Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

The Potential Impact of Artificial Intelligence on Health Disparities in Dermatology: A Literature Review

Henderson, Alexis (2023) The Potential Impact of Artificial Intelligence on Health Disparities in Dermatology: A Literature Review. Master Essay, University of Pittsburgh.

[img] PDF
Restricted to University of Pittsburgh users only until 5 January 2025.

Download (941kB) | Request a Copy


As is the case with many health outcomes, minoritized groups have worse morbidity and mortality rates in a variety of skin conditions compared to their White counterparts. As the field of medicine continues to develop, innovative technology such as the introduction of artificial intelligence into clinical practice is a not-so-distant reality. This is especially the case with specialties dependent on pattern recognition such as dermatology. Since this an emerging sector of medicine, it is important to evaluate the state of current literature on this topic to understand its future impacts on skin health equity. An Ovid-Medline literature search, a hand search using SciWheel-recommended articles, and a Google Scholar hand search yielded 10 articles discussing the health equity impact of using artificial intelligence as a dermatological diagnostic tool among diverse patient populations. While included studies have limitations that make their results difficult to generalize, most included articles demonstrated equally high performances of artificial intelligence models on a wide range of skin colors. All articles pointed towards the necessity of intentionally correcting for biases in the development, training, validation, and testing of artificial intelligence algorithms and models. Current literature in this area primarily focuses on optimizing accuracy, rather than promoting health equity. Future studies in this area including diverse patient populations are needed to determine the most equitable methods of preparing artificial intelligence diagnostic tools for widespread clinical practice, thereby avoiding future health inequities and a broader public health issue.


Social Networking:
Share |


Item Type: Other Thesis, Dissertation, or Long Paper (Master Essay)
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Henderson, Alexisamh314@pitt.eduamh314
ContributionContributors NameEmailPitt UsernameORCID
Committee ChairHill, Ashleyavh16@pitt.eduavh16UNSPECIFIED
Committee MemberJames, Alainajamesaj@upmc.eduUNSPECIFIEDUNSPECIFIED
Committee MemberBrown-Podgorski, Brittanybrittany.brownpodgorski@pitt.edubrittany.brownpodgorskiUNSPECIFIED
Date: 5 January 2023
Date Type: Completion
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 78
Institution: University of Pittsburgh
Schools and Programs: School of Public Health > Epidemiology
Degree: MPH - Master of Public Health
Thesis Type: Master Essay
Refereed: Yes
Date Deposited: 05 Jan 2023 14:28
Last Modified: 05 Jan 2023 14:28


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item