Medical Interpretation Research Articles

Deep Learning Auto-Segmentation Network for Pediatric Computed Tomography Data Sets: Can We Extrapolate From Adults?

PurposeAI-based auto-segmentation models hold promise for enhanced efficiency and consistency in organ contouring for adaptive radiotherapy and radiotherapy planning. However, their performance on paediatric CT data and cross-scanner compatibility remains unclear. This study aims to evaluate the performance of AI-based auto-segmentation models trained on adult CT data when applied to paediatric datasets and explore the improvement in performance gained by including paediatric training data. It also examines their ability to accurately segment CT data acquired from different scanners. Methods and MaterialsUsing the nnU-Net framework, segmentation models were trained on datasets of adult, paediatric, and combined CT scans for seven pelvic/thoracic organs. Each model was trained on 290-300 cases per category and organ. Training datasets included a combination of clinical data and several open repositories. The study incorporated a database of 459 paediatric (0-16 years) CT scans and 950 adults (>18 years), ensuring all scans had human expert ground-truth contours of the selected organs. Performance was evaluated based on Dice similarity coefficients (DSC) of the model-generated contours. ResultsAI-models trained exclusively on adult data underperformed on paediatric data, especially for the 0-2 age group: mean DSC was below 0.5 for the bladder and spleen. The addition of paediatric training data demonstrated significant improvement for all age groups, achieving a mean DSC of above 0.85 for all organs in every age group. Larger organs like the liver and kidneys maintained consistent performance for all models across age groups. No significant difference emerged in the cross-scanner performance evaluation, suggesting robust cross-scanner generalization. ConclusionFor optimal segmentation across age groups, it is important to include paediatric data in the training of segmentation models. The successful cross-scanner generalization also supports the real-world clinical applicability of these AI models. This study emphasizes the significance of dataset diversity in training robust AI systems for medical image interpretation tasks.

Poseidon and Caeneus: a case of pubertal gender inversion in Greek mythology.

Disorders of sex development (DSDs) are very frequently encountered in ancient Greek mythology. One of the most striking types of DSD described in many myths is gender transformation wherein a female becomes a male or vice versa. Herein, we present via the marvelous myth of Poseidon and Caeneus a case of pubertal gender inversion. A medical interpretation of the myth whereby we attempt to form a diagnosis of this case of DSD is also presented.

Improving pain communication between limited English-speaking Hmong patients, medical interpreters, and health care providers in primary care: A pilot study.

This pilot study assessed the feasibility of implementing a pain assessment information visualization (InfoViz) tool to address cultural and language barriers among limited English proficiency (LEP) Hmong patients in primary care. We used a static group comparison design to collect data from 20 patient, interpreter, and provider triads under usual care (i.e., interpreter using verbal pain descriptions), followed by another 20 triads under the intervention (i.e., interpreter using verbal pain descriptions and the InfoViz tool). Feasibility outcomes included recruitment and retention rates, InfoViz tool completion, acceptability, and fidelity. We also assessed mutual understanding (MU) and pain electronic health record (EHR) documentation. Descriptive data were calculated and thematic analysis was conducted. Thirty-six LEP Hmong patients (n = 29 female, mean age = 59.03), 27 providers (n = 15 female), and four interpreters participated in this study. The patient recruitment rate was 18% while the retention rate was 81%. Interpreter recruitment rate was 80%, and 75% for retention rate. The intervention fidelity mean score was 83%. In the intervention condition, patient-provider MU of pain severity improved by 30%, coupled with a 28% increase in pain severity EHR documentation compared to usual care. While communication of pain quality did not improve, there was a higher mean number of pain descriptors (3.31 in the intervention vs. 1.79 in usual care) in EHR documentation. All participants had a positive experience with the tool, reporting it as valuable with 100% completeness of all tools. Findings revealed the tool was acceptable and feasible to use among LEP patients-interpreters-providers, providing support for an efficacy study.

An Investigation into the Prevention of Turnover of Medical Interpreters.

Since there have been no studies for the prevention of job turnover among medical interpreters, this study examined the effects of social support, professional career maturity and stress coping on their attitudes toward job continuity intentions. A cross-sectional study was conducted to examine the relationships between social support, professional career maturity, stress coping and job continuity intentions. Stress coping was measured by using a simplified stress coping scale (with 9 items and 1 factor structure). Social support was measured by defining the interpreters who answered "Yes" for "I have someone to talk to when I feel emotional stress". Professional carrier maturity was assessed by using, 12 career-related items. We defined those interpreters who responded "No" to "Have you ever wanted to quit medical interpreting due to emotional stress?" were to have job continuity intentions. The present study indicated that 14 (25.5%) of the interpreters did not intend to continue their occupation because of their psychological stresses. Compared to interpreters without social support, the odds ratio of job continuity intentions was 4.39 (95% confidence interval [CI] : 1.13-18.3) for those with social support. Moreover, in comparison with the interpreters with low professional career maturity, the odds ratio of job continuity intentions was significantly higher for those with high professional career maturity (odds ratio [OR] = 4.35; 95%CI: 1.12-21.8). However, there was an association found for stress coping. Strengthening social support and helping professional career development were the important factors for medical interpreters to be able to continue their careers.

EYE-ECG: An RCT of the influence of student characteristics and expert eye-tracking videos with cued retrospective reporting on students' ECG interpretation skills.

Teaching of ECG interpretation frequently relies on visual schemas. However, subsequent student ECG interpretation skills are often poor. Expertise research shows that expert looking patterns frequently deviate from the steps taught in schema learning. The present study made a cardiology expert's gaze interpreting ECGs visible - through eye-tracking videos with cued retrospective reporting (CRR) - and investigated the potential as an additional expert-driven route to improve medical students' ECG interpretation skills. N=91 Medical students participated in the RCT of an ECG e-learning session aimed at medical students' ECG interpretation skills gain, either receiving the newly developed eye-tracking video with CRR audio commentary materials (n=47) or studying via four clinical cases only (n=44). Three outcome scores relating to different aspects of ECG interpretation skills were derived from pre-post MCQ ECG tests. The effect of the EYE-ECG training and additional characteristics (e.g., prior experience, interest) on student ECG interpretation skills were evaluated using t-tests and multivariate linear regression. A small, non-significant advantage of the EYE-ECG training signifying a tendency for greater knowledge gain was observed, compared to training as usual. In multivariate regression models, the predictive value of clinical case 1 was an unexpected finding warranting further exploration. Additional gains after an only 9-minute intervention using videos of expert's real-time gaze pattern in combination with hearing their thought processes during ECG interpretation is a promising finding. Furthermore, a number of specific performance characteristics enabling students to best benefit from ECG training were identified and possible modifications to the learning intervention suggested.

Effect of Virtual Versus In Person Interpreting on Diabetes Outcomes in Non-English Language Preference Patients: A Pilot Study.

The objective of this pilot study was to explore the impact of interpreter format (virtual vs in person) on clinical outcomes in patients with non-English language preference (NELP) and type 2 diabetes mellitus (T2DM) in a primary care setting. We hypothesized that NELP patients utilizing in person interpreters would have improved HbA1c values, better follow-up rate, and more complex care plans compared to patients utilizing virtual interpreters. We completed a retrospective chart review of 137 NELP patients with T2DM who required a medical interpreter (February to June 2021). We calculated univariate and bivariate statistics to characterize the sample and assess the extent to which measures of continuity (follow-up visit rate and time to follow-up visit), quality (change in HbA1c), and complexity (medication intervention complexity) were associated with interpreter type. There was no statistically significant difference in follow-up rate or average days to follow-up visit for NELP patients with in person as opposed to virtual interpreters. Patients with virtual interpreters demonstrated a non-statistically significant decrease in HbA1c compared to those with in person interpreters. Finally, there was no statistically significant association between interpreter format and intervention complexity. Quality medical interpretation contributes to optimal health outcomes in NELP patients with diabetes. Our study suggests that both in person and virtual interpreters can be effective in providing care for NELP patients, especially for chronic disease management in the context of a primary care relationship. It also highlights the importance of pursuing additional qualitative and mixed method studies to better understand the benefits of various interpreter formats across different visit types.

Koncepcja „patocenozy” a naukowe struktury narracji o pandemii COVID-19. Doświadczenia i perspektywy

The concept of “pathocoenosis” and the scientific structures of the narrative about the Covid-19 pandemic. Experiences and perspectives The author considers to what extent “pathcenosis”, the concept of the Croatian- French historian of medicine Mirko Grmek (1924–2000), can provide a theoretical framework for contemporary and historical research on pandemics. This term denoted the set of diseases occurring in a given population at a given time and the relationships between them. The current COVID-19 pandemic is the impetus for contemporary research. Research on the scientifi c discourse in the reports of the COVID-19 Advisory Team at the President of the Polish Academy of Sciences allowed for the diagnosis of the theoretical usefulness of pathocoenosis. The area of these analyzes includes historical and medical interpretations, scientifi c myth and social myths about science, scientifi c consensus and the dissemination of science. These studies showed two dangerous tendencies: 1. discrepancies in the understanding of the strategy of fi ghting the pandemic between the multidisciplinary world of science and the state authorities; 2. slight social impact of scientifi c authorities on negationist social attitudes. Both trends have a real impact on the shaping of the pandemic situation. Prospects for the continuation of this research concern, among others searching for the possibility of modifying the concept of „pathocenosis” with the epidemiological consequences of globalization processes, the use of „pathocenosis” as a narrative structure in the historiography of medical sciences, the use of the concept of „pathocenosis” as an inspiration for theoretical approaches in studies on the history of social practices towards health and disease. The prospects for continuing the research carried out also take into account the presence of the socio-cultural context and the dynamics of changes in the pandemic in the scientific discourse. And also the great importance of the narrative of anti-science movements in Poland. All these factors infl uence the nature of the Polish pathocoenosis.

Advancing language concordant care: a multimodal medical interpretation intervention

BackgroundEnsuring language concordant care through medical interpretation services (MIS) allows for accurate information sharing and positive healthcare experiences. The COVID-19 pandemic led to a regional halt of in-person interpreters, leaving...

The Road Ahead: Emerging Trends, Unresolved Issues, and Concluding Remarks in Generative AI—A Comprehensive Review

The field of generative artificial intelligence (AI) is experiencing rapid advancements, impacting a multitude of sectors, from computer vision to healthcare. This paper provides a comprehensive review of generative AI’s evolution, significance, and applications, including the foundational architectures such as generative adversarial networks (GANs), variational autoencoders (VAEs), autoregressive models, flow‐based models, and diffusion models. We delve into the impact of generative algorithms on computer vision, natural language processing, artistic creation, and healthcare, demonstrating their revolutionary potential in data augmentation, text and speech synthesis, and medical image interpretation. While the transformative capabilities of generative AI are acknowledged, the paper also examines ethical concerns, most notably the advent of deepfakes, calling for the development of robust detection frameworks and responsible use guidelines. As generative AI continues to evolve, driven by advances in neural network architectures and deep learning methodologies, this paper provides a holistic overview of the current landscape and a roadmap for future research and ethical considerations in generative AI.

医学同传译员的承诺伦理——切斯特曼传统翻译伦理模式之粘合剂

医学同传译员的承诺伦理——切斯特曼传统翻译伦理模式之粘合剂

Clinical Application of Artificial Intelligence-Based Detection Assistance Devices for Chest X-Ray Interpretation: Current Status and Practical Considerations

Artificial intelligence (AI) technology is actively being applied for the interpretation of medical imaging, such as chest X-rays. AI-based software medical devices, which automatically detect various types of abnormal findings in chest X-ray images to assist physicians in their interpretation, are actively being commercialized and clinically implemented in Korea. Several important issues need to be considered for AI-based detection assistant tools to be applied in clinical practice: the evaluation of performance and efficacy prior to implementation; the determination of the target application, range, and method of delivering results; and monitoring after implementation and legal liability issues. Appropriate decision making regarding these devices based on the situation in each institution is necessary. Radiologists must be engaged as medical assessment experts using the software for these devices as well as in medical image interpretation to ensure the safe and efficient implementation and operation of AI-based detection assistant tools.

Infusion extraction and measurement on CT images based on computer vision and neural network

This paper presents a new approach to the automated detection and quantification of pulmonary emphysema and pneumoconiosis using computed tomography images. The proposed method employs computer vision and neural network algorithms to improve the accuracy and speed of lung diagnosis, as well as the monitoring of emphysema and its changes over time. The study analyzes existing approaches and demonstrates the novelty of the proposed method. The paper reports high accuracy of emphysema extraction and size measurements based on three different patient cases, as evaluated by an expert, and the successful segmentation of pneumosclerosis. The proposed method has the potential to significantly improve medical image segmentation, particularly in the detection and diagnosis of diseases such as Chronic Obstructive Pulmonary Disease (COPD) and COVID-19. The study concludes that the proposed method may also be useful in other areas of medical imaging, contributing to the ongoing effort to develop new and improved methods for medical image analysis and interpretation.

Impacts of the advancement in artificial intelligence on laboratory medicine in low- and middle-income countries: Challenges and recommendations-A literature review.

Artificial intelligence (AI) has emerged as a transformative force in laboratory medicine, promising significant advancements in healthcare delivery. This study explores the potential impact of AI on diagnostics and patient management within the context of laboratory medicine, with a particular focus on low- and middle-income countries (LMICs). In writing this article, we conducted a thorough search of databases such as PubMed, ResearchGate, Web of Science, Scopus, and Google Scholar within 20 years. The study examines AI's capabilities, including learning, reasoning, and decision-making, mirroring human cognitive processes. It highlights AI's adeptness at processing vast data sets, identifying patterns, and expediting the extraction of actionable insights, particularly in medical imaging interpretation and laboratory test data analysis. The research emphasizes the potential benefits of AI in early disease detection, therapeutic interventions, and personalized treatment strategies. In the realm of laboratory medicine, AI demonstrates remarkable precision in interpreting medical images such as radiography, computed tomography,and magnetic resonance imaging.Its predictive analytical capabilities extend to forecasting patient trajectories and informing personalized treatment strategies using comprehensive data sets comprising clinical outcomes, patient records, and laboratory results. The study underscores the significance of AI in addressing healthcare challenges, especially in resource-constrained LMICs. While acknowledging the profound impact of AI on laboratory medicine in LMICs, the study recognizes challenges such as inadequate data availability, digital infrastructure deficiencies, and ethical considerations. Successful implementation necessitates substantial investments in digital infrastructure, the establishment of data-sharing networks, and the formulation of regulatory frameworks. The study concludes that collaborative efforts among stakeholders, including international organizations, governments, and nongovernmental entities, are crucial for overcoming obstacles and responsibly integrating AI into laboratory medicine in LMICs. A comprehensive, coordinated approach is essential for realizing AI's transformative potential and advancing health care in LMICs.

MRI for axial SpA: Diagnosis, disease activity assessment, and recent advances.

Magnetic resonance imaging (MRI) is a sensitive imaging modality to detect early inflammatory changes in axial spondyloarthritis (SpA). Over a decade has passed since the inclusion of MRI assessment in the 2009 Assessment of SpondyloArthritis International Society (ASAS) classification criteria for axial SpA. Evidence and clinical experience of MRI in axial SpA have accumulated rapidly since. This has led to a better understanding of the clinical utility of MRI in early diagnosis, disease activity assessment, and monitoring of treatment response in axial SpA. Furthermore, technological advancements have paved the way for the development of novel MRI sequences for the quantification of inflammation and image optimization. The field of artificial intelligence has also been explored to aid medical imaging interpretation, including MRI in axial SpA. This review serves to provide an update on the latest understanding of the evolving roles of MRI in axial SpA.

Translation, cultural adaptation, and validation of the PHQ-9 and GAD-7 in Kinyarwanda for primary care in the United States.

Depression and anxiety are significant health burdens that greatly impact the quality of life of refugees and migrants. In this study, we have translated and culturally adapted the Patient Health Questionnaire (PHQ-9) and Generalized Anxiety Disorder Screener (GAD-7) into Kinyarwanda and performed a validation study in a United States (US) primary care setting. A committee of seven experts including psychiatric and family medicine providers, health researchers, and trained medical interpreters translated and culturally adapted the PHQ-9 and GAD-7, and incorporated feedback from cognitive interviews with bilingual participants. The translated instruments were then tested in a cross-sectional validation study. Analyses include internal consistency, discriminant validity, principal component analyses, and confirmatory factor analyses. Analyses of 119 responses indicated overall good internal consistency with Cronbach's α of 0.85 (PHQ-9) and 0.92 (GAD-7). Both scales showed acceptable factor loadings between 0.44 and 0.90 in the principal component analyses and showed strong correlations with health-related quality of life and depression/anxiety symptoms measured with visual analog scales. Significantly higher scores for PHQ-9 and GAD-7 were shown among participants with known psychiatric conditions. PHQ-9 and GAD-7 demonstrated commendable applicability for Kinyarwanda-speaking patients in primary healthcare settings in the US. Our instruments can already be used in primary care settings and thus help to mitigate health disparities. Future research should further validate our tool against gold-standard diagnostics in larger, geographically diverse samples.

Patient Time Spent With Professional Medical Interpreters and the Care Experiences of Patients With Limited English Proficiency.

More time spent with interpreters may support clinician-patient communication for patients with limited English proficiency (LEP), especially when interpreter support before and after clinical encounters is considered. We assessed whether more time spent with interpreters is associated with better patient-reported experiences of clinician-patient communication and interpreter support among patients with LEP. Patients with LEP (n = 338) were surveyed about their experiences with both the clinician and interpreter. Duration of interpreter support during the encounter (in min) and auxiliary time spent before and after encounters supporting patients (in min) were documented by interpreters. Multivariable linear regression models were estimated to assess the association of the time duration of interpreter support and patient experiences of (1) clinician-patient communication, and (2) interpreter support, controlling for patient and encounter characteristics. The average encounter duration was 47.7 min (standard deviation, SD = 25.1), the average auxiliary time was 43.8 min (SD = 16.4), and the average total interpreter time was 91.1 min (SD = 28.6). LEP patients reported better experiences of interpreter support with a mean score of 97.4 out of 100 (SD = 6.99) compared to clinician-patient communication, with a mean score of 93.7 out of 100 (SD = 14.1). In adjusted analyses, total patient time spent with an interpreter was associated with better patient experiences of clinician-patient communication (β = 7.23, P < .01) when auxiliary time spent by interpreters supporting patients before and after the encounter was considered, but not when only the encounter time was considered. Longer duration of time spent with an interpreter was associated with better clinician-patient communication for patients with LEP when time spent with an interpreter before and after the clinician encounter is considered. Policymakers should consider reimbursing health care organizations for time interpreters spend providing patient navigation and other support beyond clinical encounters.

Detection and classification of brain tumor using hybrid deep learning models

Accurately classifying brain tumor types is critical for timely diagnosis and potentially saving lives. Magnetic Resonance Imaging (MRI) is a widely used non-invasive method for obtaining high-contrast grayscale brain images, primarily for tumor diagnosis. The application of Convolutional Neural Networks (CNNs) in deep learning has revolutionized diagnostic systems, leading to significant advancements in medical imaging interpretation. In this study, we employ a transfer learning-based fine-tuning approach using EfficientNets to classify brain tumors into three categories: glioma, meningioma, and pituitary tumors. We utilize the publicly accessible CE-MRI Figshare dataset to fine-tune five pre-trained models from the EfficientNets family, ranging from EfficientNetB0 to EfficientNetB4. Our approach involves a two-step process to refine the pre-trained EfficientNet model. First, we initialize the model with weights from the ImageNet dataset. Then, we add additional layers, including top layers and a fully connected layer, to enable tumor classification. We conduct various tests to assess the robustness of our fine-tuned EfficientNets in comparison to other pre-trained models. Additionally, we analyze the impact of data augmentation on the model's test accuracy. To gain insights into the model's decision-making, we employ Grad-CAM visualization to examine the attention maps generated by the most optimal model, effectively highlighting tumor locations within brain images. Our results reveal that using EfficientNetB2 as the underlying framework yields significant performance improvements. Specifically, the overall test accuracy, precision, recall, and F1-score were found to be 99.06%, 98.73%, 99.13%, and 98.79%, respectively.

Study on the Integration of Professional Ethics in Medical Interpretation Course Based on Situational Simulation Teaching Method and Virtual Reality Technology

Based on the theory of situational simulation, the article explores the approach to building the medical interpretation course from three aspects, which are the objective, design, and teaching model. The course aims to cultivate high-quality medical interpreting talents and enhance students’ practical interpretation skills, as well as to integrate professional ethics into teaching. Thus, it is necessary for lecturers to change their teaching philosophy, apply information technology, and improve teaching design. Through rich medical interpretation course, lecturers can promote the integration of professional ethics in medical interpretation.

ADDRESSING THE CHRONIC PAIN EPIDEMIC AMONG OLDER ADULTS IN UNDERSERVED COMMUNITY HEALTH CENTERS

Abstract Current nonpharmacological treatments are inadequate for addressing chronic pain among older adults from disadvantaged backgrounds. These treatments have been developed for affluent populations and are not implemented in underserved community health centers (CHCs) where most older adults with chronic pain seek care. We conducted 4 focus groups with 23 providers (e.g., primary care doctors, nurse practitioners, medical interpreters and support staff) and 4 focus groups with 15 English- and Spanish-speaking patients at a CHC. Our goals were to: 1) understand barriers and facilitators to sustained implementation of the GetActive+ mind-body activity program delivered by a nurse practitioner; 2) gather perceptions of program skills to facilitate cultural tailoring; and 3) gather information to support a future hybrid type 1 effectiveness implementation trial of GetActive+ versus usual care to improve pain outcomes. Qualitative analyses were conducted using a deductive-inductive approach and the Framework method. Questions were informed by Aaron’s implementation model and the Socioecological model. Results revealed multiple barriers at the individual (e.g., pain misconceptions, perceived bias, stigma, shame, treatment expectations and loneliness, language barriers, food and financial insecurity), health clinic (e.g., provider burnout, understaffed clinic, budget cuts, multiple languages) and environmental levels (e.g., lack of technology, lack of reliable transportation to clinic, billing challenges). Clinic providers felt unprepared to support older adults with chronic pain. Both patients and providers endorsed the need for, and skills of GetActive+. Nuanced differences between patient-provider and English-Spanish patients as well as modifications to the program manual, protocol, and interventionist training will be discussed.

Perceived disrespectful treatment in low-income healthcare settings through the lens of intersectionality

Race and gender differences in the quality of one’s health care encounters are widely documented, but few studies explore the multiplicative impacts of race and gender. Drawing on intersectionality frameworks, we contrast white, Black, Hispanic, Asian, and Native American men’s and women’s perceptions of disrespectful treatment from health care providers and staff (e.g., receptionists, clerks) in low-income health settings. Data are from the 2014 Health Center Patient Survey (N = 5385), a nationally representative survey of community-dwelling patients receiving care at health centers funded through Section 330 of the Public Health Service Act. Our results show race and sex differences in the study outcomes, yet weak support for intersectional effects. Asian and Native American patients report more disrespectful treatment from providers, relative to other ethnic groups. Women are more likely than men to report disrespectful treatment from staff. Asians also report disrespectful treatment from staff. Health care providers and staff may require training focused on the distinctive needs of Asian patients, for whom “saving face” may be a salient goal. Structural changes to reduce wait times and employ medical interpreters to ensure clear communication, and staff training focused on verbal and nonverbal communication may mitigate against actions perceived as disrespectful in low-income health settings.