CRYSTALENS MODEL AT-45 ACCOMMODATING POSTERIOR CHAMBER INTRAOCULAR LENS (IOL)
P030002 · Bausch & Lomb, Inc. · NAA · Nov 14, 2003 · Ophthalmic
Device Facts
Record ID
P030002
Device Name
CRYSTALENS MODEL AT-45 ACCOMMODATING POSTERIOR CHAMBER INTRAOCULAR LENS (IOL)
Applicant
Bausch & Lomb, Inc.
Product Code
NAA · Ophthalmic
Decision Date
Nov 14, 2003
Decision
APPR
Regulation
21 CFR 886.3600
Device Class
Class 3
Attributes
Therapeutic, Expedited Review
Indications for Use
The crystalens™ Model AT-45 Accommodating IOL is intended for primary implantation in the capsular bag of the eye for the visual correction of aphakia in adult patients in whom a cataractous lens has been removed and is intended to provide near, intermediate, and distance vision without spectacles. The crystalens™ IOL provides approximately one diopter of monocular accommodation.
Device Story
Modified plate haptic intraocular lens (IOL) with polyimide loops and hinges; designed for primary implantation in the capsular bag. Provides approximately one diopter of monocular accommodation to assist with near and intermediate vision. Implanted by ophthalmologists during cataract surgery. Benefits include reduced spectacle dependency for daily activities. Clinical performance evaluated via visual acuity, contrast sensitivity, and patient surveys.
Clinical Evidence
Prospective, nonrandomized study of 324 subjects (497 eyes) followed for one year. Primary endpoints: visual acuity at near, intermediate, and distance; contrast sensitivity; and patient survey. Results: 93.5% of bilateral subjects achieved 20/32 or better uncorrected visual acuity at near, intermediate, or distance. Contrast sensitivity showed no statistically significant difference compared to standard monofocal IOLs. Adverse event rates were comparable to or lower than historical controls.
Technological Characteristics
Modified plate haptic lens; polyimide loops; hinges adjacent to optic. Biconvex optic, 4.5 mm diameter. Overall length 11.5 mm (loop tip to loop tip). A-Constant 119.24. Designed for capsular bag placement.
Indications for Use
Indicated for adult patients with aphakia following cataract removal. Provides near, intermediate, and distance vision correction.
Regulatory Classification
Identification
An intraocular lens is a device made of materials such as glass or plastic intended to be implanted to replace the natural lens of an eye.
Submission Summary (Full Text)
{0}
# SUMMARY OF SAFETY AND EFFECTIVENESS DATA
## I. GENERAL INFORMATION
Device Generic Name: Monofocal Posterior Chamber Accommodating Intraocular Lens (IOL)
Device Trade Name: crystalens™ Model AT-45 Accommodating Intraocular Lens
Applicant's Name and Address:
eyeonics inc. (formerly C&C Vision)
6 Journey, Suite 125
Aliso Viejo, CA 92656
Date(s) of Panel Recommendation: May 23, 2003
Premarket Approval Application (PMA) Number: P030002
Date of Notice of Approval to Applicant: November 14, 2003
## II. INDICATIONS FOR USE
The crystalens™ Model AT-45 Accommodating IOL is intended for primary implantation in the capsular bag of the eye for the visual correction of aphakia in adult patients in whom a cataractous lens has been removed and is intended to provide near, intermediate, and distance vision without spectacles. The crystalens™ IOL provides approximately one diopter of monocular accommodation.
## III. CONTRAINDICATIONS
None known.
## IV. WARNINGS AND PRECAUTIONS
The warnings and precautions can be found in the crystalens™ IOL labeling.
## V. DEVICE DESCRIPTION
The crystalens™ IOL is a modified plate haptic lens with polyimide loops and hinges across the plates adjacent to the optic. The overall length of the lens is 11.5 mm (loop tip to loop tip measurement), while the length as measured from the ends of the plate haptics is 10.5 m. The lens optic is biconvex, 4.5 mm in diameter, with an A-Constant of 119.24,
SSED
crystalens™ Model AT-45 Accommodating IOL
page 1
{1}
and is designed for placement into the capsular bag.
## VI. ALTERNATIVE PRACTICES OR PROCEDURES
Multifocal IOLs are used for the visual correction of aphakia and may also provide near, intermediate and distance vision without spectacles.
## VII. MARKETING HISTORY
The crystalens™ IOL has been marketed in over 10 countries, including Belgium, Brazil, Germany, Greece, Italy, Mexico, Portugal, Singapore, Spain, Switzerland, Saudi Arabia, and the United Kingdom. The crystalens™ has not been withdrawn from any market for reasons relating to safety and effectiveness of the device.
## VIII. POTENTIAL ADVERSE EFFECTS OF THE DEVICE ON HEALTH
The adverse events experienced during the clinical trial of the crystalens™ IOL included persistent iritis (<1.0%), persistent cystoid macular edema (<1.0%), and cumulative cystoid macular edema (3.7%). The incidence of adverse events was comparable to or lower than the incidence reported in the historical control (“FDA grid”) population (Table 1).
Table 1
Adverse Events Reported at 12 months
| Adverse Event | Cumulative | FDA Grid | Persistent | FDA Grid |
| --- | --- | --- | --- | --- |
| Endophthalmitis | 1/324 (0.3%) | 0.1% | --- | --- |
| Hyphema | 1/324 (0.3%) | 2.2% | --- | --- |
| Hypopyon | 0/324 | 0.3% | --- | --- |
| IOL Dislocation | 0/324 | 0.1% | --- | --- |
| Cystoid Macular Edema | 12/324 (3.7%) | 3.0% | 2/304 (0.7%) | 0.5% |
| Pupillary Block | 0/324 | 0.1% | --- | --- |
| Retinal Detachment | 0/324 | 0.3% | --- | --- |
| Secondary Surgical Reintervention | 2/324 (0.6%) | 0.8% | --- | --- |
| Corneal Edema | --- | | 0/298 | 0.3% |
| Iritis | --- | | 2/298 (0.7%) | 0.3% |
| Raised IOP Requiring Treatment | --- | | 0/304 | 0.4% |
SSED
crystalens™ Model AT-45 Accommodating IOL
page 2
{2}
Potential adverse events which did not occur in this clinical trial, but which may accompany cataract or implant surgery include, but are not limited to, the following: corneal endothelial damage, non-pigment precipitates, infection, retinal detachment, vitreous wick syndrome, uveitis and pupillary membrane. No cases of hypopyon or acute corneal decompensation were reported during the clinical study.
Potential secondary surgical interventions that have been associated with intraocular lenses, but did not occur in this clinical trial include: lens removal due to corneal touch, lens removal due to inflammation, corneal transplant, vitreous aspiration for pupillary block, iridectomy for pupillary block.
## IX. SUMMARY OF PRECLINICAL STUDIES
Preclinical studies on this device that are consistent with the FDA draft guidance document for testing intraocular lenses dated October 14, 1999 were performed. The applicant conducted a battery of *in vivo* and *in vitro* acute and chronic toxicity tests that establish the biocompatibility of the lens materials. These studies, combined with data from chemistry and engineering analyses, demonstrate the suitability of the material and overall device design for use in an intraocular lens. The adequacy of the manufacturing processes, including sterilization, was established through review of the manufacturing information in the PMA as well as through on-site inspections. Preclinical testing demonstrates the safety and effectiveness of this device from microbiology, toxicology, engineering, and manufacturing perspectives.
## X. SUMMARY OF CLINICAL STUDIES
Objectives. The objectives of the clinical studies were to assess the safety and effectiveness of the crystalens™ IOL for the visual correction of aphakia in adult patients in whom a cataractous lens has been removed and assess its ability to provide near, intermediate, and distance vision without spectacles.
### Study Design
The crystalens™ IOL was evaluated in a prospective, nonrandomized study of 324 subjects followed for one year. The range of axial lengths studied in the clinical trial was 21.0 to 26.6 mm and the dioptric power range was 16.5 to 27.5 D. The clinical results were obtained using an ‘A’ Constant of 119.0, the SRK/T formula, immersion biometry or interferometry and manual keratometry. Inclusion criteria required visual potential to be 20/30 or better in the operative eye, 1.00 D or less of corneal astigmatism, an intact capsular bag and zonules after cataract extraction and before implantation of the lens.
The clinical effectiveness endpoint was visual performance at near, intermediate and distance.
SSED
crystalens™ Model AT-45 Accommodating IOL
page 3
{3}
# Gender Bias
The population at risk for developing visually-disabling cataracts and needing cataract surgery is typically elderly; the elderly population has a slightly higher proportion of females to males. The average age of the 324 subjects (497 eyes) was 69.7 years at the time of surgery; 55.9% of the 324 subjects were female and 44.1% were male. The inclusion/exclusion criteria did not exclude patients on the basis of gender or gender-related pathology. The study population was more than 90% Caucasian; 1.2% African-American, 6.8% were Hispanic and less than 1% was Asian. All patients who met the inclusion criteria were included in the study.
# Patient Assessments
Clinical evaluations included visual acuity, contrast sensitivity, subject survey and ophthalmic examinations to determine adverse event rates.
Uncorrected and distance corrected visual acuities were determined at near, intermediate and distance for all bilateral subjects. Distance corrected visual acuities were determined at near, intermediate and distance for all unilateral subjects. Uncorrected visual acuities were determined at near and distance for all unilateral subjects. A subset of the subjects was compared to subjects with standard monofocal IOLs for visual acuity at all distances.
A contrast sensitivity substudy was conducted to address concerns related to the 4.5 mm optic of the crystalens™ IOL. The substudy compared the crystalens™ IOL with a control group comprised of several models of standard monofocal IOLs of varying types (e.g., single piece, multipiece) and materials (e.g., silicone, acrylic). Contrast sensitivity was performed with a cohort of 126 crystalens™ IOL subjects and a matched control group of 64 eyes implanted with several models of standard IOLs. Testing was performed at the 3 to 6 month postoperative exam (Form 4) or later, under mesopic light conditions, in order to simulate vision in the presence of poor illumination and a large pupil. The luminance level employed was 3 cd/m² and the glare stimulus was 3 lux.
A subject survey substudy included one hundred and twenty-eight bilaterally implanted subjects who were asked at the one-year post-operative visit to assess their dependency on spectacles and to evaluate their night vision. Subjects were also asked to evaluate their daily lifestyle activities without spectacles.
# Data Analysis and Results
The bilateral postoperative uncorrected visual acuity results for the crystalens™ IOL at near, intermediate and distance are shown in Table 2. Of the subjects implanted bilaterally, 93.5% achieve visual acuities of 20/32 or better uncorrected at near, distance or intermediate one year after surgery.
SSED
crystalens™ Model AT-45 Accommodating IOL
page 4
{4}
Table 2
Bilateral – Uncorrected Visual Acuity
| | Near at 40 cm | | Intermediate at 80 cm | | Distance | |
| --- | --- | --- | --- | --- | --- | --- |
| 20/20 or better | 39/124 | 31.5% | 120/124 | 96.8% | 98/123 | 79.7% |
| 20/25 or better | 90/124 | 72.6% | 122/124 | 98.4% | 113/123 | 91.9% |
| 20/32 or better | 116/124 | 93.5% | 124/124 | 100% | 120/123 | 97.6% |
| 20/40 or better | 122/124 | 98.4% | 124/124 | 100% | 121/123 | 98.4% |
| Worse than 20/40 | 2/124 | 1.6% | 0/124 | 0% | 2/123 | 1.6% |
Table 3 shows the uncorrected visual acuity for a subset of the bilateral subjects in the study that were within ±0.5D of plano in each eye. Uncorrected visual acuities of 20/32 or better at near, distance or intermediate one year after surgery improved to 97.3% of the subjects when within 0.5D of plano in each eye.
Table 3
Bilateral – Uncorrected Visual Acuity for Patients
within ±0.5D of Plano in Each Eye
| | Near at 40 cm | | Intermediate at 80 cm | | Distance | |
| --- | --- | --- | --- | --- | --- | --- |
| 20/20 or better | 17/74 | 23.0% | -- | -- | 67/74 | 90.5% |
| 20/25 or better | 49/74 | 66.2% | 74/74 | 100% | 73/74 | 98.6% |
| 20/32 or better | 72/74 | 97.3% | 74/74 | 100% | 74/74 | 100% |
| 20/40 or better | 74/74 | 100% | 74/74 | 100% | 74/74 | 100% |
| Worse than 20/40 | 0/74 | 0% | 0/74 | 0% | 0/74 | 0% |
Table 4 shows the unilateral results for subjects implanted with the crystalcns™ IOL. Uncorrected visual acuities of 20/40 or better at near or distance one year after surgery were reported in more than 89% of the subjects.
Table 4
Unilateral – Uncorrected Visual Acuity (All Eyes)
| | Near at 40 cm | | Intermediate at 80 cm | | Distance | |
| --- | --- | --- | --- | --- | --- | --- |
| 20/20 or better | 52/368 | 14.1% | -- | -- | 184/371 | 49.6% |
| 20/25 or better | 161/368 | 43.8% | -- | -- | 269/371 | 72.5% |
| 20/32 or better | 256/368 | 69.6% | -- | -- | 311/371 | 83.8% |
| 20/40 or better | 328/368 | 89.1% | -- | -- | 339/371 | 91.4% |
| Worse than 20/40 | 40/368 | 10.9% | -- | -- | 32/371 | 8.6% |
Table 5 shows the unilateral results for the subset of subjects implanted with the crystalcns™ IOL compared to the unilateral results for subjects with the standard monofocal IOL (these were the subjects in the contrast sensitivity substudy). Distance
SSED
crystalcns™ Model AT-45 Accommodating IOL
page 5
{5}
corrected visual acuities of 20/40 or better at near, intermediate and distance 3-6 months or more after surgery were reported in 88.4% of the subjects with the crystalens™ IOL and 35.9% of the subjects implanted with the standard monofocal IOL.
Table 5
crystalens™ IOL vs. Standard IOL Distance Corrected Visual Acuity at All Distances (Distance, Near and Intermediate)
| | crystalens™ | | Standard IOL | |
| --- | --- | --- | --- | --- |
| 20/20 or better | 1/121 | 0.8% | 0/64 | 0.0% |
| 20/25 or better | 29/121 | 24.0% | 0/64 | 0.0% |
| 20/32 or better | 61/121 | 50.4% | 3/64 | 4.7% |
| 20/40 or better | 107/121 | 88.4% | 23/64 | 35.9% |
| Worse than 20/40 | 14/121 | 11.6% | 41/64 | 64.1% |
The stability of the visual acuity outcomes was demonstrated in a consistent cohort of patients across the Form 3 to Form 4 (1-2 months to 3-6 months) and Form 4 to Form 5 (3-6 months to 11-15- months) postoperative intervals. As shown in Table 6 below, a change of ≤ ±0.50 D was reported for over 84% of implanted eyes, and a change of ≤ ±1.00 D was reported for over 96% of implanted eyes. Consistent with good stability of the manifest refraction, 182 of 228 primary eyes (79.8%) had no change in DCNVA in the Form 3 to Form 4 postoperative interval as compared to 181 of 229 primary eyes (79.0%) in the Form 4 to Form 5 postoperative interval.
Table 6
Stability of Manifest Spherical Equivalent (MRSE) and Near Visual Acuity Through Distance Correction (DCNVA)
US Eyes - One-Year Consistent Cohort
| Change in MRSE | Form 3 to Form 4 (N = 234) N (Missing) = 6 | | Form 4 to Form 5 (N = 234) N (Missing) = 5 | |
| --- | --- | --- | --- | --- |
| | N | % | N | % |
| ≤ ±0.50 D | 197 | 84.5 | 201 | 85.9 |
| ≤ ±1.00 D | 225 | 96.6 | 226 | 96.6 |
| | | | | |
| Line Change in DCNVA | | | | |
| Decrease ≥ 2 lines | 18 | 7.9 | 11 | 4.8 |
| Decrease/Increase within 1 line | 182 | 79.8 | 181 | 79.0 |
Table 7 shows the results of the contrast sensitivity/ glare substudy. There were no statistically significant differences in contrast sensitivity measured under mesopic lighting, with a glare source, for eyes implanted with the crystalens™ IOL as compared to standard monofocal IOLs.
SSED
crystalens™ Model AT-45 Accommodating IOL
{6}
Table 7
Mean Contrast Sensitivity at 3-6 Months or Later
With Glare (3 cd/m² Illumination, 3 lux)
crystalens™ IOL Versus Standard Monofocal IOL
| Contrast Sensitivity – Spatial Frequency | Crystalens
N = 126
Mean (SD) | Standard IOL
N = 64
Mean (SD) |
| --- | --- | --- |
| Series A (1.5 cpd) | 1.53 (0.22) | 1.57 (0.23) |
| Series B (3 cpd) | 1.77 (0.23) | 1.70 (0.25) |
| Series C (6 cpd) | 1.34 (0.35) | 1.24 (0.31) |
| Series D (12 cpd) | 1.06 (0.34) | 0.95 (0.26) |
| Series E (18 cpd) | 0.73 (0.35) | 0.57 (0.24) |
The results of the subject survey substudy are shown in Tables 8, 9, and 10.
Table 8 reports on the percentages of subjects that were able to perform various tasks without the use of spectacles. Of the 128 subjects that completed the survey, 120 (93.8%) reported performing most visual functions without spectacles.
Table 8
Bilateral Patient Survey
Activities Without Spectacles (US Bilateral Subjects)
| Activity | Yes
N/N (%) | No
n/N (%) |
| --- | --- | --- |
| Perform most visual functions | 120/128 (93.8%) | 8/128 (6.3%) |
| Read most things | 100/129 (77.5%) | 29/129 (22.5%) |
| Go shopping | 116/124 (93.5%) | 8/124 (6.5%) |
| Participate in sports | 84/87 (96.6%) | 3/87 (3.4%) |
| Attend social gatherings | 120/126 (95.2%) | 6/126 (4.8%) |
| Drive | 111/121 (91.7%) | 10/121 (8.3%) |
| Read a newspaper | 73/128 (57.0%) | 55/128 (43.0%) |
| Sew or do needlework | 35/91 (38.5%) | 56/91 (61.5%) |
| Work on a computer | 75/93 (80.6%) | 18/93 (19.4%) |
| Do handy work around the house | 119/126 (94.4%) | 7/126 (5.6%) |
| Walk | 126/129 (97.7%) | 3/129 (2.3%) |
| Shop | 117/128 (91.4%) | 11/128 (8.6%) |
| Watch television | 120/130 (92.3%) | 10/130 (7.7%) |
Table 9 reports on the percentages of subjects that experienced difficulty with night activities.
SSED
crystalens™ Model AT-45 Accommodating IOL
{7}
Table 9
Bilateral Patient Survey
Difficulty With Night Activity (US Bilateral Subjects)
| Symptoms | Absent N/N (%) | Mild N/N (%) | Moderate n/N (%) | Severe n/N (%) |
| --- | --- | --- | --- | --- |
| Night-time glare/flare | 74/130 (56.9%) | 31/130 (23.8%) | 18/130 (13.8%) | 7/130 (5.4%) |
| Night vision (difficulty driving at night) | 82/121 (67.8%) | 21/121 (17.4%) | 14/121 (11.6%) | 4/121 (3.3%) |
| Halos (rings around lights) | 80/130 (61.5%) | 26/130 (20.0%) | 16/130 (12.3%) | 8/130 (6.2%) |
Table 10 reports on the percentage of subjects wearing spectacles during waking hours and to see at night. Twenty-six percent of subjects reported that they no longer needed spectacles for any task. An additional 48 percent reduced their spectacle dependency by at least 75% and 16% of subjects by at least 50%. Eleven percent reported wearing glasses more than 50% of the time. In addition, 110/130 subjects (84.6%) reported needing no spectacles to see at night.
Table 10
Bilateral Patient Survey
Wearing Spectacles During Waking Hours And to See At Night (US Bilateral Subjects)
| Wearing Spectacles | n/N (%) |
| --- | --- |
| How often do you wear spectacles during waking hours? | |
| I do not wear spectacles | 33/128 (25.8%) |
| I wear spectacles almost none of the time (10%-25%) | 61/128 (47.7%) |
| I wear spectacles some of the time (26%-50%) | 20/128 (15.6%) |
| I wear spectacles most of the time (51%-75%) | 8/128 (6.3%) |
| I wear spectacles all the time or almost all the time (76%-100%) | 6/128 (4.7%) |
| Do you wear spectacles to see at night? | |
| No | 110/130 (84.6%) |
| Yes | 20/130 (15.4%) |
SSED
crystalens™ Model AT-45 Accommodating IOL
{8}
SSED
crystalens™ Model AT-45 Accommodating IOL
page 9
# XI. CONCLUSIONS DRAWN FROM THE STUDIES
## SAFETY
The rates of adverse events associated with the crystalens™ IOL are comparable to or lower than the rates associated with the historical control population of standard monofocal IOLs.
## EFFECTIVENESS
The crystalens™ IOL provides improved visual acuity at near and intermediate distances compared to standard monofocal IOLs.
# XII. PANEL RECOMMENDATION
At an advisory meeting held on May 23, 2003, the Ophthalmic Devices Panel recommended that eyeonics’ PMA for the crystalens™ IOL be approved subject to submission to, and approval by, the Center for Devices and Radiological Health (CDRH) of modified physician and patient labeling that incorporated their recommendations.
# XIII. CDRH DECISION
CDRH concurred with the Ophthalmic Devices Panel recommendation of May 23, 2003, and issued a letter to eyeonics, on June 27, 2003, advising that its PMA was approvable subject to eyeonics’ modifications of the physician and patient labeling as recommended by the Panel and required by FDA. In an amendment received by FDA on October 27, 2003, eyeonics submitted the required modified labeling. FDA issued an approval order on November 14, 2003. The applicant's manufacturing facility was inspected on July 8-10 and 14, 2003 and was found to be in compliance with the Quality System Regulation (21 CFR 820).
The crystalens™ IOL was granted expedited review status on February 24, 2003, because the Model AT-45 accommodating IOL represents a clear, clinically meaningful advantage over existing technology.
# XIV. APPROVAL SPECIFICATIONS
Directions for use: See the labeling.
Hazards to Health from Use of the Device: See Indications, Contraindications, Warnings, precautions and Adverse Events in the labeling.
Postapproval Requirements and Restrictions: See approval order.
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
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.