Sci Rep. 2024 Nov 5;14(1):26752. doi: 10.1038/s41598-024-78184-x.

ABSTRACT

This study evaluates the effectiveness of an Artificial Intelligence (AI)-based smartphone application designed for decay detection on intraoral photographs, comparing its performance to that of junior dentists. Conducted at The Aga Khan University Hospital, Karachi, Pakistan, this study utilized a dataset comprising 7,465 intraoral images, including both primary and secondary dentitions. These images were meticulously annotated by two experienced dentists and further verified by senior dentists. A YOLOv5s model was trained on this dataset and integrated into a smartphone application, while a Detection Transformer was also fine-tuned for comparative purposes. Explainable AI techniques were employed to assess the AI's decision-making processes. A sample of 70 photographs was used to directly compare the application's performance with that of junior dentists. Results showed that the YOLOv5s-based smartphone application achieved a precision of 90.7%, sensitivity of 85.6%, and an F1 score of 88.0% in detecting dental decay. In contrast, junior dentists achieved 83.3% precision, 64.1% sensitivity, and an F1 score of 72.4%. The study concludes that the YOLOv5s algorithm effectively detects dental decay on intraoral photographs and performs comparably to junior dentists. This application holds potential for aiding in the evaluation of the caries index within populations, thus contributing to efforts aimed at reducing the disease burden at the community level.

PMID:39500993 | DOI:10.1038/s41598-024-78184-x

JMIR Form Res. 2024 Nov 5;8:e58776. doi: 10.2196/58776.

ABSTRACT

BACKGROUND: Breast implants, including textured variants, have been widely used in aesthetic and reconstructive mammoplasty. However, the textured type, which is one of the shell texture types of breast implants, has been identified as a possible etiologic factor for lymphoma, specifically breast implant-associated anaplastic large cell lymphoma (BIA-ALCL). Identifying the shell texture type of the implant is critical to diagnosing BIA-ALCL. However, distinguishing the shell texture type can be difficult due to the loss of human memory and medical history. An alternative approach is to use ultrasonography, but this method also has limitations in quantitative assessment.

OBJECTIVE: This study aims to determine the feasibility of using a deep learning model to classify the shell texture type of breast implants and make robust predictions from ultrasonography images from heterogeneous sources.

METHODS: A total of 19,502 breast implant images were retrospectively collected from heterogeneous sources, including images captured from both Canon and GE devices, images of ruptured implants, and images without implants, as well as publicly available images. The Canon images were trained using ResNet-50. The model's performance on the Canon dataset was evaluated using stratified 5-fold cross-validation. Additionally, external validation was conducted using the GE and publicly available datasets. The area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (PRAUC) were calculated based on the contribution of the pixels with Gradient-weighted Class Activation Mapping (Grad-CAM). To identify the significant pixels for classification, we masked the pixels that contributed less than 10%, up to a maximum of 100%. To assess the model's robustness to uncertainty, Shannon entropy was calculated for 4 image groups: Canon, GE, ruptured implants, and without implants.

RESULTS: The deep learning model achieved an average AUROC of 0.98 and a PRAUC of 0.88 in the Canon dataset. The model achieved an AUROC of 0.985 and a PRAUC of 0.748 for images captured with GE devices. Additionally, the model predicted an AUROC of 0.909 and a PRAUC of 0.958 for the publicly available dataset. This model maintained the PRAUC values for quantitative validation when masking up to 90% of the least-contributing pixels and the remnant pixels in breast shell layers. Furthermore, the prediction uncertainty increased in the following order: Canon (0.066), GE (0072), ruptured implants (0.371), and no implants (0.777).

CONCLUSIONS: We have demonstrated the feasibility of using deep learning to predict the shell texture type of breast implants. This approach quantifies the shell texture types of breast implants, supporting the first step in the diagnosis of BIA-ALCL.

PMID:39499915 | DOI:10.2196/58776

J Am Chem Soc. 2024 Nov 5. doi: 10.1021/jacs.4c11686. Online ahead of print.

ABSTRACT

The integration of deep learning-based molecular generation models into drug discovery has garnered significant attention for its potential to expedite the development process. Central to this is lead optimization, a critical phase where existing molecules are refined into viable drug candidates. As various methods for deep lead optimization continue to emerge, it is essential to classify these approaches more clearly. We categorize lead optimization methods into two main types: goal-directed and structure-directed. Our focus is on structure-directed optimization, which, while highly relevant to practical applications, is less explored compared to goal-directed methods. Through a systematic review of conventional computational approaches, we identify four tasks specific to structure-directed optimization: fragment replacement, linker design, scaffold hopping, and side-chain decoration. We discuss the motivations, training data construction, and current developments for each of these tasks. Additionally, we use classical optimization taxonomy to classify both goal-directed and structure-directed methods, highlighting their challenges and future development prospects. Finally, we propose a reference protocol for experimental chemists to effectively utilize Generative AI (GenAI)-based tools in structural modification tasks, bridging the gap between methodological advancements and practical applications.

PMID:39499822 | DOI:10.1021/jacs.4c11686

PLoS Comput Biol. 2024 Nov 5;20(11):e1012526. doi: 10.1371/journal.pcbi.1012526. Online ahead of print.

ABSTRACT

Protein domain annotation is typically done by predictive models such as HMMs trained on sequence motifs. However, sequence-based annotation methods are prone to error, particularly in calling domain boundaries and motifs within them. These methods are limited by a lack of structural information accessible to the model. With the advent of deep learning-based protein structure prediction, existing sequenced-based domain annotation methods can be improved by taking into account the geometry of protein structures. We develop dimensionality reduction methods to annotate repeat units of the Leucine Rich Repeat solenoid domain. The methods are able to correct mistakes made by existing machine learning-based annotation tools and enable the automated detection of hairpin loops and structural anomalies in the solenoid. The methods are applied to 127 predicted structures of LRR-containing intracellular innate immune proteins in the model plant Arabidopsis thaliana and validated against a benchmark dataset of 172 manually-annotated LRR domains.

PMID:39499733 | DOI:10.1371/journal.pcbi.1012526

PLoS One. 2024 Nov 5;19(11):e0308122. doi: 10.1371/journal.pone.0308122. eCollection 2024.

ABSTRACT

This study analyzed online public discourse on Twitter (later rebranded as X) during the COVID-19 pandemic to understand key factors associated with vaccine hesitancy by employing deep-learning techniques. Text classification analysis reveals a significant association between attitudes toward vaccination and the unique socio-economic characteristics of US states, such as education, race, income or voting behavior. However, our results indicate that attributing vaccine hesitancy solely to a single social factor is not appropriate. Furthermore, the topic modeling of online discourse identifies two distinct sets of justifications for vaccine hesitancy. The first set pertains to political concerns, including constitutional rights and conspiracy theories. The second pertains to medical concerns about vaccine safety and efficacy. However, vaccine-hesitant social media users pragmatically use broad categories of justification for their beliefs. This behavior may suggest that vaccine hesitancy is influenced by political beliefs, unconscious emotions, and gut-level instinct. Our findings have further implications for the critical role of trust in public institutions in shaping attitudes toward vaccination and the need for tailored communication strategies to restore faith in marginalized communities.

PMID:39499705 | DOI:10.1371/journal.pone.0308122

IEEE J Biomed Health Inform. 2024 Nov 5;PP. doi: 10.1109/JBHI.2024.3491855. Online ahead of print.

ABSTRACT

Scoliosis significantly impacts quality of life, highlighting the need for effective early scoliosis screening (SS) and intervention. However, current SS methods often involve physical contact, undressing, or radiation exposure. This study introduces an innovative, non-invasive SS approach utilizing a monocular RGB camera that eliminates the need for undressing, sensor attachment, and radiation exposure. We introduce a novel approach that employs Parameterized Human 3D Reconstruction (PH3DR) to reconstruct 3D human models, thereby effectively eliminating clothing obstructions, seamlessly integrated with an ISANet segmentation network, which has been enhanced by Multi-Scale Fusion Attention (MSFA) module we proposed for facilitating the segmentation of distinct human trunk and limb features (HTLF), capturing body surface asymmetries related to scoliosis. Additionally, we propose a Swin Transformer-enhanced CMU-Pose to extract human skeleton features (HSF), identifying skeletal asymmetries crucial for SS. Finally, we develop a fusion model that integrates the HTLF and HSF, combining surface morphology and skeletal features to improve the precision of SS. The experiments demonstrated that PH3DR and MSFA significantly improved the segmentation and extraction of HTLF, whereas ST-based CMU-Pose substantially enhanced the extraction of HSF. Our final model achieved a comparable F1 (0.895 ±0.014) to the best-performing baseline model, with only 0.79% of the parameters and 1.64% of the FLOPs, achieving 36 FPS-significantly higher than the best-performing baseline model (10 FPS). Moreover, our model outperformed two spine surgeons, one less experienced and the other moderately experienced. With its patient-friendly, privacy-preserving, and easily deployable solution, this approach is particularly well-suited for early SS and routine monitoring.

PMID:39499599 | DOI:10.1109/JBHI.2024.3491855

Transl Vis Sci Technol. 2024 Nov 4;13(11):2. doi: 10.1167/tvst.13.11.2.

ABSTRACT

PURPOSE: Automated segmentation software in optical coherence tomography (OCT) devices is usually developed for and primarily tested on common diseases. Therefore segmentation accuracy of automated software can be limited in eyes with rare pathologies.

METHODS: We sought to develop a semisupervised deep learning segmentation model that segments 10 retinal layers and four retinal features in eyes with Macular Telangiectasia Type II (MacTel) using a small labeled dataset by leveraging unlabeled images. We compared our model against popular supervised and semisupervised models, as well as conducted ablation studies on the model itself.

RESULTS: Our model significantly outperformed all other models in terms of intersection over union on the 10 retinal layers and two retinal features in the test dataset. For the remaining two features, the pre-retinal space above the internal limiting membrane and the background below the retinal pigment epithelium, all of the models performed similarly. Furthermore, we showed that using more unlabeled images improved the performance of our semisupervised model.

CONCLUSIONS: Our model improves segmentation performance over supervised models by leveraging unlabeled data. This approach has the potential to improve segmentation performance for other diseases, where labeled data is limited but unlabeled data abundant.

TRANSLATIONAL RELEVANCE: Improving automated segmentation of MacTel pathology on OCT imaging by leveraging unlabeled data may enable more accurate assessment of disease progression, and this approach may be useful for improving feature identification and location on OCT in other rare diseases as well.

PMID:39499591 | DOI:10.1167/tvst.13.11.2

Kidney360. 2024 Nov 5. doi: 10.34067/KID.0000000620. Online ahead of print.

ABSTRACT

BACKGROUND: The Network for Pancreatic Organ donors with Diabetes-Kidney (nPOD-K) project was initiated to assess the feasibility of using kidneys from organ donors to enhance understanding of diabetic kidney disease (DKD) progression.

METHODS: Traditional and digital pathology approaches were employed to characterize the nPOD-K cohort. Periodic acid-Schiff- and Hematoxylin and Eosin-stained sections were used to manually examine and score each nPOD-K case. Brightfield and fluorescently labelled whole slide images of nPOD-K sections were used to train, validate, and test deep learning compartment segmentation and machine learning image analysis tools within Visiopharm software. These digital pathology tools were subsequently employed to evaluate kidney cell-specific markers and pathological indicators.

RESULTS: Digital quantitation of mesangial expansion, tubular atrophy, kidney injury molecule (KIM)-1 expression, cellular infiltration, and fibrosis index aligned with histological DKD classification, as defined by pathologists' review. Histological quantification confirmed loss of podocyte, endothelial, and tubular markers, correlating with DKD progression. Altered expression patterns of prominin-1, protein-tyrosine phosphatase receptor type O, and coronin 2B were validated, in agreement with reported literature.

CONCLUSIONS: The nPOD-K cohort provides a unique open resource opportunity to not only validate putative drug targets but also better understand DKD pathophysiology. A broad range of pathogenesis can be visualized in each case, providing a simulated timeline of DKD progression. We conclude that organ donor-derived tissues serve as high-quality samples, provide a comprehensive view of tissue pathology, and address the need for human kidney tissues available for research.

PMID:39499578 | DOI:10.34067/KID.0000000620

J Chem Inf Model. 2024 Nov 5. doi: 10.1021/acs.jcim.4c01267. Online ahead of print.

ABSTRACT

The CACHE challenges are a series of prospective benchmarking exercises to evaluate progress in the field of computational hit-finding. Here we report the results of the inaugural CACHE challenge in which 23 computational teams each selected up to 100 commercially available compounds that they predicted would bind to the WDR domain of the Parkinson's disease target LRRK2, a domain with no known ligand and only an apo structure in the PDB. The lack of known binding data and presumably low druggability of the target is a challenge to computational hit finding methods. Of the 1955 molecules predicted by participants in Round 1 of the challenge, 73 were found to bind to LRRK2 in an SPR assay with a KD lower than 150 μM. These 73 molecules were advanced to the Round 2 hit expansion phase, where computational teams each selected up to 50 analogs. Binding was observed in two orthogonal assays for seven chemically diverse series, with affinities ranging from 18 to 140 μM. The seven successful computational workflows varied in their screening strategies and techniques. Three used molecular dynamics to produce a conformational ensemble of the targeted site, three included a fragment docking step, three implemented a generative design strategy and five used one or more deep learning steps. CACHE #1 reflects a highly exploratory phase in computational drug design where participants adopted strikingly diverging screening strategies. Machine learning-accelerated methods achieved similar results to brute force (e.g., exhaustive) docking. First-in-class, experimentally confirmed compounds were rare and weakly potent, indicating that recent advances are not sufficient to effectively address challenging targets.

PMID:39499532 | DOI:10.1021/acs.jcim.4c01267

J Patient Rep Outcomes. 2024 Nov 5;8(1):126. doi: 10.1186/s41687-024-00808-7.

ABSTRACT

PURPOSE: To critically examine the current state of machine learning (ML) models including patient-reported outcome measure (PROM) scores in cancer research, by investigating the reporting quality of currently available studies and proposing areas of improvement for future use of ML in the field.

METHODS: PubMed and Web of Science were systematically searched for publications of studies on patients with cancer applying ML models with PROM scores as either predictors or outcomes. The reporting quality of applied ML models was assessed utilizing an adapted version of the MI-CLAIM (Minimum Information about CLinical Artificial Intelligence Modelling) checklist. The key variables of the checklist are study design, data preparation, model development, optimization, performance, and examination. Reproducibility and transparency complement the reporting quality criteria.

RESULTS: The literature search yielded 1634 hits, of which 52 (3.2%) were eligible. Thirty-six (69.2%) publications included PROM scores as a predictor and 32 (61.5%) as an outcome. Results of the reporting quality appraisal indicate a potential for improvement, especially in the areas of model examination. According to the standards of the MI-CLAIM checklist, the reporting quality of ML models in included studies proved to be low. Only nine (17.3%) publications present a discussion about the clinical applicability of the developed model and reproducibility and only three (5.8%) provide a code to reproduce the model and the results.

CONCLUSION: The herein performed critical examination of the status quo of the application of ML models including PROM scores in published oncological studies allowed the identification of areas of improvement for reporting and future use of ML in the field.

PMID:39499409 | DOI:10.1186/s41687-024-00808-7

Urolithiasis. 2024 Nov 5;52(1):157. doi: 10.1007/s00240-024-01656-2.

ABSTRACT

OBJECTIVES: To develop a deep learning (DL) model based on computed tomography (CT) images to predict the success of extracorporeal shock wave lithotripsy (SWL) treatment for patients with ureteral stones larger than 1 cm.

MATERIALS AND METHODS: We enrolled 333 patients who underwent SWL treatment for ureteral stones and randomly divided them into training and test sets. A DL model was built based on CT images of ureteral stones to predict SWL outcomes. The predictive efficacy of the DL model was assessed by comparing it with traditional and radiomics models.

RESULTS: The DL model demonstrated significantly better predictive performance in both training and test sets compared to radiomics (training set, AUC: 0.993 vs. 0.923, P < 0.001; test set AUC: 0.982 vs. 0.846, P < 0.001) and traditional models (training set AUC: 0.993 vs. 0.75, P = 0.005; test set AUC: 0.982 vs. 0.677, P < 0.001). Decision curve analysis (DCA) also proved that the DL model brought more benefit in predicting the success of SWL treatment than other methods.

CONCLUSION: The DL model based on CT images showed excellent ability to predict the probability of success of SWL treatment for patients with ureteral stones larger than 1 cm, providing a new auxiliary tool for clinical treatment decision-making.

PMID:39499273 | DOI:10.1007/s00240-024-01656-2

Ann Med. 2024 Dec;56(1):2418963. doi: 10.1080/07853890.2024.2418963. Epub 2024 Nov 5.

ABSTRACT

OBJECTIVE: The risk of gastric cancer can be predicted by gastroscopic manifestation recognition and the Kyoto Gastritis Score. This study aims to validate the applicability of AI approaches for recognizing gastroscopic manifestations according to the definition of Kyoto Gastritis Score, with the goal of improving early gastric cancer detection and reducing gastric cancer mortality.

METHODS: In this retrospective study, 29013 gastric endoscopy images were collected and carefully annotated into five categories according to the Kyoto Gastritis Score, i.e. atrophy (A), diffuse redness (DR), enlarged folds (H), intestinal metaplasia (IM), and nodularity (N). As a multi-label recognition task, we propose a deep learning approach composed of five GAM-EfficientNet models, each performing a multiple classification to quantify gastroscopic manifestations, i.e. no presentation or the severity score 0-2. This approach was compared with endoscopists of varying years of experience in terms of accuracy, specificity, precision, recall, and F1 score.

RESULTS: The approach demonstrated good performance in identifying the five manifestations of the Kyoto Gastritis Score, with an average accuracy, specificity, precision, recall, and F1 score of 78.70%, 91.92%, 80.23%, 78.70%, and 0.78, respectively. The average performance of five experienced endoscopists was 72.63%, 90.00%, 77.68%, 72.63%, and 0.73, while that of five less experienced endoscopists was 66.60%, 87.44%, 70.88%, 66.60%, and 0.66, respectively. The sample t-test indicates that the approach's average accuracy, specificity, precision, recall, and F1 score for identifying the five manifestations were significantly higher than those of less experienced endoscopists, experienced endoscopists, and all endoscopists on average (p < 0.05).

CONCLUSION: Our study demonstrates the potential of deep learning approaches on gastric manifestation recognition over junior, even senior endoscopists. Thus, the deep learning approach holds potential as an auxiliary tool, although prospective validation is still needed to assess its clinical applicability.

PMID:39498518 | DOI:10.1080/07853890.2024.2418963

Front Artif Intell. 2024 Oct 21;7:1446063. doi: 10.3389/frai.2024.1446063. eCollection 2024.

ABSTRACT

INTRODUCTION: In the intricate realm of enzymology, the precise quantification of enzyme efficiency, epitomized by the turnover number (k cat), is a paramount yet elusive objective. Existing methodologies, though sophisticated, often grapple with the inherent stochasticity and multifaceted nature of enzymatic reactions. Thus, there arises a necessity to explore avant-garde computational paradigms.

METHODS: In this context, we introduce "enzyme catalytic efficiency prediction (ECEP)," leveraging advanced deep learning techniques to enhance the previous implementation, TurNuP, for predicting the enzyme catalase k cat. Our approach significantly outperforms prior methodologies, incorporating new features derived from enzyme sequences and chemical reaction dynamics. Through ECEP, we unravel the intricate enzyme-substrate interactions, capturing the nuanced interplay of molecular determinants.

RESULTS: Preliminary assessments, compared against established models like TurNuP and DLKcat, underscore the superior predictive capabilities of ECEP, marking a pivotal shift in silico enzymatic turnover number estimation. This study enriches the computational toolkit available to enzymologists and lays the groundwork for future explorations in the burgeoning field of bioinformatics. This paper suggested a multi-feature ensemble deep learning-based approach to predict enzyme kinetic parameters using an ensemble convolution neural network and XGBoost by calculating weighted-average of each feature-based model's output to outperform traditional machine learning methods. The proposed "ECEP" model significantly outperformed existing methodologies, achieving a mean squared error (MSE) reduction of 0.35 from 0.81 to 0.46 and R-squared score from 0.44 to 0.54, thereby demonstrating its superior accuracy and effectiveness in enzyme catalytic efficiency prediction.

DISCUSSION: This improvement underscores the model's potential to enhance the field of bioinformatics, setting a new benchmark for performance.

PMID:39498388 | PMC:PMC11532030 | DOI:10.3389/frai.2024.1446063

Med Image Comput Comput Assist Interv. 2023 Oct;14220:486-496. doi: 10.1007/978-3-031-43907-0_47. Epub 2023 Oct 1.

ABSTRACT

Statistical Shape Modeling (SSM) is a valuable tool for investigating and quantifying anatomical variations within populations of anatomies. However, traditional correspondence-based SSM generation methods have a prohibitive inference process and require complete geometric proxies (e.g., high-resolution binary volumes or surface meshes) as input shapes to construct the SSM. Unordered 3D point cloud representations of shapes are more easily acquired from various medical imaging practices (e.g., thresholded images and surface scanning). Point cloud deep networks have recently achieved remarkable success in learning permutation-invariant features for different point cloud tasks (e.g., completion, semantic segmentation, classification). However, their application to learning SSM from point clouds is to-date unexplored. In this work, we demonstrate that existing point cloud encoder-decoder-based completion networks can provide an untapped potential for SSM, capturing population-level statistical representations of shapes while reducing the inference burden and relaxing the input requirement. We discuss the limitations of these techniques to the SSM application and suggest future improvements. Our work paves the way for further exploration of point cloud deep learning for SSM, a promising avenue for advancing shape analysis literature and broadening SSM to diverse use cases.

PMID:39498296 | PMC:PMC11534086 | DOI:10.1007/978-3-031-43907-0_47

Comput Struct Biotechnol J. 2024 Oct 16;23:3669-3679. doi: 10.1016/j.csbj.2024.10.019. eCollection 2024 Dec.

ABSTRACT

Celiac disease poses a significant health challenge for individuals consuming gluten-containing foods. While the availability of gluten-free products has increased, there is still a need for therapeutic treatments. The advancement of computational drug design, particularly using bio-cheminformatics-oriented machine learning, offers promising avenues for developing such therapies. One promising target is Transglutaminase 2 (TG2), a protein involved in the autoimmune response triggered by gluten consumption. In this study, we utilized data from approximately 1100 TG2 inhibition assays to develop ligand-based molecular screening techniques using ensemble machine-learning models and extensive molecular feature libraries. Various classifiers, including tree-based methods, artificial neural networks, and graph neural networks, were evaluated to identify primary systems for predictive analysis and feature significance assessment. Boosting ensembles of perceptron deep learning and low-depth random forest weak learners emerged as the most effective, achieving over 90 % accuracy, significantly outperforming a baseline of 64 %. Key features, such as the presence of a terminal Michael acceptor group and a sulfonamide group, were identified as important for activity. Additionally, a regression model was created to rank active compounds. We developed a web application, Celiac Informatics (https://celiac-informatics-v1-2b0a85e75868.herokuapp.com), to facilitate the screening of potential therapeutic molecules for celiac disease. The web app also provides drug-likeness reports, supporting the development of novel drugs.

PMID:39498152 | PMC:PMC11532751 | DOI:10.1016/j.csbj.2024.10.019

Front Robot AI. 2024 Oct 21;11:1453194. doi: 10.3389/frobt.2024.1453194. eCollection 2024.

ABSTRACT

Inflammatory bowel disease (IBD) causes chronic inflammation of the colon and digestive tract, and it can be classified as Crohn's disease (CD) and Ulcerative colitis (UC). IBD is more prevalent in Europe and North America, however, since the beginning of the 21st century it has been increasing in South America, Asia, and Africa, leading to its consideration as a worldwide problem. Optical colonoscopy is one of the crucial tests in diagnosing and assessing the progression and prognosis of IBD, as it allows a real-time optical visualization of the colonic wall and ileum and allows for the collection of tissue samples. The accuracy of colonoscopy procedures depends on the expertise and ability of the endoscopists. Therefore, algorithms based on Deep Learning (DL) and Convolutional Neural Networks (CNN) for colonoscopy images and videos are growing in popularity, especially for the detection and classification of colorectal polyps. The performance of this system is dependent on the quality and quantity of the data used for training. There are several datasets publicly available for endoscopy images and videos, but most of them are solely specialized in polyps. The use of DL algorithms to detect IBD is still in its inception, most studies are based on assessing the severity of UC. As artificial intelligence (AI) grows in popularity there is a growing interest in the use of these algorithms for diagnosing and classifying the IBDs and managing their progression. To tackle this, more annotated colonoscopy images and videos will be required for the training of new and more reliable AI algorithms. This article discusses the current challenges in the early detection of IBD, focusing on the available AI algorithms, and databases, and the challenges ahead to improve the detection rate.

PMID:39498116 | PMC:PMC11532194 | DOI:10.3389/frobt.2024.1453194

Front Digit Health. 2024 Oct 21;6:1390622. doi: 10.3389/fdgth.2024.1390622. eCollection 2024.

ABSTRACT

In the past decade, the progress of traditional bioprocess optimization technique has lagged far behind the rapid development of synthetic biology, which has hindered the industrialization process of synthetic biology achievements. Recently, more and more advanced equipment and sensors have been applied for bioprocess online inspection to improve the understanding and optimization efficiency of the process. This has resulted in large amounts of process data from various sources with different communication protocols and data formats, requiring the development of techniques for integration and fusion of these heterogeneous data. Here we describe a multi-source fusion platform (Biofuser) that is designed to collect and process multi-source heterogeneous data. Biofuser integrates various data to a unique format that facilitates data visualization, further analysis, model construction, and automatic process control. Moreover, Biofuser also provides additional APIs that support machine learning or deep learning using the integrated data. We illustrate the application of Biofuser with a case study on riboflavin fermentation process development, demonstrating its ability in device faulty identification, critical process factor identification, and bioprocess prediction. Biofuser has the potential to significantly enhance the development of fermentation optimization techniques and is expected to become an important infrastructure for artificial intelligent integration into bioprocess optimization, thereby promoting the development of intelligent biomanufacturing.

PMID:39498098 | PMC:PMC11532143 | DOI:10.3389/fdgth.2024.1390622

Heliyon. 2024 Oct 19;10(20):e39613. doi: 10.1016/j.heliyon.2024.e39613. eCollection 2024 Oct 30.

ABSTRACT

In recent years, there have been unprecedented developments in artificial intelligence. Object detection, voice recognition, face recognition etc. are some of the artificial intelligence applications. In this study, an auxiliary method for the automatic detection of cracks, one of the main deterioration problems on highways, is proposed. The crack formation of hot mix asphalts is investigated with an image processing method modeled with Attention SegNet architecture. Styrene-butadiene-styrene (SBS), the most widely used additive in bitumen modification, was used at 2 %, 3 %, and 4 % ratios to modify 50/70 bitumen. Semi-circular asphalt specimens obtained with SBS modified bitumen were subjected to a semicircular bending (SCB) test and fracture performance was investigated. The effects of different temperature, notch size and additive on crack detection performance are evaluated. In the experimental study, maximum load, fracture energy, fracture toughness (KIC) values were obtained at low temperature, and resistance values against crack propagation were obtained by applying the J-integral method at intermediate temperature. The results demonstrated that with the addition of SBS, the fracture strength and maximum load values increased at each temperature value, with the 4 % SBS mixture offering the highest performance. Moreover, the image segmentation performed with SegNet provided high accuracy and precision values for cracks. It was observed that the accuracy values of the image processing methods decreased at low temperature, while at high temperature, higher accuracy values were obtained as the cracking rate.

PMID:39498054 | PMC:PMC11532877 | DOI:10.1016/j.heliyon.2024.e39613

Heliyon. 2024 Oct 12;10(20):e39178. doi: 10.1016/j.heliyon.2024.e39178. eCollection 2024 Oct 30.

ABSTRACT

BACKGROUND: The Peripherally Inserted Central Catheter (PICC) is a widely used technique for delivering intravenous fluids and medications, especially in critical care units. PICC may induce venous thrombosis (PICC-RVT), which is a frequent and serious complication. In clinical practice, Color Doppler Flow Imaging (CDFI) is regarded as the gold standard for diagnosing PICC-RVT. However, CDFI not only requires prominent time and effort from experienced healthcare professionals, but also relies on the formation and development of PICC-RVT, especially at early stages of PICC-RVT, when PICC-RVT is not apparent. A prognosis tool for PICC-RVT is crucial to bridge the gap between its diagnosis and treatment, especially in resource-limited settings, such as remote healthcare facilities.

OBJECTIVE: Evaluate over 14,885 models from various machine learning techniques to identify an effective prognostic model (referred to as PRAD - PICC-RVT Assessment via Deep-learning) for quantifying the risks associated with PICC-RVT.

METHODS: To tackle the challenges associated with PICC-RVT diagnosis, we gathered a comprehensive dataset of 5,272 patients from 27 healthcare centers across China. From a pool of 14885 models from various machine learning techniques, we systematically screened a data-driven prognostic model to quantify the risks associated with PICC-RVT. This model aims to provide objective evidence, and facilitate timely interventions.

RESULTS: The proposed model displayed exceptional predictive accuracy, achieving an accuracy of 86.4 % and an AUC of 0.837. Based on the prognosis model, we further incorporated a weight analysis to identify the major contributing factors for PICC-RVT risk during catheterization. Albumin levels, primary diagnosis, hemoglobin levels, platelet levels, and education level are emphasized as important risk factors.

CONCLUSIONS: Our method excels in predicting early PICC-RVT risks, especially in asymptomatic patients. The findings in this paper offers insights into controllable PICC risk factors that could benefit vast patients and reduce disease burden through stratification and early intervention.

PMID:39498031 | PMC:PMC11532296 | DOI:10.1016/j.heliyon.2024.e39178

Heliyon. 2024 Oct 9;10(20):e39037. doi: 10.1016/j.heliyon.2024.e39037. eCollection 2024 Oct 30.

ABSTRACT

Alzheimer's is one of the brain syndromes that steadily affects the brain memory. The early stage of Alzheimer's disease (AD) is referred to as mild cognitive impairment (MCI), and the growth of Alzheimer's is not certain in patients with MCI. The premature detection of Alzheimer's is crucial for maintaining healthy brain function and avoiding memory loss. Different multi-neural network architectures have been proposed by researchers for efficient and accurate AD detection. The absence of improved feature extraction mechanisms and unexplored efficient optimizers in complex benchmark architectures lead to an inefficient and inaccurate AD classification. Moreover, the standard convolutional neural network (CNN)-based architectures for Alzheimer's diagnosis lack interpretability in their predictions. An interpretable, simplified, yet effective deep learning model is required for the accurate classification of AD. In this study, a generalized fractional order-based CNN classifier with explainable artificial intelligence (XAI) capabilities is proposed for accurate, efficient, and interpretable classification of AD diagnosis. The proposed study (a) classifies AD accurately by incorporating unexplored pooling technique with enhanced feature extraction mechanism, (b) provides fractional order-based optimization approach for adaptive learning and fast convergence speed, and (c) suggests an interpretable method for proving the transparency of the model. The proposed model outperforms complex benchmark architectures with regard to accuracy using standard ADNI dataset. The proposed fractional order-based CNN classifier achieves an improved accuracy of 99 % as compared to the state-of-the-art models.

PMID:39498007 | PMC:PMC11532259 | DOI:10.1016/j.heliyon.2024.e39037