 An algorithm recently developed to predict survival and lung cancer has now been tested using real patient tissue. Early evidence suggests that the algorithm could help identify patients with non-small cell lung cancer who are at high risk of recurrence and who might benefit from add-on treatments. The findings are reported by researchers from the Worldwide Innovative Networking Consortium. Lung cancer is the deadliest form of cancer in the world. Part of the reason why is that in its early stages, lung cancer tends to be asymptomatic. By the time patients are diagnosed, most tumors are locally advanced or metastatic. What's more, even among early-stage patients treated by surgery, approximately half will die of metastatic recurrence. The digital display precision predictor algorithm, or DDPP, was designed to improve those odds. Based on transcriptomic and clinical outcome data for patients with advanced lung cancer, the algorithm predicts the duration of post-surgery disease-free survival for patients with early-stage lung cancer. It also predicts the duration of progression-free survival for multiple targeted treatments in patients with locally advanced or metastatic lung cancers. In the first clinical application of the DDPP algorithm, its designers examined lung tissue from 120 patients with primary resected, non-small cell lung cancer. That analysis produced a DDPP score describing a combination of key genes that predicted disease-free survival. A low score correlated with shorter disease-free survival, making it a potentially important biomarker for guiding treatment decisions in the clinic. Going further, by combining tumor-specific genes and, for the first time, the immune status of normal lung tissue, the WYN consortium team gained new insight into how disease-free survival varied among patients. Patients with the shortest survival were those with a low tumor-based DDPP score and tissue considered normal but characterized by a weak immune response, making it difficult to recognize and eliminate cancer cells. On a genetic level, the overexpression of the genes CTLA4, PDL1, and ICOS were the key drivers of such immune-tolerant tissue, predicting significantly shorter survival. While further validation is required, the findings are promising. Because the approach requires only tumor and normal tissue gathered during surgery without additional biopsy, it could be easy to implement in the clinic. And it might be adaptable to other types of solid tumors beyond lung cancer. The ability to accurately identify patients at higher risk of cancer recurrence is powerful. Tools like the DDPP algorithm are helping the WYN consortium open avenues toward new therapeutic options that can significantly improve the post-surgery outcomes of patients with lung or other cancers.