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

General General

Combining Machine Learning with Physical Knowledge in Thermodynamic Modeling of Fluid Mixtures.

In Annual review of chemical and biomolecular engineering

Thermophysical properties of fluid mixtures are important in many fields of science and engineering. However, experimental data are scarce in this field, so prediction methods are vital. Different types of physical prediction methods are available, ranging from molecular models over equations of state to models of excess properties. These well-established methods are currently being complemented by new methods from the field of machine learning (ML). This review focuses on the rapidly developing interface between these two approaches and gives a structured overview of how physical modeling and ML can be combined to yield hybrid models. We illustrate the different options with examples from recent research and give an outlook on future developments. Expected final online publication date for the Annual Review of Chemical and Biomolecular Engineering, Volume 14 is June 2023. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Jirasek Fabian, Hasse Hans

2023-Mar-21

General General

Decoding study-independent mind-wandering from EEG using convolutional neural networks.

In Journal of neural engineering ; h5-index 52.0

Mind-wandering is a mental phenomenon where the internal thought process disengages from the external environment periodically. In the current study, we trained EEG classifiers using convolutional neural networks (CNN) to track mind-wandering across studies. 
Approach: We transformed the input from raw EEG to band-frequency information (power), single-trial ERP (stERP) patterns, and connectivity matrices between channels (based on inter-site phase clustering, ISPC). We trained CNN models for each input type from each EEG channel as the input model for the meta-learner. To verify the generalizability, we used leave-N-participant-out cross-validations (N=6) and tested the meta-learner on the data from an independent study for across-study predictions.
Main results: The current results show limited generalizability across participants and tasks. Nevertheless, our meta-learner trained with the stERPs performed the best among the state-of-the-art neural networks. The mapping of each input model to the output of the meta-learner indicates the importance of each EEG channel.
Significance: Our study makes the first attempt to train study-independent mind-wandering classifiers. The results indicate that this remains challenging. The stacking neural network design we used allows an easy inspection of channel importance and feature maps. &#xD.

Jin Christina Yi, Borst Jelmer P, van Vugt Marieke

2023-Mar-21

EEG, classifier, convolutional neural network, generalizability, machine learning, meta-learner, mind-wandering

General General

Modern Artificial Neural Networks: Is Evolution Cleverer?

In Neural computation

Machine learning tools, particularly artificial neural networks (ANN), have become ubiquitous in many scientific disciplines, and machine learning-based techniques flourish not only because of the expanding computational power and the increasing availability of labeled data sets but also because of the increasingly powerful training algorithms and refined topologies of ANN. Some refined topologies were initially motivated by neuronal network architectures found in the brain, such as convolutional ANN. Later topologies of neuronal networks departed from the biological substrate and began to be developed independently as the biological processing units are not well understood or are not transferable to in silico architectures. In the field of neuroscience, the advent of multichannel recordings has enabled recording the activity of many neurons simultaneously and characterizing complex network activity in biological neural networks (BNN). The unique opportunity to compare large neuronal network topologies, processing, and learning strategies with those that have been developed in state-of-the-art ANN has become a reality. The aim of this review is to introduce certain basic concepts of modern ANN, corresponding training algorithms, and biological counterparts. The selection of these modern ANN is prone to be biased (e.g., spiking neural networks are excluded) but may be sufficient for a concise overview.

Bahmer Andreas, Gupta Daya, Effenberger Felix

2023-Mar-16

General General

Classification of Parkinson's disease with dementia using phase locking factor of event-related oscillations to visual and auditory stimuli.

In Journal of neural engineering ; h5-index 52.0


In the last decades, machine learning (ML) approaches have been widely used to distinguish Parkinson's disease (PD) and many other neuropsychiatric diseases. They also speed up the clinicians and facilitate decision-making for several conditions with similar clinical symptoms. The current study attempts to detect PD with dementia (PDD) by Event-related Oscillations (EROs) during cognitive processing in two modalities, i.e. auditory and visual.
Approach:
The study was conducted to discriminate PDD from healthy controls (HC) using event-related phase-locking factors in slow frequency ranges (delta and theta) during visual and auditory cognitive tasks. 17 PDD and 19 HC were included in the study, and Linear Discriminant Analysis (LDA) was used as a classifier. During classification analysis, multiple settings were implemented by using different sets of channels (overall, fronto-central and temporo-parieto-occipital region), frequency bands (delta-theta combined, delta, theta, and low theta), and time of interests (0.1- 0.7 s, 0.1 - 0.5 s and 0.1 - 0.3 s for delta, delta-theta combined; 0.1- 0.4 s for theta and low theta) for spatial-spectral-temporal searchlight procedure.
Main results:
The classification performance results of the current study revealed that if visual stimuli are applied to PDD, the delta and theta phase-locking factor over fronto-central region have a remarkable contribution to detecting the disease, whereas if auditory stimuli are applied, the phase-locking factor in low theta over temporo-parieto-occipital and in a wider range of frequency (1-7 Hz) over the fronto-central region classify HC and PDD with better performances.
Significance:
These findings show that the delta and theta phase-locking factor of EROs during visual and auditory stimuli has valuable contributions to detecting PDD.&#xD.

Tülay Emine Elif, Yıldırım Ebru, Aktürk Tuba, Güntekin Bahar

2023-Mar-21

Classification, Delta, Theta, Inter-trial phase coherence, Linear Discriminant Analysis, “Parkinsons Disease with dementia”

Radiology Radiology

Combination Use of Compressed Sensing and Deep Learning for Shoulder Magnetic Resonance Imaging With Various Sequences.

In Journal of computer assisted tomography

OBJECTIVE : For compressed sensing (CS) to become widely used in routine magnetic resonance imaging (MRI), it is essential to improve image quality. This study aimed to evaluate the usefulness of combining CS and deep learning-based reconstruction (DLR) for various sequences in shoulder MRI.

METHODS : This retrospective study included 37 consecutive patients who underwent undersampled shoulder MRIs, including T1-weighted (T1WI), T2-weighted (T2WI), and fat-saturation T2-weighted (FS-T2WI) images. Images were reconstructed using the conventional wavelet-based denoising method (wavelet method) and a combination of wavelet and DLR-based denoising methods (hybrid-DLR method) for each sequence. The signal-to-noise ratio and contrast-to-noise ratio of the bone, muscle, and fat and the full width at half maximum of the shoulder joint were compared between the 2 image types. In addition, 2 board-certified radiologists scored the image noise, contrast, sharpness, artifacts, and overall image quality of the 2 image types on a 4-point scale.

RESULTS : The signal-to-noise ratios and contrast-to-noise ratios of the bone, muscle, and fat in T1WI, T2WI, and FS-T2WI obtained from the hybrid-DLR method were significantly higher than those of the conventional wavelet method (P < 0.001). However, there were no significant differences in the full width at half maximum of the shoulder joint in any of the sequences (P > 0.05). Furthermore, in all sequences, the mean scores of the image noise, sharpness, artifacts, and overall image quality were significantly higher in the hybrid-DLR method than in the wavelet method (P < 0.001), but there were no significant differences in contrast among the sequences (P > 0.05).

CONCLUSIONS : The DLR denoising method can improve the image quality of CS in T1-weighted images, T2-weighted images, and fat-saturation T2-weighted images of the shoulder compared with the wavelet denoising method alone.

Shiraishi Kaori, Nakaura Takeshi, Uetani Hiroyuki, Nagayama Yasunori, Kidoh Masafumi, Kobayashi Naoki, Morita Kosuke, Yamahita Yuichi, Miyamoto Takeshi, Hirai Toshinori

2023-Mar-09

General General

Using artificial intelligence to support rapid, mixed-methods analysis: Developing an automated qualitative assistant (AQUA).

In Annals of family medicine

Context: Qualitative research - crucial for understanding human behavior - remains underutilized, in part due to the time and cost of annotating qualitative data (coding). Artificial intelligence (AI) has been suggested as a means to reduce those burdens. Older AI techniques (Latent Semantic Indexing / Latent Dirichlet Allocation (LSI/LDA)) have fallen short, in part because qualitative data is rife with idiom, non-standard expressions, and jargon. Objective: To develop an AI platform using updated techniques to augment qualitative data coding. Study Design and Analysis: We previously completed traditional qualitative analysis of a large dataset, with 11 qualitative categories and 72 subcategories (categories), and a final Cohen's kappa ≥ 0.65 as a measure of human inter-coder reliability (ICR) after coding. We built our Automated Qualitative Assistant (AQUA) using a semi-classical approach, replacing LSI/LDA with a graph-theoretic topic extraction and clustering method. AQUA was given the previously-identified qualitative categories and tasked with coding free-text data into those categories. Item coding was scored using cosine-similarity. Population Studied: Pennsylvanian adults. Instrument: Free-text responses to five open ended questions related to the COVID-19 pandemic (e.g. "What worries you most about the COVID-19 pandemic?"). Outcome Measures: AQUA's coding was compared to human coding using Cohen's kappa. This was done on all categories in aggregate, and also on category clusters to identify category groups amenable to AQUA support. AQUA's time to complete coding was compared to the time taken by the human coding team. Dataset: Five unlimited free-text survey answers from 538 responders. Results: AQUA's kappa for all categories was low (kappa~0.45), reflecting the challenge of automated analysis of diverse language. However, for several 3-category combinations (with less linguistic diversity), AQUA performed comparably to human coders, with an ICR kappa range of 0.62 to 0.72 based on test-train split. AQUA's analysis (including human interpretation) took approximately 5 hours, compared to approximately 30 person hours for traditional coding. Conclusions: AQUA enables qualitative researchers to identify categories amenable to automated coding, and to rapidly conduct that coding on the entirety of very large datasets. This saves time and money, and avoids limitations inherent in limiting qualitative analysis to limited samples of a given dataset.

Lennon Robert, Calo William, Miller Erin, Zgierska Aleksandra, Van Scoy Lauren, Fraleigh Robert

2022-Apr-01