Prediction of mortality events of patients with acute heart failure in intensive care unit based on deep neural network.

BACKGROUND: Acute heart failure (AHF) in the intensive care unit (ICU) is characterized by its criticality, rapid progression, complex and changeable condition, and its pathophysiological process involves the interaction of multiple organs and systems. This makes it difficult to predict in-hospital mortality events comprehensively and accurately. Traditional analysis methods based on statistics and machine learning suffer from insufficient model performance, poor accuracy caused by prior dependence, and difficulty in adequately considering the complex relationships between multiple risk factors. Therefore, the application of deep neural network (DNN) techniques to the specific scenario, predicting mortality events of patients with AHF under intensive care, has become a research frontier. METHODS: This research utilized the MIMIC-IV critical care database as the primary data source and employed the synthetic minority over-sampling technique (SMOTE) to balance the dataset. Deep neural network models-backpropagation neural network (BPNN) and recurrent neural network (RNN), which are based on electronic medical record data mining, were employed to investigate the in-hospital death event judgment task of patients with AHF under intensive care. Additionally, multiple single machine learning models and ensemble learning models were constructed for comparative experiments. Moreover, we achieved various optimal performance combinations by modifying the classification threshold of deep neural network models to address the diverse real-world requirements in the ICU. Finally, we conducted an interpretable deep model using SHapley Additive exPlanations (SHAP) to uncover the most influential medical record features for each patient from the aspects of global and local interpretation. RESULTS: In terms of model performance in this scenario, deep neural network models outperform both single machine learning models and ensemble learning models, achieving the highest Accuracy, Precision, Recall, F1 value, and Area under the ROC curve, which can reach 0.949, 0.925, 0.983, 0.953, and 0.987 respectively. SHAP value analysis revealed that the ICU scores (APSIII, OASIS, SOFA) are significantly correlated with the occurrence of in-hospital fatal events. CONCLUSIONS: Our study underscores that DNN-based mortality event classifier offers a novel intelligent approach for forecasting and assessing the prognosis of AHF patients in the ICU. Additionally, the ICU scores stand out as the most predictive features, which implies that in the decision-making process of the models, ICU scores can provide the most crucial information, making the greatest positive or negative contribution to influence the incidence of in-hospital mortality among patients with acute heart failure.

Prioritizing test cases for deep learning-based video classifiers.

The widespread adoption of video-based applications across various fields highlights their importance in modern software systems. However, in comparison to images or text, labelling video test cases for the purpose of assessing system accuracy can lead to increased expenses due to their temporal structure and larger volume. Test prioritization has emerged as a promising approach to mitigate the labeling cost, which prioritizes potentially misclassified test inputs so that such inputs can be identified earlier with limited time and manual labeling efforts. However, applying existing prioritization techniques to video test cases faces certain limitations: they do not account for the unique temporal information present in video data. Unlike static image datasets that only contain spatial information, video inputs consist of multiple frames that capture the dynamic changes of objects over time. In this paper, we propose VRank, the first test prioritization approach designed specifically for video test inputs. The fundamental idea behind VRank is that video-type tests with a higher probability of being misclassified by the evaluated DNN classifier are considered more likely to reveal faults and will be prioritized higher. To this end, we train a ranking model with the aim of predicting the probability of a given test input being misclassified by a DNN classifier. This prediction relies on four types of generated features: temporal features (TF), video embedding features (EF), prediction features (PF), and uncertainty features (UF). We rank all test inputs in the target test set based on their misclassification probabilities. Videos with a higher likelihood of being misclassified will be prioritized higher. We conducted an empirical evaluation to assess the performance of VRank, involving 120 subjects with both natural and noisy datasets. The experimental results reveal VRank outperforms all compared test prioritization methods, with an average improvement of 5.76% ∼ 46.51% on natural datasets and 4.26% ∼ 53.56% on noisy datasets.

MFF-DTA: Multi-scale feature fusion for drug-target affinity prediction.

Accurately predicting drug-target affinity is crucial in expediting the discovery and development of new drugs, which is a complex and risky process. Identifying these interactions not only aids in screening potential compounds but also guides further optimization. To address this, we propose a multi-perspective feature fusion model, MFF-DTA, which integrates chemical structure, biological sequence, and other data to comprehensively capture drug-target affinity features. The MFF-DTA model incorporates multiple feature learning components, each of which is capable of extracting drug molecular features and protein target information, respectively. These components are able to obtain key information from both global and local perspectives. Then, these features from different perspectives are efficiently combined using specific splicing strategies to create a comprehensive representation. Finally, the model uses the fused features to predict drug-target affinity. Comparative experiments show that MFF-DTA performs optimally on the Davis and KIBA data sets. Ablation experiments demonstrate that removing specific components results in the loss of unique information, thus confirming the effectiveness of the MFF-DTA design. Improvements in DTA prediction methods will decrease costs and time in drug development, enhancing industry efficiency and ultimately benefiting patients.

Speech synthesis from three-axis accelerometer signals using conformer-based deep neural network.

Silent speech interfaces (SSIs) have emerged as innovative non-acoustic communication methods, and our previous study demonstrated the significant potential of three-axis accelerometer-based SSIs to identify silently spoken words with high classification accuracy. The developed accelerometer-based SSI with only four accelerometers and a small training dataset outperformed a conventional surface electromyography (sEMG)-based SSI. In this study, motivated by the promising initial results, we investigated the feasibility of synthesizing spoken speech from three-axis accelerometer signals. This exploration aimed to assess the potential of accelerometer-based SSIs for practical silent communication applications. Nineteen healthy individuals participated in our experiments. Five accelerometers were attached to the face to acquire speech-related facial movements while the participants read 270 Korean sentences aloud. For the speech synthesis, we used a convolution-augmented Transformer (Conformer)-based deep neural network model to convert the accelerometer signals into a Mel spectrogram, from which an audio waveform was synthesized using HiFi-GAN. To evaluate the quality of the generated Mel spectrograms, ten-fold cross-validation was performed, and the Mel cepstral distortion (MCD) was chosen as the evaluation metric. As a result, an average MCD of 5.03 ± 0.65 was achieved using four optimized accelerometers based on our previous study. Furthermore, the quality of generated Mel spectrograms was significantly enhanced by adding one more accelerometer attached under the chin, achieving an average MCD of 4.86 ± 0.65 (p < 0.001, Wilcoxon signed-rank test). Although an objective comparison is difficult, these results surpass those obtained using conventional SSIs based on sEMG, electromagnetic articulography, and electropalatography with the fewest sensors and a similar or smaller number of sentences to train the model. Our proposed approach will contribute to the widespread adoption of accelerometer-based SSIs, leveraging the advantages of accelerometers like low power consumption, invulnerability to physiological artifacts, and high portability.

Evaluation of multiple deep neural networks for detection of intracranial dural arteriovenous fistula on susceptibility weighted angiography imaging.

BACKGROUND: The natural history of intracranial dural arteriovenous fistula (DAVF) is variable and early diagnosis is crucial in order to positively impact the clinical course of aggressive DAVF. Artificial intelligence (AI) based techniques can be promising in this regard, and in this study, we used various deep neural network (DNN) architectures to determine whether DAVF could be reliably identified on susceptibility-weighted angiography images (SWAN). MATERIALS AND METHODS: A total of 3965 SWAN image slices from 30 digital subtraction angiographically proven DAVF patients and 4380 SWAN image slices from 40 age-matched patients with normal MRI findings as control group were included. The images were categorized as either DAVF or normal and the data was trained using various DNN such as VGG-16, EfficientNet-B0, and ResNet-50. RESULTS: Various DNN architectures showed the accuracy of 95.96% (VGG-16), 91.75% (EfficientNet-B0), and 86.23% (ResNet-50) on the SWAN image dataset. ROC analysis yielded an area under the curve of 0.796 (p < .001), best for VGG-16 model. Criterion of seven consecutive positive slices for DAVF diagnosis yielded a sensitivity of 74.68% with a specificity of 69.15%, while setting eight slices improved the sensitivity to above 80.38%, with a decrease of specificity up to 56.38%. Based on seven consecutive positive slices criteria, EfficientNet-B0 yielded a sensitivity of 73.21% with a specificity of 45.92% and ResNet-50 yielded a sensitivity of 72.39% with a specificity of 67.42%. CONCLUSION: This study shows that DNN can extract discriminative features of SWAN for the classification of DAVF from normal with good accuracy, reasonably good sensitivity and specificity.

Occlusion enhanced pan-cancer classification via deep learning.

Quantitative measurement of RNA expression levels through RNA-Seq is an ideal replacement for conventional cancer diagnosis via microscope examination. Currently, cancer-related RNA-Seq studies focus on two aspects: classifying the status and tissue of origin of a sample and discovering marker genes. Existing studies typically identify marker genes by statistically comparing healthy and cancer samples. However, this approach overlooks marker genes with low expression level differences and may be influenced by experimental results. This paper introduces "GENESO," a novel framework for pan-cancer classification and marker gene discovery using the occlusion method in conjunction with deep learning. we first trained a baseline deep LSTM neural network capable of distinguishing the origins and statuses of samples utilizing RNA-Seq data. Then, we propose a novel marker gene discovery method called "Symmetrical Occlusion (SO)". It collaborates with the baseline LSTM network, mimicking the "gain of function" and "loss of function" of genes to evaluate their importance in pan-cancer classification quantitatively. By identifying the genes of utmost importance, we then isolate them to train new neural networks, resulting in higher-performance LSTM models that utilize only a reduced set of highly relevant genes. The baseline neural network achieves an impressive validation accuracy of 96.59% in pan-cancer classification. With the help of SO, the accuracy of the second network reaches 98.30%, while using 67% fewer genes. Notably, our method excels in identifying marker genes that are not differentially expressed. Moreover, we assessed the feasibility of our method using single-cell RNA-Seq data, employing known marker genes as a validation test.

Natural language processing with transformers: a review.

Natural language processing (NLP) tasks can be addressed with several deep learning architectures, and many different approaches have proven to be efficient. This study aims to briefly summarize the use cases for NLP tasks along with the main architectures. This research presents transformer-based solutions for NLP tasks such as Bidirectional Encoder Representations from Transformers (BERT), and Generative Pre-Training (GPT) architectures. To achieve that, we conducted a step-by-step process in the review strategy: identify the recent studies that include Transformers, apply filters to extract the most consistent studies, identify and define inclusion and exclusion criteria, assess the strategy proposed in each study, and finally discuss the methods and architectures presented in the resulting articles. These steps facilitated the systematic summarization and comparative analysis of NLP applications based on Transformer architectures. The primary focus is the current state of the NLP domain, particularly regarding its applications, language models, and data set types. The results provide insights into the challenges encountered in this research domain.

Predicting tissue distribution and tumor delivery of nanoparticles in mice using machine learning models.

Nanoparticles (NPs) can be designed for targeted delivery in cancer nanomedicine, but the challenge is a low delivery efficiency (DE) to the tumor site. Understanding the impact of NPs' physicochemical properties on target tissue distribution and tumor DE can help improve the design of nanomedicines. Multiple machine learning and artificial intelligence models, including linear regression, support vector machine, random forest, gradient boosting, and deep neural networks (DNN), were trained and validated to predict tissue distribution and tumor delivery based on NPs' physicochemical properties and tumor therapeutic strategies with the dataset from Nano-Tumor Database. Compared to other machine learning models, the DNN model had superior predictions of DE to tumors and major tissues. The determination coefficients (R2) for the test datasets were 0.41, 0.42, 0.45, 0.79, 0.87, and 0.83 for DE in tumor, heart, liver, spleen, lung, and kidney, respectively. All the R2 and root mean squared error (RMSE) results of the test datasets were similar to the 5-fold cross validation results. Feature importance analysis showed that the core material of NPs played an important role in output predictions among all physicochemical properties. Furthermore, multiple NP formulations with greater DE to the tumor were determined by the DNN model. To facilitate model applications, the final model was converted to a web dashboard. This model could serve as a high-throughput pre-screening tool to support the design of new and efficient nanomedicines with greater tumor DE and serve as an alternative tool to reduce, refine, and partially replace animal experimentation in cancer nanomedicine research.

Explainable localization of premature ventricular contraction using deep learning-based semantic segmentation of 12-lead electrocardiogram.

Background: Predicting the origin of premature ventricular contraction (PVC) from the preoperative electrocardiogram (ECG) is important for catheter ablation therapies. We propose an explainable method that localizes PVC origin based on the semantic segmentation result of a 12-lead ECG using a deep neural network, considering suitable diagnosis support for clinical application. Methods: The deep learning-based semantic segmentation model was trained using 265 12-lead ECG recordings from 84 patients with frequent PVCs. The model classified each ECG sampling time into four categories: background (BG), sinus rhythm (SR), PVC originating from the left ventricular outflow tract (PVC-L), and PVC originating from the right ventricular outflow tract (PVC-R). Based on the ECG segmentation results, a rule-based algorithm classified ECG recordings into three categories: PVC-L, PVC-R, as well as Neutral, which is a group for the recordings requiring the physician's careful assessment before separating them into PVC-L and PVC-R. The proposed method was evaluated with a public dataset which was used in previous research. Results: The evaluation of the proposed method achieved neutral rate, accuracy, sensitivity, specificity, F1-score, and area under the curve of 0.098, 0.932, 0.963, 0.882, 0.945, and 0.852 on a private dataset, and 0.284, 0.916, 0.912, 0.930, 0.943, and 0.848 on a public dataset, respectively. These quantitative results indicated that the proposed method outperformed almost all previous studies, although a significant number of recordings resulted in requiring the physician's assessment. Conclusions: The feasibility of explainable localization of premature ventricular contraction was demonstrated using deep learning-based semantic segmentation of 12-lead ECG.Clinical trial registration: M26-148-8.

Slice-aware 5G network orchestration framework based on dual-slice isolation and management strategy (D-SIMS).

Network slicing is crucial to the 5G architecture because it enables the virtualization of network resources into a logical network. Network slices are created, isolated, and managed using software-defined networking (SDN) and network function virtualization (NFV). The virtual network function (VNF) manager must devise strategies for all stages of network slicing to ensure optimal allocation of physical infrastructure (PI) resources to high-acceptance virtual service requests (VSRs). This paper investigates two independent network slicing frameworks named as dual-slice isolation and management strategy (D-SIMS) and recommends the best of the two based on performance measurements. D-SIMS places VNFs for network slicing using self-sustained resource reservation (SSRR) and master-sliced resource reservation (MSRR), with some flexibility for the VNF manager to choose between them based on the degree to which the underlying physical infrastructure has been sliced. The present research work consists of two phases: the first deals with the creation of slices, and the second with determining the most efficient way to distribute resources among them. A deep neural network (DNN) technique is used in the first stage to generate slices for both PI and VSR. Then, in the second stage, we propose D-SIMS for resource allocation, which uses both the fuzzy-PROMETHEE method for node mapping and Dijkstra's algorithm for link mapping. During the slice creation phase, the proposed DNN training method's classification performance is evaluated using accuracy, precision, recall, and F1 score measures. To assess the success of resource allocation, metrics such as acceptance rate and resource effectiveness are used. The performance benefit is investigated under various network conditions and VSRs. Finally, to demonstrate the importance of the proposed work, we compare the simulation results to those in the academic literature.

Photonic deep residual time-delay reservoir computing.

Time-delay reservoir computing (TDRC) represents a simplified variant of recurrent neural networks, employing a nonlinear node with a feedback mechanism to construct virtual nodes. The capabilities of TDRC can be enhanced by transitioning to a deep architecture. In this work, we propose a novel photonic deep residual TDRC (DR-TDRC) with augmented capabilities. The additional time delay added to the residual structure enables DR-TDRC superior to traditional deep structures across various benchmark tasks, especially in memory capability and almost an order of magnitude improvement in nonlinear channel equalization. Additionally, a specifically designed clipping algorithm is utilized to counteract the damage of redundant layers in deep structures, enabling the extension of the deep TDRC to dozens rather than just a few layers, with higher performance. We experimentally demonstrate the proof-of-concept with a 4-layer DR-TDRC containing 960 interrelated neurons (240 neurons per layer), based on four injection-locked distributed feedback lasers. We confirm the potential for scalable deep RC with elevated performance. Our results provide a feasible approach for expanding deep photonic computing to satisfy the boosting demand for artificial intelligence.

Phase quantification using deep neural network processing of XRD patterns.

Mineral identification and quantification are key to the understanding and, hence, the capacity to predict material properties. The method of choice for mineral quantification is powder X-ray diffraction (XRD), generally using a Rietveld refinement approach. However, a successful Rietveld refinement requires preliminary identification of the phases that make up the sample. This is generally carried out manually, and this task becomes extremely long or virtually impossible in the case of very large datasets such as those from synchrotron X-ray diffraction computed tomography. To circumvent this issue, this article proposes a novel neural network (NN) method for automating phase identification and quantification. An XRD pattern calculation code was used to generate large datasets of synthetic data that are used to train the NN. This approach offers significant advantages, including the ability to construct databases with a substantial number of XRD patterns and the introduction of extensive variability into these patterns. To enhance the performance of the NN, a specifically designed loss function for proportion inference was employed during the training process, offering improved efficiency and stability compared with traditional functions. The NN, trained exclusively with synthetic data, proved its ability to identify and quantify mineral phases on synthetic and real XRD patterns. Trained NN errors were equal to 0.5% for phase quantification on the synthetic test set, and 6% on the experimental data, in a system containing four phases of contrasting crystal structures (calcite, gibbsite, dolomite and hematite). The proposed method is freely available on GitHub and allows for major advances since it can be applied to any dataset, regardless of the mineral phases present.

Machine learning based storm time modeling of ionospheric vertical total electron content over Ethiopia.

Geomagnetic storms can cause variations in the ionization levels of the ionosphere, which is commonly studied using the total electron content (TEC). TEC is a crucial parameter to identify the possible effects of ionospheric variations on satellite communication and navigation. This paper assesses the performance of light gradient boosting machine (LGB) and deep neural network (DNN) machine learning algorithms in modeling ionospheric vertical TEC (VTEC) during geomagnetic disturbances. GPS VTEC data for years 2011-2016 from 13 dual-frequency receiver stations over Ethiopia was utilized. Input parameters for the models were derived from the factors that influence VTEC, such as time, location, geomagnetic activity, solar activity, solar wind, and the interplanetary magnetic field. The LGB model improved the predictions of the DNN model from root mean squared error (RMSE), mean absolute percentage error (MAPE), and R2 values of 5.45 TECU, 21%, and 0.93 to 4.98 TECU, 18%, and 0.94 on the testing data, respectively. The two machine learning models significantly outperformed the International Reference Ionosphere (IRI 2020) model during the selected geomagnetic storm periods. This study could provide insight into the impacts of ionosphere variations on satellite communication and navigation systems in the low-latitude ionospheric region.

Benchmarking robustness of deep neural networks in semantic segmentation of fluorescence microscopy images.

BACKGROUND: Fluorescence microscopy (FM) is an important and widely adopted biological imaging technique. Segmentation is often the first step in quantitative analysis of FM images. Deep neural networks (DNNs) have become the state-of-the-art tools for image segmentation. However, their performance on natural images may collapse under certain image corruptions or adversarial attacks. This poses real risks to their deployment in real-world applications. Although the robustness of DNN models in segmenting natural images has been studied extensively, their robustness in segmenting FM images remains poorly understood RESULTS: To address this deficiency, we have developed an assay that benchmarks robustness of DNN segmentation models using datasets of realistic synthetic 2D FM images with precisely controlled corruptions or adversarial attacks. Using this assay, we have benchmarked robustness of ten representative models such as DeepLab and Vision Transformer. We find that models with good robustness on natural images may perform poorly on FM images. We also find new robustness properties of DNN models and new connections between their corruption robustness and adversarial robustness. To further assess the robustness of the selected models, we have also benchmarked them on real microscopy images of different modalities without using simulated degradation. The results are consistent with those obtained on the realistic synthetic images, confirming the fidelity and reliability of our image synthesis method as well as the effectiveness of our assay. CONCLUSIONS: Based on comprehensive benchmarking experiments, we have found distinct robustness properties of deep neural networks in semantic segmentation of FM images. Based on the findings, we have made specific recommendations on selection and design of robust models for FM image segmentation.

Manifold-based Shapley explanations for high dimensional correlated features.

Explainable artificial intelligence (XAI) holds significant importance in enhancing the reliability and transparency of network decision-making. SHapley Additive exPlanations (SHAP) is a game-theoretic approach for network interpretation, attributing confidence to inputs features to measure their importance. However, SHAP often relies on a flawed assumption that the model's features are independent, leading to incorrect results when dealing with correlated features. In this paper, we introduce a novel manifold-based Shapley explanation method, termed Latent SHAP. Latent SHAP transforms high-dimensional data into low-dimensional manifolds to capture correlations among features. We compute Shapley values on the data manifold and devise three distinct gradient-based mapping methods to transfer them back to the high-dimensional space. Our primary objectives include: (1) correcting misinterpretations by SHAP in certain samples; (2) addressing the challenge of feature correlations in high-dimensional data interpretation; and (3) reducing algorithmic complexity through Manifold SHAP for application in complex network interpretations. Code is available at https://github.com/Teriri1999/Latent-SHAP.

PD-DETECTOR: A sustainable and computationally intelligent mobile application model for Parkinson's disease severity assessment.

This paper introduces a mobile cloud-based predictive model for assisting Parkinson's disease (PD) patients. PD, a chronic neurodegenerative disorder, impairs motor functions and daily tasks due to the degeneration of dopamine-producing neurons in the brain. The model utilizes smartphones to aid patients in collecting voice samples, which are then sent to a cloud service for storage and processing. A hybrid deep learning model, trained using the UCI Parkinson's Telemonitoring Voice dataset, analyzes this data to estimate the severity of PD symptoms. The model's performance is noteworthy, with accuracy, sensitivity, and specificity metrics of 96.2 %, 94.15 %, and 96.15 %, respectively. Additionally, it boasts a rapid response time of just 13 s. Results are delivered to users via smartphone alert notifications, coupled with a knowledge base feature that educates them about PD. This system provides reliable home-based assessment and monitoring of PD and enables prompt medical intervention, significantly enhancing the quality of life for patients with Parkinson's disease.

Prediction of protein content in paddy rice (Oryza sativa L.) combining near-infrared spectroscopy and deep-learning algorithm.

Rice is a staple crop in Asia, with more than 400 million tons consumed annually worldwide. The protein content of rice is a major determinant of its unique structural, physical, and nutritional properties. Chemical analysis, a traditional method for measuring rice's protein content, demands considerable manpower, time, and costs, including preprocessing such as removing the rice husk. Therefore, of the technology is needed to rapidly and nondestructively measure the protein content of paddy rice during harvest and storage stages. In this study, the nondestructive technique for predicting the protein content of rice with husks (paddy rice) was developed using near-infrared spectroscopy and deep learning techniques. The protein content prediction model based on partial least square regression, support vector regression, and deep neural network (DNN) were developed using the near-infrared spectrum in the range of 950 to 2200 nm. 1800 spectra of the paddy rice and 1200 spectra from the brown rice were obtained, and these were used for model development and performance evaluation of the developed model. Various spectral preprocessing techniques was applied. The DNN model showed the best results among three types of rice protein content prediction models. The optimal DNN model for paddy rice was the model with first-order derivative preprocessing and the accuracy was a coefficient of determination for prediction, Rp 2 = 0.972 and root mean squared error for prediction, RMSEP = 0.048%. The optimal DNN model for brown rice was the model applied first-order derivative preprocessing with Rp 2 = 0.987 and RMSEP = 0.033%. These results demonstrate the commercial feasibility of using near-infrared spectroscopy for the non-destructive prediction of protein content in both husked rice seeds and paddy rice.

A deep neural network-based approach for seizure activity recognition of epilepsy sufferers.

Epilepsy is one of the most frequent neurological illnesses caused by epileptic seizures and the second most prevalent neurological ailment after stroke, affecting millions of people worldwide. People with epileptic disease are considered a category of people with disabilities. It significantly impairs a person's capacity to perform daily tasks, especially those requiring focusing or remembering. Electroencephalogram (EEG) signals are commonly used to diagnose people with epilepsy. However, it is tedious, time-consuming, and subjected to human errors. Several machine learning techniques have been applied to recognize epilepsy previously, but they have some limitations. This study proposes a deep neural network (DNN) machine learning model to determine the existing limitations of previous studies by improving the recognition efficiency of epileptic disease. A public dataset is used in this study and classified into training and testing sets. Experiments were performed to evaluate the DNN model with different dataset classification ratios (80:20), (70:30), (60:40), and (50:50) for training and testing, respectively. Results were evaluated by using different performance metrics including validations, and comparison processes that allow the assessment of the model's effectiveness. The experimental results showed that the overall efficiency of the proposed model is the highest compared with previous works, with an accuracy rate of 97%. Thus, this study is more accurate and efficient than the existing seizure detection approaches. DNN model has great potential for recognizing epileptic patient activity using a numerical EEG dataset offering a data-driven approach to improve the accuracy and reliability of seizure detection systems for the betterment of patient care and management of epilepsy.

Estimation of human age using machine learning on panoramic radiographs for Brazilian patients.

This paper addresses a relevant problem in Forensic Sciences by integrating radiological techniques with advanced machine learning methodologies to create a non-invasive, efficient, and less examiner-dependent approach to age estimation. Our study includes a new dataset of 12,827 dental panoramic X-ray images representing the Brazilian population, covering an age range from 2.25 to 96.50 years. To analyze these exams, we employed a model adapted from InceptionV4, enhanced with data augmentation techniques. The proposed approach achieved robust and reliable results, with a Test Mean Absolute Error of 3.1 years and an R-squared value of 95.5%. Professional radiologists have validated that our model focuses on critical features for age assessment used in odontology, such as pulp chamber dimensions and stages of permanent teeth calcification. Importantly, the model also relies on anatomical information from the mandible, maxillary sinus, and vertebrae, which enables it to perform well even in edentulous cases. This study demonstrates the significant potential of machine learning to revolutionize age estimation in Forensic Science, offering a more accurate, efficient, and universally applicable solution.

Deep Neural Network Integrated into Network-Based Stratification (D3NS): A Method to Uncover Cancer Subtypes from Somatic Mutations.

(1) Background: The identification of tumor subtypes is fundamental in precision medicine for accurate diagnoses and personalized therapies. Cancer development is often driven by the accumulation of somatic mutations that can cause alterations in tissue functions and morphologies. In this work, a method based on a deep neural network integrated into a network-based stratification framework (D3NS) is proposed to stratify tumors according to somatic mutations. (2) Methods: This approach leverages the power of deep neural networks to detect hidden information in the data by combining the knowledge contained in a network of gene interactions, as typical of network-based stratification methods. D3NS was applied using real-world data from The Cancer Genome Atlas for bladder, ovarian, and kidney cancers. (3) Results: This technique allows for the identification of tumor subtypes characterized by different survival rates and significant associations with several clinical outcomes (tumor stage, grade or response to therapy). (4) Conclusion: D3NS can provide a base model in cancer research and could be considered as a useful tool for tumor stratification, offering potential support in clinical settings.