Lung cancer remains a leading cause of cancer-related deaths globally, with non-small cell lung cancer (NSCLC) being the most common subtype. This study aimed to identify key biomarkers associated with stage III NSCLC in non-smoking females using gene expression profiling from the GDS3837 dataset. Utilizing XGBoost, a machine learning algorithm, the analysis achieved a strong predictive performance with an AUC score of 0.835. The top biomarkers identified - CCAAT enhancer binding protein alpha (C/EBP-alpha), lactate dehydrogenase A4 (LDHA), UNC-45 myosin chaperone B (UNC-45B), checkpoint kinase 1 (CHK1), and hypoxia-inducible factor 1 subunit alpha (HIF-1-alpha) - have been validated in the literature as being significantly linked to lung cancer. These findings highlight the potential of these biomarkers for early diagnosis and personalized therapy, emphasizing the value of integrating machine learning with molecular profiling in cancer research.

Identifying predictive biomarkers, which forecast individual treatment effectiveness, is crucial for personalized medicine and informs decision-making across diverse disciplines. These biomarkers are extracted from pre-treatment data, often within randomized controlled trials, and have to be distinguished from prognostic biomarkers, which are independent of treatment assignment. Our study focuses on the discovery of predictive imaging biomarkers, aiming to leverage pre-treatment images to unveil new causal relationships. Previous approaches relied on labor-intensive handcrafted or manually derived features, which may introduce biases. In response, we present a new task of discovering predictive imaging biomarkers directly from the pre-treatment images to learn relevant image features. We propose an evaluation protocol for this task to assess a model's ability to identify predictive imaging biomarkers and differentiate them from prognostic ones. It employs statistical testing and a comprehensive analysis of image feature attribution. We explore the suitability of deep learning models originally designed for estimating the conditional average treatment effect (CATE) for this task, which previously have been primarily assessed for the precision of CATE estimation, overlooking the evaluation of imaging biomarker discovery. Our proof-of-concept analysis demonstrates promising results in discovering and validating predictive imaging biomarkers from synthetic outcomes and real-world image datasets.

Scientists at Case Western Reserve University have used Artificial Intelligence (AI) to identify new biomarkers for breast cancer that can predict whether the cancer will return after treatment--and which can be identified from routinely acquired tissue biopsy samples of early-stage breast cancer. The key to that initial determination is collagen, a common protein found throughout the body, including in breast tissue. Previous research had suggested that the collagen network, or arrangement of the fibers, relates strongly to breast cancer aggressiveness. But this work by Case Western Reserve researchers definitively demonstrated collagen's critical role--using only standard tissue biopsy slides and AI. The researchers, using machine-learning technology to analyze a dataset of digitized tissue samples from breast cancer patients, were able to prove that a well-ordered arrangement of collagen is a key prognostic biomarker for an aggressive tumor and a likely recurrence.

Yoshua Bengio, Founder of Mila and computer science professor at University of Montreal, will support the ongoing research of Perceiv AI in precision medicine to improve and optimize drug development clinical trials. Founded by graduate students out of University of Montreal and Mila, Perceiv AI aims to improve treatment efficacy thanks to refined patient selection. Through advanced Machine Learning algorithms, Perceiv AI helps pharmaceutical companies with more efficient and accurate subject stratification for their clinical trials. Heterogeneity in patient populations creates challenges in enrolment for clinical trials, which can result in increased trial costs and failures, delaying the commercialization of much-needed treatments. "For having seen the ravages of diseases like Alzheimer's from up close, I am very motivated to see more development of AI techniques, such as done at Perceiv AI, to provide better targeted treatments, and I am delighted to see the next generation of AI researchers embarking on such projects of important value for society while contributing to grow the startup ecosystem in Montreal," said Yoshua Bengio, Ph.D. "We are thrilled to reinforce our relationship with Mila and to welcome Yoshua as an advisor!" said Christian Dansereau, Ph.D., CEO and co-founder of Perceiv AI. "With their help, we will be able to leverage the most recent advances in Representation Learning to further refine our prognostic biomarkers, not only for Alzheimer's but also for new therapeutic areas."

James Weatherall Advanced Analytics Centre, Global Medicines Development, AstraZeneca james.weatherall@astrazeneca.com We study information theoretic methods for ranking biomarkers. In clinical trials there are two, closely related, types of biomarkers: predictive and prognostic, and disentangling them is a key challenge. Our first step is to phrase biomarker ranking in terms of optimizing an information theoretic quantity. This formalization of the problem will enable us to derive rankings of predictive/prognostic biomarkers, by estimating different, high dimensional, conditional mutual information terms. To estimate these terms, we suggest efficient low dimensional approximations, and we derive an empirical Bayes estimator, which is suitable for small or sparse datasets. Finally, we introduce a new visualisation tool that captures the prognostic and the predictive strength of a set of biomarkers. We believe this representation will prove to be a powerful tool in biomarker discovery.