The Roche cobas c 111 analyzer is an in-vitro diagnostic analyzer capable of performing clinical chemistry, specific protein and electrolyte tests in the professional setting and small laboratories, specialized testing and CLIA-licensed doctor's offices. Analytes are measured photometrically or turbidimetrically; the analyzer also has an optional ISE module for measuring sodium, potassium and chloride.
Device Story
Cobas c 111 analyzer performs clinical chemistry, specific protein, and electrolyte testing. Inputs: human serum, plasma, or urine samples. Operation: photometric/turbidimetric assays or optional ion-selective electrode (ISE) module. Output: quantitative analyte concentrations. Used in professional settings, small labs, and CLIA-licensed doctor's offices by trained technicians. Healthcare providers use results for diagnosis and monitoring of liver/heart disease, diabetes, tissue injury, and electrolyte imbalances. System provides automated analysis to support clinical decision-making at point-of-care.
Clinical Evidence
Bench testing only. Performance evaluated via method comparison studies (n=280-333) against the Integra 400 analyzer, demonstrating high correlation (Passing Bablok regression). Precision studies (within-run and total CV%) conducted on human sera and controls for all analytes (AST, Glucose, CRP, ISE-Cl/K/Na). Interference studies confirmed no significant impact from common drugs, bilirubin, hemolysis, or lipemia within specified limits.
Technological Characteristics
Photometric/turbidimetric analyzer with optional ISE module. Reagents include enzymes (MDH, hexokinase, G6PDH), latex particles, and buffers. ISE module uses neutral carrier (Na, K) and ion exchanger (Cl) electrodes. Standardized against IFCC, ID/MS, or gravimetric primary calibrators. Complies with CLSI EP5-A for precision.
Indications for Use
Indicated for professional use in small labs, specialized testing, and CLIA-licensed doctor's offices for quantitative determination of AST, glucose, CRP, sodium, potassium, and chloride in human serum, plasma, and urine (electrolytes only). Used for diagnosis/treatment of liver/heart disease, carbohydrate metabolism disorders, tissue injury, and electrolyte/metabolic disorders.
Regulatory Classification
Identification
An aspartate amino transferase (AST/SGOT) test system is a device intended to measure the activity of the enzyme aspartate amino transferase (AST) (also known as a serum glutamic oxaloacetic transferase or SGOT) in serum and plasma. Aspartate amino transferase measurements are used in the diagnosis and treatment of certain types of liver and heart disease.
Special Controls
*Classification.* Class II (special controls). 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.
{0}
1
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
ASSAY ONLY TEMPLATE
A. 510(k) Number:
k071211
B. Purpose for Submission:
To extend the indications for use claim to include use at point of care sites
C. Measurand:
Aspartate aminotransferase (AST)
Glucose
C-reactive protein (CRP)
Chloride
Potassium
Sodium
D. Type of Test:
Photometric, turbidimetric or ion selective quantitative assays
E. Applicant:
Roche Diagnostics Corp.
F. Proprietary and Established Names:
Cobas c 111 analyzer
Aspartate aminotransferase (ASTL/ASTPL)
C-Reactive Protein Latex (CRPLX)
Glucose HK (GLUC2)
ISE Chloride Electrode
ISE Potassium Electrode
ISE Sodium Electrode
G. Regulatory Information:
{1}
| Product Code | Classification | | Regulation Section | Panel |
| --- | --- | --- | --- | --- |
| CIT | II | Aspartate amino transferase (AST/SGOT) test system | 21 CFR 862.1100 | 75 Clinical Chemistry |
| CFR | II | Glucose test system | 21 CFR 862.1345 | 75 Clinical Chemistry |
| DCN | II | C-reactive protein immunological test system | 21 CFR 866.5270 | 81 Immunology |
| CEM | II | Potassium test system | 21 CFR 862.1600 | 75 Clinical Chemistry |
| CGZ | II | Chloride test system | 21 CFR 862.1170 | 75 Clinical Chemistry |
| JGS | II | Sodium test system | 21 CFR 862.1665 | 75 Clinical Chemistry |
| JJE | Class I | Discrete photometric chemistry analyzer | 21 CFR 862.2160 | 75 Clinical Chemistry |
H. Intended Use:
1. Intended use(s):
See indications for use below.
2. Indication(s) for use:
cobas c 111 analyzer:
The Roche cobas c 111 analyzer is an in-vitro diagnostic analyzer capable of performing clinical chemistry, specific protein and electrolyte tests for professional settings and small laboratories, specialized testing and CLIA-licensed doctor's offices.
Analytes are measured photometrically or turbidimetrically; the analyzer also has an optional ISE module for measuring sodium, potassium and chloride.
Reagents:
Aspartate aminotransferase (ASTL/ASTPL)
In vitro test for the quantitative determination of AST in human serum and plasma
{2}
on the cobas c111 system. Aspartate amino transferase measurements are used in the diagnosis and treatment of certain types of liver and heart disease.
## C-Reactive Protein Latex (CRPLX)
In vitro test for the quantitative immunological determination of human C-reactive protein in human serum and plasma on the cobas c111 system.
Measurement of C-reactive protein aids in evaluation of the amount of injury to body tissues.
## Glucose HK (GLUC2)
In vitro test for the quantitative determination of glucose concentration in human serum and plasma on the cobas c111 system. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus and idiopathic hypoglycemia.
## ISE Chloride Electrode
The chloride electrode for the cobas c111 system is intended for the quantitative determination of chloride in diluted serum, plasma, and urine. Chloride measurements are used in the diagnosis and treatment of electrolyte and metabolic disorders such as cystic fibrosis and diabetic acidosis.
## ISE Potassium Electrode
The potassium electrode for the cobas c111 system is intended for the quantitative determination of potassium in diluted serum, plasma, and urine. Measurements of potassium are used to monitor electrolyte balance in the diagnosis and treatment of diseases conditions characterized by low or high blood potassium levels.
## ISE Sodium Electrode
The sodium electrode for the cobas c111 system is intended for the quantitative determination of sodium in diluted serum, plasma, and urine. Measurements of sodium are used in the diagnosis and treatment of aldosteronism (excessive secretion of the hormone aldosterone), diabetes insipidus (chronic excretion of large amounts of dilute urine, accompanied by extreme thirst), adrenal hypertension, Addison's disease (caused by destruction of the adrenal glands), dehydration, inappropriate antidiuretic hormone secretion, or other diseases involving electrolyte imbalance.
## 3. Special conditions for use statement(s):
Prescription use only
## 4. Special instrument requirements:
Roche Diagnostics cobas c 111
{3}
I. Device Description:
The Roche cobas c 111 analyzer is an in-vitro diagnostic analyzer capable of performing clinical chemistry, specific protein and electrolyte tests for professional settings and small laboratories, specialized testing and CLIA-licensed doctor’s offices. Analytes are measured photometrically or turbidimetrically; the analyzer also has an optional ISE module for measuring sodium, potassium and chloride.
Aspartate aminotransferase (ASTL/ASTPL) reagent consists of a primary reagent containing l-aspartate, malate dehydrogenase (MDH) from porcine heart, albumin (bovine), TRIS buffer and preservative. The reagent also contains pyridoxal phosphate (PYP) and NADH, 2-oxoglutarate, preservatives and additives.
The Glucose HK (GLUC2) reagent is a dual reagent system. Reagent 1 consists of TRIS buffer, NADP and preservatives. Reagent 2 consists of HEPES buffer, hexokinase (yeast) and glucose-6-phosphate dehydrogenase.
The C-reactive Protein latex (CRPLX) is a dual reagent system. Reagent 1 consists of TRIS buffer with bovine serum albumin and immunoglobulins (mouse) and preservatives. Reagent 2 is latex particles coated with anti-CRP (mouse) in glycine buffer and preservatives.
The Sodium, Potassium and Chloride ISE Electrode are comprised of the ISE solution 1 or 2 (volume dependant), indirect calibrator, ISE reference solution, activator, ISE deproteinizer and ISE etcher.
J. Substantial Equivalence Information:
1. Predicate device name(s) and k numbers:
Cobas c 111 analyzer -k051595
Aspartate Aminotransferase (AST) -k951595
Glucose Gen. 2 (GLUC2) -k980996
CRP Latex (CRPLX) -k981897
Chloride electrode (ISE-Cl) -k963627
Potassium electrode (ISE-K) -k963627
Sodium electrode (ISE-Na) -k963627
{4}
2. Predicate 510(k) number(s):
See 1 above.
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Intended use for the reagents | AST: In vitro test for the quantitative determination of aspartate aminotransferase (AST) in human serum and plasma on the cobas c 111 system.
Glucose: In vitro test for the quantitative determination of glucose in human serum and plasma on the cobas c 111 system.
CRP: In vitro test for the quantitative determination of C-reactive protein in human serum and plasma on the cobas c 111 system.
ISE-CI: The chloride electrode for the cobas c 111 system is intended for the quantitative determination of chloride in diluted serum, plasma and urine.
ISE-K: The potassium electrode for the cobas c 111 system is intended for the quantitative determination of chloride in diluted serum, plasma and urine.
ISE-Na: The sodium electrode for the cobas c 111 system is intended for the quantitative determination of chloride in diluted serum, plasma and urine. | Same |
| Instrument | Cobas c 111 | Same |
| Sample Type | AST: serum and plasma
Glucose: serum and plasma
CRP: serum and plasma | Same |
5
{5}
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| | ISE-CI: serum, plasma and urine
ISE-K: serum, plasma and urine
ISE-Na: serum, plasma and urine | |
| Traceability/Standardization | AST: standardized against the original IFCC formulation using calibrated pipettes together with manual photometer providing absolute values and the substrate-specific absorptivity, Glucose: standardized against ID/MS
CRP: standardized against the reference preparation of the IRMM – BCR470/CRM470 (RPPHS – Reference Preparation for Proteins in Human Serum)
ISE-CI/K/Na: standardized against primary calibrators prepared gravimetrically from purified salts | Same |
| Measuring range | AST: 2-700 U/L
Glucose: 0.11-40 mmol/L
CRP: 1-200 mg/L
ISE-CI: 20-250 mmol/L
ISE-K: 1-100 mmol/L
ISE-Na: 20-250 mmol/L | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Intended use modified | The Roche cobas c111 analyzer is an in-vitro diagnostic analyzer capable of performing clinical chemistry, specific protein and electrolyte tests. | The Roche cobas c111 analyzer is an in-vitro diagnostic analyzer capable of performing clinical chemistry, specific protein and electrolyte tests in the professional setting and small laboratories, specialized testing and CLIA-licensed doctor's office. |
| Operators | Professional setting | Point-of-care setting |
| | | |
{6}
7
K. Standard/Guidance Document Referenced (if applicable):
CLSI EP5-A – Evaluation of Precision Performance of Quantitative Measurement Methods
L. Test Principle:
The aspartate aminotransferase (ASTL) assay uses enzymatic activation. AST in a sample catalyzed the transfer of an amino group between L-aspartate and 2-oxoglutarate to form oxaloacetate and L-glutamate. The oxaloacetate then reacts with NADH, in the presence of malate dehydrogenase (MDH), to form NAD+. Pyridoxal phosphate serves as a coenzyme in the amino transfer reaction. The rate of the NADH oxidation is directly proportional to the catalytic AST activity. It is determined by measuring the decrease in absorbance.
The glucose hexokinase (GLUC2) assay is a UV test with enzymatic reference method that utilizes hexokinase. The hexokinase catalyzes the phosphorylation of glucose to glucose-6-phosphate by ATP. Glucose-6-phosphate dehydrogenase oxidizes glucose-6-phosphate in the presence of NAHP to gluconate-6-phosphate. The rate of NADPH formation during the reaction is directly proportional to the glucose concentration and is measured photometrically.
The C-reactive protein (latex) (CRPLX) is a particle enhanced turbidimetric assay. Human CRP agglutinates with latex particles coated with monoclonal anti-CRP antibodies. The precipitate is determined turbidimetrically.
The sodium, potassium and chloride ion-selective electrode (ISE) have a selective membrane in contact with both the test solution and an internal filling solution. The internal filling solution contains the test ion at a fixed concentration. The membrane EMF is determined by difference in concentration of the test ion in the test solution and the internal filling solution. The EMF develops according to the Nerst equation for a specific ion in solution. The complete measurement system for a particular ion includes the ISE, a reference electrode and electronic circuits to measure and process the EMF to give the test ion concentration. The sodium and potassium electrodes are based on neutral carriers and the chloride electrode is based on an ion exchanger.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
Within-run precision studies were conducted in three physician office laboratories (POL) using trained medical technicians to test for potential systematic and random error. Two controls materials and two sample pools (prepared daily) were run in triplicates for 9 to 15 days (site-dependant) at two
{7}
US sites and one European site.
The sponsor also conducted an imprecision study according to modified CLSI EP5-A. Two controls and two human serum pools (normal and evaluated) were run in triplicate for twenty-one days in one US and one foreign site. The second US site conducted the study with the two controls and two human serum pools in triplicate twice a day for ten days.
The combined results from all three POL sites and materials are shown in the combined tables below:
Within-Run Controls
| Assay | POL sites concentration (mean) | | POL sites (range % CV or SD (unit)) | | Hospital Sites concentration (mean) | | Hospital Sites (average % CV or SD (unit)) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | PNU | PPU | PNU | PPU | PNU | PPU | PNU | PPU |
| AST (U/L) | 41.1 | 137.9 | 1.1–3.6% | 0.4-0.9% | 41.4 | 138.9 | 2.19 | 0.93 |
| GLUC (mg/dL) | 96.1 | 255.5 | 0.3-1.0% | 0.5-1.2% | 94.0 | 250.4 | 0.50 | 0.33 |
| CRP (mg/dL) | 0.8 | 4.8 | 0.3-0.9% | 0.3-0.5% | 0.8 | 4.7 | 0.86 | 0.37 |
| Sodium (mmol/L) | 126.7 | 149.9 | 0.2-1.0% | 0.2-0.5% | 128.0 | 152.4 | 0.42 | 0.36 |
| Potassium (mmol/L) | 3.5 | 6.6 | 0.2-1.2% | 0.012-0.109 SD | 3.5 | 6.7 | 0.41 | SD 0.03 |
| Chloride (mmol/L) | 86.2 | 118.5 | 0.23-0.64 SD | 0.24-0.99% | 87.8 | 120.8 | SD 0.43 | 0.37 |
PNU= PreciNorm Universal Control, PPU=PreciPath Universal Control
Within-Run Human Samples
| | POL sites concentration (mean) | | POL sites (range % CV or SD (unit)) | | Hospital Sites concentration (mean) | | Hospital Sites (ge % CV or SD(unit)) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | HS 1 | HS2 | HS 1 | HS2 | HS 1 | HS2 | HS 1 | HS2 |
| AST (U/L) | 19.0 | 46.9 | 0.46-1.48 SD | 0.8-5.2% | 19.5 | 188.5 | SD 0.85 | 0.69 |
| GLUC (mg/dL) | 89.1 | 168.3 | 0.2-1.1% | 0.4-0.9% | 86.2 | 216.8 | 0.39 | 0.48 |
| CRP (mg/dL) | 0.6 | 2.4 | 1.1-2.3% | 0.6-2.1% | 0.7 | 7.1 | SD 0.007 | 0.57 |
| Sodium (mmol/L) | 144.0 | 134.2 | 0.2-0.5% | 0.2-0.4% | 137.2 | 146.4 | 0.46 | 0.49 |
| Potassium (mmol/L) | 4.5 | 4.5 | 0.3-0.7% | 0.3-0.5% | 4.2 | 5.3 | 0.42 | 0.49 |
| Chloride (mmol/L) | 104.5 | 97.9 | 0.2-0.5% | 0.2-0.6% | 102.9 | 113.4 | 0.43 | 0.48 |
HSP1=Human Serum Pool 1 (normal), HSP2= Human Serum Pool 2 (elevated).
{8}
Total Controls
| Assay | POL sites concentrations (mean) | | POL sites (range % CV or SD (unit)) | | Hospital Sites concentrations (mean) | | Hospital Sites (average % CV or SD (unit)) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | PNU | PPU | PNU | PPU | PNU | PPU | PNU | PPU |
| AST (U/L) | 40.2 | 137.0 | 2.9-3.8% | 1.7-2.8% | 41.6 | 139.6 | 3.2 | 1.7 |
| Glucose (mg/dL) | 93.0 | 247.1 | 1.6-4.1% | 1.4-4.1% | 91.7 | 244.4 | 1.0 | 0.9 |
| CRP (mg/dL) | 0.8 | 4.8 | 1.6-4.2% | 1.2-5.1% | 0.8 | 4.7 | 1.5 | 1.3 |
| Sodium (mmol/L) | 126.5 | 151.0 | 1.6-1.9% | 1.5-2.0% | 125.3 | 149.8 | 0.9 | 1.0 |
| Potassium (mmol/L) | 3.4 | 6.6 | 1.7-1.8% | 0.1-0.2SD | 3.4 | 6.6 | 1.1 | SD 0.07 |
| Chloride (mmol/L) | 87.2 | 120.0 | 1.5-2.1 SD | 1.6-3.0% | 85.6 | 118.5 | SD 0.9 | 1.0 |
PNU= PreciNorm Universal Control, PPU=PreciPath Universal Control
Total Human Samples
| Assay | POL sites concentrations (mean) | | POL sites (range % CV) | | Hospital Sites concentrations (mean) | | Hospital Sites (average % CV or SD (unit)) | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | HS I | HS 2 | HS I | HS 2 | HS 1 | HS 2 | HS I | HS 2 |
| AST (U/L) | 16.4 | 48.7 | 0.9-1.8 SD | 2.5-3.8% | SD 1.2 | 3.7 | SD 1.3 | 2.9 |
| Glucose (mg/dL) | 97.5 | 130.7 | 1.8-4.3% | 1.9-4.6% | 2.6 | 2.8 | 1.2 | 2.2 |
| CRP (mg/dL) | 4.1 | 4.7 | 3.3-3.7% | 2.8-3.4% | 3.7 | 3.2 | SD 0.01 | 1.5 |
| Sodium (mmol/L) | 139.9 | 131.6 | 1.5-1.9% | 1.5-1.7% | 1.6 | 1.6 | 1.2 | 1.4 |
| Potassium (mmol/L) | 4.5 | 4.5 | 1.2-1.8% | 1.4-1.8% | 1.4 | 1.6 | 1.0 | 1.1 |
| Chloride (mmol/L) | 104.7 | 104.6 | 1.3-1.5% | 1.4-1.8% | 1.4 | 1.6 | 0.9 | 0.8 |
HSP1=Human Serum Pool 1 (normal), HSP2= Human Serum Pool 2 (elevated).
b. Linearity/assay reportable range:
Previously established for predicate devices.
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Previously established for predicate devices.
d. Detection limit:
{9}
Previously established for predicate devices.
e. Analytical specificity:
Previously established for predicate devices.
f. Assay cut-off:
Previously established for predicate devices.
2. Comparison studies:
a. Method comparison with predicate device:
A method comparison study was performed at three Point-of-Care sites using serum and plasma samples. Each site ran seven fresh human samples each day for 20 days (8 samples in the US for 6 to 10 days) on the cobas c 111 (y) and the cobas integra 400 (x).
The following is the comparison from the three point-of-care sites.
AST:
Passing Bablok:
y = 0.989x + 1.276 U/L
τ = 0.8316
r = 0.9906
range = 93-286.48 U/L
n = 333
Glucose:
y = 0.997x + 2.069 mg/dL
τ = 0.9217
r = 0.9954
range = 42.4-404.80 mg/dL
n = 333
CRP:
y = 1.058x + 0.022 mg/L
τ = 0.9789
r = 0.9988
range = 0.010-75/990 mg/L
n = 326
10
{10}
ISE-Cl:
y = 1.011x - 0.51 mmol/L
τ = 0.7532
r = 0.9243
range= 65.20-111.90 mmol/L
n = 280
ISE-K:
y = 0.943x + 0.189 mmol/L
τ = 0.8835
r = 0.9824
range= 2.950-8.290 mmol/L
n = 280
ISE-Na:
y = 1.064x - 9.818 mmol/L
τ = 0.6920
r = 0.9366
range= 87.9-146.4 mmol/L
n = 280
b. Matrix comparison:
Previously established for predicate devices.
3. Clinical studies:
a. Clinical Sensitivity:
Previously established for predicate devices.
b. Clinical specificity:
Previously established for predicate devices.
c. Other clinical supportive data (when a. and b. are not applicable):
Previously established for predicate devices.
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
Previously established for predicate devices.
{11}
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
12
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.