Wrist trauma is common in children, typically requiring radiography for diagnosis and treatment planning. However, many children do not have fractures and are unnecessarily exposed to radiation. Ultrasound performed at bedside could detect fractures prior to radiography. Modern tools including three-dimensional ultrasound (3DUS) and artificial intelligence (AI) have not yet been applied to this task. Our purpose was to assess (1) feasibility, reliability, and accuracy of 3DUS for detection of pediatric wrist fractures, and (2) accuracy of automated fracture detection via AI from 3DUS sweeps. Children presenting to an emergency department with unilateral upper extremity injury to the wrist region were scanned on both the affected and unaffected limb. Radiographs of the symptomatic limb were obtained for comparison. Ultrasound scans were read by three individuals to determine reliability. An AI network was trained and compared against the human readers. Thirty participants were enrolled, resulting in scans from fifty-five wrists. Readers had a combined sensitivity of 1.00 and specificity of 0.90 for fractures. AI interpretation was indistinguishable from human interpretation, with all fractures detected in the test set of 36 images (sensitivity = 1.0). The high sensitivity of 3D ultrasound and automated AI ultrasound interpretation suggests that ultrasound could potentially rule out fractures in the emergency department.

genitourinary, 4.9% small-cell lung (SCLC), and 3.3% other. Overall median survival after palliative RT was 5.74 months. Patients receiving lower dose per fraction (2Gy/Fx) were more likely to be younger and healthier, yet experienced worse palliative outcomes with higher median PRLSRT, rates of incompletion, and deaths on treatment (Table 1). Breast and prostate were most likely to complete RT (89.1% and 89.6%), while GI NOS and SCLC were least likely (77.6% and 78.6%) (P < 0.001). Upper GI patients were most likely to die on treatment (1.3%), while prostate patients were the least (0.2%) (P < 0.001). PRLSRT ≥50% was observed more frequently in GI NOS (16.6%), upper GI (10.4), NSCLC (10.3%), and skin (9.8%) compared to prostate (2.4%) and breast (2.7%) (P < 0.001). Logistic regression indicated age, race, insurance status, Charlson-Deyo score, primary site, metastatic involvement, bone RT site, and Gy/Fx were significant factors affecting completion rates of RT. Median PRLSRTs were: 14.89% GI NOS, 9.90% upper GI, 9.49% NSCLC, 7.89% skin, 7.18% SCLC, 6.12% lower GI, 5.64% GYN, 5.42% GU, 5.24% HNC, 2.05% prostate, and 2.02% endocrine, and 1.84% breast (P < 0.001). Those receiving 3Gy/Fx and 2Gy/Fx were less likely to complete RT when compared to 4Gy/Fx, with odds ratios of 1.209 and 15.023 respectively (P < 0.001). Patients with SCLC were least likely to complete RT, with a 1.694 odds ratio compared to breast (P < 0.001). Conclusion: For palliative RT for osseous metastases, dose per fraction and primary cancer impact the palliative outcomes of PRSLRT, the likelihood of completing RT, and death during treatment and should be considered to minimize the burden of care and maximize benefits of treatment.

Background Several studies within the psychiatry literature have illustrated the importance of discharge planning and execution, as well as accessibility of outpatient follow-up post-discharge. We report the results of implementing a new seamless care transition policy to expedite post-discharge follow-up in the community Addiction and Mental Health (AMH) program in the Edmonton Zone, Alberta, Canada. The policy involved a distribution mechanism for assessment by a Mental Health Therapist (MHT) within 7 days of discharge as well as a dedicated roster of community psychiatrists to accept newly discharged patients. Methods Our study involved a retrospective clinical audit with total sampling design and a comparison of data one year prior to (2015/2016 fiscal year) and one year after (2017/2018 fiscal year) the implementation of the seamless care policy within the Edmonton zone. Extracted data was analyzed with simple descriptive statistics and presented as percentages, mean and median. Results Overall, with the enactment of this policy, follow-up volumes ultimately increased, whilst wait times for initial assessment decreased on average for patients discharged from hospital. In the 2015/2016 fiscal year, MHT completed 128 assessments of post-discharge patients who were new to AMH community compared to 298 completed new assessments for the 2017/2018 fiscal year. The corresponding wait times for the new MHT assessments were 12.7 days (median of 12 days) and 7.8 days (median of 6 days), respectively. Similarly, psychiatrists completed only 59 assessments of post-discharge patients who were new to the AMH community compared to 133 new psychiatric assessments for the 2017/2018 fiscal year. The corresponding wait times for the new psychiatric assessments were 15.3 days (median of 14 days) and 8.8 days (median of 7 days), respectively. We correspondingly found a slight decline in readmission rates after the implementation of our model in the subsequent fiscal year. Conclusion We envision that this policy will set a precedent with regards to streamlining post-discharge follow-up care for admitted inpatients, ultimately improving mental health outcomes for patients.