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

Cardiology Cardiology

External validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunction.

In International journal of cardiology ; h5-index 68.0

OBJECTIVE : To validate a novel artificial-intelligence electrocardiogram algorithm (AI-ECG) to detect left ventricular systolic dysfunction (LVSD) in an external population.

BACKGROUND : LVSD, even when asymptomatic, confers increased morbidity and mortality. We recently derived AI-ECG to detect LVSD using ECGs based on a large sample of patients treated at the Mayo Clinic.

METHODS : We performed an external validation study with subjects from the Know Your Heart Study, a cross-sectional study of adults aged 35-69 years residing in two cities in Russia, who had undergone both ECG and transthoracic echocardiography. LVSD was defined as left ventricular ejection fraction ≤ 35%. We assessed the performance of the AI-ECG to identify LVSD in this distinct patient population.

RESULTS : Among 4277 subjects in this external population-based validation study, 0.6% had LVSD (compared to 7.8% of the original clinical derivation study). The overall performance of the AI-ECG to detect LVSD was robust with an area under the receiver operating curve of 0.82. When using the LVSD probability cut-off of 0.256 from the original derivation study, the sensitivity, specificity, and accuracy in this population were 26.9%, 97.4%, 97.0%, respectively. Other probability cut-offs were analysed for different sensitivity values.

CONCLUSIONS : The AI-ECG detected LVSD with robust test performance in a population that was very different from that used to develop the algorithm. Population-specific cut-offs may be necessary for clinical implementation. Differences in population characteristics, ECG and echocardiographic data quality may affect test performance.

Attia Itzhak Zachi, Tseng Andrew S, Benavente Ernest Diez, Inojosa Jose Medina, Clark Taane G, Malyutina Sofia, Kapa Suraj, Schirmer Henrik, Kudryavtsev Alexander V, Noseworthy Peter A, Carter Rickey E, Ryabikov Audrey, Perel Pablo, Friedman Paul A, Leon David A, Lopez-Jimenez Francisco

2021-Jan-02

Artificial intelligence, Electrocardiogram, Left ventricular systolic dysfunction, Machine learning

Radiology Radiology

Structural and functional connectivity of motor circuits after perinatal stroke: A machine learning study.

In NeuroImage. Clinical

Developmental neuroplasticity allows young brains to adapt via experiences early in life and also to compensate after injury. Why certain individuals are more adaptable remains underexplored. Perinatal stroke is an ideal human model of neuroplasticity with focal lesions acquired near birth in a healthy brain. Machine learning can identify complex patterns in multi-dimensional datasets. We used machine learning to identify structural and functional connectivity biomarkers most predictive of motor function. Forty-nine children with perinatal stroke and 27 controls were studied. Functional connectivity was quantified by fluctuations in blood oxygen-level dependent (BOLD) signal between regions. White matter tractography of corticospinal tracts quantified structural connectivity. Motor function was assessed using validated bimanual and unimanual tests. RELIEFF feature selection and random forest regression models identified predictors of each motor outcome using neuroimaging and demographic features. Unilateral motor outcomes were predicted with highest accuracy (8/54 features r = 0.58, 11/54 features, r = 0.34) but bimanual function required more features (51/54 features, r = 0.38). Connectivity of both hemispheres had important roles as did cortical and subcortical regions. Lesion size, age at scan, and type of stroke were predictive but not highly ranked. Machine learning regression models may represent a powerful tool in identifying neuroimaging biomarkers associated with clinical motor function in perinatal stroke and may inform personalized targets for neuromodulation.

Carlson Helen L, Craig Brandon T, Hilderley Alicia J, Hodge Jacquie, Rajashekar Deepthi, Mouches Pauline, Forkert Nils D, Kirton Adam

2020

Diffusion tractography, MRI, Machine learning, Pediatric, Perinatal stroke, Resting state fMRI

General General

Analyzing the vast coronavirus literature with CoronaCentral.

In bioRxiv : the preprint server for biology

The global SARS-CoV-2 pandemic has caused a surge in research exploring all aspects of the virus and its effects on human health. The overwhelming rate of publications means that human researchers are unable to keep abreast of the research. To ameliorate this, we present the CoronaCentral resource which uses machine learning to process the research literature on SARS-CoV-2 along with articles on SARS-CoV and MERS-CoV. We break the literature down into useful categories and enable analysis of the contents, pace, and emphasis of research during the crisis. These categories cover therapeutics, forecasting as well as growing areas such as "Long Covid" and studies of inequality and misinformation. Using this data, we compare topics that appear in original research articles compared to commentaries and other article types. Finally, using Altmetric data, we identify the topics that have gained the most media attention. This resource, available at https://coronacentral.ai , is updated multiple times per day and provides an easy-to-navigate system to find papers in different categories, focussing on different aspects of the virus along with currently trending articles.

Lever Jake, Altman Russ B

2020-Dec-22

General General

On the regularization of feature fusion and mapping for fast MR multi-contrast imaging via iterative networks.

In Magnetic resonance imaging

Multi-contrast (MC) Magnetic Resonance Imaging (MRI) of the same patient usually requires long scanning times, despite the images sharing redundant information. In this work, we propose a new iterative network that utilizes the sharable information among MC images for MRI acceleration. The proposed network has reinforced data fidelity control and anatomy guidance through an iterative optimization procedure of Gradient Descent, leading to reduced uncertainties and improved reconstruction results. Through a convolutional network, the new method incorporates a learnable regularization unit that is capable of extracting, fusing, and mapping shareable information among different contrasts. Specifically, a dilated inception block is proposed to promote multi-scale feature extractions and increase the receptive field diversity for contextual information incorporation. Lastly, an optimal MC information feeding protocol is built through the design of a complementary feature extractor block. Comprehensive experiments demonstrated the superiority of the proposed network, both qualitatively and quantitatively.

Liu Xinwen, Wang Jing, Sun Hongfu, Chandra Shekhar S, Crozier Stuart, Liu Feng

2021-Jan-02

Deep learning, Image reconstruction, Magnetic resonance imaging (MRI), Multi-contrast

General General

Active Inference: Demystified and Compared.

In Neural computation

Active inference is a first principle account of how autonomous agents operate in dynamic, nonstationary environments. This problem is also considered in reinforcement learning, but limited work exists on comparing the two approaches on the same discrete-state environments. In this letter, we provide (1) an accessible overview of the discrete-state formulation of active inference, highlighting natural behaviors in active inference that are generally engineered in reinforcement learning, and (2) an explicit discrete-state comparison between active inference and reinforcement learning on an OpenAI gym baseline. We begin by providing a condensed overview of the active inference literature, in particular viewing the various natural behaviors of active inference agents through the lens of reinforcement learning. We show that by operating in a pure belief-based setting, active inference agents can carry out epistemic exploration-and account for uncertainty about their environment-in a Bayes-optimal fashion. Furthermore, we show that the reliance on an explicit reward signal in reinforcement learning is removed in active inference, where reward can simply be treated as another observation we have a preference over; even in the total absence of rewards, agent behaviors are learned through preference learning. We make these properties explicit by showing two scenarios in which active inference agents can infer behaviors in reward-free environments compared to both Q-learning and Bayesian model-based reinforcement learning agents and by placing zero prior preferences over rewards and learning the prior preferences over the observations corresponding to reward. We conclude by noting that this formalism can be applied to more complex settings (e.g., robotic arm movement, Atari games) if appropriate generative models can be formulated. In short, we aim to demystify the behavior of active inference agents by presenting an accessible discrete state-space and time formulation and demonstrate these behaviors in a OpenAI gym environment, alongside reinforcement learning agents.

Sajid Noor, Ball Philip J, Parr Thomas, Friston Karl J

2021-Jan-05

General General

Predicting the Ease of Human Category Learning Using Radial Basis Function Networks.

In Neural computation

Our goal is to understand and optimize human concept learning by predicting the ease of learning of a particular exemplar or category. We propose a method for estimating ease values, quantitative measures of ease of learning, as an alternative to conducting costly empirical training studies. Our method combines a psychological embedding of domain exemplars with a pragmatic categorization model. The two components are integrated using a radial basis function network (RBFN) that predicts ease values. The free parameters of the RBFN are fit using human similarity judgments, circumventing the need to collect human training data to fit more complex models of human categorization. We conduct two category-training experiments to validate predictions of the RBFN. We demonstrate that an instance-based RBFN outperforms both a prototype-based RBFN and an empirical approach using the raw data. Although the human data were collected across diverse experimental conditions, the predicted ease values strongly correlate with human learning performance. Training can be sequenced by (predicted) ease, achieving what is known as fading in the psychology literature and curriculum learning in the machine-learning literature, both of which have been shown to facilitate learning.

Roads Brett D, Mozer Michael C

2021-Jan-05