Independent Test Dataset Research Articles

Effective strategies for correcting spatial sampling bias in species distribution models without independent test data

AbstractAimSpatial sampling bias (SSB) is a feature of opportunistically sampled species records. Species distribution models (SDMs) built using these data (i.e. presence‐background models) can produce biased predictions of suitability across geographic space, confounding species occurrence with the distribution of sampling effort. A wide range of SSB correction methods have been developed but simulations suggest effects on predictive performance are highly variable. Here, we aim to identify the SSB correction methods that have the highest likelihood of improving true predictive performance and evaluation strategies that provide a reliable indicator of model performance when independent test data are unavailable.LocationGlobal, simulation.Time PeriodCurrent, simulation.MethodsA meta‐analysis was used to evaluate the performance of SSB correction methods in studies where there were direct comparisons between corrected and uncorrected SDMs. A simulation model was then developed to test evaluation strategies against a known truth using four common SSB correction methods.ResultsEffect sizes from published studies suggest some support for small positive effects of SSB correction on predictive performance when assessed using independent test data, but this was not evident using internal cross‐validation and no single method stood out as consistently effective. Simulations support these findings and show that evaluation using internal test data was generally a poor indicator of the true effect of SSB correction. Methods that adjust models relative to a known driver of SSB produced the largest performance gains, but were also the most inconsistent.Main ConclusionsCorrecting SSB in presence‐background SDMs without independent test data to evaluate the effect on model performance requires careful implementation. We recommend clearer documentation of SSB correction effects on SDMs, presenting results from models with and without correction, evaluating effects of different assumptions of SSB implementation on predictions, as well as greater efforts to collect independent test datasets to validate model predictions.

ISUMO-RsFPN: A predictor for identifying lysine SUMOylation sites based on multi-features and feature pyramid networks

SUMOylation is a protein post-translational modification that plays an essential role in cellular functions. For predicting SUMO sites, numerous researchers have proposed advanced methods based on ordinary machine learning algorithms. These reported methods have shown excellent predictive performance, but there is room for improvement. In this study, we constructed a novel deep neural network Residual Pyramid Network (RsFPN), and developed an ensemble deep learning predictor called iSUMO-RsFPN. Initially, three feature extraction methods were employed to extract features from samples. Following this, weak classifiers were trained based on RsFPN for each feature type. Ultimately, the weak classifiers were integrated to construct the final classifier. Moreover, the predictor underwent systematically testing on an independent test dataset, where the results demonstrated a significant improvement over the existing state-of-the-art predictors. The code of iSUMO-RsFPN is free and available at https://github.com/454170054/iSUMO-RsFPN.

SumoPred-PLM: human SUMOylation and SUMO2/3 sites Prediction using Pre-trained Protein Language Model.

SUMOylation is an essential post-translational modification system with the ability to regulate nearly all aspects of cellular physiology. Three major paralogues SUMO1, SUMO2and SUMO3 form a covalent bond between the small ubiquitin-like modifier with lysine residues at consensus sites in protein substrates. Biochemical studies continue to identify unique biological functions for protein targets conjugated to SUMO1 versus the highly homologous SUMO2 and SUMO3 paralogues. Yet, the field has failed to harness contemporary AI approaches including pre-trained protein language models to fully expand and/or recognize the SUMOylated proteome. Herein, we present a novel, deep learning-based approach called SumoPred-PLM for human SUMOylation prediction with sensitivity, specificity, Matthew's correlation coefficient, and accuracy of 74.64%, 73.36%, 0.48% and 74.00%, respectively, on the CPLM 4.0 independent test dataset. In addition, this novel platform uses contextualized embeddings obtained from a pre-trained protein language model, ProtT5-XL-UniRef50 to identify SUMO2/3-specific conjugation sites. The results demonstrate that SumoPred-PLM is a powerful and unique computational tool to predict SUMOylation sites in proteins and accelerate discovery.

STM-ac4C: a hybrid model for identification of N4-acetylcytidine (ac4C) in human mRNA based on selective kernel convolution, temporal convolutional network, and multi-head self-attention.

N4-acetylcysteine (ac4C) is a chemical modification in mRNAs that alters the structure and function of mRNA by adding an acetyl group to the N4 position of cytosine. Researchers have shown that ac4C is closely associated with the occurrence and development of various cancers. Therefore, accurate prediction of ac4C modification sites on human mRNA is crucial for revealing its role in diseases and developing new diagnostic and therapeutic strategies. However, existing deep learning models still have limitations in prediction accuracy and generalization ability, which restrict their effectiveness in handling complex biological sequence data. This paper introduces a deep learning-based model, STM-ac4C, for predicting ac4C modification sites on human mRNA. The model combines the advantages of selective kernel convolution, temporal convolutional networks, and multi-head self-attention mechanisms to effectively extract and integrate multi-level features of RNA sequences, thereby achieving high-precision prediction of ac4C sites. On the independent test dataset, STM-ac4C showed improvements of 1.81%, 3.5%, and 0.37% in accuracy, Matthews correlation coefficient, and area under the curve, respectively, compared to the existing state-of-the-art technologies. Moreover, its performance on additional balanced and imbalanced datasets also confirmed the model's robustness and generalization ability. Various experimental results indicate that STM-ac4C outperforms existing methods in predictive performance. In summary, STM-ac4C excels in predicting ac4C modification sites on human mRNA, providing a powerful new tool for a deeper understanding of the biological significance of mRNA modifications and cancer treatment. Additionally, the model reveals key sequence features that influence the prediction of ac4C sites through sequence region impact analysis, offering new perspectives for future research. The source code and experimental data are available at https://github.com/ymy12341/STM-ac4C.

An individualized stemness-related signature to predict prognosis and immunotherapy responses for gastric cancer using single-cell and bulk tissue transcriptomes.

Currently, many stemness-related signatures have been developed for gastric cancer (GC) to predict prognosis and immunotherapy outcomes. However, due to batch effects, these signatures cannot accurately analyze patients one by one, rendering them impractical in real clinical scenarios. Therefore, we aimed to develop an individualized and clinically applicable signature based on GC stemness. Malignant epithelial cells from single-cell RNA-Seq data of GC were used to identify stemness-related signature genes based on the CytoTRACE score. Using two bulk tissue datasets as training data, the enrichment scores of the signature genes were applied to classify samples into two subtypes. Then, using the identified subtypes as criteria, we developed an individualized stemness-related signature based on the within-sample relative expression orderings of genes. We identified 175 stemness-related signature genes, which exhibited significantly higher AUCell scores in poorly differentiated GCs compared to differentiated GCs. In training datasets, GC samples were classified into two subtypes with significantly different survival times and genomic characteristics. Utilizing the two subtypes, an individualized signature was constructed containing 47 gene pairs. In four independent testing datasets, GC samples classified as high risk exhibited significantly shorter survival times, higher infiltration of M2 macrophages, and lower immune responses compared to low-risk samples. Moreover, the potential therapeutic targets and corresponding drugs were identified for the high-risk group, such as CD248 targeted by ontuxizumab. We developed an individualized stemness-related signature, which can accurately predict the prognosis and efficacy of immunotherapy for each GC sample.

A Physics-informed Deep Neural Network for Harmonization of CT Images.

An adversarial generative network was trained on virtual CT images acquired under various imaging conditions using a virtual imaging platform with 40 computational patient models. These models featured anthropomorphic lungs with different levels of pulmonary diseases, including nodules and emphysema. Imaging was conducted using a validated CT simulator at two dose levels and varying reconstruction kernels. The trained model was tested on an independent virtual test dataset and two clinical datasets. On the virtual test set, the harmonizer improved the structural similarity index from 79.3 ±16.4% to 95.8 ±1.7%, normalized mean squared error from 16.7 ±9.7% to 9.2 ±1.7%, and peak signal-to-noise ratio from 27.7 ±3.7dB to 32.2 ±1.6dB. Moreover, the harmonized images yielded more precise quantification of emphysema-based imaging biomarkers for lung attenuation, LAA-950 from 5.6 ±8.7% to 0.23 ±0.16%, Perc15 from 43.4 ±45.4 HU to 20.0 ±7.5 HU, and Lung Mass from 0.3 ±0.3 g to 0.1 ±0.2 g. In clinical data, the harmonizer reduced biomarker variability by an average of 70%. For lung nodules, harmonized images improved the detectability index by 6.5-fold and DNN-based precision by 6%. The proposed harmonizer significantly enhances image quality and quantification accuracy in CT imaging. The study demonstrated the potential utility of image harmonization for consistent CT image quality and reliable quantification, which is crucial for clinical applications and patient management.

External evaluation of the Dynamic Criticality Index: A machine learning model to predict future need for ICU care in hospitalized pediatric patients.

To assess the single site performance of the Dynamic Criticality Index (CI-D) models developed from a multi-institutional database to predict future care. Secondarily, to assess future care-location predictions in a single institution when CI-D models are re-developed using single-site data with identical variables and modeling methods. Four CI-D models were assessed for predicting care locations >6-12 hours, >12-18 hours, >18-24 hours, and >24-30 hours in the future. Prognostic study comparing multi-institutional CI-D models' performance in a single-site electronic health record dataset to an institution-specific CI-D model developed using identical variables and modelling methods. The institution did not participate in the multi-institutional dataset. All pediatric inpatients admitted from January 1st 2018 -February 29th 2020 through the emergency department. The main outcome was inpatient care in routine or ICU care locations. A total of 29,037 pediatric hospital admissions were included, with 5,563 (19.2%) admitted directly to the ICU, 869 (3.0%) transferred from routine to ICU care, and 5,023 (17.3%) transferred from ICU to routine care. Patients had a median [IQR] age 68 months (15-157), 47.5% were female and 43.4% were black. The area under the receiver operating characteristic curve (AUROC) for the multi-institutional CI-D models applied to a single-site test dataset was 0.493-0.545 and area under the precision-recall curve (AUPRC) was 0.262-0.299. The single-site CI-D models applied to an independent single-site test dataset had an AUROC 0.906-0.944 and AUPRC range from 0.754-0.824. Accuracy at 0.95 sensitivity for those transferred from routine to ICU care was 72.6%-81.0%. Accuracy at 0.95 specificity was 58.2%-76.4% for patients who transferred from ICU to routine care. Models developed from multi-institutional datasets and intended for application to individual institutions should be assessed locally and may benefit from re-development with site-specific data prior to deployment.

DeepAMPNet: a novel antimicrobial peptide predictor employing AlphaFold2 predicted structures and a bi-directional long short-term memory protein language model.

Global public health is seriously threatened by the escalating issue of antimicrobial resistance (AMR). Antimicrobial peptides (AMPs), pivotal components of the innate immune system, have emerged as a potent solution to AMR due to their therapeutic potential. Employing computational methodologies for the prompt recognition of these antimicrobial peptides indeed unlocks fresh perspectives, thereby potentially revolutionizing antimicrobial drug development. In this study, we have developed a model named as deepAMPNet. This model, which leverages graph neural networks, excels at the swift identification of AMPs. It employs structures of antimicrobial peptides predicted by AlphaFold2, encodes residue-level features through a bi-directional long short-term memory (Bi-LSTM) protein language model, and constructs adjacency matrices anchored on amino acids' contact maps. In a comparative study with other state-of-the-art AMP predictors on two external independent test datasets, deepAMPNet outperformed in accuracy. Furthermore, in terms of commonly accepted evaluation matrices such as AUC, Mcc, sensitivity, and specificity, deepAMPNet achieved the highest or highly comparable performances against other predictors. deepAMPNet interweaves both structural and sequence information of AMPs, stands as a high-performance identification model that propels the evolution and design in antimicrobial peptide pharmaceuticals. The data and code utilized in this study can be accessed at https://github.com/Iseeu233/deepAMPNet.

DMAMP: A deep-learning model for detecting antimicrobial peptides and their multi-activities.

Due to the broad-spectrum and high-efficiency antibacterial activity, antimicrobial peptides (AMPs) and their functions have been studied in the field of drug discovery. Using biological experiments to detect the AMPs and corresponding activities require a high cost, whereas computational technologies do so for much less. Currently, most computational methods solve the identification of AMPs and their activities as two independent tasks, which ignore the relationship between them. Therefore, the combination and sharing of patterns for two tasks is a crucial problem that needs to be addressed. In this study, we propose a deep learning model, called DMAMP, for detecting AMPs and activities simultaneously, which is benefited from multi-task learning. The first stage is to utilize convolutional neural network models and residual blocks to extract the sharing hidden features from two related tasks. The next stage is to use two fully connected layers to learn the distinct information of two tasks. Meanwhile, the original evolutionary features from the peptide sequence are also fed to the predictor of the second task to complement the forgotten information. The experiments on the independent test dataset demonstrate that our method performs better than the single-task model with 4.28% of Matthews Correlation Coefficient (MCC) on the first task, and achieves 0.2627 of an average MCC which is higher than the single-task model and two existing methods for five activities on the second task. To understand whether features derived from the convolutional layers of models capture the differences between target classes, we visualize these high-dimensional features by projecting into 3D space. In addition, we show that our predictor has the ability to identify peptides that achieve activity against Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2). We hope that our proposed method can give new insights into the discovery of novel antiviral peptide drugs.

Strengthening deep-learning models for intracranial hemorrhage detection: strongly annotated computed tomography images and model ensembles.

Multiple attempts at intracranial hemorrhage (ICH) detection using deep-learning techniques have been plagued by clinical failures. We aimed to compare the performance of a deep-learning algorithm for ICH detection trained on strongly and weakly annotated datasets, and to assess whether a weighted ensemble model that integrates separate models trained using datasets with different ICH improves performance. We used brain CT scans from the Radiological Society of North America (27,861 CT scans, 3,528 ICHs) and AI-Hub (53,045 CT scans, 7,013 ICHs) for training. DenseNet121, InceptionResNetV2, MobileNetV2, and VGG19 were trained on strongly and weakly annotated datasets and compared using independent external test datasets. We then developed a weighted ensemble model combining separate models trained on all ICH, subdural hemorrhage (SDH), subarachnoid hemorrhage (SAH), and small-lesion ICH cases. The final weighted ensemble model was compared to four well-known deep-learning models. After external testing, six neurologists reviewed 91 ICH cases difficult for AI and humans. InceptionResNetV2, MobileNetV2, and VGG19 models outperformed when trained on strongly annotated datasets. A weighted ensemble model combining models trained on SDH, SAH, and small-lesion ICH had a higher AUC, compared with a model trained on all ICH cases only. This model outperformed four deep-learning models (AUC [95% C.I.]: Ensemble model, 0.953[0.938-0.965]; InceptionResNetV2, 0.852[0.828-0.873]; DenseNet121, 0.875[0.852-0.895]; VGG19, 0.796[0.770-0.821]; MobileNetV2, 0.650[0.620-0.680]; p < 0.0001). In addition, the case review showed that a better understanding and management of difficult cases may facilitate clinical use of ICH detection algorithms. We propose a weighted ensemble model for ICH detection, trained on large-scale, strongly annotated CT scans, as no model can capture all aspects of complex tasks.

Evaluation of two miniaturized FT‐NIR spectrometers for rapid soil property analysis

AbstractUtilizing reflectance spectroscopy to generate the necessary soil data to drive innovations in precision agriculture and soil management is an increasing focus of agronomic research. One of the key limitations for widespread practical adoption of reflectance spectroscopy is hardware cost, and lower cost hardware is actively being developed. This study evaluated two inexpensive nano Fourier‐transform near infrared spectrometers in the laboratory. One was a laboratory‐based analyzer (LabFlow) and the second was a field portable analyzer (Field Probe). Soil spectra were collected in the shortwave infrared range and processed using wavelet transforms and machine learning models. The optimal wavelet transforms and machine learning model were selected using cross validation on the training dataset, and performance of the optimal model was evaluated using an independent testing dataset. The Field Probe configuration total nitrogen model had the best performance when compared to the LabFlow laboratory analyzer with an R2 of 0.91, a concordance correlation coefficient of 0.95, and an root mean square error of 0.03. Soil inorganic carbon did not perform as well with an R2 of 0.65. However, performance was likely limited by a large number of low values and a limited range in the training dataset. Overall, these results highlight the potential for lower cost spectrometers to provide useful soil data for soil management applications.

Im5C-DSCGA: A Proposed Hybrid Framework Based on Improved DenseNet and Attention Mechanisms for Identifying 5-methylcytosine Sites in Human RNA.

5-methylcytosine (m5C) is a key post-transcriptional modification that plays a critical role in RNA metabolism. Owing to the large increase in identified m5C modification sites in organisms, their epigenetic roles are becoming increasingly unknown. Therefore, it is crucial to precisely identify m5C modification sites to gain more insight into cellular processes and other mechanisms related to biological functions. Although researchers have proposed some traditional computational methods and machine learning algorithms, some limitations still remain. In this study, we propose a more powerful and reliable deep-learning model, im5C-DSCGA, to identify novel RNA m5C modification sites in humans. Our proposed im5C-DSCGA model uses three feature encoding methods initially-one-hot, nucleotide chemical property (NCP), and nucleotide density (ND)-to extract the original features in RNA sequences and ensure splicing; next, the original features are fed into the improved densely connected convolutional network (DenseNet) and Convolutional Block Attention Module (CBAM) mechanisms to extract the advanced local features; then, the bidirectional gated recurrent unit (BGRU) method is used to capture the long-term dependencies from advanced local features and extract global features using Self-Attention; Finally, ensemble learning is used and full connectivity is used to classify and predict the m5C site. Unsurprisingly, the deep-learning-based im5C-DSCGA model performed well in terms of sensitivity (Sn), specificity (SP), accuracy (Acc), Matthew's correlation coefficient (MCC), and area under the curve (AUC), generating values of 81.0%, 90.8%, 85.9%, 72.1%, and 92.6%, respectively, in the independent test dataset following the use of three feature encoding methods. We critically evaluated the performance of im5C-DSCGA using five-fold cross-validation and independent testing and compared it to existing methods. The MCC metric reached 72.1% when using the independent test, which is 3.0% higher than the current state-of-the-art prediction method Deepm5C model. The results show that the im5C-DSCGA model achieves more accurate and stable performances and is an effective tool for predicting m5C modification sites. To the authors' knowledge, this is the first time that the improved DenseNet, BGRU, CBAM Attention mechanism, and Self-Attention mechanism have been combined to predict novel m5C sites in human RNA.

Machine learning-driven identification of the gene-expression signature associated with a persistent multiple organ dysfunction trajectory in critical illness

Multiple organ dysfunction syndrome (MODS) disproportionately drives morbidity and mortality among critically ill patients. However, we lack a comprehensive understanding of its pathobiology. Identification of genes associated with a persistent MODS trajectory may shed light on underlying biology and allow for accurate prediction of those at-risk. Secondary analyses of publicly available gene-expression datasets. Supervised machine learning (ML) was used to identify a parsimonious set of genes associated with a persistent MODS trajectory in a training set of pediatric septic shock. We optimized model parameters and tested risk-prediction capabilities in independent validation and test datasets, respectively. We compared model performance relative to an established gene-set predictive of sepsis mortality. Patients with a persistent MODS trajectory had 568 differentially expressed genes and characterized by a dysregulated innate immune response. Supervised ML identified 111 genes associated with the outcome of interest on repeated cross-validation, with an AUROC of 0.87 (95% CI: 0.85-0.88) in the training set. The optimized model, limited to 20 genes, achieved AUROCs ranging from 0.74 to 0.79 in the validation and test sets to predict those with persistent MODS, regardless of host age and cause of organ dysfunction. Our classifier demonstrated reproducibility in identifying those with persistent MODS in comparison with a published gene-set predictive of sepsis mortality. We demonstrate the utility of supervised ML driven identification of the genes associated with persistent MODS. Pending validation in enriched cohorts with a high burden of organ dysfunction, such an approach may inform targeted delivery of interventions among at-risk patients. H.R.W.'s NIHR35GM126943 award supported the work detailed in this manuscript. Upon his death, the award was transferred to M.N.A. M.R.A., N.S.P, and R.K were supported by NIHR21GM151703. R.K. was supported by R01GM139967.

E2EATP: Fast and High-Accuracy Protein-ATP Binding Residue Prediction via Protein Language Model Embedding.

Identifying the ATP-binding sites of proteins is fundamentally important to uncover the mechanisms of protein functions and explore drug discovery. Many computational methods are proposed to predict ATP-binding sites. However, due to the limitation of the quality of feature representation, the prediction performance still has a big room for improvement. In this study, we propose an end-to-end deep learning model, E2EATP, to dig out more discriminative information from a protein sequence for improving the ATP-binding site prediction performance. Concretely, we employ a pretrained deep learning-based protein language model (ESM2) to automatically extract high-latent discriminative representations of protein sequences relevant for protein functions. Based on ESM2, we design a residual convolutional neural network to train a protein-ATP binding site prediction model. Furthermore, a weighted focal loss function is used to reduce the negative impact of imbalanced data on the model training stage. Experimental results on the two independent testing data sets demonstrate that E2EATP could achieve higher Matthew's correlation coefficient and AUC values than most existing state-of-the-art prediction methods. The speed (about 0.05 s per protein) of E2EATP is much faster than the other existing prediction methods. Detailed data analyses show that the major advantage of E2EATP lies at the utilization of the pretrained protein language model that extracts more discriminative information from the protein sequence only. The standalone package of E2EATP is freely available for academic at https://github.com/jun-csbio/e2eatp/.

Predicting tumor deposits in rectal cancer: a combined deep learning model using T2-MR imaging and clinical features

BackgroundTumor deposits (TDs) are associated with poor prognosis in rectal cancer (RC). This study aims to develop and validate a deep learning (DL) model incorporating T2-MR image and clinical factors for the preoperative prediction of TDs in RC patients.Methods and methodsA total of 327 RC patients with pathologically confirmed TDs status from January 2016 to December 2019 were retrospectively recruited, and the T2-MR images and clinical variables were collected. Patients were randomly split into a development dataset (n = 246) and an independent testing dataset (n = 81). A single-channel DL model, a multi-channel DL model, a hybrid DL model, and a clinical model were constructed. The performance of these predictive models was assessed by using receiver operating characteristics (ROC) analysis and decision curve analysis (DCA).ResultsThe areas under the curves (AUCs) of the clinical, single-DL, multi-DL, and hybrid-DL models were 0.734 (95% CI, 0.674–0.788), 0.710 (95% CI, 0.649–0.766), 0.767 (95% CI, 0.710–0.819), and 0.857 (95% CI, 0.807–0.898) in the development dataset. The AUC of the hybrid-DL model was significantly higher than the single-DL and multi-DL models (both p < 0.001) in the development dataset, and the single-DL model (p = 0.028) in the testing dataset. Decision curve analysis demonstrated the hybrid-DL model had higher net benefit than other models across the majority range of threshold probabilities.ConclusionsThe proposed hybrid-DL model achieved good predictive efficacy and could be used to predict tumor deposits in rectal cancer.Critical relevance statementThe proposed hybrid-DL model achieved good predictive efficacy and could be used to predict tumor deposits in rectal cancer.Key points• Preoperative non-invasive identification of TDs is of great clinical significance.• The combined hybrid-DL model achieved good predictive efficacy and could be used to predict tumor deposits in rectal cancer.• A preoperative nomogram provides gastroenterologist with an accurate and effective tool.Graphical

Prediction of post-traumatic stress disorder in family members of ICU patients: a machine learning approach.

Post-traumatic stress disorder (PTSD) can affect family members of patients admitted to the intensive care unit (ICU). Easily accessible patient's and relative's information may help develop accurate risk stratification tools to direct relatives at higher risk of PTSD toward appropriate management. PTSD was measured 90days after ICU discharge using validated instruments (Impact of Event Scale and Impact of Event Scale-Revised) in 2374 family members. Various supervised machine learning approaches were used to predict PTSD in family members and evaluated on an independent held-out test dataset. To better understand variables' contributions to PTSD predicted probability, we used machine learning interpretability methods on the best predictive algorithm. Non-linear ensemble learning tree-based methods showed better predictive performances (Random Forest-area under curve, AUC = 0.73 [0.68-0.77] and XGBoost-AUC = 0.73 [0.69-0.78]) than regularized linear models, kernel-based models, or deep learning models. In the best performing algorithm, most important features that positively contributed to PTSD's predicted probability were all non-modifiable factors, namely, lower patient's age, longer duration of ICU stay, relative's female sex, lower relative's age, relative being a spouse/child, and patient's death in ICU. A sensitivity analysis in bereaved relatives did not alter the algorithm's predictive performance. We propose a machine learning-based approach to predict PTSD in relatives of ICU patients at an individual level. In this model, PTSD is mostly influenced by non-modifiable factors.

Predicting the need for a replan in oropharyngeal cancer: A radiomic, clinical, and dosimetric model.

Patients with oropharyngeal cancer (OPC) treated with chemoradiation can experience weight loss and tumor shrinkage, altering the prescribed treatment. Treatment replanning ensures patients do not receive excessive doses to normal tissue. However, it is a time- and resource-intensive process, as it takes 1 to 2 weeks to acquire a new treatment plan, and during this time, overtreatment of normal tissues could lead to increased toxicities. Currently, there are limited prognostic factors to determine which patients will require a replan. There remains an unmet need for predictive models to assist in identifying patients who could benefit from the knowledge of a replan prior to treatment. We aimed to develop and evaluate a CT-based radiomic model, integrating clinical and dosimetric information, to predict the need for a replan prior to treatment. A dataset of patients (n=315) with OPC treated with chemoradiation was used for this study. The dataset was split into independent training (n=220) and testing (n=95) datasets. Tumor volumes and organs at risk (OARs) were contoured on planning CT images. PyRadiomics was used to compute radiomic image features (n=1218) on the original and filtered images from each of the primary tumor, nodal volumes, and ipsilateral and contralateral parotid glands. Nine clinical features and nine dose features extracted from the OARs were collected and those significantly (p<0.05) associated with the need for a replan in the training dataset were used in a baseline model. Random forest feature selection was applied to select the optimal radiomic features to predict replanning. Logistic regression, Naïve Bayes, support vector machine, and random forest classifiers were built using the non-correlated selected radiomic, clinical, and dose features on the training dataset and performance was assessed in the testing dataset. The area under the curve (AUC) was used to assess the prognostic value. A total of 78 patients (25%) required a replan. Smoking status, nodal stage, base of tongue subsite, and larynx mean dose were found to be significantly associated with the need for a replan in the training dataset and incorporated into the baseline model, as well as into the combined models. Five predictive radiomic features were selected (one nodal volume, one primary tumor, two ipsilateral and one contralateral parotid gland). The baseline model comprised of clinical and dose features alone achieved an AUC of 0.66 [95% CI: 0.51-0.79] in the testing dataset. The random forest classifier was the top-performing radiomics model and achieved an AUC of 0.82 [0.75-0.89] in the training dataset and an AUC of 0.78 [0.68-0.87] in the testing dataset, which significantly outperformed the baseline model (p=0.023, testing dataset). This is the first study to use radiomics from the primary tumor, nodal volumes, and parotid glands for the prediction of replanning for patients with OPC. Radiomic features augmented clinical and dose features for predicting the need for a replan in our testing dataset. Once validated, this model has the potential to assist physicians in identifying patients that may benefit from a replan, allowing for better resource allocation and reduced toxicities.

A Machine Learning Algorithm Predicting Acute Kidney Injury in Intensive Care Unit Patients (NAVOY Acute Kidney Injury): Proof-of-Concept Study.

Acute kidney injury (AKI) represents a significant global health challenge, leading to increased patient distress and financial health care burdens. The development of AKI in intensive care unit (ICU) settings is linked to prolonged ICU stays, a heightened risk of long-term renal dysfunction, and elevated short- and long-term mortality rates. The current diagnostic approach for AKI is based on late indicators, such as elevated serum creatinine and decreased urine output, which can only detect AKI after renal injury has transpired. There are no treatments to reverse or restore renal function once AKI has developed, other than supportive care. Early prediction of AKI enables proactive management and may improve patient outcomes. The primary aim was to develop a machine learning algorithm, NAVOY Acute Kidney Injury, capable of predicting the onset of AKI in ICU patients using data routinely collected in ICU electronic health records. The ultimate goal was to create a clinical decision support tool that empowers ICU clinicians to proactively manage AKI and, consequently, enhance patient outcomes. We developed the NAVOY Acute Kidney Injury algorithm using a hybrid ensemble model, which combines the strengths of both a Random Forest (Leo Breiman and Adele Cutler) and an XGBoost model (Tianqi Chen). To ensure the accuracy of predictions, the algorithm used 22 clinical variables for hourly predictions of AKI as defined by the Kidney Disease: Improving Global Outcomes guidelines. Data for algorithm development were sourced from the Massachusetts Institute of Technology Lab for Computational Physiology Medical Information Mart for Intensive Care IV clinical database, focusing on ICU patients aged 18 years or older. The developed algorithm, NAVOY Acute Kidney Injury, uses 4 hours of input and can, with high accuracy, predict patients with a high risk of developing AKI 12 hours before onset. The prediction performance compares well with previously published prediction algorithms designed to predict AKI onset in accordance with Kidney Disease: Improving Global Outcomes diagnosis criteria, with an impressive area under the receiver operating characteristics curve (AUROC) of 0.91 and an area under the precision-recall curve (AUPRC) of 0.75. The algorithm's predictive performance was externally validated on an independent hold-out test data set, confirming its ability to predict AKI with exceptional accuracy. NAVOY Acute Kidney Injury is an important development in the field of critical care medicine. It offers the ability to predict the onset of AKI with high accuracy using only 4 hours of data routinely collected in ICU electronic health records. This early detection capability has the potential to strengthen patient monitoring and management, ultimately leading to improved patient outcomes. Furthermore, NAVOY Acute Kidney Injury has been granted Conformite Europeenne (CE)-marking, marking a significant milestone as the first CE-marked AKI prediction algorithm for commercial use in European ICUs.

Vision Transformers for Breast Cancer Human Epidermal Growth Factor Receptor 2 Expression Staging without Immunohistochemical Staining

Accurate staging of human epidermal growth factor receptor 2 (HER2) expression is vital for evaluating breast cancer treatment efficacy. However, it typically involves costly and complex immunohistochemical staining, along with hematoxylin and eosin staining. This work presents customized vision transformers for staging HER2 expression in breast cancer using only hematoxylin and eosin-stained images. The proposed algorithm comprised three modules: a localization module for weakly localizing critical image features using spatial transformers, an attention module for global learning via vision transformers, and a loss module to determine proximity to a HER2 expression level based on input images by calculating ordinal loss. Results, reported with 95% CIs, reveal the proposed approach's success in HER2 expression staging: area under the receiver operating characteristic curve, 0.9202±0.01; precision, 0.922±0.01; sensitivity, 0.876±0.01; and specificity, 0.959±0.02 over fivefold cross-validation. Comparatively, this approach significantly outperformed conventional vision transformer models and state-of-the-art convolutional neural network models (P<0.001). Furthermore, it surpassed existing methods when evaluated on an independent test data set. This work holds great importance, aiding HER2 expression staging in breast cancer treatment while circumventing the costly and time-consuming immunohistochemical staining procedure, thereby addressing diagnostic disparities in low-resource settings and low-income countries.

GBDT_KgluSite: An improved computational prediction model for lysine glutarylation sites based on feature fusion and GBDT classifier

BackgroundLysine glutarylation (Kglu) is one of the most important Post-translational modifications (PTMs), which plays significant roles in various cellular functions, including metabolism, mitochondrial processes, and translation. Therefore, accurate identification of the Kglu site is important for elucidating protein molecular function. Due to the time-consuming and expensive limitations of traditional biological experiments, computational-based Kglu site prediction research is gaining more and more attention.ResultsIn this paper, we proposed GBDT_KgluSite, a novel Kglu site prediction model based on GBDT and appropriate feature combinations, which achieved satisfactory performance. Specifically, seven features including sequence-based features, physicochemical property-based features, structural-based features, and evolutionary-derived features were used to characterize proteins. NearMiss-3 and Elastic Net were applied to address data imbalance and feature redundancy issues, respectively. The experimental results show that GBDT_KgluSite has good robustness and generalization ability, with accuracy and AUC values of 93.73%, and 98.14% on five-fold cross-validation as well as 90.11%, and 96.75% on the independent test dataset, respectively.ConclusionGBDT_KgluSite is an effective computational method for identifying Kglu sites in protein sequences. It has good stability and generalization ability and could be useful for the identification of new Kglu sites in the future. The relevant code and dataset are available at https://github.com/flyinsky6/GBDT_KgluSite.