Nevisense caught nearly all melanomas at low specificity

In FDA's review of Nevisense, the device detected 256 of 267 melanomas (95.9%) at 31.3% specificity, and dermatologists' sensitivity rose from 77.2% to 83.6% with its output.

  • 2 an organization

    Dermatologists' sensitivity for melanoma rose from 77.2% to 83.6% with the device output in the reader study.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

The same dermatologists judging the same lesion images without the device output. Measured.

Without the system
Sensitivity 77.2%
With it
Sensitivity 83.6%
The system’s part
In the reader study each dermatologist judged every lesion without and then with the device output, so the change in sensitivity is attributed to the device. The classifier was developed on measurement data from earlier training studies.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
Nevisense (electrical impedance spectroscopy with a trained lesion classifier)
Made by
SciBase AB
Used by
Dermatology sites in the SIMPS study in Europe and the United States, and 41 US dermatologists in a reader study
Where
Twenty-two dermatology sites in Europe and the United States
Stage
In a pilot
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events
Collections
Scrutiny and findings, Cross-border records
Last revised
31 October 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    U.S. Food and Drug Administration, Center for Devices and Radiological Health. Summary of Safety and Effectiveness Data (SSED), P150046: Nevisense. Approved 2017-06-28.

    The Nevisense device correctly identified 256 melanoma lesions out of 267 melanoma lesions, yielding sensitivity of 95.9%.

Details

AI system

Workflow

Clinicians measured lesions between 2 mm and 20 mm across that dermatologists had already chosen to excise. Readers judged each lesion without the device score first and then with it.

Follow-up

Conditions for replication

The lesion has clinical or historical signs of melanoma and is not clinically obvious melanoma. The skin over the lesion is intact and outside hair-covered areas and special sites such as acral skin.

Entry details

Sector

Healthcare.

Purpose

SciBase built Nevisense to give dermatologists more information about lesions with signs of melanoma when they are considering a biopsy.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Nevisense caught nearly all melanomas at low specificity (AIBD-0791). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0791.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions