The Pathwork® Tissue of Origin Test is an in vitro diagnostic intended to measure the degree of similarity between the RNA expression patterns in a patient's formalin-fixed, paraffin-embedded (FFPE) tumor and the RNA expression patterns in a database of fifteen tumor types (poorly differentiated, undifferentiated and metastatic cases) that were diagnosed according to then current clinical and pathological practice. This test should be evaluated by a qualified physician in the context of the patient's clinical history and other diagnostic test results.

Limitations: The Pathwork Tissue of Origin Test is not intended to establish the origin of tumors (e.g. cancer of unknown primary) that cannot be diagnosed according to current clinical and pathological practice. It is not intended to subclassify or modify the classification of tumors that can be diagnosed by current clinical and pathological practice, nor to predict disease course or survival or treatment efficacy, nor to distinguish primary from metastatic tumor. Tumor types not in the Pathwork Tissue of Origin Test database may have RNA expression patterns that are similar to patterns in the database; therefore, results cannot be used to distinguish tumor types in the database from tumor types not in the database.

Device Description

The Pathwork® Tissue of Origin Test Kit-FFPE is a test kit consisting of the Pathchip microarray, reagents, software, and labeling. The Pathchip is a custom-designed microarray manufactured by Affymetrix, Inc. (Santa Clara, CA) per Pathwork design requirements and functions in a manner similar to GeneChip HG-U133A. The Pathchip has over 500,000 unique oligonucleotide features (18-micron in size), covering over 18,400 transcript variants (across 22.300 probesets) which in turn represent 14,500 of the best characterized human genes. Each transcript is represented by a probeset, comprised of 11-16 pairs of oligonucleotide probes. The probesets are spatially distributed over the arrav and are used to measure the level of transcription of each sequence represented on the array. For each array, there are 2000 probesets representing 2000 human genes which are used by the Tissue of Origin Test Kit - FFPE algorithm as markers to identify the tissue of origin of the specimen being tested. These probesets were selected using machine learning methods and each set has between 11 and 16 probe pairs of 25 bases whose sequences are matched to mRNA species that are found in human tissue. In addition, the array has 29 probesets that are used for normalization and data verification.

The algorithm of the Pathwork® Tissue of Origin Test was developed using a database of 2196 specimens, divided into independent training and test datasets. The test development used a machine learning approach based on marker selection to build a predictive model. The model consists of a list of markers, a set of reference (support) samples and a set of coefficients. These components are combined to produce 15 Similarity Scores, one for each of the possible tissues on the test panel. Each similarity score ranges from 0 to 100, with a higher score being associated with a higher likelihood that the input specimen has a molecular signature of the corresponding tissue of origin. The 15 similarity scores are scaled to sum up to 100. Each is based on the microarray standardized expression (SE) values of selected biomarkers. The process consists of the following steps:

Read SE values for the biomarkers used in the Tissue of Origin Test from 1. the input file.
Compute a decision function ("score") for each of 105 possible pairings of 2. the 15 tissues on the test panel with respect to the sample described by the input SE values.
Convert the 105 pairwise scores into pairwise probabilities. 3.
Reduce the 105 pairwise probabilities to 15 Similarity Scores, one for each 4. Tissue of Origin. These are the final 15 Similarity Scores presented in the Tissue of Origin Test Report.

AI/ML Overview

Here's an analysis 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
Percent agreement between the modified method (30-150ng RNA with ethanol) and the original method (≥150ng RNA without ethanol)	97.7% (95% CI: 87.7%, 99.9%)

Study Details

Sample Size and Data Provenance:
- Test Set Sample Size: 43 tumor specimens were actually analyzed for comparison. The study aimed for 45 tumors (3 of each of the 15 tumor types).
- Data Provenance: The specimens were "reserves of FFPE tumor specimens employed for assessment of performance during development of the TOO-FFPE Test." These pre-existing specimens had prior results obtained using the 510(k) cleared method. The text does not specify the country of origin, but the company is based in Redwood City, CA, USA. The data is retrospective, as it used pre-existing specimens with "extant results."
Number of Experts and Qualifications for Ground Truth:
- The primary ground truth for this modification study was the result obtained from the original 510(k) cleared method using ≥150 ng of RNA without ethanol. The text states these original results "all agreed with their available diagnosis."
- The ground truth for the original validation of the device (K092967) was established by "then current clinical and pathological practice." The text does not specify the number or qualifications of experts involved in establishing these diagnoses for the original specimens.
Adjudication Method for Test Set: Not applicable. The study was a comparison of results from two different processing methods on the same specimens against a pre-established "available diagnosis." There wasn't an expert adjudication process described for new interpretations in this specific modification study.
Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study: No. This study focused on the technical performance equivalence of a modified RNA extraction and purification protocol, not on human reader performance with or without AI assistance.
Standalone Performance (Algorithm Only without Human-in-the-loop): Yes, the study evaluated the performance of the algorithm with different input RNA quantities and processing steps. The output (Similarity Scores) is generated by the algorithm and then compared. While the ultimate intended use involves a physician's interpretation, this particular study focused on the analytical performance of the modified test.
Type of Ground Truth Used:
- For the modification study, the ground truth was the result obtained from the original 510(k) cleared method for the same specimen, which "agreed with their available diagnosis."
- For the original establishment of the device's accuracy (referenced as the predicate device), the ground truth was established by "available diagnosis" or "current clinical and pathological practice."
Sample Size for Training Set: The algorithm for the Pathwork® Tissue of Origin Test was developed using a database of 2196 specimens, divided into independent training and test datasets. The exact split between training and test sets from this 2196 is not provided, but the sample size for the overall algorithm development is stated.
How Ground Truth for Training Set was Established: The ground truth for the training set (part of the 2196 specimens) was established based on diagnoses "according to then current clinical and pathological practice."

Summary

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

May 16, 2012

Pathwork Diagnostics, Inc. 510(k): Device Modification: Tissue of Origin Test Kit-FFPE

SECTION 6 510(k) SUMMARY

This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of SMDA 1990 and 21 CFR 807.92.

The assigned 510(k) number is K120489

807.92 (a)(1):	Name:	Pathwork® Diagnostics, Inc.
	Address:	595 Penobscot DriveRedwood City, CA 94063

Phone:	650-366-1003 x101
Contact:	Deborah Neff President & CEO

807.92 (a)(2): Device Name - trade name and common name, and classification

Trade name:	Pathwork® Tissue of Origin Test Kit-FFPE
Common name:	Microarray, reagents and software system kit for geneexpression-based diagnostics
Classification:	21 CFR § 862.3100, Amphetamine Test SystemClass II
Product Code:	OIW, Software, similarity score algorithm, tissue of origin formalignant tumor types
Panel:	Toxicology (91)

807.92 (a)(3): Identification of the legally marketed predicate device

The Tissue of Origin Test Kit-FFPE as modified is substantially equivalent to the Pathwork Tissue of Origin Test Kit FFPE cleared under premarket notification K092967 on June 9, 2010.

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

807.92 (a)(4): Device Description

The Pathwork® Tissue of Origin Test Kit-FFPE is a test kit consisting of the Pathchip microarray, reagents, software, and labeling.

The Pathchip is a custom-designed microarray manufactured by Affymetrix, Inc. (Santa Clara, CA) per Pathwork design requirements and functions in a manner similar to GeneChip HG-U133A. The Pathchip has over 500,000 unique oligonucleotide features (18-micron in size), covering over 18,400 transcript variants (across 22.300 probesets) which in turn represent 14,500 of the best characterized human genes. Each transcript is represented by a probeset, comprised of 11-16 pairs of oligonucleotide probes. The probesets are spatially distributed over the arrav and are used to measure the level of transcription of each sequence represented on the array. For each array, there are 2000 probesets representing 2000 human genes which are used by the Tissue of Origin Test Kit - FFPE algorithm as markers to identify the tissue of origin of the specimen being tested. These probesets were selected using machine learning methods and each set has between 11 and 16 probe pairs of 25 bases whose sequences are matched to mRNA species that are found in human tissue. In addition, the array has 29 probesets that are used for normalization and data verification.

Read SE values for the biomarkers used in the Tissue of Origin Test from 1. the input file.
Compute a decision function ("score") for each of 105 possible pairings of 2. the 15 tissues on the test panel with respect to the sample described by the input SE values.
Convert the 105 pairwise scores into pairwise probabilities. 3.
Reduce the 105 pairwise probabilities to 15 Similarity Scores, one for each 4. Tissue of Origin. These are the final 15 Similarity Scores presented in the Tissue of Origin Test Report.

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

The Pathwork Specimen Processing Guide contains instructions for the user to process tissue specimens in the manner specimens were processed during the clinical validation of the Pathwork Tissue of Origin Test Kit - FFPE.

Components included in the kit

Microarray: Pathchip microarrays, packaged in boxes of 5 or 10.

Gene Expression Reagents: Reagents for specimen processing (extraction, amplification, labeling, hybridization, staining and washing).

Report

Tissue of Origin Test Kit-FFPE Report is produced by the Pathwork System Software (by licensed agreement); The Pathwork® System Software receives data from the scanned Pathchip™ microarray and performs data quality control and analysis. The System Software then generates a Pathwork® Tissue of Origin Test Kit-FFPE Report which provides a Similarity Score for each of the 15 tissues on the test panel. The test report is accessible for clinical interpretation via a secure password protected website.

807.92 (a)(5): Intended Use

Intended use: The Pathwork® Tissue of Origin Test is an in vitro diagnostic intended to measure the degree of similarity between the RNA expression patterns in a patient's formalin-fixed, paraffin-embedded (FFPE) tumor and the RNA expression patterns in a database of fifteen tumor types (poorly differentiated, undifferentiated and metastatic cases) that were diagnosed according to then current clinical and pathological practice. This test should be evaluated by a qualified physician in the context of the patient's clinical history and other diagnostic test results.

807.92 (a)(6): Technological Similarities and Differences to Predicate

Pathwork Diagnostics, Inc.

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

Comparison with Unmodified Device
Feature/component	Tissue of Origin Test Kit-FFPEK092967	Modified Tissue of Origin Test Kit-FFPE
Intended use	The Pathwork Tissue of Origin Testis an in vitro diagnostic intended tomeasure the degree of similaritybetween the RNA expressionpatterns in a patient's formalin fixed,paraffin embedded (FFPE) tumorand the RNA expression patterns ina database of fifteen tumor types(poorly differentiated,undifferentiated, and metastaticcases) that were diagnosedaccording to then current clinicaland pathological practice. This testshould be evaluated by a qualifiedphysician in the context of thepatient's clinical history and otherdiagnostic test results.	Same.Same chip, same location of all geneexpression probes.
MicroarrayEquipment	Pathchip®
	Hybridization oven	Same
	Stain, wash	Same
	Scanner	Same or substantially equivalent
Purification ofbiotinylatedcDNA	As Described in the Labeling inK092976	Changed, to add ETOHChanged to: Allow a minimum of30ng total RNA extracted from tissuespecimen is required at aconcentration of 10 ng/µl (± 0.5ng/µl). If the specimen has an area<25mm², commonly employedtechniques for manual dissectionunder a microscope need to be
		followed to obtain at least 60% tumor
Extraction/amplificationprocedure:	As Described in the Labeling inK092976	and a recommended tissue volume ofat least 0.05 mm³
InternalProcessingQuality Control(DataVerification)	Percent PositiveOverall SignalRegional Discontinuity	Same
Comparison with Unmodified Device
Feature/component	Tissue of Origin Test Kit-FFPEK092967	Modified Tissue of Origin Test Kit-FFPE
Software	FTP	Same
Analysis	Algorithm as described in K092967	Same
Report	Graphic presentation of SimilarityScores for fifteen tissues of origin	Same
Extraction/amplificationreagents	As K092967	Same
AnalyteDetected onChip	cDNA	Same
Probes employedin test	2000	Same
Clinicalvalidation/verification	Compare results with test toavailable results for tissue sample	Compare results with modifiedamount and procedure to results withunmodified amount and procedure
StatisticalMethod foranalysis ofvalidation study	Gaussian-(frequentist) Mean, S.D.	Same
% Agreementwith availablediagnosis("accuracy")	N= 462 (≥ 25 for each of 15malignant tumor types). Agreement,88.5% (85.3,91.3)	Percent agreement with result reportedby original method, vs. reported bychanged method.N=45, 3 per tissue attempted. 43actually analyzed, 1 quality failure, 1unusable because original test resultunavailable for comparison.Agreement, 99.7% (87.7, 99.9)
InterlabReproducibility	3 labs, N=149, 49-51 per lab, 88.5%overall concordance (83.1-93.2)	Not repeated
Limitations	as K092967	Same

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

May 16, 2012

807.92 (b)(1): Brief Description of Non-clinical data

The study was a comparison of the same tumor specimens already analyzed using the 510(k) cleared method, with specimens where the amount of starting tissue was diminished to provide between 30 and 150 nanograms of RNA. In addition, the procedure had been modified to include the use of ethanol in the purification of biotinylated DNA, and this modification was also included in the study. Specimens were selected from reserves of FFPE tumor specimens employed for assessment of performance during development of the TOO-FFPE Test. These tumors had extant results obtained when ≥150 ng of RNA had been

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

extracted using the 510(k) cleared method, and they all agreed with their These tumor specimens were manually dissected under a available diagnosis. microscope to provide less tissue for extraction, resulting in smaller amounts of extracted RNA. Several very small specimens were taken from each tumor sample. RNA was extracted from each of the smaller specimens, and the amount of RNA present determined spectroscopically. If a single specimen provided between 30 and 150 ng, and could be concentrated to at least 9.5 ng/ul, it was used. Otherwise, up to 4 extractions were combined until at least 30 ng RNA was present at a concentration of at least 9.5 ng/ul. The final tissues used were at least 0.05 mm3 with at least 60% tumor content. These total RNA samples were carried through the modified assay and results compared to those obtained with the larger amounts of total RNA for the same tissue. - Forty-five turnors, 3 of each of the tumor types in the database, were entered into the study. Comparisons between ≥150 ng RNA speciments processed without ethanol, and 30-150 ng of RNA extracted and processed with ethanol could be made for 43 tumors. Forty-two of these were concordant and one was not, for a % concordance of 97.7% (95% confidence interval of 87.7%, 99.9%). The change was considered validated, because all preestablished criteria were met or exceeded.

Concordance in Tissue of Origin Test Results between paired specimens with ≥ 150 ng of totalRNA yield processed in the absence and specimens with 30 to 150 ng of total RNA yield processedin the presence of Ethanol
		Concordance			Discordance
Comparison	#Specimens	Ratio	Percent	95%ConfidenceInterval	Ratio	Percent	95%ConfidenceInterval
≥ 150 ng andethanolabsentVersus 30 to150 ng andethanolpresent	43	42/43	97.7%	[87.7, 99.9]	1/43	2.3%	[0.1, 12.3]

Additional data analysis was performed "for information". Similarity score regression plots were obtained comparing the similarity scores for all 15 tissues, for matched pairs of specimens that yielded either ≥150 ng of total RNA processed in the absence of ethanol (x-axis) vs. between 30 and 150 ng of total RNA processed in the presence of ethanol (y-axis). Similarity scores range between 0 and 100. The resulting regression analysis gave an intercept of 0.61 (0.11, 1.10) and a slope of 0.91 (0.88. 0.93) and an R of 0.94.

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

Image /page/6/Figure/0 description: The image is a scatter plot titled "Low RNA Yield Comparison Similarity Scores". The x-axis is labeled "Greater than 150 Without Ethanol", and the y-axis is labeled "30 to 150 With Ethanol". The plot shows a positive correlation between the two variables, with a slope of 0.91, an intercept of 0.61, and an R-value of 0.94. The data was collected on Nov. 22, 2011.

Additionally, a Bland Altman plot was made comparing the difference between the highest similarity scores for the ≥150 ng RNA runs and the highest similarity score for the 30-150 ng runs to the average for these two similarity scores. The mean value of the difference was 4 and no trends were observed.

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

Image /page/7/Figure/0 description: This image is a scatter plot titled "Greater than 150 without Ethanol, 30 to 150 with Ethanol (n = 43)". The x-axis is labeled "Average Truth Similarity Score", and the y-axis is labeled "Difference in Truth Similarity Scores". The plot shows a series of points scattered across the graph, with a mean of 4.0. The plot also shows that 9.3% of points are outside 95% limits, and CR is 40.8.

Conclusion: the procedure changes have not changed the performance of the : Test.

807.92 (b)(2): Brief Description of Clinical Data

No clinical data is provided in this 510(k).

807.92 (b)(3): Conclusions from Clinical Testing

No clinical testing was provided in this 510(k)

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

DEPARTMENT OF HEALTH & HUMAN SERVICES

Image /page/8/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo consists of a circular seal with the text "DEPARTMENT OF HEALTH & HUMAN SERVICES • USA" around the perimeter. Inside the circle is an abstract symbol resembling a stylized caduceus or a series of flowing lines, possibly representing health and human services.

Food and Drug Administration 10903 New Hampshire Avenue Silver Spring, MD 20993

MAY 1 7 2012

Pathwork Diagnostics, Inc. c/o Anna Longwell Regulatory consultant to Pathwork Diagnostics, Longwell & Associates 595 Penobscot Drive Redwood City, CA 94063

Re: K120489

Trade/Device Name: Pathwork® Tissue of Origin Test Kit - FFPE Regulation Number: 21 CFR § 862.3100 Regulation Name: Amphetamine Test System Regulatory Class: Class II Product Code: OIW Dated: February 15, 2012 Received: February 17, 2012

Dear Ms. Longwell:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. The general morely manisons of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration.

If your device is classified (see above) into class II (Special Controls), it may be subject to such additional controls. Existing major regulations affecting your device can be found in Title 21, Code of Federal Regulations (CFR), Parts 800 to 895. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act of thur Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); an the Act s requirements) and 809); medical device reporting of medical device-related labering (21 CFR 803); and good manufacturing practice requirements as set forth in the adverse overns (QS) regulation (21 CFR Part 820). This letter will allow you to begin marketing

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

· Page2 - Ms. Longwell

your device as described in your Section 510(k) premarket notification. The FDA finding of substantial equivalence of your device to a legally marketed predicate device results in a classification for your device and thus, permits your device to proceed to the market.

If you desire specific advice for your device on our labeling regulation (21 CFR Parts 801 and 809), please contact the Office of In Vitro Diagnostic Device Evaluation and Safety at (301) 796-5450. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to

http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

You may obtain other general information on your responsibilities under the Act from the Division of Small Manufacturers, International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address http://www.fda.gov/cdrh/industry/support/index.html.

Sincerely yours,

for Reena Philip
Maria M. Chan, Ph.D.

Maria M. Chan, Ph.D. Director Division of Immunology and Hematology Devices Office of In Vitro Diagnostic Device Evaluation and Safety Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known):

Device Name: Pathwork® Tissue of Origin Test Kit-FFPE

Indications For Use:

Limitations: The Pathwork® Tissue of Origin Test is not intended to establish the origin of tumors (e.g. cancer of unknown primary) that cannot be diagnosed according to current clinical and pathological practice. It is not intended to subclassify or modify the classification of tumors that can be diagnosed by current clinical and pathological practice, nor to predict disease course or survival or treatment efficacy, nor to distinguish primary from metastatic tumor. Tumor types not in the Pathwork Tissue of Origin Test database may have RNA expression patterns that are similar to patterns in the database; therefore, results cannot be used to distinguish tumor types in the database from tumor types not in the database.

× Prescription Use (Part 21 CFR 801 Subpart D) AND/OR

Over-The-Counter Use (21 CFR 807 Subpart C)

(PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE IF NEEDED)

Concurrence of CDRH, Office of In Vitro Diagnostic Devices (OIVD)

Division Sign-Off

Office of In Vitro Diagnostic Device Evaluation and Safety

510K K12-0489

Page 1 of 1

Regulation Number and Section

§ 862.3100 Amphetamine test system.

(a)
Identification. An amphetamine test system is a device intended to measure amphetamine, a central nervous system stimulating drug, in plasma and urine. Measurements obtained by this device are used in the diagnosis and treatment of amphetamine use or overdose and in monitoring levels of amphetamine to ensure appropriate therapy.(b)
Classification. Class II (special controls). An amphetamine test system is not exempt if it is intended for any use other than employment or insurance testing or is intended for Federal drug testing programs. The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9, provided the test system is intended for employment and insurance testing and includes a statement in the labeling that the device is intended solely for use in employment and insurance testing, and does not include devices intended for Federal drug testing programs (e.g., programs run by the Substance Abuse and Mental Health Services Administration (SAMHSA), the Department of Transportation (DOT), and the U.S. military).