Researchers from the Mayo Clinic are sounding the alarm about potential biases in Artificial Intelligence (AI) tools used for cancer detection, warning that they could lead to disparities in diagnosis and treatment outcomes across diverse patient groups. In an editorial published in Oncotarget's Volume 15, authors Yashbir Singh, Heenaben Patel, Diana V. Vera-Garcia, Quincy A. Hathaway, Deepa Sarkar, and Emilio Quaia emphasize the need for fair and equitable healthcare. They caution that AI models trained on limited or non-diverse data may misdiagnose or overlook certain populations, particularly those in underserved communities. For instance, an AI model trained on Caucasian patients may struggle to detect skin cancer accurately in patients with darker skin, leading to missed diagnoses or false positives. The researchers propose a comprehensive approach to developing fair AI models in healthcare, including using diverse datasets, rigorous testing, and transparent decision-making processes. They also urge regulatory bodies, such as the U.S. Food and Drug Administration (FDA), to implement updated frameworks aimed at addressing AI bias in healthcare.
↧