Temporal Relation Extraction in Clinical Texts

Unstructured data in electronic health records, represented by clinical texts, are a vast source of healthcare information because they describe a patient's journey, including clinical findings, procedures, and information about the continuity of care. The publication of several studies on temporal relation extraction from clinical texts during the last decade and the realization of multiple shared tasks highlight the importance of this research theme. Therefore, we propose a review of temporal relation extraction in clinical texts. We analyzed 105 articles and verified that relations between events and document creation time, a coarse temporality type, were addressed with traditional machine learning–based models with few recent initiatives to push the state-of-the-art with deep learning–based models. For temporal relations between entities (event and temporal expressions) in the document, factors such as dataset imbalance because of candidate pair generation and task complexity directly affect the system's performance. The state-of-the-art resides on attention-based models, with contextualized word representations being fine-tuned for temporal relation extraction. However, further experiments and advances in the research topic are required until real-time clinical domain applications are released. Furthermore, most of the publications mainly reside on the same dataset, hindering the need for new annotation projects that provide datasets for different medical specialties, clinical text types, and even languages.

Orientation of medical trainees to a new clinical environment (the ready-steady-go model): a constructivist grounded theory study

Background High-quality orientation of trainees entering a new clinical workplace is essential to support education and patient safety. However, few consultants receive extensive formal training to support new trainees and must create their own ways of integrating newcomers into their clinical team and work environment. We aim to conceptualise the strategies consultants use in the early stages of working with new trainees that will be useful for future faculty development in this area. Methods We used constructivist grounded theory (CGT) methodology by interviewing fifteen consultants in three medical specialties, to explore how trainees are integrated into a new clinical environment. We used CGT principles and procedures (iteration, constant comparison, and theoretical sampling) to analyse and construct a conceptual interpretation of the empirical data. Results Consultants’ central concern when introduced to a new cohort of trainees was that they had the required knowledge and skills (ready), were adapted and integrated into the new workplace and clinical team (steady), and safely participating in practice (go). Consultants used two broad strategies: formal orientation and informal orientation. Both these approaches had the common goal of intensifying interaction between consultants and trainees to get trainees to a position where they were ready, adapted, integrated, and participating safely and efficiently in practice. Several disruptors were identified by participants that delayed and sometimes completely inhibited the orientation process. Conclusions The model of orientation constructed through this research could be a valuable tool to support faculty development initiatives, the reflective learning practice of clinical supervisors, and curriculum design. The disruptors were identified as valid priorities for improving trainee orientation in postgraduate medical education. Future research should involve a longitudinal approach to explore trainee engagement with orientation upon entering a new clinical workplace.

Using Gagne’s instructional design to teach communication skills in phlebotomy education through role-play

Background: Phlebotomy is a medical procedure that is performed frequently in the blood collection activities of medical institutions. The procedure involves close interaction with different types of patients—some of whom are cooperative and others, who, for many reasons, are not (for example, patients who have a fear of needles). Blood extraction is an essential skill in several medical specialties, such as in laboratory sciences. Lesson planning in phlebotomy education is mainly focused on procedural skills, and very little attention is given towards teaching communication skills despite the close patient interaction in phlebotomy. In this paper, I propose a lesson plan for teaching communication skills to medical laboratory sciences and nursing students based on Gagne’s instructional design. Methods: The training session included two main parts: training session using Gange’s instructional design and at the end of the session, the participants were surveyed for the effectiveness of the training session. Results: 17 participants were included in the study. Overall, the majority of the participants were highly satisfied with the effectiveness of the training session in teaching communication skills with all seven survey questions receiving a mean score of 4.58 on a Likert scale of 1-5. Conclusion: We demonstrated the effectiveness of Gange’s instructional beyond theoretical lesson planning to teach communication skills through role-play in phlebotomy education.

Machine learning in knee arthroplasty: specific data are key—a systematic review

Purpose Artificial intelligence (AI) in healthcare is rapidly growing and offers novel options of data analysis. Machine learning (ML) represents a distinct application of AI, which is capable of generating predictions and has already been tested in different medical specialties with various approaches such as diagnostic applications, cost predictions or identification of risk factors. In orthopaedics, this technology has only recently been introduced and the literature on ML in knee arthroplasty is scarce. In this review, we aim to investigate which predictions are already feasible using ML models in knee arthroplasty to identify prerequisites for the effective use of this novel approach. For this reason, we conducted a systematic review of ML algorithms for outcome prediction in knee arthroplasty. Methods A comprehensive search of PubMed, Medline database and the Cochrane Library was conducted to find ML applications for knee arthroplasty. All relevant articles were systematically retrieved and evaluated by an orthopaedic surgeon and a data scientist on the basis of the PRISMA statement. The search strategy yielded 225 articles of which 19 were finally assessed as eligible. A modified Coleman Methodology Score (mCMS) was applied to account for a methodological evaluation. Results The studies presented in this review demonstrated fair to good results (AUC median 0.76/range 0.57–0.98), while heterogeneous prediction models were analysed: complications (6), costs (4), functional outcome (3), revision (2), postoperative satisfaction (2), surgical technique (1) and biomechanical properties (1) were investigated. The median mCMS was 65 (range 40–80) points. Conclusion The prediction of distinct outcomes with ML models applying specific data is already feasible; however, the prediction of more complex outcomes is still inaccurate. Registry data on knee arthroplasty have not been fully analysed yet so that specific parameters have not been sufficiently evaluated. The inclusion of specific input data as well as the collaboration of orthopaedic surgeons and data scientists are essential prerequisites to fully utilize the capacity of ML in knee arthroplasty. Future studies should investigate prospective data with specific and longitudinally recorded parameters. Level of evidence III.

A Brief Online Implicit Bias Intervention for School Mental Health Clinicians

Clinician bias has been identified as a potential contributor to persistent healthcare disparities across many medical specialties and service settings. Few studies have examined strategies to reduce clinician bias, especially in mental healthcare, despite decades of research evidencing service and outcome disparities in adult and pediatric populations. This manuscript describes an intervention development study and a pilot feasibility trial of the Virtual Implicit Bias Reduction and Neutralization Training (VIBRANT) for mental health clinicians in schools—where most youth in the U.S. access mental healthcare. Clinicians (N = 12) in the feasibility study—a non-randomized open trial—rated VIBRANT as highly usable, appropriate, acceptable, and feasible for their school-based practice. Preliminarily, clinicians appeared to demonstrate improvements in implicit bias knowledge, use of bias-management strategies, and implicit biases (as measured by the Implicit Association Test [IAT]) post-training. Moreover, putative mediators (e.g., clinicians’ VIBRANT strategies use, IAT D scores) and outcome variables (e.g., clinician-rated quality of rapport) generally demonstrated correlations in the expected directions. These pilot results suggest that brief and highly scalable online interventions such as VIBRANT are feasible and promising for addressing implicit bias among healthcare providers (e.g., mental health clinicians) and can have potential downstream impacts on minoritized youth’s care experience.

Inpatient COVID-19 Mortality Rates: What are the predictors?

Objective: This study aims to investigate the relationship between registered nurses and hospital-based medical specialties staffing levels with inpatient COVID-19 mortality rates. Methods: We rely on data from AHA Annual Survey Database, Area Health Resource File, and UnitedHealth Group Clinical Discovery Database. We use linear regression to analyze the association between hospital staffing levels and bed capacity with inpatient COVID-19 mortality rates from March 1, 2020, through December 31, 2020. Results: Higher staffing levels of registered nurses, hospitalists, and emergency medicine physicians were associated with lower COVID-19 mortality rates. Moreover, a higher number of ICU and skilled nursing beds were associated with better patient outcomes. Hospitals located in urban counties with high infection rates had the worst patient mortality rates. Conclusion: Higher staffing levels are associated with lower inpatient mortality rates for COVID-19 patients. A future assessment is needed to establish benchmarks on the minimum staffing levels for nursing and hospital-based medical specialties during pandemics.

Multi-Level Monitoring of Vaccination Adherence of Various Population Groups in the Context of the COVID-19 Pandemic: Problematic Issues

Relevance. Despite significant progress in the prevention of many infectious diseases, a number of organizational issues remain in the area of special attention. One of them is to ensure the timeliness and completeness of vaccination coverage in the decreed age groups, which is possible only with a high level of public commitment to vaccination. During the pandemic of the new coronavirus infection (COVID-19), achieving a high level of vaccination coverage of the National Calendar of Preventive vaccinations is of particular relevance. Aim. Using state-of-the-art online resources, assess population vaccination adherence to develop effective communication risk management technologies for immunoprophylaxis in the COVID-19 pandemic. Materials and methods. To assess the commitment of various population groups and professional contingents of a large industrial city to vaccine prevention, a survey of 965 parents was conducted at the initial stage, and subsequently a survey of 2,632 employees of medical organizations, including 1,422 people in the period before the COVID - 19 pandemic, 572 people in the «first wave» of the pandemic and 638 people in the «second wave». Instagram Facebook, Instagram, and VKontakte social networks were used to quickly obtain the necessary information (Google forms, corporate e-mails, WhatsApp, Telegram messengers, etc.). The work uses epidemiological, sociological and statistical methods of research. Results and discussion. When assessing the attitude of parents to vaccination, it was found that 78.8% of respondents were positive about vaccinations, 14.6% doubted their effectiveness and safety, and 6.6% denied their need. The main source of information that forms the attitude to vaccinations of parents was the opinion of medical professionals. In a survey of 1,422 employees, 190 people (13.3%) were identified, mainly from among the trained specialists, who themselves had a negative attitude to vaccination. When assessing the commitment of employees of medical organizations to the vaccination of a new coronavirus infection, the attitude to vaccination was ambiguous, especially in the group of secondary medical personnel and female employees of non-medical specialties, who are a potential risk group for forming a negative attitude to vaccinations and can act as «opinion leaders» on this issue for other categories of the population. Insufficient adherence to COVID-19 vaccine prevention has also been observed in other countries among various population groups, which is a serious problem on a global scale, hindering the fight against the pandemic of a new disease, which requires corrective measures. Conclusion. In this study, using modern online resources, a rapid assessment of the vaccination adherence of various population groups (parents and medical professionals) was carried out. It is shown that the use of modern technologies and software tools makes it possible to analyze a large array of data to solve problems of overcoming communication risks. The results obtained point to the need for prompt corrective measures in terms of the introduction of educational programs to increase adherence to vaccination, especially in groups at potential risk of the disease, including medical professionals, which is a priority for health care in all countries.

Activity of a psychologist in a Medical Specialties Unit: Ambulatory Center for the Prevention and Attention of AIDS and other sexually transmitted infections.

Introduction: The attention provided at Medical Specialties Unit (UNEME), Ambulatory Center for the Prevention and Attention of AIDS and other sexually transmitted diseases (CAPASITS), the psychologist develops activities that strengthen the patients’ treatment, as a part of a multidisciplinary work. In this way, it becomes essential knowing the importance of the psychologist activities and how they get involved in the Public Health problems. Objective: To analyze the professional competencies that psychologists must possess and how they apply them in their activity at the UNEME CAPASITS Material and Methods: A descriptive bibliographic review was carried out. For the inclusion criteria, it was considered that they will report on: the development of professional skills of health psychologists, the activity of psychologists in public health institutions, development of professional skills of the psychologist and the objectives of health psychology. To search for information, the following keywords were used: health psychology, activity and professional skills. The bibliographic search was performed in the databases: EBSCO, ScienceDirect, Dialnet, PubMed, REdalyc, ResearchGate and pages from official sites: WHO and the National Center for the Prevention and Control of HIV and AIDS. Results: From the analyzed information it was found that the professional competencies that the psychologist must possess in the field of health are focused on the management of preventive strategies, use of health technologies, creation of plans and programs to promote a healthy lifestyle, evaluation and treatment as well as collaborative work. Conclusions: The UNEMES CAPSITS require that psychologists possess competencies such as: communication, use of information and communication technologies (ICT), research, evaluation for treatment, monitoring and creation of clinical records, in addition to: research for health and the dissemination of the results, especially in the treatments.

The impact of the SARS-CoV-2 pandemic on healthcare provision in Italy to non-COVID patients: a systematic review

Background Italy has been one of the countries most affected by the SARS-CoV-2 pandemic and the regional healthcare system has had to quickly adapt its organization to meet the needs of infected patients. This has led to a drastic change in the routine management of non-communicable diseases with a potential long-term impact on patient health care. We investigated the management of non-COVID-19 patients across all medical specialties in Italy. Methods A PRISMA guideline-based systematic review of the literature was performed using PubMed, Embase, and Scopus, restricting the search to the main outbreak period in Italy (from 20 February to 22 June, 2020). We selected articles in English or Italian that detailed changes in the Italian hospital care for non-COVID-19 patients due to the pandemic. Our keywords included all medical specialties in combination with our geographical focus (Italy) and COVID-19. Results Of the 4643 potentially eligible studies identified by the search, 247 studies were included. A decrease in the management of emergencies in non-COVID patients was found together with an increase in mortality. Similarly, non-deferrable conditions met a tendency toward decreased diagnosis. All specialties have been affected by the reorganization of healthcare provision in the hub-and-spoke system and have benefited from telemedicine. Conclusions Our work highlights the changes taking place in the Italian public healthcare system to tackle the developing health crisis due to the COVID-19 pandemic. The findings of our review may be useful to analyze future directions for the healthcare system in the case of new pandemic scenarios.