Methods Mol Biol. 2024;2768:59-85. doi: 10.1007/978-1-0716-3690-9_5.

ABSTRACT

Antigen-specific B-cell ELISPOT and multicolor FluoroSpot assays, in which the membrane-bound antigen itself serves as the capture reagent for the antibodies that B cells secrete, inherently result in a broad range of spot sizes and intensities. The diversity of secretory footprint morphologies reflects the polyclonal nature of the antigen-specific B cell repertoire, with individual antibody-secreting B cells in the test sample differing in their affinity for the antigen, fine epitope specificity, and activation/secretion kinetics. To account for these heterogeneous spot morphologies, and to eliminate the need for setting up subjective counting parameters well-by-well, CTL introduces here its cutting-edge deep learning-based IntelliCount™ algorithm within the ImmunoSpot® Studio Software Suite, which integrates CTL's proprietary deep neural network. Here, we report detailed analyses of spots with a broad range of morphologies that were challenging to analyze using standard parameter-based counting approaches. IntelliCount™, especially in conjunction with high dynamic range (HDR) imaging, permits the extraction of accurate, high-content information of such spots, as required for assessing the affinity distribution of an antigen-specific memory B-cell repertoire ex vivo. IntelliCount™ also extends the range in which the number of antibody-secreting B cells plated and spots detected follow a linear function; that is, in which the frequencies of antigen-specific B cells can be accurately established. Introducing high-content analysis of secretory footprints in B-cell ELISPOT/FluoroSpot assays, therefore, fundamentally enhances the depth in which an antigen-specific B-cell repertoire can be studied using freshly isolated or cryopreserved primary cell material, such as peripheral blood mononuclear cells.

PMID:38502388 | DOI:10.1007/978-1-0716-3690-9_5

Eur J Pediatr. 2024 Mar 19. doi: 10.1007/s00431-024-05527-1. Online ahead of print.

ABSTRACT

This study is aimed at examining the impact of ChatGPT on pediatric endocrine and metabolic conditions, particularly in the areas of screening and diagnosis, in both Chinese and English modes. A 40-question questionnaire covering the four most common pediatric endocrine and metabolic conditions was posed to ChatGPT in both Chinese and English three times each. Six pediatric endocrinologists evaluated the responses. ChatGPT performed better when responding to questions in English, with an unreliable rate of 7.5% compared to 27.5% for Chinese questions, indicating a more consistent response pattern in English. Among the reliable questions, the answers were more comprehensive and satisfactory in the English mode. We also found disparities in ChatGPT's performance when interacting with different target groups and diseases, with improved performance for questions posed by clinicians in English and better performance for questions related to diabetes and overweight/obesity in Chinese for both clinicians and patients. Language comprehension, providing incomprehensive answers, and errors in key data were the main contributors to the low scores, according to reviewer feedback.

CONCLUSION: Despite these limitations, as ChatGPT continues to evolve and expand its network, it has significant potential as a practical and effective tool for clinical diagnosis and treatment.

WHAT IS KNOWN: • The deep learning-based large-language model ChatGPT holds great promise for improving clinical practice for both physicians and patients and has the potential to increase the speed and accuracy of disease screening and diagnosis, as well as enhance the overall efficiency of the medical process. However, the reliability and appropriateness of AI model responses in specific field remains unclear. • This study focused on the reliability and appropriateness of AI model responses to straightforward and fundamental questions related to the four most prevalent pediatric endocrine and metabolic disorders, for both healthcare providers and patients, in different language scenarios.

WHAT IS NEW: • The AI model performed better when responding to questions in English, with more consistent, as well as more comprehensive and satisfactory responses. In addition, we also found disparities in ChatGPT's performance when interacting with different target groups and different diseases. • Despite these limitations, as ChatGPT continues to evolve and expand its network, it has significant potential as a practical and effective tool for clinical diagnosis and treatment.

PMID:38502320 | DOI:10.1007/s00431-024-05527-1

JMIR Cancer. 2024 Mar 19;10:e52322. doi: 10.2196/52322.

ABSTRACT

BACKGROUND: People with cancer frequently experience severe and distressing symptoms associated with cancer and its treatments. Predicting symptoms in patients with cancer continues to be a significant challenge for both clinicians and researchers. The rapid evolution of machine learning (ML) highlights the need for a current systematic review to improve cancer symptom prediction.

OBJECTIVE: This systematic review aims to synthesize the literature that has used ML algorithms to predict the development of cancer symptoms and to identify the predictors of these symptoms. This is essential for integrating new developments and identifying gaps in existing literature.

METHODS: We conducted this systematic review in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist. We conducted a systematic search of CINAHL, Embase, and PubMed for English records published from 1984 to August 11, 2023, using the following search terms: cancer, neoplasm, specific symptoms, neural networks, machine learning, specific algorithm names, and deep learning. All records that met the eligibility criteria were individually reviewed by 2 coauthors, and key findings were extracted and synthesized. We focused on studies using ML algorithms to predict cancer symptoms, excluding nonhuman research, technical reports, reviews, book chapters, conference proceedings, and inaccessible full texts.

RESULTS: A total of 42 studies were included, the majority of which were published after 2017. Most studies were conducted in North America (18/42, 43%) and Asia (16/42, 38%). The sample sizes in most studies (27/42, 64%) typically ranged from 100 to 1000 participants. The most prevalent category of algorithms was supervised ML, accounting for 39 (93%) of the 42 studies. Each of the methods-deep learning, ensemble classifiers, and unsupervised ML-constituted 3 (3%) of the 42 studies. The ML algorithms with the best performance were logistic regression (9/42, 17%), random forest (7/42, 13%), artificial neural networks (5/42, 9%), and decision trees (5/42, 9%). The most commonly included primary cancer sites were the head and neck (9/42, 22%) and breast (8/42, 19%), with 17 (41%) of the 42 studies not specifying the site. The most frequently studied symptoms were xerostomia (9/42, 14%), depression (8/42, 13%), pain (8/42, 13%), and fatigue (6/42, 10%). The significant predictors were age, gender, treatment type, treatment number, cancer site, cancer stage, chemotherapy, radiotherapy, chronic diseases, comorbidities, physical factors, and psychological factors.

CONCLUSIONS: This review outlines the algorithms used for predicting symptoms in individuals with cancer. Given the diversity of symptoms people with cancer experience, analytic approaches that can handle complex and nonlinear relationships are critical. This knowledge can pave the way for crafting algorithms tailored to a specific symptom. In addition, to improve prediction precision, future research should compare cutting-edge ML strategies such as deep learning and ensemble methods with traditional statistical models.

PMID:38502171 | DOI:10.2196/52322

Radiology. 2024 Mar;310(3):e232780. doi: 10.1148/radiol.232780.

ABSTRACT

Background Mirai, a state-of-the-art deep learning-based algorithm for predicting short-term breast cancer risk, outperforms standard clinical risk models. However, Mirai is a black box, risking overreliance on the algorithm and incorrect diagnoses. Purpose To identify whether bilateral dissimilarity underpins Mirai's reasoning process; create a simplified, intelligible model, AsymMirai, using bilateral dissimilarity; and determine if AsymMirai may approximate Mirai's performance in 1-5-year breast cancer risk prediction. Materials and Methods This retrospective study involved mammograms obtained from patients in the EMory BrEast imaging Dataset, known as EMBED, from January 2013 to December 2020. To approximate 1-5-year breast cancer risk predictions from Mirai, another deep learning-based model, AsymMirai, was built with an interpretable module: local bilateral dissimilarity (localized differences between left and right breast tissue). Pearson correlation coefficients were computed between the risk scores of Mirai and those of AsymMirai. Subgroup analysis was performed in patients for whom AsymMirai's year-over-year reasoning was consistent. AsymMirai and Mirai risk scores were compared using the area under the receiver operating characteristic curve (AUC), and 95% CIs were calculated using the DeLong method. Results Screening mammograms (n = 210 067) from 81 824 patients (mean age, 59.4 years ± 11.4 [SD]) were included in the study. Deep learning-extracted bilateral dissimilarity produced similar risk scores to those of Mirai (1-year risk prediction, r = 0.6832; 4-5-year prediction, r = 0.6988) and achieved similar performance as Mirai. For AsymMirai, the 1-year breast cancer risk AUC was 0.79 (95% CI: 0.73, 0.85) (Mirai, 0.84; 95% CI: 0.79, 0.89; P = .002), and the 5-year risk AUC was 0.66 (95% CI: 0.63, 0.69) (Mirai, 0.71; 95% CI: 0.68, 0.74; P < .001). In a subgroup of 183 patients for whom AsymMirai repeatedly highlighted the same tissue over time, AsymMirai achieved a 3-year AUC of 0.92 (95% CI: 0.86, 0.97). Conclusion Localized bilateral dissimilarity, an imaging marker for breast cancer risk, approximated the predictive power of Mirai and was a key to Mirai's reasoning. © RSNA, 2024 Supplemental material is available for this article See also the editorial by Freitas in this issue.

PMID:38501952 | DOI:10.1148/radiol.232780

ACS Appl Mater Interfaces. 2024 Mar 19. doi: 10.1021/acsami.4c01207. Online ahead of print.

ABSTRACT

In this work, we designed a multimodal transformer that combines both the Simplified Molecular Input Line Entry System (SMILES) and molecular graph representations to enhance the prediction of polymer properties. Three models with different embeddings (SMILES, SMILES + monomer, and SMILES + dimer) were employed to assess the performance of incorporating multimodal features into transformer architectures. Fine-tuning results across five properties (i.e., density, glass-transition temperature (Tg), melting temperature (Tm), volume resistivity, and conductivity) demonstrated that the multimodal transformer with both the SMILES and the dimer configuration as inputs outperformed the transformer using only SMILES across all five properties. Furthermore, our model facilitates in-depth analysis by examining attention scores, providing deeper insights into the relationship between the deep learning model and the polymer attributes. We believe that our work, shedding light on the potential of multimodal transformers in predicting polymer properties, paves a new direction for understanding and refining polymer properties.

PMID:38501934 | DOI:10.1021/acsami.4c01207

Microsc Res Tech. 2024 Mar 19. doi: 10.1002/jemt.24548. Online ahead of print.

ABSTRACT

Recent advances in computing power triggered the use of artificial intelligence in image analysis in life sciences. To train these algorithms, a large enough set of certified labeled data is required. The trained neural network is then capable of producing accurate instance segmentation results that will then need to be re-assembled into the original dataset: the entire process requires substantial expertise and time to achieve quantifiable results. To speed-up the process, from cell organelle detection to quantification across electron microscopy modalities, we propose a deep-learning based approach for fast automatic outline segmentation (FAMOUS), that involves organelle detection combined with image morphology, and 3D meshing to automatically segment, visualize and quantify cell organelles within volume electron microscopy datasets. From start to finish, FAMOUS provides full segmentation results within a week on previously unseen datasets. FAMOUS was showcased on a HeLa cell dataset acquired using a focused ion beam scanning electron microscope, and on yeast cells acquired by transmission electron tomography. RESEARCH HIGHLIGHTS: Introducing a rapid, multimodal machine-learning workflow for the automatic segmentation of 3D cell organelles. Successfully applied to a variety of volume electron microscopy datasets and cell lines. Outperforming manual segmentation methods in time and accuracy. Enabling high-throughput quantitative cell biology.

PMID:38501891 | DOI:10.1002/jemt.24548

Chem Res Toxicol. 2024 Mar 19. doi: 10.1021/acs.chemrestox.3c00305. Online ahead of print.

ABSTRACT

Most drugs are mainly metabolized by cytochrome P450 (CYP450), which can lead to drug-drug interactions (DDI). Specifically, time-dependent inhibition (TDI) of CYP3A4 isoenzyme has been associated with clinically relevant DDI. To overcome potential DDI issues, high-throughput in vitro assays were established to assess the TDI of CYP3A4 during the discovery and lead optimization phases. However, in silico machine learning models would enable an earlier and larger-scale assessment of TDI potential liabilities. For CYP inhibition, most modeling efforts have focused on highly imbalanced and small data sets. Moreover, assay variability is rarely considered, which is key to understand the model's quality and suitability for decision-making. In this work, machine learning models were built for the prediction of TDI of CYP3A4, evaluated prospectively, and compared to the variability of the experimental assay. Different modeling strategies were investigated to assess their influence on the model's performance. Through multitask learning, additional data sets were leveraged for model building, coming from public databases, in-house CYP-related assays, or other pharmaceutical companies (federated learning). Apart from the numerical prediction of inactivation rates of CYP3A4 TDI, three-class predictions were carried out, giving a negative (inactivation rate kobs < 0.01 min-1), weak positive (0.01 ≤ kobs ≤ 0.025 min-1), or positive (kobs > 0.025 min-1) output. The final multitask graph neural network model achieved misclassification rates of 8 and 7% for positive and negative TDI, respectively. Importantly, the presented deep learning-based predictions had a similar precision to the reproducibility of in vitro experiments and thus offered great opportunities for drug design, early derisk of DDI potential, and selection of experiments. To facilitate CYP inhibition modeling efforts in the public domain, the developed model was used to annotate ∼16 000 publicly available structures, and a surrogate data set is shared as Supporting Information.

PMID:38501689 | DOI:10.1021/acs.chemrestox.3c00305

J Chem Theory Comput. 2024 Mar 19. doi: 10.1021/acs.jctc.3c01211. Online ahead of print.

ABSTRACT

The ordered assembly of Tau protein into filaments characterizes Alzheimer's and other neurodegenerative diseases, and thus, stabilization of Tau protein is a promising avenue for tauopathies therapy. To dissect the underlying aggregation mechanisms on Tau, we employ a set of molecular simulations and the Markov state model to determine the kinetics of ensemble of K18. K18 is the microtubule-binding domain of Tau protein and plays a vital role in the microtubule assembly, recycling processes, and amyloid fibril formation. Here, we efficiently explore the conformation of K18 with about 150 μs lifetimes in silico. Our results observe that all four repeat regions (R1-R4) are very dynamic, featuring frequent conformational conversion and lacking stable conformations, and the R2 region is more flexible than the R1, R3, and R4 regions. Additionally, it is worth noting that residues 300-310 in R2-R3 and residues 319-336 in R3 tend to form sheet structures, indicating that K18 has a broader functional role than individual repeat monomers. Finally, the simulations combined with Markov state models and deep learning reveal 5 key conformational states along the transition pathway and provide the information on the microsecond time scale interstate transition rates. Overall, this study offers significant insights into the molecular mechanism of Tau pathological aggregation and develops novel strategies for both securing tauopathies and advancing drug discovery.

PMID:38501645 | DOI:10.1021/acs.jctc.3c01211

Protein Sci. 2024 Apr;33(4):e4928. doi: 10.1002/pro.4928.

ABSTRACT

Molecular features play an important role in different bio-chem-informatics tasks, such as the Quantitative Structure-Activity Relationships (QSAR) modeling. Several pre-trained models have been recently created to be used in downstream tasks, either by fine-tuning a specific model or by extracting features to feed traditional classifiers. In this regard, a new family of Evolutionary Scale Modeling models (termed as ESM-2 models) was recently introduced, demonstrating outstanding results in protein structure prediction benchmarks. Herein, we studied the usefulness of the different-dimensional embeddings derived from the ESM-2 models to classify antimicrobial peptides (AMPs). To this end, we built a KNIME workflow to use the same modeling methodology across experiments in order to guarantee fair analyses. As a result, the 640- and 1280-dimensional embeddings derived from the 30- and 33-layer ESM-2 models, respectively, are the most valuable since statistically better performances were achieved by the QSAR models built from them. We also fused features of the different ESM-2 models, and it was concluded that the fusion contributes to getting better QSAR models than using features of a single ESM-2 model. Frequency studies revealed that only a portion of the ESM-2 embeddings is valuable for modeling tasks since between 43% and 66% of the features were never used. Comparisons regarding state-of-the-art deep learning (DL) models confirm that when performing methodologically principled studies in the prediction of AMPs, non-DL based QSAR models yield comparable-to-superior performances to DL-based QSAR models. The developed KNIME workflow is available-freely at https://github.com/cicese-biocom/classification-QSAR-bioKom. This workflow can be valuable to avoid unfair comparisons regarding new computational methods, as well as to propose new non-DL based QSAR models.

PMID:38501511 | DOI:10.1002/pro.4928

Protein Sci. 2024 Apr;33(4):e4936. doi: 10.1002/pro.4936.

ABSTRACT

De novo designing immunoglobulin-like frameworks that allow for functional loop diversification shows great potential for crafting antibody-like scaffolds with fully customizable structures and functions. In this work, we combined de novo parametric design with deep-learning methods for protein structure prediction and design to explore the structural landscape of 7-stranded immunoglobulin domains. After screening folding of nearly 4 million designs, we have assembled a structurally diverse library of ~50,000 immunoglobulin domains with high-confidence AlphaFold2 predictions and structures diverging from naturally occurring ones. The designed dataset enabled us to identify structural requirements for the correct folding of immunoglobulin domains, shed light on β-sheet-β-sheet rotational preferences and how these are linked to functional properties. Our approach eliminates the need for preset loop conformations and opens the route to large-scale de novo design of immunoglobulin-like frameworks.

PMID:38501461 | DOI:10.1002/pro.4936

Nan Fang Yi Ke Da Xue Xue Bao. 2024 Feb 20;44(2):387-396. doi: 10.12122/j.issn.1673-4254.2024.02.22.

ABSTRACT

OBJECTIVE: To develop a method for accurate identification of multiscale carotid plaques in ultrasound images.

METHODS: We proposed a two-stage carotid plaque detection method based on deep convolutional neural network (SM-YOLO).A series of algorithms such as median filtering, histogram equalization, and Gamma transformation were used to preprocess the dataset to improve image quality. In the first stage of the model construction, a candidate plaque set was built based on the YOLOX_l target detection network, using multiscale image training and multiscale image prediction strategies to accommodate carotid artery plaques of different shapes and sizes. In the second stage, the Histogram of Oriented Gradient (HOG) features and Local Binary Pattern (LBP) features were extracted and fused, and a Support Vector Machine (SVM) classifier was used to screen the candidate plaque set to obtain the final detection results. This model was compared quantitatively and visually with several target detection models (YOLOX_l, SSD, EfficientDet, YOLOV5_l, Faster R-CNN).

RESULTS: SM-YOLO achieved a recall of 89.44%, an accuracy of 90.96%, a F1-Score of 90.19%, and an AP of 92.70% on the test set, outperforming other models in all performance indicators and visual effects. The constructed model had a much shorter detection time than the Faster R-CNN model (only one third of that of the latter), thus meeting the requirements of real-time detection.

CONCLUSION: The proposed carotid artery plaque detection method has good performance for accurate identification of carotid plaques in ultrasound images.

PMID:38501425 | DOI:10.12122/j.issn.1673-4254.2024.02.22

Nan Fang Yi Ke Da Xue Xue Bao. 2024 Feb 20;44(2):333-343. doi: 10.12122/j.issn.1673-4254.2024.02.16.

ABSTRACT

OBJECTIVE: To propose a low-dose CT reconstruction algorithm across different scanners based on federated feature learning (FedCT) to improve the generalization of deep learning models for multiple CT scanners and protect data privacy.

METHODS: In the proposed FedCT framework, each client is assigned an inverse Radon transform-based reconstruction model to serve as a local network model that participates in federated learning. A projection- domain specific learning strategy is adopted to preserve the geometry specificity in the local projection domain. Federated feature learning is introduced in the model, which utilizes conditional parameters to mark the local data and feed the conditional parameters into the network for encoding to enhance the generalization of the model in the image domain.

RESULTS: In the cross-client, multi-scanner, and multi-protocol low-dose CT reconstruction experiments, FedCT achieved the highest PSNR (+2.8048, +2.7301, and +2.7263 compared to the second best federated learning method), the highest SSIM (+0.0009, +0.0165, and +0.0131 in the same comparison), and the lowest RMSE (- 0.6687, - 1.5956, and - 0.9962). In the ablation experiment, compared with the general federated learning strategy, the model with projection-specific learning strategy showed an average improvement by 1.18 on Q1 of the PSNR and an average decrease by 1.36 on Q3 of the RMSE on the test set. The introduction of federated feature learning in FedCT further improved the Q1 of the PSNR on the test set by 3.56 and reduced the Q3 of the RMSE by 1.80.

CONCLUSION: FedCT provides an effective solution for collaborative construction of CT reconstruction models, which can enhance model generalization and further improve the reconstruction performance on global data while protecting data privacy.

PMID:38501419 | DOI:10.12122/j.issn.1673-4254.2024.02.16

Med Image Comput Comput Assist Interv. 2023 Oct;14223:354-363. doi: 10.1007/978-3-031-43901-8_34. Epub 2023 Oct 1.

ABSTRACT

The automated segmentation and analysis of small vessels from in vivo imaging data is an important task for many clinical applications. While current filtering and learning methods have achieved good performance on the segmentation of large vessels, they are sub-optimal for small vessel detection due to their apparent geometric irregularity and weak contrast given the relatively limited resolution of existing imaging techniques. In addition, for supervised learning approaches, the acquisition of accurate pixel-wise annotations in these small vascular regions heavily relies on skilled experts. In this work, we propose a novel self-supervised network to tackle these challenges and improve the detection of small vessels from 3D imaging data. First, our network maximizes a novel shape-aware flux-based measure to enhance the estimation of small vasculature with non-circular and irregular appearances. Then, we develop novel local contrast guided attention(LCA) and enhancement(LCE) modules to boost the vesselness responses of vascular regions of low contrast. In our experiments, we compare with four filtering-based methods and a state-of-the-art self-supervised deep learning method in multiple 3D datasets to demonstrate that our method achieves significant improvement in all datasets. Further analysis and ablation studies have also been performed to assess the contributions of various modules to the improved performance in 3D small vessel segmentation. Our code is available at https://github.com/dengchihwei/LCNetVesselSeg.

PMID:38500803 | PMC:PMC10948105 | DOI:10.1007/978-3-031-43901-8_34

Comput Diffus MRI. 2023;14328:58-69. doi: 10.1007/978-3-031-47292-3_6. Epub 2024 Feb 7.

ABSTRACT

Susceptibility-induced distortion is a common artifact in diffusion MRI (dMRI), which deforms the dMRI locally and poses significant challenges in connectivity analysis. While various methods were proposed to correct the distortion, residual distortions often persist at varying degrees across brain regions and subjects. Generating a voxel-level residual distortion severity map can thus be a valuable tool to better inform downstream connectivity analysis. To fill this current gap in dMRI analysis, we propose a supervised deep-learning network to predict a severity map of residual distortion. The training process is supervised using the structural similarity index measure (SSIM) of the fiber orientation distribution (FOD) in two opposite phase encoding (PE) directions. Only b0 images and related outputs from the distortion correction methods are needed as inputs in the testing process. The proposed method is applicable in large-scale datasets such as the UK Biobank, Adolescent Brain Cognitive Development (ABCD), and other emerging studies that only have complete dMRI data in one PE direction but acquires b0 images in both PEs. In our experiments, we trained the proposed model using the Lifespan Human Connectome Project Aging (HCP-Aging) dataset (n=662) and apply the trained model to data (n=1330) from UK Biobank. Our results show low training, validation, and test errors, and the severity map correlates excellently with an FOD integrity measure in both HCP-Aging and UK Biobank data. The proposed method is also highly efficient and can generate the severity map in around 1 second for each subject.

PMID:38500569 | PMC:PMC10948104 | DOI:10.1007/978-3-031-47292-3_6

IEEE Trans Artif Intell. 2024 Jan;5(1):80-91. doi: 10.1109/TAI.2023.3249685. Epub 2023 Feb 27.

ABSTRACT

Deep learning models perform remarkably well on many classification tasks recently. The superior performance of deep neural networks relies on the large number of training data, which at the same time must have an equal class distribution in order to be efficient. However, in most real-world applications, the labeled data may be limited with high imbalance ratios among the classes, and thus, the learning process of most classification algorithms is adversely affected resulting in unstable predictions and low performance. Three main categories of approaches address the problem of imbalanced learning, i.e., data-level, algorithmic level, and hybrid methods, which combine the two aforementioned approaches. Data generative methods are typically based on generative adversarial networks, which require significant amounts of data, while model-level methods entail extensive domain expert knowledge to craft the learning objectives, thereby being less accessible for users without such knowledge. Moreover, the vast majority of these approaches are designed and applied to imaging applications, less to time series, and extremely rare to both of them. To address the above issues, we introduce GENDA, a generative neighborhood-based deep autoencoder, which is simple yet effective in its design and can be successfully applied to both image and time-series data. GENDA is based on learning latent representations that rely on the neighboring embedding space of the samples. Extensive experiments, conducted on a variety of widely-used real datasets demonstrate the efficacy of the proposed method.

IMPACT STATEMENT—: Imbalanced data classification is an actual and important issue in many real-world learning applications hampering most classification tasks. Fraud detection, biomedical imaging categorizing healthy people versus patients, and object detection are some indicative domains with an economic, social and technological impact, which are greatly affected by inherent imbalanced data distribution. However, the majority of the existing algorithms that address the imbalanced classification problem are designed with a particular application in mind, and thus they can be used with specific datasets and even hyperparameters. The generative model introduced in this paper overcomes this limitation and produces improved results for a large class of imaging and time series data even under severe imbalance ratios, making it quite competitive.

PMID:38500544 | PMC:PMC10947150 | DOI:10.1109/TAI.2023.3249685

Cybern Syst. 2021;52(1):105-126. doi: 10.1080/01969722.2020.1827796. Epub 2020 Oct 6.

ABSTRACT

Electricity generation from burning fossil fuel is one of the major contributors to global warming. Renewable energy sources are a viable alternative to produce electrical energy and to reduce the emission from power industry. They have unlocked opportunities for consumers to produce electricity locally and use it on-site that reduces dependency on centralized generation. Despite the widespread availability, one of the major challenges is to understand their characteristics in a more informative way. Wind energy is highly dependent on the intermittent wind speed profile. This paper proposes the prediction of wind speed that simplifies wind farm planning and feasibility study. Twelve artificial intelligence algorithms were used for wind speed prediction from collected meteorological parameters. The model performances were compared to determine the wind speed prediction accuracy and model comparison for different sizes of data set. The results show, the most effective algorithm varies based on the data size.

PMID:38500540 | PMC:PMC10947156 | DOI:10.1080/01969722.2020.1827796

Parasit Vectors. 2024 Mar 18;17(1):143. doi: 10.1186/s13071-024-06209-5.

ABSTRACT

BACKGROUND: Accurately determining the age and survival probabilities of adult mosquitoes is crucial for understanding parasite transmission, evaluating the effectiveness of control interventions and assessing disease risk in communities. This study was aimed at demonstrating the rapid identification of epidemiologically relevant age categories of Anopheles funestus, a major Afro-tropical malaria vector, through the innovative combination of infrared spectroscopy and machine learning, instead of the cumbersome practice of dissecting mosquito ovaries to estimate age based on parity status.

METHODS: Anopheles funestus larvae were collected in rural south-eastern Tanzania and reared in an insectary. Emerging adult females were sorted by age (1-16 days old) and preserved using silica gel. Polymerase chain reaction (PCR) confirmation was conducted using DNA extracted from mosquito legs to verify the presence of An. funestus and to eliminate undesired mosquitoes. Mid-infrared spectra were obtained by scanning the heads and thoraces of the mosquitoes using an attenuated total reflection-Fourier transform infrared (ATR-FT-IR) spectrometer. The spectra (N = 2084) were divided into two epidemiologically relevant age groups: 1-9 days (young, non-infectious) and 10-16 days (old, potentially infectious). The dimensionality of the spectra was reduced using principal component analysis, and then a set of machine learning and multi-layer perceptron (MLP) models were trained using the spectra to predict the mosquito age categories.

RESULTS: The best-performing model, XGBoost, achieved overall accuracy of 87%, with classification accuracy of 89% for young and 84% for old An. funestus. When the most important spectral features influencing the model performance were selected to train a new model, the overall accuracy increased slightly to 89%. The MLP model, utilizing the significant spectral features, achieved higher classification accuracy of 95% and 94% for the young and old An. funestus, respectively. After dimensionality reduction, the MLP achieved 93% accuracy for both age categories.

CONCLUSIONS: This study shows how machine learning can quickly classify epidemiologically relevant age groups of An. funestus based on their mid-infrared spectra. Having been previously applied to An. gambiae, An. arabiensis and An. coluzzii, this demonstration on An. funestus underscores the potential of this low-cost, reagent-free technique for widespread use on all the major Afro-tropical malaria vectors. Future research should demonstrate how such machine-derived age classifications in field-collected mosquitoes correlate with malaria in human populations.

PMID:38500231 | DOI:10.1186/s13071-024-06209-5

BMC Med Inform Decis Mak. 2024 Mar 18;24(1):77. doi: 10.1186/s12911-024-02479-2.

ABSTRACT

OBJECTIVE: To address the challenge of assessing sedation status in critically ill patients in the intensive care unit (ICU), we aimed to develop a non-contact automatic classifier of agitation using artificial intelligence and deep learning.

METHODS: We collected the video recordings of ICU patients and cut them into 30-second (30-s) and 2-second (2-s) segments. All of the segments were annotated with the status of agitation as "Attention" and "Non-attention". After transforming the video segments into movement quantification, we constructed the models of agitation classifiers with Threshold, Random Forest, and LSTM and evaluated their performances.

RESULTS: The video recording segmentation yielded 427 30-s and 6405 2-s segments from 61 patients for model construction. The LSTM model achieved remarkable accuracy (ACC 0.92, AUC 0.91), outperforming other methods.

CONCLUSION: Our study proposes an advanced monitoring system combining LSTM and image processing to ensure mild patient sedation in ICU care. LSTM proves to be the optimal choice for accurate monitoring. Future efforts should prioritize expanding data collection and enhancing system integration for practical application.

PMID:38500135 | DOI:10.1186/s12911-024-02479-2

BMC Med Imaging. 2024 Mar 18;24(1):63. doi: 10.1186/s12880-024-01241-4.

ABSTRACT

Significant advancements in machine learning algorithms have the potential to aid in the early detection and prevention of cancer, a devastating disease. However, traditional research methods face obstacles, and the amount of cancer-related information is rapidly expanding. The authors have developed a helpful support system using three distinct deep-learning models, ResNet-50, EfficientNet-B3, and ResNet-101, along with transfer learning, to predict lung cancer, thereby contributing to health and reducing the mortality rate associated with this condition. This offer aims to address the issue effectively. Using a dataset of 1,000 DICOM lung cancer images from the LIDC-IDRI repository, each image is classified into four different categories. Although deep learning is still making progress in its ability to analyze and understand cancer data, this research marks a significant step forward in the fight against cancer, promoting better health outcomes and potentially lowering the mortality rate. The Fusion Model, like all other models, achieved 100% precision in classifying Squamous Cells. The Fusion Model and ResNet-50 achieved a precision of 90%, closely followed by EfficientNet-B3 and ResNet-101 with slightly lower precision. To prevent overfitting and improve data collection and planning, the authors implemented a data extension strategy. The relationship between acquiring knowledge and reaching specific scores was also connected to advancing and addressing the issue of imprecise accuracy, ultimately contributing to advancements in health and a reduction in the mortality rate associated with lung cancer.

PMID:38500083 | DOI:10.1186/s12880-024-01241-4

Med Biol Eng Comput. 2024 Mar 19. doi: 10.1007/s11517-024-03056-5. Online ahead of print.

ABSTRACT

Respiratory diseases have a significant global impact, and assessing these conditions is crucial for improving patient outcomes. Chest X-ray is widely used for diagnosis, but expert evaluation can be challenging. Automatic computer-aided diagnosis methods can provide support for clinicians in these tasks. Deep learning has emerged as a set of algorithms with exceptional potential in such tasks. However, these algorithms require a vast amount of data, often scarce in medical imaging domains. In this work, a new data augmentation methodology based on adapted generative latent diffusion models is proposed to improve the performance of an automatic pathological screening in two high-impact scenarios: tuberculosis and lung nodules. The methodology is evaluated using three publicly available datasets, representative of real-world settings. An ablation study obtained the highest-performing image generation model configuration regarding the number of training steps. The results demonstrate that the novel set of generated images can improve the performance of the screening of these two highly relevant pathologies, obtaining an accuracy of 97.09%, 92.14% in each dataset of tuberculosis screening, respectively, and 82.19% in lung nodules. The proposal notably improves on previous image generation methods for data augmentation, highlighting the importance of the contribution in these critical public health challenges.

PMID:38499946 | DOI:10.1007/s11517-024-03056-5