Search

Radiomics is the quantitative analysis of standard-of-care medical imaging; the information obtained can be applied within clinical decision support systems to create diagnostic, prognostic, and/or predictive models. Radiomics analysis can be performed by extracting hand-crafted radiomics features or via deep learning algorithms. Radiomics has evolved tremendously in the last decade, becoming a bridge between imaging and precision medicine. Radiomics exploits sophisticated image analysis tools coupled with statistical elaboration to extract the wealth of information hidden inside medical images, such as computed tomography (CT), magnetic resonance (MR), and/or Positron emission tomography (PET) scans, routinely performed in the everyday clinical practice. Many efforts have been devoted in recent years to the standardization and validation of radiomics approaches, to demonstrate their usefulness and robustness beyond any reasonable doubts. However, the booming of publications and commercial applications of radiomics approaches warrant caution and proper understanding of all the factors involved to avoid "scientific pollution" and overly enthusiastic claims by researchers and clinicians alike. For these reasons the present review aims to be a guidebook of sorts, describing the process of radiomics, its pitfalls, challenges, and opportunities, along with its ability to improve clinical decision-making, from oncology and respiratory medicine to pharmacological and genotyping studies.

The coronavirus disease 2019 (COVID-19) outbreak has reached pandemic status. Drastic measures of social distancing are enforced in society and healthcare systems are being pushed to and beyond their limits. To help in the fight against this threat on human health, a fully automated AI framework was developed to extract radiomics features from volumetric chest computed tomography (CT) exams. The detection model was developed on a dataset of 1381 patients (181 COVID-19 patients plus 1200 non COVID control patients). A second, independent dataset of 197 RT-PCR confirmed COVID-19 patients and 500 control patients was used to assess the performance of the model. Diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC). The model had an AUC of 0.882 (95% CI: 0.851&ndash, 0.913) in the independent test dataset (641 patients). The optimal decision threshold, considering the cost of false negatives twice as high as the cost of false positives, resulted in an accuracy of 85.18%, a sensitivity of 69.52%, a specificity of 91.63%, a negative predictive value (NPV) of 94.46% and a positive predictive value (PPV) of 59.44%. Benchmarked against RT-PCR confirmed cases of COVID-19, our AI framework can accurately differentiate COVID-19 from routine clinical conditions in a fully automated fashion. Thus, providing rapid accurate diagnosis in patients suspected of COVID-19 infection, facilitating the timely implementation of isolation procedures and early intervention.

The coronavirus disease 2019 (COVID-19) outbreak has reached pandemic status and pushed healthcare systems beyond the limits. We aim to develop a fully automatic framework to detect COVID-19 by applying artificial intelligence (AI). A fully automated AI framework was developed to extract radiomics features from chest CT scans to detect COVID-19 patients. We curated and analysed the data from a total of 1381 patients. A cohort of 181 RT-PCR confirmed COVID-19 patients and 1200 control patients was included for model development. An independent dataset of 697 patients was used to validate the model. The datasets were collected from CHU Liege, Belgium. Model performance was assessed by the area under the receiver operating characteristic curve (AUC). Assuming 15% disease prevalence, a comprehensive analysis of classification performance in terms of accuracy, sensitivity, specificity, negative predictive value (NPV) and positive predictive value (PPV) was performed for all possible decision thresholds. The final curated dataset used for model development and testing consisted of chest CT scans of 1224 patients and 641 patients, respectively. The model had an AUC of 0.882 (95% CI: 0.851-0.913) in the independent test dataset. Assuming the cost of false negatives is twice as high as the cost of false positives, the optimal decision threshold resulted in an accuracy of 85.18%, a sensitivity of 69.52, a specificity of 91.63%, an NPV of 94.46% and a PPV of 59.44%. Our AI framework can accurately detect COVID-19. Thus, providing rapid accurate diagnosis in patients suspected of COVID-19 infection, facilitating the implementation of isolation procedures and early intervention.

Leukocyte telomere length (LTL) is a heritable biomarker of genomic aging. In this study, we perform a genome-wide meta-analysis of LTL by pooling densely genotyped and imputed association results across large-scale European-descent studies including up to 78,592 individuals. We identify 49 genomic regions at a false dicovery rate (FDR) < 0.05 threshold and prioritize genes at 31, with five highlighting nucleotide metabolism as an important regulator of LTL. We report six genome-wide significant loci in or near SENP7, MOB1B, CARMIL1, PRRC2A, TERF2, and RFWD3, and our results support recently identified PARP1, POT1, ATM, and MPHOSPH6 loci. Phenome-wide analyses in >350,000 UK Biobank participants suggest that genetically shorter telomere length increases the risk of hypothyroidism and decreases the risk of thyroid cancer, lymphoma, and a range of proliferative conditions. Our results replicate previously reported associations with increased risk of coronary artery disease and lower risk for multiple cancer types. Our findings substantially expand current knowledge on genes that regulate LTL and their impact on human health and disease.

The utility of Artificial Intelligence (AI) in healthcare strongly depends upon the quality of the data used to build models, and the confidence in the predictions they generate. Access to sufficient amounts of high-quality data to build accurate and reliable models remains problematic owing to substantive legal and ethical constraints in making clinically relevant research data available offsite. New technologies such as distributed learning offer a pathway forward, but unfortunately tend to suffer from a lack of transparency, which undermines trust in what data are used for the analysis. To address such issues, we hypothesized that, a novel distributed learning that combines sequential distributed learning with a blockchain-based platform, namely Chained Distributed Machine learning C-DistriM, would be feasible and would give a similar result as a standard centralized approach. C-DistriM enables health centers to dynamically participate in training distributed learning models. We demonstrate C-DistriM using the NSCLC-Radiomics open data to predict two-year lung-cancer survival. A comparison of the performance of this distributed solution, evaluated in six different scenarios, and the centralized approach, showed no statistically significant difference (AUCs between central and distributed models), all DeLong tests yielded p-val > 0.05. This methodology removes the need to blindly trust the computation in one specific server on a distributed learning network. This fusion of blockchain and distributed learning serves as a proof-of-concept to increase transparency, trust, and ultimately accelerate the adoption of AI in multicentric studies. We conclude that our blockchain-based model for sequential training on distributed datasets is a feasible approach, provides equivalent performance to the centralized approach.

Using a genome-wide screen of 9.6 million genetic variants achieved through 1000 Genomes Project imputation in 62,166 samples,we identify association to lipid traits in 93 loci, including 79 previously identified loci with new lead SNPs and 10 new loci, 15 loci with a low-frequency lead SNP and 10 loci with a missense lead SNP, and 2 loci with an accumulation of rare variants. In six loci,SNPs with established function in lipid genetics (CELSR2, GCKR, LIPC and APOE) or candidate missense mutations with predicted damaging function (CD300LG and TM6SF2) explained the locus associations. The low-frequency variants increased the proportion of variance explained, particularly for low-density lipoprotein cholesterol and total cholesterol. Altogether, our results highlight the impact of low-frequency variants in complex traits and show that imputation offers a cost-effective alternative to resequencing. Refereed/Peer-reviewed

Big data for health care is one of the potential solutions to deal with the numerous challenges of health care, such as rising cost, aging population, precision medicine, universal health coverage, and the increase of noncommunicable diseases. However, data centralization for big data raises privacy and regulatory concerns. Covered topics include (1) an introduction to privacy of patient data and distributed learning as a potential solution to preserving these data, a description of the legal context for patient data research, and a definition of machine/deep learning concepts; (2) a presentation of the adopted review protocol; (3) a presentation of the search results; and (4) a discussion of the findings, limitations of the review, and future perspectives. Distributed learning from federated databases makes data centralization unnecessary. Distributed algorithms iteratively analyze separate databases, essentially sharing research questions and answers between databases instead of sharing the data. In other words, one can learn from separate and isolated datasets without patient data ever leaving the individual clinical institutes. Distributed learning promises great potential to facilitate big data for medical application, in particular for international consortiums. Our purpose is to review the major implementations of distributed learning in health care.