter, we describe the clinical informatics components needed for successful implementation of translational research at a cancer center. This chapter is meant to be an introduction to those clinical informatics concepts that are needed for translational research. For a detailed account of clinical informatics, the authors will guide the reader to comprehensive resources. We provide examples of workflows from Moffitt Cancer Center led by Drs. Perkins and Markowitz. This perspective represents an interesting collaboration as Dr. Perkins is the Chief Medical Information Officer and Dr. Markowitz is a translational researcher in Melanoma with an active informatics component to his laboratory to study the mechanisms of resistance to checkpoint blockade and an active member of the clinical informatics team.

Natural language processing and machine learning to enable automatic extraction and classification of patients' smoking status from electronic medical records

BACKGROUND

The electronic medical record (EMR) offers unique possibilities for clinical research, but some important patient attributes are not readily available due to its unstructured properties. We applied text mining using machine learning to enable automatic classification of unstructured information on smoking status from Swedish EMR data.

METHODS

Data on patients' smoking status from EMRs were used to develop 32 different predictive models that were trained using Weka, changing sentence frequency, classifier type, tokenization, and attribute selection in a database of 85,000 classified sentences. The models were evaluated using F-score and accuracy based on out-of-sample test data including 8500 sentences. The error weight matrix was used to select the best model, assigning a weight to each type of misclassification and applying it to the model confusion matrices. The best performing model was then compared to a rule-based method.

RESULTS

The best performing model was based on the Support Vector Machine (SVM) Sequential Minimal Optimization (SMO) classifier using a combination of unigrams and bigrams as tokens. Sentence frequency and attributes selection did not improve model performance. SMO achieved 98.14% accuracy and 0.981 F-score versus 79.32% and 0.756 for the rule-based model.

CONCLUSION

A model using machine-learning algorithms to automatically classify patients' smoking status was successfully developed. Such algorithms may enable automatic assessment of smoking status and other unstructured data directly from EMRs without manual classification of complete case notes.

Can Orthodontic Informatics Combat the Pandemic Pitfalls?

The largest public health crisis of our time, COVID-19 has recklessly squandered many of the channelized healthcare facilities globally with execution of newer guidelines over the standard architectural norms. There has been unparalleled use of smartphones and internet services to bear the major pitfall- social distancing- especially for elective treatment services. This demands a new paradigm shift from offline to online doctor-patient, student-educator, researcher-researcher operations. This articles provides an insight into potential role of orthodontic informatics to provide a combined platform to generate a learning system that routinely collects, correlates, and analyzes data for developing artificial intelligence programs, lab exploratory systems, clinical decision support systems and health-information exchange systems. In order to develop this system, orthodontic analytic communities as start-ups for developing user-friendly programs must be encouraged, where orthodontic informatics itself can be taken up as a didactic career source.

Impact of Provider Prior Use of HIE on System Complexity, Performance, Patient Care, Quality and System Concerns

To date, most HIE studies have investigated user perceptions of value prior to use. Few studies have assessed factors associated with the value of HIE through its actual use. This study investigates provider perceptions on HIE comparing those who had prior experience vs those who had no experience with it. In so doing, we identify six constructs: prior use, system complexity, system concerns, public/population health, care delivery, and provider performance. This study uses a mixed methods approach to data collection. From 15 interviews of medical community leaders, a survey was constructed and administered to 263 clinicians. Descriptive statistics and analysis of variance was used, along with Tukey HSD tests for multiple comparisons. Results indicated providers whom previously used HIE had more positive perceptions about its benefits in terms of system complexity (p = .001), care delivery (p = .000), population health (p = .003), and provider performance (p = .005); women providers were more positive in terms of system concerns (p = .000); patient care (p = .031), and population health (p = .009); providers age 44-55 were more positive than older and younger groups in terms of patient care (p = .032), population health (p = .021), and provider performance (p = .014); while differences also existed across professional license groups (physician, nurse, other license, admin (no license)) for all five constructs (p < .05); and type of organization setting (hospital, ambulatory clinic, medical office, other) for three constructs including system concerns (p = .017), population health (p = .018), and provider performance (p = .018). There were no statistically significant differences found between groups based on a provider's role in an organization (patient care, administration, teaching/research, other). Different provider perspectives about the value derived from HIE use exist depending on prior experience with HIE, age, gender, license (physician, nurse, other license, admin (no license)), and type of organization setting (hospital, ambulatory clinic, medical office, other). This study draws from the theory of planned behavior to understand factors related to physicians' perceptions about HIE value, serving as a departure point for more detailed investigations of provider perceptions and behavior in regard to future HIE use and promoting interoperability.

A short cultural history of the UK Renal Registry 1995-2020

The Renal Association UK Renal Registry (UKRR), established in 1995, has reflected the development of Nephrology within the NHS over 25 years. It has been gradually enlarged to provide a formal agency for a range of consensus initiatives. It remains the source of the national epidemiology of renal replacement, feeding NHS infrastructures and Health Services Research. An extension into acute and chronic kidney disorders is in hand. As a template for medical audit it has contributed to a quality improvement ethos derived from several methodologies. It now offers a multifaceted virtual platform for special interest groups and patient-centricity. Its transformation demonstrates one of the compromises that have permitted specialty development within the inconstant envelope of the NHS.

If not always a bellwether, the clarity, form and scale of kidney disease provision still qualifies the UKRR as a demonstrator of healthcare possibilities to Medicine, Clinical Informatics and the NHS.

Integration of International Classification of Diseases Version 11 Application Program Interface (API) in the Rwandan Electronic Medical Records (openMRS): Findings from Two District Hospitals in Rwanda

World Health Organisation (WHO) has updated the International Classification of Diseases to version 11 (ICD-11) which was recently adopted for use by countries in 2019. ICD-11 can be used in Electronic Medical Records (EMR) systems with support of extended technologies like Application Program Interface (API). Integration of ICD-11 in Rwandan EMR (OpenMRS) in two health facilities was conducted in July-October 2019. Findings indicated that adapting ICD11-API in EMR is feasible. More than 50% of diagnoses were recorded using ICD-11. Healthcare providers perceived ICD-11 API as easy to learn and useful for harmonization of diagnosis, data reporting and insurance reimbursement. Integration of ICD-11 API in EMR can be scaled up to all hospitals for use in Rwanda and other countries using similar system.

The Value of the Surgeon Informatician

Clinical informatics is an interdisciplinary specialty that leverages big data, health information technologies, and the science of biomedical informatics within clinical environments to improve quality and outcomes in the increasingly complex and often siloed health care systems. Core competencies of clinical informatics primarily focus on clinical decision making and care process improvement, health information systems, and leadership and change management. Although the broad relevance of clinical informatics is apparent, this review focuses on its application and pertinence to the discipline of surgery, which is less well defined. In doing so, we hope to highlight the importance of the surgeon informatician. Topics covered include electronic health records, clinical decision support systems, computerized order entry, data analytics, clinical documentation, information architectures, implementation science, quality improvement, simulation, education, and telemedicine. The formal pathway for surgeons to become clinical informaticians is also discussed.

Automatic detection algorithm for establishing standard to identify "surge blood pressure"

Blood pressure (BP) variability is one of the important risk factors of cardiovascular disease (CVD). “Surge BP,” which represents short-term BP variability, is defined as pathological exaggerated BP increase capable of triggering cardiovascular events. Surge BP is effectively evaluated by our new BP monitoring device. To the best of our knowledge, we are the first to develop an algorithm for the automatic detection of surge BP from continuous “beat-by-beat” (BbB) BP measurements. It enables clinicians to save significant time identifying surge BP in big data from their patients’ continuous BbB BP measurements. A total of 94 subjects (74 males and 20 females) participated in our study to develop the surge BP detection algorithm, resulting in a total of 3272 surges collected from the study subjects. The surge BP detection algorithm is a simple classification model based on supervised learning which formulates shape of surge BP as detection rules. Surge BP identified with our algorithm was evaluated against surge BP manually labeled by experts with 5-fold cross validation. The recall and precision of the algorithm were 0.90 and 0.64, respectively. Processing time on each subject was 11.0 ± 4.7 s. Our algorithm is adequate for use in clinical practice and will be helpful in efforts to better understand this unique aspect of the onset of CVD.

Graphical abstract

Confidential image transfer: an ethico-legal dilemma

Clinical photographs aid decision-making and represent important medicolegal records. Storage and transfer of images of the facial area must adhere to Caldicott Principles. Outside working hours, clinical photography services are often limited. Our Trust has introduced a Secure Clinical Image Transfer (SCIT) app allowing clinicians to take photographs on personal devices to be securely uploaded to the patient's electronic health record. To evaluate whether clinicians were taking clinical images in an insecure manner, clinicians completed an anonymous questionnaire before and after introduction of the SCIT app. The standard was 100% knowledge of, and adherence to, trust information governance guidelines. Response rate was 100% in both cycles. Introduction of the SCIT app reduced inappropriate clinical photography on personal devices. Our completed audit cycle shows that the SCIT app allows convenient, secure information capture on personal devices and automatic secure synchronisation to trust electronic health records.

Defining Major Depressive Disorder Cohorts Using the EHR: Multiple Phenotypes Based on ICD-9 Codes and Medication Orders

Background

Major Depressive Disorder (MDD) is one of the most common mental illnesses and a leading cause of disability worldwide. Electronic Health Records (EHR) allow researchers to conduct unprecedented large-scale observational studies investigating MDD, its disease development and its interaction with other health outcomes. While there exist methods to classify patients as clear cases or controls, given specific data requirements, there are presently no simple, generalizable, and validated methods to classify an entire patient population into varying groups of depression likelihood and severity.

Methods

We have tested a simple, pragmatic electronic phenotype algorithm that classifies patients into one of five mutually exclusive, ordinal groups, varying in depression phenotype. Using data from an integrated health system on 278,026 patients from a 10-year study period we have tested the convergent validity of these constructs using measures of external validation, including patterns of psychiatric prescriptions, symptom severity, indicators of suicidality, comorbidity, mortality, health care utilization, and polygenic risk scores for MDD.

Results

We found consistent patterns of increasing morbidity and/or adverse outcomes across the five groups, providing evidence for convergent validity.

Limitations

The study population is from a single rural integrated health system which is predominantly white, possibly limiting its generalizability.

Conclusion

Our study provides initial evidence that a simple algorithm, generalizable to most EHR data sets, provides categories with meaningful face and convergent validity that can be used for stratification of an entire patient population.

Health information technology:Fallacies and Sober realities - Redux A homage to Bentzi Karsh and Robert Wears

Since the publication of "Health Information Technology: Fallacies and Sober Realities" in 2010, health information technology (HIT) has become nearly ubiquitous in US healthcare facilities. Yet, HIT has yet to achieve its putative benefits of higher quality, safer, and lower cost care. There has been variable but largely marginal progress at addressing the 12 HIT fallacies delineated in the original paper. Here, we revisit several of the original fallacies and add five new ones. These fallacies must be understood and addressed by all stakeholders for HIT to be a positive force in achieving the high value healthcare system the nation deserves. Foundational cognitive and human factors engineering research and development continue to be essential to HIT development, deployment, and use.

Broadening horizons: the case for capturing function and the role of health informatics in its use

Background

Human activity and the interaction between health conditions and activity is a critical part of understanding the overall function of individuals. The World Health Organization’s International Classification of Functioning, Disability and Health (ICF) models function as all aspects of an individual’s interaction with the world, including organismal concepts such as individual body structures, functions, and pathologies, as well as the outcomes of the individual’s interaction with their environment, referred to as activity and participation. Function, particularly activity and participation outcomes, is an important indicator of health at both the level of an individual and the population level, as it is highly correlated with quality of life and a critical component of identifying resource needs. Since it reflects the cumulative impact of health conditions on individuals and is not disease specific, its use as a health indicator helps to address major barriers to holistic, patient-centered care that result from multiple, and often competing, disease specific interventions. While the need for better information on function has been widely endorsed, this has not translated into its routine incorporation into modern health systems.

Purpose

We present the importance of capturing information on activity as a core component of modern health systems and identify specific steps and analytic methods that can be used to make it more available to utilize in improving patient care. We identify challenges in the use of activity and participation information, such as a lack of consistent documentation and diversity of data specificity and representation across providers, health systems, and national surveys. We describe how activity and participation information can be more effectively captured, and how health informatics methodologies, including natural language processing (NLP), can enable automatically locating, extracting, and organizing this information on a large scale, supporting standardization and utilization with minimal additional provider burden. We examine the analytic requirements and potential challenges of capturing this information with informatics, and describe how data-driven techniques can combine with common standards and documentation practices to make activity and participation information standardized and accessible for improving patient care.

Recommendations

We recommend four specific actions to improve the capture and analysis of activity and participation information throughout the continuum of care: (1) make activity and participation annotation standards and datasets available to the broader research community; (2) define common research problems in automatically processing activity and participation information; (3) develop robust, machine-readable ontologies for function that describe the components of activity and participation information and their relationships; and (4) establish standards for how and when to document activity and participation status during clinical encounters. We further provide specific short-term goals to make significant progress in each of these areas within a reasonable time frame.

Factors Influencing Implementation of an Electronic Medical Record in a Tertiary Cancer Centre

BACKGROUND

EMRs are one of a range of digital health solutions that are key enablers of the data revolution transforming the health sector. They offer a wide range of benefits to health professionals, patients and other key stakeholders. However, effective implementation has proved challenging.

METHOD

A qualitative methodology was used in the study. Interviews were conducted with members of a cancer team 12 months post-implementation of an EMR. Data from the interviews was collected via audio recording. Audio recordings were transcribed, de-identified and analyzed to identify the experiences of staff with the EMR.

FINDINGS

Data was categorized in to six categories: 1) Standardisation of documentation and completeness of data; 2) Effect on workload; 3) Feature completeness and functionality; 4) Interaction with technical support; 5) Learning curve; 6) Buy-in from staff.

CONCLUSIONS & IMPLICATIONS

Findings from this study contribute new knowledge on barriers and enablers to the implementation of EMRs in complex clinical settings. Barriers to successful implementation include lack of technical support, perceived increase in workload and a learning curve to fully familiarize with the feature set of the EMR.

Development of a Calculated Panel Reactive Antibody Web Service with Local Frequencies for Platelet Transfusion Refractoriness Risk Stratification

BACKGROUND

Calculated panel reactive antibody (cPRA) scoring is used to assess whether platelet refractoriness is mediated by human leukocyte antigen (HLA) antibodies in the recipient. cPRA testing uses a national sample of US kidney donors to estimate the population frequency of HLA antigens, which may be different than HLA frequencies within local platelet inventories. We aimed to determine the impact on patient cPRA scores of using HLA frequencies derived from typing local platelet donations rather than national HLA frequencies.

METHODS

We built an open-source web service to calculate cPRA scores based on national frequencies or custom-derived frequencies. We calculated cPRA scores for every hematopoietic stem cell transplantation (HSCT) patient at our institution based on the United Network for Organ Sharing (UNOS) frequencies and local frequencies. We compared frequencies and correlations between the calculators, segmented by gender. Finally, we put all scores into three buckets (mild, moderate, and high sensitizations) and looked at intergroup movement.

RESULTS

2531 patients that underwent HSCT at our institution had at least 1 antibody and were included in the analysis. Overall, the difference in medians between each group's UNOS cPRA and local cPRA was statistically significant, but highly correlated (UNOS vs. local total: 0.249 and 0.243, ρ = 0.994; UNOS vs. local female: 0.474 and 0.463, ρ = 0.987, UNOS vs. local male: 0.165 and 0.141, ρ = 0.996; P < 0.001 for all comparisons). The median difference between UNOS and cPRA scores for all patients was low (male: 0.014, interquartile range [IQR]: 0.004-0.029; female: 0.0013, IQR: 0.003-0.028). Placement of patients into three groups revealed little intergroup movement, with 2.96% (75/2531) of patients differentially classified.

CONCLUSIONS

cPRA scores using local frequencies were modestly but significantly different than those obtained using national HLA frequencies. We released our software as open source, so other groups can calculate cPRA scores from national or custom-derived frequencies. Further investigation is needed to determine whether a local-HLA frequency approach can improve outcomes in patients who are immune-refractory to platelets.

Toward an accelerated adoption of data-driven findings in medicine : Research, skepticism, and the need to speed up public visibility of data-driven findings

To accelerate the adoption of a new method with a high potential to replace or extend an existing, presumably less accurate, medical scoring system, evaluation should begin days after the new concept is presented publicly, not years or even decades later. Metaphorically speaking, as chameleons capable of quickly changing colors to help their bodies adjust to changes in temperature or light, health-care decision makers should be capable of more quickly evaluating new data-driven insights and tools and should integrate the highest performing ones into national and international care systems. Doing so is essential, because it will truly save the lives of many individuals.

Feasibility study of an EHR-integrated mobile shared decision making application

INTRODUCTION

Integrating mobile applications (apps) into users' standard electronic health record (EHR) workflows may be valuable, especially for apps that both read and write data. This report details the lessons learned during the integration of a patient decision aid - prostate specific antigen (PSA) testing for prostate cancer screening - into our users' standard EHR workflow for a small usability assessment.

MATERIALS AND METHODS

This feasibility study included two steps. First we enabled realtime, secure bidirectional data exchange between the mobile app and EHR for 14 data elements, and second we pilot tested the production environment app with 9 primary care patients aged 60-65 years. Our primary usability metric was a net promoter score (NPS), based on users' recommendation of the app to a friend or family member; we also assessed the proportion of users who 1) updated their prostate cancer risk factor information present in the EHR and 2) submitted more than one unique response regarding their preference to have PSA testing.

RESULTS

The seven web services necessary to read and write data required considerable configuration, but successfully delivered risk factor-specific educational content and recorded patients' values and decision preference directly within the EHR. Seven of the 9 patients (78%) would recommend this app to a friend/family member (NPS = 55.6%), one patient used the app to update risk factor information, and 4/9 (44%) changed their decision preference while using the app.

CONCLUSIONS

It is feasible to implement a decision aid directly into users' standard EHR workflow for limited usability testing. Broad scale implementation may have a positive effect on patient engagement and improve shared decision making, but several challenges exist with proprietary EHR vendor application programming interfaces (API)s.

Incorporating Observed Physiological Data to Personalize Pediatric Vital Sign Alarm Thresholds

Bedside monitors are intended as a safety net in patient care, but their management in the inpatient setting is a significant patient safety concern. The low precision of vital sign alarm systems leads to clinical staff becoming desensitized to the sound of the alarm, a phenomenon known as alarm fatigue. Alarm fatigue has been shown to increase response time to alarms or result in alarms being ignored altogether and has negative consequences for patient safety. We present methods to establish personalized thresholds for heart rate and respiratory rate alarms. These thresholds are first chosen based on patient characteristics available at the time of admission and are then adapted to incorporate vital signs observed in the first 2 hours of monitoring. We demonstrate that the adapted thresholds are similar to those chosen by clinicians for individual patients and would result in fewer alarms than the currently used age-based thresholds. Personalized vital sign alarm thresholds can help to alleviate the problem of alarm fatigue in an inpatient setting while ensuring that all critical vital signs are detected.

Leveraging Big Data to Transform Drug Discovery

The surge of public disease and drug-related data availability has facilitated the application of computational methodologies to transform drug discovery. In the current chapter, we outline and detail the various resources and tools one can leverage in order to perform such analyses. We further describe in depth the in silico workflows of two recent studies that have identified possible novel indications of existing drugs. Lastly, we delve into the caveats and considerations of this process to enable other researchers to perform rigorous computational drug discovery experiments of their own.

Using clinical Natural Language Processing for health outcomes research: Overview and actionable suggestions for future advances

The importance of incorporating Natural Language Processing (NLP) methods in clinical informatics research has been increasingly recognized over the past years, and has led to transformative advances. Typically, clinical NLP systems are developed and evaluated on word, sentence, or document level annotations that model specific attributes and features, such as document content (e.g., patient status, or report type), document section types (e.g., current medications, past medical history, or discharge summary), named entities and concepts (e.g., diagnoses, symptoms, or treatments) or semantic attributes (e.g., negation, severity, or temporality). From a clinical perspective, on the other hand, research studies are typically modelled and evaluated on a patient- or population-level, such as predicting how a patient group might respond to specific treatments or patient monitoring over time. While some NLP tasks consider predictions at the individual or group user level, these tasks still constitute a minority. Owing to the discrepancy between scientific objectives of each field, and because of differences in methodological evaluation priorities, there is no clear alignment between these evaluation approaches. Here we provide a broad summary and outline of the challenging issues involved in defining appropriate intrinsic and extrinsic evaluation methods for NLP research that is to be used for clinical outcomes research, and vice versa. A particular focus is placed on mental health research, an area still relatively understudied by the clinical NLP research community, but where NLP methods are of notable relevance. Recent advances in clinical NLP method development have been significant, but we propose more emphasis needs to be placed on rigorous evaluation for the field to advance further. To enable this, we provide actionable suggestions, including a minimal protocol that could be used when reporting clinical NLP method development and its evaluation.

Challenging popular tools for the annotation of genetic variations with a real case, pathogenic mutations of lysosomal alpha-galactosidase

Background

Severity gradation of missense mutations is a big challenge for exome annotation. Predictors of deleteriousness that are most frequently used to filter variants found by next generation sequencing, produce qualitative predictions, but also numerical scores. It has never been tested if these scores correlate with disease severity.

Results

wANNOVAR, a popular tool that can generate several different types of deleteriousness-prediction scores, was tested on Fabry disease. This pathology, which is caused by a deficit of lysosomal alpha-galactosidase, has a very large genotypic and phenotypic spectrum and offers the possibility of associating a quantitative measure of the damage caused by mutations to the functioning of the enzyme in the cells. Some predictors, and in particular VEST3 and PolyPhen2 provide scores that correlate with the severity of lysosomal alpha-galactosidase mutations in a statistically significant way.

Conclusions

Sorting disease mutations by severity is possible and offers advantages over binary classification. Dataset for testing and training in silico predictors can be obtained by transient transfection and evaluation of residual activity of mutants in cell extracts. This approach consents to quantitative data for severe, mild and non pathological variants.

Electronic supplementary material

The online version of this article (10.1186/s12859-018-2416-7) contains supplementary material, which is available to authorized users.

Review of Use of Asynchronous Technologies Incorporated in Mental Health Care

PURPOSE OF REVIEW

Mental health clinicians should understand how technologies augment, enhance, and provide alternate means for the delivery of mental healthcare. These technologies can be used asynchronously, in which the patient and the clinician need not be communicating at the same time. This contrasts with synchronous technologies, in which patient and clinician must communicate at the same time.

RECENT FINDINGS

The review is based on research literature and the authors' clinical and healthcare administration experiences. Asynchronous technologies can exist between a single clinician and a single patient, such as patient portal e-mail and messaging, in-app messaging, asynchronous telepsychiatry via store-and-forward video, and specialty patient-to-provider mobile apps. Asynchronous technologies have already been used in different countries with success, and can alleviate the psychiatric workforce shortage and improve barriers to access. Multiple studies referred to in this review demonstrate good retention and acceptability of asynchronous psychotherapy interventions by patients. Asynchronous technologies can alleviate access barriers, such as geographical, scheduling, administrative, and financial issues. It is important for clinicians to understand the efficacy, assess the ethics, and manage privacy and legal concerns that may arise from using asynchronous technologies.

An initiative using informatics to facilitate clinical research planning and recruitment in the VA health care system

Background

Randomized clinical trials are the gold standard for evaluating healthcare interventions and, more generally, add to the medical knowledge related to the treatment, diagnosis and prevention of diseases and conditions. Recent literature continues to identify health informatics methods that can help improve study efficiency throughout the life cycle of a clinical trial. Electronic medical record (EMR) data provides a mechanism to facilitate clinical trial research during the study planning and execution phases, and ultimately, can be utilized to enhance recruitment. The Department of Veterans Affairs (VA) has a strong history of clinical and epidemiological research with over four decades of data collected from Veterans it has served nationwide. The VA Informatics and Computing Infrastructure (VINCI) provides VA research investigators with a nationwide view of high-value VA patient data. Within VA, the Cooperative Studies Program (CSP) Network of Dedicated Enrollment Sites (NODES) is a consortium of nine sites that are part of an embedded clinical research infrastructure intended to provide systematic site-level solutions to issues that arise during the conduct of VA CSP clinical research. This paper describes the collaboration initiated by the Salt Lake City (SLC) node site to bring informatics and clinical trials together to enhance study planning and recruitment within the VA.

Methods

The SLC VA Medical Center physically houses both VINCI and a node site and the co-location of these two groups prompted a natural collaboration on both a local and national level. One of the functions of the SLC NODES is to enhance recruitment and promote the success of CSP projects. VINCI supports these efforts by providing VA researchers access to potential population pools. VINCI can provide 1) feasibility data during study planning, and 2) active patient lists during recruitment. The process for CSP study teams to utilize these services involves regulatory documentation, development of queries, revisions to the initial data request, and ongoing communications with several key study personnel including the requesting research team, study statisticians, and VINCI data managers.

Results

The early efforts of SLC NODES and VINCI aimed to provide patient lists exclusively to the SLC CSP study teams for the following purposes: 1) increasing recruitment for trials that were struggling to meet their respective enrollment goals, and 2) decreasing the time required by study coordinators to complete chart review activities. This effort was expanded to include multiple CSP sites and studies. To date, SLC NODES has facilitated the delivery of these VINCI services to nine active CSP studies.

Conclusion

The ability of clinical trial study teams to successfully plan and execute their respective trials is contingent upon their proficiency in obtaining data that will help them efficiently and effectively recruit and enroll eligible participants. This collaboration demonstrates that the utilization of a model that partners two distinct entities, with similar objectives, was effective in the provision of feasibility and patient lists to clinical trial study teams and facilitation of clinical trial research within a large, integrated healthcare system.

CogStack - experiences of deploying integrated information retrieval and extraction services in a large National Health Service Foundation Trust hospital

BACKGROUND

Traditional health information systems are generally devised to support clinical data collection at the point of care. However, as the significance of the modern information economy expands in scope and permeates the healthcare domain, there is an increasing urgency for healthcare organisations to offer information systems that address the expectations of clinicians, researchers and the business intelligence community alike. Amongst other emergent requirements, the principal unmet need might be defined as the 3R principle (right data, right place, right time) to address deficiencies in organisational data flow while retaining the strict information governance policies that apply within the UK National Health Service (NHS). Here, we describe our work on creating and deploying a low cost structured and unstructured information retrieval and extraction architecture within King's College Hospital, the management of governance concerns and the associated use cases and cost saving opportunities that such components present.

RESULTS

To date, our CogStack architecture has processed over 300 million lines of clinical data, making it available for internal service improvement projects at King's College London. On generated data designed to simulate real world clinical text, our de-identification algorithm achieved up to 94% precision and up to 96% recall.

CONCLUSION

We describe a toolkit which we feel is of huge value to the UK (and beyond) healthcare community. It is the only open source, easily deployable solution designed for the UK healthcare environment, in a landscape populated by expensive proprietary systems. Solutions such as these provide a crucial foundation for the genomic revolution in medicine.

Text-based phenotypic profiles incorporating biochemical phenotypes of inborn errors of metabolism improve phenomics-based diagnosis

Phenomics is the comprehensive study of phenotypes at every level of biology: from metabolites to organisms. With high throughput technologies increasing the scope of biological discoveries, the field of phenomics has been developing rapid and precise methods to collect, catalog, and analyze phenotypes. Such methods have allowed phenotypic data to be widely used in medical applications, from assisting clinical diagnoses to prioritizing genomic diagnoses. To channel the benefits of phenomics into the field of inborn errors of metabolism (IEM), we have recently launched IEMbase, an expert-curated knowledgebase of IEM and their disease-characterizing phenotypes. While our efforts with IEMbase have realized benefits, taking full advantage of phenomics requires a comprehensive curation of IEM phenotypes in core phenomics projects, which is dependent upon contributions from the IEM clinical and research community. Here, we assess the inclusion of IEM biochemical phenotypes in a core phenomics project, the Human Phenotype Ontology. We then demonstrate the utility of biochemical phenotypes using a text-based phenomics method to predict gene-disease relationships, showing that the prediction of IEM genes is significantly better using biochemical rather than clinical profiles. The findings herein provide a motivating goal for the IEM community to expand the computationally accessible descriptions of biochemical phenotypes associated with IEM in phenomics resources.