Yoo, Hyunsuk
Lee, Sang Hyup
Arru, Chiara Daniela
Doda Khera, Ruhani
Singh, Ramandeep
Siebert, Sean
Kim, Dohoon
Lee, Yuna
Park, Ju Hyun
Eom, Hye Joung
Digumarthy, Subba R.
Kalra, Mannudeep K. http://orcid.org/0000-0001-9938-7476
Funding for this research was provided by:
Siemens Healthineers
Riverain Technologies LLC
Lunit Inc.
Article History
Received: 2 February 2021
Revised: 20 March 2021
Accepted: 17 May 2021
First Online: 4 June 2021
Declarations
:
: The scientific guarantor of this publication is Mannudeep K. Kalra.
: Mannudeep K. Kalra has received research grants from Siemens Healthineers and Riverain Technologies LLC for unrelated works. Subba R. Digumarthy reported receiving grants from Lunit during the conduct of the study and providing independent image analysis for hospital-contracted clinical trials for Abbvie, Bristol-Myers Squibb, Cascadian Therapeutics, Clinical Bay Laboratories, Gradalis, Merck, Novartis, Pfizer, Roche, Polaris Pharmaceuticals, and Zai Laboratories, and receiving honoraria from Siemens outside the submitted work. Hyunsuk Yoo and Sanghyup Lee are employees of Lunit, South Korea. No funding was received for this project.
: Soo Young Kwak kindly provided statistical advice for this manuscript. Hyunsuk Yoo carried out actual statistical analysis of the data.
: Written informed consent was waived by the Institutional Review Board.
: Ethics review and approval were obtained from the institutional review board of Massachusetts General Hospital.
: This study was carried out using randomly sampled data of patients enrolled through ACRIN arm of the public National Lung Screening Trial (NLST) dataset, which has been used in prior publications by the NLST investigators and others who have used the public dataset for various research purposes. We are the first to carry out a reader study comparing the performance of readers with and without AI using NLST dataset for the detection of visible lung cancer.
: • retrospective• diagnostic or prognostic study• multicenter study