The Portable Scalp Cooling System (PSCS) is indicated to reduce the likelihood of chemotherapy-induced alopecia in cancer patients with solid tumors. The PSCS is indicated for adult patients only.

The Portable Scalp Cooling System (PSCS) is a wearable device for people undergoing chemotherapy treatment for solid tumor cancer who want to avoid chemotherapy-induced hair loss, or alopecia. Treatment with the PSCS is administered by a user or caregiver in a treatment center, during travel time to the patient's home and in the home setting. It is designed for continual use during the transition from the infusion center to the patient's home. The portable device provides the cooling therapy by circulating a water/isopropyl alcohol (IPA) mixture through a cooling cap worn securely on the patient's head.

The provided text describes a 510(k) summary for the Portable Scalp Cooling System (PSCS). This type of submission focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than presenting a detailed clinical study with specific acceptance criteria for performance metrics like sensitivity, specificity, or reader improvement.

Therefore, the requested information regarding acceptance criteria and a study proving the device meets them, particularly in the context of diagnostic accuracy/performance metrics, is largely not applicable or not available in this document. The document focuses on demonstrating safety and effectiveness through non-clinical testing and comparison to a predicate device.

Here's a breakdown based on the information provided and what is not available:

1. Table of Acceptance Criteria and Reported Device Performance:

No specific "acceptance criteria" for clinical performance metrics (like sensitivity, specificity, or a certain reduction in alopecia percentage) are outlined in this document. The document describes non-clinical testing to ensure the device is as safe and effective as the predicate.

2. Sample Size for the Test Set and Data Provenance:

• Sample Size for Test Set: Not applicable/not provided for clinical performance as no such study is described. The "test set" in this context refers to the non-clinical tests performed.
• Data Provenance: Not applicable for device performance; the non-clinical testing was performed by the manufacturer, Cooler Heads Care, Inc.

3. Number of Experts Used to Establish Ground Truth and Qualifications:

• Number of Experts: Not applicable/not provided. This is relevant for diagnostic devices requiring expert interpretation.
• Qualifications of Experts: Not applicable/not provided.

4. Adjudication Method for the Test Set:

• Adjudication Method: Not applicable/not provided. This is relevant for diagnostic devices where multiple expert opinions are reconciled.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

• MRMC Study: No, an MRMC comparative effectiveness study was not described or referenced. The device is a "Scalp Cooling System," not an AI diagnostic tool that assists human readers.
• Effect Size of Human Readers: Not applicable as no MRMC study was performed.

6. Standalone (Algorithm Only) Performance Study:

• Standalone Study: No, a standalone algorithm performance study was not described or referenced. The PSCS is a physical device, not an algorithm.

7. Type of Ground Truth Used:

• Type of Ground Truth: Not applicable for clinical ground truth. For the non-clinical tests, the "ground truth" was established by adherence to recognized international standards (e.g., IEC, ISO) and comparison to the predicate device's characteristics and performance.

8. Sample Size for the Training Set:

• Sample Size for Training Set: Not applicable. The PSCS is a physical medical device, not an AI/ML algorithm that requires a training set of data.

9. How the Ground Truth for the Training Set was Established:

• Ground Truth for Training Set: Not applicable as there is no training set for an AI/ML algorithm.

In summary: The provided document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device through non-clinical testing. It does not contain information about clinical trials with traditional acceptance criteria for performance metrics, human reader studies, or AI/ML algorithm performance.

Ask a specific question about this device

The DigniCap Delta® Scalp Cooling System is indicated to reduce the likelihood of chemotherapy-induced alopecia in cancer patients with solid tumors.

The DigniCap Delta Scalp Cooling System ("DigniCap Delta")is a device that is intended to function as a cooling system to reduce the likelihood of chemotherapy-induced alopecia in cancer patients with solid tumors. The proposed therapy of the new device is comparable to the therapy of the predicate device, DigniCap Scalp Cooling System (K170871).

DigniCap Delta cools fluid to a prescribed set temperature and circulates that cooled fluid through a cooling wrap and then back to the device. This mode of operation is equivalent to other scalp cooling devices. User operation of the DigniCap Delta system is carried out on the illuminated graphics display with the integrated touch control, located on the front of the unit. The navigation and selection buttons on the display are used to interface with the device.

The provided text is a 510(k) Premarket Notification for the DigniCap Delta Scalp Cooling System. This document focuses on demonstrating substantial equivalence to a predicate device (DigniCap Scalp Cooling System, K170871) rather than establishing new acceptance criteria and proving device performance against them through a clinical study.

Therefore, the requested information (acceptance criteria, study details, sample sizes, expert qualifications, adjudication, MRMC, standalone performance, ground truth, training set information) for a new, independent study demonstrating fundamental device performance against specific acceptance criteria is largely not present in this document.

Instead, the document details non-clinical bench testing to demonstrate that the modifications in the DigniCap Delta (subject device) do not raise new questions of safety or effectiveness compared to the already cleared predicate device.

However, I can extract the information that is present and indicate where the requested information is not applicable or not provided.

Description of Acceptance Criteria and Study to Prove Device Meets Acceptance Criteria

1. Table of acceptance criteria and the reported device performance:

Since this 510(k) relies on substantial equivalence and non-clinical bench testing for minor modifications, there isn't a table of "acceptance criteria" for a new clinical efficacy study in the traditional sense. The "acceptance criteria" are implied by the performance requirements tested during non-clinical bench testing to ensure the device performs as intended and is safe. The "reported device performance" is a summary statement that the device met these requirements.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

• Sample Size for Test Set: Not applicable. No clinical test set (patient-based) was used as this submission relies on non-clinical bench testing and substantial equivalence to a predicate device.
• Data Provenance: Not applicable. The data is from non-clinical bench testing, not patient data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

• Not applicable. There was no clinical test set requiring expert-established ground truth for a diagnostic or treatment outcome. Non-clinical testing results are verified against established engineering and regulatory standards by qualified personnel within the testing process.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

• Not applicable. No clinical test set was used requiring adjudication.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• Not applicable. This device is a scalp cooling system, not an AI diagnostic tool involving human readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

• Not applicable. This device is a physical cooling system, not an algorithm. Its operation is "standalone" in that it performs its cooling function independently, but this is not the typical interpretation of "standalone" performance for an AI/algorithm-based device.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

• For the non-clinical testing, the "ground truth" refers to established engineering specifications, published standards (e.g., ISO 10993-1, IEC 60601 series), and the intended functional performance of the device (e.g., maintaining specific temperatures, correct alarm function).

8. The sample size for the training set:

• Not applicable. This device does not involve a "training set" in the context of machine learning or AI.

9. How the ground truth for the training set was established:

• Not applicable. No training set was used.

Ask a specific question about this device

The Paxman Scalp Cooler is indicated to reduce the likelihood of chemotherapy-induced alopecia (CIA) in cancer patients with solid tumors.

The Paxman Scalp Cooler is a self-contained, mobile, electrically-powered refrigeration unit that circulates a refrigerated liquid coolant, at a pre-set temperature and flow rate, through a cooling cap, which is fitted to the top of the patient's head and connected to the refrigeration unit by a pair of coolant lines. A touchscreen controller with a menu-driven, graphical user interface, integrated into the refrigeration unit, allows the healthcare professional to initiate, monitor, and complete the scalp cooling process.

The provided text is a 510(k) summary for the Paxman Scalp Cooler, which is a medical device intended to reduce chemotherapy-induced alopecia. The document outlines the device's characteristics, indications for use, and a comparison to a predicate device. It also summarizes clinical performance data.

However, the document does not contain the specific information typically associated with acceptance criteria and a study proving a new device meets these criteria in the context of an Artificial Intelligence/Machine Learning (AI/ML) device. Instead, this 510(k) is for an expansion of the indication for use of an already cleared device, stating that "No additional testing was conducted for this 510(k) to support substantial equivalence." The supporting clinical data provided are summaries of existing published and non-published studies, primarily focusing on the device's performance in different patient populations and with various chemotherapy regimens.

Therefore, I cannot extract information related to acceptance criteria, sample sizes for a test set, expert involvement, adjudication methods, MRMC studies, standalone performance, ground truth establishment for novel AI/ML device validation.

The closest I can get to "acceptance criteria" based on the provided text would be the success rates observed in the clinical studies, which demonstrate whether the device performed as intended in reducing alopecia.

Here's an attempt to organize the available relevant information from the document, with caveats where the requested information is not present:

Study Proving Device Meets Acceptance Criteria (as interpreted from a 510(k) for an expanded indication)

The Paxman Scalp Cooler's expanded indication for use (from "women with breast cancer" to "cancer patients with solid tumors") was supported by a review of published and non-published clinical data from the Paxman Scalp Cooling System. This was not a new clinical study specifically designed to establish performance for the expanded indication, but rather a compilation of existing evidence. The previous 510(k) (K163484) for the device's initial clearance would have included performance testing, but the details are not fully provided here, beyond a general statement that "All tests met the pre-determined specifications and acceptance criteria and demonstrated the Paxman Scalp Cooler to be safe and effective as labeled."

1. Table of Acceptance Criteria (Interpreted from Clinical Outcomes) and Reported Device Performance

Since this is a 510(k) for an expanded indication and not a new clinical trial with pre-defined acceptance criteria for a novel device, I will present the success rates and observations from the most relevant studies for showing the device's effectiveness in reducing chemotherapy-induced alopecia for solid tumors. The "acceptance criteria" here are implied by the positive outcomes and conclusions drawn in the existing literature.

• Success rates varied from 8% (TAC chemotherapy) to 95% (paclitaxel treatment).
• For the SCALP study (K163484 predicate), 53.1% (95% CI, 44.5%-61.4%) had successful hair preservation in the cooling group vs. 0% in control group (95% CI, 0%-6.6%).
• Alopecia occurrence with 3-weekly docetaxel: Paxman: 23% vs. No cooling: 74%.
• Alopecia occurrence with weekly docetaxel: Paxman: 7% vs. No cooling: 17%.
• 69.7% of patients completed sensor-controlled scalp cooling, with 58.6% experiencing complete hair preservation (DS 0) and 11.1% partial success (DS 1-2).
• 91.21% overall scalp cooling had excellent results in the Lebanese study, with 6/6 (100%) patients on TAC showing no signs of hair loss. | - Dutch Scalp Cooling Registry (2012, 2017)
• Paxman Coolers Limited SCALP study (Nangia J, et al. 2017)
• Betticher DC, et al. (2013) (Paxman Swiss Clinical Studies of Efficacy)
• Kurbacher CM, et al. (2017)
• Paxman Lebanese Clinical Studies of Efficacy |
  | Patient Tolerability and Comfort | - "Well-tolerated and were infrequently discontinued by patients."
• "The sensation of cold was sometimes reported, no serious adverse events occurred, and patient ratings of cooling therapy were generally favorable."
• SCALP study: 71 device-related adverse events, all grades 1 and 2. No serious device-related adverse events.
• 85% of patients (Massey C, 2004) described it as very comfortable, reasonably comfortable or comfortable.
• 73.3% of patients (El-saka RO, et al., 2009) were comfortable during cooling.
• 5% of patients (Betticher DC, et al., 2013) reported adverse events (most frequently sensation of cold).
• 5% of patients (Paxman UK Clinical Study of Efficacy) discontinued scalp cooling.
• 5% of patients (Paxman Netherlands Clinical Study of Efficacy/2) discontinued due to intolerance. | - General conclusion from clinical literature
• Nangia J, et al. (2017)
• Massey C (2004)
• El-saka RO, et al. (2009)
• Betticher DC, et al. (2013)
• Paxman UK Clinical Study of Efficacy
• Paxman Netherlands Clinical Study of Efficacy/2 |
  | No significant long-term adverse effects (e.g., increased scalp metastasis) | - "No unfavorable development of disease due to scalp cooling has been documented in patients with solid tumors."
• "No difference in overall mortality was observed between scalp-cooled patients and non-scalp-cooled patients."
• Scalp cooling had "no negative effect on survival." | - van den Hurk, CJ, et al. (2013)
• Lemieux J, et al. (2015) |

2. Sample sizes for the test set and data provenance:

• Test Set Sample Sizes:
  • Dutch Scalp Cooling Registry: Over 6000 cancer patients enrolled (since 2006, up to 2017 data points provided in tables). Specific patient counts provided for different years (e.g., n=1411 for 2006-2010, n=4864 for 2010-2015, n=827 for 2015-2017).
  • Paxman Coolers Limited SCALP study (NCT01986140): 182 women with stage 1 or II breast cancer (119 in cooling group, 63 in no cooling group). The publication reports on an interim analysis of n=142 patients (95 in cooling, 47 in control).
  • Massey C (2004): 94 breast cancer patients.
  • Bini M, et al. (2004): 47 breast cancer patients.
  • Betticher DC, et al. (2013): 238 patients with solid tumors (128 Paxman, 77 cool cap, 39 no cooling).
  • Kurbacher CM, et al. (2017): 99 female patients.
  • Silva G, et al. (2016): 20 female patients.
  • Paxman Lebanese Clinical Studies of Efficacy: 91 cancer patients.
• Data Provenance: The studies summarized are from various international locations including the Netherlands (Dutch Registry, Paxman Netherlands studies), UK (Massey C, Paxman UK study), Switzerland (Betticher DC, Paxman Swiss studies), Brazil (Silva G), Lebanon (Paxman Lebanese study), and the US (Nangia J, et al. - SCALP study).
• Retrospective or Prospective:
  • Dutch Scalp Cooling Registry: Retrospective (registry data collection).
  • Paxman Coolers Limited SCALP study (Nangia J, et al.): Randomized, multi-center, prospective clinical trial.
  • Lemieux J, et al. (2015): Retrospective cohort study.
  • Massey C (2004): Open, non-randomized, observational, multi-center.
  • Bini M, et al. (2004): Observational, single-center.
  • Falanga M, et al. (2010): Observational, single-center (pilot study).
  • El-saka RO, et al. (2009): Randomized.
  • Betticher DC, et al. (2013): Open-label, prospective, non-randomized.
  • Kurbacher CM, et al. (2017): Retrospective analysis.
  • Silva G, et al. (2016): Observational.
  • Boyle F, et al. (2015): Focus group/semi-structured interview (qualitative).
  • Kinoshita T, et al. (2015): Case review.
  • Letchford DB, et al. (2016): Ongoing prospective cohort.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

This information is not provided as the summarized studies are clinical trials and observational studies, not typically "ground truth" establishment for an AI/ML algorithm's test set. Hair loss assessment was done by clinicians, nurses, or through patient self-reporting, often using standardized scales (WHO grading system, CTCAE v4.0).

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

This information is not applicable as it's not a reader study for an AI/ML algorithm's test set. Hair loss assessment methods varied by study (e.g., blinded clinician, patient's clinician, patient self-reporting).

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

This information is not applicable. The studies describe the effectiveness of the device (scalp cooler) itself, not the assistance of an AI to human readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

This information is not applicable. The device is a physical cooling system, not a software algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

The "ground truth" for the effectiveness of the device in these studies was primarily clinical outcomes data related to hair preservation (e.g., success defined as not needing a wig/head cover, or specified grades of alopecia using scales like WHO grading system and CTCAE). Safety data involved reporting of adverse events. Survivability data were also used in some studies.

8. The sample size for the training set:

This information is not applicable as the device is a physical medical device, not an AI/ML algorithm that requires a "training set."

9. How the ground truth for the training set was established:

This information is not applicable for the same reason as above.

Ask a specific question about this device

The DigniCap® Scalp Cooling System is indicated to reduce the likelihood of chemotherapy-induced alopecia in cancer patients with solid tumors.

The DigniCap® Scalp Cooling System consists of a computer controlled system that includes a refrigerated tank containing the liquid coolant that is maintained at -7 ± 2°C. The coolant circulates from the cooling unit to and through the channels of the cap and back to the cooling unit. The scalp temperature is monitored by three separate sensors. Deviations from the treatment temperature are automatically adjusted by the system (scalp temperature can be controlled with an accuracy of ± 2.0°C). The DigniCap® Scalp Cooling System components include the following:
Digni C3 – Is a refrigerator unit with an integral control system operated via a touch screen and is capable of controlling two separate DigniCap® Cooling caps independently of each other. Scalp cooling is performed in conjunction with a silicone inner cap (DigniCap®), an outer neoprene cap (DigniTherm), and the liquid coolant (DigniCool).
DigniCap® – A soft, tight-fitting silicone cap which has two separate cooling circuits, one for the front and one for the back of the head. Each cooling circuit is equipped with a temperature sensor, and the cap is also equipped with a third sensor for safety control. The cap is available in different sizes.
DigniCool - The liquid coolant monopropylene glycol.
DigniTherm - The outer neoprene cap that insulates and keeps the inner cap in place. This neoprene cover cap, called the DigniTherm, comes in different sizes and is colored coded to match the corresponding DigniCap® Cooling cap.
DigniStick- A component used to save data from a treatment or for troubleshooting. It can also be used to update software.
DigniCard - A key card which has to be inserted in order to start a treatment.

The provided document is a 510(k) summary for the DigniCap Scalp Cooling System. It focuses on the substantial equivalence to a predicate device and an expanded indication for use.

Based on the document, here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA 510(k) summary for K170871 does not explicitly define acceptance criteria in terms of specific performance metrics (e.g., success rate thresholds) that the device must meet for this specific submission. Instead, it relies on demonstrating substantial equivalence to a previously cleared device (DEN150010) and provides a literature review of clinical studies from outside the U.S. to support the expanded indication for use.

The clinical studies vary in their definitions of success and methods of assessment. Here's a summary of the reported success rates and the conditions under which they were achieved, derived from "Table 1 Clinical Data with the DigniCap® Scalp Cooling System Outside of U.S.":

| Study (Year) | Chemotherapy Regimens (Examples) | Sample Size | Completed Cooling % | Reported Device Performance (% Success with

Ask a specific question about this device

The Paxman Scalp Cooler is indicated to reduce the likelihood of chemotherapy-induced alopecia (CIA) in women with breast cancer.

The Paxman Scalp Cooler is a self-contained, mobile, electrically-powered refrigeration unit that circulates a refrigerated liquid coolant, at a pre-set temperature and flow rate, through a cooling cap, which is fitted to the top of the patient's head and connected to the refrigeration unit by a pair of coolant lines. A touch screen controller with a menu-driven, graphical user interface, integrated into the refrigeration unit, allows the healthcare professional to initiate, monitor, and complete the scalp cooling process.

Two (2) models of the Paxman Scalp Cooler are available:

• . ORBIS I – featuring one pair of coolant lines for attaching a single cooling cap; designed for scalp cooling of one patient at a time; and,
• . ORBIS II – featuring two pairs of coolant lines for attaching two cooling caps; designed for scalp cooling of up to two (2) patients at a time.

The touch screen displays a menu-driven Graphical User Interface (GUI) that provides information to the user concerning the operational status of the scalp cooling unit; it also prompts the user to initiate certain actions relating to the scalp cooling procedure and provides a timer count-down function for scalp cooling sessions. The GUI does not, however, directly control the scalp cooling process as there are pre-established programs for the scalp cooling administration.

The touch screen controller provides feedback to the user concerning the status of the Paxman Scalp Cooler as it relates to achievement of the pre-set temperature of the coolant, operation of the recirculation pump and connection of a cooling cap to the software also provides a timer count-down function for the initiated pre- and post-infusion cooling procedure. At the pre-set time, a message is displayed on the touch screen and a buzzer sounds to alert the fact that the scalp cooling time is complete.

Here's a breakdown of the acceptance criteria and the study proving device performance, based on the provided text:

Acceptance Criteria and Reported Device Performance

Study Details

1. Sample Size used for the test set and the data provenance:

   • Sample Size: 142 evaluable patients (95 in cooling group, 47 in control group).
   • Data Provenance: Prospective, randomized, two-arm study conducted across six (6) clinical sites in the United States.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Number of Experts: Two (a delegated physician or nurse practitioner, and a second independent healthcare provider).
   • Qualifications: "delegated physician or nurse practitioner" and "second independent healthcare provider who is blinded to study treatment." Specific experience levels are not detailed.

3. Adjudication method for the test set:

   • An alopecia assessment was performed "by a delegated physician or nurse practitioner and a second independent healthcare provider who is blinded to study treatment." This implies a form of independent assessment, potentially with reconciliation if there were discrepancies, though the specific adjudication method (e.g., 2+1, 3+1) is not explicitly stated. The "blinded" aspect for the second provider is noted.

4. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • This was not an MRMC comparative effectiveness study involving AI assistance. It was a clinical trial comparing a medical device (scalp cooler) with a control group (no cooling) for reducing chemotherapy-induced alopecia.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • This was not a standalone algorithm-only performance study. It was a device study involving human patients and a physical medical device.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

   • The primary effectiveness ground truth was expert assessment/consensus (alopecia assessment by a delegated physician or nurse practitioner and a second independent healthcare provider) and patient self-report (success in hair preservation by subject self, use of wigs and/or hair wrap, and Quality of Life questionnaires).

7. The sample size for the training set:

   • The document describes a clinical study to evaluate the safety and efficacy of the Paxman Scalp Cooler. It does not mention a "training set" as would be used in an AI/machine learning context. This device is a physical cooling unit, not an AI algorithm, so the concept of a training set is not applicable here.

8. How the ground truth for the training set was established:

   • As this is a physical medical device and not an AI algorithm, there is no "training set" or corresponding ground truth establishment process described in the context of machine learning. The clinical study described in the document served as the performance evaluation for the device itself.

Ask a specific question about this device

The DigniCap™ Scalp Cooling System is indicated to reduce the likelihood of chemotherapy induced alopecia in women with breast cancer.

The Dignitana DigmiCap™ Scalp Cooling System consists of a computer controlled system that includes a refrigerated tank containing the cooling agent that is maintained at -8 ± 1 ℃. The liquid coolant circulates from the cooling unit to and through the channels of the cap and back to the cooling unit. The scalp temperature is monitored by three separate thermometers. Deviations from the pre-set temperature are automatically adjusted by the system (scalp temperature can be controlled with an accuracy of ±2.0℃).

The DigniCap™ Scalp Cooling System components include the following:

Digni C3 system - Is a refrigerator unit with an integral control system operated via a touch screen monitor and is capable of controlling two separate cooling caps independently of each other. Scalp cooling is performed in conjunction with a silicon inner cap (DigniCap™), an outer neoprene cap (DigniTherm™), and the liquid coolant (DigniCool™).

DigniCap™ - A soft, tight-fitting silicon cap which has two separate cooling circuits, one for the front of the head and one for the back of the head plus a third sensor for overall safety control.

DigniCool™ - The liquid coolant monopropylene glycol (MPG5).

DigniTherm™ - The outer neoprene cap that insulates and keeps the inner cap in place. To improve cooling and ensure proper fitting, this cap is covers the DigniCap™ and includes a chin strap which is used to hold the cap in place. This neoprene cover cap, called the DigniTherm™, comes in different sizes and is colored coded to match the corresponding correct silicone Cooling Cap. In addition to acting as a means of maintaining cooling cap placement, this outer cap also provides insulation which improves cooling efficiency

DIGNISTICK™ – A component used to save data from a treatment or for troubleshooting when inserted in the slot. It can also be used to update software.

DIGNICARD™ – A key card which has to be inserted in order to start a treatment.

Acceptance Criteria and Device Performance for DigniCap™ Scalp Cooling System

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance

• Pivotal Study (effectiveness and safety):
  • Test Set Sample Size: 101 evaluable patients in the treatment group, 16 patients in the control group.
  • Data Provenance: Prospective, multi-center (6 sites), concurrent controlled clinical study conducted in the U.S. (based on the FDA De Novo submission context).
• Feasibility Study (safety and feasibility):
  * Test Set Sample Size: 19 evaluable patients.
  * Data Provenance: Prospective, 2-site clinical study conducted in the U.S.

3. Number of Experts and Qualifications for Ground Truth

• Pivotal Study:
  • For the primary effectiveness endpoint (Dean score ≤ 2), the assessment was based on patient self-assessment of standardized photographs. This does not involve independent expert grading in the primary outcome.
  • For an independent secondary assessment, "An independent panel review of the photographs was conducted and 73 patients (72%) were rated as treatment successes." The qualifications of these panel members are not specified in the provided text.
• Feasibility Study:
  • Hair loss was assessed by an independent panel consisting of: a hair dresser, a patient advocate, and a dermatologist specializing in hair. The number of experts within this panel is three. Specific years of experience are not provided for the individual experts.

4. Adjudication Method for the Test Set

• Pivotal Study: The primary endpoint was patient self-assessment against standardized photographs. This implies individual assessment rather than a consensus or adjudication method among multiple graders for the primary endpoint. For the independent panel review (secondary), the adjudication method is not described beyond "review of photographs."
• Feasibility Study: Hair loss assessment was done by an "independent panel" by "review of photographs blinded to patient and sequence." The specific adjudication method (e.g., majority vote, discussion to consensus) is not specified.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• A MRMC comparative effectiveness study, in the typical sense of evaluating human reader performance with and without AI assistance, was not performed.
• The pivotal study was a controlled clinical trial comparing the device (with human users) to a control group without the device. The "effect size of how much human readers improve with AI vs without AI assistance" is not applicable as this is a device for patients, not an AI diagnostic tool for readers. The study did, however, demonstrate a significant improvement in hair retention for patients using the device compared to those who did not.

6. Standalone (Algorithm Only) Performance

• A standalone (algorithm only) performance study was not performed or is not applicable in this context. The DigniCap™ Scalp Cooling System is a physical device used by patients, not an AI algorithm intended for automated analysis. The "software" component mentioned in the device description primarily controls cooling mechanisms, not performs diagnostic analysis.

7. Type of Ground Truth Used

• Pivotal Study (Primary Endpoint): Patient self-assessment based on the Dean Scale using standardized photographs.
• Pivotal Study (Secondary Independent Assessment): Independent panel review of photographs based on the Dean Scale.
• Feasibility Study: Independent panel review of photographs based on the Dean Scale, and also patient assessment following the Dean Scale.

8. Sample Size for the Training Set

• The provided text describes clinical studies (feasibility and pivotal) that serve as testing for the device's efficacy and safety. It does not describe a "training set" in the context of machine learning. The DigniCap™ is a mechanical device with software controls, not a machine learning model that requires a training set of data to learn from.

9. How the Ground Truth for the Training Set was Established

• As explained above, there is no mention of a "training set" in the machine learning sense in the provided document. The clinical studies represent testing of the device's performance, not training of an algorithm.

Ask a specific question about this device