Proximal fibular physeal stress injury: a known entity in an unusual location.

In the skeletally immature patient, physeal stress injury is a common diagnosis in repetitive stress injury; in this case, we present an atypical location of physeal stress injury of the bilateral proximal fibulae. There are multiple well-documented diagnoses of physeal stress injury involving the shoulder, elbow, wrist and tibia, often considered when patients present with the typical history of intensive sports training and pain exacerbated by repetitive movements. However, isolated proximal fibular physeal stress injury is either unusual or under-recognized and underreported. Although less common, proximal fibular physeal stress injury should be among the diagnostic considerations in active adolescents complaining of lower extremity pain as failure to identify this entity can lead to delayed care and preventable potential long-term musculoskeletal effects.

A "Bumper-Car" Curriculum for Teaching Deep Learning to Radiology Residents☆.

RATIONALE AND OBJECTIVES: Our goal was to create an artificial intelligence (AI) training curriculum for residents that taught them to create, train, evaluate and refine deep learning (DL) models. Hands-on training of models was emphasized and didactic presentations of the mathematical and programmatic underpinnings of DL were minimized. MATERIALS AND METHODS: We created a three-session, 6-hour curriculum based on a "no-code" machine learning system called Lobe.ai. This class met weekly in June 2021. Pre-class homework included reading assignments, software installation, dataset downloads, and image-collection and labeling. The class sessions included several short, didactic presentations, but were largely devoted to hands-on training of DL models. After the course, our residents completed a short, anonymous, online survey about the course. RESULTS: Our residents learned to acquire and label a wide variety of image datasets. They quickly learned to train DL models to classify these datasets, as well as how to evaluate and refine these models. Our survey showed that most residents felt AI to be important and worth learning, but most were not very interested in learning to program. Most felt that the course taught them useful things about DL, and they were now more interested in the topic. Most would recommend the course to other residents, as well as to medical students and to radiology faculty. CONCLUSION: The course met our objectives of teaching our residents to create, train, evaluate, and refine DL models. We hope that the hands-on experience they gained in this course will enable them to recognize problems in diagnostic AI systems, and to help solve such problems in their own radiology practices.

Is There a Difference Between LI-RADS 3 to LI-RADS 5 Progression Assessment Using CT Versus MR? A Retrospective, Single-Center, Longitudinal Study of Patients Who Underwent 5082 Radiologic Examinations for Surveillance of Hepatocellular Carcinoma Over a 43-Month Period.

OBJECTIVE: The Liver Imaging Reporting and Data System (LI-RADS) has been widely applied to CT and MR liver observations in patients at high-risk for hepatocellular carcinoma (HCC). We investigated the impact of CT vs MR in upgrading LI-RADS 3 to LI-RADS 5 observations using a large cohort of high-risk patients. METHODS: We performed a retrospective, longitudinal study of CT and MR radiographic reports (June 2013 - February 2017) with an assigned LI-RADS category. A final population of 757 individual scans and 212 high-risk patients had at least one LI-RADS 3 observation. Differences in observation time to progression between modalities were determined using uni- and multivariable analysis. RESULTS: Of the 212 patients with a LI-RADS 3 observation, 52 (25%) had progression to LI-RADS 5. Tp ranged from 64 - 818 days (median: 196 days). One hundred and three patients (49%) had MR and 109 patients (51%) had CT as their index study. Twenty-four patients with an MR index exam progressed to LI-RADS 5 during the follow-up interval, with progression rates of 22% (CI:13%-30%) at 1 year and 29% (CI:17%-40%) at 2 years. Twenty-eight patients with a CT index exam progressed to LI-RADS 5 during follow-up, with progression rates of 26% (CI:16%-35%) at 1 year and 31% (CI:19%-41%) at 2 years. Progression rates were not significantly different between patients whose LI-RADS 3 observation was initially diagnosed on MR vs CT (HR: 0.81, P = 0.44). DISCUSSION: MR and CT modalities are comparable for demonstrating progression from LI-RADS 3 to 5 for high risk patients.

Post discharge issues identified by a call-back program: identifying improvement opportunities.

OBJECTIVES: The period following discharge from the hospital is one of heightened vulnerability. Discharge instructions serve as a guide during this transition. Yet, clinicians receive little feedback on the quality of this document that ties into the patients' experience. We reviewed the issues voiced by discharged patients via a call-back program and compared them to the discharge instructions they had received. METHODS: At our institution, patients receive an automated call forty-eight hours following discharge inquiring about progress. If indicated by the response to the call, they are directed to a nurse who assists with problem solving. We reviewed the nursing documentation of these encounters for a period of nine months. The issues voiced were grouped into five categories: communication, medications, durable medical equipment/therapies, follow up and new or ongoing symptoms. The discharge instructions given to each patient were reviewed. We retrieved data on the number of discharges from each specialty from the hospital over the same period. RESULTS: A total of 592 patients voiced 685 issues. The numbers of patients discharged from medical or surgical services identified as having issues via the call-back line paralleled the proportions discharged from medical and surgical services from the hospital during the same period. Nearly a quarter of the issues discussed had been addressed in the discharge instructions. The most common category of issues was related to communication deficits including missing or incomplete information which made it difficult for the patient to enact or understand the plan of care. Medication prescription related issues were the next most common. Resource barriers and questions surrounding medications were often unaddressed. CONCLUSIONS: Post discharge issues affect patients discharged from all services equally. Data from call back programs may provide actionable targets for improvement, identify the inpatient team's 'blind spots' and be used to provide feedback to clinicians.