Independent Test Data Research Articles

Diagnosis of hypertrophic cardiomyopathy by artificial intelligence using standard transthoracic echocardiography

Abstract Introduction Misdiagnosis of hypertrophic cardiomyopathy (HCM) is not uncommon among patients with left ventricular hypertrophy (LVH). Purpose We hypothesized that a convolutional neural network (CNN) could be trained to identify HCM patients among individuals with LVH using standard transthoracic echocardiography (TTE). Methods Echocardiographic reports of 121,767 unique patients linked to clinical data from the largest tertiary medical centre in the country (2007-2022) were reviewed. Patients with no septal hypertrophy were excluded. All HCM cases were retrieved from electronic medical records and were adjudicated by the authors. Data was then divided into 3 mutually exclusive cohorts: training (N=7,368), testing (N=2,456) and validation (2,456) cohorts. Deep learning models were used in order to train a model that identifies HCM patients. The model was based solely on parasternal long axis and apical four chamber views. Results Final study population included 12,281 patients who underwent a total of 27,242 echocardiography studies. There were 1535 (12%) patients with HCM. Mean age of study population was 72±14 and 7,943 (65%) were men. Overall, the model obtained 98.1% classification accuracy with an area under the curve of 0.851 in the independent test data (FIGURE) which could translate to sensitivity and specificity of 68% and 99%, respectively with positive and negative predictive values of 50% and 99%, respectively. Conclusions Applying artificial intelligence to the standard TTE can identify HCM patients with a reasonable accuracy. With further evaluation, this tool can be used to assist in HCM diagnosis.

Comprehensive Assessment of BERT-Based Methods for Predicting Antimicrobial Peptides.

In recent years, the prediction of antimicrobial peptides (AMPs) has gained prominence due to their high antibacterial activity and reduced susceptibility to drug resistance, making them potential antibiotic substitutes. To advance the field of AMP recognition, an increasing number of natural language processing methods are being applied. These methods exhibit diversity in terms of pretraining models, pretraining data sets, word vector embeddings, feature encoding methods, and downstream classification models. Here, we provide a comprehensive survey of current BERT-based methods for AMP prediction. An independent benchmark test data set is constructed to evaluate the predictive capabilities of the surveyed tools. Furthermore, we compared the predictive performance of these computational methods based on six different AMP public databases. LM_pred (BFD) outperformed all other surveyed tools due to abundant pretraining data set and the unique vector embedding approach. To avoid the impact of varying training data sets used by different methods on prediction performance, we performed the 5-fold cross-validation experiments using the same data set, involving retraining. Additionally, to explore the applicability and generalization ability of the models, we constructed a short peptide data set and an external data set to test the retrained models. Although these prediction methods based on BERT can achieve good prediction performance, there is still room for improvement in recognition accuracy. With the continuous enhancement of protein language model, we proposed an AMP prediction method based on the ESM-2 pretrained model called iAMP-bert. Experimental results demonstrate that iAMP-bert outperforms other approaches. iAMP-bert is freely accessible to the public at http://iamp.aielab.cc/.

Herbage biomass predictions from UAV data using a derived digital terrain model and machine learning

AbstractMore than 70% of Switzerland's agricultural area is covered by grasslands that often exhibit highly diverse species compositions and heterogeneous growth patterns. An essential requirement for efficient and effective pasture management is the regular estimation of herbage biomass. While various methods exist for estimating herbage biomass, they are often time‐consuming and may not accurately capture the variability within pastures. This highlights the need for more efficient, accurate estimation techniques. To help improve herbage biomass estimation, we present estiGrass3D+, a Random Forest model. This model predicts pasture biomass using a digital terrain model (DTM) derived from a digital surface model (DSM) for sward height modelling, along with vegetation indices and agronomic variables from UAV images only. The model was successfully evaluated with independent test data from different sites on the Swiss central plateau, including both grazed and mown areas. Model performance on an independent validation dataset achieved a NRMSE of 20.3%, while the training dataset had an NRMSE of 21.5%. These consistent results confirm that estiGrass3D+ is both transferable and applicable to unseen data while maintaining accuracy and reliability across different datasets. The wide applicability of our method demonstrates its practicality for predicting herbage biomass under different pasture management scenarios. Additionally, our method of deriving a DTM directly from a DSM simplifies the measurement of grass sward height by UAVs, eliminating the need for prior ground control point (GCP) marking and subsequent aligning, enhancing the efficiency of herbage biomass estimation.

Constitutive Model for Thermal-Oxygen-Aged EPDM Rubber Based on the Arrhenius Law.

Ethylene-propylene-diene monomer (EPDM) is a key engineering material; its mechanical characterization is important for the safe use of the material. In this paper, the coupled effects of thermal degradation temperature and time on the tensile mechanical behavior of EPDM rubber were investigated. The tensile stress-strain curves of the aged and unaged EPDM rubber show strong nonlinearity, demonstrating especially rapid stiffening as the strain increases under small deformation. The popular Mooney-Rivlin and Ogden (N = 3) models were chosen to fit the test data, and the results indicate that neither of the classical models can accurately describe the tensile mechanical behavior of this rubber. Six hyperelastic constitutive models, which are excellent for rubber with highly nonlinearity, were employed, and their abilities to reproduce the stress-strain curve of the unaged EPDM were assessed. Finally, the Davis-De-Thomas model was found to be an appropriate hyperelastic model for EPDM rubber. A Dakin-type kinetic relationship was employed to describe the relationships between the model parameters and aging temperature and time, and, combined with the Arrhenius law, a thermal aging constitutive model for EPDM rubber was established. The ability of the proposed model was checked by independent testing data. In the moderate strain range of 200%, the errors remained below 10%. The maximum errors of the prediction results at 85 °C for 4 days and 100 °C for 2 and 4 days were computed to be 17.06%, 17.51% and 19.77%, respectively. This work develops a theoretical approach to predicting the mechanical behavior of rubber material that has suffered thermal aging; this approach is helpful in determining the safe long-term use of the material.

Axial compression behaviour of circular concrete-filled stainless-clad bimetallic steel tubular stub columns

The axial compression behaviour of circular concrete-filled stainless-clad bimetallic steel tubular (CFSCBST) stub columns is addressed in this paper by experimental and numerical investigations. A total of five specimens were fabricated and subjected to axial compression loading. The varying parameters in the experimental study included the clad ratio of steel tube, the diameter-to-thickness ratio and the strength of the concrete. A three-dimensional finite element (FE) model was developed and validated against both dependent and independent test data to further study the axial compressive behaviour of circular CFSCBST stub columns in this paper. The parametric studies considering five major parameters, including the strength of the concrete, the substrate steel grade, the clad ratio, the diameter-to-thickness ratio and different bonding conditions of the stainless-clad (SC) bimetallic steel, were carried out by using the verified FE model. The applicability of existing design codes to the circular CFSCBST stub columns was further analysed through comparisons with the numerical results. New design methods based on unified and superposition theory have been proposed herein, which have improved accuracy for predicting the ultimate compression capacity of such circular CFSCBST stub columns.

Multimodal fusion learning for long QT syndrome pathogenic genotypes in a racially diverse population

Congenital long QT syndrome (LQTS) diagnosis is complicated by limited genetic testing at scale, low prevalence, and normal QT corrected interval in patients with high-risk genotypes. We developed a deep learning approach combining electrocardiogram (ECG) waveform and electronic health record data to assess whether patients had pathogenic variants causing LQTS. We defined patients with high-risk genotypes as having ≥1 pathogenic variant in one of the LQTS-susceptibility genes. We trained the model using data from United Kingdom Biobank (UKBB) and then fine-tuned in a racially/ethnically diverse cohort using Mount Sinai BioMe Biobank. Following group-stratified 5-fold splitting, the fine-tuned model achieved area under the precision-recall curve of 0.29 (95% confidence interval [CI] 0.28–0.29) and area under the receiver operating curve of 0.83 (0.82–0.83) on independent testing data from BioMe. Multimodal fusion learning has promise to identify individuals with pathogenic genetic mutations to enable patient prioritization for further work up.

Protein-peptide binding residue prediction based on protein language models and cross-attention mechanism

Accurate identifications of protein-peptide binding residues are essential for protein-peptide interactions and advancing drug discovery. To address this problem, extensive research efforts have been made to design more discriminative feature representations. However, extracting these explicit features usually depend on third-party tools, resulting in low computational efficacy and suffering from low predictive performance. In this study, we design an end-to-end deep learning-based method, E2EPep, for protein-peptide binding residue prediction using protein sequence only. E2EPep first employs and fine-tunes two state-of-the-art pre-trained protein language models that can extract two different high-latent feature representations from protein sequences relevant for protein structures and functions. A novel feature fusion module is then designed in E2EPep to fuse and optimize the above two feature representations of binding residues. In addition, we have also design E2EPep+, which integrates E2EPep and PepBCL models, to improve the prediction performance. Experimental results on two independent testing data sets demonstrate that E2EPep and E2EPep + could achieve the average AUC values of 0.846 and 0.842 while achieving an average Matthew's correlation coefficient value that is significantly higher than that of existing most of sequence-based methods and comparable to that of the state-of-the-art structure-based predictors. Detailed data analysis shows that the primary strength of E2EPep lies in the effectiveness of feature representation using cross-attention mechanism to fuse the embeddings generated by two fine-tuned protein language models. The standalone package of E2EPep and E2EPep + can be obtained at https://github.com/ckx259/E2EPep.git for academic use only.

Uplifting the complexity of analysis for probabilistic security of electricity supply assessments using artificial neural networks

The energy sector faces rapid decarbonisation and decision-makers demand reliable assessments of the security of electricity supply. For this, detailed simulation models with a high temporal and technological resolution are required. When confronted with increasing weather-dependent renewable energy generation, probabilistic simulation models have proven. The significant computational costs of calculating a scenario, however, limit the complexity of further analysis. Advances in code optimization as well as the use of computing clusters still lead to runtimes of up to eight hours per scenario. However ongoing research highlights that tailor-made approximations are potentially the key factor in further reducing computing time. Consequently, current research aims to provide a method for the rapid prediction of widely varying scenarios. In this work artificial neural networks (ANN) are trained and compared to approximate the system behavior of the probabilistic simulation model. To do so, information needs to be sampled from the probabilistic simulation in an efficient way. Because only a limited space in the whole design space of the 16 independent variables is of interest, a classification is developed. Finally it required only around 35 min to create the regression models, including sampling the design space, simulating the training data and training the ANNs. The resulting ANNs are able to predict all scenarios within the validity range of the regression model with a coefficient of determination of over 0.9998 for independent test data (1.051.200 data points). They need only a few milliseconds to predict one scenario, enabling in-depth analysis in a brief period of time.

ToxTeller: Predicting Peptide Toxicity Using Four Different Machine Learning Approaches.

Examining the toxicity of peptides is essential for therapeutic peptide-based drug design. Machine learning approaches are frequently used to develop highly accurate predictors for peptide toxicity prediction. In this paper, we present ToxTeller, which provides four predictors using logistic regression, support vector machines, random forests, and XGBoost, respectively. For prediction model development, we construct a data set of toxic and nontoxic peptides from SwissProt and ConoServer databases with existence evidence levels checked. We also fully utilize the protein annotation in SwissProt to collect more toxic peptides than using keyword search alone. From this data set, we construct an independent test data set that shares at most 40% sequence similarity within itself and with the training data set. From a quite comprehensive list of 28 feature combinations, we conduct 10-fold cross-validation on the training data set to determine the optimized feature combination for model development. ToxTeller's performance is evaluated and compared with existing predictors on the independent test data set. Since toxic peptides must be avoided for drug design, we analyze strategies for reducing false-negative predictions of toxic peptides and suggest selecting models by top sensitivity instead of the widely used Matthews correlation coefficient, and also suggest using a meta-predictor approach with multiple predictors.

Optimizing neurointerventional procedures: an algorithm for embolization coil detection and automated collimation to enable dose reduction.

Monitoring radiation dose and time parameters during radiological interventions is crucial, especially in neurointerventional procedures, such as aneurysm treatment with embolization coils. The algorithm presented detects the presence of these embolization coils in medical images. It establishes a bounding box as a reference for automated collimation, with the primary objective being to enhance the efficiency and safety of neurointerventional procedures by actively optimizing image quality while minimizing patient dose. Two distinct methodologies are evaluated in our study. The first involves deep learning, employing the Faster R-CNN model with a ResNet-50 FPN as a backbone and a RetinaNet model. The second method utilizes a classical blob detection approach, serving as a benchmark for comparison. We performed a fivefold cross-validation, and our top-performing model achieved mean mAP@75 of 0.84 across all folds on validation data and mean mAP@75 of 0.94 on independent test data. Since we use an upscaled bounding box, achieving 100% overlap between ground truth and prediction is not necessary. To highlight the real-world applications of our algorithm, we conducted a simulation featuring a coil constructed from an alloy wire, effectively showcasing the implementation of automatic collimation. This resulted in a notable reduction in the dose area product, signifying the reduction of stochastic risks for both patients and medical staff by minimizing scatter radiation. Additionally, our algorithm assists in avoiding extreme brightness or darkness in X-ray angiography images during narrow collimation, ultimately streamlining the collimation process for physicians. To our knowledge, this marks the initial attempt at an approach successfully detecting embolization coils, showcasing the extended applications of integrating detection results into the X-ray angiography system. The method we present has the potential for broader application, allowing its extension to detect other medical objects utilized in interventional procedures.

Anatomically constrained tractography of the fetal brain

Diffusion-weighted Magnetic Resonance Imaging (dMRI) is increasingly used to study the fetal brain in utero. An important computation enabled by dMRI is streamline tractography, which has unique applications such as tract-specific analysis of the brain white matter and structural connectivity assessment. However, due to the low fetal dMRI data quality and the challenging nature of tractography, existing methods tend to produce highly inaccurate results. They generate many false streamlines while failing to reconstruct the streamlines that constitute the major white matter tracts. In this paper, we advocate for anatomically constrained tractography based on an accurate segmentation of the fetal brain tissue directly in the dMRI space. We develop a deep learning method to compute the segmentation automatically. Experiments on independent test data show that this method can accurately segment the fetal brain tissue and drastically improve the tractography results. It enables the reconstruction of highly curved tracts such as optic radiations. Importantly, our method infers the tissue segmentation and streamline propagation direction from a diffusion tensor fit to the dMRI data, making it applicable to routine fetal dMRI scans. The proposed method can facilitate the study of fetal brain white matter tracts with dMRI.

Detecting key genes relative expression orderings as biomarkers for machine learning-based intelligent screening and analysis of type 2 diabetes mellitus

Type 2 diabetes (T2D), a prevalent chronic metabolic disease of public health concern, is growing rapidly worldwide. In order to characterize robust transcriptomic differences between T2D and the healthy pancreatic islets, we proposed a novel data analysis approach based on the within-sample relative expression orderings of genes (REOs) and machine learning, which can efficiently integrate data from diverse gene expression datasets and help discover some potential signatures. We first identified the overlapped disease-specific reverse REOs from three bulk islets expression profiles that are substantially distinct. Subsequently, the minimum-Redundancy-Maximum-Relevance (mRMR) combined with incremental feature selection (IFS) strategy was applied to select the optimal reverse REOs by using the support vector machine (SVM). As a result, 7 optimal reverse REOs encompassing 12 genes were found, which could produce encouraging predictive performance on training data, independent testing, and external islets data, showcasing robust prediction capability and superior generalization despite the heterogeneity of data. Furthermore, the analysis of differential expression gene (DEG) in bulk islets data and pseudobulk method in single-cell RNA sequencing (scRNA-seq) islets data reaffirmed the crucial roles of these 7 REOs in islets function and disease progression. In conclusion, these REOs are robust biomarkers in T2D and may also be potential therapeutic targets for T2D. We hope these findings can help elucidate the underlying pathogenic mechanisms of T2D and contribute to the treatment of diabetes. The source code is available at https://github.com/xiexq007/T2D-REO.

Sex estimation from mandibular morphometry using discriminant analysis–CT scan based retrospective study

It is well known that skeletal characteristics vary among different populations. Sex dimorphic characteristics of the mandible have been reported from studies using either mandible bone or computer tomography (CT) scan images of the mandible to test its efficacy in estimating sex. Mandibular studies for estimating sex in any particular population group may not hold well for different populations owing to inherent geographical variations. With this background, we assessed the validity of mandible measurements from CT scan images to determine sex in the South Indian population. As a part of our study, 11 metric parameters and 1 angular parameter were measured and analyzed. The mean values of all the parameters were significantly higher for males as compared to females. Bigonial breadth indicated the best discriminatory ability of the study. Mandibular angle had the least predictive accuracy among all the discriminant functions studied. We further observed that a combination of parameters gave the best overall classification rate (92.3 %). When the same functions were tested on an independent testing data set, a combination of parameters and bigonial breadth gave the best classification rate (82.1 %) which was consistent. We concluded that the mandible has a high accuracy for sex estimation. All the parameters studied demonstrated statistically significant differences between the two sexes except the mandibular angle.

P-700 Modelling individual follicle growth rates during ovarian stimulation in medically assisted reproduction cycles to enable prediction of final follicle profiles

Abstract Study question Can the growth of individual follicles during ovarian stimulation in medically assisted reproduction (MAR) cycles be modelled to enable prediction of final follicle profiles? Summary answer Mean follicle growth rate is 1.35 mm per day. Our model reliably forecasts follicle size profiles on the final scan within ±2mm with 75.1% accuracy. What is known already Follicle growth rates during ovarian stimulation are believed to be linear with various mean growth rates reported between 1 to 4 mm per day. Follicles are believed to grow faster during ovarian stimulation than in the natural menstrual cycle. The change in mean follicle size was 1.69 mm per day with ovarian stimulation in 131 MAR cycles, and 1.4 mm per day in 50 natural cycles. However, there are only very limited data using individual follicle sizes to model follicle growth to enable prediction of future follicle size profiles. Study design, size, duration We conducted a retrospective cohort study of 12,950 patients from 11 European clinics (2005-2023). First IVF/ICSI cycles with at least three follicles and two scans were analysed. Using 8,564 cycles with scans one or two days apart, 98,029 follicles were modelled to estimate follicle growth rates per day. Stratification by age, weight, total antral follicle count (AFC), initial FSH dose, and suppressant protocol was performed. Predictive modelling was conducted using 39,698 scans including 434,082 follicles. Participants/materials, setting, methods Assessment of Follicle Growth: Follicles were ranked and the difference in corresponding follicle sizes over consecutive scans estimated, and the impact of baseline characteristics evaluated. Prediction of follicle size profile on final scan: A kernel density estimator and random forest model were developed using the same training data. Both approaches estimated future follicle growth from the initial scan. The two predictions were combined using maximum-likelihood adjustments. Generalisation error was estimated using independent test data. Main results and the role of chance The mean growth rate of individual follicles was 1.350 mm per day (95% CI 1.346 – 1.353 mm per day), which was lower than the previously reported mean follicle growth rate during ovarian stimulation (1.7 mm per day). The large number of patient-cycles and follicles assessed enabled a precise estimate of follicle growth per day during ovarian stimulation. Age, total AFC, initial FSH dose, bodyweight, and suppressant protocol had no statistically significant effect on the estimated mean growth rate. Using only the follicle sizes from the initial scan during ovarian stimulation, our model had 75.1% accuracy for predicting follicle sizes on the final scan within ±2mm. Including follicle size data from the first two scans improved the accuracy of the model to predict the follicle sizes on the final scan to 80.4%. In a confirmatory analysis, we cross-validated our findings across each of 11 individual clinics, and similar estimates for the generalisation error as for the standard test/train split were maintained, suggesting suitable generalisability of these findings. Limitations, reasons for caution A key simplifying assumption in this study is that follicles demonstrate monotonic growth patterns. Specifically, the relative ordering of follicle sizes is preserved over the entire cycle. This assumption enables straightforward extraction of growth statistics from the observed data but assumes that follicles do not regress in size. Wider implications of the findings We have used a large high-quality dataset, allied to advanced modern machine learning techniques, to precisely estimate follicle growth rates during ovarian stimulation, and use this to reliably predict future follicle size profiles during ovarian stimulation. This supports the design, personalisation, streamlining and success of future assisted conception cycles. Trial registration number None

XRAInet: AI-based decision support for pneumothorax and pleural effusion management.

This study aimed to develop and assess the performance of an artificial intelligence(AI)-driven decision support system, XRAInet, in accurately identifying pediatric patients with pleural effusion or pneumothorax and determining whether tube thoracostomy intervention is warranted. In this diagnostic accuracy study, we retrospectively analyzed a data set containing 510 X-ray images from 170 pediatric patients admitted between 2005 and 2022. Patients were categorized into two groups: Tube (requiring tube thoracostomy) and Conservative (managed conservatively). XRAInet, a deep learning-based algorithm, was trained using this data set. We evaluated its performance using various metrics, including mean Average Precision (mAP), recall, precision, and F1 score. XRAInet, achieved a mAP score of 0.918. This result underscores its ability to accurately identify and localize regions necessitating tube thoracostomy for pediatric patients with pneumothorax and pleural effusion. In an independent testing data set, the model exhibited a sensitivity of 64.00% and specificity of 96.15%. In conclusion, XRAInet presents a promising solution for improving the detection and decision-making process for cases of pneumothorax and pleural effusion in pediatric patients using X-ray images. These findings contribute to the expanding field of AI-driven medical imaging, with potential applications for enhancing patient outcomes. Future research endeavors should explore hybrid models, enhance interpretability, address data quality issues, and align with regulatory requirements to ensure the safe and effective deployment of XRAInet in healthcare settings.

Prediction of Plant Ubiquitylation Proteins and Sites by Fusing Multiple Features

Introduction: Protein ubiquitylation is an important post-translational modification (PTM), which is considered to be one of the most important processes regulating cell function and various diseases. Therefore, accurate prediction of ubiquitylation proteins and their PTM sites is of great significance for the study of basic biological processes and the development of related drugs. Researchers have developed some large-scale computational methods to predict ubiquitylation sites, but there is still much room for improvement. Much of the research related to ubiquitylation is cross-species while the life pattern is diversified, and the prediction method always shows its specificity in practical application. This study just aims at the issue of plants and has constructed computational methods for identifying ubiquitylation protein and ubiquitylation sites. Method: In this work, we constructed two predictive models to identify plant ubiquitylation proteins and sites. First, in the ubiquitylation proteins prediction model, in order to better reflect protein sequence information and obtain better prediction results, the KNN scoring matrix model based on functional domain Gene Ontology (GO) annotation and word embedding model, i.e. Skip-Gram and Continuous Bag of Words (CBOW), are used to extract the features, and the light gradient boosting machine (LGBM) is selected as the ubiquitylation proteins prediction engine. Results: As a result, accuracy (ACC), Precision, recall rate (Recall), F1_score and AUC are respectively 85.12%, 80.96%, 72.80%, 76.37% and 0.9193 in the 10-fold cross-validations on independent dataset. In the ubiquitylation sites prediction model, Skip-Gram, CBOW and enhanced amino acid composition (EAAC) feature extraction codes were used to extract protein sequence fragment features, and the predicted results on training and independent test data have also achieved good performance. Conclusion: In a word, the comparison results demonstrate that our models have a decided advantage in predicting ubiquitylation proteins and sites, and it may provide useful insights for studying the mechanisms and modulation of ubiquitination pathways

Prediction of Seropositivity in Suspected Autoimmune Encephalitis by Use of Radiomics: A Radiological Proof-of-Concept Study.

In this study, we sought to evaluate the capabilities of radiomics and machine learning in predicting seropositivity in patients with suspected autoimmune encephalitis (AE) from MR images obtained at symptom onset. In 83 patients diagnosed with AE between 2011 and 2022, manual bilateral segmentation of the amygdala was performed on pre-contrast T2 images using 3D Slicer open-source software. Our sample of 83 patients contained 43 seropositive and 40 seronegative AE cases. Images were obtained at our tertiary care center and at various secondary care centers in North Rhine-Westphalia, Germany. The sample was randomly split into training data and independent test data. A total of 107 radiomic features were extracted from bilateral regions of interest (ROIs). Automated machine learning (AutoML) was used to identify the most promising machine learning algorithms. Feature selection was performed using recursive feature elimination (RFE) and based on the determination of the most important features. Selected features were used to train various machine learning algorithms on 100 different data partitions. Performance was subsequently evaluated on independent test data. Our radiomics approach was able to predict the presence of autoantibodies in the independent test samples with a mean AUC of 0.90, a mean accuracy of 0.83, a mean sensitivity of 0.84 and a mean specificity of 0.82, with Lasso regression models yielding the most promising results. These results indicate that radiomics-based machine learning could be a promising tool in predicting the presence of autoantibodies in suspected AE patients. Given the implications of seropositivity for definitive diagnosis of suspected AE cases, this may expedite diagnostic workup even before results from specialized laboratory testing can be obtained. Furthermore, in conjunction with recent publications, our results indicate that characterization of AE subtypes by use of radiomics may become possible in the future, potentially allowing physicians to tailor treatment in the spirit of personalized medicine even before laboratory workup is completed.

Artificial Intelligence-Assisted Prescription Determination for Orthokeratology Lens Fitting: From Algorithm to Clinical Practice.

To explore the potential of artificial intelligence (AI) to assist prescription determination for orthokeratology (OK) lenses. Artificial intelligence algorithm development followed by a real-world trial. A total of 11,502 OK lenses fitting records collected from seven clinical environments covering major brands. Records were randomly divided in a three-way data split. Cross-validation was used to identify the most accurate algorithm, followed by an evaluation using an independent test data set. An online AI-assisted system was implemented and assessed in a real-world trial involving four junior and three senior clinicians. The primary outcome measure was the algorithm's accuracy (ACC). The ACC of the best performance of algorithms to predict the targeted reduction amplitude, lens diameter, and alignment curve of the prescription was 0.80, 0.82, and 0.83, respectively. With the assistance of the AI system, the number of trials required to determine the final prescription significantly decreased for six of the seven participating clinicians (all P <0.01). This reduction was more significant among junior clinicians compared with consultants (0.76±0.60 vs. 0.32±0.60, P <0.001). Junior clinicians achieved clinical outcomes comparable to their seniors, as 93.96% (140/149) and 94.44% (119/126), respectively, of the eyes fitted achieved unaided visual acuity no worse than 0.8 ( P =0.864). AI can improve prescription efficiency and reduce discrepancies in clinical outcomes among clinicians with differing levels of experience. Embedment of AI in practice should ultimately help lessen the medical burden and improve service quality for myopia boom emerging worldwide.

A SIMPLE APPROACH FOR PREDICTING CURVATURE IN CONCRETE MEMBERS REINFORCED WITH STEEL FIBERS AND BARS

The paper proposes a simple deflection model for concrete bending members reinforced with steel fibers and bars (further denoted as R/SFRC members). Most of the current design approaches for such elements require the knowledge of the residual strength of steel fiber reinforced concrete (SFRC) in tension with the latter characteristic being obtained from standard bending tests. The involvement of extra tests hampers a wider application of R/SFRC structures in practice. The proposed model does not require the characteristic of the residual strength. It was derived using an inverse approach earlier proposed by the authors. The resultant tensile force of SFRC acting in the tension zone of a R/SFRC beam was derived from the experimental moment-curvature diagram. A load level was identified at which the resultant tensile force reached zero, implying that the section stiffness equals to the stiffness of the fully cracked RC section. The proposed model in a simple way expresses curvature via the curvatures at a cracking load and the load corresponding to the stiffness of the fully cracked RC section. The predictions by the proposed model were checked against independent test data.

IPSI(2L)-EDL: a Two-layer Predictor for Identifying Promoters and their Types based on Ensemble Deep Learning

Abstract: Promoters are DNA fragments located near the transcription initiation site, they can be divided into strong promoter type and weak promoter type according to transcriptional activation and expression level. Identifying promoters and their strengths in DNA sequences is essential for understanding gene expression regulation. Therefore, it is crucial to further improve predictive quality of predictors for real-world application requirements. Here, we constructed the latest training dataset based on the RegalonDB website, where all the promoters in this dataset have been experimentally validated, and their sequence similarity is less than 85%. We used one-hot and nucleotide chemical property and density (NCPD) to represent DNA sequence samples. Additionally, we proposed an ensemble deep learning framework containing a multi-head attention module, long short-term memory present, and a convolutional neural network module. : The results showed that iPSI(2L)-EDL outperformed other existing methods for both promoter prediction and identification of strong promoter type and weak promoter type, the AUC and MCC for the iPSI(2L)-EDL in identifying promoter were improved by 2.23% and 2.96% compared to that of PseDNC-DL on independent testing data, respectively, while the AUC and MCC for the iPSI(2L)- EDL were increased by 3.74% and 5.86% in predicting promoter strength type, respectively. The results of ablation experiments indicate that CNN plays a crucial role in recognizing promoters, the importance of different input positions and long-range dependency relationships among features are helpful for recognizing promoters. : Furthermore, to make it easier for most experimental scientists to get the results they need, a userfriendly web server has been established and can be accessed at http://47.94.248.117/IPSW(2L)-EDL.