Kalman, Justin
(2024)
Beyond Human Limits: The Introduction of Artificial Intelligence Into Screening Mammography to Improve Breast Cancer Detection.
Master Essay, University of Pittsburgh.
Abstract
Radiologists can greatly improve their ability to detect breast cancer, with the integration of artificial intelligence (AI) into the breast cancer screening process. The use of AI within screening mammography can help minimize the frequency of false negative diagnoses of breast cancer, by calling out areas of concern that may otherwise be overlooked. By maximizing the ability to detect breast cancer at an earlier stage, the patient can maximize their ability to receive treatment at a time to control if not eradicate the breast cancer. The early detection of breast cancer can potentially reduce healthcare costs by treating patients at an early stage and avoiding the costs for treatment of cancer that has metastasized.
In the United States, breast cancer is the second leading cause of cancer death in women and is estimated to kill 42,250 women in just 2024 alone (Breast Cancer Statistics, n.d.). Breast cancer can be treated effectively when detected early on, which is why the American Cancer Society (ACS) recommends that women receive a screening mammogram each year. This recommendation has helped to reduce the breast cancer death rate 43% since 1989 (Breast Cancer Statistics, n.d.). Although this is a drastic improvement, not all women are able to receive the intended benefit of a yearly screening due to an epidemic of misdiagnosis.
Upwards of 30% of mammograms are misdiagnosed, causing women to forego treatment that may ultimately save their lives. 85% of the misdiagnoses can be attributed directly to human error, and could have been avoided (Ganesan, Karthikeyan, et al., 2013). In order to reduce human error, we need to provide greater support to radiologists and improve screening mammography. AI has the ability to diagnose patients and provide explanations simple enough for both physicians and patients to understand. While this technology is new and currently still being tested, integration is imperative to ensure that women receive treatment for breast cancer as soon as it’s detectable.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
| Item Type: |
Other Thesis, Dissertation, or Long Paper
(Master Essay)
|
| Status: |
Unpublished |
| Creators/Authors: |
|
| Contributors: |
| Contribution | Contributors Name | Email | Pitt Username | ORCID  |
|---|
| Thesis advisor | Broom, Kevin | kevinbroom@pitt.edu | kevinbroom | UNSPECIFIED | | Committee Member | Ramasubbu, Narayan | narayanr@pitt.edu | narayanr | UNSPECIFIED |
|
| Date: |
17 May 2024 |
| Date Type: |
Completion |
| Submission Date: |
6 April 2024 |
| Access Restriction: |
No restriction; Release the ETD for access worldwide immediately. |
| Number of Pages: |
31 |
| Institution: |
University of Pittsburgh |
| Schools and Programs: |
School of Public Health > Health Policy & Management |
| Degree: |
MHA - Master of Health Administration |
| Thesis Type: |
Master Essay |
| Refereed: |
Yes |
| Uncontrolled Keywords: |
Breast Cancer
Artificial Intelligence
Screening Mammography |
| Date Deposited: |
17 May 2024 18:31 |
| Last Modified: |
17 May 2024 18:31 |
| URI: |
http://d-scholarship.pitt.edu/id/eprint/46043 |
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |
![[feed]](/images/feed-icon-32x32.png){kind=icon}