Low birth weight is associated with impaired murine kidney development and function.

BackgroundLow birth weight (LBW) neonates have impaired kidney development that leaves them susceptible to kidney disease and hypertension during adulthood. The study here identifies events that blunt nephrogenesis and kidney development in the murine LBW neonate.MethodsWe examined survival, kidney development, GFR, gene expression, and cyto-/chemokines in the LBW offspring of malnourished (caloric and protein-restricted) pregnant mice.ResultsMalnourished pregnant mothers gave birth to LBW neonates that had 40% reduced body weight and 54% decreased survival. Renal blood perfusion was reduced by 37%, whereas kidney volume and GFR were diminished in the LBW neonate. During gestation, the LBW neonatal kidney had 2.2-fold increased apoptosis, 76% decreased SIX2+ progenitor cells, downregulation of mesenchymal-to-epithelial signaling factors Wnt9b and Fgf8, 64% less renal vesicle formation, and 32% fewer nephrons than controls. At birth, increased plasma levels of IL-1ß, IL-6, IL-12(p70), and granulocyte-macrophage colony-stimulating factor in the LBW neonate reduced SIX2+ progenitor cells.ConclusionIncreased pro-inflammatory cytokines in the LBW neonate decrease SIX2+ stem cells in the developing kidney. Reduced renal stem cells (along with the decreased mesenchymal-to-epithelial signaling) blunt renal vesicle generation, nephron formation, and kidney development. Subsequently, the mouse LBW neonate has reduced glomeruli volume, renal perfusion, and GFR.

Prevention of Chemotherapy Induced Cardiomyopathy.

PURPOSE OF REVIEW: Cardiomyopathy is a significant complication of various cancer treatments and has been best studied in patients receiving anthracyclines and trastuzumab. This paper evaluates strategies to prevent chemotherapy-induced cardiotoxicity. RECENT FINDINGS: Increasing cumulative anthracycline dose, use of ≥2 cardiotoxic therapies, extremes of age, and pre-existing cardiovascular risk factors, or established cardiovascular disease, heighten the risk of developing chemotherapy-induced cardiomyopathy. Continuous rather than bolus anthracycline infusions, liposomal doxorubicin, or concomitant dexrazoxane reduces chemotherapy-induced cardiotoxicity. Treatment with neurohormonal antagonists or statins and exercise training during chemotherapy are promising, but as yet unproven, cardioprotective strategies. Identification of high-risk patients and optimization of their underlying cardiovascular risk factors/disease are essential to prevent cardiotoxicity. In patients requiring high-dose anthracyclines, continuous infusions, liposomal doxorubicin, or dexrazoxane should be considered to mitigate cardiotoxicity. Current data do not support the routine use of neurohormonal antagonists or statins as cardioprotective agents in patients treated with cardiotoxic chemotherapies.

Automated Detection of Cervical Spinal Stenosis and Cord Compression via Vision Transformer and Rules-Based Classification.

BACKGROUND AND PURPOSE: Cervical spinal cord compression, defined as spinal cord deformity and severe narrowing of the spinal canal in the cervical region, can lead to severe clinical consequences, including intractable pain, sensory disturbance, paralysis, and even death, and may require emergent intervention to prevent negative outcomes. Despite the critical nature of cord compression, no automated tool is available to alert clinical radiologists to the presence of such findings. This study aims to demonstrate the ability of a vision transformer (ViT) model for the accurate detection of cervical cord compression. MATERIALS AND METHODS: A clinically diverse cohort of 142 cervical spine MRIs was identified, 34% of which were normal or had mild stenosis, 31% with moderate stenosis, and 35% with cord compression. Utilizing gradient-echo images, slices were labeled as no cord compression/mild stenosis, moderate stenosis, or severe stenosis/cord compression. Segmentation of the spinal canal was performed and confirmed by neuroradiology faculty. A pretrained ViT model was fine-tuned to predict section-level severity by using a train:validation:test split of 60:20:20. Each examination was assigned an overall severity based on the highest level of section severity, with an examination labeled as positive for cord compression if ≥1 section was predicted in the severe category. Additionally, 2 convolutional neural network (CNN) models (ResNet50, DenseNet121) were tested in the same manner. RESULTS: The ViT model outperformed both CNN models at the section level, achieving section-level accuracy of 82%, compared with 72% and 78% for ResNet and DenseNet121, respectively. ViT patient-level classification achieved accuracy of 93%, sensitivity of 0.90, positive predictive value of 0.90, specificity of 0.95, and negative predictive value of 0.95. Receiver operating characteristic area under the curve was greater for ViT than either CNN. CONCLUSIONS: This classification approach using a ViT model and rules-based classification accurately detects the presence of cervical spinal cord compression at the patient level. In this study, the ViT model outperformed both conventional CNN approaches at the section and patient levels. If implemented into the clinical setting, such a tool may streamline neuroradiology workflow, improving efficiency and consistency.

Performance of GPT-4 on the American College of Radiology In-training Examination: Evaluating Accuracy, Model Drift, and Fine-tuning.

RATIONALE AND OBJECTIVES: In our study, we evaluate GPT-4's performance on the American College of Radiology (ACR) 2022 Diagnostic Radiology In-Training Examination (DXIT). We perform multiple experiments across time points to assess for model drift, as well as after fine-tuning to assess for differences in accuracy. MATERIALS AND METHODS: Questions were sequentially input into GPT-4 with a standardized prompt. Each answer was recorded and overall accuracy was calculated, as was logic-adjusted accuracy, and accuracy on image-based questions. This experiment was repeated several months later to assess for model drift, then again after the performance of fine-tuning to assess for changes in GPT's performance. RESULTS: GPT-4 achieved 58.5% overall accuracy, lower than the PGY-3 average (61.9%) but higher than the PGY-2 average (52.8%). Adjusted accuracy was 52.8%. GPT-4 showed significantly higher (p = 0.012) confidence for correct answers (87.1%) compared to incorrect (84.0%). Performance on image-based questions was significantly poorer (p < 0.001) at 45.4% compared to text-only questions (80.0%), with adjusted accuracy for image-based questions of 36.4%. When the questions were repeated, GPT-4 chose a different answer 25.5% of the time and there was no change in accuracy. Fine-tuning did not improve accuracy. CONCLUSION: GPT-4 performed between PGY-2 and PGY-3 levels on the 2022 DXIT, significantly poorer on image-based questions, and with large variability in answer choices across time points. Exploratory experiments in fine-tuning did not improve performance. This study underscores the potential and risks of using minimally-prompted general AI models in interpreting radiologic images as a diagnostic tool. Implementers of general AI radiology systems should exercise caution given the possibility of spurious yet confident responses.

Association of post-diagnosis cardiorespiratory fitness with cause-specific mortality in cancer.

AIMS: The prognostic importance of post-diagnosis assessment of cardiorespiratory fitness (CRF) in cancer patients is not well established. We sought to examine the association between CRF and mortality in cancer patients. METHODS AND RESULTS: This was a single-centre cohort analysis of 1632 patients (58% male; 64 ± 12 years) with adult-onset cancer who were clinically referred for exercise treadmill testing a median of 7 [interquartile range (IQR): 3-12] years after primary diagnosis. Cardiorespiratory fitness was defined as peak metabolic equivalents (METs) achieved during standard Bruce protocol and categorized by tertiles. The association between CRF and all-cause and cause-specific mortality was assessed using multivariable Cox proportional hazard models adjusting for important covariates. Median follow-up was 4.6 (IQR: 2.6-7.0) years; a total of 411 deaths (229, 50, and 132 all-cause, cardiovascular (CV), and cancer related, respectively) occurred during this period. Compared with low CRF (range: 1.9-7.6 METs), the adjusted hazard ratio (HR) for all-cause mortality was 0.38 [95% confidence interval (CI): 0.28-0.52] for intermediate CRF (range: 7.7-10.6 METs) and 0.17 (95% CI: 0.11-0.27) for high CRF (range: 10.7-22.0 METs). The corresponding HRs were 0.40 (95% CI: 0.19-0.86) and 0.41 (95% CI: 0.16-1.05) for CV mortality and 0.40 (95% CI: 0.26-0.60) and 0.16 (95% CI: 0.09-0.28) for cancer mortality, respectively. The adjusted risk of all-cause, CV, and cancer mortality decreased by 26%, 14%, and 25%, respectively with each one MET increment in CRF. CONCLUSION: Cardiorespiratory fitness is a strong, independent predictor of all-cause, CV, and cancer mortality, even after adjustment for important clinical covariates in patients with certain cancers.