The birth of ChatGPT, a cutting-edge language model-based chatbot developed by OpenAI, ushered in a new era in AI. However, due to potential pitfalls, its role in rigorous scientific research is not clear yet. This paper vividly showcases its innovative application within the field of drug discovery. Focused specifically on developing anti-cocaine addiction drugs, the study employs GPT-4 as a virtual guide, offering strategic and methodological insights to researchers working on generative models for drug candidates. The primary objective is to generate optimal drug-like molecules with desired properties. By leveraging the capabilities of ChatGPT, the study introduces a novel approach to the drug discovery process. This symbiotic partnership between AI and researchers transforms how drug development is approached. Chatbots become facilitators, steering researchers towards innovative methodologies and productive paths for creating effective drug candidates. This research sheds light on the collaborative synergy between human expertise and AI assistance, wherein ChatGPT\'s cognitive abilities enhance the design and development of potential pharmaceutical solutions. This paper not only explores the integration of advanced AI in drug discovery but also reimagines the landscape by advocating for AI-powered chatbots as trailblazers in revolutionizing therapeutic innovation.

We propose a deep spread multiplexing (DSM) scheme using a DNN-based encoder and decoder and we investigate training procedures for a DNN-based encoder and decoder system. Multiplexing for multiple orthogonal resources is designed with an autoencoder structure, which originates from the deep learning technique. Furthermore, we investigate training methods that can leverage the performance in terms of various aspects such as channel models, training signal-to-noise (SNR) level and noise types. The performance of these factors is evaluated by training the DNN-based encoder and decoder and verified with simulation results.

UNASSIGNED: Traumatic brain injury (TBI) is a major public health concern in children. Children with TBI have elevated risk in developing attention deficits. Existing studies have found that structural and functional alterations in multiple brain regions were linked to TBI-related attention deficits in children. Most of these existing studies have utilized conventional parametric models for group comparisons, which have limited capacity in dealing with large-scale and high dimensional neuroimaging measures that have unknown nonlinear relationships. Nevertheless, none of these existing findings have been successfully implemented to clinical practice for guiding diagnoses and interventions of TBI-related attention problems. Machine learning techniques, especially deep learning techniques, are able to handle the multi-dimensional and nonlinear information to generate more robust predictions. Therefore, the current research proposed to construct a deep learning model, semi-supervised autoencoder, to investigate the topological alterations in both structural and functional brain networks in children with TBI and their predictive power for post-TBI attention deficits.
UNASSIGNED: Functional magnetic resonance imaging data during sustained attention processing task and diffusion tensor imaging data from 110 subjects (55 children with TBI and 55 group-matched controls) were used to construct the functional and structural brain networks, respectively. A total of 60 topological properties were selected as brain features for building the model.
UNASSIGNED: The model was able to differentiate children with TBI and controls with an average accuracy of 82.86%. Functional and structural nodal topological properties associated with left frontal, inferior temporal, postcentral, and medial occipitotemporal regions served as the most important brain features for accurate classification of the two subject groups. Post hoc regression-based machine learning analyses in the whole study sample showed that among these most important neuroimaging features, those associated with left postcentral area, superior frontal region, and medial occipitotemporal regions had significant value for predicting the elevated inattentive and hyperactive/impulsive symptoms.
UNASSIGNED: Findings of this study suggested that deep learning techniques may have the potential to help identifying robust neurobiological markers for post-TBI attention deficits; and the left superior frontal, postcentral, and medial occipitotemporal regions may serve as reliable targets for diagnosis and interventions of TBI-related attention problems in children.

In the medical field, it is delicate to anticipate good performance in using deep learning due to the lack of large-scale training data and class imbalance. In particular, ultrasound, which is a key breast cancer diagnosis method, is delicate to diagnose accurately as the quality and interpretation of images can vary depending on the operator\'s experience and proficiency. Therefore, computer-aided diagnosis technology can facilitate diagnosis by visualizing abnormal information such as tumors and masses in ultrasound images. In this study, we implemented deep learning-based anomaly detection methods for breast ultrasound images and validated their effectiveness in detecting abnormal regions. Herein, we specifically compared the sliced-Wasserstein autoencoder with two representative unsupervised learning models autoencoder and variational autoencoder. The anomalous region detection performance is estimated with the normal region labels. Our experimental results showed that the sliced-Wasserstein autoencoder model outperformed the anomaly detection performance of others. However, anomaly detection using the reconstruction-based approach may not be effective because of the occurrence of numerous false-positive values. In the following studies, reducing these false positives becomes an important challenge.

UNASSIGNED: The principal component analysis (PCA) is known as a multivariate statistical model for reducing dimensions into a representation of principal components. Thus, the PCA is commonly adopted for establishing psychometric properties, i.e., the construct validity. Autoencoder is a neural network model, which has also been shown to perform well in dimensionality reduction. Although there are several ways the PCA and autoencoders could be compared for their differences, most of the recent literature focused on differences in image reconstruction, which are often sufficient for training data. In the current study, we looked at details of each autoencoder classifier and how they may provide neural network superiority that can better generalize non-normally distributed small datasets.
UNASSIGNED: A Monte Carlo simulation was conducted, varying the levels of non-normality, sample sizes, and levels of communality. The performances of autoencoders and a PCA were compared using the mean square error, mean absolute value, and Euclidian distance. The feasibility of autoencoders with small sample sizes was examined.
UNASSIGNED: With extreme flexibility in decoding representation using linear and non-linear mapping, this study demonstrated that the autoencoder can robustly reduce dimensions, and hence was effective in building the construct validity with a sample size as small as 100. The autoencoders could obtain a smaller mean square error and small Euclidian distance between original dataset and predictions for a small non-normal dataset. Hence, when behavioral scientists attempt to explore the construct validity of a newly designed questionnaire, an autoencoder could also be considered an alternative to a PCA.

In this paper, we propose a breakthrough single-trial P300 detector that maximizes the information translate rate (ITR) of the brain-computer interface (BCI), keeping high recognition accuracy performance. The architecture, designed to improve the portability of the algorithm, demonstrated full implementability on a dedicated embedded platform. The proposed P300 detector is based on the combination of a novel pre-processing stage based on the EEG signals symbolization and an autoencoded convolutional neural network (CNN). The proposed system acquires data from only six EEG channels; thus, it treats them with a low-complexity preprocessing stage including baseline correction, windsorizing and symbolization. The symbolized EEG signals are then sent to an autoencoder model to emphasize those temporal features that can be meaningful for the following CNN stage. This latter consists of a seven-layer CNN, including a 1D convolutional layer and three dense ones. Two datasets have been analyzed to assess the algorithm performance: one from a P300 speller application in BCI competition III data and one from self-collected data during a fluid prototype car driving experiment. Experimental results on the P300 speller dataset showed that the proposed method achieves an average ITR (on two subjects) of 16.83 bits/min, outperforming by +5.75 bits/min the state-of-the-art for this parameter. Jointly with the speed increase, the recognition performance returned disruptive results in terms of the harmonic mean of precision and recall (F1-Score), which achieve 51.78 ± 6.24%. The same method used in the prototype car driving led to an ITR of ~33 bit/min with an F1-Score of 70.00% in a single-trial P300 detection context, allowing fluid usage of the BCI for driving purposes. The realized network has been validated on an STM32L4 microcontroller target, for complexity and implementation assessment. The implementation showed an overall resource occupation of 5.57% of the total available ROM, ~3% of the available RAM, requiring less than 3.5 ms to provide the classification outcome.

The surface areas of lakes alter constantly due to many factors such as climate change, land use policies, and human interventions, and their surface areas tend to decrease. It is necessary for obtain baseline datasets such as surface areas and boundaries of water bodies with high accuracy, effectively, economically, and practically by using satellite images in terms of management and planning of lakes. Extracting surface areas of water bodies using image classification algorithms and high-resolution RGB satellite images and evaluating the effectiveness of different image classification algorithms have become an important research domain. In this experimental study, eight different machine learning-based classification approaches, namely, k-nearest neighborhood (kNN), subspaced kNN, support vector machines (SVMs), random forest (RF), bagged tree (BT), Naive Bayes (NB), and linear discriminant (LD), have been utilized to extract the surface areas of lakes. Lastly, autoencoder (AE) classification algorithm was applied, and the effectiveness of all those algorithms was compared. Experimental studies were carried out on three different lakes (Hazar Lake, Salda Lake, Manyas Lake) using high-resolution Turkish RASAT RGB satellite images. The results indicated that AE algorithm obtained the highest accuracy values in both quantitative and qualitative analyses. Another important aspect of this study is that Structural Similarity Index (SSIM) and Universal Image Quality Index (UIQI) metrics that can evaluate close to human perception are used for comparison. With this application, it has been shown that overall accuracy calculated from test data may be inadequate in some cases by using SSIM, UIQI, mean squared error (MSE), peak signal to noise ratio (PSNR), and Cohen\'s KAPPA metrics. In the last application, the robustness of AE was examined with boxplots.

Deep unsupervised representation learning has recently led to new approaches in the field of Unsupervised Anomaly Detection (UAD) in brain MRI. The main principle behind these works is to learn a model of normal anatomy by learning to compress and recover healthy data. This allows to spot abnormal structures from erroneous recoveries of compressed, potentially anomalous samples. The concept is of great interest to the medical image analysis community as it i) relieves from the need of vast amounts of manually segmented training data-a necessity for and pitfall of current supervised Deep Learning-and ii) theoretically allows to detect arbitrary, even rare pathologies which supervised approaches might fail to find. To date, the experimental design of most works hinders a valid comparison, because i) they are evaluated against different datasets and different pathologies, ii) use different image resolutions and iii) different model architectures with varying complexity. The intent of this work is to establish comparability among recent methods by utilizing a single architecture, a single resolution and the same dataset(s). Besides providing a ranking of the methods, we also try to answer questions like i) how many healthy training subjects are needed to model normality and ii) if the reviewed approaches are also sensitive to domain shift. Further, we identify open challenges and provide suggestions for future community efforts and research directions.

Machine learning (ML) approaches have been widely applied to medical data in order to find reliable classifiers to improve diagnosis and detect candidate biomarkers of a disease. However, as a powerful, multivariate, data-driven approach, ML can be misled by biases and outliers in the training set, finding sample-dependent classification patterns. This phenomenon often occurs in biomedical applications in which, due to the scarcity of the data, combined with their heterogeneous nature and complex acquisition process, outliers and biases are very common. In this work we present a new workflow for biomedical research based on ML approaches, that maximizes the generalizability of the classification. This workflow is based on the adoption of two data selection tools: an autoencoder to identify the outliers and the Confounding Index, to understand which characteristics of the sample can mislead classification. As a study-case we adopt the controversial research about extracting brain structural biomarkers of Autism Spectrum Disorders (ASD) from magnetic resonance images. A classifier trained on a dataset composed by 86 subjects, selected using this framework, obtained an area under the receiver operating characteristic curve of 0.79. The feature pattern identified by this classifier is still able to capture the mean differences between the ASD and Typically Developing Control classes on 1460 new subjects in the same age range of the training set, thus providing new insights on the brain characteristics of ASD. In this work, we show that the proposed workflow allows to find generalizable patterns even if the dataset is limited, while skipping the two mentioned steps and using a larger but not well designed training set would have produced a sample-dependent classifier.

Data collected by an actigraphy device worn on the wrist or waist can provide objective measurements for studies related to physical activity; however, some data may contain intervals where values are missing. In previous studies, statistical methods have been applied to impute missing values on the basis of statistical assumptions. Deep learning algorithms, however, can learn features from the data without any such assumptions and may outperform previous approaches in imputation tasks.
The aim of this study was to impute missing values in data using a deep learning approach.
To develop an imputation model for missing values in accelerometer-based actigraphy data, a denoising convolutional autoencoder was adopted. We trained and tested our deep learning-based imputation model with the National Health and Nutrition Examination Survey data set and validated it with the external Korea National Health and Nutrition Examination Survey and the Korean Chronic Cerebrovascular Disease Oriented Biobank data sets which consist of daily records measuring activity counts. The partial root mean square error and partial mean absolute error of the imputed intervals (partial RMSE and partial MAE, respectively) were calculated using our deep learning-based imputation model (zero-inflated denoising convolutional autoencoder) as well as using other approaches (mean imputation, zero-inflated Poisson regression, and Bayesian regression).
The zero-inflated denoising convolutional autoencoder exhibited a partial RMSE of 839.3 counts and partial MAE of 431.1 counts, whereas mean imputation achieved a partial RMSE of 1053.2 counts and partial MAE of 545.4 counts, the zero-inflated Poisson regression model achieved a partial RMSE of 1255.6 counts and partial MAE of 508.6 counts, and Bayesian regression achieved a partial RMSE of 924.5 counts and partial MAE of 605.8 counts.
Our deep learning-based imputation model performed better than the other methods when imputing missing values in actigraphy data.