Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Public Health Public Health

Plasma metabolites with mechanistic and clinical links to the neurovascular disease cavernous angioma.

In Communications medicine

BACKGROUND : Cavernous angiomas (CAs) affect 0.5% of the population, predisposing to serious neurologic sequelae from brain bleeding. A leaky gut epithelium associated with a permissive gut microbiome, was identified in patients who develop CAs, favoring lipid polysaccharide producing bacterial species. Micro-ribonucleic acids along with plasma levels of proteins reflecting angiogenesis and inflammation were also previously correlated with CA and CA with symptomatic hemorrhage.

METHODS : The plasma metabolome of CA patients and CA patients with symptomatic hemorrhage was assessed using liquid-chromatography mass spectrometry. Differential metabolites were identified using partial least squares-discriminant analysis (p < 0.05, FDR corrected). Interactions between these metabolites and the previously established CA transcriptome, microbiome, and differential proteins were queried for mechanistic relevance. Differential metabolites in CA patients with symptomatic hemorrhage were then validated in an independent, propensity matched cohort. A machine learning-implemented, Bayesian approach was used to integrate proteins, micro-RNAs and metabolites to develop a diagnostic model for CA patients with symptomatic hemorrhage.

RESULTS : Here we identify plasma metabolites, including cholic acid and hypoxanthine distinguishing CA patients, while arachidonic and linoleic acids distinguish those with symptomatic hemorrhage. Plasma metabolites are linked to the permissive microbiome genes, and to previously implicated disease mechanisms. The metabolites distinguishing CA with symptomatic hemorrhage are validated in an independent propensity-matched cohort, and their integration, along with levels of circulating miRNAs, enhance the performance of plasma protein biomarkers (up to 85% sensitivity and 80% specificity).

CONCLUSIONS : Plasma metabolites reflect CAs and their hemorrhagic activity. A model of their multiomic integration is applicable to other pathologies.

Srinath Abhinav, Xie Bingqing, Li Ying, Sone Je Yeong, Romanos Sharbel, Chen Chang, Sharma Anukriti, Polster Sean, Dorrestein Pieter C, Weldon Kelly C, DeBiasse Dorothy, Moore Thomas, Lightle Rhonda, Koskimäki Janne, Zhang Dongdong, Stadnik Agnieszka, Piedad Kristina, Hagan Matthew, Shkoukani Abdallah, Carrión-Penagos Julián, Bi Dehua, Shen Le, Shenkar Robert, Ji Yuan, Sidebottom Ashley, Pamer Eric, Gilbert Jack A, Kahn Mark L, D’Souza Mark, Sulakhe Dinanath, Awad Issam A, Girard Romuald

2023-Mar-03

General General

Consecutive multiscale feature learning-based image classification model.

In Scientific reports ; h5-index 158.0

Extracting useful features at multiple scales is a crucial task in computer vision. The emergence of deep-learning techniques and the advancements in convolutional neural networks (CNNs) have facilitated effective multiscale feature extraction that results in stable performance improvements in numerous real-life applications. However, currently available state-of-the-art methods primarily rely on a parallel multiscale feature extraction approach, and despite exhibiting competitive accuracy, the models lead to poor results in efficient computation and low generalization on small-scale images. Moreover, efficient and lightweight networks cannot appropriately learn useful features, and this causes underfitting when training with small-scale images or datasets with a limited number of samples. To address these problems, we propose a novel image classification system based on elaborate data preprocessing steps and a carefully designed CNN model architecture. Specifically, we present a consecutive multiscale feature-learning network (CMSFL-Net) that employs a consecutive feature-learning approach based on the usage of various feature maps with different receptive fields to achieve faster training/inference and higher accuracy. In the conducted experiments using six real-life image classification datasets, including small-scale, large-scale, and limited data, the CMSFL-Net exhibits an accuracy comparable with those of existing state-of-the-art efficient networks. Moreover, the proposed system outperforms them in terms of efficiency and speed and achieves the best results in accuracy-efficiency trade-off.

Olimov Bekhzod, Subramanian Barathi, Ugli Rakhmonov Akhrorjon Akhmadjon, Kim Jea-Soo, Kim Jeonghong

2023-Mar-03

General General

Machine learning identifies straightforward early warning rules for human Puumala hantavirus outbreaks.

In Scientific reports ; h5-index 158.0

Human Puumala virus (PUUV) infections in Germany fluctuate multi-annually, following fluctuations of the bank vole population size. We applied a transformation to the annual incidence values and established a heuristic method to develop a straightforward robust model for the binary human infection risk at the district level. The classification model was powered by a machine-learning algorithm and achieved 85% sensitivity and 71% precision, despite using only three weather parameters from the previous years as inputs, namely the soil temperature in April of two years before and in September of the previous year, and the sunshine duration in September of two years before. Moreover, we introduced the PUUV Outbreak Index that quantifies the spatial synchrony of local PUUV-outbreaks, and applied it to the seven reported outbreaks in the period 2006-2021. Finally, we used the classification model to estimate the PUUV Outbreak Index, achieving 20% maximum uncertainty.

Kazasidis Orestis, Jacob Jens

2023-Mar-03

General General

Machine learning classifiers for screening nonalcoholic fatty liver disease in general adults.

In Scientific reports ; h5-index 158.0

Nonalcoholic fatty liver disease (NAFLD) is one of major causes of end-stage liver disease in the coming decades, but it shows few symptoms until it develops into cirrhosis. We aim to develop classification models with machine learning to screen NAFLD patients among general adults. This study included 14,439 adults who took health examination. We developed classification models to classify subjects with or without NAFLD using decision tree, random forest (RF), extreme gradient boosting (XGBoost) and support vector machine (SVM). The classifier with SVM was showed the best performance with the highest accuracy (0.801), positive predictive value (PPV) (0.795), F1 score (0.795), Kappa score (0.508) and area under the precision-recall curve (AUPRC) (0.712), and the second top of area under receiver operating characteristic curve (AUROC) (0.850). The second-best classifier was RF model, which was showed the highest AUROC (0.852) and the second top of accuracy (0.789), PPV (0.782), F1 score (0.782), Kappa score (0.478) and AUPRC (0.708). In conclusion, the classifier with SVM is the best one to screen NAFLD in general population based on the results from physical examination and blood testing, followed by the classifier with RF. Those classifiers have a potential to screen NAFLD in general population for physician and primary care doctors, which could benefit to NAFLD patients from early diagnosis.

Qin Shenghua, Hou Xiaomin, Wen Yuan, Wang Chunqing, Tan Xiaxian, Tian Hao, Ao Qingqing, Li Jingze, Chu Shuyuan

2023-Mar-03

Radiology Radiology

Iodine maps derived from sparse-view kV-switching dual-energy CT equipped with a deep learning reconstruction for diagnosis of hepatocellular carcinoma.

In Scientific reports ; h5-index 158.0

Deep learning-based spectral CT imaging (DL-SCTI) is a novel type of fast kilovolt-switching dual-energy CT equipped with a cascaded deep-learning reconstruction which completes the views missing in the sinogram space and improves the image quality in the image space because it uses deep convolutional neural networks trained on fully sampled dual-energy data acquired via dual kV rotations. We investigated the clinical utility of iodine maps generated from DL-SCTI scans for assessing hepatocellular carcinoma (HCC). In the clinical study, dynamic DL-SCTI scans (tube voltage 135 and 80 kV) were acquired in 52 patients with hypervascular HCCs whose vascularity was confirmed by CT during hepatic arteriography. Virtual monochromatic 70 keV images served as the reference images. Iodine maps were reconstructed using three-material decomposition (fat, healthy liver tissue, iodine). A radiologist calculated the contrast-to-noise ratio (CNR) during the hepatic arterial phase (CNRa) and the equilibrium phase (CNRe). In the phantom study, DL-SCTI scans (tube voltage 135 and 80 kV) were acquired to assess the accuracy of iodine maps; the iodine concentration was known. The CNRa was significantly higher on the iodine maps than on 70 keV images (p < 0.01). The CNRe was significantly higher on 70 keV images than on iodine maps (p < 0.01). The estimated iodine concentration derived from DL-SCTI scans in the phantom study was highly correlated with the known iodine concentration. It was underestimated in small-diameter modules and in large-diameter modules with an iodine concentration of less than 2.0 mgI/ml. Iodine maps generated from DL-SCTI scans can improve the CNR for HCCs during hepatic arterial phase but not during equilibrium phase in comparison with virtual monochromatic 70 keV images. Also, when the lesion is small or the iodine concentration is low, iodine quantification may result in underestimation.

Narita Keigo, Nakamura Yuko, Higaki Toru, Kondo Shota, Honda Yukiko, Kawashita Ikuo, Mitani Hidenori, Fukumoto Wataru, Tani Chihiro, Chosa Keigo, Tatsugami Fuminari, Awai Kazuo

2023-Mar-03

General General

Current and future implications of artificial intelligence in colonoscopy.

In Annals of gastroenterology

Gastrointestinal endoscopy has proved to be a perfect context for the development of artificial intelligence (AI) systems that can aid endoscopists in many tasks of their daily activities. Lesion detection (computer-aided detection, CADe) and lesion characterization (computer-aided characterization, CADx) during colonoscopy are the clinical applications of AI in gastroenterology for which by far the most evidence has been published. Indeed, they are the only applications for which more than one system has been developed by different companies, is currently available on the market, and may be used in clinical practice. Both CADe and CADx, alongside hopes and hypes, come with potential drawbacks, limitations and dangers that must be known, studied and researched as much as the optimal uses of these machines, aiming to stay one step ahead of the possible misuse of what will always be an aid to the clinician and never a substitute. An AI revolution in colonoscopy is on the way, but the potential uses are infinite and only a fraction of them have currently been studied. Future applications can be designed to ensure all aspects of colonoscopy quality parameters and truly deliver a standardization of practice, regardless of the setting in which the procedure is performed. In this review, we cover the available clinical evidence on AI applications in colonoscopy and offer an overview of future directions.

Antonelli Giulio, Rizkala Tommy, Iacopini Federico, Hassan Cesare

2023

Artificial intelligence, adenoma detection rate, colonoscopy, machine learning, polyp detection