KidneyIntelX.dkd is for in-vitro diagnostic use for the determination of a KidneyIntelX.dkd Level using an algorithm to combine clinical variables (blood urea nitrogen (BUN), hemoglobin A 1c (HbAlc) and urine albumin creatinine ratio (uACR)) and the quantitative measurements of tumor necrosis factor receptor-1 (TNFR-1), tumor necrosis factor receptor-2 (TNFR-2) and kidney injury molecule-1 (KIM-1) in human plasma employing a Meso Sector S 600 electrochemiluminescence immunoassay. It is indicated for use as an aid in assessment of the risk of progressive decline in kidney function (sustained decrease in eGFR greater than or equal to 40% lasting more than 3 months) within a period of up to 5 years following KidneyIntelX.dkd Level measurement in adult patients with type 2 diabetes and existing chronic kidney disease (defined for the purposes of this device as patients with an estimated glomerular filtration rate of 30-59 ml/min/1.73m2 or eGFR ≥ 60 ml/min/1.73m2 with albuminuria (uACR ≥ 30 mg/g)).

KidneyIntelX.dkd is not intended for screening or as a stand-alone diagnostic test.

Device Description

KidneyIntelX.dkd provides the KidneyIntelX.dkd level, generated by the KidneyIntelX.dkd algorithm. The algorithm includes inputs from clinical data collected on the patient as well as component analytes measured directly by KidneyIntelX.dkd.

The three component analytes measured by KidneyIntelX.dkd directly are quantitated via a multiplex electrochemiluminescence technology for the in vitro quantitative determination the concentration of three circulating biomarkers in human EDTA plasma:

i) soluble Tumor Necrosis Factor Receptor 1 (TNFR-1),
ii) soluble Tumor Necrosis Factor Receptor 2 (TNFR-2),
iii) and Kidney Injury Molecule (KIM)-1.

The three measured components of the KidneyIntelX.dkd level are measured using the MESO SECTOR® S 600 instrument, by trained laboratory personnel using the assay components that includes the KidneyIntelX 96-well plate, the detection antibody, calibrator, and controls along with the Meso Scale Diagnostics diluents, blocker, wash buffer and read buffer.

A sandwich immunoassay is used to measure KIM-1, TNFR-1, and TNFR-2. The plate wells are precoated with goat polyclonal antibodies to KIM-1, and mouse monoclonal antibodies specific to TNFR-1 and TNFR-2. After treating the wells with a blocking solution, the specimens and controls are incubated in the wells then washed. The analytes are quantified via electrochemiluminescence, with secondary detection antibodies (goat polyclonal antibodies to KIM-1, and mouse monoclonal antibodies specific to TNFR-1 and TNFR-2) covalently linked to electrochemiluminescent labels. The MESO SECTOR® S 600A instrument measures the light emitted via charged-coupled device (CCD) camera.

A software with an artificial intelligence derived algorithm provides a risk assessment score by combining the biomarker results from the assay (TNFR-1, TNFR-2, and KIM-1) and a set of clinical data, which are provided by a patient's physician via a test requisition form (urine albumin creatinine ratio [uACR], hemoglobin A1c [HbA1c], and Blood Urea Nitrogen [BUN]). The algorithm generates a risk level (Low, Moderate, or High) for progressive decline in kidney function, defined as sustained decrease (<40% of baseline value) in eGFR. The KidneyIntelX.dkd algorithm was modeled using machine learning (Random Forest) to identify and analyze risk factors for kidney disease progression.

The software is installed and maintained in the KidneyIntelX Portal, a cloud-based system. The biomarker results and clinical data set are manually inputted into the KidneyIntelX Portal determining the KidneyIntelX.dkd level. A KidneyIntelX.dkd Test Report containing the KidneyIntelX.dkd level is provided to the ordering physician. The KidneyIntelX.dkd level is to be used in conjunction with clinical information as an aid in assessing progressive decline in kidney function in T2D patients with DKD.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

Acceptance Criteria	Reported Device Performance	Comments
Clinical Performance: Ability to predict progressive decline in kidney function (sustained decrease in eGFR ≥ 40% lasting > 3 months) or reaching end stage kidney disease (sustained eGFR <15 ml/min/1.73 m2) within up to 5 years.	Shows significant differentiation in risk of progressive decline in kidney function across Low, Moderate, and High KidneyIntelX.dkd Levels.
- Low Level	Estimated 5-year event rate: 5.9% (95% CI: 3.6-9.4%)
- Moderate Level	Estimated 5-year event rate: 21.5% (95% CI: 15.9-28.6%)
- High Level	Estimated 5-year event rate: 66.9% (95% CI: 49.3-83.5%)
Analytical Precision/Reproducibility: Classification consistency despite cumulative imprecision of all 6 inputs.	Majority of patients remained in the measured level across 100 simulations for each patient. For KidneyIntelX.dkd Level: - Low: 89% remained Low - Moderate: 90.4% remained Moderate - High: 85.5% remained High No patients changed from "low" to "high" level.	Worst-case scenario imprecision used for analytes; publicly available imprecise results for BUN, HbA1c, uACR. Criteria: <95% match original category considered affected by imprecision.
Analytical Bias: Classification consistency despite systematic biases in input features.	Majority of patients remained in the measured level across 100 simulations for each patient. For KidneyIntelX.dkd Level: - Low: 96.0% remained Low - Moderate: 94.3% remained Moderate - High: 96.4% remained High No patients changed from "low" to "high" level.	Worst-case scenario bias used; higher bias than observed in labeled performance of assays.
Analytical Linearity: KIM-1, TNFR-1, and TNFR-2 measurements.	Deviation from linearity < ±10% within claimed measuring intervals.	Conforms to CLSI EP06-Ed2.
Analytical Specificity/Interference: Robustness against interfering substances.	Majority of patients remained in the measured level across 100 simulations for each patient. For KidneyIntelX.dkd Level: - Low: 84.2% remained Low - Moderate: 68.9% remained Moderate - High: 80.0% remained High No patients changed from "low" level to "high" level. Some specific interferences identified with > ±10% change for KIM-1, TNFR-1, TNFR-2 (Total Protein, Rheumatoid Factor).	Worst-case scenario interference (+/- 10%) used for simulations. Specific limitations added regarding high RF or total protein. Criteria: >=5% of patient simulations not matching original category considered affected.
Assay Reportable Range: Established measuring intervals for KIM-1, TNFR-1, TNFR-2.	KIM-1: 12 pg/mL to 3,915 pg/mL TNFR-1: 1,057 pg/mL to 14,322 pg/mL TNFR-2: 4,270 pg/mL to 43,291 pg/mL	Data supports these intervals considering LoB/LoD/LoQ, linearity, and precision.
Traceability: KIM-1, TNFR-1, TNFR-2 methodologies.	Traceable to internal standards.
Stability: KIM-1, TNFR-1, TNFR-2 in samples for shipping.	Stable for 3 days at up to 37℃.	Consistent with handling instructions for shipping to the lab.
Detection Limit (LoB, LoD, LoQ): For KIM-1, TNFR-1, TNFR-2.	LoB, LoD determined per CLSI EP17-A2. LoQ defined as lowest concentration with total within-laboratory precision of %CV<20%. Specific values are listed but not explicitly included in the table above as they are part of meeting the reportable range and precision.
Hook Effect: No hook effect for individual components.	No hook effect expected at tested levels.
Subgroup Performance: Performance similar across major subgroups (e.g., eGFR, race).	Demonstrated similar performance across subgroups for progressive decline in kidney function (e.g., eGFR 30-59.9 vs >60, Black/African American vs Non-Black/African American).	Shown via Kaplan-Meier curves and estimated 5-year rates.
Lack of Diagnosis/Staging: Not intended for diagnosing or staging DKD.	Labeling explicitly states this.	Part of the "Special Conditions for Use Statement(s)".
Rx - For Prescription Use Only: Restriction on use.	Labeling explicitly states this.	Part of the "Special Conditions for Use Statement(s)".

Study Information:

A table of acceptance criteria and the reported device performance: Included above.
Sample sized used for the test set and the data provenance:
- Sample Size: N = 657 patients.
- Data Provenance: Retrospective analysis of biobanked samples. Sourced from a single biorepository site that collected from 10 clinical sites in the United States (implied by references to US population and demographics like "American Indian/Alaskan Native", "Black/African American", "White", "Hispanic"). The study included up to 5 years of data per sample.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document does not specify the number or qualifications of experts used to establish the ground truth for the test set. The ground truth ("progressive decline in kidney function" and "end-stage kidney disease") is defined by clinical outcomes (e.g., sustained decrease in eGFR, eGFR <15 ml/min/1.73 m2), rather than expert interpretation of images or other subjective data.
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- The document does not describe an adjudication method. Since the ground truth is defined by objective clinical measurements (eGFR decline, ESKD), there would typically be no need for expert adjudication.
If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- No, an MRMC comparative effectiveness study was not done. This device is an in-vitro diagnostic test generating a risk score, not an AI-assisted diagnostic imaging tool that would typically involve human readers.
If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
- Yes, a standalone performance study was done. The clinical study evaluates the KidneyIntelX.dkd algorithm's ability to predict outcomes in a cohort of patients without human intervention in its scoring process. The algorithm generates a risk level (Low, Moderate, High) which is then correlated with observed clinical outcomes. The outputs are intended to be used in conjunction with other clinical findings, but the generation of the score itself is standalone.
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Outcomes data. The ground truth was defined by time to the first occurrence of a composite endpoint:
  - Sustained decrease in eGFR greater than or equal to 40% lasting more than 3 months.
  - Reaching end-stage kidney disease (sustained eGFR <15 ml/min/1.73 m2).
The sample size for the training set:
- The document does not explicitly state the sample size for the training set. It mentions that the "KidneyIntelX.dkd algorithm was modeled using machine learning (Random Forest) to identify and analyze risk factors for kidney disease progression," but details on the training set used for this modeling are absent from the provided text. The N=657 is described as the "clinical validation" set.
How the ground truth for the training set was established:
- The document does not describe how the ground truth for the training set was established. Given the nature of the clinical validation ground truth (outcomes data), it is highly probable that similar outcomes-based ground truth was used for training, but this is not explicitly stated.

Summary

{0}------------------------------------------------

EVALUATION OF AUTOMATIC CLASS III DESIGNATION FOR KidneyIntelX.dkd DECISION SUMMARY

I Background Information:

A De Novo Number

DEN200052

B Applicant

Renalytix AI, Inc.

C Proprietary and Established Names

KidneyIntelX.dkd

D Regulatory Information

ProductCode(s)	Classification	RegulationSection	Panel
QWZ	Class II withspecial controls	21 CFR 862.1223 -Prognostic test forassessment of chronickidney diseaseprogression	Clinical Chemistry andToxicology Devices

Submission/Device Overview: II

A Purpose for Submission:

De Novo request for evaluation of automatic class III designation for KidneyIntelX.dkd.

B Measurand:

The device reports a KidneyIntelx.dkd score derived from measurements of Tumor Necrosis Factor Receptor 1 (TNFR-1), Tumor Necrosis Factor Receptor 2 (TNFR-2), Kidney Injury Molecule 1 (KIM-1) and clinical variables (Urine Albumin Creatinine Ratio (uACR), Hemoglobin Alc (HbAlc) and Blood Urea Nitrogen (BUN).

C Type of Test:

Immunofluorescent quantitative assay

{1}------------------------------------------------

III Indications for Use:

A Indication(s) for Use:

KidneyIntelX.dkd is not intended for screening or as a stand-alone diagnostic test.

B Special Conditions for Use Statement(s):

Rx - For Prescription Use Only

KidneyIntelX.dkd is for In-Vitro Diagnostic Use: Only performed at Renalytix clinical laboratory.

KidneyIntelX.dkd is not intended as a screening or stand-alone diagnostic test.

KidneyIntelX.dkd is not for use in the diagnosing or staging of diabetic kidney disease.

KidneyIntelX.dkd test results are intended to be used in conjunction with other clinical and diagnostic findings, consistent with professional standards of practice, including information obtained by alternative methods, and clinical evaluation and physician assessment as appropriate.

Always interpret KidneyIntelX.dkd test results in conjunction with the patient's medical history, clinical presentation, physician assessment and other findings.

A KidneyIntelX.dkd Low Level is associated with a lower prognostic risk, but disease progression will occur in some patients with a KidneyIntelX.dkd Low Level test result.

A KidneyIntelX.dkd High Level is associated with a higher prognostic risk, but disease progression does not occur in some patients with a KidneyIntelX.dkd High Level test result.

Only K2EDTA plasma samples can be analyzed for the measurement of KIM-1, TNFR-1 and TNFR-2 used to generate the KidneyIntelX.dkd test results.

Only measurements of uACR, HbA1c, and BUN within measuring intervals and eGFR and serum creatinine detailed in the Test Requisition Form taken within 12 months prior to sample collection should be used with the KidneyIntelX.dkd test.

{2}------------------------------------------------

All inputs to the KidneyIntelX.dkd algorithm are subject to measurement and intra-individual variability resulting in some subjects being reported at different KidneyIntelX.dkd Levels on repeat testing.

C Special Instrument Requirements:

Plate imager instrument

IV Device/System Characteristics:

A Device Description:

i) soluble Tumor Necrosis Factor Receptor 1 (TNFR-1),
ii) soluble Tumor Necrosis Factor Receptor 2 (TNFR-2),
iii) and Kidney Injury Molecule (KIM)-1.

Principle of Operation B

{3}------------------------------------------------

albumin creatinine ratio [uACR], hemoglobin A1c [HbA1c], and Blood Urea Nitrogen [BUN]). The algorithm generates a risk level (Low, Moderate, or High) for progressive decline in kidney function, defined as sustained decrease (<40% of baseline value) in eGFR. The KidneyIntelX.dkd algorithm was modeled using machine learning (Random Forest) to identify and analyze risk factors for kidney disease progression.

V Standards/Guidance Documents Referenced:

CLSI EP05-A3, Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline - Third Edition

CLSI EP15-A3. User Verification of Precision and Estimation of Bias: Approved Guideline -Third Edition

CLSI EP17-A2, Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline - Second Edition

CLSI EP07, Interference Testing in Clinical Chemistry, 3rd Edition

CLSI EP37, Supplemental Tables for Interference Testing in Clinical Chemistry

CLSI EP28-A3c, Defining, Establishing, and Verifying Reference Intervals in the Clinical Laboratory; Approved Guideline - Third Edition

CLSI EP19. A Framework for Using CLSI Documents to Evaluate Clinical Laboratory Measurement Procedures, 2nd Edition

CLSI EP25-A, Evaluation of Stability of In Vitro Diagnostics Reagents; Approved Guideline

VI Performance Characteristics:

A Analytical Performance:

1. Precision/Reproducibility:
  Precision Simulation Studies

{4}------------------------------------------------

The sponsor performed simulation studies using the data from their clinical validation to assess the effect of the cumulative imprecision of all 6 inputs into the algorithm (both those measured in their internal lab as well as those provided by the ordering clinician). For the measured analytes, the sponsor used the precision profiles generated in their analytical studies, selecting the worst-case scenario imprecision recorded. For BUN, HbA lc and uACR, the sponsor used publicly available information for FDA cleared assays to estimate the worst-case scenario (most imprecise results of available devices) for imprecision.

Imprecision simulation study results

Using the information described above. 100 simulations were performed for each patient to generate the overall imprecision (n=657 patients. n=65.700 simulations) and the mean results are presented here:

The sponsor set the criteria that if <95% of a patient's simulations did not match the original category results, the results were considered to be affected by imprecision.

MeasuredKidneyIntelX.dkdlevel	Low levelfollowingSimulation	Medium levelfollowingSimulation	High levelfollowingSimulation
Low (n=374)	89%	11.0%	0.0%
Moderate (n=228)	6.1%	90.4%	3.5%
High (n=55)	0%	14.5%	85.5%

While some patients could be re-categorized due to imprecision, the majority of patients remained in the measured level, and no patients changed from a "low" level to a "high" level.

Bias simulation study

The sponsor also modeled the effects of bias in their input features on the final output of their device to demonstrate the effect of different systematic biases between analytes (HbA IC, BUN and uACR) measured on different test systems. The sponsor used publicly available information from to identify the systematic differences in cleared devices, in order to find the worst-case scenario of bias in these inputs. In each case, the sponsor chose to use a higher bias than observed in the labeled performance of the assays. The sponsor analyzed the results considering each patient's set of 100 simulations as above.

					Bias simulation study results
--	--	--	--	--	-------------------------------

MeasuredKidneyIntelX.dkdlevel	Low Levelfollowing biasSimulation	Medium Levelfollowing biasSimulation	High Levelfollowing biasSimulation
---------------------------------------	-------------------------------------------	----------------------------------------------	--------------------------------------------

{5}------------------------------------------------

Low (n=374)	96.0%	4.0%	0.0%
Moderate (n=228)	4.4%	94.3%	1.3%
High(n=55)	0%	3.6%	96.4%

While some patients could be re-categorized due to systemic bias differences between test systems, the majority of patients remained in the measured level, and no patients changed from a "low" level to a "high" level.

The repeatability and within-laboratory precision were also evaluated for KIM-1, TNFR-1, and TNFR-2 when measured in the KidneyIntelX.dkd laboratory and found to be acceptable.

2. Linearity:

Linearity of KIM-1, TNFR-1, and TNFR-2 when measured in the KidneyIntelX.dkd laboratory measurements was evaluated according to CLSI EP06-Ed2. High samples were prepared by spiking into intended use specimens. Low pools were created from native samples of presumed healthy individuals. Each dilution series comprised at least 11 levels that were prepared by mixing the high and low pools. The data supported the linearity of KIM-1, TNFR-1, and TNFR-2 with the claimed measuring interval of each component with deviation from linearity < ±10%.

3. Analytical Specificity/Interference:

The sponsor performed simulation studies using the data from their clinical validation to assess the effect of the cumulative interference for all 6 inputs into the algorithm (for both, those measured in their internal lab as well as those provided by the ordering clinician). For the measured analytes, the sponsor used the interference information generated in their analytical studies, selecting the worst-case scenario interference recorded. For the remaining data inputs (BUN, HbA1c, and UACR) the sponsor used publicly available information to estimate expected interference. Taken together, the sponsor determined that ±10% interference on each of the 6 data inputs represented a worst-case scenario for interference in the intended use population. Using the information described above, 100 simulations were performed for each patient to estimate the overall effects of interference (n=657 patients, n=65,700 simulations). The sponsor considered that if ≥5% of a patient's simulations did not match the original category results, that patient was affected by interference, and placed that adjacent level in the following table:

MeasuredKidneyIntelX.dkdlevel	Low LevelfollowinginterferenceSimulation	Moderate LevelfollowinginterferenceSimulation	High LevelfollowinginterferenceSimulation
Low (n=374)	84.2%	15.8%	0.0%
Moderate (n=228)	23.2%	68.9%	7.9%
High(n=55)	0%	20.0 %	80.0%

{6}------------------------------------------------

While some patients could be re-categorized due to cumulative interference from the inputs to the device, the majority of patients remained in the measured level, and no patients changed from a "low" level to a "high" level.

To inform the simulations above, the sponsor conducted interference testing to look at the effect of the following interferents for KIM-1, TNFR-1 and TNFR-2. Significant interference was defined as change in 10% or more for each analyte. The list of interferents tested and the concentrations at which no interference was observed is presented below:

Interferent	Highest Concentration Tested
Acetaminophen	15.6 mg/dL
Acetylsalicylic acid (ASA)	3 mg/dL
Adalimumab (Humira)	0.5 mg/mL
Ampicillin sodium	7.5 mg/dL
Bilirubin (conjugated)	40 mg/dL
Bilirubin (unconjugated)	40 mg/dL
Blood urea nitrogen (BUN)	120 mg/dL
Calcium Carbonate (total)	30.9 mg/dL
Calcium Dobesilate	4.5 mg/dL
Cefoxitin Sodium	660 mg/dL
Cholecalciferol (Vitamin D3 medicine)	195 ng/mL
Creatinine	15 mg/dL
Cyclosporine	0.18 mg/dL
Dapagliflozin	1.9 mg/dL
Doxycycline Hydrochloride	1.8 mg/dL
Eplerenone (Aldosterone antagonist)	0.0555 mg/dL
Ethinyl estradiol	750 pg/dL
Fluorescein	30 mg/dL
Glipizide (Sulfonylureas)	0.3 mg/dL
GLP-1R agonist	1.25 mg/dL
Glucose	1,000 mg/dL
HAMA	372.4 ng/mL
Hemolysate	0.5 g/dL
Heparin	330 units/dL
Ibuprofen	21.9 mg/dL
Insulin	900 pmol/L
Lixisenatide (GLP-1R agonist)	0.05 mg/mL
Metformin	4 mg/dL
Metformin-HCl	4 mg/dL
Metronidazole	12.3 mg/dL
Progesterone	227.7 nmol/L
Rheumatoid Factor	665 IU/mL
Rifampicin	4.8 mg/dL
Interferent	Highest Concentration Tested
Selenium (selenomethionine)	226 ng/mL
Sertraline-HCl	0.0927 mg/dL
Sex Hormone Binding Globulin	435 nmol/L
Sitagliptin Phosphate (DPP-4i)	0.115 mg/dL
Theophylline	6.0 mg/dL
TNF-α	100 ng/mL
TNF-β	100 ng/mL
Total Protein	8.48 g/dL
Triglyceride-rich Lipoproteins	1,500 mg/dL
Uric Acid	23.5 mg/dL
Vitamin B9 (Folic Acid)	36.6 µg/L
Vitamin B12	2,034 ng/L
Vitamin C	5.25 mg/dL
Vitamin D	195 ng/mL
Vitamin E	51 µg/mL
Zinc-sulfate	360 µg/mL

{7}------------------------------------------------

Interference > ±10% was observed for the measurements of KIM-1, TNFR-1 and TNFR-2 at the concentrations shown below for the following substances:

Interfering Substance	InterferenceLevel	% ObservedInterference
Total Protein	13 g/dL	23%
Rheumatoid Factor (RF)	997 IU/mL	-11%

The sponsor included the following limitations in the labeling:

. The KidneyIntelX.dkd test should not be used in patients with known elevation of RF above 665 IU/mL.
The KidneyIntelX.dkd test should not be used in patients with known elevation of total . protein above 8.5 g/dL.
Specimens with selenium levels above 226 ng/mL may have falsely elevated results. .

4. Assay Reportable Range:

In summary, considering LoB/LoD/LoQ, linearity and precision studies, the sponsor provided data to support the following measuring intervals for the three inputs:

KIM-1 measurement interval: 12 pg/mL to 3,915 pg/mL TNFR-1 measurement interval: 1,057 pg/mL to 14,322 pg/mL TNFR-2 measurement interval: 4,270 pg/mL to 43,291 pg/mL

{8}------------------------------------------------

5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):

The KIM-1, TNFR-1 and TNFR-2 methodologies used in the KidneyIntelX.dkd laboratory are traceable to internal standards.

The sponsor provided data to support that the KIM-1, TNFR-1 and TNFR-2 are stable for 3 days at up to 37℃, consistent with the instructions for handling samples for shipping to the KidneyIntelX.dkd laboratory.

6. Detection Limit:

Limit of blank (LoB):

Limit of blank was determined for KIM-1. TNFR-1 and TNFR-2 when measured in the KidneyIntelX.dkd laboratory using 2 lots of reagents on 1 instrument. 160 determinations per lot were obtained by testing 8 blank serum samples in 2 replicates during 10 runs.

The LoB was calculated non-parametrically according to the CLSI EP17-A2 as the value at the ranked position (152.5 in this study) using the following equation:

(DR. 0)

where B = total number of blank sample measurements.

Limit of Detection (LoD):

Limit of detection was determined for the for KIM-1, TNFR-1 and TNFR-2 when measured in the KidneyIntelX.dkd laboratory using 2 lots of reagents and 1 instrument. A total of 80 determinations per lot were obtained by testing 4 low analyte serum samples in 2 replicates during 10 runs.

The limit of detection was determined using the precision profile approach as described in the CLSI document EP17-A2

Limit of Quantitation (LoO):

The LoQ was derived using a precision profile approach using data from the low-end region of the measuring interval for KIM-1, TNFR-1, and TNFR-2 when measured in the KidneyIntelX.dkd laboratory. Results from testing of the 13 samples were used for calculation of the LoQ. The LoQ for each reagent lot was determined as the analyte concentration corresponding to the intersection of the acceptance criterion goal with the precision profile. The LoQ was defined as the lowest concentration with total within-laboratory precision of %CV<20%.

Hook Effect:

The sponsor provided information to support that no hook effect can be expected for individual components of the test at the levels tested.

7. Assay Cut-Off:

{9}------------------------------------------------

Not applicable.

B Comparison Studies:

1. Method Comparison:
  Not applicable.
1. Matrix Comparison:
  Not applicable.

C Clinical Studies:

1. Clinical Sensitivity:
  See section C.12.
1. Clinical Specificity:
  See section C.12.

12. Other Clinical Supportive Data:

The sponsor performed a retrospective analysis of biobanked samples to validate the performance of their device. Biobanked samples were sourced from a single biorepository site that collected from 10 clinical sites and were stored until analyzed. The sponsor set the criteria for their study such that they would have up to 5 years of data per sample.

Inclusion and exclusion criteria were designed to identify patients with Type 2 diabetes, diagnosed on or at the time of biobank enrollment. Specimens were required to have eGFR or eGFR and uACR within 12 months prior to enrollment in the biobank to meet one of the following criteria:

eGFR value is between 30 to 59.9 mL/min/1.73 m2 (OR) eGFR is >60 mL/min/1.73 m2 and uACR is >30 mg/g

Specimens were also required to have the externally provided measurements (BUN, uACR, HbA1c) within 12 months prior to enrollment.

{10}------------------------------------------------

Patient Population

Enrollment Criterion	Total (N=657)n (%)
eGFR value is between 30 to 59.9 mL/min/1.73 m²	388 (59%)
eGFR is ≥60 mL/min/1.73 m² and uACR is ≥30 mg/g	269 (41%)

Age		Median (IQR)	72 (64, 78)
		Min, Max	38,90
Sex	n (%)		Male 284 (43.2%)
			Female 373 (56.8%)
Race	n (%)		American Indian/Alaskan Native 3 (0.5%)
			Asian 27 (4.1%)
			Black/African American 240 (36.5%)
			Native Hawaiian/Pacific Islander 0 (0%)
			White 100 (15.2%)
			Other 284 (43.2%)
			No Response 3(0.5%)
Ethnicity	n (%)		Hispanic 264 (40.2%)
			Non-Hispanic 393 (59.8%)
Clinical History	n (%)		Hypertension 568 (86.5%)
			Heart Failure 78 (11.9%)
			Coronary Artery Disease 138 (21.0%)

Demographics and Medical History:

The sponsor performed an analysis to identify the ability of the KidneyIntelX.dkd test to predict progressive decline in kidney function by quantifying the event rates for patients in each of the three KidneyIntelX.dkd levels. The pre-specified event rate for the analysis is time to the first occurrence of a composite end point that was defined as ≥40% sustained decline in eGFR or reaching end stage kidney disease (sustained eGFR <15 ml/min/1.73 m2). The follow-up period is defined as up to 5 years from the time that patient had a KidneyIntelX.dkd score measured on their sample. In all cases, end stage kidney disease events were preceded by sustained decline events. Therefore, the primary outcome reflects the rate of sustained decline events. However, the sponsor also collected data on the rate of kidney failure events for each group.

A summary of the distribution of KidneyIntelX.dkd levels, observed events during the follow-up period and follow-up timeframes of the subjects analyzed in this study are presented below.

{11}------------------------------------------------

	KidneyIntelX.dkdLevel LowN=374	KidneyIntelX.dkdLevel ModerateN=228	KidneyIntelX.dkdLevel HighN=55
40% decline events	17	38	23
% of patientsexperiencing KidneyEvents (95%Confidence Intervals)	4.6%(2.7-7.2%)	16.7%(12.1-22.2%)	41.8%(28.7-55.9%)

	KidneyIntelX.dkdLevel LowMean (SD)N=374	KidneyIntelX.dkdLevel ModerateMean (SD)N=228	KidneyIntelX.dkdLevel HighMean (SD)N=55	TotalMean (SD)N=657
Follow UpTime in days	1344.9 (471.68)	1158.6 (555.39)	719.5 (488.52)	1227.9 (532.95)

Kaplan-Meier Survival Analysis, Estimation of Absolute Risk

Image /page/11/Figure/3 description: The image is a graph titled "Product-Limit Failure Curves With 95% Confidence Limits". The x-axis is labeled "Years" and ranges from 0 to 5. The y-axis is labeled "Failure Probability" and ranges from 0.0 to 1.0. There are three curves on the graph, labeled "Low", "Moderate", and "High", which represent different levels of failure probability over time.

To account for incomplete data during the 5-year observation period, the sponsor applied the Kaplan-Meier survival analysis method to estimate the estimated rate at five years for the outcome for each of the KidneyIntelX.dkd test risk categories. The estimated rates showed similar trends as the absolute rates, with the lowest rate of kidney decline events occurring in the "Low" KidneyIntelX.dkd group, and a moderate number in the "Moderate" group and the greatest number in the "High" group.

{12}------------------------------------------------

	KidneyIntelX.dkdLevel LowN=374	KidneyIntelX.dkdLevel ModerateN=228	KidneyIntelX.dkdLevel HighN=55
Estimated rate at 5-years (95% ConfidenceIntervals)	5.9%(3.6-9.4%)	21.5%(15.9-28.6%)	66.9%(49.3-83.5%)

To support their claims, the sponsor also provided several analysis demonstrating that the device performance was still adequate when controlling for several well-known risk factors expected to affect rate of disease progression, including age, sex, race, systolic blood pressure, baseline eGFR, baseline uACR, and baseline HbA1c. The proportional analysis remained significantly different compared to the low group when adjusting for well known risk factors.

The sponsor provided sub-group analysis demonstrating the performance of the device remained similar across most major subgroups.

Kaplan-Meier curves were plotted to show performance of KidneyIntelX.dkd in sub-populations represented in the clinical performance study as defined by starting eGFR:

Image /page/12/Figure/4 description: The image is a graph titled "Product-Limit Failure Curves With 95% Confidence Limits". The graph shows the failure probability over time in years for three different categories: low, moderate, and high. The failure probability for the low category is around 0.1 at 5 years, for the moderate category it is around 0.3 at 5 years, and for the high category it is around 0.75 at 5 years.

Kaplan-Meier curve for progressive decline in kidney function over time up to a maximum follow-up of 5 years of individuals with eGFR 30 - 59 mL/min/1.73m2.

{13}------------------------------------------------

Image /page/13/Figure/0 description: The image shows product-limit failure curves with 95% confidence limits. The x-axis represents years, ranging from 0 to 5, while the y-axis represents failure probability, ranging from 0.0 to 1.0. There are three curves representing low, moderate, and high failure probabilities over time. The high failure probability reaches approximately 0.45 at 5 years.

Kaplan-Meier curve for progressive decline in kidney function over time up to a maximum follow-up of 5 years of individuals with eGFR ≥ 60 mL/min/1.73m2.

Subgroup	KidneyIntelX.dkdLevel	Numberofsubjects	Progressive Declinein Kidney Function		Estimated rate at5 years (95%confidenceintervals)
			Yes	No
StartingeGFR 30-59.9(n = 388)	Low	215	11	204	6.5%(3.6-11.7%)
StartingeGFR 30-59.9(n = 388)	Moderate	131	24	107	24.2%(16.7-34.3%)
StartingeGFR 30-59.9(n = 388)	High	42	19	23	76.9%(55.4-93.1%)
StartingeGFR > 60(n = 269)	Low	159	6	153	4.9%(2.2-10.8%)
StartingeGFR > 60(n = 269)	Moderate	97	13	84	16.9%(9.9-28.0%)
StartingeGFR > 60(n = 269)	High	13	4	9	45.5%(19.5-81.6%)

Kaplan-Meier curves were plotted to show performance of KidneyIntelX.dkd in sub-populations represented in the clinical performance study as defined by race:

{14}------------------------------------------------

Image /page/14/Figure/0 description: The image shows product-limit failure curves with 95% confidence limits. The x-axis represents years, ranging from 0 to 5, while the y-axis represents failure probability, ranging from 0.0 to 1.0. There are three curves representing low, moderate, and high failure probabilities over time. The high curve shows the highest failure probability, reaching over 0.8 by year 5, while the low curve shows the lowest failure probability, remaining below 0.1.

Kaplan-Meier curve for progressive decline in kidney function over time up to a maximum follow-up of 5 years of individuals self-identified as Black or African American ancestry.

Image /page/14/Figure/2 description: The image shows product-limit failure curves with 95% confidence limits. The x-axis represents years, ranging from 0 to 5, while the y-axis represents failure probability, ranging from 0.0 to 1.0. There are three curves representing low, moderate, and high failure probabilities. The high failure probability curve reaches approximately 0.6 at 5 years, while the moderate curve reaches approximately 0.2, and the low curve reaches approximately 0.1.

Kaplan-Meier curve for progressive decline in kidney function over time up to a maximum follow-up of 5 years of individuals self-identified of Non-Black or Non-African ancestry.

{15}------------------------------------------------

Subgroup	KidneyIntelX.dkdLevel	Numberofsubjects	Progressive Declinein Kidney Function		Estimated rate at5 years (95%confidenceintervals)
			Yes	No
Black/AfricanAmerican(n = 240)	Low	140	6	134	4.9%(2.2-10.7%)
	Moderate	82	15	67	22.2%(13.7-34.8%)
	High	18	9	9	83.9%(52.4-98.9%)
Non-Black/AfricanAmerican(n = 417)	Low	234	11	223	6.6%(3.6-11.8%)
	Moderate	146	22	124	20.6%(13.8-30.0%)
	High	37	14	23	60.1%(39.1-81.7%)

Although the study was not powered to detect statistically significant differences in the rates of end stage kidney disease between groups, the sponsor also provided information on the number of patients who experienced end-stage kidney disease by each risk group:

	KidneyIntelX.dkdLevel LowN=374	KidneyIntelX.dkdLevel ModerateN=228	KidneyIntelX.dkdLevel HighN=55	TotalN=657
% of patientsexperiencingEnd StageKidney Disease	0	3.1%	18.2%	2.6%

D Clinical Cut-Off:

Not Applicable.

E Expected Values/Reference Range:

Expected values for apparently healthy subjects and for patients with type 2 diabetes but without CKD were established in accordance with CLS1 guideline EP28-A3c. Study subjects were selected to be representative of the U.S. population. The absence of chronic kidney disease (CKD) was defined as those subjects with eGFR ≥60 mL/min/1.73m2 and uACR <30 mg/g, categorized as normal or mildly increased albuminuria, or low risk (if no other markers of kidney disease, no

{16}------------------------------------------------

CKD). The proportion of patients in each KidneyIntelX.dkd Level was established for this population for reference purposes only. The KidneyIntelX.dkd test is not intended for subjects with diabetes without CKD.

Population	Gender	Race/Ethnicity	N	AgeRange	KidneyIntelX.dkcLevel
ApparentlyHealthy	Female (64%)Male (36%)	African American (12%)Caucasian (45%)Other (43%)	121	18 to 58	Low (100%)Moderate (0%)High (0%)
Patients withType 2Diabeteswithout CKD	Female (64%)Male (36%)	African American (30%)Caucasian (8%)Other (62%)	104	29 to 80	Low (77%)Moderate (22%)High (1%)

Other Supportive Performance Characteristics Data: F

Not applicable.

Proposed Labeling:

The labeling supports the decision to grant the De Novo request for this device.

Identified Risks and Mitigations:

Risks to Health	Mitigation Measures
Incorrect performance of the device leading tofalse positive, false negative or failure toprovide a result	Certain design verification and validationactivities and documentation.
	Certain labeling information, includingcertain limiting statements and performancecharacteristics.
Incorrect interpretation of test results	Certain design verification and validationactivities and documentation.
	Certain labeling information, includingcertain limiting statements and performancecharacteristics.

Benefit/Risk Assessment:

{17}------------------------------------------------

A Summary of the Assessment of Benefit:

The following benefits are considered:

The KidneyIntelX.dkd test may be useful in determining which patients could benefit . from additional examinations, increased monitoring, lifestyle changes, and treatment interventions.
The test provides additional independent patient-specific prognostic information on the . risk profile of patient with DKD that can be used by physician/healthcare providers to inform management decisions for individual patients. The test is to be used in conjunction with other laboratory measurements and clinical examination as an aid to determine therapeutic management decisions. It is not to be used as a diagnostic marker or in isolation.
The information provided by the test characterizes the risk profile in terms of clinically . meaningful endpoints, sustained decrease in eGFR ≥ 40% or end-stage kidney disease (sustained eGFR <15 ml/min/1.73m2), within a defined 5-year time frame.
It is anticipated that the KidneyIntelX.dkd result will be used in conjunction with other . laboratory and clinical findings to further guide the care pathway for patients in accordance with clinical guidelines.
. Earlier engagement with nephrologists for high-risk patients may also allow for more opportunities to advise and educate patients about home-based dialysis and pre-emptive or early kidney transplant as patient-centered kidney replacement options if more aggressive treatment does not ultimately prevent progression of DKD.

B Summary of the Assessment of Risk:

The risks considered in this benefit-risk assessment include risks associated with false negative and false positive test results as well as the risk of misinterpretation of test result by clinicians:

False negative: While the opportunity to initiate more aggressive therapies may be lost if . the patient is erroneously mis-classified as a lower risk, the patients will remain under physician's care for their underlying disease(s) and as such undergo clinical evaluation and routine laboratory and other assessments as recommended in clinical guidelines/ standard of practice. Standard of care treatment will not be lost; thus, risk is considered low.
False positive: Somewhat more intensive clinical management interventions may be used . sooner in patients with positive test result; however, such interventions in this patient population do not carry significant risk. It is anticipated that as this is an adjunctive aid for risk assessment and clinicians would use other clinical indicators of severity of disease before making therapeutic decisions based solely on an isolated result from the KidneyIntelX.dkd device.

C Patient Perspectives:

This submission did not include specific information on patient perspectives for this device.

{18}------------------------------------------------

D Summary of the Assessment of Benefit-Risk:

Given the totality of the information presented in this De Novo request it is concluded that the probable benefits of the KidneyIntelX.dkd device outweigh the probable risks in light of the identified special controls and general controls when the device is used as intended in the appropriate intended use population.

VII Conclusion:

The De Novo request is granted, and the device is classified under the following and subject to the special controls identified in the letter granting the De Novo request:

Product Code: QWZ

Device Type: Prognostic test for assessment of chronic kidney disease progression

Device Class: Class II with special controls.

Regulation: 21 CFR 862.1223

Regulation Number and Section

N/A