Training AUC Research Articles

Spatial modeling and ecological suitability of Ebola virus disease in Africa.

This paper looks into the MaxEnt model in a trial to comprehend the ecological and environmental conditions that propagate and drive the spread of Ebola Virus Disease in Africa. We use the MaxEnt model to assess risk determinants associated with the occurrence and distribution of EVD, taking into account non-correlated variables such as neighborhood mean temperature, rainfall, and human population density. Our findings indicate that among the factors that significantly shape the geographical distribution of EVD risk are human population density, annual rainfall, temperature variability, and seasonality. The model used is both reliable and accurate (the average value for training AUC was 0.987); it can be used as a valuable approach for the prediction of infectious disease outbreaks. High-risk areas are primarily identified in the western and central regions of Africa, with some of the others in the east also vulnerable. This further calls for specified public health interventions and enhanced surveillance in specified hotspots, contributing to global efforts to predict and mitigate risks associated with EVD outbreaks more adequately. The findings further support that it remains imperative to conduct additional research, including socio-economic and cultural variables, to enhance the understanding of how environmental factors contribute to the emergence and transmission of Ebola.

Application of angiogenesis-related genes associated with immune infiltration in the molecular typing and diagnosis of acute myocardial infarction.

Angiogenesis has been discovered to be a critical factor in developing tumors and ischemic diseases. However, the role of angiogenesis-related genes (ARGs) in acute myocardial infarction (AMI) remains unclear. The GSE66360 dataset was used as the training cohort, and the GSE48060 dataset was used as the external validation cohort. The random forest (RF) algorithm was used to identify the signature genes. Consensus clustering analysis was used to identify robust molecular clusters associated with angiogenesis. The ssGSEA was used to analyze the correlation between ARGs and immune cell infiltration. In addition, we constructed miRNA-gene, transcription factor network, and targeted drug network of signature genes. RT-qPCR was used to verify the expression levels of signature genes. Seven signature ARGs were identified based on the RF algorithm. Receiver operating characteristic curves confirmed the classification accuracy of the risk predictive model based on signature ARGs (area under the curve [AUC] = 0.9596 in the training cohort and AUC = 0.7773 in the external validation cohort). Subsequently, the ARG clusters were identified by consensus clustering. Cluster B had a more generalized high expression of ARGs and was significantly associated with immune infiltration. The miRNA and transcription factor network provided new ideas for finding potential upstream targets and biomarkers. Finally, the results of RT-qPCR were consistent with the bioinformatics analysis, further validating our results. Angiogenesis is closely related to AMI, and characterizing the angiogenic features of patients with AMI can help to risk-stratify patients and provide personalized treatment.

Forecasting the Expansion of Bactrocera tsuneonis (Miyake) (Diptera: Tephritidae) in China Using the MaxEnt Model.

The invasive pest, Bactrocera tsuneonis (Miyake), has become a significant threat to China's citrus industry. Predicting the area of potentially suitable habitats for B. tsuneonis is essential for optimizing pest control strategies that mitigate its impact on the citrus industry. Here, existing distribution data for B. tsuneonis, as well as current climate data and projections for four future periods (2021-2040, 2041-2060, 2061-2080, and 2081-2100) from the Coupled Model Intercomparison Project Phase 6 (CMIP6) were obtained. The distribution of B. tsuneonis under current and different climate change scenarios in China was predicted using the optimized MaxEnt model, ArcGIS, and the ENMeval data package. Model accuracy was assessed using ROC curves, and the primary environmental factors influencing the distribution of the pest were identified based on the percent contribution. When the regularization multiplier (RM) was set to 1.5 and the feature combination (FC) was set to LQH, a model with lower complexity was obtained. Under these parameter settings, the mean training AUC was 0.9916, and the mean testing AUC was 0.9854, indicating high predictive performance. The most influential environmental variables limiting the distribution of B. tsuneonis were the Precipitation of Warmest Quarter (Bio18) and Temperature Seasonality (standard deviation ×100) (Bio4). Under current climatic conditions, potentially suitable habitat for B. tsuneonis in China covered an area of 215.9 × 104 km2, accounting for 22.49% of the country's land area. Potentially suitable habitat was primarily concentrated in Central China, South China, and East China. However, under future climatic projections, the area of suitable habitat for B. tsuneonis exhibited varying degrees of expansion. Furthermore, the centroid of the total suitable habitat for this pest gradually shifted westward and northward. These findings suggest that B. tsuneonis will spread to northern and western regions of China under future climate changes. The results of our study indicate that climate change will have a major effect on the invasion of B. tsuneonis and have implications for the development of strategies to control the spread of B. tsuneonis in China.

Efficacy and biomarker analysis of carboplatin plus taxanes neoadjuvant chemotherapy in triple-negative breast cancer: A prospective multicenter cohort study.

e12619 Background: The efficacy and survival data of carboplatin plus taxane (anthracycline-free) neoadjuvant chemotherapy (NAC) in triple-negative breast cancer (TNBC) was lack of a large-sample study. The predictive biomarker of efficacy based on cell-free DNA (cfDNA) whole-methylome sequencing (WMS) has not been reported yet. Methods: The prospective multi-center cohort study was conducted in four hospitals of Chinabetween 2016 and 2023. Stage II-III TNBC patients were enrolled to receive NAC of carboplatin (AUC 5) every 3 weeks or carboplatin (AUC 4) every 2 weeks plus taxane(standard dose) for 4-6 cycles. Primary study endpoint were pathological complete response (pCR) and relapse-free survival (RFS). Plasma samples were prospectively collected at baseline (T1) and after NAC(T2). Chromosomal aneuploidy of featured fragments (CAFF),fragment size index (FSI) and methylation density score (MD) of cfDNA were detected with WMS. Results: A total of 267 patients were included in the study. The median age was 49 years, 156 patients (58.4%) were stage III disease. 147 patients (55.1%) received the triweekly NAC. 263 patients underwent breast surgery after NAC and 106 patients (40.3%) achieved pCR. The pCR were similar in biweekly or triweekly groups (39.8% vs 40.7%, P=0.89). The 3-year RFS and overall survival (OS) were 77.9%, 87.6%, respectively. Patients who achieved pCR had a significant better RFS (95.5%) and OS (97.7%) than those non-pCR (76.6%, P<0.001; 81.2%, P<0.001). A total of 66 patients with 120 plasma samples (64 samples at T1, 56 samples at T2) were included in WMS analysis. Patients with CAFF, FSI or MD positive at T1 had a higher tumor burden (stage III or cN2-3, all P values <0.05). The proportion of patients with FSI negative at T2 was significantly higher in pCR group compared to non-pCR(86.2% vs 59.3%, P=0.034). There is a similar tendency in patients with CAFF negative. Patients with MD positive at T1 was significantly associated with poor RFS compared to MD negative (HR = 7.36, 95% CI: 0.93-58.75, Log-rank P=0.028). A linear SVM model based on FSI, CAFF, combining with immune cell (effector memory CD8 T cells, immature B cells) and clinical features was developed to predict pCR, with AUC = 0.90 for training dataset and AUC = 0.86 for testing data. Conclusions: Our large-sample study further confirmed that carboplatin plus taxanes (anthracycline-free) NAC in TNBC is an effective option with clinical applicability. Biomarkers based on cfDNA WMS may offer some predictive and prognostic value which needed to be further investigated.

Enhancing pathological complete response prediction in breast cancer: the role of dynamic characterization of DCE-MRI and its association with tumor heterogeneity

BackgroundEarly prediction of pathological complete response (pCR) is important for deciding appropriate treatment strategies for patients. In this study, we aimed to quantify the dynamic characteristics of dynamic contrast-enhanced magnetic resonance images (DCE-MRI) and investigate its value to improve pCR prediction as well as its association with tumor heterogeneity in breast cancer patients.MethodsThe DCE-MRI, clinicopathologic record, and full transcriptomic data of 785 breast cancer patients receiving neoadjuvant chemotherapy were retrospectively included from a public dataset. Dynamic features of DCE-MRI were computed from extracted phase-varying radiomic feature series using 22 CAnonical Time-sereis CHaracteristics. Dynamic model and radiomic model were developed by logistic regression using dynamic features and traditional radiomic features respectively. Various combined models with clinical factors were also developed to find the optimal combination and the significance of each components was evaluated. All the models were evaluated in independent test set in terms of area under receiver operating characteristic curve (AUC). To explore the potential underlying biological mechanisms, radiogenomic analysis was implemented on patient subgroups stratified by dynamic model to identify differentially expressed genes (DEGs) and enriched pathways.ResultsA 10-feature dynamic model and a 4-feature radiomic model were developed (AUC = 0.688, 95%CI: 0.635–0.741 and AUC = 0.650, 95%CI: 0.595–0.705) and tested (AUC = 0.686, 95%CI: 0.594–0.778 and AUC = 0.626, 95%CI: 0.529–0.722), with the dynamic model showing slightly higher AUC (train p = 0.181, test p = 0.222). The combined model of clinical, radiomic, and dynamic achieved the highest AUC in pCR prediction (train: 0.769, 95%CI: 0.722–0.816 and test: 0.762, 95%CI: 0.679–0.845). Compared with clinical-radiomic combined model (train AUC = 0.716, 95%CI: 0.665–0.767 and test AUC = 0.695, 95%CI: 0.656–0.714), adding the dynamic component brought significant improvement in model performance (train p < 0.001 and test p = 0.005). Radiogenomic analysis identified 297 DEGs, including CXCL9, CCL18, and HLA-DPB1 which are known to be associated with breast cancer prognosis or angiogenesis. Gene set enrichment analysis further revealed enrichment of gene ontology terms and pathways related to immune system.ConclusionDynamic characteristics of DCE-MRI were quantified and used to develop dynamic model for improving pCR prediction in breast cancer patients. The dynamic model was associated with tumor heterogeniety in prognostic-related gene expression and immune-related pathways.

Prognostic value of CDKN2A in head and neck squamous cell carcinoma via pathomics and machine learning.

This study aims to enhance the prognosis prediction of Head and Neck Squamous Cell Carcinoma (HNSCC) by employing artificial intelligence (AI) to analyse CDKN2A gene expression from pathology images, directly correlating with patient outcomes. Our approach introduces a novel AI-driven pathomics framework, delineating a more precise relationship between CDKN2A expression and survival rates compared to previous studies. Utilizing 475 HNSCC cases from the TCGA database, we stratified patients into high-risk and low-risk groups based on CDKN2A expression thresholds. Through pathomics analysis of 271 cases with available slides, we extracted 465 distinctive features to construct a Gradient Boosting Machine (GBM) model. This model was then employed to compute Pathomics scores (PS), predicting CDKN2A expression levels with validation for accuracy and pathway association analysis. Our study demonstrates a significant correlation between higher CDKN2A expression and improved median overall survival (66.73 months for high expression vs. 42.97 months for low expression, p = 0.013), establishing CDKN2A's prognostic value. The pathomic model exhibited exceptional predictive accuracy (training AUC: 0.806; validation AUC: 0.710) and identified a strong link between higher Pathomics scores and cell cycle activation pathways. Validation through tissue microarray corroborated the predictive capacity of our model. Confirming CDKN2A as a crucial prognostic marker in HNSCC, this study advances the existing literature by implementing an AI-driven pathomics analysis for gene expression evaluation. This innovative methodology offers a cost-efficient and non-invasive alternative to traditional diagnostic procedures, potentially revolutionizing personalized medicine in oncology.

Role of climate change on Oriental spruce (Picea orientalis L.): Modeling and mapping

Global climate change is a process with dramatic consequences for ecosystems, and changes that may occur in the potential distribution of plant communities especially draw attention. This study aimed to reveal the potential distribution modeling and mapping of the Oriental spruce (Picea orientalis L.), distributed in a limited area, using current and future (year 2100) climate scenarios in Turkey. The maximum entropy method for potential distribution and Chelsa V2.1 technical specification IPSL-CM6A-LR scenarios (SSP126-SSP370-SSP585) were preferred to reveal the effect of climate change. Results for the current were in the “excellent” category with training and test data AUC 0.981 and 0.977, respectively. The variables contributing to the model were the precipitation amount of the driest month, mean diurnal air temperature range, annual precipitation amount, and mean annual air temperature. Variables contributing to the current model were analysed using the SSP126, SSP370, and SSP585 scenarios of the year 2100. It was assessed that the potential distribution for 2100 decreases according to SSP126, was fragmented according to SSP370, and decreased according to the SSP585 scenario. As a result, the authors determined that the high potential distribution is reduced 61% when the current mapping of Oriental spruce is compared with the SSP585 mapping.

A practical nomogram for predicting early death in elderly small cell lung cancer patients: A SEER-based study.

This study aimed to identify risk factors for early death in elderly small cell lung cancer (SCLC) patients and develop nomogram prediction models for all-cause and cancer-specific early death to improve patient management. Data of elderly patients diagnosed with SCLC were extracted from the SEER database, then randomly divided into training and validation cohorts. Univariate and stepwise multivariable Logistic regression analyses were performed on the training cohort to identify independent risk factors for early death in these patients. Nomograms were developed based on these factors to predict the overall risk of early death. The efficacy of the nomograms was validated using various methods, including ROC analysis, calibration curves, DCA, NRI, and IDI. Among 2077 elderly SCLC patients, 773 died within 3 months, 713 due to cancer-specific causes. Older age, higher AJCC staging, brain metastases, and lack of surgery, chemotherapy, or radiotherapy increase the risk of all-cause early death, while higher AJCC staging, brain metastases, lung metastases, and lack of surgery, chemotherapy, or radiotherapy increase the risk of cancer-specific death (P < .05). These identified factors were used to construct 2 nomograms to predict the risk of early death. The ROC indicated that the nomograms performed well in predicting both all-cause early death (AUC = 0.823 in the training cohort and AUC = 0.843 in the validation cohort) and cancer-specific early death (AUC = 0.814 in the training cohort and AUC = 0.841 in the validation cohort). The results of calibration curves, DCAs, NRI and IDI also showed that the 2 sets of nomograms had good predictive power and clinical utility and were superior to the commonly used TNM staging system. The nomogram prediction models constructed in this study can effectively assist clinicians in predicting the risk of early death in elderly SCLC patients, and can also help physicians screen patients at higher risk and develop personalized treatment plans for them.

Combined diagnosis for Parkinson's disease via gait and eye movement disorders

Background and objectivesWith the discovery of the potential role of gait and eye movement disorders in Parkinson's disease (PD) recognition, we intend to investigate the combined diagnostic value of gait and eye movement disorders for PD. MethodsWe enrolled some Chinese PD patients and healthy controls and separated them into the training and validation sets based on enrollment time. Performance in five oculomotor paradigms and in one gait paradigm was examined using an infrared eye tracking device and a wearable gait analysis device. We developed and validated a combined model for PD diagnosis via multivariate stepwise logistic regression analysis. Furthermore, subgroup comparisons and multi-model comparison were performed to assess its applicability and advantages. ResultsA total of 145 PD patients and 80 healthy controls in China were recruited. The pro-saccade velocity, the trunk-sway max, and the turn mean angular velocity were finally screened out for the model development. Incorporating age factor, the ternary model demonstrated more satisfactory performance on ROC (AUC of 0.953 in the training set and AUC of 0.972 in the validation set), calibration curve, and decision curve. A nomogram was drawn to visualize the model. The combined model outperforms individual models with a broad application and the unique diagnostic value for early detection of PD patients, especially TD-PD patients. ConclusionWe demonstrated the presence of gait and eye movement disorders, as well as the feasibility, applicability, and superiority of employing them together to diagnose PD.

A novel framework for identifying causes of forest fire events using environmental and temporal characteristics of the ignition point in fire footprint

BackgroundForest fire is a very common natural or human-made disaster, which not only burns precious forest resources, but also further alters the forest ecosystem structure and functions as well as global climate. Accordingly, effective information extraction, data management, and modeling of historical fire events are imperative for forecasting and mitigating the onset and progression of forest fires. Traditional remote sensing-based forest fire detection and risk prediction operate at the pixel scale, overlooking the integrity of fire behaviour. Moreover, fire cause records typically stem from ground reports, not fully leveraging the advantages of high temporal resolution thermal infrared remote sensing products. MethodsWe proposed a framework to identify the causes of forest fire events, experimenting with fire incidents from 2001 to 2020 in the Daxing'anling region of Northeast China. Initially, the Jenk-DBSCAN model was employed to acquire fire footprints representative of forest fire events from MODIS MCD64A1 product, and footprint-based fire event attribute information such as ignition locations and timings. Fire footprints matching ground surveys were subsequently filtered, and corresponding environmental variable datasets (including meteorological, topographical, fuel, and human activity factors) were derived in consideration of the spatio-temporal differences of footprint origin and center points. Finally, the optimal variable combinations of the two datasets were fed to three binary classification models including Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM) respectively to identify natural fires or human-induced fires, followed by assessing the accuracy of the fire cause identification models. ResultsResults revealed that there was a high spatio-temporal consistency of those matched fire footprints between the model-extracted and the ground-recorded fire events, evidenced by an overall R2 of 0.87 derived from their area validation. The ignition dates extracted from fire footprints often preceded those reported by local agencies. Among all the selected variable combinations for fire cause identification, the meteorological variables dominated, with daily mean dew point (DEWP) and daily mean visibility (VISIB) being preferentially selected by most models. Across the six models, the model training AUC values were almost greater than 0.8, with the LR model demonstrating superior validation accuracy over RF and SVM. Notably, the accuracy of the LR model using the origin point based dataset surpassed that of the center point-based dataset. The best model achieved an overall accuracy of 90.48%, with the user’s accuracies for human-made fire and natural fire being at 92.86% and 85.71%, respectively. ConclusionsThe proposed framework offers a reliable method for enriching attribute information in forest fire management databases. The resulting fire footprints and origin points can assist in better characterizing the progression of forest fire events. Such endeavours help devise targeted forest fire prevention regulations, fostering sustainable forest management.

Association between TyG index trajectory and new-onset lean NAFLD: a longitudinal study.

The purpose of this manuscript is to identify longitudinal trajectories of changes in triglyceride glucose (TyG) index and investigate the association of TyG index trajectories with risk of lean nonalcoholic fatty liver disease (NAFLD). Using data from 1,109 participants in the Health Management Cohort longitudinal study, we used Latent Class Growth Modeling (LCGM) to develop TyG index trajectories. Using a Cox proportional hazard model, the relationship between TyG index trajectories and incident lean NAFLD was analyzed. Restricted cubic splines (RCS) were used to visually display the dose-response association between TyG index and lean NAFLD. We also deployed machine learning (ML) via Light Gradient Boosting Machine (LightGBM) to predict lean NAFLD, validated by receiver operating characteristic curves (ROCs). The LightGBM model was used to create an online tool for medical use. In addition, NAFLD was assessed by abdominal ultrasound after excluding other liver fat causes. The median age of the population was 46.6 years, and 440 (39.68%) of the participants were men. Three distinct TyG index trajectories were identified: "low stable" (TyG index ranged from 7.66 to 7.71, n=206, 18.5%), "moderate stable" (TyG index ranged from 8.11 to 8.15, n=542, 48.8%), and "high stable" (TyG index ranged from 8.61 to 8.67, n=363, 32.7%). Using a "low stable" trajectory as a reference, a "high stable" trajectory was associated with an increased risk of lean-NAFLD (HR: 2.668, 95% CI: 1.098-6.484). After adjusting for baseline age, WC, SBP, BMI, and ALT, HR increased slightly in "moderate stable" and "high stable" trajectories to 1.767 (95% CI:0.730-4.275) and 2.668 (95% CI:1.098-6.484), respectively. RCS analysis showed a significant nonlinear dose-response relationship between TyG index and lean NAFLD risk (χ2=11.5, P=0.003). The LightGBM model demonstrated high accuracy (Train AUC 0.870, Test AUC 0.766). An online tool based on our model was developed to assist clinicians in assessing lean NAFLD risk. The TyG index serves as a promising noninvasive marker for lean NAFLD, with significant implications for clinical practice and public health policy.

A convolution neural network for rapid and accurate staging of breast cancer based on mammography

IntroductionBreast cancer (BC) has been one of the main reasons for women's deaths in the recent decade. This study hypothesizes that the deep features resulting from mammography staging can be used to determine tumor staging and lymph nodes of the sentinel lymph node (SLN) before surgery in BC patients. MethodsA retrospective study of female BC patients being treated. Pathological variables were collected from medical records, including age, tumor location, staging based on the American Joint Committee on Cancer (AJCC), pathological type, human epidermal growth factor receptor 2 (HER2) status, Progesterone Receptor (PR) status, and Estrogen Receptor (ER) status. The contrast enhancement technique with Contrast-Limited Adaptive Histogram Equalization (CLAHE) was applied to the studied data using MATLAB software. The images were first changed from color to gray in the preprocessing process, and then the images were changed from gray to color again. The regions of interest (ROI) of the primary tumor were isolated from other areas of breast tissue by two expert radiologists. Therefore, a proposed convolution neural network (CNN) model was applied. ResultsIn this study, 390 patients' information was used to analyze the data. In total, out of 390 patients, 300 had metastatic SLN involvement, and 390 had a tumor size greater than 1 mm. Performance evaluation of the proposed CNN staging was AUC 0.919 (95 % CI: 0.852,0.971) for the training group and AUC 0.877 (95 % CI: 0.805,0.949) for the validation group. ConclusionsThis study proposes a deep learning model based on CNN based on mammographic images, which has a suitable function for determining tumor staging and SLN metastasis.

Prediction of locally advanced rectal cancer response to neoadjuvant chemoradiation therapy using volumetric multiparametric MRI-based radiomics.

To assess the role of pretreatment multiparametric (mp)MRI-based radiomic features in predicting pathologic complete response (pCR) of locally advanced rectal cancer (LARC) to neoadjuvant chemoradiation therapy (nCRT). This was a retrospective dual-center study including 98 patients (M/F 77/21, mean age 60years) with LARC who underwent pretreatment mpMRI followed by nCRT and total mesorectal excision or watch and wait. Fifty-eight patients from institution 1 constituted the training set and 40 from institution 2 the validation set. Manual segmentation using volumes of interest was performed on T1WI pre-/post-contrast, T2WI and diffusion-weighted imaging (DWI) sequences. Demographic information and serum carcinoembryonic antigen (CEA) levels were collected. Shape, 1st and 2nd order radiomic features were extracted and entered in models based on principal component analysis used to predict pCR. The best model was obtained using a k-fold cross-validation method on the training set, and AUC, sensitivity and specificity for prediction of pCR were calculated on the validation set. Stage distribution was T3 (n = 79) or T4 (n = 19). Overall, 16 (16.3%) patients achieved pCR. Demographics, MRI TNM stage, and CEA were not predictive of pCR (p range 0.59-0.96), while several radiomic models achieved high diagnostic performance for prediction of pCR (in the validation set), with AUCs ranging from 0.7 to 0.9, with the best model based on high b-value DWI demonstrating AUC of 0.9 [95% confidence intervals: 0.67, 1], sensitivity of 100% [100%, 100%], and specificity of 81% [66%, 96%]. Radiomic models obtained from pre-treatment MRI show good to excellent performance for the prediction of pCR in patients with LARC, superior to clinical parameters and CEA. A larger study is needed for confirmation of these results.

Assessing success in attempts to eradicate an emerging invader plant: Tephrocactus articulatus (Pfeiff.) Backeb in arid areas of South Africa

Tephrocactus articulatus (Pfeiff.) Backeb (family: Cactaceae) is an emerging invader plant that is native to Argentina and was introduced as an ornamental plant in South Africa. The South African national regulations and legislation for controlling biological invasions dictate that emerging alien species must be eradicated. We evaluated the effectiveness of foliar spray in clearing the populations of T. articulatus, and determined the management challenges in 16 representative sites. We also applied bioclimatic models to forecast how T. articulatus invasion might respond to climate change. The exposure to climate change forecasts for T. articulatus was quantified using the Intergovernmental Panel on Climate Change - IPCC (2014) two representative concentration pathways – RCP scenarios (4.5 and 8.5) for the 2061–2080 period. Overall, the foliar spray method significantly suppressed T. articulatus populations in all sites (i.e., 75–99%) except in four sites that did not display the population suppression threshold of X ≥ 75%. The clearing success (i.e., % of dead plants), was significantly and negatively correlated to the size of the site (ha) wherein the bigger sites had relatively low success. Climate suitability projections under the RCP4.5 and RCP8.5 scenarios for T. articulatus produced excellent data fits (i.e., training AUC = 0.939 and test AUC = 0.914). Noteworthy, both future scenarios model projections have shown an expansion of suitable habitat for T. articulatus: 49.9% and 60.4% respectively, of the current estimated total spatial coverage of 219102 km2, and with possible expansion into neighbouring countries, Namibia and Botswana. The significant variation in the projections was contributed by precipitation in the wettest (47.5%) and warmest quarters (48.9%). Our results advance the importance of predictive models in planning optimisation in the management of emerging alien plant species in South Africa: if the ongoing eradication of T. articulatus in the core invasion areas fails, and climate change prevails, a switch from foliar spray to biological control method will be essential.

Evaluation of molecular receptors status in breast cancer using an mpMRI-based feature fusion radiomics model: mimicking radiologists’ diagnosis

ObjectiveTo investigate the performance of a novel feature fusion radiomics (RFF) model that incorporates features from multiparametric MRIs (mpMRI) in distinguishing different statuses of molecular receptors in breast cancer (BC) preoperatively.Methods460 patients with 466 pathology-confirmed BCs who underwent breast mpMRI at 1.5T in our center were retrospectively included hormone receptor (HR) positive (HR+) (n=336) and HR negative (HR-) (n=130). The HR- patients were further categorized into human epidermal growth factor receptor 2 (HER-2) enriched BC (HEBC) (n=76) and triple negative BC (TNBC) (n=54). All lesions were divided into a training/validation cohort (n=337) and a test cohort (n=129). Volumes of interest (VOIs) delineation, followed by radiomics feature extraction, was performed on T2WI, DWI600 (b=600 s/mm2), DWI800 (b=800 s/mm2), ADC map, and DCE1-6 (six continuous DCE-MRI) images of each lesion. Simulating a radiologist’s work pattern, 150 classification base models were constructed and analyzed to determine the top four optimum sequences for classifying HR+ vs. HR-, TNBC vs. HEBC, TNBC vs. non-TNBC in a random selected training cohort (n=337). Building upon these findings, the optimal single sequence models (Rss) and combined sequences models (RFF) were developed. The AUC, sensitivity, accuracy and specificity of each model for subtype differentiation were evaluated. The paired samples Wilcoxon signed rank test was used for performance comparison.ResultsDuring the three classification tasks, the optimal single sequence for classifying HR+ vs. HR- was DWI600, while the ADC map, derived from DWI800 performed the best in distinguishing TNBC vs. HEBC, as well as identifying TNBC vs. non-TNBC, with corresponding training AUC values of 0.787, 0.788, and 0.809, respectively. Furthermore, the integration of the top four sequences in RFF models yielded improved performance, achieving AUC values of 0.809, 0.805 and 0.847, respectively. Consistent results was observed in both the training/validation and testing cohorts, with AUC values of 0.778, 0.787, 0.818 and 0.726, 0.773, 0.773, respectively (all p &amp;lt; 0.05 except HR+ vs. HR-).ConclusionThe RFF model, integrating mpMRI radiomics features, demonstrated promising ability to mimic radiologists’ diagnosis for preoperative identification of molecular receptors of BC.

Prediction of cerebral hemorrhagic transformation after thrombectomy using a deep learning of dual-energy CT.

To develop and validate a deep learning model for predicting hemorrhagic transformation after endovascular thrombectomy using dual-energy computed tomography (CT). This was a retrospective study from a prospective registry of acute ischemic stroke. Patients admitted between May 2019 and February 2023 who underwent endovascular thrombectomy for acute anterior circulation occlusions were enrolled. Hemorrhagic transformation was defined using follow-up magnetic resonance imaging or CT. The deep learning model was developed using post-thrombectomy dual-energy CT to predict hemorrhagic transformation within 72h. Temporal validation was performed with patients who were admitted after July 2022. The deep learning model's performance was compared with a logistic regression model developed from clinical variables using the area under the receiver operating characteristic curve (AUC). Total of 202 patients (mean age 71.4years ± 14.5 [standard deviation], 92 men) were included, with 109 (54.0%) patients having hemorrhagic transformation. The deep learning model performed consistently well, showing an average AUC of 0.867 (95% confidence interval [CI], 0.815-0.902) upon five-fold cross validation and AUC of 0.911 (95% CI, 0.774-1.000) with the test dataset. The clinical variable model showed an AUC of 0.775 (95% CI, 0.709-0.842) on the training dataset (p < 0.01) and AUC of 0.634 (95% CI, 0.385-0.883) on the test dataset (p = 0.06). A deep learning model was developed and validated for prediction of hemorrhagic transformation after endovascular thrombectomy in patients with acute stroke using dual-energy computed tomography. This study demonstrates that a convolutional neural network (CNN) can be utilized on dual-energy computed tomography (DECT) for the accurate prediction of hemorrhagic transformation after thrombectomy. The CNN achieves high performance without the need for region of interest drawing. • Iodine leakage on dual-energy CT after thrombectomy may be from blood-brain barrier disruption. • A convolutional neural network on post-thrombectomy dual-energy CT enables individualized prediction of hemorrhagic transformation. • Iodine leakage is an important predictor of hemorrhagic transformation following thrombectomy for ischemic stroke.

Predicting survival of advanced laryngeal squamous cell carcinoma: comparison of machine learning models and Cox regression models

Laryngeal squamous cell carcinoma (LSCC) is a common tumor type. High recurrence rates remain an important factor affecting the survival and quality of life of advanced LSCC patients. We aimed to build a new nomogram and a random survival forest model using machine learning to predict the risk of LSCC progress. The study included 671 patients with AJCC stages III–IV LSCC. To develop a prognostic model, Cox regression analyses were used to assess the relationship between clinic-pathologic factors and disease-free survival (DFS). RSF analysis was also used to predict the DFS of LSCC patients. The ROC curve revealed that the Cox model exhibited good sensitivity and specificity in predicting DFS in the training and validation cohorts (1 year, validation AUC = 0.679, training AUC = 0.693; 3 years, validation AUC = 0.716, training AUC = 0.655; 5 years, validation AUC = 0.717, training AUC = 0.659). Random survival forest analysis showed that N stage, clinical stage, and postoperative chemoradiotherapy were prognostically significant variables associated with survival. The random forest model exhibited better prediction ability than the Cox regression model in the training cohort; however, the two models showed similar prediction ability in the validation cohort.

Comparing effectiveness of image perturbation and test retest imaging in improving radiomic model reliability

Image perturbation is a promising technique to assess radiomic feature repeatability, but whether it can achieve the same effect as test–retest imaging on model reliability is unknown. This study aimed to compare radiomic model reliability based on repeatable features determined by the two methods using four different classifiers. A 191-patient public breast cancer dataset with 71 test–retest scans was used with pre-determined 117 training and 74 testing samples. We collected apparent diffusion coefficient images and manual tumor segmentations for radiomic feature extraction. Random translations, rotations, and contour randomizations were performed on the training images, and intra-class correlation coefficient (ICC) was used to filter high repeatable features. We evaluated model reliability in both internal generalizability and robustness, which were quantified by training and testing AUC and prediction ICC. Higher testing performance was found at higher feature ICC thresholds, but it dropped significantly at ICC = 0.95 for the test–retest model. Similar optimal reliability can be achieved with testing AUC = 0.7–0.8 and prediction ICC > 0.9 at the ICC threshold of 0.9. It is recommended to include feature repeatability analysis using image perturbation in any radiomic study when test–retest is not feasible, but care should be taken when deciding the optimal feature repeatability criteria.

The value of plasma presepsin as a diagnostic and prognostic biomarker for sepsis in Southern China.

Presepsin is a soluble CD14 subtype that has been considered as a novel marker for patients with sepsis.This study explored the clinical value of presepsin for sepsis in Southern China, and further established models for diagnosis and prognosis of sepsis through using machine learning (ML), by combining presepsin and other laboratory parameters. 269 subjects (105 infected patients, 164 sepsis and septic shock) and 198 healthy controls were enrolled. Laboratory parameters (hematological parameters, coagulation parameters, liver function indices, renal function indices, and inflammatory markers) were collected. Plasma presepsin was tested by chemiluminescence enzyme immunoassay. ML of DxAI™ Research platform was used to establish diagnostic and prognostic models. Sensitivity, specificity, and other performance indicators were used to evaluate the performance of each model. The level of presepsin was obviously increased in sepsis and sepsis shock, compared with that of infected and healthy group (all P < 0.0001). Presepsin concentration was positively correlated with positive blood culture and 30-day mortality in sepsis and septic shock patients. Through ROC curve analysis, Hb, UREA, APTT, CRP, PCT, and presepsin were incorporated into machine learning to construct diagnosis models. Ada Boost model had the best diagnostic efficiency (AUC: 0.94 (95% CI 0.919-0.968) in the training set and AUC: 0.86 (95% CI 0.813-0.900) in validation set). Furthermore, AST, APTT, UREA, PCT, and presepsin were included in the prognosis ML models, and the Bernoulli NB model had greater predictive ability for 30-day mortality risk of sepsis (AUC: 0.706), which was higher than that of PCT (AUC: 0.617) and presepsin (AUC: 0.634) alone. Machine-learning model based on presepsin and routinely laboratory parameters showed good performance of diagnostic and prognostic ability for sepsis patients.

Machine learning to predict risk for community-onset Staphylococcus aureus infections in children living in southeastern United States.

Staphylococcus aureus (S. aureus) is known to cause human infections and since the late 1990s, community-onset antibiotic resistant infections (methicillin resistant S. aureus (MRSA)) continue to cause significant infections in the United States. Skin and soft tissue infections (SSTIs) still account for the majority of these in the outpatient setting. Machine learning can predict the location-based risks for community-level S. aureus infections. Multi-year (2002-2016) electronic health records of children <19 years old with S. aureus infections were queried for patient level data for demographic, clinical, and laboratory information. Area level data (Block group) was abstracted from U.S. Census data. A machine learning ecological niche model, maximum entropy (MaxEnt), was applied to assess model performance of specific place-based factors (determined a priori) associated with S. aureus infections; analyses were structured to compare methicillin resistant (MRSA) against methicillin sensitive S. aureus (MSSA) infections. Differences in rates of MRSA and MSSA infections were determined by comparing those which occurred in the early phase (2002-2005) and those in the later phase (2006-2016). Multi-level modeling was applied to identify risks factors for S. aureus infections. Among 16,124 unique patients with community-onset MRSA and MSSA, majority occurred in the most densely populated neighborhoods of Atlanta's metropolitan area. MaxEnt model performance showed the training AUC ranged from 0.771 to 0.824, while the testing AUC ranged from 0.769 to 0.839. Population density was the area variable which contributed the most in predicting S. aureus disease (stratified by CO-MRSA and CO-MSSA) across early and late periods. Race contributed more to CO-MRSA prediction models during the early and late periods than for CO-MSSA. Machine learning accurately predicts which densely populated areas are at highest and lowest risk for community-onset S. aureus infections over a 14-year time span.