Background: Glomerular filtration rate (GFR) decreases in the aging human kidney, but limited data exist in dogs. Hypothesis: There is an effect of age and body size on estimated GFR in healthy dogs. Animals: One hundred and eighteen healthy dogs of various breeds, ages, and body weights presenting to 3 referral centers. Methods: GFR was estimated in clinically healthy dogs between 1 and 14 years of age. GFR was estimated from the plasma clearance of iohexol, by a compartmental model and an empirical correction formula, normalized to body weight in kilograms or liters of extracellular fluid volume (ECFV). For data analysis, dogs were divided into body weight quartiles 1.8-12.4, 13.2-25.5, 25.7-31.6, and 32.0-70.3 kg.Results: In the complete data set, there was no trend toward lower estimated GFR/kg or GFR/ECFV with increasing age. GFR decreased with age in dogs in the smallest weight quartile only. A significant negative linear relationship was detected between body weight and estimated GFR/kg and GFR/ECFV. Reference ranges in different weight quartiles were 1.54-4.25, 1.29-3.50, 0.95-3.36, and 1.12-3.39 mL/min/kg, respectively. Standardization to ECFV rather than kilogram body weight did not produce substantial changes in the relationships between GFR estimates and age or weight.Conclusions and Clinical Importance: Interpretation of GFR results for early diagnosis of renal failure should take into account the weight and the age of the patient for small dogs.

The derived feline correction formula applied to slope-intercept plasma iohexol clearance accurately predicted multisample clearance in cats. Use of this technique offers an important advantage by reducing stress to cats associated with repeated blood sample collection and decreasing the costs of analysis.

Reference ranges for estimated GFR via plasma clearance of iohexol and creatinine should facilitate early detection of impaired renal function in cats, although body weight should be taken into account.

OBJECTIVES/GOALS: Can we detect Parkinson’s-disease-related motor impairments using computer vision and machine learning? METHODS/STUDY POPULATION: A sample of 29 people with Parkinson’s disease (PD) and 29 non-Parkinson’s disease (non-PD) controls were recruited from the University of Iowa Movement Disorders Clinic. Videos of 3 motor assessment tasks performed using the hands were recorded and hand location information was abstracted using the computer vision program MediaPipe. Measures from the raw data series and FFT were used as features to train a model using boosted trees to classify each video as PD or non-PD. Model performance was evaluated using leave-one-out cross-validation. Additionally, we used recursive feature elimination to reduce model complexity. RESULTS/ANTICIPATED RESULTS: A model using two features identified by recursive feature elimination yielded a model with an overall accuracy of 81% in cross-validation. In our sample, the model had 86.2% sensitivity, 75.9% specificity, and an AUC of 0.839. Additional improvement may be possible with more data processing, especially in the time-domain. DISCUSSION/SIGNIFICANCE: We built a classifier that was able to reliably and accurately discriminate between videos of motor assessments in people with Parkinson’s and people without. This may provide a low cost screening tool in rural areas or primary care clinics with limited access to neurologist expertise.