Opening book details…
Can I read Recalibration of a Deep Learning Model for Low-Dose Computed Tomographic Images to Inform Lung Cancer Screening Intervals on EtoBox?
Recalibration of a Deep Learning Model for Low-Dose Computed Tomographic Images to Inform Lung Cancer Screening Intervals by Rebecca Landy; Vivian L. Wang; David R. Baldwin; Paul F. Pinsky; Li C. Cheung; Philip E. Castle; Martin Skarzynski; Hilary A. Robbins; Hormuzd A. Katki is a Medicine article available to read on EtoBox.
What is Recalibration of a Deep Learning Model for Low-Dose Computed Tomographic Images to Inform Lung Cancer Screening Intervals about?
## Key Points ## Question Can a deep learning algorithm reuse a lung screening low-dose computed tomographic image to safely assign individuals with nodules to 1- vs 2-year screening? ## Findings Using data from 10 831 low-dose computed tomographic images with lung nodules from patients in the National Lung Screening Trial, this diagnostic study showed that a recalibrated deep learning algorithm was able to predict lung cancer diagnosis at a 1-year screen with good discrimination. The deep learning algorithm outperformed current American College of Radiology guidelines and statistical models. ## Meaning These findings suggest that deep learning algorithms could be used to assign individuals to 2-year screening intervals, reducing the harms of screening and potentially making screening cost-effective in some health care systems.
Who reads Recalibration of a Deep Learning Model for Low-Dose Computed Tomographic Images to Inform Lung Cancer Screening Intervals?
It is typically read by researchers, students, and practitioners in Medicine.
- Author
- Rebecca Landy; Vivian L. Wang; David R. Baldwin; Paul F. Pinsky; Li C. Cheung; Philip E. Castle; Martin Skarzynski; Hilary A. Robbins; Hormuzd A. Katki
- Publisher
- American Medical Association (AMA)
- Published
- 2023
- Language
- EN
- Field
- Medicine (Health Sciences)