Tumors are unique and complex ecosystems, in which heterogeneous cell subpopulations with variable molecular profiles, aggressiveness, and proliferation potential coexist and interact. Understanding how heterogeneity influences tumor progression has important clinical implications for improving diagnosis, prognosis, and treatment response prediction. Several recent innovations in data acquisition methods and computational metrics have enabled the quantification of spatiotemporal heterogeneity across different scales of tumor organization. Here, we summarize the most promising efforts from a common experimental and computational perspective, discussing their advantages, shortcomings, and challenges. With personalized medicine entering a new era of unprecedented opportunities, our vision is that of future workflows integrating across modalities, scales, and dimensions to capture intricate aspects of the tumor ecosystem and to open new avenues for improved patient care.

The black-box nature of most artificial intelligence (AI) models encourages the development of explainability methods to engender trust into the AI decision-making process. Such methods can be broadly categorized into two main types: post hoc explanations and inherently interpretable algorithms. We aimed at analyzing the possible associations between COVID-19 and the push of explainable AI (XAI) to the forefront of biomedical research. We automatically extracted from the PubMed database biomedical XAI studies related to concepts of causality or explainability and manually labeled 1,603 papers with respect to XAI categories. To compare the trends pre- and post-COVID-19, we fit a change point detection model and evaluated significant changes in publication rates. We show that the advent of COVID-19 in the beginning of 2020 could be the driving factor behind an increased focus concerning XAI, playing a crucial role in accelerating an already evolving trend. Finally, we present a discussion with future societal use and impact of XAI technologies and potential future directions for those who pursue fostering clinical trust with interpretable machine learning models.

An artificial intelligence–based algorithm trained with mammograms and linked electronic health records classified biopsied breast lesions and may improve personalized care management. Background Computational models based on artificial intelligence (AI) are increasingly used to diagnose malignant breast lesions. However, assessment from radiologic images of the specific patholog...

In response to the outbreak of the coronavirus disease 2019 (Covid-19), governments worldwide have introduced multiple restriction policies, known as non-pharmaceutical interventions (NPIs). However, the relative impact of control measures and the long-term causal contribution of each NPI are still a topic of debate. We present a method to rigorously study the effectiveness of interventions on the rate of the time-varying reproduction number R_t and on human mobility, considered here as a proxy measure of policy adherence and social distancing. We frame our model using a causal inference approach to quantify the impact of five governmental interventions introduced until June 2020 to control the outbreak in 113 countries: confinement, school closure, mask wearing, cultural closure, and work restrictions. Our results indicate that mobility changes are more accurately predicted when compared to reproduction number. All NPIs, except for mask wearing, significantly affected human mobility trends. From these, schools and cultural closure mandates showed the largest effect on social distancing. We also found that closing schools, issuing face mask usage, and work-from-home mandates also caused a persistent reduction on R_t after their initiation, which was not observed with the other social distancing measures. Our results are robust and consistent across different model specifications and can shed more light on the impact of individual NPIs.

In response to the outbreak of the coronavirus disease 2019 (Covid-19), governments worldwide have introduced multiple restriction policies, known as non-pharmaceutical interventions (NPIs). However, the relative impact of control measures and the long-term causal contribution of each NPI are still a topic of debate. We present a method to rigorously study the effectiveness of interventions on the rate of the time-varying reproduction number R _t and on human mobility, considered here as a proxy measure of policy adherence and social distancing. We frame our model using a causal inference approach to quantify the impact of five governmental interventions introduced until June 2020 to control the outbreak in 113 countries: confinement, school closure, mask wearing, cultural closure, and work restrictions. Our results indicate that mobility changes are more accurately predicted when compared to reproduction number. All NPIs, except for mask wearing, significantly affected human mobility trends. From these, schools and cultural closure mandates showed the largest effect on social distancing. We also found that closing schools, issuing face mask usage, and work-from-home mandates also caused a persistent reduction on R _t after their initiation, which was not observed with the other social distancing measures. Our results are robust and consistent across different model specifications and can shed more light on the impact of individual NPIs.

The increasing incidence of renal mass encourages using computational models as accurate noninvasive tools to distinguish between benign and malignant tumors. Besides diagnosis, the relationship between the mass’ appearance on cross-sectional imaging and the patient’s postoperative risk has also shown to be a promising direction to optimize and personalize patient care. Given this premise, this paper aims to identify markers that can be predictive of renal cancer prognosis. As a starting point, we investigated the performance of an average ensemble model to estimate postoperative renal tumor risk and patient’s eligibility to adjuvant therapy. The training dataset consisted of preoperative CT images and linked medical records of 300 individuals with renal tumors who underwent partial or radical nephrectomy between 2011 and 2020. In addition, we developed a Random Forest Classifier model for a clinical feature ablation study. For predicting adjuvant therapy candidacy on the test set of 103 patients, the ensemble model obtained an area under the receiver operating characteristic curve (AUC) of 0.85 (95% confidence interval [CI]: 0.78, 0.92). We found no evidence of a difference between the Random Forest Classifier model trained with all clinical features versus trained only with tumor size measured in CT and nephrometry scores (AUCs, 0.80 [95% CI: 0.70, 0.89] and 0.80 (95% CI: 0.71, 0.90), respectively, P = 0.999). Our results offer supporting evidence that AI applied to CT imaging and medical history can identify higher-risk patients in need of adjuvant treatment. We present the AI systems as benchmark models that allow fair comparisons with future studies that intend to solve similar tasks with different methods or datasets.