K262576 · Deka Research and Development Corp. · QJI · Oct 15, 2026 · Clinical Chemistry
Device Facts
Record ID
K262576
Device Name
twiist Loop Algorithm
Applicant
Deka Research and Development Corp.
Product Code
QJI · Clinical Chemistry
Decision Date
Oct 15, 2026
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1356
Device Class
Class 2
Attributes
Therapeutic, Pediatric
Indications for Use
The twiist Loop Algorithm is intended for use with compatible integrated continuous glucose monitors (iCGMs) and the twiist alternate controller enabled (ACE) insulin infusion pump to automatically increase, decrease, and suspend delivery of basal insulin based on iCGM readings and predicted glucose values. It can also recommend, and with the user's confirmation, control the delivery of correction boluses when glucose values are predicted to exceed user configurable thresholds. The twiist Loop Algorithm is intended for the management of type 1 diabetes mellitus in persons six years of age and greater and for the management of type 2 diabetes mellitus in persons eighteen years of age and greater. The twiist Loop Algorithm is intended for single-patient use and requires a prescription.
Device Story
Interoperable automated glycemic controller (iAGC) software; inputs iCGM glucose readings; predicts future glucose levels; automatically adjusts basal insulin delivery (increase, decrease, suspend) via compatible ACE insulin pump; recommends correction boluses for user confirmation; intended for home use by patients; requires prescription; manages glycemic control in T1D and T2D patients; benefits include improved time-in-range and reduced HbA1c.
Clinical Evidence
Single-arm, open-label, multicenter study (n=307) in insulin-treated T2D adults (mean age 58). Primary endpoint: change in HbA1c from baseline to 13 weeks. Results: HbA1c decreased from 8.15% to 7.40% (mean change -0.74%, 95% CI -0.88 to -0.61). Secondary endpoints: Time in range (70-180 mg/dL) increased from 57% to 72% (p<0.001). Safety: No severe hypoglycemia; one DKA event reported.
Technological Characteristics
Interoperable automated glycemic controller (iAGC) software. Operates as part of an AID system with iCGM and ACE pump. No changes to software code from predicate. Connectivity via compatible iCGM sensors. Regulatory class II under 21 CFR 862.1356.
Indications for Use
Indicated for management of type 1 diabetes mellitus in persons ≥6 years and type 2 diabetes mellitus in persons ≥18 years. Contraindicated for pregnant individuals, dialysis patients, critically ill patients, or those with uncontrolled thyroid disease, renal failure (eGFR <30), hemophilia/major bleeding disorders, or unstable cardiovascular disease.
Regulatory Classification
Identification
An interoperable automated glycemic controller is a device intended to automatically calculate drug doses based on inputs such as glucose and other relevant physiological parameters, and to command the delivery of such drug doses from a connected infusion pump. Interoperable automated glycemic controllers are designed to reliably and securely communicate with digitally connected devices to allow drug delivery commands to be sent, received, executed, and confirmed. Interoperable automated glycemic controllers are intended to be used in conjunction with digitally connected devices for the purpose of maintaining glycemic control.
Special Controls
*Classification.* Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) An appropriate, as determined by FDA, clinical implementation strategy, including data demonstrating appropriate, as determined by FDA, clinical performance of the device for its intended use, including all of its indications for use.
(A) The clinical data must be representative of the performance of the device in the intended use population and in clinically relevant use scenarios and sufficient to demonstrate appropriate, as determined by FDA, clinical performance of the device for its intended use, including all of its indications for use.
(B) For devices indicated for use with multiple therapeutic agents for the same therapeutic effect (
*e.g.,* more than one type of insulin), data demonstrating performance with each product or, alternatively, an appropriate, as determined by FDA, clinical justification for why such data are not needed.(C) When determined to be necessary by FDA, the strategy must include postmarket data collection to confirm safe real-world use and monitor for rare adverse events.
(ii) Results obtained through a human factors study that demonstrates that an intended user can safely use the device for its intended use.
(iii) A detailed and appropriate, as determined by FDA, strategy to ensure secure and reliable means of data transmission with other intended connected devices.
(iv) Specifications that are appropriate, as determined by FDA, for connected devices that shall be eligible to provide input to (
*e.g.,* specification of glucose sensor performance) or accept commands from (*e.g.,* specifications for drug infusion pump performance) the controller, and a detailed strategy for ensuring that connected devices meet these specifications.(v) Specifications for devices responsible for hosting the controller, and a detailed and appropriate, as determined by FDA, strategy for ensuring that the specifications are met by the hosting devices.
(vi) Documentation demonstrating that appropriate, as determined by FDA, measures are in place (
*e.g.,* validated device design features) to ensure that safe therapy is maintained when communication with digitally connected devices is interrupted, lost, or re-established after an interruption. Validation testing results must demonstrate that critical events that occur during a loss of communications (*e.g.,* commands, device malfunctions, occlusions, etc.) are handled and logged appropriately during and after the interruption to maintain patient safety.(vii) A detailed plan and procedure for assigning postmarket responsibilities including adverse event reporting, complaint handling, and investigations with the manufacturers of devices that are digitally connected to the controller.
(2) Design verification and validation documentation must include appropriate design inputs and design outputs that are essential for the proper functioning of the device that have been documented and include the following:
(i) Risk control measures to address device system hazards;
(ii) Design decisions related to how the risk control measures impact essential performance; and
(iii) A traceability analysis demonstrating that all hazards are adequately controlled and that all controls have been validated in the final device design.
(3) The device shall include appropriate, as determined by FDA, and validated interface specifications for digitally connected devices. These interface specifications shall, at a minimum, provide for the following:
(i) Secure authentication (pairing) to connected devices;
(ii) Secure, accurate, and reliable means of data transmission between the controller and connected devices;
(iii) Sharing of necessary state information between the controller and any connected devices (
*e.g.,* battery level, reservoir level, sensor use life, pump status, error conditions);(iv) Ensuring that the controller continues to operate safely when data is received in a manner outside the bounds of the parameters specified;
(v) A detailed process and procedures for sharing the controller's interface specification with connected devices and for validating the correct implementation of that protocol; and
(vi) A mechanism for updating the controller software, including any software that is required for operation of the controller in a manner that ensures its safety and performance.
(4) The device design must ensure that a record of critical events is stored and accessible for an adequate period to allow for auditing of communications between digitally connected devices, and to facilitate the sharing of pertinent information with the responsible parties for those connected devices. Critical events to be stored by the controller must, at a minimum, include:
(i) Commands issued by the controller, and associated confirmations the controller receives from digitally connected devices;
(ii) Malfunctions of the controller and malfunctions reported to the controller by digitally connected devices (
*e.g.,* infusion pump occlusion, glucose sensor shut down);(iii) Alarms and alerts and associated acknowledgements from the controller as well as those reported to the controller by digitally connected devices; and
(iv) Connectivity events (
*e.g.,* establishment or loss of communications).(5) The device must only receive glucose input from devices cleared under § 862.1355 (integrated continuous glucose monitoring system), unless FDA determines an alternate type of glucose input device is designed appropriately to allow the controller to meet the special controls contained within this section.
(6) The device must only command drug delivery from devices cleared under § 880.5730 of this chapter (alternate controller enabled infusion pump), unless FDA determines an alternate type of drug infusion pump device is designed appropriately to allow the controller to meet the special controls contained within this section.
(7) An appropriate, as determined by FDA, training plan must be established for users and healthcare providers to assure the safety and performance of the device when used. This may include, but not be limited to, training on device contraindications, situations in which the device should not be used, notable differences in device functionality or features compared to similar alternative therapies, and information to help prescribers identify suitable candidate patients, as applicable.
(8) The labeling required under § 809.10(b) of this chapter must include:
(i) A contraindication for use in pediatric populations except to the extent clinical performance data or other available information demonstrates that it can be safely used in pediatric populations in whole or in part.
(ii) A prominent statement identifying any populations for which use of this device has been determined to be unsafe.
(iii) A prominent statement identifying by name the therapeutic agents that are compatible with the controller, including their identity and concentration, as appropriate.
(iv) The identity of those digitally connected devices with which the controller can be used, including descriptions of the specific system configurations that can be used, per the detailed strategy submitted under paragraph (b)(1)(iii) of this section.
(v) A comprehensive description of representative clinical performance in the hands of the intended user, including information specific to use in the pediatric use population, as appropriate.
(vi) A comprehensive description of safety of the device, including, for example, the incidence of severe hypoglycemia, diabetic ketoacidosis, and other relevant adverse events observed in a study conducted to satisfy paragraph (b)(1)(i) of this section.
(vii) For wireless connection enabled devices, a description of the wireless quality of service required for proper use of the device.
(viii) For any controller with hardware components intended for multiple patient reuse, instructions for safely reprocessing the hardware components between uses.
{0}
[LOGO]
FDA
U.S. FOOD & DRUG
ADMINISTRATION
### 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
### I Background Information:
A 510(k) Number
K262576
B Applicant
Deka Research and Development Corp.
C Proprietary and Established Names
twiist Loop Algorithm
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| QJI | Class II | 21 CFR 862.1356 | CH – Clinical Chemistry |
E Purpose for Submission:
Modification to the DEKA Loop cleared under K234055 to add an indication for patients with Type 2 diabetes mellitus in persons age 18 and greater.
### II Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
The twiist Loop Algorithm is intended for use with compatible integrated continuous glucose monitors (iCGMs) and the twiist alternate controller enabled (ACE) insulin infusion pump to automatically increase, decrease, and suspend delivery of basal insulin based on iCGM readings and predicted glucose values. It can also recommend, and with the user's confirmation, control the delivery of correction boluses when glucose values are predicted to exceed user configurable thresholds.
The twiist Loop Algorithm is intended for the management of type 1 diabetes mellitus in persons six years of age and greater and for the management of type 2 diabetes mellitus in persons eighteen years of age and greater.
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
The twiist Loop Algorithm is intended for single-patient use and requires a prescription.
### **C Special Conditions for Use Statement(s):**
Rx – For Prescription Use Only
The twiist automated insulin delivery system is not intended for anyone unable or unwilling to:
- Test blood glucose (BG) levels as recommended by their healthcare provider.
- Maintain sufficient diabetes selfcare skills.
- See their healthcare provider regularly.
- Demonstrate adequate carbohydrate-counting skills (preferred, not required).
The twiist AID System should not be prescribed to patients with vision, hearing, cognitive, or physical impairments that would affect their ability to use the twiist AID System.
It is not indicated for use by anyone who is pregnant, on dialysis, or critically ill. It is not known how different conditions or medications used in these scenarios may affect performance of the twiist AID system. CGM readings being used by the system may be inaccurate in these cases, meaning the twiist AID system will not have accurate information to use for dosage recommendations. This could result in over-delivery or under-delivery of insulin, which can lead to low or high glucose.
Do not use the twiist AID system if you have a condition which, in the opinion of your healthcare provider, would put you at risk. Examples of individuals who should not use the twiist AID system include those with uncontrolled thyroid disease, renal failure (e.g. dialysis or eGFR <30), hemophilia, or another major bleeding disorder, or unstable cardiovascular disease.
twiist Loop combined with GLP-1 agonists, SGLT-2 inhibitors, DPP-4 inhibitors or metformin has only been studied in people with Type 2 diabetes mellitus and has not been studied in people with Type 1 diabetes mellitus. The performance of twiist Loop in conjunction with these medications is unknown in the Type 1 patient population.
### **III Device Description**
The candidate device is the twiist Loop Algorithm, an interoperable automated glycemic controller (iAGC). It is a modification to the indications for use of the previously cleared DEKA Loop (K234055) by adding an indication for patients with Type 2 diabetes mellitus in persons age 18 and greater. No changes were made to the iAGC software code cleared under K234055.
The candidate device is intended for use with compatible integrated continuous glucose monitors (iCGMs) and the twiist alternate controller enabled (ACE) insulin infusion pump. It is intended to automatically increase, decrease, and suspend delivery of basal insulin based on readings from an iCGM and predicted glucose values. It can recommend correction boluses when glucose values are predicted to exceed user configurable thresholds and upon the user's confirmation, control the delivery of correction boluses.
K262576- Page 2 of 13
{2}
The candidate device utilizes a dosing algorithm design to predict future glucose levels and adjust the amount of insulin to be delivered to the patient. The algorithm consists of four components involved in the automation of basal insulin delivery: insulin effect, carbohydrate effect, glucose momentum effect, and retrospective correction effect. It also utilizes these components to make recommendations for correction and meal boluses.
#### IV Substantial Equivalence Information:
##### A Predicate Device Name(s):
DEKA Loop
##### B Predicate 510(k) Number(s):
K234055
##### C Comparison with Predicate(s):
| Device & Predicate Device(s): | K262576 | K234055 |
| --- | --- | --- |
| Device Trade Name | twiist Loop Algorithm | DEKA Loop |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | The twiist Loop Algorithm is intended for use with compatible integrated continuous glucose monitors (iCGMs) and the twiist alternate controller enabled (ACE) insulin infusion pump to automatically increase, decrease, and suspend delivery of basal insulin based on iCGM readings and predicted glucose values. It can also recommend, and with the user's confirmation, control the delivery of correction boluses when glucose values are predicted to exceed user configurable thresholds. The twiist Loop Algorithm is intended for the management of type 1 diabetes mellitus in persons six years of age and greater and for the management of type 2 diabetes mellitus in persons eighteen years of age and greater. | Same |
K262576- Page 3 of 13
{3}
| General Device Characteristic Differences | | |
| --- | --- | --- |
| Intended use population | T1D six years of age and greater and T2D eighteen years of age and greater. | T1D six years of age and greater. |
| Compatible iGCM | Eversense 365 and FreeStyle Libre 3 Plus | Dexcom G6 |
# V Standards/Guidance Documents Referenced:
Special controls established under 21 CFR 862.1356 for interoperable automated glycemic controller.
# VI Performance Characteristics:
# A. Non-Clinical Performance
Non-clinical performance is leveraged from the predicate submission.
# B. Clinical Studies:
# Summary of Clinical Testing
A clinical study was performed to validate the twiist Loop Algorithm for use in persons 18 years of age and greater diagnosed with Type 2 diabetes. A summary of the clinical study is provided in the following table:
| Study Feature | Description |
| --- | --- |
| Title | A Single-arm Trial with an Innovative Automated Insulin Delivery System for Type 2 Diabetes (“twiist-T2D”) |
| Study Objective | - To evaluate the efficacy of the twiist system with respect to glycemic outcomes in adults with T2D - To evaluate the safety of the twiist system in adults with T2D - To assess the impact of use of the twiist system on patient satisfaction and other patient reported outcomes. |
| Study Design | The study was a single-arm, open-label, multicenter clinical study conducted in adults aged 18 years and greater with insulin-treated T2D. The study evaluated the safety, performance, and usability of the device over a 13-week treatment period. HbA1c was the primary efficacy endpoint. The study was comprised of a Feasibility Phase followed by a Main Phase under one protocol. An independent Data and Safety Monitoring Board (DSMB) conducted an interim safety evaluation. |
K262576- Page 4 of 13
{4}
| Study Feature | Description |
| --- | --- |
| | Following DSMB confirmation that no protocol modifications were required, enrollment proceeded into the Main Phase. Participants in both phases were followed for 13 weeks under identical study procedures, and their data were pooled for the final analysis. |
| Investigational Device | The twiist Loop Algorithm included in the twiist AID system that also includes an insulin pump and an Abbott Libre 3+ sensor |
| Study site | Thirty (30) sites in the United States |
| Inclusion Criteria | 1. Age ≥18 years at the time of screening 2. Clinical diagnosis of Type 2 Diabetes for at least 6 months 3. Using one of the following insulin regimens for at least 13 weeks prior to screening: • Basal-bolus insulin therapy with at least one daily rapid-acting injection • Open-loop insulin pump therapy • Premixed insulin with a rapid-acting component • Basal insulin without bolus insulin 4. If using non-insulin glucose-lowering medications (e.g., GLP-1 receptor agonists, SGLT-2 inhibitors), dose must have been stable for at least 4 weeks prior to screening with no planned changes during the study 5. Willing and able to use only insulin approved for use in the study pump 6. Ability to read and understand written English or another available language for the pump's user interface 7. Sufficient cognitive capacity to provide informed consent, as judged by the investigator 8. Capable of safely operating all study devices and adhering to the protocol 9. Willing to participate in meal and exercise challenges 10. Participants capable of becoming pregnant must have a negative pregnancy test and agree to use accepted contraceptive measures |
| Exclusion Criteria | 1. Diagnosis of Type 1 Diabetes |
K262576- Page 5 of 13
{5}
| Study Feature | Description |
| --- | --- |
| | 2. Prior use of an FDA-approved or non-FDA approved closed-loop or hybrid closed-loop insulin delivery system within the past 3 months 3. Pregnancy or breastfeeding at time of screening, or planning to become pregnant during the next 4 months 4. Concomitant disease or condition that may compromise patient safety (e.g., cystic fibrosis, severe mental illness, eating disorder) 5. Current use of an implantable CGM sensor (e.g., Senseonics) 6. Current use of ≥500 mg of ascorbic acid (Vitamin C) 7. Presence of a hemoglobinopathy or other condition affecting HbA1c measurement 8. Immediate family member of study site personnel or employees of Sequel Med Tech, DEKA, or affiliated organizations 9. More than 2 severe hypoglycemic events requiring third-party help or hospitalization within the last 6 months 10. More than one DKA or HHS event within the last 6 months 11. Lack of reliable telephone or internet service 12. Known allergy to medical grade adhesives or skin condition precluding use of the study pump or CGM 13. Current participation in another diabetes-related interventional clinical trial 14. Anticipated travel or change of residency for more than 14 days at a time during the study 15. Feasibility Phase only: Clarke Hypoglycemia Awareness Survey score of ≥4 |
| Study Population and Breakdown of Subjects | The study enrolled adults (≥18 years) with insulin-treated Type 2 Diabetes (T2D). A total of: • 340 participants were consented and screened • 307 participants initiated use of the twiist system • 284 participants were included in the primary analysis population |
K262576- Page 6 of 13
{6}
| Study Feature | Description |
| --- | --- |
| | - 223 participants were included in the per-protocol population - 307 participants were included in the safety population |
| Protocol Overview | The study comprised a Feasibility Phase (target ~30 participants) followed by a Main Phase (target ~270 participants). An independent Data and Safety Monitoring Board (DSMB) conducted an interim safety evaluation after 32 Feasibility participants had initiated twiist and 22 Feasibility participants had completed ≥ 3 weeks of twiist use. Following DSMB confirmation that no protocol modifications were required, enrollment proceeded directly into the Main Phase. Participants in both phases were followed for 13 weeks under identical study procedures, and their data were pooled for the final analyses. Following informed consent and eligibility confirmation, participants completed a CGM run-in of 2-3 weeks (which could be skipped by current Libre 3 CGM users), during which they continued their personal insulin regimen. Eligible participants then attended a Baseline visit to initiate use of the twiist system. The initial correction range was based on the participant's mean glucose from the baseline CGM data collection. Subsequent adjustments followed protocol-specified criteria. Virtual visits (phone or video) occurred 2–3 days after twiist initiation, at 7 ± 2 days, 3 weeks ± 4 days, and 6 weeks ± 4 days; an in-clinic visit occurred at 13 weeks ± 4 days. Participants who discontinued twiist were asked to attend an in-clinic early termination visit. The primary efficacy endpoint was change in HbA1c from baseline to 13 weeks, measured by a central laboratory. Patient-reported outcomes were collected at screening and 13 weeks. Participants completed two standardized home meal challenges and three standardized home exercise challenges during the treatment period. |
| Endpoints | Primary Endpoint: Change in HbA1c from baseline to 13 weeks (central laboratory measurement) Key Secondary Endpoints (Hierarchical Testing Order) 1. CGM-measured % time in range 70–180 mg/dL 2. CGM-measured % time in tight range 70–140 mg/dL |
K262576- Page 7 of 13
{7}
| Study Feature | Description |
| --- | --- |
| | 3. CGM-measured % time <54 mg/dL 4. CGM-measured % time <70 mg/dL 5. CGM-measured mean glucose 6. CGM-measured % time >180 mg/dL 7. CGM-measured % time >250 mg/dL 8. CGM-measured % time <70 mg/dL 9. CGM-measured % time <54 mg/dL Exploratory Endpoints - Binary HbA1c thresholds (<7.0%, <7.5%, reduction ≥0.5%, reduction ≥1.0%) - Additional CGM metrics (% time >300 mg/dL, coefficient of variation, prolonged hyperglycemia event rate, hypoglycemia event rate) - Binary CGM responder metrics (TIR >70%, time >180 mg/dL <25%, etc.) - Total daily insulin dose and percentage delivered as basal - Body weight and BMI - Patient-reported outcomes (PROs) |
| Safety Endpoints | Key safety outcomes monitored throughout the study: - Severe hypoglycemia (SH) events - Diabetic Ketoacidosis (DKA) events - Hyperosmolar Hyperglycemic Syndrome (HHS) events - Other Serious Adverse Events (SAEs) - Adverse Device Effects (ADEs) - Unanticipated Adverse Device Effects (UADEs) - CGM-measured time <54 mg/dL - CGM-measured prolonged hyperglycemia event rate per week - CGM-measured hypoglycemia event rate per week |
K262576- Page 8 of 13
{8}
| Study Feature | Description |
| --- | --- |
| Summary of Results | - Primary Efficacy Endpoint: The mean HbA1c decreased from 8.15% ± 1.48% at baseline to 7.40% ± 0.89% at 13 weeks. The mean change from baseline was -0.74% (95% CI -0.88 to -0.61). - Key Secondary Endpoints: Mean time in range 70-180 mg/dL increased from 57% ± 26% at baseline to 72% ± 17% at 13 weeks. The mean change was 15% (95% CI 13% to 18%). - Key Safety Endpoints: No severe hypoglycemia events occurred. There was one DKA event and no device malfunction was identified. |
# Participant Demographics
| | PARTICIPANTS WHO INITIATED TWIST (N=307) |
| --- | --- |
| **Age at enrollment (years)** | |
| Mean ± SD | 58 ± 13 |
| Range | 19 to 85 |
| Age >50 years old n (%) | 235 (77%) |
| **Sex – Female n (%)** | 143 (47%) |
| **Ethnicity n (%)** | |
| Hispanic or Latino | 41 (13%) |
| Not Hispanic or Latino | 265 (86%) |
| Unknown/not reported | 1 (<1%) |
| **Race n (%)** | |
| White | 193 (63%) |
| Black/African American | 78 (25%) |
| Asian | 14 (5%) |
| Native Hawaiian/Other Pacific Islander | 5 (2%) |
| American Indian/Alaskan Native | 1 (<1%) |
| More than one race | 8 (3%) |
| Unknown/not reported | 8 (3%) |
| **Education n (%)** | |
| Less than high school | 9 (3%) |
| High school graduate/diploma/GED | 91 (30%) |
| Technical/vocational | 25 (8%) |
| Associate degree (AA) | 40 (13%) |
| College graduate (Bachelor’s degree or equivalent) | 92 (30%) |
| Advanced degree (e.g. Masters, PhD, MD) | 37 (12%) |
| Unknown | 1 (<1%) |
| Do not wish to provide | 12 (4%) |
K262576- Page 9 of 13
{9}
| | PARTICIPANTS WHO INITIATED TWIST (N=307) |
| --- | --- |
| Annual income n (%) | |
| <$25,000 | 23 (7%) |
| $25,000-<$35,000 | 22 (7%) |
| $35,000-<$50,000 | 24 (8%) |
| $50,000-<$75,000 | 49 (16%) |
| $75,000-<$100,000 | 45 (15%) |
| $100,000-<$200,000 | 65 (21%) |
| $200,000 or more | 19 (6%) |
| Unknown/not reported | 13 (4%) |
| Do not wish to provide | 47 (15%) |
| Insurance n (%) | |
| Private only | 148 (48%) |
| Medicaid only | 29 (9%) |
| Medicare only | 52 (17%) |
| Private and government | 34 (11%) |
| Other government | 31 (10%) |
| No coverage | 1 (<1%) |
Participant Characteristics – T2D Diabetes by Age and Duration
| | PARTICIPANTS WHO INITIATED TWIST (N=307) |
| --- | --- |
| Age at diagnosis of diabetes (years) | |
| Mean ± SD | 39 ± 12 |
| Range | 12 to 71 |
| Diabetes duration at enrollment (years) | |
| <5 years n (%) | 22 (7%) |
| 5-<10 years n (%) | 26 (8%) |
| 10-<20 years n (%) | 126 (41%) |
| ≥20 years n (%) | 133 (43%) |
| Mean ± SD | 19 ± 10 |
| Range | 1 to 51 |
| Central lab HbA1c at baseline | N=305 |
| <7.0% n (%) | 51 (17%) |
| 7.0%-7.9% n (%) | 112 (37%) |
| 8.0%-8.9% n (%) | 74 (24%) |
| 9.0%-9.9% n (%) | 34 (11%) |
| ≥10.0% n (%) | 34 (11%) |
K262576- Page 10 of 13
{10}
| | PARTICIPANTS WHO INITIATED TWIIST (N=307) |
| --- | --- |
| Mean ± SD | 8.2 ± 1.5 |
| Range | 5.2 to 15.5 |
| C-peptide (nmol/L) | N=304 |
| Mean ± SD | 1.13 ± 0.84 |
| Median (Q1, Q3) | 0.95 (0.57, 1.46) |
| Range | <0.007 to 6.48 |
| GAD antibodies n (%) | N=305 |
| <5 IU/mL | 283 (93%) |
| 5-250 IU/mL | 12 (4%) |
| >250 IU/mL | 10 (3%) |
| Any prior automated insulin delivery (AID) use in the last 5 years n (%) | 59 (19%) |
| Any prior non-automated insulin pump use in the last 5 years n (%) | 10 (3%) |
| Insulin modality at baseline n (%) | |
| Pump | 2 (<1%) |
| Basal-bolus injections or inhaled insulin | 223 (73%) |
| Pre-mixed insulin with a rapid component | 7 (2%) |
| Basal-insulin only | 75 (24%) |
| Total daily insulin dose (TDD) at baseline | |
| Mean ± SD (units/kg/day) | 0.76 ± 0.46 |
| Mean ± SD (units/day) | 77 ± 52 |
| Range (units/day) | 5 to 285 |
| >100 units/day n (%) | 81 (26%) |
| Meal bolus method n (%) | |
| Fixed dose | 86 (28%) |
| Small/medium/large | 28 (9%) |
| Carbohydrate counting | 35 (11%) |
| Sliding scale | 72 (23%) |
| Not applicable | 77 (25%) |
| Other | 9 (3%) |
| CGM use at screening n (%) | 258 (84%) |
| CGM use duration n (%) | |
| Not applicable | 49 (16%) |
| <3 months | 19 (6%) |
| 3 months-<1 year | 32 (10%) |
K262576- Page 11 of 13
{11}
| | PARTICIPANTS WHO INITIATED TWIIST (N=307) |
| --- | --- |
| ≥1 year | 207 (67%) |
| CGM device type n (%) | |
| None | 49 (16%) |
| Abbott 14-Day | 2 (<1%) |
| Abbott Libre 2 | 19 (6%) |
| Abbott Libre 3 | 138 (45%) |
| Dexcom G6 | 6 (2%) |
| Dexcom G7 | 93 (30%) |
| Use of non-insulin glucose-lowering medications at enrollment n (%) | |
| None | 41 (13%) |
| Metformin only | 30 (10%) |
| GLP-1ra without SGLT2i | 102 (33%) |
| SGLT2i without GLP-1ra | 45 (15%) |
| GLP-1ra and SGLT2i | 70 (23%) |
| Othera | 19 (6%) |
| BMI (kg/m2) | |
| BMI ≥30 kg/m2n (%) | 193 (63%) |
| Mean ± SD | 34 ± 8 |
| Range | 18 to 61 |
\( ^{a} \) Other non-insulin glucose-lowering medications at enrollment include: sulfonylurea only (N=8), sulfonylurea and metformin (N=4), metformin and thiazolidinedione (N=3), DPP4 only (N=1), DPP4 and metformin (N=1), DPP4 and sulfonylurea (N=1), DPP4, metformin, and sulfonylurea (N=1).
Primary Endpoint Results
| | BASELINE (N=284)a | 13 WEEKS (N=284)a | CHANGE FROM BASELINE (N=284)a |
| --- | --- | --- | --- |
| | Mean ± SD | Mean ± SD | Mean (95% CI)b |
| HbA1c (%) | 8.15 ± 1.48 | 7.40 ± 0.89 | -0.74 (-0.88, -0.61) |
\( ^{a} \) Per the statistical analysis plan, participants were required to have an available HbA1c measurement at baseline and 13 weeks to be included in the analysis of HbA1c.
Secondary CGM-Measured Outcomes
| | BASELINE (N=304)a | 13 WEEKS (N=306)a | CHANGE FROM BASELINE (N=307)b | P-Valueb |
| --- | --- | --- | --- | --- |
| | Mean ± SD | Mean ± SD | Mean (95% CI) | |
K262576- Page 12 of 13
{12}
| CGM hours | 332 ± 12 | 1935 ± 390 | - | - |
| --- | --- | --- | --- | --- |
| % time 70-180 mg/dL | 57% ± 26% | 72% ± 17% | 15% (13%, 18%) | <0.001 |
| % time 70-140 mg/dL | 32% ± 22% | 44% ± 20% | 12% (10%, 14%) | <0.001 |
| % time <54 mg/dL^{c} | 0.02% ± 0.08% | 0.02% ± 0.04% | 0.00% (-0.01%, 0.01%) | <0.001 |
| % time <70 mg/dL^{c} | 0.64% ± 1.22% | 0.35% ± 0.50% | -0.26% (-0.39%, -0.12%) | <0.001 |
| Mean glucose (mg/dL) | 183 ± 51 | 158 ± 26 | -25 (-29, -20) | <0.001 |
| % time >180 mg/dL | 42% ± 26% | 27% ± 17% | -15% (-17%, -13%) | <0.001 |
| % time >250 mg/dL^{c} | 13.1% ± 19.1% | 5.2% ± 6.7% | -7.2% (-8.9%, -5.6%) | <0.001 |
| % time <70 mg/dL^{c} | 0.64% ± 1.22% | 0.35% ± 0.50% | -0.26% (-0.39%, -0.12%) | <0.001 |
| % time <54 mg/dL^{c} | 0.02% ± 0.08% | 0.02% ± 0.04% | 0.00% (-0.01%, 0.01%) | 0.74 |
$^{a}$ Among the 307 participants who initiated the study pump, N=3 at baseline and N=1 at 13 weeks did not have any CGM data available. Summary statistics are based on observed data only.
$^{b}$ N=307 with multiple imputation used to handle the participants who were missing the endpoint at baseline or 13 weeks. Paired t-tests were used to compare the change from baseline to 13 weeks. If the change was not normally distributed, a generalized linear regression model with the t-distribution was used instead of a paired t-test.
$^{c}$ Skewed outcomes. Summary statistics were calculated from an intercept only model assuming a t-distribution with 10 degrees of freedom for the errors in order to down-weight outliers.
### C. Other Supportive Device Performance Characteristics Data
Leveraged from the predicate submission: Software, Cybersecurity, and HF validation.
### 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.
K262576- Page 13 of 13
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.
