Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: iProceedings

Date Submitted: Dec 3, 2021
Date Accepted: Dec 3, 2021

The final, peer-reviewed published version of this preprint can be found here:

The Safety and Effectiveness of Elastic Scattering Spectroscopy and Machine Learning in the Evaluation of Skin Lesions for Cancer

Benevenuto-Andrade C, Cognetta A, Manolakos D

The Safety and Effectiveness of Elastic Scattering Spectroscopy and Machine Learning in the Evaluation of Skin Lesions for Cancer

iProc 2021;7(1):e35441

DOI: 10.2196/35441

PMID: 27752094

PMCID: 5067506

Safety and Effectiveness of Elastic Scattering Spectroscopy and Machine Learning in the Evaluation of Skin Lesions for Cancer

  • Cristiane Benevenuto-Andrade; 
  • A Cognetta; 
  • D Manolakos

ABSTRACT

Background:

Elastic-scattering spectroscopy (ESS) is an optical biopsy technique that can distinguish between normal and abnormal tissue in vivo without the need to remove tissue. The handheld device measures ESS spectra of skin lesions and classifies lesions as either malignant or benign with an output of “Investigate Further” or “Monitor”, respectively, with positive results accompanied by a spectral score output from 1-10 indicating how similar the lesion is to malignant lesions the device was trained on. The algorithm was trained and validated with over 11,000 spectral scans from over 3,500 skin lesions.

Objective:

The purpose of the study was to evaluate the safety and effectiveness of the handheld ESS device in detecting the most common types of skin cancers.

Methods:

A prospective, single-arm, investigator-blinded, multi-center study conducted at 4 investigational sites in the US was performed. Patients who presented with skin lesions suggestive to melanoma, basal cell carcinoma, squamous cell carcinoma and other highly atypical lesions were evaluated with the handheld-ESS device. A validation performance analysis was performed with 553 lesions from 350 subjects. An independent test set of 281 lesions were selected and used to evaluate device performance in detection of melanoma, basal cell carcinoma and squamous cell carcinoma. Statistical analyses included overall effectiveness analyses for sensitivity, specificity and subgroup analyses for lesion diagnoses.

Results:

Overall sensitivity of the device was 92.3% (95% CI: 87.1 to 95.5%) Sensitivity for subgroups of lesions was 95% (95% CI 75.1%–99.9%) for melanomas, 94.4% (95% CI 86.3%–98.4%) for BCCs, and 92.5% (95% CI 83.4%–97.5%) for SCCs. Overall device specificity was 36.6% (95% sCI 29.3%–44.6%). There was no statistically significant difference between dermatologist performance and ESS device. Specificity of the device was highest for benign melanocytic nevi (62.5%) and seborrheic keratoses (78.2%). Overall PPV was 59.8% and NPV was 81.9% with the study’s malignancy prevalence rate of 51%. For a prevalence rate of 5%, the PPV is estimated to be 7.1% and NPV is estimated to be 98.9%. For an prevalence rate of 7%, the PPV is estimated to be 9.79% and NPV is estimated to be 98.4%. For a prevalence rate 15%, the PPV is estimated to be 20.3% and NPV is 96.4%.

Conclusions:

The handheld ESS device has a high sensitivity for detection of melanoma, BCC and SCC. Coupled with clinical exam findings, this device can aid physicians in detecting a variety of skin malignancies. The device output can aid teledermatology evaluations by helping frontline providers determine which lesions to share for teledermatologist evaluation as well as potentially benefitting teledermatologists’ virtual evaluation, especially in instances of sub-optimal photo quality.


 Citation

Please cite as:

Benevenuto-Andrade C, Cognetta A, Manolakos D

The Safety and Effectiveness of Elastic Scattering Spectroscopy and Machine Learning in the Evaluation of Skin Lesions for Cancer

iProc 2021;7(1):e35441

DOI: 10.2196/35441

PMID: 27752094

PMCID: 5067506

Per the author's request the PDF is not available.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.