Independent Validation Set Research Articles

Prognosis prediction and risk stratification of breast cancer patients based on a mitochondria-related gene signature

As the malignancy with the highest global incidence, breast cancer represents a significant threat to women’s health. Recent advances have shed light on the importance of mitochondrial function in cancer, particularly in metabolic reprogramming within tumors. Recognizing this, we developed a novel risk signature based on mitochondrial-related genes to improve prognosis prediction and risk stratification in breast cancer patients. In this study, transcriptome data and clinical features of breast cancer samples were extracted from two sources: the TCGA, serving as the training set, and the METABRIC, used as the independent validation set. We developed the signature using LASSO-Cox regression and assessed its prognostic efficacy via ROC curves. Furthermore, the signature was integrated with clinical features to create a Nomogram model, whose accuracy was validated through clinical calibration curves and decision curve analysis. To further elucidate prognostic variations between high and low-risk groups, we conducted functional enrichment and immune infiltration analyses. Additionally, the study encompassed a comparison of mutation landscapes and drug sensitivity, providing a comprehensive understanding of the differing characteristics in these groups. Conclusively, we established a risk signature comprising 8 mitochondrial-related genes—ACSL1, ALDH2, MTHFD2, MRPL13, TP53AIP1, SLC1A1, ME3, and BCL2A1. This signature was identified as an independent risk predictor for breast cancer patient survival, exhibiting a significant high hazard ratio (HR = 3.028, 95%CI 2.038–4.499, P < 0.001). Patients in the low-risk group showed a more favorable prognosis, with enhanced immune infiltration, distinct mutation landscapes, and greater sensitivity to anti-tumor drugs. In contrast, the high-risk group exhibited an adverse trend in these aspects. This risk signature represents a novel and effective prognostic indicator, suggesting valuable insights for patient stratification in breast cancer.

The Value of Topological Radiomics Analysis in Predicting Malignant Risk of Pulmonary Ground-Glass Nodules: A Multi-Center Study.

Early detection and accurate differentiation of malignant ground-glass nodules (GGNs) in lung CT scans are crucial for the effective treatment of lung adenocarcinoma. However, existing imaging diagnostic methods often struggle to distinguish between benign and malignant GGNs in the early stages. This study aims to predict the malignancy risk of GGNs observed in lung CT scans by applying two radiomics methods: topological data analysis and texture analysis. A retrospective analysis was conducted on 3223 patients from two centers between January 2018 and June2023. The dataset was divided into training, testing, and validation sets to ensure robust model development and validation. We developed topological features applied to GGNs using radiomics analysis based on homology. This innovative approach emphasizes the integration of topological information, capturing complex geometric and spatial relationships within GGNs. By combining machine learning and deep learning algorithms, we established a predictive model that integrates clinical parameters, previous radiomics features, and topological radiomics features. Incorporating topological radiomics into our model significantly enhanced the ability to distinguish between benign and malignant GGNs. The topological radiomics model achieved areas under the curve (AUC) of 0.85 and 0.862 in two independent validation sets, outperforming previous radiomics models. Furthermore, this model demonstrated higher sensitivity compared to models based solely on clinical parameters, with sensitivities of 80.7% in validation set 1 and 82.3% in validation set 2. The most comprehensive model, which combined clinical parameters, previous radiomics features, and topological radiomics features, achieved the highest AUC value of 0.879 across all datasets. This study validates the potential of topological radiomics in improving the predictive performance for distinguishing between benign and malignant GGNs. By integrating topological features with previous radiomics and clinical parameters, our comprehensive model provides a more accurate and reliable basis for developing treatment strategies for patients with GGNs.

Development of a machine learning-based radiomics signature for estimating breast cancer TME phenotypes and predicting anti-PD-1/PD-L1 immunotherapy response

BackgroundsSince breast cancer patients respond diversely to immunotherapy, there is an urgent need to explore novel biomarkers to precisely predict clinical responses and enhance therapeutic efficacy. The purpose of our present research was to construct and independently validate a biomarker of tumor microenvironment (TME) phenotypes via a machine learning-based radiomics way. The interrelationship between the biomarker, TME phenotypes and recipients’ clinical response was also revealed.MethodsIn this retrospective multi-cohort investigation, five separate cohorts of breast cancer patients were recruited to measure breast cancer TME phenotypes via a radiomics signature, which was constructed and validated by integrating RNA-seq data with DCE-MRI images for predicting immunotherapy response. Initially, we constructed TME phenotypes using RNA-seq of 1089 breast cancer patients in the TCGA database. Then, parallel DCE-MRI images and RNA-seq of 94 breast cancer patients obtained from TCIA were applied to develop a radiomics-based TME phenotypes signature using random forest in machine learning. The repeatability of the radiomics signature was then validated in an internal validation set. Two additional independent external validation sets were analyzed to reassess this signature. The Immune phenotype cohort (n = 158) was divided based on CD8 cell infiltration into immune-inflamed and immune-desert phenotypes; these data were utilized to examine the relationship between the immune phenotypes and this signature. Finally, we utilized an Immunotherapy-treated cohort with 77 cases who received anti-PD-1/PD-L1 treatment to evaluate the predictive efficiency of this signature in terms of clinical outcomes.ResultsThe TME phenotypes of breast cancer were separated into two heterogeneous clusters: Cluster A, an "immune-inflamed" cluster, containing substantial innate and adaptive immune cell infiltration, and Cluster B, an "immune-desert" cluster, with modest TME cell infiltration. We constructed a radiomics signature for the TME phenotypes ([AUC] = 0.855; 95% CI 0.777–0.932; p < 0.05) and verified it in an internal validation set (0.844; 0.606–1; p < 0.05). In the known immune phenotypes cohort, the signature can identify either immune-inflamed or immune-desert tumor (0.814; 0.717–0.911; p < 0.05). In the Immunotherapy-treated cohort, patients with objective response had higher baseline radiomics scores than those with stable or progressing disease (p < 0.05); moreover, the radiomics signature achieved an AUC of 0.784 (0.643–0.926; p < 0.05) for predicting immunotherapy response.ConclusionsOur imaging biomarker, a practicable radiomics signature, is beneficial for predicting the TME phenotypes and clinical response in anti-PD-1/PD-L1-treated breast cancer patients. It is particularly effective in identifying the "immune-desert" phenotype and may aid in its transformation into an "immune-inflamed" phenotype.

Next generation phenotyping for diagnosis and phenotype–genotype correlations in Kabuki syndrome

The field of dysmorphology has been changed by the use Artificial Intelligence (AI) and the development of Next Generation Phenotyping (NGP). The aim of this study was to propose a new NGP model for predicting KS (Kabuki Syndrome) on 2D facial photographs and distinguish KS1 (KS type 1, KMT2D-related) from KS2 (KS type 2, KDM6A-related). We included retrospectively and prospectively, from 1998 to 2023, all frontal and lateral pictures of patients with a molecular confirmation of KS. After automatic preprocessing, we extracted geometric and textural features. After incorporation of age, gender, and ethnicity, we used XGboost (eXtreme Gradient Boosting), a supervised machine learning classifier. The model was tested on an independent validation set. Finally, we compared the performances of our model with DeepGestalt (Face2Gene). The study included 1448 frontal and lateral facial photographs from 6 centers, corresponding to 634 patients (527 controls, 107 KS); 82 (78%) of KS patients had a variation in the KMT2D gene (KS1) and 23 (22%) in the KDM6A gene (KS2). We were able to distinguish KS from controls in the independent validation group with an accuracy of 95.8% (78.9–99.9%, p < 0.001) and distinguish KS1 from KS2 with an empirical Area Under the Curve (AUC) of 0.805 (0.729–0.880, p < 0.001). We report an automatic detection model for KS with high performances (AUC 0.993 and accuracy 95.8%). We were able to distinguish patients with KS1 from KS2, with an AUC of 0.805. These results outperform the current commercial AI-based solutions and expert clinicians.

Mononuclear phagocyte system-related multi-omics features yield head and neck squamous cell carcinoma subtypes with distinct overall survival, drug, and immunotherapy responses

BackgroundRecent research reported that mononuclear phagocyte system (MPS) can contribute to immune defense but the classification of head and neck squamous cell carcinoma (HNSCC) patients based on MPS-related multi-omics features using machine learning lacked.MethodsIn this study, we obtain marker genes for MPS through differential analysis at the single-cell level and utilize “similarity network fusion” and “MoCluster” algorithms to cluster patients’ multi-omics features. Subsequently, based on the corresponding clinical information, we investigate the prognosis, drugs, immunotherapy, and biological differences between the subtypes. A total of 848 patients have been included in this study, and the results obtained from the training set can be verified by two independent validation sets using “the nearest template prediction”.ResultsWe identified two subtypes of HNSCC based on MPS-related multi-omics features, with CS2 exhibiting better predictive prognosis and drug response. CS2 represented better xenobiotic metabolism and higher levels of T and B cell infiltration, while the biological functions of CS1 were mainly enriched in coagulation function, extracellular matrix, and the JAK-STAT signaling pathway. Furthermore, we established a novel and stable classifier called “getMPsub” to classify HNSCC patients, demonstrating good consistency in the same training set. External validation sets classified by “getMPsub” also illustrated similar differences between the two subtypes.ConclusionsOur study identified two HNSCC subtypes by machine learning and explored their biological difference. Notably, we constructed a robust classifier that presented an excellent classifying prediction, providing new insight into the precision medicine of HNSCC.

Advanced chemometric methods for simultaneous quantitation of caffeine, codeine, paracetamol, and p-aminophenol in their quaternary mixture

Two different multivariate techniques have been applied for the quantitative analysis of caffeine, codeine, paracetamol and p-aminophenol (PAP) in quaternary mixture, namely, Partial Least Squares (PLS-1) and Artificial Neural Networks (ANN). For suitable analysis, a calibration set of 25 mixtures with various ratios of the drugs and PAP impurity were established using a 4-factor 5-level experimental design. The most meaningful wavelengths for the chemometric models were chosen using Genetic Algorithm (GA) as a variable selection technique. By using an independent validation set, the validity of the proposed methods was evaluated. A comparative study was established between the three multivariate models (PLS-1, GA–PLS and GA–ANN). The comparison between the various models revealed that the GA–ANN model was superior at resolving the highly overlapped spectra of this quaternary combination. The drugs were successfully quantified in their pharmaceutical dosage form utilizing the GA–ANN models.

Integrating Machine Learning and Mendelian Randomization Determined a Functional Neurotrophin-Related Gene Signature in Patients with Lower-Grade Glioma.

Recent researches reported that neurotrophins can promote glioma growth/invasion but the relevant model for predicting patients' survival in Lower-Grade Gliomas (LGGs) lacked. In this study, we adopted univariate Cox analysis, LASSO regression, and multivariate Cox analysis to determine a signature including five neurotrophin-related genes (NTGs), CLIC1, SULF2, TGIF1, TTF2, and WEE1. Two-sample Mendelian Randomization (MR) further explored whether these prognostic-related genes were genetic variants that increase the risk of glioma. A total of 1306 patients have been included in this study, and the results obtained from the training set can be verified by four independent validation sets. The low-risk subgroup had longer overall survival in five datasets, and its AUC values all reached above 0.7. The risk groups divided by the NTGs signature exhibited a distinct difference in targeted therapies from the copy-number variation, somatic mutation, LGG's surrounding microenvironment, and drug response. MR corroborated that TGIF1 was a potential causal target for increasing the risk of glioma. Our study identified a five-NTGs signature that presented an excellent survival prediction and potential biological function, providing new insight for the selection of LGGs therapy.

Multisite external validation of blood test for colorectal neoplasia screening in a majority average-risk screening cohort of 449 subjects.

66 Background: The FirstSight CRC screening blood test was previously shown to have sensitivities of 92.1% and 54.5% for CRC and AA at a specificity of 90.6% for 1,038 subjects from 18 clinical sites. In this report, we describe the independent external validation of the predefined FirstSight CRC screening blood test with new subjects from 16 sites dispersed across the US, 4 of which are new and did not participate in the previous study. Methods: The validation study included subjects from two sources: Average-risk, asymptomatic screening subjects from screening clinics supplemented with diseased-only subjects from surgical oncology centers. Blood was drawn before bowel prep for colonoscopy or treatment. External validation as well as Monte Carlo cross-validation (MCCV) methods were used to evaluate the performance of the pre-defined FirstSight assay, algorithm, and clinical thresholds in this independent external validation set. Results include sensitivity and specificity to detect CRC and AA and 95% confidence intervals. Results: The study cohort (55.2% female; mean age 56.9 yrs.) consisted of 449 subjects (White 61.7%; Black 14.5%; Hispanic 18%; AAPI and Middle Easterners 5.8%). The majority of them, 376 (84%), were asymptomatic, average-risk screening subjects (including 1 CRC, 53 AA, and all 322 negative subjects). An additional 73 (16%) diseased subjects (39 CRC and 34 AA) were enriched due to low disease prevalence. The FirstSight algorithm derives a test score from 0 to 100 as a quantitative measure of AA and CRC risk with a cutpoint to assign a binary low- or high-risk designation. The previously described cutpoint of 47.2 yielded a test specificity of 90.0%, and 90.0% and 52.9% sensitivity for the detection of CRC and AA, respectively. Here we report a higher cutpoint 50 with identical sensitivities but improved specificity to 90.7%. Point estimates of sensitivity and specificity, including CRC staging, and Clopper-Pearson exact 95% confidence intervals based on the external validation results are presented below. Conclusions: An external validation included 449 subjects from a multi-site, majority average-risk CRC screening study successfully validated the FirstSight Blood Test’s high performance as previously established with 1,038 subjects. The results bring forth confidence in the Test’s reproducibility in a large-scale clinical trial. Clinical trial information: NCT05127096 . [Table: see text]

Analysis of landslide susceptibility prediction accuracy with an event-based inventory: The 6 February 2023 Turkiye earthquakes

Landslide susceptibility assessment is a complex challenge explored by various scientists, but not fully resolved. In this study, we produced the landslide susceptibility map of a large region covering 38,500 km2 area in South-East Turkiye severely affected by the 6 February 2023 Kahramanmaras Earthquakes (Mw 7.7 and Mw 7.6) using an inventory produced in previous years. We employed random forest regression with a total of nine geomorphological and environmental features and evaluated the results using the co-seismic inventory with 2611 landslides compiled here. Although high accuracy was obtained from pixel-based assessments of test data split from the learning set, the independent validation set of co-seismic landslides showed that attention needs to be paid unseen features such as rare lithological units. Given the significant damage caused by latent hazards with the Kahramanmaras earthquakes, producing reliable inventories and precise landslide susceptibility maps is crucial for risk reduction and minimizing damages.

Biometric systems for identification and verification scenarios using spatial footsteps components

AbstractHumans are distinguished by their walking patterns; many approaches, including using various types of sensors, have been used to establish walking patterns as biometrics. By studying the distinguishing features of a person's footsteps, footstep recognition may be utilized in numerous security applications, such as managing access in protected locations or giving an additional layer of biometric verification for secure admittance into restricted regions. We proposed biometric systems for verifying and identifying a person by acquiring spatial foot pressure images from the values obtained from the piezoelectric sensors using the Swansea Foot Biometric Database, which contains 19,980 footstep signals from 127 users and is the most prominent open-source gait database available for footstep recognition. The images acquired are fed into the ConvNeXt model, which was trained using the transfer learning technique, using 16 stride footstep signals in each batch with an Adam optimizer and a learning rate of 0.0001, and using sparse categorical cross-entropy as the loss function. The proposed ConvNeXt model has been adjusted to acquire 512 feature vectors per image, and these feature vectors are used to train the logistic regression models. We propose two biometric systems. The first biometric system is based on training one logistic regression model as a classifier to identify 40 different users using 1600 signals for training, 6697 signals for validation, and 200 signals for evaluation. The second biometric system is based on training 40 logistic regression models, one for each user, to validate the user's authenticity, with a total number of 2363 training signals, 7077 validation signals, and 500 evaluation signals. Each of the 40 models has a 40-training signal per client and a different number of signals per imposter, a different number of signals for the validation that ranges between 8 and 650 signals, a 5-signal for an authenticated client, and a different number of signals per imposter for evaluation. Independent validation and evaluation sets are used to evaluate our systems. In the biometric identification system, we obtained an equal error rate of 15.30% and 21.72% for the validation and evaluation sets, while in the biometric verification system, we obtained an equal error rate of 6.97% and 10.25% for the validation and evaluation sets.

Automated MRI liver segmentation for anatomical segmentation, liver volumetry, and the extraction of radiomics.

To develop and evaluate a deep convolutional neural network (DCNN) for automated liver segmentation, volumetry, and radiomic feature extraction on contrast-enhanced portal venous phase magnetic resonance imaging (MRI). This retrospective study included hepatocellular carcinoma patients from an institutional database with portal venous MRI. After manual segmentation, the data was randomly split into independent training, validation, and internal testing sets. From a collaborating institution, de-identified scans were used for external testing. The public LiverHccSeg dataset was used for further external validation. A 3D DCNN was trained to automatically segment the liver. Segmentation accuracy was quantified by theDice similarity coefficient (DSC) with respect to manual segmentation. A Mann-Whitney U test was used to compare the internal and external test sets. Agreement of volumetry and radiomic features was assessed using the intraclass correlation coefficient (ICC). In total, 470 patients met the inclusion criteria (63.9±8.2 years; 376 males) and 20 patients were used for external validation (41±12 years; 13 males). DSC segmentation accuracy of the DCNN was similarly high between the internal (0.97±0.01) and external (0.96±0.03) test sets (p=0.28) and demonstrated robust segmentation performance on public testing (0.93±0.03). Agreement of liver volumetry was satisfactory in the internal (ICC, 0.99), external (ICC, 0.97), and public (ICC, 0.85) test sets. Radiomic features demonstrated excellent agreement in the internal (mean ICC, 0.98±0.04), external (mean ICC, 0.94±0.10), and public (mean ICC, 0.91±0.09) datasets. Automated liver segmentation yields robust and generalizable segmentation performance on MRI data and can be used for volumetry and radiomic feature extraction. Liver volumetry, anatomic localization, and extraction of quantitative imaging biomarkers require accurate segmentation, but manual segmentation is time-consuming. A deep convolutional neural network demonstrates fast and accurate segmentation performance on T1-weighted portal venous MRI. • This deep convolutional neural network yields robust and generalizable liver segmentation performance on internal, external, and public testing data. • Automated liver volumetry demonstrated excellent agreement with manual volumetry. • Automated liver segmentations can be used for robust and reproducible radiomic feature extraction.

Establishment and validation of a multivariate predictive model for the efficacy of oral rehydration salts in children with postural tachycardia syndrome

The therapeutic effectiveness of the empirical and unselected use of oral rehydration salts (ORS) on postural tachycardia syndrome (POTS) is not satisfactory in children. Therefore, looking for suitable predictors of the therapeutic effects of ORS before treatment is extremely necessary to implement individualised treatment for paediatric patients with POTS. A retrospective case-control analysis of 130 patients (aged 5-18 years) who suffered from POTS with a 3-month treatment of ORS was conducted. A nomogram model was developed in the training set (n=87) to predict the therapeutic response to ORS. Univariate analysis and logistic regression were applied to select the most useful predictors. ROC curves were applied to evaluate the discriminative performance of the nomogram model. The nomogram was then evaluated by calibration curves and the Hosmer-Lemeshow (H-L) test. The results were further validated using 1000 bootstrap resamples. External validation was performed in an independent validation set (n=43). Among the ten variables with significant differences between the responders and non-responders in univariate analysis, five variables were found to be independently associated factors for ORS therapeutic efficacy among POTS children in the further logistic regression, including mean corpuscular haemoglobin concentration (MCHC), mean corpuscular volume (MCV), mean arterial pressure (MAP) at the first minute of the upright position, urine specific gravity (SG), and P-wave voltage peaking ratio (PWP). The nomogram model was established in the training set (AUC 0.926 [95% CI: 0.865-0.988], yielding a sensitivity of 87.8% and a specificity of 86.8%). The calibration curves showed good agreement between the prediction of the nomogram and actual observation in both the training and validation sets. The nomogram also effectively predicted the external validation set (sensitivity 82.1%, specificity 73.3%, and accuracy 79.1%). We established a feasible and high-precision nomogram model to predict the efficacy of ORS, which would help implement individualised treatment for children with POTS. This study was supported by National High-Level Hospital Clinical Research Funding (Multi-centre Clinical Research Project of Peking University First Hospital) (2022CR59).

Artificial neural network-based model for sleep quality prediction for frontline medical staff during major medical assistance.

Background: The sleep quality of medical staff was severely affected during COVID-19, but the factors influencing the sleep quality of frontline staff involved in medical assistance remained unclear, and screening tools for their sleep quality were lacking. Methods: From June 25 to July 14, 2022, we conducted an Internet-based cross-sectional survey. The Pittsburgh Sleep Quality Index (PSQI), a self-designed general information questionnaire, and a questionnaire regarding the factors influencing sleep quality were combined to understand the sleep quality of frontline medical staff in Fujian Province supporting Shanghai in the past month. A chi-square test was used to compare participant characteristics, and multivariate unconditional logistic regression analysis was used to determine the predictors of sleep quality. Stratified sampling was used to divide the data into a training test set (n = 1061, 80%) and an independent validation set (n = 265, 20%). Six models were developed and validated using logistic regression, artificial neural network, gradient augmented tree, random forest, naive Bayes, and model decision tree. Results: A total of 1326 frontline medical staff were included in this survey, with a mean PSQI score of 11.354 ± 4.051. The prevalence of poor sleep quality was 80.8% (n = 1072, PSQI >7). Six variables related to sleep quality were used as parameters in the prediction model, including type of work, professional job title, work shift, weight change, tea consumption during assistance, and basic diseases. The artificial neural network (ANN) model produced the best overall performance with area under the curve, accuracy, sensitivity, specificity, precision, F1 score, and kappa of 71.6%, 68.7%, 66.7%, 69.2%, 34.0%, 45.0%, and 26.2% respectively. Conclusions: In this study, the ANN model, which demonstrated excellent predictive efficiency, showed potential for application in monitoring the sleep quality of medical staff and provide some scientific guidance suggestions for early intervention.

ProteoMutaMetrics: machine learning approaches for solute carrier family 6 mutation pathogenicity prediction.

The solute carrier transporter family 6 (SLC6) is of key interest for their critical role in the transport of small amino acids or amino acid-like molecules. Their dysfunction is strongly associated with human diseases such as including schizophrenia, depression, and Parkinson's disease. Linking single point mutations to disease may support insights into the structure-function relationship of these transporters. This work aimed to develop a computational model for predicting the potential pathogenic effect of single point mutations in the SLC6 family. Missense mutation data was retrieved from UniProt, LitVar, and ClinVar, covering multiple protein-coding transcripts. As encoding approach, amino acid descriptors were used to calculate the average sequence properties for both original and mutated sequences. In addition to the full-sequence calculation, the sequences were cut into twelve domains. The domains are defined according to the transmembrane domains of the SLC6 transporters to analyse the regions' contributions to the pathogenicity prediction. Subsequently, several classification models, namely Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) with the hyperparameters optimized through grid search were built. For estimation of model performance, repeated stratified k-fold cross-validation was used. The accuracy values of the generated models are in the range of 0.72 to 0.80. Analysis of feature importance indicates that mutations in distinct regions of SLC6 transporters are associated with an increased risk for pathogenicity. When applying the model on an independent validation set, the performance in accuracy dropped to averagely 0.6 with high precision but low sensitivity scores.

Use of Machine Learning to Predict Onset of NAFLD in an All-Comers Cohort—Development and Validation in 2 Large Asian Cohorts

Background and AimsNon-alcoholic fatty liver disease (NAFLD) is one of the most common liver diseases. There are no universally accepted models that accurately predict time to onset of NAFLD. Machine learning (ML) models may allow prediction of such time-to-event (i.e. survival) outcomes. This study aims to develop and independently validate ML derived models to allow personalised prediction of time to onset of NAFLD in individuals who have no NAFLD at baseline. MethodsThe development dataset comprised 25599 individuals from a South Korean NAFLD registry. A random 70:30 split divided it into training and internal validation sets. ML survival models (Random Survival Forest (RSF), Extra Survival Trees (XST)) were fitted, with time to NAFLD diagnosis in months as the target variable and routine anthropometric and laboratory parameters as predictors. The independent validation dataset comprised 16173 individuals from a Chinese open dataset. Models were evaluated using the concordance index (c-index) and Brier score on both the internal and independent validation sets. ResultsThe datasets (development vs independent validation) had 1331107 vs 543874 person months of follow up, NAFLD incidence of 25.7% (6584 individuals) vs 14.4% (2322 individuals), and median time to NAFLD onset of 60 (IQR 38-75) vs 24 (IQR 13-37) months, respectively. The ML models achieved a good c-index of >0.7 in the validation cohort - RSF 0.751 (95% CI 0.742-0.759), XST 0.752 (95% CI 0.744-0.762). ConclusionML models can predict time-to-onset of NAFLD based on routine patient data. They can be used by clinicians to deliver personalised predictions to patients, which may facilitate patient counselling and clinical decision making on interval imaging timing.

An Innovative Deep Learning Approach to Spinal Fracture Detection in CT Images.

Spinal fractures, particularly vertebral compression fractures, pose a significant challenge in medical imaging due to their small-scale nature and blurred boundaries in Computed Tomography (CT) scans. However, advanced deep learning models, such as the integration of the You Only Look Once (YOLO) V7 model with Efficient Layer Aggregation Networks (ELAN) and Max-Pooling Convolution (MPConv) architectures, can substantially reduce the loss of small-scale information during computational processing, thus improving detection accuracy. The purpose of this study is to develop an innovative deep learning approach for detecting spinal fractures, particularly vertebral compression fractures, in CT images. We proposed a novel method to precisely identify spinal injury using the YOLO V7 model as a classifier. This model was enhanced by integrating ELAN and MPConv architectures, which were influenced by the Receptive Field Learning and Aggregation (RFLA) small object recognition framework. Standard normalization techniques were utilized to preprocess the CT images. The YOLO V7 model, integrated with ELAN and MPConv architectures, was trained using a dataset containing annotated spinal fractures. Additionally, to mitigate boundary ambiguities in compressive fractures, a Theoretical Receptive Field (TRF) based on Gaussian distribution and an Effective Receptive Field (ERF) were used to capture multi-scale features better. Furthermore, the Wasserstein distance was employed to optimize the model's learning process. A total of 240 CT images from patients diagnosed with spinal fractures were included in this study, sourced from Ningbo No.2 Hospital, ensuring a robust dataset for training the deep learning model. Our method demonstrated superior performance over conventional object detection networks like YOLO V7 and YOLO V3. Specifically, with a dataset of 200 pathological images and 40 normal spinal images, our method achieved a 3% increase in accuracy compared to YOLO V7. The proposed method offers an innovative and more effective approach for identifying vertebral compression fractures in CT scans. These promising findings suggest the method's potential for practical clinical applications, highlighting the significance of deep learning in enhancing patient care and treatment in medical imaging. Future research should incorporate cross-validation and independent validation and test sets to assess the model's robustness and generalizability. Additionally, exploring other deep learning models and methods could further enhance detection accuracy and reliability, contributing to the development of more effective diagnostic tools in medical imaging.

A novel immune cell signature for predicting glioblastoma after radiotherapy prognosis and guiding therapy.

Background: Glioblastoma, a highly aggressive brain tumor, poses a significant clinical challenge, particularly in the context of radiotherapy. In this study, we aimed to explore infiltrating immune cells and identify immune-related genes associated with glioblastoma radiotherapy prognosis. Subsequently, we constructed a signature based on these genes to discern differences in molecular and tumor microenvironment immune characteristics, ultimately informing potential therapeutic strategies for patients with varying risk profiles. Methods: We leveraged UCSC Xena and CGGA gene expression profiles from post-radiotherapy glioblastoma as verification cohorts. Infiltration ratios were stratified into high and low groups based on the median value. Differential gene expression was determined through Limma differential analysis. A signature comprising four genes was constructed, guided by Gene Ontology (GO) functional enrichment results and Kaplan-Meier survival analysis. We evaluated differences in cell infiltration levels, Immune Score, Stromal Score, and ESTIMATE Score and their Pearson correlations with the signature. Spearman's correlation was computed between the signature and patient drug sensitivity (IC50), predicted using Genomics of Drug Sensitivity in Cancer (GDSC) and CCLE databases. Results: Notably, the infiltration of central memory CD8+T cells exhibited a significant correlation with glioblastoma radiotherapy prognosis. Samples were dichotomized into high- and low-risk groups based on the optimal signature threshold (2.466642). Kaplan-Meier (K-M) survival analysis revealed that the high-risk group experienced a significantly poorer prognosis (p = .0068), with AUC values exceeding 0.82 at 1, 3, and 5 years, underscoring the robust predictive potential of the signature scoring system. Independent validation sets substantiated the validity of the signature. Statistically significant differences in tumor microenvironments (p < .05) were observed between high- and low-risk groups, and these differences were significantly correlated with the signature (p < .05). Furthermore, there were significant correlations between high and low-risk groups regarding immune checkpoint expressions, Immune Prognostic Score (IPS), and Tumor Immune Dysfunction and Exclusion (TIDE) scores. Conclusion: The immune cell signature, comprising SDC-1, PLAUR, FN1, and CXCL13, holds promise as a predictive tool for assessing glioblastoma prognosis following radiotherapy. This signature also offers valuable guidance for tailoring treatment strategies, emphasizing its potential clinical relevance in improving patient outcomes.

Predictive machine learning models based on VASARI features for WHO grading, isocitrate dehydrogenase mutation, and 1p19q co-deletion status: a multicenter study.

The objective of our study was to develop predictive models using Visually Accessible Rembrandt Images (VASARI) magnetic resonance imaging (MRI) features combined with machine learning techniques to predict the World Health Organization (WHO) grade, isocitrate dehydrogenase (IDH) mutation status, and 1p19q co-deletion status of high-grade gliomas. To achieve this, we retrospectively included 485 patients with high-grade glioma from the First Affiliated Hospital of Xinjiang Medical University, of which 312 patients were randomly divided into a training set (n=218) and a test set (n=94) in a 7:3 ratio. Twenty-five VASARI MRI features were selected from an initial set of 30, and three machine learning models - Multilayer Perceptron (MP), Bernoulli Naive Bayes (BNB), and Logistic Regression (LR) - were trained using the training set. The most informative features were identified using recursive feature elimination. Model performance was assessed using the test set and an independent validation set of 173 patients from Beijing Tiantan Hospital. The results indicated that the MP model exhibited the highest predictive accuracy on the training set, achieving an area under the curve (AUC) close to 1, indicating perfect discrimination. However, its performance decreased in the test and validation sets; particularly for predicting the 1p19q co-deletion status, the AUC was only 0.703, suggesting potential overfitting. On the other hand, the BNB model demonstrated robust generalization on the test and validation sets, with AUC values of 0.8292 and 0.8106, respectively, for predicting IDH mutation status and 1p19q co-deletion status, indicating high accuracy, sensitivity, and specificity. The LR model also showed good performance with AUCs of 0.7845 and 0.8674 on the test and validation sets, respectively, for predicting IDH mutation status, although it was slightly inferior to the BNB model for the 1p19q co-deletion status. In conclusion, integrating VASARI MRI features with machine learning techniques shows promise for the non-invasive prediction of glioma molecular markers, which could guide treatment strategies and improve prognosis in glioma patients. Nonetheless, further model optimization and validation are necessary to enhance its clinical utility.

Estimation of Spring Maize Planting Dates in China Using the Environmental Similarity Method

Global climate change is a serious threat to food and energy security. Crop growth modelling is an important tool for simulating crop food production and assisting in decision making. Planting date is one of the important model parameters. Larger-scale spatial distribution with high accuracy for planting dates is essential for the widespread application of crop growth models. In this study, a planting date prediction method based on environmental similarity was developed in accordance with the third law of geography. Spring maize planting date observations from 124 agricultural meteorological experiment stations in China over the years 1992–2010 were used as the data source. Samples spanning from 1992 to 2009 were allocated as training data, while samples from 2010 constituted the independent validation set. The results indicated that the root mean square error (RMSE) for spring maize planting date based on environmental similarity was 10 days, which is better than that of multiple regression analysis (RMSE = 13 days) in 2010. Additionally, when applied at varying scales, the accuracy of national-scale prediction was better than that of regional-scale prediction in areas with large differences in planting dates. Consequently, the method based on environmental similarity can effectively and accurately estimate planting date parameters at multiple scales and provide reasonable parameter support for large-scale crop growth modelling.

Expression profile of microRNAs in patients with decompensated cirrhosis by small RNA deep sequencing

Introduction and objectiveDecompensated cirrhosis (DCC) is a more advanced stage of liver cirrhosis (LC). It is important to identify biomarkers to predict DCC progression. The aim of this study was to analyze microRNA (miRNA) profiles of whole blood involved in the DCC process to gain a better understanding of the molecular mechanisms underlying its development. Materials and methodsRNA-Seq analysis of blood samples from a discovery set, including four DCC patients and four LC individuals, was performed to identify differentially expressed miRNAs. The selected differentially expressed miRNAs were validated by using an independent validation set. ResultsIn this study, a total of 1,036 miRNAs were identified in whole blood samples. Forty differentially expressed miRNAs were identified, including 24 upregulated and 16 downregulated miRNAs. The expression levels of three upregulated miRNAs (hsa-miR-20b-5p, hsa-miR-421, and hsa-miR-1307-3p) and two downregulated miRNAs (hsa-miR-139-5p and hsa-miR-150-5p) were validated by quantitative reverse transcriptase polymerase chain reaction. The receiver operator characteristic curve for the logistic regression model based on hsa-miR-20b-5p, hsa-miR-421, and hsa-miR-150-5p could distinguish DCC patients with excellent diagnostic accuracy (area under the curve: 0.981, p < 0.01). ConclusionThe miRNA expression profiles in patients with DCC and LC controls suggested that miR-20b-5p, miR-421, and miR-150-5p could be potential biomarkers and therapeutic targets for this condition.