Search Results

The Erchonia® FX-635 (Model#: HPS) is low level laser system that uses three semi-conductor diodes (visible red-light) 630nm to 650mm. The Erchonia® FX-635 (Model#: HPS) is a variable hertz device. The variable hertz feature of the Erchonia® FX-635 (Model#: HPS) is a pulsed wave, defined as containing a selected series of breaks, variances that are preprogrammed. The Erchonia® FX 635 (Model#: HPS) has been classified by the FDA/EC as a Class II/Ila device and a Class II/2 Laser.

The Erchonia® FX 635, model: HPS laser is indicated for the adjunctive use in providing temporary relief of nociceptive musculoskeletal pain. The Erchonia® Laser is applied externally and has proven through clinical trials to treat the neck, shoulder, low back and plantar fasciitis.

The components of the device include a mobile base which plugs into the wall, using a hospital grade power cord, equipped with a medical grade transformer. The device runs on AC power of 120 Volt 60 Hz or 220 Volt 50 Hz by plugging to main power. Four (4) antistatic wheels that enable ease for maneuverability. A touch screen that functions as a display screen and input panel. The touch screen communicates with the PCB to initiate, stop or pause the energy flow to the laser diodes. The laser diodes can only be on or off; there is no user interface that allows the end user to alter the laser diode output. The low back protocol and heel pain protocol is factory set and cannot be altered by the end user. The device has an adjustable main arm that is attached to the mobile base with the laser head assembly located at the end. The adjustable main arm is capable to collapse into the mobile base for storage and transporting or extends to position the laser heads above the area of involvement. The laser head assembly that is attached to the adjustable main arm that is manually raised and lowered, utilizes internal mechanics that collects the light emitted from each of the three (3) laser diodes that rotate in a spiraling circle pattern that is totally random and independent of the other diodes. The laser head assembly is positioned 3-4 inches from the patient's skin to deliver treatment for pain. This assembly can be rotated 120 degrees for proper positioning to patient for accurate treatment. The laser head assembly includes arms and pivots that allow the three (3) laser output heads to be rotated, tilted, and raised / lowered independently. The device contains software that is loaded into the PCB drivers. This data includes the touch screen images (GUI) and the command prompts that activate the screen icons; work in conjunction with the component platform to ensure the device operates as intended.

The associated accessories include:

Hospital grade power cord
Patient protective eyewear
Power safety lockout keys

AI/ML Overview

1. A table of acceptance criteria and the reported device performance

Clinical Endpoints	Acceptance Criteria	Reported Device Performance
Pivotal Study 1 (K012580): Neck/Shoulder Pain	Primary Effectiveness Endpoint:	Primary Effectiveness Endpoint:
- Individual Subject Success	Defined as a 30% or greater improvement (decrease) in the primary efficacy measure (change in neck and shoulder pain rating on the 0-100 VAS) from baseline to endpoint.	65.1% of actively treated subjects attained individual success.
- Study Success	Defined as a minimum 30% difference between treatment groups, comparing the proportion of individual successes.	A 53.5% difference between treatment groups was achieved, exceeding the 30% criteria by 23.5% (p<0.0001).
- Mean Change in VAS Rating	(Implied acceptance: statistically significant improvement in actively treated group compared to control)	Magnitude of mean change in neck and shoulder pain VAS rating at endpoint relative to baseline was -29.02 for actively-treated subjects and -4.91 for control subjects, a 20.08 difference (p<0.0005).
Pivotal Study 2 (K132940): Heel Pain	Primary Effectiveness Endpoint:	Primary Effectiveness Endpoint:
- Individual Subject Success	Defined as a 30% or greater improvement (decrease) in the primary efficacy measure (change in 2-day average first steps of the day heel pain on the 0-100 VAS) from baseline to endpoint.	62% of actively treated subjects attained individual success.
- Study Success	Defined as a minimum 35% difference between treatment groups, comparing the proportion of individual successes.	A 49.5% difference between treatment groups was achieved, exceeding the 35% criteria by 19.5% (p<0.00005).
- Mean Change in VAS Rating	(Implied acceptance: statistically significant improvement in actively treated group compared to control)	Magnitude of mean change in 2-day average first steps of the day heel pain VAS rating at endpoint relative to baseline was -29.47 for actively-treated subjects and -5.38 for control subjects, a 24.09 difference (p<0.0001). For actively-treated subjects followed to 12 months, mean change decreased 62.94 points to 6.94 (p<0.0001).
Pivotal Study 3 (K180197): Low Back Pain	Primary Effectiveness Endpoint:	Primary Effectiveness Endpoint:
- Individual Subject Success	Defined as a 30% or greater improvement (decrease) in the primary efficacy measure (change in low back pain rating on the 0-100 VAS) from baseline to endpoint.	72.4% of actively treated subjects attained individual success.
- Study Success	Defined as a minimum 35% difference between treatment groups, comparing the proportion of individual successes.	A 44.8% difference between treatment groups was achieved, exceeding the 35% criteria by 14.8% (p<0.005).
- Mean Change in VAS Rating	(Implied acceptance: statistically significant improvement in actively treated group compared to control)	Magnitude of mean change in low back pain VAS rating at endpoint relative to baseline was -34.24 for actively-treated subjects and -10.97 for control subjects, a 23.37 difference (p<0.001).
Clinical Safety	No treatment-related adverse events.	No treatment-related adverse events were reported or observed for any subject throughout the duration of any of the three studies. No other safety issues occurred.

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

The document refers to three pivotal clinical studies. These studies were prospective, multi-center, randomized, double-blinded, and placebo-controlled multi-arm studies.

Pivotal Study 1 (K012580 - TUCO Erchonia PL2000 for Neck/Shoulder Pain):
- Test Set Sample Size: 86 subjects available for primary endpoint analysis (43 in investigational device arm, 43 in control arm). 100 subjects were initially enrolled.
- Data Provenance: Prospective, multi-center, randomized, double-blinded, and placebo-controlled. Conducted at 3 sites, all in the United States.
Pivotal Study 2 (K132940 - Erchonia Allay™ for Heel Pain):
- Test Set Sample Size: 69 subjects available for primary endpoint analysis (37 in investigational device arm, 32 in control arm). All 69 enrolled subjects were available for primary endpoint analysis.
- Data Provenance: Prospective, multi-center, randomized, double-blinded, and placebo-controlled. Conducted at 2 sites, both in the United States.
Pivotal Study 3 (K180197 - Erchonia® FX-635™ for Low Back Pain):
- Test Set Sample Size: 58 subjects available for primary endpoint analysis (29 in investigational device arm, 29 in control arm). All 58 enrolled subjects were available for primary endpoint analysis.
- Data Provenance: Prospective, multi-center, randomized, double-blinded, and placebo-controlled. Conducted at 3 sites, all in the United States.

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)

The device is a low-level laser system for pain relief, and the acceptance criteria are based on patient-reported pain scores (Visual Analog Scale - VAS) and clinical safety. The "ground truth" in this context is the patient's subjective experience of pain reduction and the absence of adverse events.

Therefore:

No external "experts" (like radiologists interpreting images) were used to establish ground truth.
The ground truth was established directly by the subjects/patients through their self-assessment of pain using the VAS scale.
Clinical investigators (physicians, study coordinators) would have been involved in patient selection, treatment administration, and data collection, but their role was not to "adjudicate" pain scores as experts.

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

The document states that all three pivotal studies were "double-blinded." This means:

Neither the subjects receiving the treatment nor the treatment providers/assessors knew whether the subject was receiving the active device or the placebo. This blinding serves as a form of "adjudication" or bias mitigation by preventing knowledge of treatment assignment from influencing outcome assessment.
The primary outcome measure (VAS pain rating) is a subjective patient-reported outcome. There is no mention of an independent expert adjudication panel for these subjective pain scores as the outcome is directly reported by the patient.

So, the adjudication method was: Double-blinding of subjects and treatment providers/assessors for the patient-reported outcome (VAS pain score). No external "adjudication panel" (like 2+1 or 3+1) was used for the primary endpoints.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done.

This device is a therapeutic laser for pain relief, not an diagnostic imaging or AI-assisted interpretation device. The studies described are clinical trials comparing the device's efficacy against a placebo for pain reduction, not studies involving human readers and AI assistance. Therefore, there is no effect size related to human reader improvement with AI assistance.

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

No, a standalone algorithm-only performance study was not done.

The device is a physical therapeutic device (laser) operated by a clinician on a patient. It is not an algorithm, and its performance is inherently linked to its application by a human healthcare professional in a clinical setting (human-in-the-loop performance). The studies evaluated the device's effect on patients when used as intended.

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

The ground truth used was patient-reported outcomes data, specifically:

Visual Analog Scale (VAS) pain ratings: Subjects self-reported their pain levels on a 0-100 scale.
Clinical Safety Data: Absence of treatment-related adverse events, collected through patient observation and reporting.

8. The sample size for the training set

The document describes clinical studies that are designed to demonstrate safety and effectiveness for regulatory clearance, typically done after significant development. It does not mention a "training set" in the context of machine learning or AI.

The studies described are the pivotal clinical trials used to demonstrate the device's efficacy and safety. The subjects in these trials (ranging from 58 to 86 for primary endpoint analysis per study) constitute the data upon which the claims of effectiveness were based. They are not a "training set" for an AI model.

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

As there is no "training set" in the context of an AI/ML model for this device:

This question is not applicable. The clinical trials are designed to test the device's effectiveness against a placebo, and the "ground truth" (patient pain scores and safety) for these trials was established by the patients themselves and observed safety data, as described in point 7.

Ask a Question

Ask a specific question about this device

Page 1 of 1