K Number
K170585
Device Name
Skylife
Manufacturer
Date Cleared
2017-10-27

(241 days)

Product Code
Regulation Number
880.5700
Panel
HO
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

Skylife™ is intended for the treatment of neonatal unconjugated hyperbilirubinemia. It is designed to provide phototherapy treatment from underneath the baby. Skylife™ must be used within a patient enclosure, such as a bassinet, an open crib, a warming table or an incubator. Skylife™ can be used in a clinical setting or in the home.

Device Description

Skylife™ is a portable phototherapy light system that delivers a narrow band of high-intensity blue light via blue light emitting diodes (LEDs) to provide treatment for neonatal unconjugated hyperbilirubinemia. Skylife™ is designed to provide phototherapy treatment from underneath the baby. The system must be used within a patient enclosure, such as a bassinet, an open crib, a warming table or an incubator. Skylife™ utilizes blue LEDs to achieve intensities from 25 uW/cm²/nm to >55 uW/cm²/nm, emitting light in a narrow bandwidth between 430-475 nm. This light bandwidth corresponds to the spectral absorption of light by bilirubin. Skylife™ utilizes blue LEDs in this range to achieve peak intensities between 25 to 35, and over 55 uw/cm²/nm at low, high settings. Skylife™ at the Very High setting provides an average intensity of 56.3 uw/cm/nm over the treatment area with peak at 72.4 uw /cm-/nm. Treatment is intended to be applied until the bilirubin levels have dropped sufficiently that the child no longer suffers from jaundice. Phototherapy treatment of neonatal jaundice using Skylife™ can be applied at home or in a hospital. Skylife™ consists of the following components: Light bed and light modules, GelMat, disposable mattress cover (Cloud Swaddle), controller, and power supply.

AI/ML Overview

The NeoLight Skylife™ phototherapy unit for neonatal unconjugated hyperbilirubinemia underwent performance testing to demonstrate its substantial equivalence to predicate devices. The studies focused on electrical safety, electromagnetic compatibility, biocompatibility, and human factors usability.

Here's a breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance

Test CategoryAcceptance Criteria (Standard)Reported Device Performance
Electrical SafetyIEC 60601-1: 2005, 3rd Edition (Medical Electrical Equipments for basic safety and essential performance)Device met the standard.
IEC 60601-1-2: 2014, 4th Edition (Electromagnetic compatibility - Requirements and tests)Device met the standard.
IEC 60601-2-50: 2009, 2nd Edition (Particular requirements for the safety of infant phototherapy equipment)Device met the standard.
IEC 60601-1-11: 2015, 2nd Edition (Requirements for medical electrical equipment and medical electrical systems used in the home healthcare environment)Device met the standard.
IEC 60601-1-8: 2006 (General requirements, tests and guidance for alarm systems in medical electrical equipment and medical electrical systems)Device met the standard.
BiocompatibilityISO 10993-1 (Surface Contact, Skin, Prolonged Contact (> 24 hours, 55 μW/cm²/nm (Very High setting, avg 56.3 μW/cm²/nm, max 72.4 μW/cm²/nm)This is a specification, not an acceptance criterion from a performance test against a standard in this section. However, the document states this range is comparable or higher than predicates and does not raise new questions of safety or effectiveness.
Wavelength (Device Specification)430 – 475 nm (453 - 460 nm typical peak)This is a specification. Wavelength range and peak wavelengths overlap with predicate devices, thus not raising new safety/efficacy questions.

2. Sample Sizes Used for the Test Set and Data Provenance

The provided document refers to various performance tests against international standards (IEC and ISO). These types of tests typically involve specific sample sizes prescribed by the standards for evaluating materials, electrical components, and hardware. However, the exact numerical sample sizes for each specific test (e.g., number of units tested for electrical safety, number of material samples for biocompatibility) are not explicitly stated in this summary.

For the Human Factors Usability study:

  • Number of participants: 2 user groups
  • Data provenance: Not explicitly stated, but based on the nature of human factors usability, it would be prospective data collection (users interacting with the device).

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

For the technical performance tests (electrical safety, EMC, biocompatibility), the "ground truth" is established by adherence to the specified international standards. The evaluation is typically performed by trained engineers and technicians in accredited testing facilities. The document does not specify the number or qualifications of experts explicitly.

For the Human Factors Usability study:

  • The document implies that the study was conducted by human factors experts. However, the number of experts used to establish "ground truth" (e.g., identifying usability issues or defining successful use) and their specific qualifications are not provided. The "ground truth" for usability is generally derived from user performance and expert observation against established usability principles.

4. Adjudication Method for the Test Set

The document does not describe specific adjudication methods for the performance tests in the context of clinical endpoints or expert review. For objective technical tests, the results either meet the standard's criteria or they don't, often without a need for "adjudication" in the sense of resolving inter-rater disagreement.

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, the provided document does not describe an MRMC comparative effectiveness study, nor does it mention AI in any context. This device is a phototherapy unit, not an AI-powered diagnostic or assistive tool.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

No, as mentioned, this device is a phototherapy unit and does not involve an algorithm or AI for standalone performance evaluation in that manner.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

  • For Electrical Safety, EMC, and Safety of Infant Phototherapy Equipment: The ground truth is established by the requirements and methodologies defined within the respective IEC standards. Compliance with these standards indicates safety and essential performance.
  • For Biocompatibility: The ground truth is established by the requirements and testing protocols defined within the ISO 10993 series of standards. Non-cytotoxicity, non-sensitization, and non-irritation are the "ground truth" criteria.
  • For Human Factors Usability: The ground truth is established by the requirements of IEC 60601-1-6 and IEC 62366, which focus on preventing use errors and ensuring that the device can be used safely and effectively as intended. User performance during the study, observed errors, and successful task completion against defined criteria form the basis of the ground truth.

8. The Sample Size for the Training Set

This information is not applicable as the device is a phototherapy unit and does not rely on a "training set" in the context of machine learning.

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

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

§ 880.5700 Neonatal phototherapy unit.

(a)
Identification. A neonatal phototherapy unit is a device used to treat or prevent hyperbilirubinemia (elevated serum bilirubin level). The device consists of one or more lamps that emit a specific spectral band of light, under which an infant is placed for therapy. This generic type of device may include supports for the patient and equipment and component parts.(b)
Classification. Class II (performance standards).