Fiona Stanley Hospital

Artificial intelligence (AI) is increasingly embedded in radiology research and practice, yet concerns about the reproducibility of AI studies remain a key barrier to regulatory acceptance and clinical translation. Transparent reporting across the analytic pipeline is essential for independent verification, evidence synthesis, and safe implementation. To examine major barriers to transparent reporting in radiological AI research and propose practical solutions to strengthen reproducibility. We identify four interrelated challenges undermining reporting quality. First, reporting is often treated as a final-stage manuscript requirement rather than a prospectively embedded component of study design, leading to loss of methodological detail. Second, inconsistent operationalization of reporting standards by journals and funders makes it difficult to assess reporting completeness. Third, fragmentation and overlapping complexity of AI-specific reporting guidelines increase interpretive burden for authors and reviews and contribute to heterogeneity in reporting. Fourth, limited availability and usability of data and code restrict independent verification, even when resources are nominally shared. These issues are amplified by the methodological complexity and heterogeneity of radiological AI pipelines. For each challenge, we outline actionable strategies including prospective documentation of methods, mandatory and consistently applied reporting standards, harmonized reporting principles, and clearer requirements for data and code availability with structured alternatives when sharing is constrained. Strengthening transparent reporting is a prerequisite for reproducible and clinically translatable radiological AI research. Embedding reporting within study design, aligning stakeholder expectations, and improving access to reproducibility-enabling resources are essential to enhance credibility, facilitate independent evaluation, and support safe clinical implementation of AI in radiology.

Knee osteoarthritis (OA) is disabling, with few effective treatments. Anti-inflammatory treatments may be effective for patients with an inflammatory phenotype. To evaluate the efficacy of the interleukin-1β blocker diacerein, compared with placebo, on knee pain in people with knee OA who have substantial knee pain and inflammation (effusion-synovitis on magnetic resonance imaging). This multicenter, randomized, double-blind, placebo-controlled clinical trial was conducted in 4 Australian centers. Participants with clinical knee OA, substantial knee pain, and effusion-synovitis on magnetic resonance imaging were enrolled from June 2019 to September 2022. Final follow-up occurred on February 6, 2023. Data analysis began on July 7, 2023. Participants were randomized (1:1) to diacerein, 50 mg, once daily or identical placebo for the first 2 weeks, which increased to 50 mg, twice daily until 24 weeks if adverse effects were tolerable. The primary outcome was change in knee pain as assessed by the visual analogue scale (range, 0-100 mm; minimal clinically important improvement, 15) over 24 weeks. Of 262 participants randomized (mean [SD] age, 54.9 [6.1] years; 147 [56.1%] female and 115 [43.9%] male), 231 (88.2%) completed the trial. Compared with placebo, diacerein did not improve knee pain over 24 weeks (-19.9 mm [diacerein] vs -18.6 mm [placebo]; between-group mean difference, -1.3 mm; 95% CI, -9.8 to 7.3). The most common adverse events were gastrointestinal symptoms, which occurred in 55 participants (41.7%) in the diacerein group and 33 (25.4%) in the placebo group, most commonly diarrhea (51 [38.6%] in the diacerein group vs 29 [22.3%] in the placebo group). Change in urine color was observed among 13 participants (9.8%) who received diacerein. This randomized clinical trial found that, in patients with symptomatic knee OA and effusion-synovitis, diacerein (50 mg, twice daily) over 24 weeks resulted in no greater improvement in knee pain compared with placebo. These findings do not support diacerein for treating knee pain in this population. Australian New Zealand Clinical Trials Registry: ACTRN12618001656224.

A descriptive quantitative study. To determine how much and what type of exercises and training were provided as part of usual physiotherapy and occupational therapy to participants of the SCI-MT Trial (the Early and Intensive Motor Training for People with Spinal Cord Injuries Trial). This information is important because the SCI-MT Trial concluded that additional motor training is redundant if people with SCI receive equivalent usual care as what was provided to participants of the SCI-MT Trial. Fifteen spinal injury units across Europe and Australia. Data were collected on the time participants of both groups of the SCI-MT Trial (n = 220) attended physiotherapy and occupational therapy provided as part of usual care over the 10-week intervention period. The International Spinal Cord Injury Physical Therapy and Occupational Therapy Basic Data Set was used to capture time spent on activity and impairment directed categories of exercises and training. Participants attended a median (interquartile range) of 8.3 (6.2 to 11.4) hours of physiotherapy and occupational therapy per week. Approximately 70% of therapy time was spent actively exercising or training with a median of 3.8 h per week spent on activity-directedand 1.9 h per week spent on impairment-directedexercises and training. The results of this study detail the amount and type of physiotherapy and occupational therapy that needs to be provided as part of usual rehabilitation care to render additional motor training redundant.

The predictive value of PromarkerD tests for incident diabetic kidney disease or rapid decline in estimated glomerular filtration rate was evaluated in 1010 non-Aboriginal and 71 Aboriginal adults with diabetes. Areas under the receiver operating characteristic curves were not significantly different (P ≥ 0.081) for first- (non-Aboriginals 0.890 (95% confidence interval 0.864 to 0.915) and Aboriginals 0.769 (0.624 to 0.915)) and second-generation (0.890 (0.862 to 0.917) and 0.711 (0.543 to 0.878)) tests. PromarkerD has potential renal prognostic value in Aboriginals with diabetes.

To describe 5-year outcomes of chronic kidney disease (CKD) in a large, population-based cohort in Western Australia, including rates of progression, regression, kidney failure and death. CKD is a major public health challenge associated with increased morbidity and mortality, yet the natural history of early-stage disease in population settings remains poorly defined. We conducted a retrospective cohort study using linked pathology and hospital data for adults with incident CKD between 2006 and 2022. CKD stage was defined by two estimated glomerular filtration rate (eGFR) values ≥ 3 and < 12 months apart: mild (45-59), moderate (30-44) and severe (15-29) mL/min/1.73 m2. Outcomes were assessed over 5 years using a competing risks framework. Among 153 527 individuals with incident CKD during the study period (mean age 75.6 years, 52.6% women) 118 248 had mild, 58 323 moderate and 20 322 severe CKD. At 5 years, death occurred in 16.8% (mild), 26.7% (moderate) and 30.5% (severe); kidney failure occurred in 0.6%, 2.5% and 30.0%, respectively. CKD progression was more common than regression in mild (20.1% vs. 11.8%) and moderate (18.9% vs. 14.5%) disease. Albuminuria testing was recorded in < 35% of patients. People with early-stage CKD face substantial risks of progression, kidney failure and death within 5 years. The low rate of albuminuria testing suggests missed opportunities for early identification of high-risk individuals and timely intervention. Enhancing CKD detection and monitoring in primary care may improve outcomes.

Immune checkpoint inhibitor immunotherapy enhances T cell activity against cancer cells but often leads to the immune system targeting healthy cells, causing 'immune-related adverse events' (irAEs). We report the case of a man in his 70s with metastatic melanoma being treated with ipilimumab and nivolumab. He presented with febrile neutropenia after lacerating a thumb on his compost bin. The neutrophil count only recovered once oral prednisolone was commenced, indicating a haematological irAE. A restaging Positron Emission Tomography scan revealed intramuscular ring-enhancing collections throughout his body, one of which was aspirated and cultured the fungus Lomentospora prolificans He was treated with voriconazole plus terbinafine, both of which were later substituted with olorofim due to a voriconazole-induced rash. After 4 months, the collections had resolved on repeat imaging, and olorofim was ceased due to transaminitis. This case highlights neutropenia as a lesser-known adverse effect of immunotherapy and raises awareness about L. prolificans infection.

Abdominal pain is a common pediatric presentation in the emergency department (ED), and acute appendicitis (AA) is the most common surgical diagnosis. This study describes the management of suspected AA in a tertiary Australian pediatric ED. A single-center prospective observational study was performed between November 2022 and May 2023. Children aged 5 to 15 years presenting to the ED with acute abdominal pain and clinician suspicion of AA were included. Clinical gestalt was measured using a 5-point Likert Scale before and after blood tests. Diagnosis of AA was confirmed on histopathology, and non-AA was confirmed with follow-up at 30 to 60 days. The study enrolled 481 children; AA was diagnosed in 146 (30.6%). Patients with AA were older (11.1 vs. 10.0y) and more likely to be male (69.2% vs. 48.1%) compared with those without AA. Blood tests were performed in 449 (93.3%) children, with higher rates in AA cases (100% vs. 90.4%). Gestalt improved with blood test results, with overall diagnostic accuracy increasing from 65.9% pre-blood tests to 88.5% post-blood tests. Ultrasound (US) was performed in 361 (75.1%) children with a diagnostic accuracy of 90.6% and was frequently used even in patients deemed low-risk post-blood tests (65.7%). One hundred and fifty (31.2%) of suspected AA cases underwent surgery, with 3 negative appendectomies and 1 ovarian cystectomy without appendectomy. Median (IQR) hospital length of stay was significantly longer for AA cases than non-AA cases [50.8 (35.3 to 95.0) h vs. 7.1 (4.6 to 16.8) h]. This study reviews the management and outcomes of suspected AA in a high-volume Australian ED. It shows the importance of blood tests in improving diagnostic accuracy of clinician gestalt and highlights the potential overuse of US in low-risk patients. Future research should explore a more structured diagnostic approach to increase diagnostic accuracy, optimize resource utilization, and improve patient outcomes.