ACR  LAB Urine Analysis Test System

The ACR | LAB Urine Analysis Test System is an in-vitro diagnostic device designed for healthcare professionals to semi-quantitatively measure urinary albumin and creatinine, and their ratio, at the point of care to aid in assessing kidney function. It operates using a smartphone application, a proprietary Color-Board, and reagent strips, employing reflectance photometry and backend image recognition algorithms for analysis, with performance comparable to established laboratory analyzers.

The ACR | LAB Urine Analysis Test System by Healthy.io Ltd. is an in-vitro diagnostic tool intended for use by healthcare professionals in point-of-care settings. Its primary function is the semi-quantitative detection of albumin and creatinine in urine samples, and the subsequent calculation and presentation of their ratio, which serves as an aid in diagnosing kidney function. The system integrates a smartphone application (specifically for iPhone 7 with iOS 12), a proprietary Color-Board, and commercially available ACR Reagent Strips (ACON Laboratories Inc. Mission Urinalysis Reagent Strips). The scientific methodology employed is reflectance photometry. The smartphone app guides the user through the testing process, captures an image of the reagent strip placed on the Color-Board, conducts initial boundary condition analyses on the scan, and then transmits the data to a secure, cloud-based backend server. This backend server utilizes an image recognition algorithm to perform a complete analysis of the strip's color changes, determine the analyte concentrations, and then securely forwards these results to a patient's Electronic Medical Record for professional review. Performance evaluations of the ACR | LAB system included extensive analytical and clinical studies. Analytical testing demonstrated high precision, with repeatability studies showing 100% exact matches and reproducibility studies yielding 99.8% exact matches. Linearity for both albumin and creatinine detection was confirmed across the measurable range, and limits of detection were established. Interference studies identified substances that could affect test accuracy, with these details included in the user manual. Timing flexibility studies underscored the importance of adherence to procedural steps: for instance, a 60-second delay in blotting albumin strips led to false positives, and 5-10 second dipping times for albumin also increased false positive rates, leading to specific user instructions. Clinical method comparison studies, involving 375 native and 60 contrived urine samples across three U.S. clinical sites, compared the ACR | LAB system to the ACON Laboratories’ Mission U120 Ultra Urine Analyzer. These studies showed overall exact match agreement rates of 89% for albumin, 84% for creatinine, and 93% for the albumin-creatinine ratio. Furthermore, the agreement within ±1 color block was 100% for albumin, creatinine, and their ratio when compared to the predicate device.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. What specific interfering substances were identified, and at what concentrations do they impact albumin and creatinine readings using the ACR
• Q2. LAB system?; How does the backend image recognition algorithm account for potential variations in ambient lighting or smartphone camera quality beyond the specified iPhone 7 with iOS 12?; What were the specific concentration ranges for albumin and creatinine that corresponded to each color block, particularly around the established cut-off values from the Limit of Detection studies?; Given the 84-89% exact match for individual analytes (albumin, creatinine) compared to the predicate, what is the potential clinical impact of these discrepancies on kidney function assessment, especially in borderline cases?; What are the specific parameters and thresholds used in the 'boundary condition analyses' performed by the smartphone app to ensure scan quality before data transmission to the backend?