Search Results
Found 1 results
510(k) Data Aggregation
(626 days)
The SEM Scanner (Model 200) is intended to be used by healthcare professionals as an adjunct to standard of care when assessing the heels and sacrum of patients who are at increased risk for pressure ulcers.
The SEM Scanner (Model 200) is a hand-held, portable device that consists of a single electrode sensor, an integrated pressure sensor, and hardware and software to run a user interface device screen that displays the device status, battery status, SEM Value, and SEM Delta ("SEM Δ"). The SEM Scanner (Model 200) is pre-calibrated. The SEM Scanner (Model 200) is provided with an inductive charging mat and power supply for recharging the device unit.
The SEM Scanner (Model 200) assesses changes in electrical capacitance of tissue and expresses the result in a SEM Value of 0.3 to 3.9. SEM is a unitless number (not an International System of Unit). The SEM Scanner (Model 200) displays a △ (delta) value after taking a minimum of three (3) SEM Values readings. A minimum of four readings were taken to obtain a result during the supporting clinical studies. The reported SEM A is used as an adjunct to the standard of care when assessing the heels and sacrum of patients who are at increased risk for pressure ulcers.
Here's a breakdown of the acceptance criteria and study details for the SEM Scanner (Model 200), based on the provided text:
Description of Acceptance Criteria and Proving Study
The SEM Scanner (Model 200) is intended to be used by healthcare professionals as an adjunct to standard of care for identifying patients at increased risk for pressure ulcers at the heels or sacrum. The primary effectiveness was evaluated based on the device's ability to detect positive and negative instances related to pressure ulcer development.
1. Table of Acceptance Criteria and Reported Device Performance
| Criteria Category | Criteria Description | Acceptance Value | Reported Device Performance and Confidence Interval | Met? |
|---|---|---|---|---|
| Effectiveness | Positive Detection (Sensitivity): Observation of two or more SEM Δ >0.5 from three consecutive series of SEM Scanner readings prior to pressure ulcer diagnosis by clinical judgment of the Specialist. A sensitivity of at least 0.70 (70%) is defined for positive detection success. | ≥ 0.70 (70%) | 87.4% (95% CI: 77.8%, 96.7%) | Yes |
| Negative Detection (Specificity): Observation of two or more SEM Δ <0.5 from three consecutive series of SEM Scanner readings prior to no pressure ulcer diagnosis by clinical judgment of the Specialist. A specificity of at least 0.55 (55%) is defined for negative detection success. | ≥ 0.55 (55%) | 33.0% (95% CI: 27.6%, 38.7%) | No | |
| Safety | Percentage of device-related adverse events reported in the study. A continued demonstration of no reports of device-related adverse events. | 0% | 0% (No reports of adverse events related to use of the SEM Scanner device units) | Yes |
| Biocompatibility | Skin-contacting materials tested to be biocompatible, not causing irritating, sensitizing, or cytotoxic effects. | No irritating, sensitizing, or cytotoxic effect | Testing conducted per ISO 10993-5:2009 and ISO 10993-10:2010 confirmed: "The device did not cause an irritating, sensitizing or cytotoxic effect upon the skin." | Yes |
| Cleaning/Disinf. | Device withstands repeated exposure to cleaning and disinfection agents without wear-induced failure or degradation. | Maintains functional performance | "Wear testing was conducted to assess wear-induced failure of the device components and potential degradation of the seal material or functional performance due to exposure to cleaning agents used during cleaning and disinfection." (The results implicitly met the criteria as there were no stated issues). | Yes |
| EMC/Electrical S. | Conformance to specified electromagnetic compatibility and electrical safety standards. | Conformance to IEC 60601-1, EN 60601-1-2, EN 60529-1 | Testing confirmed EMC and electrical safety of the device in accordance with IEC 60601-1 (3rd edition), EN 60601-1-2:2001/A1:2006, and EN 60529-1:1992, including specific test parameters for electrostatic discharge, radiated immunity, transient/burst, surge, conducted disturbances, magnetic field immunity, voltage dips, and radiated/conducted emissions. | Yes |
Note on Specificity: While the device did not meet the specificity endpoint of 55%, the FDA still granted the De Novo request, concluding that the probable benefits (high sensitivity) outweigh the probable risks, especially considering its intended use as an adjunct tool.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size (Test Set): 182 subjects contributed to the Intent-to-Treat (ITT) data analysis. These 182 subjects had 437 individual anatomical locations (heels and sacrum) assessed.
- Data Provenance:
- Country of Origin: Nine (9) US centers and three (3) UK centers. 77.8% of subjects were from US centers and 22.2% from UK centers.
- Retrospective or Prospective: Prospective, multi-site, longitudinal, blinded study.
3. Number of Experts and their Qualifications for Ground Truth
- Number of Experts: Multiple "Specialists" at each participating site.
- Qualifications of Experts: The "Specialist" was assigned to nursing staff who were the facility's experts on wound care. Their "clinical judgment of the wound/tissue viability experts" served as the gold standard.
4. Adjudication Method for the Test Set
The ground truth was established by the "clinical judgment of the wound/tissue viability experts" (Specialists). The study design implies a single expert's judgment for each case, as it refers to "the clinical judgment of the Specialist" being the "gold standard." There is no explicit mention of an adjudication process (like 2+1 or 3+1 consensus) among multiple experts for individual cases or the ground truth.
5. Multi Reader Multi Case (MRMC) Comparative Effectiveness Study
No, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not done in the traditional sense of comparing human readers' performance with and without AI assistance to quantify improvement.
The study did compare the SEM Scanner to Standard of Care, Visual Skin Assessment (VSA), but not in a way that directly measures the effect size of how much human readers improve with AI vs. without AI. Instead, it assessed the device's diagnostic performance (sensitivity and specificity) against the gold standard (Specialist's clinical judgment/VSA). The "Generalists" used the SEM Scanner, but their performance with the device was compared against the Specialists' judgment rather than comparing their own performance with and without the device.
6. Standalone (Algorithm Only) Performance
No, a standalone (algorithm only without human-in-the-loop performance) study was not conducted. The device is explicitly intended "to be used by healthcare professionals as an adjunct to standard of care." The study involved "Generalists" taking SEM Scanner readings, and these readings were interpreted in the context of clinical judgment. The acceptance criteria for sensitivity and specificity are based on the device's readings (SEM Δ values) correlating with the Specialist's clinical judgment of the presence or absence of pressure ulcers.
7. Type of Ground Truth Used
The ground truth used was expert consensus / clinical judgment. Specifically, it was "the clinical judgment of the wound/tissue viability experts" (Specialists) who continued "standard of care" evaluations, including pressure ulcer diagnosis based on Visual Skin Assessment (VSA).
8. Sample Size for the Training Set
The document does not specify a training set sample size. The entire clinical study described (189 subjects, 182 ITT for analysis) appears to be the primary dataset used for evaluating the device's performance against predefined endpoints, not specifically for training an algorithm that then undergoes separate testing. Given that the device assesses changes in electrical capacitance and displays a value (SEM Δ) rather than providing a "diagnosis" from an AI algorithm, it's unlikely to have a separate "training set" in the machine learning sense. The device's operational parameters (e.g., the threshold for SEM Δ > 0.5) were likely established through earlier engineering or pre-clinical work, but a formal clinical training set is not mentioned.
9. How the Ground Truth for the Training Set Was Established
As a separate "training set" is not explicitly mentioned for an AI/algorithm in the provided text, the method for establishing ground truth for such a set is also not described. The clinical study described served as the validation for the device's performance based on its inherent mechanism and pre-established thresholds.
Ask a specific question about this device
Page 1 of 1