Appendix: Content Summaries of Selected Best Papers for the IMIA Yearbook 2022, Section
Cancer Informatics
Liu R, Rizzo S, Whipple S, Pal N, Pineda AL, Lu M, Arnieri B, Lu Y, Capra W, Copping
R, Zou J
Evaluating eligibility criteria of oncology trials using real-world data and AI
Nature 2021 Apr;592(7855):629-33
A computational framework called Trial Pathfinder was developed and evaluated on a
series of non-small cell lung cancer (NSCLC) trials to determine whether changing
trial eligibility criteria would change the results. The simulations were conducted
using a large real-world data source of 61,094 patients with advanced NSCLC. The authors
determined that relaxing eligibility criteria would result in small changes to hazard
ratios, while potentially expanding the pool of eligible patients by at least two-fold.
This has major implications for the future design of cancer clinical trials.
Yang DX, Khera R, Miccio JA, Jairam V, Chang E, Yu JB, Park HS, Krumholz HM, Aneja
S
Prevalence of missing data in the National Cancer Database and association with overall
survival
JAMA Netw Open 2021 Mar 1;4(3):e211793
The authors assessed the prevalence of missing data in a very large registry of patients
with cancer, and whether missingness in itself was prognostic. They found substantial
missingness, e.g., with 71% of patients with NSCLC missing data for variables of interest.
When compared to patients with complete case data, they found a statistically significant
difference in 2-year overall survival in lung, breast, and prostate cancer. This study
demonstrates the importance of metadata characteristics in the conduct and evaluation
of real-world data registry studies.
