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

General General

Automated postural asymmetry assessment in infants neurodevelopmental evaluation using novel video-based features.

In Computer methods and programs in biomedicine

BACKGROUND AND OBJECTIVE : Neurodevelopmental assessment enables the identification of infant developmental disorders in the first months of life. Thus, the appropriate therapy can be initiated promptly, increasing the chances for correct motor function. Posture asymmetry is one of the crucial aspects evaluated during the diagnosis. Available diagnostic methods are mainly based on qualitative assessment and subjective expert opinion. Current trends in computer-aided diagnosis focus mostly on analyzing infants' spontaneous movement videos using artificial intelligence methods, based primarily on limbs movement. This study aims to develop an automatic method for determining the infant's positional asymmetry in a video recording using computer image processing methods.

METHODS : We made the first attempt to determine positional preferences in a recording automatically. We proposed six quantitative features describing trunk and head position based on pose estimation. As a result of our algorithm, we estimate the percentage of each trunk position in a recording using known machine learning methods. The training and test sets were created from 51 recordings collected during our research and 12 recordings from the benchmark dataset evaluated by five of our experts. The method was assessed using the leave-one-subject-out cross-validation method for ground truth video fragments and different classifiers. Log loss for multiclass classification and ROC AUC were determined to evaluate the results for both our and benchmark datasets.

RESULTS : In a classification of the shortened side, the QDA classifier yields the most accurate results, gaining the lowest log loss of 0.552 and AUC of 0.913. The high accuracy (92.03) and sensitivity (93.26) confirm the method's potential in screening for asymmetry.

CONCLUSIONS : The method allows obtaining quantitative information about positional preference, a valuable extension of basic diagnostics without additional tools and procedures. In combination with an analysis of limbs movement, it may constitute one of the elements of a novelty computer-aided infants' diagnosis system in the future.

Ledwoń Daniel, Danch-Wierzchowska Marta, Doroniewicz Iwona, Kieszczyńska Katarzyna, Affanasowicz Alicja, Latos Dominika, Matyja Małgorzata, Mitas Andrzej W, Myśliwiec Andrzej

2023-Mar-05

Asymmetry, Computer-aided diagnosis, Features extraction, Infant, Machine learning, Physiotherapy

Cardiology Cardiology

Differences in Cardiac Mechanics and Exercise Physiology Among Heart Failure With Preserved Ejection Fraction Phenomapping Subgroups.

In The American journal of cardiology ; h5-index 64.0

Unsupervised machine learning (phenomapping) has been used successfully to identify novel subgroups (phenogroups) of heart failure with preserved ejection fraction (HFpEF). However, further investigation of pathophysiological differences between HFpEF phenogroups is necessary to help determine potential treatment options. We performed speckle-tracking echocardiography and cardiopulmonary exercise testing (CPET) in 301 and 150 patients with HFpEF, respectively, as part of a prospective phenomapping study (median age 65 [25th to 75th percentile 56 to 73] years, 39% Black individuals, 65% female). Linear regression was used to compare strain and CPET parameters by phenogroup. All indicies of cardiac mechanics except for left ventricular global circumferential strain worsened in a stepwise fashion from phenogroups 1 to 3 after adjustment for demographic and clinical factors. After further adjustment for conventional echocardiographic parameters, phenogroup 3 had the worst left ventricular global longitudinal, right ventricular free wall, and left atrial booster and reservoir strain. On CPET, phenogroup 2 had the lowest exercise time and absolute peak oxygen consumption (VO2), driven primarily by obesity, whereas phenogroup 3 achieved the lowest workload, relative peak oxygen consumption (VO2), and heart rate reserve on multivariable-adjusted analyses. In conclusion, HFpEF phenogroups identified by unsupervised machine learning analysis differ in the indicies of cardiac mechanics and exercise physiology.

Dixon Debra D, Beussink-Nelson Lauren, Deo Rahul, Shah Sanjiv J

2023-Mar-06

General General

Improved space breakdown method - A robust clustering technique for spike sorting.

In Frontiers in computational neuroscience

UNLABELLED : Space Breakdown Method (SBM) is a clustering algorithm that was developed specifically for low-dimensional neuronal spike sorting. Cluster overlap and imbalance are common characteristics of neuronal data that produce difficulties for clustering methods. SBM is able to identify overlapping clusters through its design of cluster centre identification and the expansion of these centres. SBM's approach is to divide the distribution of values of each feature into chunks of equal size. In each of these chunks, the number of points is counted and based on this number the centres of clusters are found and expanded. SBM has been shown to be a contender for other well-known clustering algorithms especially for the particular case of two dimensions while being too computationally expensive for high-dimensional data. Here, we present two main improvements to the original algorithm in order to increase its ability to deal with high-dimensional data while preserving its performance: the initial array structure was substituted with a graph structure and the number of partitions has been made feature-dependent, denominating this improved version as the Improved Space Breakdown Method (ISBM). In addition, we propose a clustering validation metric that does not punish overclustering and such obtains more suitable evaluations of clustering for spike sorting. Extracellular data recorded from the brain is unlabelled, therefore we have chosen simulated neural data, to which we have the ground truth, to evaluate more accurately the performance. Evaluations conducted on synthetic data indicate that the proposed improvements reduce the space and time complexity of the original algorithm, while simultaneously leading to an increased performance on neural data when compared with other state-of-the-art algorithms.

CODE AVAILABLE AT : https://github.com/ArdeleanRichard/Space-Breakdown-Method.

Ardelean Eugen-Richard, Ichim Ana-Maria, Dînşoreanu Mihaela, Mureşan Raul Cristian

2023

clustering, density, different density, grid, machine learning, overlapping clusters, spike sorting

Public Health Public Health

Determinants of COVID-19 vaccine hesitancy among students and parents in Sentinel Schools Network of Catalonia, Spain.

In PloS one ; h5-index 176.0

Vaccine hesitancy is defined as a delay in acceptance of vaccines despite its availability, caused by many determinants. Our study presents the key reasons, determinants and characteristics associated with COVID-19 vaccine acceptability among students over 16 years and parents of students under 16 years and describe the COVID-19 vaccination among students in the settings of sentinel schools of Catalonia, Spain. This is a cross-sectional study that includes 3,383 students and the parents between October 2021 and January 2022. We describe the student's vaccination status and proceed a univariate and multivariate analysis using a Deletion Substitution Addition (DSA) machine learning algorithm. Vaccination against COVID-19 reached 70.8% in students under 16 years and 95.8% in students over 16 years at the end of the study project. The acceptability among unvaccinated students was 40.9% and 20.8% in October and January, respectively, and among parents was proportionally higher among students aged 5-11 (70.2%) in October and aged 3-4 (47.8%) in January. The key reason to not vaccinate themselves, or their children, were concern about side effects, insufficient research about the effect of the vaccine in children, rapid development of vaccines, necessity for more information and previous infection by SARS-CoV-2. Several variables were associated with refusal end hesitancy. For students, the main ones were risk perception and use of alternative therapies. For parents, the age of students, sociodemographic variables, socioeconomic impact related to the pandemic, and use of alternative therapies were more evident. Monitoring vaccine acceptance and refusal among children and their parents has been important to understand the interaction between different multilevel determinants and we hope it will be useful to improve public health strategies for future interventions in this population.

Ganem Fabiana, Folch Cinta, Colom-Cadena Andreu, Bordas Anna, Alonso Lucia, Soriano-Arandes Antoni, Casabona Jordi

2023

General General

Assessing long-term climate change impact on spatiotemporal changes of groundwater level using autoregressive-based and ensemble machine learning models.

In Journal of environmental management

To evaluate the long-term climate change impacts on groundwater fluctuations of the Ardabil plain, Iran, a groundwater level (GWL) modeling was proposed in this study. Accordingly, the outputs of Global Climate Models (GCMs) under the sixth report of Coupled Model Intercomparison Project (CMIP6) and future scenario of the Shared Socioeconomic Pathway 5-8.5 (SSP5-8.5), were used as climate change forcing to the Machine learning (ML) models. The GCM data were first downscaled and projected for the future via Artificial Neural Networks (ANNs). Based on the results, compared to 2014 (the last year of the base period), the mean annual temperature may increase by 0.8 °C per decade until 2100. On the other hand, the mean precipitation may decrease by about 8% compared to the base period. Then, the centroid wells of clusters were modeled by Feedforward Neural Network (FFNN), examining different input combination sets to simulate both autoregressive and non-autoregressive models. Since each of the ML models can extract different kinds of information from a dataset, after finding the dominant input set via FFNN, GWL time series were modeled via various ML methods. The modeling results indicated that the ensemble of shallow ML models could lead to a 6% more accurate outcome than the individual shallow ML models, and 4% than the deep learning models. Also, the simulation results for future GWLs illustrated that temperature can impact groundwater oscillations directly, whereas precipitation may not have uniform impacts on the GWLs. The uncertainty evolving in the modeling process was quantified and observed to be in acceptable range. Modeling results showed that the main reason for the declining GWL in the Ardabil plain could be primarily linked to the excessive exploitation of the water table, while climate change impact could be also notable.

Nourani Vahid, Ghareh Tapeh Ali Hasanpour, Khodkar Kasra, Huang Jinhui Jeanne

2023-Mar-07

Ardabil plain, GCM, Groundwater, K-means clustering, Machine learning

Public Health Public Health

Does social distancing impact pediatric upper airway infections? An observational controlled study and a brief literature review.

In American journal of otolaryngology ; h5-index 23.0

PURPOSE : SARS-CoV-2 pandemic has reduced social interaction even among children. The objective of the study was to assess the role of social distancing in the course of common pediatric upper airway recurrent diseases.

MATERIALS AND METHODS : Patients aged ≤14 years with at least one ENT-related clinical condition were retrospectively recruited. All patients had two outpatient evaluations in the same period (April - September): the control group had the first evaluation in 2018 and second in 2019, whereas the case group had the first evaluation in 2019 and second in 2020. Patients of each group were individually compared between their two visits and deemed improved/unchanged/worsened for each specific ENT condition. The percentage of children improved/unchanged/worsened were then collectively compared between the two groups for each condition.

RESULTS : Patients who experienced social distancing presented a significantly higher improvement rate than controls for recurrent acute otitis media episodes (35.1 % vs. 10.8 %; Fisher's exact test p = 0.033) and for tympanogram type (54.5 % vs. 11.1 %, Fisher's exact test p = 0.009).

CONCLUSIONS : The anti-contagion social restrictions decreased the prevalence of middle ear infections and effusion in children. Further studies on larger cohorts are required to better elucidate these findings.

Franchella Sebastiano, Favaretto Niccolò, Frigo Annachiara, Franz Leonardo, Pilo Simona, Mularoni Francesca, Marciani Silvia, Nicolai Piero, Marioni Gino, Cazzador Diego

2023-Mar-01

COVID-19, Pediatric, SARS-CoV-2, Social distancing, Upper airways infection