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

General General

Machine-learning-based computationally efficient particle size distribution retrieval from bulk optical properties.

In Applied optics

Retrieval of particle size distribution from bulk optical properties based on evolutionary algorithms is usually computationally expensive. In this paper, we report an efficient numerical approach to solving the inverse scattering problem by accelerating the calculation of bulk optical properties based on machine learning. With the assumption of spherical particles, the forward scattering by particles is first solved by Mie scattering theory and then approximated by machine learning. The particle swarm optimization algorithm is finally employed to optimize the particle size distribution parameters by minimizing the deviation between the target and simulated bulk optical properties. The accuracies of machine learning and particle swarm optimization are separately investigated. Meanwhile, both monomodal and bimodal size distributions are tested, considering the influences of random noise. Results show that machine learning is capable of accurately predicting the scattering efficiency for a specific size distribution in approximately 0.5 µs on a standalone computer. Therefore, the proposed method has the potential to serve as a powerful tool in real-time particle size measurement due to its advantages of simplicity and high efficiency.

Jia Ruhui, Zhang Xiaohao, Cui Fenping, Chen Gongye, Li Haomiao, Peng Haochen, Cao Zhaolou, Pei Shixin

2020-Aug-20

General General

On-machine surface defect detection using light scattering and deep learning.

In Journal of the Optical Society of America. A, Optics, image science, and vision

This paper presents an on-machine surface defect detection system using light scattering and deep learning. A supervised deep learning model is used to mine the information related to defects from light scattering patterns. A convolutional neural network is trained on a large dataset of scattering patterns that are predicted by a rigorous forward scattering model. The model is valid for any surface topography with homogeneous materials and has been verified by comparing with experimental data. Once the neural network is trained, it allows for fast, accurate, and robust defect detection. The system capability is validated on microstructured surfaces produced by ultraprecision diamond machining.

Liu Mingyu, Fai Cheung Chi, Senin Nicola, Wang Shixiang, Su Rong, Leach Richard

2020-Sep-01

General General

Validity and Usability of a Smartphone Image-Based Dietary Assessment App Compared to 3-Day Food Diaries in Assessing Dietary Intake Among Canadian Adults: Randomized Controlled Trial.

In JMIR mHealth and uHealth

BACKGROUND : Accurate dietary assessment is needed in studies that include analysis of nutritional intake. Image-based dietary assessment apps have gained in popularity for assessing diet, which may ease researcher and participant burden compared to traditional pen-to-paper methods. However, few studies report the validity of these apps for use in research. Keenoa is a smartphone image-based dietary assessment app that recognizes and identifies food items using artificial intelligence and permits real-time editing of food journals.

OBJECTIVE : This study aimed to assess the relative validity of an image-based dietary assessment app - Keenoa - against a 3-day food diary (3DFD) and to test its usability in a sample of healthy Canadian adults.

METHODS : We recruited 102 participants to complete two 3-day food records. For 2 weeks, on 2 non-consecutive days and 1 weekend day, in random order, participants completed a traditional pen-to-paper 3DFD and the Keenoa app. At the end of the study, participants completed the System Usability Scale. The nutrient analyses of the 3DFD and Keenoa data before (Keenoa-participant) and after they were reviewed by dietitians (Keenoa-dietitian) were analyzed using analysis of variance. Multiple tests, including the Pearson coefficient, cross-classification, kappa score, % difference, paired t test, and Bland-Altman test, were performed to analyze the validity of Keenoa (Keenoa-dietitian).

RESULTS : The study was completed by 72 subjects. Most variables were significantly different between Keenoa-participant and Keenoa-dietitian (P<.05) except for energy, protein, carbohydrates, fiber, vitamin B1, vitamin B12, vitamin C, vitamin D, and potassium. Significant differences in total energy, protein, carbohydrates, % fat, saturated fatty acids, iron, and potassium were found between the 3DFD and Keenoa-dietitian data (P<.05). The Pearson correlation coefficients between the Keenoa-dietitian and 3DFD ranged from .04 to .51. Differences between the mean intakes assessed by the 3DFD and Keenoa-dietitian were within 10% except for vitamin D (misclassification rate=33.8%). The majority of nutrients were within an acceptable range of agreement in the Bland-Altman analysis; no agreements were seen for total energy, protein, carbohydrates, fat (%), saturated fatty acids, iron, potassium, and sodium (P<.05). According to the System Usability Scale, 34.2% of the participants preferred using Keenoa, while 9.6% preferred the 3DFD.

CONCLUSIONS : The Keenoa app provides acceptable relative validity for some nutrients compared to the 3DFD. However, the average intake of some nutrients, including energy, protein, carbohydrates, % fat, saturated fatty acids, and iron, differed from the average obtained using the 3DFD. These findings highlight the importance of verifying data entries of participants before proceeding with nutrient analysis. Overall, Keenoa showed better validity at the group level than the individual level, suggesting it can be used when focusing on the dietary intake of the general population. Further research is recommended with larger sample sizes and objective dietary assessment approaches.

Ji Yuwei, Plourde Hugues, Bouzo Valerie, Kilgour Robert D, Cohen Tamara R

2020-Sep-09

3-day food diary, Canada, application, diet, healthy adults, image-based dietary assessment, mHealth, mobile food record, nutrition, validity

General General

Obesity Measures and Dietary Parameters as Predictors of Gut Microbiota Phyla in Healthy Individuals.

In Nutrients ; h5-index 86.0

The dynamics and diversity of human gut microbiota that can remarkably influence the wellbeing and health of the host are constantly changing through the host's lifetime in response to various factors. The aim of the present study was to determine a set of parameters that could have a major impact on classifying subjects into a single cluster regarding gut bacteria composition. Therefore, a set of demographical, environmental, and clinical data of healthy adults aged 25-50 years (117 female and 83 men) was collected. Fecal microbiota composition was characterized using Illumina MiSeq 16S rRNA gene amplicon sequencing. Hierarchical clustering was performed to analyze the microbiota data set, and a supervised machine learning model (SVM; Support Vector Machines) was applied for classification. Seventy variables from collected data were included in machine learning analysis. The agglomerative clustering algorithm suggested the presence of four distinct community types of most abundant bacterial phyla. Each cluster harbored a statistically significant different proportion of bacterial phyla. Regarding prediction, the most important features classifying subjects into clusters were measures of obesity (waist to hip ratio, BMI, and visceral fat index), total body water, blood pressure, energy intake, total fat, olive oil intake, total fiber intake, and water intake. In conclusion, the SVM model was shown as a valuable tool to classify healthy individuals based on their gut microbiota composition.

Bezek Katja, Petelin Ana, Pražnikar Jure, Nova Esther, Redondo Noemi, Marcos Ascensión, Jenko Pražnikar Zala

2020-Sep-03

clustering, gut microbiota, lifestyle parameters, machine learning, nutrition, obesity measures

Surgery Surgery

Endothelial Injury and Glycocalyx Degradation in Critically Ill Coronavirus Disease 2019 Patients: Implications for Microvascular Platelet Aggregation.

In Critical care explorations

Objectives : Coronavirus disease 2019 is caused by the novel severe acute respiratory syndrome coronavirus 2 virus. Patients admitted to the ICU suffer from microvascular thrombosis, which may contribute to mortality. Our aim was to profile plasma thrombotic factors and endothelial injury markers in critically ill coronavirus disease 2019 ICU patients to help understand their thrombotic mechanisms.

Design : Daily blood coagulation and thrombotic factor profiling with immunoassays and in vitro experiments on human pulmonary microvascular endothelial cells.

Setting : Tertiary care ICU and academic laboratory.

Subjects : All patients admitted to the ICU suspected of being infected with severe acute respiratory syndrome coronavirus 2, using standardized hospital screening methodologies, had daily blood samples collected until testing was confirmed coronavirus disease 2019 negative on either ICU day 3 or ICU day 7 if the patient was coronavirus disease 2019 positive.

Interventions : None.

Measurement and Main Results : Age- and sex-matched healthy control subjects and ICU patients that were either coronavirus disease 2019 positive or coronavirus disease 2019 negative were enrolled. Cohorts were well balanced with the exception that coronavirus disease 2019 positive patients were more likely than coronavirus disease 2019 negative patients to suffer bilateral pneumonia. Mortality rate for coronavirus disease 2019 positive ICU patients was 40%. Compared with healthy control subjects, coronavirus disease 2019 positive patients had higher plasma von Willebrand factor (p < 0.001) and glycocalyx-degradation products (chondroitin sulfate and syndecan-1; p < 0.01). When compared with coronavirus disease 2019 negative patients, coronavirus disease 2019 positive patients had persistently higher soluble P-selectin, hyaluronic acid, and syndecan-1 (p < 0.05), particularly on ICU day 3 and thereafter. Thrombosis profiling on ICU days 1-3 predicted coronavirus disease 2019 status with 85% accuracy and patient mortality with 86% accuracy. Surface hyaluronic acid removal from human pulmonary microvascular endothelial cells with hyaluronidase treatment resulted in depressed nitric oxide, an instigating mechanism for platelet adhesion to the microvascular endothelium.

Conclusions : Thrombosis profiling identified endothelial activation and glycocalyx degradation in coronavirus disease 2019 positive patients. Our data suggest that medications to protect and/or restore the endothelial glycocalyx, as well as platelet inhibitors, should be considered for further study.

Fraser Douglas D, Patterson Eric K, Slessarev Marat, Gill Sean E, Martin Claudio, Daley Mark, Miller Michael R, Patel Maitray A, Dos Santos Claudia C, Bosma Karen J, O’Gorman David B, Cepinskas Gediminas

2020-Sep

coronavirus disease 2019, endothelial injury, glycocalyx degradation, platelet adhesion, thrombosis

General General

Classification and Specific Primer Design for Accurate Detection of SARS-CoV-2 Using Deep Learning

bioRxiv Preprint

In this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. A convolutional neural network classifier is first trained on 553 sequences from available repositories, separating the genome of different virus strains from the Coronavirus family with considerable accuracy. The networks behavior is then analyzed, to discover sequences used by the model to identify SARS-CoV-2, ultimately uncovering sequences exclusive to it. The discovered sequences are first validated on samples from other repositories, and proven able to separate SARS-CoV-2 from different virus strains with near-perfect accuracy. Next, one of the sequences is selected to generate a primer set, and tested against other state-of-the-art primer sets on existing datasets, obtaining competitive results. Finally, the primer is synthesized and tested on patient samples (n=6 previously tested positive), delivering a sensibility similar to routine diagnostic methods, and 100% specificity. In this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. A convolutional neural network classifier is first trained on 553 sequences from NGDC, separating the genome of different virus strains from the Coronavirus family with accuracy 98.73%. The networks behavior is then analyzed, to discover sequences used by the model to identify SARS-CoV-2, ultimately uncovering sequences exclusive to it. The discovered sequences are validated on samples from NCBI and GISAID, and proven able to separate SARS-CoV-2 from different virus strains with near-perfect accuracy. Next, one of the sequences is selected to generate a primer set, and tested against other state-of-the-art primer sets, obtaining competitive results. Finally, the primer is synthesized and tested on patient samples (n=6 previously tested positive), delivering a sensibility similar to routine diagnostic methods, and 100% specificity. The proposed methodology has a substantial added value over existing methods, as it is able to both identify promising primer sets for a virus from a limited amount of data, and deliver effective results in a minimal amount of time. Considering the possibility of future pandemics, these characteristics are invaluable to promptly create specific detection methods for diagnostics.

Lopez-Rincon, A.; Tonda, A.; Mendoza-Maldonado, L.; Mulders, D.; Molenkamp, R.; Perez-Romero, C. A.; Claassen, E.; Garssen, J.; Kraneveld, A. D.

2020-09-10