AI device may assist primary care physicians in skin cancer detection
Click Here to Manage Email Alerts
Key takeaways:
- The device achieved an overall sensitivity of 97.04%.
- The device had an overall specificity of 26.22%, a negative predictive value of 89.58% and a positive predictive value of 57.4%.
A device using elastic-scattering spectroscopy and artificial intelligence may assist primary care physicians in the quick and accurate detection of skin cancer, according to a study.
“An alternative, noninvasive, handheld device utilizing elastic-scattering spectroscopy (ESS) and artificial intelligence (AI) may augment lesion risk stratification in the primary care setting and increase health care accessibility in resource-constrained settings,” Danielle Manolakos, DO, MPH, of Gold Coast Dermatology Center, and colleagues wrote.
Using an AI algorithm based on an expansive databank of spectral scans of benign and malignant lesions, an ESS device assesses suspicious lesions in fewer than 30 seconds to determine its risk for malignancy.
According to the authors, the ease of using an ESS device with AI, compared with other tools such as dermoscopy and reflectance confocal microscopy, may make it a useful tool for physicians that do not specialize in skin cancer detection.
In a prospective, multi-center validation study, the authors evaluated the safety and efficacy of an ESS device in evaluating suspicious lesions. A total of 614 lesions from 394 participants were included, with 333 of these lesions assigned to the testing group and 281 to the cross-validation group.
The device achieved an overall sensitivity of 97.04%, which the researchers said was not significantly different than the 96.45% sensitivity of dermatologists. The device’s sensitivity for basal cell carcinoma was the highest (97.22%) followed by squamous cell carcinoma (97.01%) and melanoma (96.67%).
Overall, the device had a specificity of 26.22%, a negative predictive value of 89.58% and a positive predictive value of 57.4%.
Since there was no significant difference between the performance of the device and dermatologists, the authors recommended that the device be used to assist primary care clinicians in assessing suspicious lesions.
“Its rapid clinical analysis of lesions (less than 30 seconds) allows for easy integration into clinical practice infrastructures,” the authors wrote. “Proper utilization of this device may aid in the reduction of morbidity and mortality associated with skin cancer through expedited and enhanced detection and intervention.”