Pediatric Radiologist Workforce Shortage: Action Steps to Resolve

Case competition sessions: a global education and academic engagement tool

BACKGROUND

Radiology virtual teaching sessions utilize live video conferencing to promote collaborative learning and engagement by discussing radiology cases. Because of its convenience and flexibility, this mode of education has gained popularity, particularly after the corona virus disease 2019 pandemic.

OBJECTIVE

We describe our experience in organizing a series of "Global Health Imaging Case Competitions" for trainees in low- and middle-income countries (LMICs). These competitions provide the trainees with an opportunity to present unique radiology cases, network with radiologists, learn about various radiology topics, win prizes and potentially publish their case reports in a peer-reviewed journal.

MATERIALS AND METHODS

Planning and execution of the competition involves several steps. First, trainees are invited to participate and submit abstracts discussing unique cases. The organizing committee grades these abstracts; the authors of the 20 abstracts with the highest scores are asked to submit a video presentation of their cases to be presented during the live webinar. During this webinar, presentations are displayed and graded to select winners. Additionally, the audience votes to choose a participant as the people's favorite. We have completed four cycles (Africa, Latin America and the Caribbean, Africa and the Middle East and Asia) and will continue in the same order of rotation.

RESULTS

Attendance totalled 2,510 participants from 50 countries. Pediatric cases represented the majority of cases among finalists. Feedback was positive; 26 out of 29  (90%) participants surveyed indicated that the webinar was "very good" to "excellent" with well-organized and challenging cases. Diversity of participating countries was noted. Limitations included technology barriers such as internet connectivity.

CONCLUSION

This innovative approach emphasizing audience participation engaged trainees from LMICs and fostered locoregional collegiality and mentoring.

The 2021 ACR/RBMA Workforce Survey: Practice Types, Employment Trends, and Hiring Needs

PURPOSE

The aim of this study was to analyze current radiology practice types, specific subspecialty needs, employment trends, and retirement trends.

METHODS

ACR members, nonmembers, and Radiology Business Management Association members were surveyed using predominantly structured closed-ended questions about a variety of current and recent radiology practice characteristics. Responses were group practice deduplicated and weighted.

RESULTS

Of 1,702 survey respondents, 64% were men, with a median age of 51 years. In 2021, 62% of responding practices hired radiologists, with the average practice hiring 2 radiologists and academic practices on average hiring the most (3.5). Most radiologists (87%) were hired for full-time positions, with independent practices hiring the largest proportion of part-time positions. Body and breast imagers represented the largest numbers of hired radiologists (17% each). Practices anticipated similar hiring patterns in 2022, prioritizing breast (37%) and body (35%) imaging. Of all practice types, academic groups were least likely to prioritize general radiologist hiring. A large majority (82%) of radiology practices permit remote work (teleradiology), more common at academic than other practices. Of currently employed radiologists, 16% plan to seek new employment in the next year; early-career radiologists indicated the highest likelihood (92%) and academic radiologists the lowest (66%) of remaining in the same practice for at least 5 years. A large majority of practices (80%) reported no radiologist retirements in 2021. Of those retiring, the average age was 75 years, and 66% worked full-time until retirement.

CONCLUSIONS

Radiologist recruiting remains robust. Current information on practice characteristics may help inform radiology practice leaders seeking to right-size their groups.

A "global village": promoting research and careers in the pediatric radiology community through diversity

There is a severe shortage of pediatric radiologists in the USA and across the globe due to multiple factors. These severe shortages, along with increased clinical demand, growing research costs and limited funding sources place pediatric radiologists, particularly those in academic departments, under increasing time pressure, affecting their ability to maintain research productivity. In this paper, we model a new concept that should help boost the research efforts within the pediatric radiology community, while diversifying the academic workforce through the involvement of international medical graduates (IMGs). We describe the mutual advantages this concept could have on academic pediatric radiology departments and IMGs alike, as well as pose some of the unique challenges that could impact this concept and effective strategies to ensure success.

Visa Opportunities for International Medical Graduates Applying for U.S. Academic Radiology Department Faculty Positions: A National Survey

BACKGROUND. International medical graduates (IMGs) are a source of physicians who could help alleviate radiologist workforce shortages in the United States. However, IMGs may face barriers in obtaining appropriate visas (e.g., H-1B or O-1 visas) to allow faculty employment. OBJECTIVE. The purpose of this study was to assess the policies and experiences of U.S. academic radiology departments in offering visas to IMGs applying for faculty positions. METHODS. A web-based survey on policies and experiences in offering visas to IMG faculty candidates was distributed to chairs of U.S. radiology departments with a diagnostic radiology training program recognized by the National Resident Matching Program. Individual survey questions were optional. The initial survey and subsequent reminders were sent from October 7, 2022, through November 7, 2022. RESULTS. The survey response rate was 81% (143/177). A total of 24% (28/115), 38% (44/115), 17% (20/115), and 20% (23/115) of departments offered H-1B visas to IMG faculty frequently, sometimes, rarely, and never, respectively; 3% (3/113), 27% (31/113), 22% (25/113), and 48% (54/113) of departments offered O-1 visas frequently, sometimes, rarely, and never, respectively. However, 41% (46/113) and 5% (6/113) of departments had default policies of offering H-1B and O-1 visas for IMG faculty candidates, respectively. The most common reasons given for why departments did not offer visas included, for both H-1B and O-1 visas, the time-consuming process, lack of reliability of candidates' starting time, and the expense of the visa application; for O-1 visas, the reasons given also included lack of expertise. A total of 15% (16/108) of departments set their own visa policies, 75% (81/108) followed institutional policies, and 10% (11/108) followed policies set by other entities (e.g., state government). CONCLUSION. Although to at least some extent most U.S. academic radiology departments offer H-1B and O-1 visas for IMGs seeking faculty positions, use of such visas typically is not the departments' default policy. A variety of barriers contributed to visas not being offered. The departments' visa policies were primarily determined at the institutional level. CLINICAL IMPACT. The identified barriers faced by U.S. academic radiology departments in offering visas to IMG faculty candidates impact the role of IMGs in helping to address radiologist workforce shortages.

Development and optimization of AI algorithms for wrist fracture detection in children using a freely available dataset

Introduction

In the field of pediatric trauma computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems have emerged offering a promising avenue for improved patient care. Especially children with wrist fractures may benefit from machine learning (ML) solutions, since some of these lesions may be overlooked on conventional X-ray due to minimal compression without dislocation or mistaken for cartilaginous growth plates. In this article, we describe the development and optimization of AI algorithms for wrist fracture detection in children.

Methods

A team of IT-specialists, pediatric radiologists and pediatric surgeons used the freely available GRAZPEDWRI-DX dataset containing annotated pediatric trauma wrist radiographs of 6,091 patients, a total number of 10,643 studies (20,327 images). First, a basic object detection model, a You Only Look Once object detector of the seventh generation (YOLOv7) was trained and tested on these data. Then, team decisions were taken to adjust data preparation, image sizes used for training and testing, and configuration of the detection model. Furthermore, we investigated each of these models using an Explainable Artificial Intelligence (XAI) method called Gradient Class Activation Mapping (Grad-CAM). This method visualizes where a model directs its attention to before classifying and regressing a certain class through saliency maps.

Results

Mean average precision (mAP) improved when applying optimizations pre-processing the dataset images (maximum increases of + 25.51% mAP@0.5 and + 39.78% mAP@[0.5:0.95]), as well as the object detection model itself (maximum increases of + 13.36% mAP@0.5 and + 27.01% mAP@[0.5:0.95]). Generally, when analyzing the resulting models using XAI methods, higher scoring model variations in terms of mAP paid more attention to broader regions of the image, prioritizing detection accuracy over precision compared to the less accurate models.

Discussion

This paper supports the implementation of ML solutions for pediatric trauma care. Optimization of a large X-ray dataset and the YOLOv7 model improve the model's ability to detect objects and provide valid diagnostic support to health care specialists. Such optimization protocols must be understood and advocated, before comparing ML performances against health care specialists.

Professional practice and awareness of child abuse among radiologists and radiologic technologists: results from Saudi Arabia

BACKGROUND

The knowledge, awareness and professionalism of health care providers in the field of child protection are crucial in identifying and reporting suspected child abuse. Radiologic technologists and radiologists play a vital role in the diagnosis of suspected physical child abuse.

OBJECTIVE

To assess current practice, knowledge and awareness of child abuse among radiologic technologists and radiologists in Saudi Arabia.

MATERIALS AND METHODS

We distributed an internet-based questionnaire to radiologic technologists and radiologists working in Saudi Arabia via national radiology societies and social media channels over a 6-week period (27 October to 8 December 2021). Survey questions covered knowledge regarding child abuse, professional practice in radiology departments in Saudi Arabia in cases of suspected physical abuse (SPA), and knowledge of the national legislation and reporting and acting procedures in child abuse.

RESULTS

A total of 315 respondents (224 radiologic technologists and 91 radiologists) participated in this study. The median score for knowledge of abuse was higher amongst radiologists (4.8) than radiologic technologists (4.0); P < 0.001. In total, 210 (93.8%) radiologic technologists and 61 (67.0%) radiologists reported that there was no protocol (i.e. skeletal survey) at their hospital for imaging children with SPA. Most radiologic technologists had no training in paediatric radiology (165/224, 73.7%) and most radiologists had received no training in evaluating imaging performed for SPA (73/91, 80.2%). More than half of respondents - 131 (58.5%) radiologic technologists and 44 (48.4%) radiologists - were not familiar with the reporting and acting procedures at their hospitals in cases of child abuse.

CONCLUSION

Although radiologic technologists and radiologists in Saudi Arabia have good knowledge and awareness of child abuse in general, they lack specific knowledge of the reporting and acting procedures at their hospitals in cases of suspected child abuse. National imaging guidelines and training courses are needed to develop appropriate skills in the recognition, imaging and reporting of SPA in infants and young children in Saudi Arabia.

Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists

BACKGROUND

As the number of conventional radiographic examinations in pediatric emergency departments increases, so, too, does the number of reading errors by radiologists.

OBJECTIVE

The aim of this study is to investigate the ability of artificial intelligence (AI) to improve the detection of fractures by radiologists in children and young adults.

MATERIALS AND METHODS

A cohort of 300 anonymized radiographs performed for the detection of appendicular fractures in patients ages 2 to 21 years was collected retrospectively. The ground truth for each examination was established after an independent review by two radiologists with expertise in musculoskeletal imaging. Discrepancies were resolved by consensus with a third radiologist. Half of the 300 examinations showed at least 1 fracture. Radiographs were read by three senior pediatric radiologists and five radiology residents in the usual manner and then read again immediately after with the help of AI.

RESULTS

The mean sensitivity for all groups was 73.3% (110/150) without AI; it increased significantly by almost 10% (P<0.001) to 82.8% (125/150) with AI. For junior radiologists, it increased by 10.3% (P<0.001) and for senior radiologists by 8.2% (P=0.08). On average, there was no significant change in specificity (from 89.6% to 90.3% [+0.7%, P=0.28]); for junior radiologists, specificity increased from 86.2% to 87.6% (+1.4%, P=0.42) and for senior radiologists, it decreased from 95.1% to 94.9% (-0.2%, P=0.23). The stand-alone sensitivity and specificity of the AI were, respectively, 91% and 90%.

CONCLUSION

With the help of AI, sensitivity increased by an average of 10% without significantly decreasing specificity in fracture detection in a predominantly pediatric population.

Quality Assurance of a Cross-Border and Sub-Specialized Teleradiology Service

BACKGROUND

The current literature discusses aspects of quality assurance (QA) and sub-specialization. However, the challenges of these topics in a teleradiology network have been less explored. In a project report, we aimed to review the development and enforcement of sub-specialized radiology at Telemedicine Clinic (TMC), one of the largest teleradiology providers in Europe, and to describe each step of its QA.

EVALUATION

The company-specific background was provided by the co-authors-current and former staff members of TMC. Detailed descriptions of the structures of sub-specialization and QA at TMC are provided. Exemplary quantitative evaluation of caseloads and disagreement rates of secondary reviews are illustrated. Description of Sub-specialization and Quality Assurance at TMC: Sub-specialization at TMC is divided into musculoskeletal radiology, neuroradiology, head and neck, a body, and an emergency section operating at local daytime in Europe and Australia. Quality assurance is based on a strict selection process of radiologists, specific reporting guidelines, feedback through the secondary reading of 100% of all radiology reports for new starters, and a minimum of 5% of radiology reports on a continuous basis for all other radiologists, knowledge sharing activities and ongoing training. The level of sub-specialization of each radiologist is monitored continuously on an individual basis in detail. After prospective secondary readings, the mean disagreement rate at TMC indicating at least possibly clinically relevant findings was 4% in 2021.

CONCLUSION

With continuing and current developments in radiology in mind, the essential features of sub-specialization and innovative QA are relevant for further expansion of teleradiology services and for most radiology departments worldwide to respond to the increasing demand for value-based radiology.