Artificial intelligence supporting cancer patients across Europe-The ASCAPE project.

INTRODUCTION: Breast and prostate cancer survivors can experience impaired quality of life (QoL) in several QoL domains. The current strategy to support cancer survivors with impaired QoL is suboptimal, leading to unmet patient needs. ASCAPE aims to provide personalized- and artificial intelligence (AI)-based predictions for QoL issues in breast- and prostate cancer patients as well as to suggest potential interventions to their physicians to offer a more modern and holistic approach on cancer rehabilitation. METHODS AND ANALYSES: An AI-based platform aiming to predict QoL issues and suggest appropriate interventions to clinicians will be built based on patient data gathered through medical records, questionnaires, apps, and wearables. This platform will be prospectively evaluated through a longitudinal study where breast and prostate cancer survivors from four different study sites across the Europe will be enrolled. The evaluation of the AI-based follow-up strategy through the ASCAPE platform will be based on patients' experience, engagement, and potential improvement in QoL during the study as well as on clinicians' view on how ASCAPE platform impacts their clinical practice and doctor-patient relationship, and their experience in using the platform. ETHICS AND DISSEMINATION: ASCAPE is the first research project that will prospectively investigate an AI-based approach for an individualized follow-up strategy for patients with breast- or prostate cancer focusing on patients' QoL issues. ASCAPE represents a paradigm shift both in terms of a more individualized approach for follow-up based on QoL issues, which is an unmet need for cancer survivors, and in terms of how to use Big Data in cancer care through democratizing the knowledge and the access to AI and Big Data related innovations. TRIAL REGISTRATION: Trial Registration on clinicaltrials.gov: NCT04879563.

Scalable Prediction of Acute Myeloid Leukemia Using High-Dimensional Machine Learning and Blood Transcriptomics.

Acute myeloid leukemia (AML) is a severe, mostly fatal hematopoietic malignancy. We were interested in whether transcriptomic-based machine learning could predict AML status without requiring expert input. Using 12,029 samples from 105 different studies, we present a large-scale study of machine learning-based prediction of AML in which we address key questions relating to the combination of machine learning and transcriptomics and their practical use. We find data-driven, high-dimensional approaches-in which multivariate signatures are learned directly from genome-wide data with no prior knowledge-to be accurate and robust. Importantly, these approaches are highly scalable with low marginal cost, essentially matching human expert annotation in a near-automated workflow. Our results support the notion that transcriptomics combined with machine learning could be used as part of an integrated -omics approach wherein risk prediction, differential diagnosis, and subclassification of AML are achieved by genomics while diagnosis could be assisted by transcriptomic-based machine learning.

Controlling for seasonal patterns and time varying confounders in time-series epidemiological models: a simulation study.

An important topic when estimating the effect of air pollutants on human health is choosing the best method to control for seasonal patterns and time varying confounders, such as temperature and humidity. Semi-parametric Poisson time-series models include smooth functions of calendar time and weather effects to control for potential confounders. Case-crossover (CC) approaches are considered efficient alternatives that control seasonal confounding by design and allow inclusion of smooth functions of weather confounders through their equivalent Poisson representations. We evaluate both methodological designs with respect to seasonal control and compare spline-based approaches, using natural splines and penalized splines, and two time-stratified CC approaches. For the spline-based methods, we consider fixed degrees of freedom, minimization of the partial autocorrelation function, and general cross-validation as smoothing criteria. Issues of model misspecification with respect to weather confounding are investigated under simulation scenarios, which allow quantifying omitted, misspecified, and irrelevant-variable bias. The simulations are based on fully parametric mechanisms designed to replicate two datasets with different mortality and atmospheric patterns. Overall, minimum partial autocorrelation function approaches provide more stable results for high mortality counts and strong seasonal trends, whereas natural splines with fixed degrees of freedom perform better for low mortality counts and weak seasonal trends followed by the time-season-stratified CC model, which performs equally well in terms of bias but yields higher standard errors.