Finding new ways to cost-effectively facilitate population screening and improve cancer diagnoses at an early stage supported by data-driven AI models provides unprecedented opportunities to reduce cancer related mortality. This work presents the INCISIVE project initiative towards enhancing AI solutions for health imaging by unifying, harmonizing, and securely sharing scattered cancer-related data to ensure large datasets which are critically needed to develop and evaluate trustworthy AI models. The adopted solutions of the INCISIVE project have been outlined in terms of data collection, harmonization, data sharing, and federated data storage in compliance with legal, ethical, and FAIR principles. Experiences and examples feature breast cancer data integration and mammography collection, indicating the current progress, challenges, and future directions.

Objective. This study evaluates the effectiveness of four machine learning algorithms in classifying physiological stress using heart rate variability (HRV) and pulse rate variability (PRV) time series, comparing an automatic feature selection based on Akaike’s criterion to a physiologically-based feature selection approach. Approach. Linear discriminant analysis, support vector machines, K-nearest neighbors and random forest were applied on ten HRV and PRV indices from time, frequency and information domains, selected with the two feature selection approaches. Data were collected from 127 healthy individuals during different stress conditions (rest, postural and mental stress). Main results. Our results highlight that, while specific stress classification is feasible, distinguishing between postural and mental stress remains challenging. The used classifiers exhibited similar performance, with automatic Akaike Information Criterion-based feature selection proving overall better than the physiology-driven approach. Additionally, PRV-based features performed comparably to HRV-based ones, indicating their potential in outpatient monitoring using wearable devices. Significance. The obtained findings help to determine the most relevant HRV/PRV features for stress classification, potentially useful to highlight different physiological mechanisms involved during both challenges accompanied by a shift in the sympathovagal balance. The proposed approach may have implications for advancing stress assessment methodologies in clinical settings and real-world contexts for well-being evaluation.

Apnea and other breathing-related disorders have been linked to the development of hypertension or impairments of the cardiovascular, cognitive or metabolic systems. The combined assessment of multiple physiological signals acquired during sleep is of fundamental importance for providing additional insights about breathing disorder events and the associated impairments. In this work, we apply information-theoretic measures to describe the joint dynamics of cardiorespiratory physiological processes in a large group of patients reporting repeated episodes of hypopneas, apneas (central, obstructive, mixed) and respiratory effort related arousals (RERAs). We analyze the heart period as the target process and the airflow amplitude as the driver, computing the predictive information, the information storage, the information transfer, the internal information and the cross information, using a fuzzy kernel entropy estimator. The analyses were performed comparing the information measures among segments during, immediately before and after the respiratory event and with control segments. Results highlight a general tendency to decrease of predictive information and information storage of heart period, as well as of cross information and information transfer from respiration to heart period, during the breathing disordered events. The information-theoretic measures also vary according to the breathing disorder, and significant changes of information transfer can be detected during RERAs, suggesting that the latter could represent a risk factor for developing cardiovascular diseases. These findings reflect the impact of different sleep breathing disorders on respiratory sinus arrhythmia, suggesting overall higher complexity of the cardiac dynamics and weaker cardiorespiratory interactions which may have physiological and clinical relevance.

The framework of partial information decomposition (PID) unveils complex nonlinear interactions in network systems by dissecting the mutual information (MI) between a target variable and several source variables. PID measures have been formulated mostly for discrete variables, with only recent extensions to continuous systems. In the case of mixed variables where the target is discrete and the sources are continuous, the application of existing PID schemes requires the manipulation of the data generated by the analyzed system, thus altering their information content. To overcome this issue, we introduce a PID scheme whereby the MI between a specific state of the discrete target and (subsets of) the continuous sources is expressed as a Kullback-Leibler divergence and is estimated through a nearest-neighbor strategy. The effectiveness of this PID is demonstrated in simulated systems of mixed variables and on benchmark data. Our approach is relevant to many scientific problems, including sensory coding in neuroscience and feature selection in machine learning.