MODI insulin dose calculator is software intended for the management of type 2 diabetes in persons aged 18 years and older requiring long-acting insulin with or without rapid-acting insulin injections. MODI insulin dose calculator calculates a dose of basal (long-acting) insulin with or without a dose of bolus (rapid-acting for meal and correction) insulin based on glucose measurements from an iCGM (Integrated Continuous Glucose Monitor) and insulin delivery data (i.e. time of dose with or without amount of dose). MODI insulin dose calculator intended for single patient, home use and requires a prescription by a healthcare provider.
Device Story
MODI is a CGM-informed insulin dose calculator for home use by adults with type 2 diabetes; requires prescription. Inputs: iCGM glucose measurements, insulin delivery logs, patient treatment parameters, body weight. Operation: MODI Algorithm analyzes inputs to generate optimized basal/bolus insulin dose recommendations; typically issued every 7 days; daily adjustments provided if hypoglycemia risk detected. Output: Dose recommendations displayed via Host App (DreaMed Diary). System components: MODI Algorithm, MODI Engine (middleware), Host App, Host DMS. Clinical impact: Assists patients in insulin titration; supports glycemic management. Benefits: Potential reduction in HbA1c and hypoglycemia risk without serious adverse events.
Clinical Evidence
Prospective, single-arm study (N=29) in type 2 diabetes patients. Primary endpoint: safety (percentage of CGM values <54 mg/dL, severe hypoglycemia, DKA). Results: No severe hypoglycemia or DKA; all safety thresholds met. Exploratory efficacy: In participants with baseline TIR <70% (N=11), significant increase in TIR (58% to 69%, p=0.02) and decrease in Time Above 180 mg/dL (39% to 29%, p=0.02) observed. HbA1c decreased by 0.4% (p=0.06).
Technological Characteristics
Algorithmic software device; operates on mobile/cloud-integrated platform. Inputs: iCGM data, patient-logged insulin, and treatment parameters. Outputs: Basal/bolus dose recommendations and diabetes management tips. Connectivity: Integrates with Host App and Host DMS. Cybersecurity: Risk-managed per FDA guidance (June 2025). Software: Class II medical device; verified per IEC 62304.
Indications for Use
Indicated for patients aged 18+ with type 2 diabetes requiring long-acting insulin, with or without rapid-acting insulin. Contraindicated for patients using insulin pumps, Automated Insulin Dosing (AID), IV insulin, or combinations of injections and pump therapy. Not recommended for pregnant individuals or those initiating basal insulin therapy for the first time.
Regulatory Classification
Identification
An insulin therapy adjustment device is a device intended to incorporate biological inputs, including glucose measurement data from a continuous glucose monitor, to recommend insulin therapy adjustments as an aid in optimizing insulin therapy regimens for patients with diabetes mellitus.
Special Controls
(b) Classification: Class II (special controls). The special controls for this device are
- 1. Design verification and validation must include the following:
- (i) A complete description of the required data inputs, including timeframe over which data inputs must be collected and number of data points required for accurate recommendations.
- (ii) A complete description of the types of device outputs and insulin therapy adjustment recommendations, including how the recommendations are generated.
- (iii)Robust data demonstrating the clinical validity of the device outputs and insulin therapy recommendations.
- (iv)A robust assessment of all input data specifications, including accuracy requirements for continuous glucose monitors and other devices generating data inputs, to ensure accurate and reliable therapy adjustment recommendations. This assessment must include adequate clinical justification for each specification.
- (v) A detailed strategy to ensure secure and reliable means of data transmission to and from the device, including data integrity checks, accuracy checks, reliability checks, and security measures.
- (vi)Robust data demonstrating that users can understand and appropriately interpret recommendations generated by the device.
- (vii) An appropriate mitigation strategy to minimize the occurrence of dosing recommendation errors, and to mitigate the risk to patients of any residual dosing recommendation errors to a clinically acceptable level.
- 2. The device must not be intended for use in implementing automated insulin dosing.
- 3. Your 809.10(b) labeling must include:
- (i) The identification of specific insulin formulations that have been demonstrated to be compatible with use of the device.
- (ii) A detailed description of the specifications of compatible devices that provide acceptable input data (e.g., continuous glucose monitors, insulin pumps) used to provide accurate and reliable therapy adjustment recommendations.
- (iii) A detailed description of all types of required data (inputs) and dosing recommendations (outputs) that are provided by the device.
- (iv) A description of device limitations, and instructions to prevent possible disruption of accurate therapy adjustment recommendations (e.g., time zone changes due to travel).
*Classification.* Class II (special controls). The special controls for this device are:(1) Design verification and validation must include the following:
(i) A complete description of the required data inputs, including timeframe over which data inputs must be collected and number of data points required for accurate recommendations;
(ii) A complete description of the types of device outputs and insulin therapy adjustment recommendations, including how the recommendations are generated;
(iii) Robust data demonstrating the clinical validity of the device outputs and insulin therapy recommendations;
(iv) A robust assessment of all input data specifications, including accuracy requirements for continuous glucose monitors and other devices generating data inputs, to ensure accurate and reliable therapy adjustment recommendations. This assessment must include adequate clinical justification for each specification;
(v) A detailed strategy to ensure secure and reliable means of data transmission to and from the device, including data integrity checks, accuracy checks, reliability checks, and security measures;
(vi) Robust data demonstrating that users can understand and appropriately interpret recommendations generated by the device; and
(vii) An appropriate mitigation strategy to minimize the occurrence of dosing recommendation errors, and to mitigate the risk to patients of any residual dosing recommendation errors to a clinically acceptable level.
(2) The device must not be intended for use in implementing automated insulin dosing.
(3) Your 21 CFR 809.10(b) labeling must include:
(i) The identification of specific insulin formulations that have been demonstrated to be compatible with use of the device;
(ii) A detailed description of the specifications of compatible devices that provide acceptable input data (e.g., continuous glucose monitors, insulin pumps) used to provide accurate and reliable therapy adjustment recommendations;
(iii) A detailed description of all types of required data (inputs) and dosing recommendations (outputs) that are provided by the device; and
(iv) A description of device limitations, and instructions to prevent possible disruption of accurate therapy adjustment recommendations (e.g., time zone changes due to travel).
{0}
[LOGO]
FDA
U.S. FOOD & DRUG
ADMINISTRATION
### 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
### I Background Information:
### A 510(k) Number
K260062
### B Applicant
DreaMed Diabetes Ltd.
### C Proprietary and Established Names
MODI System
### D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| QRX | Class II | 21 CFR 862.1358 – Insulin Therapy Adjustment Device | CH – Clinical Chemistry |
### E Purpose for Submission:
- New Device
- Establish a Predetermined Change Control Plan (PCCP) to integrate with a 3rd Party Host Diabetes Management System (DMS) and to integrate new data source partners
### II Intended Use/Indications for Use:
### A Intended Use(s):
See Indications for Use below.
### B Indication(s) for Use:
MODI insulin dose calculator is software intended for the management of type 2 diabetes in persons aged 18 years and older requiring long-acting insulin with or without rapid-acting insulin injections. MODI insulin dose calculator calculates a dose of basal (long-acting) insulin with or without a dose of bolus (rapid-acting for meal and correction) insulin based on glucose measurements from an iCGM (Integrated Continuous Glucose Monitor) and insulin delivery data (i.e. time of dose with or without amount of dose). MODI insulin dose calculator intended for single patient, home use and requires a prescription by a healthcare provider.
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
Special conditions for Use Statement:
- MODI is Rx - For Prescription Use Only
- MODI algorithm is not intended for use with patients treated with insulin pump, Automated Insulin Dosing (AID), intravenous (IV) insulin injections, or a combination of insulin injections and/or IV insulin and insulin pump therapy.
- MODI insulin dose calculator is not recommended for use during pregnancy. MODI has not been tested with individuals who are pregnant.
### C Special Conditions for Use Statement(s):
MODI is Rx – For Prescription Use Only
MODI algorithm is not intended for use with patients treated with an insulin pump, automated insulin dosing (AID), intravenous (IV) insulin injections, or a combination of insulin injections and/or IV insulin and insulin pump therapy.
MODI insulin dose calculator is not recommended for use during pregnancy. MODI has not been tested with individuals who are pregnant.
The MODI algorithm is not intended for use in individuals initiating basal insulin therapy for the first time. DreaMed Diary and MODI algorithm are not intended for use by patients who use insulin(s) other than the types indicated in the User Manual. Using MODI with other types of insulin may lead to potential harm.
### III Device Description
MODI system is an insulin does calculator intended for use by people aged 18 years and older with type 2 diabetes who require long-acting insulin, with or without rapid-acting insulin injections. MODI is a CGM-informed insulin dose calculator that uses continuous glucose monitoring (CGM) data, insulin administration logs, and patient-specific treatment parameters to optimize and recommend basal and/or bolus insulin doses.
The MODI system comprises software components include:
- MODI, including the MODI Algorithm and the MODI Engine
- DreaMed Diary App (modified from K232722) as the Host App
- Endo.digital platform (modified from K232722) as the Host Diabetes Management Software (DMS)
The MODI Algorithm analyzes glucose levels, insulin delivery history, treatment plan, and body weight to generate insulin dose recommendations that are typically issued every 7 days and are delivered to the patient via the Host App (through the MODI Engine). The MODI Engine facilitates communication between the Host App, Host DMS, and the MODI Algorithm, supporting system initialization, titration assessment, and transmission of dose recommendations.
K260062 - Page 2 of 8
{2}
The Host App is a dedicated version of the DreaMed Diary app (K232722) enabling patient interaction with the MODI Algorithm (e.g., patient self-onboarding, insulin event logging, and visualization of dose recommendations) via the MODI Engine. The Host DMS is a diabetes management middleware integrating with CGM data, the Host App, and the MODI Engine.
#### IV Substantial Equivalence Information:
##### A Predicate Device Name(s):
Dexcom Smart Basal
##### B Predicate 510(k) Number(s):
K252818
##### C Comparison with Predicate(s):
| Device & Predicate Device(s): | K260062 | K252818 |
| --- | --- | --- |
| Device Trade Name | MODI System | Dexcom Smart Basal |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | Intended to calculate insulin doses based on CGM values and/or other relevant information | Same |
| Diabetes Type | Type 2 diabetes | Same |
| Principle of Operation | Algorithmic software device | Same |
| Age range of intended users | 18 years and older | Same |
| Display to users | Calculated doses via mobile application | Same |
| General Device Characteristic Differences | | |
| Insulin use | Basal (long-acting) with or without bolus (rapid-acting) | Basal (long-acting) only |
| Insulin type | Long-acting: Basaglar, Degludec U-100, Degludec U-200, Glargine, Lantus, | U-100 glargine only |
K260062 - Page 3 of 8
{3}
| | Levemir, Rezvoglar, Semglee, Soliqua, Toujeo U-300, Toujeo Max U-300, Tresiba U-100, Tresiba U-200, Xultophy, Tregludec U-100, Tregludec U-200 Rapid-acting: Admelog, Apidra, Aspart, Fiasp, Humalog U-100, Humalog U-200, Lispro U-100, Lyumjev U-100, Lyumjev U-200, Novolog, ReliOn Novolog, Novorapid | |
| --- | --- | --- |
| Data inputs | CGM values and historic data, initial configuration from user, daily insulin log | CGM values and historic data, initial configuration from HCP, daily basal insulin log |
| Device outputs | Weekly recommendations of optimized insulin dose plan (basal plan, meal bolus plan for fixed meal and meal estimation types, personal diabetes management tips) | Suggested daily basal dose output |
| Titration frequency | Every 7 days; daily decrease is allowed as needed | Daily |
| Titration episode length | Continuous unless terminated by user, or in case the patient has not reported insulin doses in 90 days | Up to 90 days, unless terminated by the HCP or patient |
**Pre-determined Change Control Plan (PCCP):** In addition to the similarities and differences between the candidate and the predicate device listed in the table above, the candidate device has an authorized PCCP for integrating with a 3rd Party Host Diabetes Management System (DMS) and for integrating with new data source partners, such as a CGM or insulin pen. The PCCP includes a description of the modifications, a modification protocol, and an impact assessment. The PCCP specifies the testing methods, validation activities, and performance requirements to implement the specified modifications such that DreaMed MODI remains as safe and as effective as the predicate device and continues to comply with 21 CFR 862.1358. The sponsor's PCCP comprises the following:
K260062 - Page 4 of 8
{4}
- Integration with a new 3rd Party Host DMS allows an Integration Partner to implement MODI within their mobile app, and in turn, the Integration Partner will utilize and visualize MODI's output within their app. The PCCP describes DreaMed's responsibilities for supporting this change including providing adequate labeling and specifying integration requirements and conducting a cybersecurity risk assessment. Software changes to facilitate the integration that would require a new 510(k) are not covered in this PCCP. Cybersecurity risks and risks associated with human factors (changes to user tasks, user interface flow, connected-device setup, data source authorization, device status, warnings, training, or labeling) will be evaluated by the same methods used in this 510(k). Mitigation of new risks are outside the scope of this PCCP.
- Integration with a new data source partner allows additional data sources (e.g., CGMs sensor or connected insulin pens) to connect with MODI. The new data source partners expand compatibility of MODI and do not change the clinical input types or modify the MODI algorithm. Verification and validation activities will be conducted according to the PCCP. New data source devices must be FDA-authorized and DreaMed will conduct a risk assessment for hazards introduced or changed by the new data source and a use-related risk analysis for any changes to user tasks and the user interface. Integration validation testing will be conducted per device type (e.g., CGMs versus insulin pens), and MODI labeling will be updated to list authorized devices. If integration verification and validation meet the PCCP's acceptance criteria, a new data source may be integrated with MODI.
# V Standards/Guidance Documents Referenced:
Special controls established under 21 CFR 862.1358
ISO 14155 Third Edition 2020-07 Clinical investigation of medical devices for human subjects – Good clinical practice
ANSI/AAMI/ISO 14971:2019 Medical devices – Applications of risk management to medical Devices
ANSI/AAMI/IEC 62304:2006/A1:2016 Medical device software – Software life cycle processes [Including Amendment 1 (2016)]
ANSI/AAMI/IEC 62366-1:2015 + AMDI:2020 (Consolidated Text) Medical devices Part 1: Application of usability engineering to medical devices including Amendment 1
# VI Performance Characteristics:
Clinical Testing
A prospective, single-center, single-arm study was conducted to evaluate the safety of the MODI system in subjects with type 2 diabetes. The study enrolled 29 participants aged 18 years and older under multiple daily injections (MDI) or basal insulin therapy. The average age was 67 years, 48% of subjects were female, the average BMI was 29.8 kg/m², and the average baseline HbA1c was 7.6%. Patients' long-acting regimen included Glargine U-100 (7 patients), Detamir
K260062 - Page 5 of 8
{5}
U-100 (3 patients), Glargine U-300 (1 patient), Degludec U-200 (7 patients) and Insulin degludec and Liraglutide U-100 (5 patients). For patients under multiple daily injections, short acting insulin regimen included Aspart U-100 (13 patients) and Glulisine U-100 (1 patient).
The study consisted of a 2–4 weeks run-in period (baseline) followed by a 10-weeks intervention period, during which insulin dosing recommendations were generated by the MODI System. At study initiation, study staff entered the initial treatment plan settings. Subjects were permitted to the use the device as they wish at home for the study duration and there were study visits at 4 and 10 weeks to review data for adverse events at HbA1c collection (only at 10 weeks). Study staff contacted subjects during the study outside of protocol-specified visits to confirm that no adverse events had occurred. During these calls, study staff did not provide individualized guidance regarding interpretation of MODI outputs, insulin dose decisions, or diabetes management beyond protocol-defined activities and routine safety follow-up.
The primary objective was to evaluate the safety of the MODI system. Safety was assessed by evaluating percentage of CGM values below 54 mg/dL and serious adverse events, including severe hypoglycemia and diabetic ketoacidosis. Secondary objectives included time above 250 mg/dL, hypoglycemia events (< 54 mg/dL for ≥ 15 minutes) and prolonged hyperglycemia events (> 250 mg/dL for 120 minutes). Exploratory endpoints included efficacy-related endpoints (CGM metrics and HbA1c), as shown in the table below. There were no reports of serious adverse events of any kind, including device-related events, severe hypoglycemia and diabetic ketoacidosis, during the intervention period of the study.
| Percent | Baseline Mean ± SD | End-of-Study Mean ± SD | Difference Mean ± SD | P-value^{a} |
| --- | --- | --- | --- | --- |
| **All Subjects with T2D (N = 29)** | | | | |
| Time in range 70-180 mg/dL | 74 ± 15 | 76 ± 13 | 2.2 ± 12 | 0.32 |
| Time below 54 mg/dL | 0.47 ± 1.8 | 0.23 ± 0.51 | -0.24 ± 1.6 | 0.44 |
| Time below 70 mg/dL | 2.4 ± 4.9 | 1.3 ± 1.5 | -1.1 ± 4.0 | 0.16 |
| Time above 180 mg/dL | 24 ± 16 | 23 ± 13 | -1.1 ± 11 | 0.59 |
| Time above 250 mg/dL | 3.9 ± 4.4 | 3.0 ± 3.6 | -0.91 ± 3.9 | 0.22 |
| HbA1c | 7.6 ± 0.96 | 7.2 ± 0.8 | -0.43 ± 0.71 | 0.003 |
| **All Subjects with T2D on MDI Therapy (N = 14)** | | | | |
| Time in range 70-180 mg/dL | 68.1 ± 16.9 | 73.8 ± 13.6 | 5.64 ± 12.8 | 0.12 |
| Time below 54 mg/dL | 0.09 ± 0.14 | 0.12 ± 0.26 | 0.02 ± 0.3 | 0.77 |
| Time below 70 mg/dL | 1.29 ± 1.49 | 1.09 ± 0.92 | -0.2 ± 0.94 | 0.45 |
| Time above 180 mg/dL | 30.6 ± 17.0 | 25.1 ± 13.8 | -5.45 ± 13.2 | 0.15 |
| Time above 250 mg/dL | 5.4 ± 5.3 | 3.1 ± 3.1 | -2.29 ± 4.22 | 0.063 |
K260062 - Page 6 of 8
{6}
| HbA1c | 7.89 ± 1.06 | 7.42 ± 0.87 | -0.47 ± 0.76 | 0.038 |
| --- | --- | --- | --- | --- |
| All Subjects with T2D on Basal-Only Therapy (N = 15) | | | | |
| Time in range 70-180 mg/dL | 78.7 ± 12.0 | 77.7 ± 13.3 | -0.95 ± 10.0 | 0.72 |
| Time below 54 mg/dL | 0.83 ± 2.44 | 0.3 ± 0.52 | -0.53 ± 2.17 | 0.36 |
| Time below 70 mg/dL | 3.77 ± 6.94 | 1.52 ± 1.93 | -2.25 ± 5.56 | 0.14 |
| Time above 180 mg/dL | 18.0 ± 12.2 | 20.9 ± 13.5 | 3.0 ± 7.7 | 0.15 |
| Time above 250 mg/dL | 2.41 ± 2.7 | 2.91 ± 4.22 | 0.5 ± 3.19 | 0.56 |
| HbA1c | 7.41 ± 0.83 | 7.02 ± 0.7 | -0.4 ± 0.7 | 0.04 |
\( ^{a} \) Paired t-test
Recommendations are typically issued by MODI every seven days and delivered to the patient. If MODI detects an increased risk of hypoglycemia, daily adjustments may be provided. During the study, MODI detected 260 cases of a potentially increased risk of hypoglycemia. In 36 cases, a recommendation from the app was issued. To evaluate the effect of these recommendations, patient CGM data from before the recommendation was compared to their CGM data after the recommendation. The same comparison was made for instances where no recommendation was sent to the patients. These results are reported in the table below.
| | Mean Time below 54 mg/dL (%) Mean ± SD | | Mean Time below 70 mg/dL (%) Mean ± SD | |
| --- | --- | --- | --- | --- |
| | 3 days before | 3 days after | 3 days before | 3 days after |
| Recommendation issued (36 cases in 11 patients) | 6.1 ± 13.3 | 3.3 ± 9.6 | 14.3 ± 19.3 | 8.9 ± 15.3 |
| No recommendation issued (224 cases in 18 patients) | 0.3 ± 0.9 | 0.2 ± 1.0 | 4.7 ± 5.6 | 3.8 ± 6.1 |
### Software
DreaMed provided software documentation consistent with FDA Guidance for the Content of Premarket Submissions for Device Software Functions and consistent with software with a major level of concern. Software documentation was acceptable.
### Cybersecurity
DreaMed provided cybersecurity documentation consistent with FDA Guidance Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions. Cybersecurity documentation was acceptable.
K260062 - Page 7 of 8
{7}
# Human Factors
Human factors validation studies were conducted to assess if representative users of MODI can safely use the system and perform all critical tasks under representative conditions. Studies were conducted with 20 adult participants with Type 1 or insulin-requiring Type 2 diabetes, including adult-caregiver dyads and subjects who take basal insulin only. All study participants received training that was consistent with the training that patients will receive with the commercial product and interacted with the device in a simulated use environment. Usability evaluations assessed comprehension and usability of the device for critical device tasks. Results of the study demonstrated that the device could be used safely by intended users.
# VII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
# VIII Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
K260062 - Page 8 of 8
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:
Guidance alerts
New and changed FDA guidance documents, emailed as a daily digest.
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 ? 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 as a Medical Device, 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 as a Medical Device), 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.
