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

Pathology Pathology

The Use of Synthetic Microbial Communities (SynComs) to Improve Plant Health.

In Phytopathology

Despite the numerous benefits plants receive from probiotics, maintaining consistent results across applications is still a challenge. Cultivation-independent methods associated with reduced sequencing costs have considerably improved the overall understanding of microbial ecology in the plant environment. As a result, now it is possible to engineer a consortium of microbes aiming for improved plant health. Such synthetic microbial communities (SynComs) contain carefully chosen microbial species to produce the desired microbiome function. Microbial biofilm formation, production of secondary metabolites and ability to induce plant resistance are some of the microbial traits to take into consideration when designing SynComs. Plant-associated microbial communities are not assembled randomly. Ecological theories suggest that these communities have a defined phylogenetic organization structured by general community assembly rules. Using machine learning, we can study these rules and target microbial functions that generate desired plant phenotypes. Well-structured assemblages are more likely to lead to a stable SynCom that thrives under environmental stressors, as compared to the classical selection of single microbial activities or taxonomy. However, ensuring microbial colonization and long-term plant phenotype stability are still some of the challenges to overcome with SynComs, as the synthetic community may change over time with microbial horizontal gene transfer and retained mutations. Here, we explored the advances made in SynCom research regarding plant health focusing on bacteria, as they are the most dominant microbial form compared with other members of the microbiome and the most commonly found in SynCom studies.

Martins Samuel J, Pasche Josephine M, Silva Hiago A, Selten Gijs G, Savastano Noah, Abreu Lucas, Bais Harsh, Garrett Karen A, Kraisitudomsook Nattapol, Pieterse Corne M J, Cernava Tomislav

2023-Mar-01

Biological Control, Biotechnology, Climate Change, Computational Biology, Disease Control and Pest Management, Food Safety, Microbiome, Symbiosis

Public Health Public Health

Development and validation of echocardiography-based machine-learning models to predict mortality.

In EBioMedicine

BACKGROUND : Echocardiography (echo) based machine learning (ML) models may be useful in identifying patients at high-risk of all-cause mortality.

METHODS : We developed ML models (ResNet deep learning using echo videos and CatBoost gradient boosting using echo measurements) to predict 1-year, 3-year, and 5-year mortality. Models were trained on the Mackay dataset, Taiwan (6083 echos, 3626 patients) and validated in the Alberta HEART dataset, Canada (997 echos, 595 patients). We examined the performance of the models overall, and in subgroups (healthy controls, at risk of heart failure (HF), HF with reduced ejection fraction (HFrEF) and HF with preserved ejection fraction (HFpEF)). We compared the models' performance to the MAGGIC risk score, and examined the correlation between the models' predicted probability of death and baseline quality of life as measured by the Kansas City Cardiomyopathy Questionnaire (KCCQ).

FINDINGS : Mortality rates at 1-, 3- and 5-years were 14.9%, 28.6%, and 42.5% in the Mackay cohort, and 3.0%, 10.3%, and 18.7%, in the Alberta HEART cohort. The ResNet and CatBoost models achieved area under the receiver-operating curve (AUROC) between 85% and 92% in internal validation. In external validation, the AUROCs for the ResNet (82%, 82%, and 78%) were significantly better than CatBoost (78%, 73%, and 75%), for 1-, 3- and 5-year mortality prediction respectively, with better or comparable performance to the MAGGIC score. ResNet models predicted higher probability of death in the HFpEF and HFrEF (30%-50%) subgroups than in controls and at risk patients (5%-20%). The predicted probabilities of death correlated with KCCQ scores (all p < 0.05).

INTERPRETATION : Echo-based ML models to predict mortality had good internal and external validity, were generalizable, correlated with patients' quality of life, and are comparable to an established HF risk score. These models can be leveraged for automated risk stratification at point-of-care.

FUNDING : Funding for Alberta HEART was provided by an Alberta Innovates - Health Solutions Interdisciplinary Team Grant no. AHFMRITG 200801018. P.K. holds a Canadian Institutes of Health Research (CIHR) Sex and Gender Science Chair and a Heart & Stroke Foundation Chair in Cardiovascular Research. A.V. and V.S. received funding from the Mitacs Globalink Research Internship.

Valsaraj Akshay, Kalmady Sunil Vasu, Sharma Vaibhav, Frost Matthew, Sun Weijie, Sepehrvand Nariman, Ong Marcus, Equibec Cyril, Dyck Jason R B, Anderson Todd, Becher Harald, Weeks Sarah, Tromp Jasper, Hung Chung-Lieh, Ezekowitz Justin A, Kaul Padma

2023-Feb-27

Deep learning, Echocardiography, Functional status, Heart failure, Machine learning, Mortality, Prognostic models

General General

Sex-specific equations to estimate body composition: Derivation and validation of diagnostic prediction models using UK Biobank.

In Clinical nutrition (Edinburgh, Scotland)

BACKGROUND & AIMS : Body mass index and waist circumference are simple measures of obesity. However, they do not distinguish between visceral and subcutaneous fat, or muscle, potentially leading to biased relationships between individual body composition parameters and adverse health outcomes. The purpose of this study was to develop and validate prediction models for volumetric adipose and muscle.

METHODS : Based on cross-sectional data of 18,457, 18,260, and 17,052 White adults from the UK Biobank, we developed sex-specific equations to estimate visceral adipose tissue (VAT), abdominal subcutaneous adipose tissue (ASAT), and total thigh fat-free muscle (FFM) volumes, respectively. Volumetric magnetic resonance imaging served as the reference. We used the least absolute shrinkage and selection operator and the extreme gradient boosting methods separately to fit three sequential models, the inputs of which included demographics and anthropometrics and, in some, bioelectrical impedance analysis parameters. We applied comprehensive metrics to assess model performance in the temporal validation set.

RESULTS : The equations that included more predictors generally performed better. Accuracy of the equations was moderate for VAT (percentage of estimates that differed <30% from the measured values, 70 to 78 in males, 64 to 69 in females) and good for ASAT (85 to 91 in males, 90 to 95 in females) and FFM (99 to 100 in both sexes). All the equations appeared precise (interquartile range of the difference, 0.89 to 1.76 L for VAT, 1.16 to 1.61 L for ASAT, 0.81 to 1.39 L for FFM). Bias of all the equations was negligible (-0.17 to 0.05 L for VAT, -0.10 to 0.12 L for ASAT, -0.07 to 0.09 L for FFM). The equations achieved superior cardiometabolic correlations compared with body mass index and waist circumference.

CONCLUSIONS : The developed equations to estimate VAT, ASAT, and FFM volumes achieved moderate to good performance. They may be cost-effective tools to revisit the implications of diverse body components.

Lu Yueqi, Shan Ying, Dai Liang, Jiang Xiaosen, Song Congying, Chen Bangwei, Zhang Jingwen, Li Jing, Zhang Yue, Xu Junjie, Li Tao, Xiong Zuying, Bai Yong, Huang Xiaoyan

2023-Feb-16

Abdominal subcutaneous adipose tissue, Machine learning, Prediction model, Total thigh fat-free muscle, Visceral adipose tissue, Volumetric magnetic resonance imaging

General General

Unsupervised anomaly detection for posteroanterior chest X-rays using multiresolution patch-based self-supervised learning.

In Scientific reports ; h5-index 158.0

The demand for anomaly detection, which involves the identification of abnormal samples, has continued to increase in various domains. In particular, with increases in the data volume of medical imaging, the demand for automated screening systems has also risen. Consequently, in actual clinical practice, radiologists can focus only on diagnosing patients with abnormal findings. In this study, we propose an unsupervised anomaly detection method for posteroanterior chest X-rays (CXR) using multiresolution patch-based self-supervised learning. The core aspect of our approach is to leverage patch images of different sizes for training and testing to recognize diverse anomalies characterized by unknown shapes and scales. In addition, self-supervised contrastive learning is applied to learn the generalized and robust features of the patches. The performance of the proposed method is evaluated using posteroanterior CXR images from a public dataset for training and testing. The results show that the proposed method is superior to state-of-the-art anomaly detection methods. In addition, unlike single-resolution patch-based methods, the proposed method consistently exhibits a good overall performance regardless of the evaluation criteria used for comparison, thus demonstrating the effectiveness of using multiresolution patch-based features. Overall, the results of this study validate the effectiveness of multiresolution patch-based self-supervised learning for detecting anomalies in CXR images.

Kim Minki, Moon Ki-Ryum, Lee Byoung-Dai

2023-Feb-28

General General

Speaking with mask in the COVID-19 era: Multiclass machine learning classification of acoustic and perceptual parameters.

In The Journal of the Acoustical Society of America

The intensive use of personal protective equipment often requires increasing voice intensity, with possible development of voice disorders. This paper exploits machine learning approaches to investigate the impact of different types of masks on sustained vowels /a/, /i/, and /u/ and the sequence /a'jw/ inside a standardized sentence. Both objective acoustical parameters and subjective ratings were used for statistical analysis, multiple comparisons, and in multivariate machine learning classification experiments. Significant differences were found between mask+shield configuration and no-mask and between mask and mask+shield conditions. Power spectral density decreases with statistical significance above 1.5 kHz when wearing masks. Subjective ratings confirmed increasing discomfort from no-mask condition to protective masks and shield. Machine learning techniques proved that masks alter voice production: in a multiclass experiment, random forest (RF) models were able to distinguish amongst seven masks conditions with up to 94% validation accuracy, separating masked from unmasked conditions with up to 100% validation accuracy and detecting the shield presence with up to 86% validation accuracy. Moreover, an RF classifier allowed distinguishing male from female subject in masked conditions with 100% validation accuracy. Combining acoustic and perceptual analysis represents a robust approach to characterize masks configurations and quantify the corresponding level of discomfort.

Calà F, Manfredi C, Battilocchi L, Frassineti L, Cantarella G

2023-Feb

Pathology Pathology

Evolutionary Computation in Action: Hyperdimensional Deep Embedding Spaces of Gigapixel Pathology Images

IEEE Transactions on Evolutionary Computation, vol. 27, no. 1, pp. 52-66, Feb. 2023

One of the main obstacles of adopting digital pathology is the challenge of efficient processing of hyperdimensional digitized biopsy samples, called whole slide images (WSIs). Exploiting deep learning and introducing compact WSI representations are urgently needed to accelerate image analysis and facilitate the visualization and interpretability of pathology results in a postpandemic world. In this paper, we introduce a new evolutionary approach for WSI representation based on large-scale multi-objective optimization (LSMOP) of deep embeddings. We start with patch-based sampling to feed KimiaNet , a histopathology-specialized deep network, and to extract a multitude of feature vectors. Coarse multi-objective feature selection uses the reduced search space strategy guided by the classification accuracy and the number of features. In the second stage, the frequent features histogram (FFH), a novel WSI representation, is constructed by multiple runs of coarse LSMOP. Fine evolutionary feature selection is then applied to find a compact (short-length) feature vector based on the FFH and contributes to a more robust deep-learning approach to digital pathology supported by the stochastic power of evolutionary algorithms. We validate the proposed schemes using The Cancer Genome Atlas (TCGA) images in terms of WSI representation, classification accuracy, and feature quality. Furthermore, a novel decision space for multicriteria decision making in the LSMOP field is introduced. Finally, a patch-level visualization approach is proposed to increase the interpretability of deep features. The proposed evolutionary algorithm finds a very compact feature vector to represent a WSI (almost 14,000 times smaller than the original feature vectors) with 8% higher accuracy compared to the codes provided by the state-of-the-art methods.

Azam Asilian Bidgoli, Shahryar Rahnamayan, Taher Dehkharghanian, Abtin Riasatian, H. R. Tizhoosh

2023-03-02