PDF(Pubmed)
Abstract：
The health inequalities experienced by ethnic minorities have been a persistent and global phenomenon. The diagnosis of different types of skin conditions, e.g., melanoma, among people of color is one of such health domains where misdiagnosis can take place, potentially leading to life-threatening consequences. Although Caucasians are more likely to be diagnosed with melanoma, African Americans are four times more likely to present stage IV melanoma due to delayed diagnosis. It is essential to recognize that additional factors such as socioeconomic status and limited access to healthcare services can be contributing factors. African Americans are also 1.5 times more likely to die from melanoma than Caucasians, with 5-year survival rates for African Americans significantly lower than for Caucasians (72.2% vs. 89.6%). This is a complex problem compounded by several factors: ill-prepared medical practitioners, lack of awareness of melanoma and other skin conditions among people of colour, lack of information and medical resources for practitioners\' continuous development, under-representation of people of colour in research, POC being a notoriously hard to reach group, and \'whitewashed\' medical school curricula. Whilst digital technology can bring new hope for the reduction of health inequality, the deployment of artificial intelligence in healthcare carries risks that may amplify the health disparities experienced by people of color, whilst digital technology may provide a false sense of participation. For instance, Derm Assist, a skin diagnosis phone application which is under development, has already been criticized for relying on data from a limited number of people of color. This paper focuses on understanding the problem of misdiagnosing skin conditions in people of color and exploring the progress and innovations that have been experimented with, to pave the way to the possible application of big data analytics, artificial intelligence, and user-centred technology to reduce health inequalities among people of color.
摘要：
少数民族经历的健康不平等一直是一个持续的全球现象。诊断不同类型的皮肤状况，例如，黑色素瘤，有色人种是可能发生误诊的健康领域之一，可能导致危及生命的后果。尽管高加索人更有可能被诊断为黑色素瘤，由于延迟诊断，非洲裔美国人出现IV期黑色素瘤的可能性要高出四倍。必须认识到，社会经济地位和获得医疗保健服务的机会有限等其他因素可能是促成因素。非洲裔美国人死于黑色素瘤的可能性也是白种人的1.5倍，非洲裔美国人的5年生存率明显低于高加索人(72.2%vs.89.6%）。这是一个复杂的问题，加上几个因素：准备不足的医生，有色人种缺乏对黑色素瘤和其他皮肤病的认识，缺乏信息和医疗资源，为从业者的不断发展，有色人种在研究中代表性不足，POC是一个出了名的难以接触的群体，和“粉刷的”医学院课程。虽然数字技术可以为减少健康不平等带来新的希望，人工智能在医疗保健中的部署会带来风险，可能会放大有色人种所经历的健康差距，而数字技术可能会提供一种虚假的参与感。例如,真皮辅助,正在开发的皮肤诊断电话应用程序，已经因为依赖少数有色人种的数据而受到批评。本文着重了解有色人种皮肤状况的误诊问题，并探索已尝试的进展和创新，为大数据分析的可能应用铺平道路，人工智能,和以用户为中心的技术，以减少有色人种之间的健康不平等。
