Could Artificial Intelligence Be the Future for Skin Cancer Screening?
Posted: Tuesday, April 21, 2020
Patients appear to be receptive to the use of artificial intelligence in screening for non-melanoma, according to a qualitative study published in JAMA Dermatology. “Although additional research is required, the themes that emerged in this study have important implications across the house of medicine,” said Caroline A. Nelson, MD, of the Yale School of Medicine, and colleagues. “Through patients’ eyes, augmented intelligence may improve health-care quality but should be implemented in a manner that preserves the integrity of the human physician-patient relationship.”
A total of 48 patients were enrolled in the study at Brigham and Women’s Hospital and melanoma clinics at the Dana-Farber Cancer Institute. Participants included 26 women and 22 men; there was an even distribution of patients, with some having melanoma, some having non-melanoma, and some with no history of skin cancer. Patients were interviewed about the benefits and risks associated with either direct-to-patient artificial intelligence or clinician decision-support artificial intelligence.
Patients most commonly referred to increased diagnostic speed (60%) and increased health-care access (60%) as the benefits of artificial intelligence for skin cancer screening. Increased anxiety (40%) for patients was the primary risk. The accuracy of diagnosis was perceived to be both the greatest strength (69%) and weakness (85%) of screening with artificial intelligence. For many patients, artificial intelligence offered an increased database of knowledge, but it might lack the context of diagnosis, which could lead to false-positive or false-negative results. Overall, patients believed that a relationship between humans and artificial intelligence could be most beneficial in screening for skin cancer.
“The key finding of our study was that 75% of patients would recommend the use of artificial intelligence for skin cancer screening to friends and family members,” the authors reported. However, “rather than replacing a physician, patients envisioned artificial intelligence referring to a physician and providing a second opinion for a physician.”
Disclosure: For full disclosure of the study authors, visit jamanetwork.com
