Experienced Physicians Research Articles

Exploring the Correlation Between Palliative Care Training in Brazil and Compassion Fatigue: A Cross-Sectional Study.

The literature lacks conclusive evidence regarding whether palliative care training confers a protective or predisposing influence on compassion fatigue. The present study hypothesizes that training in palliative care is associated with minor compassion fatigue levels among physicians and an improvement in their confidence in several procedures. To explore the physicians experiences with and without palliative care training who work as general practitioners in order to assess the prevalence of compassion fatigue in these groups. This is a quantitative and qualitative cross-sectional survey. For data analysis, Mann-Whitney and Pearson's chi-squared test tests were used considering P < 0.05 for significance. The majority respondents had no training in palliative care (77.8%), however, 58.3% declared that they cared for at least 1 palliative care patient every 2 shifts - an intermediate frequency in our analysis. Trauma levels among doctors were classified as medium (24 ± 6), burnout as low (19 ± 5) and compassion as medium (41 ± 5). Professionals without training in palliative care had higher rates of burnout (P = 0.002), but there was no association between training and rates of trauma or compassion. Doctors with training in palliative care in Brazil showed lower burnout rates when working as general practitioners in secondary hospitals. This could instigate the implementation of educational programs in palliative care at hospitals and the further development of the field so as to improve professionals' performance at patients' treatment. There was no difference between Trauma and Compassion scores.

Boundary-work of primary care physicians using telemedicine technologies for communication.

Implementing telemedicine technologies (TT) for patient-physician communication leads to the emergence of new structures of boundaries. Hence, boundary work theory can provide a useful lens for examining how primary care physicians (PCPs) experience TT. The objective of this research was to examine the experiences of PCPs in using TT in their communication with patients. During 2023 in-depth interviews were conducted with 20 Israeli PCPs: family physicians and pediatricians. The concept of boundary work emerged as a focal point, with three forms of boundary work identified in the PCPs' descriptions of their TT experiences: collaborative, competitive, and configurational. Interviewees described improved collaboration with patients who find it difficult to get to the clinic and better service for administrative issues. However, they reported constant power struggles to maintain their authority. They expressed concern about treatment failure and suggested that healthcare organizations reconfigure TT so that it can be used to provide optimal care. They suggested that healthcare organizations should instruct physicians how to best manage TT consultations and regulate its usage. This article demonstrates that while implementing TT in primary care has many advantages, it uncovers boundary work for maintaining power and authority that both PCPs and healthcare organizations should take into account in practice as well as in policy.

Application value of generative artificial intelligence in the field of stomatology.

This study aims to compare and analyze three types of generative artificial intelligence (GAI) and explore their application value and existing problems in the field of stomatology in the Chinese context. A total of 36 questions were designed, covering all the professional areas of stomatology. The questions encompassed various aspects including medical records, professional knowledge, and translation and editing. These questions were submitted to ChatGPT4-turbo, Gemini (2024.2) and ERNIE Bot 4.0. After obtaining the answers, a blinded evaluation was conducted by three experienced oral medicine physicians using a four-point Likert scale. The value of GAI in various application scenarios was evaluated. Gemini scored 45, ERNIE Bot scored 38, and ChatGPT scored 33 for clinical documentation and image production. For research assistance, Gemini achieved 45, ERNIE Bot had 39, and ChatGPT scored 35. Teaching assistance capabilities were rated at 54 for ERNIE Bot, 50 for Gemini, and 48 for ChatGPT. In patient consultation and guidance, Gemini scored 78, ERNIE Bot scored 59, and ChatGPT scored 48. Overall, the total scores were 218, 190, and 164 for Gemini, ERNIE Bot, and ChatGPT, respectively. Among GAI applications, the top scoring categories were article translation and polishing (26), patient-doctor communication documentation (23), and popular science content creation (23). The lowest scoring categories were literature search and reporting (13) and image generation (12). In the Chinese context, the application value of GAI is the highest for Gemini, followed by ERNIE Bot and ChatGPT. GAI shows significant value in translation, patient-doctor communication, and popular science writing. However, its value in literature search, reporting, and image generation remains limited.

Providing Palliative Care for Sexual and Gender Minority Individuals: A Qualitative Interview Study of Physicians' Attitudes and Experiences.

Introduction: Sexual and gender minority (SGM) individuals face increased risk of receiving suboptimal care, including palliative care. Despite research demonstrating strategies to improve care, little is known about the experiences of palliative care clinicians providing care to these communities. Objectives: The primary aim of this study is to characterize attitudes and practices of palliative care physicians around providing care to SGM individuals. Design: This exploratory, qualitative study used semi-structured interviewing. Interviews were transcribed and coded using reflexive thematic analysis. Setting and Participants: Twenty-four palliative care physicians practicing in the homecare, hospice, and hospital settings from geographically diverse sites across Canada were recruited from palliative care organizations using convenience and snowball sampling. Results: Four main themes represent perspectives on improving palliative care for SGM individuals: (1) increasing experience with and knowledge about SGM communities increases clinicians' confidence and competency; (2) standardizing inclusive sexual orientation and gender identity (SOGI) data collection and documentation can improve patient care; (3) addressing individual, systemic, and societal biases may improve palliative care provided to SGM individuals; and (4) knowing SOGI improves care quality. Conclusions: Clinicians must familiarize themselves with the importance of SOGI to the care provided as well as the palliative care needs of SGM communities. Institutions should provide tailored training around the unique needs of SGM patients and implement policies and tools that standardize sexual and gender orientation data collection and documentation.

Resilience among family physicians during the COVID-19 pandemic in Canada.

The purpose of this study was to investigate how the COVID-19 pandemic's inaugural wave impacted the professional autonomy of family physicians in Canada. This study highlights how family physician's resilience enabled them to overcome the many challenges they faced to provide health services to patients and has enabled them to rebuild their sense of purpose and duty of care. Four themes were found to summarize physician experiences: (1) loss of clinical autonomy and control; (2) abandonment and neglect by the health system; (3) a fear of patients "falling through the cracks" and moral injury; and (4) building resilience to support duty of care in family practice. These results highlight the emergence of resilience among family physicians to restore professional autonomy in family practice, overcoming moral injury in order to fulfil their "duty of care" to their patients. Physicians believe the health system's crisis preparedness efforts need to be dedicated to protecting the autonomy of practicing physicians to maintain the continuity of quality patient care in future health crises.

TIRADS-based artificial intelligence systems for ultrasound images of thyroid nodules: protocol for a systematic review.

The thyroid imaging reporting and data system (TIRADS) was developed as a standard global term to describe thyroid nodule risk features, aiming to address issues such as variability and low reproducibility in nodule feature detection and interpretation by different physicians. The objective of this study is to comprehensively study articles that utilize AI techniques to design and develop decision support systems for classifying thyroid nodule risk on the basis of various TIRADS guidelines from ultrasound images. This protocol includes five steps: identification of key research questions of the review, descriptions of the systematic literature search strategies, criteria for study inclusion and exclusion, study quality measures, and the data extraction process. We designed a complete search string using PubMed, Scopus, and Web of Sciences to retrieve all relevant English language studies up to January 2024. A PRISMA diagram was constructed, inclusion and exclusion criteria were defined, and after a quality assessment of the included papers, relevant data were extracted. The protocol of this systematic review was registered in the PROSPERO database (CRD42024551311). We anticipate that our findings will assist researchers in creating higher-quality systems with increased efficiency, reducing unnecessary biopsies, improving the reproducibility and reliability of thyroid nodule diagnostics, and providing good educational opportunities for less experienced physicians. In this study, a protocol was used for performing a systematic review to evaluate the diagnostic performance and other various aspects used in the design and development of artificial intelligence CAD systems based on various thyroid imaging reporting and data systems (TI-RADSs).

EGFDA: Experience-guided Fine-grained Domain Adaptation for cross-domain pneumonia diagnosis

Although recent advances in deep learning have led to accurate pneumonia diagnoses, their heavy reliance on data annotation hinders their expected performance in clinical practice. Unsupervised domain adaptation (UDA) methods have been developed to address the scarcity of annotations. Nevertheless, the diverse manifestations of pneumonia pose challenges for current UDA methods, including spatial lesion-preference bias and discriminative class-preference bias. To overcome these problems, we propose an Experience-Guided Fine-grained Domain Adaptation (EGFDA) framework for automatic cross-domain pneumonia diagnosis. Our framework consists of two main modules: (1) Gradient-aware Lesion Area Matching (GaLAM), which aims to reduce the global domain gap while avoiding misleading from lesion-unrelated targets, and (2) Reweighing Smooth Certainty-aware Matching (RSCaM), which aims to match class space with a smooth certainty-aware feature mapping to guide the model to learn more precise class-discriminative features. Benefiting from the collaboration between GaLAM and RSCaM, the proposed EGFDA is able to process unlabeled samples following a pattern similar to the diagnostic experience of physicians, that is, first locating the disease-related lesion area and then performing fine-grained discrimination. Comprehensive experiments on three different tasks using six datasets demonstrate the superior performance of our EGFDA. Furthermore, extensive ablation studies and visual analyses highlight the remarkable interpretability and generalization of the proposed method.

Physician experiences of team-based clinical microsystems: implications for the future of inpatient interprofessional communication

ABSTRACT Healthcare clinical microsystems are small, goal-oriented groups of healthcare professionals that work together on a regular basis to provide care to discrete patient populations. They often include team-based frameworks such as bedside interprofessional rounds, geographic colocation of healthcare team members, interprofessional staff leadership, and unit-level data sharing. In inpatient settings, microsystems improve interprofessional communication and collaboration. In this qualitative study, we examined physician experiences of clinical microsystems and the mechanisms underpinning interprofessional communication in this environment. We interviewed 51 resident and hospitalist physicians. Thematic analysis of physician experiences revealed three key themes: (a) Clinical microsystem effect on workflow, (b) Open forum and work relationships, and (c) Face-to-face vs technology-based communication. Physicians described strong interprofessional relationships based on frequent face-to-face communication. Familiarity with healthcare team members, often resulting from being co-located to the same units, created a comfortable work environment, advanced patient care, and accelerated workflow. Physicians preferred in-person communication with interprofessional colleagues over technology-based communicationand described how in-person interactions enriched subsequent technology-led interactions. As the use of technology-based communication grows in inpatient settings, decreasing face-to-face interactions and facilitating dispersed care, understanding and implementing optimal conditions for effective interprofessional communication is essential.

Weathering the Storm

The provision of palliative care has been seen to have a significant impact on the interprofessional health care team. Being emotionally present to support patients and families at their most stressful points in life can result in compassion satisfaction or compassion fatigue. Providing palliative care through the COVID-19 pandemic added another layer of complexity to this professional caregiving experience. Although efforts have been made by employers to support health care providers in the practices of self-care and mindfulness, the true experience of care providers was not known. This study was conducted from June 2020 to October 2020 to better understand the experiences of physicians, nurses, social workers, and spiritual care providers who were providing palliative care during the first wave of the pandemic. Twenty-five participants completed the Professional Quality of Life (The Concise ProQOL Manual: The Concise Manual for the Professional Quality of Life Scale) measure and open-ended questions to evaluate their experiences as health care providers. The findings resulted in an overarching theme of “Weathering the Storm” with 6 themes describing the experiences of the interprofessional team.

The study on ultrasound image classification using a dual-branch model based on Resnet50 guided by U-net segmentation results

In recent years, the incidence of nodular thyroid diseases has been increasing annually. Ultrasonography has become a routine diagnostic tool for thyroid nodules due to its high real-time capabilities and low invasiveness. However, thyroid images obtained from current ultrasound tests often have low resolution and are plagued by significant noise interference. Regional differences in medical conditions and varying levels of physician experience can impact the accuracy and efficiency of diagnostic results. With the advancement of deep learning technology, deep learning models are used to identify whether a nodule in a thyroid ultrasound image is benign or malignant. This helps to close the gap between doctors’ experience and equipment differences, improving the accuracy of the initial diagnosis of thyroid nodules. To cope with the problem that thyroid ultrasound images contain complex background and noise as well as poorly defined local features. in this paper, we first construct an improved ResNet50 classification model that uses a two-branch input and incorporates a global attention lightening module. This model is used to improve the accuracy of benign and malignant nodule classification in thyroid ultrasound images and to reduce the computational effort due to the two-branch structure.We constructed a U-net segmentation model incorporating our proposed ACR module, which uses hollow convolution with different dilation rates to capture multi-scale contextual information for feature extraction of nodules in thyroid ultrasound images and uses the results of the segmentation task as an auxiliary branch for the classification task to guide the classification model to focus on the lesion region more efficiently in the case of weak local features. The classification model is guided to focus on the lesion region more efficiently, and the classification and segmentation sub-networks are respectively improved specifically for this study, which is used to improve the accuracy of classifying the benign and malignant nature of the nodules in thyroid ultrasound images. The experimental results show that the four evaluation metrics of accuracy, precision, recall, and f1 of the improved model are 96.01%, 93.3%, 98.8%, and 96.0%, respectively. The improvements were 5.7%, 1.6%, 13.1%, and 7.4%, respectively, compared with the baseline classification model.

The Expanding Role of Designated Institutional Officials in Graduate Medical Education

Abstract The Accreditation Council for Graduate Medical Education (ACGME) plays a pivotal role in ensuring the quality of graduate medical education (GME) training across the United States. Central to the success of this mission are designated institutional officials (DIOs), who usually serve as chief GME officers within the ACGME-accredited sponsoring institutions (SIs). Despite the critical role of DIOs, the qualifications, level of administrative support, and responsibilities of DIOs are not defined and vary significantly among SIs. Although responsibilities mandated by ACGME Institutional Requirements provide a framework, the actual scope of work of DIOs often extends far beyond what is outlined in the ACGME Institutional Requirements, involving collaboration with a wide variety of institutional stakeholders and harnessing the GME enterprise to achieve institutional goals. Nearly all DIOs face a multitude of challenges, including adapting to new ACGME requirements and initiatives, addressing resident and fellow wellness concerns, promoting health equity, nurturing scholarly endeavors, and advocating for their residents and fellows. Additionally, emerging technologies and innovations as well as the changing financial climate for SIs and the health care facilities that host GME learners can present both educational opportunities and new challenges for DIOs in ensuring trainees are prepared for their roles as the next generation of physicians. As the health care landscape evolves, DIOs will continue to play a vital role in shaping the educational experiences of physicians in training while balancing institutional priorities and ensuring high-quality patient care.

Exploring the attitudes and experiences of Hungarian primary care physicians on the utilisation of digital health solutions

BackgroundDuring the COVID-19 pandemic, digital health solutions ensured the continuity of care especially in primary healthcare practices. COVID-19 accelerated the adoption of digital health solutions. The aim of this study is to describe the digital health-related attitudes and experiences of Hungarian Primary Care Physicians (PCPs) and also analyse the socio-demographic effects on digital health attitudes among PCPs.MethodsThis study used a quantitative and qualitative mixed methodological approach to examine the digital health-related attitudes and experience of Hungarian PCPs. As part of the "E-physicians and E-patients in Hungary" survey, we conducted an online survey among medical doctors working in Hungary between July 2021 to May 2022. A total of 1,774 questionnaires were received, consisting of 1,576 medical doctors and 198 dentists. Among the medical doctors there were 415 primary care physicians (PCPs). In addition to the online questionnaire survey, qualitative research in the form of semi-structured interviews with doctors was also conducted. These interviews took place between October 2021 and June 2022. A total of 62 interviews were conducted,19 with PCPs.ResultsPrimary care physicians are more open to technologies that facilitate communication and collaboration with patients, while showing less interest in technologies that support clinical work. Of the demographic variables (age, gender, type of settlement), age was found to have the most significant effect on digital health knowledge, use and intended use. Both the interviews and the multivariate analysis indicate that individuals with greater knowledge, expertise, and experience are more likely to perceive the advantages of digital solutions. This highlights the importance of training, especially given the significant aging population among Hungarian primary care physicians, who may not be accustomed to using these tools naturally. The way PCPs perceive patient expectations regarding the use of digital health tools has a significant impact on the PCPs’ use and intended use of digital tools. When looking at perceived patient needs among PCPs the effect of age and municipality type of PCPs is significant. As age increases, the perception of patient needs decreases (from 5.02 to 4.47), and by municipality type, the average number of perceived needs decreases as one moves from larger cities to smaller municipalities (from 4.85 to 4.14).ConclusionsDigital health solutions have the potential to enhance the work of PCPs, but successful implementation requires addressing specific needs, demographic differences, and challenges faced by PCPs. Development of infrastructure, education, and institutional support is necessary to ensure more efficient and higher-quality healthcare delivery through the use of digital technologies.

Skin Cancer Diagnosis by Lesion, Physician, and Examination Type

Skin cancer is the most common cancer in the US; accurate detection can minimize morbidity and mortality. To assess the accuracy of skin cancer diagnosis by lesion type, physician specialty and experience, and physical examination method. PubMed, Embase, and Web of Science. Cross-sectional and case-control studies, randomized clinical trials, and nonrandomized controlled trials that used dermatologists or primary care physicians (PCPs) to examine keratinocytic and/or melanocytic skin lesions were included. Search terms, study objectives, and protocol methods were defined before study initiation. Data extraction was performed by a reviewer, with verification by a second reviewer. A mixed-effects model was used in the data analysis. Data analyses were performed from May 2022 to December 2023. Meta-analysis of diagnostic accuracy comprised sensitivity and specificity by physician type (primary care physician or dermatologist; experienced or inexperienced) and examination method (in-person clinical examination and/or clinical images vs dermoscopy and/or dermoscopic images). In all, 100 studies were included in the analysis. With experienced dermatologists using clinical examination and clinical images, the sensitivity and specificity for diagnosing keratinocytic carcinomas were 79.0% and 89.1%, respectively; using dermoscopy and dermoscopic images, sensitivity and specificity were 83.7% and 87.4%, and for PCPs, 81.4% and 80.1%. Experienced dermatologists had 2.5-fold higher odds of accurate diagnosis of keratinocytic carcinomas using in-person dermoscopy and dermoscopic images compared with in-person clinical examination and images. When examining for melanoma using clinical examination and images, sensitivity and specificity were 76.9% and 89.1% for experienced dermatologists, 78.3% and 66.2% for inexperienced dermatologists, and 37.5% and 84.6% for PCPs, respectively; whereas when using dermoscopy and dermoscopic images, sensitivity and specificity were 85.7% and 81.3%, 78.0% and 69.5%, and 49.5% and 91.3%, respectively. Experienced dermatologists had 5.7-fold higher odds of accurate diagnosis of melanoma using dermoscopy compared with clinical examination. Compared with PCPs, experienced dermatologists had 13.3-fold higher odds of accurate diagnosis of melanoma using dermoscopic images. The findings of this systematic review and meta-analysis indicate that there are significant differences in diagnostic accuracy for skin cancer when comparing physician specialty and experience, and examination methods. These summary metrics of clinician diagnostic accuracy could be useful benchmarks for clinical trials, practitioner training, and the performance of emerging technologies.

Different Evaluation Strategies of Oncological CT Examinations with Regard to Professional Experience: A Clinical Study Using Eye-tracking.

Contrast-enhanced CT is the standard imaging technique in oncological objectives. Rates of missed pathologies depend on work experience of the respective radiologists. Thus the aim of this study is to analyze the eye movements of professionals while reading CT images in order to evaluate whether the eye-fixation patterns and search strategies of experienced radiologists could explain higher detection rates of pathologies and whether such patterns can be learned.Anonymized images of 10 patients were presented to three medical students and six radiologists with different levels of work experience. During image analysis, ocular fixation positions were recorded using an eye-tracking software tool. The CT scans were analyzed retrospectively, considering the individual course of disease with the issue of successful detection of all pathologies. Visual attention and dwell time of ocular fixation on clinically important abnormalities or areas with pathological findings, general search patterns, and time efficiency were assessed. For statistical analysis, interobserver variability and accuracy of lesion detection were evaluated taking into account individual experience.The results revealed that observer sensitivity depends on work experience due to a more systematic order of inspection and a well-known course of disease, e.g. in case of metastatic spread. The areas of missed pathologies mostly included secondary findings. Inexperienced readers changed the stratification considerably more often and required more time for reporting or detecting pathologies.Our results suggest that experienced radiological physicians reduce their amount of missed findings by looking more systematically at images and by applying a more targeted inspection of clinically important regions. · CT interpretation by radiology residents is faster and less error-prone compared to postgraduate residents. · systematic image analysis is trainable. · engrams tend to be acquired through experience. · Kluge S, Schülke C, Ites HC et al. Different Evaluation Strategies of Oncological CT Examinations with Regard to Professional Experience: A Clinical Study Using Eye-tracking. Fortschr Röntgenstr 2024; DOI 10.1055/a-2452-2180.

Lived experiences of palliative care physicians on the impacts of language and cultural discordance on end-of-life care across Ontario, Canada: a qualitative study using the intersectionality-based policy framework

BackgroundLanguage and cultural discordance refer to when a physician and patient do not share the same language or culture. This can create barriers to providing high-quality care at the end-of-life (EoL). This study explores the intersections of language, culture, geography, and care model in EoL care from the perspectives of palliative care physicians.MethodsIn this exploratory-descriptive qualitative study, semi-structured interviews (1-h) were conducted virtually between July and November 2023. We interviewed 16 family physicians with experience providing linguistic and/or culturally discordant palliative/EoL care in various urban, suburban, and rural regions of Ontario, who practiced at community and hospital outpatient clinics, home-based care, or long-term care homes. We used reflexive thematic analysis to identify themes across the interviews guided by the intersectionality theoretical framework.ResultsWe identified three themes 1) Visible barriers to care access due to the inability to communicate accurate information and insufficient time spent during appointments with patients; 2) Invisible barriers to care access, shaped by the Eurocentric approach to palliative care and physicians’ lack of awareness on cultural discordance; 3) Workplace supports that currently exist and interventions that physicians would like to see. Community physicians following fee-for-service models were less likely to have access to professional interpreter services. Physicians in long-term care emphasized resource limitations to providing culturally-appropriate care environments.ConclusionCultural discordance required awareness of personal biases, while language discordance hindered basic communication. These findings will be useful in informing clinical practice guidelines and mobilizing policy-level change to improve palliative/EoL care for patients from linguistic and cultural minority groups.

Motivations and Experiences of Physicians Who Pursued Hemostasis and Thrombosis Fellowship - a Survey Study

Motivations and Experiences of Physicians Who Pursued Hemostasis and Thrombosis Fellowship - a Survey Study

Factors Associated with Increased Risk of Contamination in Bone Marrow Transplants

Hematopoietic cell transplantation (HCT) remains the definitive therapeutic modality for numerous malignant and non-malignant hematologic disorders. Conventional bone marrow remains a viable donor source for HCT. However, microbial contamination of bone marrow harvests may present a risk to immunocompromised recipients. This analysis sought to identify clinical factors associated with bone marrow contamination. We analyzed a single institution experience comprising 667 unique bone marrow harvests collected between 1999 and 2021. We trended the yearly microbial contamination rate over this time span. Harvest type (autologous versus allogenic), donor age, donor sex, physician experience, total nucleated cell (TNC) count, volume collected, and TNC concentration were included in a univariate (UV) and multivariate (MV) logistic model to assess which factors were associated with contamination. Males comprised 55.8% of the donor population and the median age of the cohort was 35 [IQR: 27 to 45]. There were 19 autologous, 151 related allogenic, and 497 unrelated allogenic transplants in this cohort. 87 of the 667 (13.0%) harvests were contaminated and essentially all contaminants were common skin flora. The yearly contamination rates displayed substantial variability, ranging from 0% to 42.9%, with no discernible trend. Harvest type did not exhibit a significant association with contamination risk. However, male donor sex was found to be significantly associated with a higher contamination rate (18%) compared to female sex (6.8%, P < .001). In both UV and MV logistic models, male sex emerged as the sole factor linked to contamination risk (OR: 2.90, 95% CI: 1.65 to 5.35). This analysis represents the largest single-center investigation of bone marrow harvest microbial contamination rates. Notably, it is the first to establish an association between contamination and male donor sex. We propose that this association may be attributed to differences in skin flora composition or innate immune function between sexes, general hygiene practices or possibly the result of the frequent clipping of body hair in males prior to the harvest procedure. Further research is warranted to explore the underlying mechanisms and clinical implications of this novel finding.

Behavioural intentions towards use of digital video consultations in primary care: a survey study on physicians’, nurses’ and psychologists’ perceptions in Swedish primary care

ObjectivesThe study aimed to describe the experiences of physicians, nurses and psychologists employed in primary care in using digital video consultations. The second objective was to study the association between...

Utilization management and physician burnout.

This study was designed to assess physician experiences with utilization management and burnout and investigate whether they are linked. We conducted an electronic survey with items related to demographics, profession, utilization management, burnout, and potential policy solutions. The survey was sent to 7222 physicians working in outpatient settings who were recruited from a large, opt-in database. Outcome measures were responses to categorical and Likert-style survey items related to demographics, utilization management, burnout, and potential policy solutions. Of 7222 requests sent, 501 physicians completed the survey and were included in the final data set (77% men; mean [SD] age, 57 [9.8] years; mean [SD] years in practice, 24 [8.9]). Of these, 200 were general practitioners and 301 were nonhospital specialists. Physicians indicated that utilization management procedures for prior authorization (81%), step therapy (79%), and nonmedical switching (69%) were major or significant barriers to their clinical and patient care. More than half (52%) reported spending 6 to 21 or more hours per week on paperwork related to health insurance utilization management, 67% had experienced burnout at some point in their careers, and 64% indicated that utilization management had been a contributing factor to feelings of burnout, with an additional 8% citing it as the main factor. Physicians favored streamlining prior authorization practice (77%), requiring step therapy to be based on science (73%), and ensuring that peer-to-peer reviews are done by qualified medical experts (67%). These findings indicate that utilization management has a detrimental impact on physicians and patient care and contributes to physician burnout.

A machine learning framework to adjust for learning effects in medical device safety evaluation.

Traditional methods for medical device post-market surveillance often fail to accurately account for operator learning effects, leading to biased assessments of device safety. These methods struggle with non-linearity, complex learning curves, and time-varying covariates, such as physician experience. To address these limitations, we sought to develop a machine learning (ML) framework to detect and adjust for operator learning effects. A gradient-boosted decision tree ML method was used to analyze synthetic datasets that replicate the complexity of clinical scenarios involving high-risk medical devices. We designed this process to detect learning effects using a risk-adjusted cumulative sum method, quantify the excess adverse event rate attributable to operator inexperience, and adjust for these alongside patient factors in evaluating device safety signals. To maintain integrity, we employed blinding between data generation and analysis teams. Synthetic data used underlying distributions and patient feature correlations based on clinical data from the Department of Veterans Affairs between 2005 and 2012. We generated 2494 synthetic datasets with widely varying characteristics including number of patient features, operators and institutions, and the operator learning form. Each dataset contained a hypothetical study device, Device B, and a reference device, Device A. We evaluated accuracy in identifying learning effects and identifying and estimating the strength of the device safety signal. Our approach also evaluated different clinically relevant thresholds for safety signal detection. Our framework accurately identified the presence or absence of learning effects in 93.6% of datasets and correctly determined device safety signals in 93.4% of cases. The estimated device odds ratios' 95% confidence intervals were accurately aligned with the specified ratios in 94.7% of datasets. In contrast, a comparative model excluding operator learning effects significantly underperformed in detecting device signals and in accuracy. Notably, our framework achieved 100% specificity for clinically relevant safety signal thresholds, although sensitivity varied with the threshold applied. A machine learning framework, tailored for the complexities of post-market device evaluation, may provide superior performance compared to standard parametric techniques when operator learning is present. Demonstrating the capacity of ML to overcome complex evaluative challenges, our framework addresses the limitations of traditional statistical methods in current post-market surveillance processes. By offering a reliable means to detect and adjust for learning effects, it may significantly improve medical device safety evaluation.