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

Radiology Radiology

Lung ultrasonography for risk stratification in patients with COVID-19: a prospective observational cohort study.

In Clinical infectious diseases : an official publication of the Infectious Diseases Society of America

BACKGROUND : Point-of-care lung ultrasound (LUS) is a promising pragmatic risk stratification tool in COVID-19. This study describes and compares LUS characteristics between patients with different clinical outcomes.

METHODS : Prospective observational study of PCR-confirmed COVID-19 adults with symptoms of lower respiratory tract infection in the emergency department (ED) of Lausanne University Hospital. A trained physician recorded LUS images using a standardized protocol. Two experts reviewed images blinded to patient outcome. We describe and compare early LUS findings (acquired within 24hours of presentation to the ED) between patient groups based on their outcome at 7 days after inclusion: 1) outpatients, 2) hospitalised and 3) intubated/death. Normalized LUS score was used to discriminate between groups.

RESULTS : Between March 6 and April 3 2020, we included 80 patients (17 outpatients, 42 hospitalized and 21 intubated/dead). 73 patients (91%) had abnormal LUS (70% outpatients, 95% hospitalised and 100% intubated/death; p=0.003). The proportion of involved zones was lower in outpatients compared with other groups (median 30% [IQR 0-40%], 44% [31-70%] and 70% [50-88%], p<0.001). Predominant abnormal patterns were bilateral and multifocal spread thickening of the pleura with pleural line irregularities (70%), confluent B lines (60%) and pathologic B lines (50%). Posterior inferior zones were more often affected. Median normalized LUS score had a good level of discrimination between outpatients and others with area under the ROC of 0.80 (95% CI 0.68-0.92).

CONCLUSIONS : Systematic LUS has potential as a reliable, cheap and easy-to-use triage tool for the early risk stratification in COVID-19 patients presenting in EDs.

Brahier Thomas, Meuwly Jean-Yves, Pantet Olivier, Brochu Vez Marie-Josée, Gerhard Donnet Hélène, Hartley Mary-Anne, Hugli Olivier, Boillat-Blanco Noémie


COVID-19, LUS score, Lung ultrasound, Triage tool

Surgery Surgery

TopNet: Topology Preserving Metric Learning for Vessel Tree Reconstruction and Labelling

ArXiv Preprint

Reconstructing Portal Vein and Hepatic Vein trees from contrast enhanced abdominal CT scans is a prerequisite for preoperative liver surgery simulation. Existing deep learning based methods treat vascular tree reconstruction as a semantic segmentation problem. However, vessels such as hepatic and portal vein look very similar locally and need to be traced to their source for robust label assignment. Therefore, semantic segmentation by looking at local 3D patch results in noisy misclassifications. To tackle this, we propose a novel multi-task deep learning architecture for vessel tree reconstruction. The network architecture simultaneously solves the task of detecting voxels on vascular centerlines (i.e. nodes) and estimates connectivity between center-voxels (edges) in the tree structure to be reconstructed. Further, we propose a novel connectivity metric which considers both inter-class distance and intra-class topological distance between center-voxel pairs. Vascular trees are reconstructed starting from the vessel source using the learned connectivity metric using the shortest path tree algorithm. A thorough evaluation on public IRCAD dataset shows that the proposed method considerably outperforms existing semantic segmentation based methods. To the best of our knowledge, this is the first deep learning based approach which learns multi-label tree structure connectivity from images.

Deepak Keshwani, Yoshiro Kitamura, Satoshi Ihara, Satoshi Iizuka, Edgar Simo-Serra


General General

Machine-Learning Guided Quantum Chemical and Molecular Dynamics Calculations to Design Novel Hole Conducting Organic Materials.

In The journal of physical chemistry. A

Materials exhibiting higher mobilities than conventional organic semiconducting materials such as fullerenes and fused thiophenes are in high demand for applications such as printed electronics, organic solar cells, and image sensors. In order to discover new molecules that might show improved charge mobility, combined density functional theory (DFT) and molecular dynamics (MD) calculations were performed, guided by predictions from machine learning (ML). A ML model was constructed based on 32 values of theoretically calculated hole mobilities for thiophene derivatives, benzodifuran derivatives, a carbazole derivative and a perylene diimide derivative with the maximum value of 10-1.96 cm2/(Vs). Sequential learning, also known as active learning, was applied to select compounds on which to perform DFT/MD calculation of hole mobility to simultaneously improve the mobility surrogate model and identify high mobility compounds. By performing 60 cycles of sequential learning with 165 DFT/MD calculations, a molecule having a fused thioacene structure with its calculated hole mobility of 10-1.86 cm2/(Vs) was identified. This values is higher than the maximum value of mobility in the initial training dataset, showing that an extrapolative discovery could be made with the sequential learning.

Antono Erin, Matsuzawa Nobuyuki N, Ling Julia, Saal James Edward, Arai Hideyuki, Sasago Masaru, Fujii Eiji


General General

Machine Learning Guided 3D Printing of Tissue Engineering Scaffolds.

In Tissue engineering. Part A

Various material compositions have been successfully used in 3D printing with promising applications as scaffolds in tissue engineering. However, identifying suitable printing conditions for new materials requires extensive experimentation in a time and resource-demanding process. This study investigates the use of Machine Learning (ML) for distinguishing between printing configurations that are likely to result in low quality prints and printing configurations that are more promising as a first step towards the development of a recommendation system for identifying suitable printing conditions. The ML-based framework takes as input the printing conditions regarding the material composition and the printing parameters and predicts the quality of the resulting print as either "low" or "high". We investigate two ML-based approaches: a direct classification-based approach that trains a classifier to distinguish between "low" and "high" quality prints and an indirect approach that uses a regression ML model that approximates the values of a printing quality metric. Both models are built upon Random Forests. We trained and evaluated the models on a dataset that was generated in a previous study which investigated fabrication of porous polymer scaffolds by means of extrusion-based 3D printing with a full-factorial design. Our results show that both models were able to correctly label the majority of the tested configurations while a simpler linear ML model was not effective. Additionally our analysis showed that a full factorial design for data collection can lead to redundancies in the data, in the context of ML, and we propose a more efficient data collection strategy.

Conev Anja, Litsa Eleni, Perez Marissa, Diba Mani, Mikos Antonios G, Kavraki Lydia


General General

Artificial Intelligence Effecting a Paradigm Shift in Drug Development.

In SLAS technology

The inverse relationship between the cost of drug development and the successful integration of drugs into the market has resulted in the need for innovative solutions to overcome this burgeoning problem. This problem could be attributed to several factors, including the premature termination of clinical trials, regulatory factors, or decisions made in the earlier drug development processes. The introduction of artificial intelligence (AI) to accelerate and assist drug development has resulted in cheaper and more efficient processes, ultimately improving the success rates of clinical trials. This review aims to showcase and compare the different applications of AI technology that aid automation and improve success in drug development, particularly in novel drug target identification and design, drug repositioning, biomarker identification, and effective patient stratification, through exploration of different disease landscapes. In addition, it will also highlight how these technologies are translated into the clinic. This paradigm shift will lead to even greater advancements in the integration of AI in automating processes within drug development and discovery, enabling the probability and reality of attaining future precision and personalized medicine.

Rashid Masturah Bte Mohd Abdul


artificial intelligence, drug development, drug discovery, industry

General General

Mathematical Models of Meal Amount and Timing Variability With Implementation in the Type-1 Diabetes Patient Decision Simulator.

In Journal of diabetes science and technology ; h5-index 38.0

BACKGROUND : In type 1 diabetes (T1D) research, in-silico clinical trials (ISCTs) have proven effective in accelerating the development of new therapies. However, published simulators lack a realistic description of some aspects of patient lifestyle which can remarkably affect glucose control. In this paper, we develop a mathematical description of meal carbohydrates (CHO) amount and timing, with the aim to improve the meal generation module in the T1D Patient Decision Simulator (T1D-PDS) published in Vettoretti et al.

METHODS : Data of 32 T1D subjects under free-living conditions for 4874 days were used. Univariate probability density function (PDF) parametric models with different candidate shapes were fitted, individually, against sample distributions of: CHO amounts of breakfast (CHOB), lunch (CHOL), dinner (CHOD), and snack (CHOS); breakfast timing (TB); and time between breakfast-lunch (TBL) and between lunch-dinner (TLD). Furthermore, a support vector machine (SVM) classifier was developed to predict the occurrence of a snack in future fixed-length time windows. Once embedded inside the T1D-PDS, an ISCT was performed.

RESULTS : Resulting PDF models were: gamma (CHOB, CHOS), lognormal (CHOL, TB), loglogistic (CHOD), and generalized-extreme-values (TBL, TLD). The SVM showed a classification accuracy of 0.8 over the test set. The distributions of simulated meal data were not statistically different from the distributions of the real data used to develop the models (α = 0.05).

CONCLUSIONS : The models of meal amount and timing variability developed are suitable for describing real data. Their inclusion in modules that describe patient behavior in the T1D-PDS can permit investigators to perform more realistic, reliable, and insightful ISCTs.

Camerlingo Nunzio, Vettoretti Martina, Del Favero Simone, Facchinetti Andrea, Sparacino Giovanni


in-silico clinical trials, machine learning, maximum absolute difference, parametric modelling, support vector machine