Combined Model Research Articles

Enhancing Music Mood Recognition with LLMs and Audio Signal Processing: A Multimodal Approach

Abstract: Music Mood Recognition aims to allow computers to understand the emotions behind music the way humans do, in order to facilitate better perception of media by computers to aid in enhanced services like music recommendations, therapeutic interventions, and Human Computer Interaction. In this paper, we propose a novel approach to improving Music Mood Recognition using a multi-modal model that uses lyrical and audio features of a song. Lyrical features are analysed using stateof-the-art open-source Large Language Models like Microsoft Phi-3 to classify lyrics from one of the four possible emotion categories as per the James Russel Circumplex Model. Audio features are used to train a Deep Learning (ConvNet) model to predict emotion classes. A multimodal combiner model with Audio and Lyrics is then trained and deployed to enable accurate predictions. The dataset used in this research is “MoodyLyrics”, a collection of 2000+ songs classified with one of 4 possible emotion classes as per the James Russel Circumplex Model. Due to compute limitations, we are using a balanced set of 1000 songs to train and test our models. The workin this paper outperforms most other multimodal researches by allowing higher accuracies with universal language support

Assessment of inflammatory biomarkers to identify surgical/death necrotizing enterocolitis in preterm infants without pneumoperitoneum.

Necrotizing enterocolitis (NEC) is a life-threatening disease that affects premature infants. However, the role of inflammatory biomarkers in identifying surgical/death NEC without pneumoperitoneum remains elusive. We aimed to verify the value of platelet-to-lymphocyte ratio (PLR) and the combination of white blood cell (WBC), absolute neutrophil count (ANC), absolute lymphocyte count (ALC), neutrophil lymphocyte ratio (NLR), PLR, C reactive protein (CRP) and procalcitonin (PCT) in predicting the severity of NEC, and to construct a model to differ surgically NEC from non-surgically NEC. A retrospective analysis was performed on 191 premature infants with NEC. Based on the inclusion and exclusion criteria, 90 infants with Stage II and IIIA NEC were enrolled in this study, including surgical/death NEC (n = 38) and medical NEC (n = 52). The values of inflammatory biomarkers were collected within 24h of onset. The univariate analysis revealed that the values of WBC (p = 0.040), ANC (p = 0.048), PLR (p = 0.009), CRP (p = 0.016) and PCT (p < 0.01) in surgical/death NEC cohort were significantly higher than medical NEC cohort. Binary multivariate logistic regression analysis indicates that ANC, PLR, CRP, and PCT are capable of distinguishing infants with surgical/death NEC, and the AUC of the regression equation was 0.79 (95% CI 0.64-0.89; sensitivity 0.63; specificity 0.88), suggesting the equation has a good discrimination. Elevated PLR is associated with severe inflammation in surgical/death NEC patients. The prediction modelling of combination of ANC, PLR, CRP and PCT can differentiate surgical/death NEC from infants with medical NEC, which may improve risk awareness and facilitate effective communication between nurses and clinicians. However, multicentre research is needed to verify these findings for better clinical management of NEC.

Predicting mixed venous oxygen saturation (SvO2) impairment in COPD patients using clinical-CT radiomics data: A preliminary study.

Chronic obstructive pulmonary disease (COPD) is one of the most common chronic airway diseases in the world. To predict the degree of mixed venous oxygen saturation (SvO2) impairment in patients with COPD by modeling using clinical-CT radiomics data and to provide reference for clinical decision-making. A total of 236 patients with COPD diagnosed by CT and clinical data at Xiangyang No. 1 People's Hospital (n= 157) and Xiangyang Central Hospital (n= 79) from June 2018 to September 2021 were retrospectively analyzed. The patients were divided into group A (SvO⩾2 62%, N= 107) and group B (SvO<2 62%, N= 129). We set up training set and test set at a ratio of 7/3 and time cutoff spot; In training set, Logistic regression was conducted to analyze the differences in general data (e.g. height, weight, systolic blood pressure), laboratory indicators (e.g. arterial oxygen saturation and pulmonary artery systolic pressure), and CT radiomics (radscore generated using chest CT texture parameters from 3D slicer software and LASSO regression) between these two groups. Further the risk factors screened by the above method were used to establish models for predicting the degree of hypoxia in COPD, conduct verification in test set and create a nomogram. Univariate analysis demonstrated that age, smoking history, drinking history, systemic systolic pressure, digestive symptoms, right ventricular diameter (RV), mean systolic pulmonary artery pressure (sPAP), cardiac index (CI), pulmonary vascular resistance (PVR), 6-min walking distance (6MWD), WHO functional classification of pulmonary hypertension (WHOPHFC), the ratio of forced expiratory volume in the first second to the forced vital capacity (FEV1%), and radscore in group B were all significantly different from those in group A (P< 0.05). Multivariate regression demonstrated that age, smoking history, digestive symptoms, 6MWD, and radscore were independent risk factors for SvO2 impairment. The combined model established based on the abovementioned indicators exhibited a good prediction effect [AUC: 0.903; 95%CI (0.858-0.937)], higher than the general clinical model [AUC: 0.760; 95%CI (0.701-0.813), P< 0.05] and laboratory examination-radiomics model [AUC: 0.868; 95%CI (0.818-0.908), P= 0.012]. The newly created nomogram may be helpful for clinical decision-making and benefit COPD patients. SvO2 is an important indicator of hypoxia in COPD, and it is highly related to age, 6MWD, and radscore. The combined model is helpful for early identification of SvO2 impairment and adjustment of COPD treatment strategies.

Development and validation of a deep learning radiomics model with clinical-radiological characteristics for the identification of occult peritoneal metastases in patients with pancreatic ductal adenocarcinoma.

Occult peritoneal metastases (OPM) in patients with pancreatic ductal adenocarcinoma (PDAC) are frequently overlooked during imaging. The authors aimed to develop and validate a computed tomography (CT)-based deep learning-based radiomics (DLR) model to identify OPM in PDAC before treatment. This retrospective, bicentric study included 302 patients with PDAC (training: n =167, OPM-positive, n =22; internal test: n =72, OPM-positive, n =9: external test, n =63, OPM-positive, n =9) who had undergone baseline CT examinations between January 2012 and October 2022. Handcrafted radiomics (HCR) and DLR features of the tumor and HCR features of peritoneum were extracted from CT images. Mutual information and least absolute shrinkage and selection operator algorithms were used for feature selection. A combined model, which incorporated the selected clinical-radiological, HCR, and DLR features, was developed using a logistic regression classifier using data from the training cohort and validated in the test cohorts. Three clinical-radiological characteristics (carcinoembryonic antigen 19-9 and CT-based T and N stages), nine HCR features of the tumor, 14 DLR features of the tumor, and three HCR features of the peritoneum were retained after feature selection. The combined model yielded satisfactory predictive performance, with an area under the curve (AUC) of 0.853 (95% CI: 0.790-0.903), 0.845 (95% CI: 0.740-0.919), and 0.852 (95% CI: 0.740-0.929) in the training, internal test, and external test cohorts, respectively (all P <0.05). The combined model showed better discrimination than the clinical-radiological model in the training (AUC=0.853 vs. 0.612, P <0.001) and the total test (AUC=0.842 vs. 0.638, P <0.05) cohorts. The decision curves revealed that the combined model had greater clinical applicability than the clinical-radiological model. The model combining CT-based DLR and clinical-radiological features showed satisfactory performance for predicting OPM in patients with PDAC.

Optimizing Color Matching and Color Effects in Oil Painting Using Computer Vision Technology

The fusion of traditional oil painting techniques with computer vision technology presents an exciting frontier in the realm of artistic expression. This paper explores the intersection of these disciplines, focusing specifically on optimizing color matching and manipulating color effects in oil painting through computational means. By leveraging algorithms and image processing techniques, artists can enhance their creative process, enabling precise color measurement, nuanced color analysis, and predictive modelling of color combinations' visual impact. Through a comprehensive review of relevant literature, case studies, and practical applications, this paper elucidates the methodologies and advancements driving this convergence. Furthermore, it examines the implications of integrating computer vision into oil painting, offering insights into its transformative potential for artistic practice and aesthetic outcomes. By fostering a deeper understanding of this interdisciplinary intersection, this paper aims to inspire further exploration and innovation at the nexus of art and technology, ultimately enriching the landscape of contemporary artistic expression.

Radiomic Analysis of Contrast-Enhanced CT Predicts Glypican 3-Positive Hepatocellular Carcinoma.

The Glypican 3 (GPC3)-positive expression in Hepatocellular Carcinoma (HCC) is associated with a worse prognosis. Moreover, GPC3 has emerged as an immunotherapeutic target in advanced unresectable HCC systemic therapy. It is significant to diagnose GPC3-positive HCCs before therapy. Regarding imaging diagnosis of HCC, dynamic contrast-enhanced CT is more common than MRI in many regions. The aim of this study was to construct and validate a radiomics model based on contrast-enhanced CT to predict the GPC3 expression in hepatocellular carcinoma. This retrospective study included 141 (training cohort: n = 100; validation cohort: n = 41) pathologically confirmed HCC patients. Radiomics features were extracted from the Artery Phase (AP) images of contrast-enhanced CT. Logistic regression with the Least Absolute Shrinkage and Selection Operator (LASSO) regularization was used to select features to construct radiomics score (Rad-score). A final combined model, including the Rad-score of the selected features and clinical risk factors, was established. Receiver Operating Characteristic (ROC) curve analysis, Delong test, and Decision Curve Analysis (DCA) were used to assess the predictive performance of the clinical and radiomics models. 5 features were selected to construct the AP radiomics model of contrast-enhanced CT. The radiomics model of AP from contrast-enhanced CT was superior to the clinical model of AFP in training cohorts (P < 0.001), but not superior to the clinical model in validation cohorts (P = 0.151). The combined model (AUC = 0.867 vs. 0.895), including AP Rad-score and serum Alpha-Fetoprotein (AFP) levels, improved the predictive performance more than the AFP model (AUC = 0.651 vs. 0.718) in the training and validation cohorts. The combined model, with a higher decision curve indicating more net benefit, exhibited a better predictive performance than the AP radiomics model. DCA revealed that at a range threshold probability approximately above 60%, the combined model added more net benefit compared to the AP radiomics model of contrastenhanced CT. A combined model including AP Rad-score and serum AFP levels based on contrast-enhanced CT could preoperatively predict GPC3-positive expression in HCC.

GRU combined model based on multi-objective optimization for short-term residential load forecasting

Reliable and accurate short-term forecasting of residential load plays an important role in DSM. However, the high uncertainty inherent in single-user loads makes them difficult to forecast accurately. Various traditional methods have been used to address the problem of residential load forecasting. A single load forecast model in the traditional method does not allow for comprehensive learning of data characteristics for residential loads, and utilizing RNNs faces the problem of long-term memory with vanishing or exploding gradients in backpropagation. Therefore, a gated GRU combined model based on multi-objective optimization is proposed to improve the short-term residential load forecasting accuracy in this paper. In order to demonstrate the effectiveness, GRUCC-MOP is first experimentally tested with the unimproved model to verify the model performance and forecasting effectiveness. Secondly the method is evaluated experimentally with other excellent forecasting methods: models such as DBN, LSTM, GRU, EMD-DBN and EMD-MODBN. By comparing simulation experiments, the proposed GRU combined model can get better results in terms of MAPE on January, April, July, and November load data, so this proposed method has better performance than other research methods in short-term residential load forecasting.

Preoperative ultrasound radiomics for predicting clinically relevant postoperative pancreatic fistula after pancreatectomy.

To evaluate the efficacy of the radiomics model based on preoperative B-mode ultrasound (BMUS) and shear wave elastography (SWE) for predicting the occurrence of clinically relevant-postoperative pancreatic fistula (CR-POPF). Patients who were scheduled to undergo pancreatectomy were prospectively enrolled and received ultrasound assessment within one week before surgery. The risk factors of POPF (grades B and grades C) were analyzed. Preoperative BMUS images, SWE values of pancreatic lesions and surrounding parenchyma were used to build preoperative prediction radiomics models. Radiomic signatures were extracted and constructed using a minimal Redundancy Maximal Relevance (mRMR) algorithm and an L1 penalized logistic regression. A combined model was built using multivariate regression which incorporated radiomics signatures and clinical data. From January 2020 to November 2021, a total of 147 patients (85 distal pancreatectomies and 62 pancreaticoduodenectomies) were enrolled. During the three-week follow-up after pancreatectomy, the incidence rates of grade B/C POPF were 28.6% (42/147). Radiomic signatures constructed from BMUS of pancreas parenchymal regions (panRS) achieved an area under the receiver operating characteristic curve (AUC) of 0.75, accuracy of 68.7%, sensitivity of 85.7 %, and specificity of 61.9 % in preoperative noninvasive prediction of CR-POPF. The AUC of the radiomics model increased to 0.81 when panRS was used for the prediction of CR-POPF after pancreaticoduodenectomy. Radiomics model based on ultrasound images was potentially useful for predicting CR-POPF. Patients with high-risk factors should be closely monitored when postoperation.

Efficacy of SPR720 in murine models of non-tuberculous mycobacterial pulmonary infection.

Non-tuberculous mycobacterial pulmonary disease (NTM-PD) is increasing worldwide, with Mycobacterium avium complex (MAC) and Mycobacterium abscessus as the predominant pathogens. Current treatments are poorly tolerated and modestly effective, highlighting the need for new treatments. SPR719, the active moiety of the benzimidazole prodrug SPR720, inhibits the ATPase subunits of DNA gyrase B, a target not exploited by current antibiotics, and therefore, no cross-resistance is expected with standard-of-care (SOC) agents. To evaluate the in vitro activity of SPR719 against MAC and M. abscessus clinical isolates, including those resistant to SOC agents, and in vivo efficacy of SPR720 in murine non-tuberculous mycobacteria (NTM) pulmonary infection models. NTM isolates were tested for susceptibility to SPR719. Chronic C3HeB/FeJ and severe combined immunodeficient murine models of pulmonary infection were used to assess efficacy of SPR720 against MAC and M. abscessus, respectively. SPR719 was active against MAC (MIC90, 2 mg/L) and M. abscessus (MIC90, 4 mg/L) clinical isolates. Efficacy of SPR720 was demonstrated against MAC pulmonary infection, both as a monotherapy and in combination with SOC agents. SPR720 monotherapy exhibited dose-dependent reduction in bacterial burden, with the largest reduction observed when combined with clarithromycin and ethambutol. Efficacy of SPR720 was also demonstrated against M. abscessus pulmonary infection where monotherapy exhibited a dose-dependent reduction in bacterial burden with further reductions detected when combined with SOC agents. In vitro activity of SPR720 against common NTM pathogens and efficacy in murine infections warrant the continued clinical evaluation of SPR720 as a new oral option for the treatment of NTM-PD.

229 Quantitative Imaging Biomarkers for Risk Stratification of Intracranial Aneurysms

INTRODUCTION: Aneurysm wall enhancement (AWE) has emerged as a potential imaging biomarker for risk stratification of Intracranial aneurysms (IAs). Herein, the contrast-enhanced MRI (CE-MRI) exhibits markedly higher intensity on the IA sac as compared to the non-enhanced MRI (NE-MRI). However, currently it is assessed subjectively by clinicians which can introduce subjectivity. METHODS: We retrospectively collected 105 IAs with their NE-MRI, CE-MRI and Time-of-flight angiography images. IAs were classified as high or low risk if they had PHASES &gt;5 or ELAPSS &gt;20. We then identified the significantly different RFs and used them to build a logistic regression model for identifying high-risk IAs. We also compared the performance of this model with traditional AWE metrics like CCRatio (Average intensity on the IA sac normalized by the corpus callosum intensity) and CRStalk (Average intensity on the IA sac normalized by the pituitary stalk intensity). RESULTS: We found 35 high-risk IAs in the cohort and identified 183 RFs that were significantly different between them. After eliminating collinear RFs, we used 52 RFs to build our final model. We observed that the RF based model vastly outperformed the conventional metrics. In the testing set, we observed that the LR model had a higher accuracy as compared to conventional metrics. We observed that non-uniformity in pre-contrast MRI, homogeneity in post-contrast MRI and the difference in gray level non-uniformity had the highest odds ratios in the LR model. CONCLUSIONS: RFs from pre- and post-contrast MRI could identify high-risk IAs better than conventional metrics. This model in combination with 3D visualization could aid in better visualization of VWE and better risk stratification of IAs.

Contemporaneity of the Tree of Life Image in the Towels of Poltava Region of the 19th and 20th Centuries

The purpose of the article consists in identifying and analysing the ornaments of traditional towel embroidery of the Poltava region of the nineteenth and twentieth centuries, the peculiarities of the technique and technology of their production with a focus on the Tree of Life motif for the full reproduction of its authentic meaning in contemporary design.&#x0D; Research methodology is based on the methods of comparison, analysis and analogies used for a detailed literature analysis. Induction and deduction methods were useful for identifying the characteristic manifestations of the Poltava tradition against the background of embroidered towels of Ukraine. The typological and comparative methods were used in the study of the Poltava region territorial features. The historical method made it possible to study and identify the sequence of embroidery formation, symbolic and semantic features in embroidered towels. The scientific novelty of the article lies in the comparison of the principles of depicting the Tree of Life in embroidered towels of Podillia, Polissia, and Poltava region of the nineteenth and twentieth centuries; in the formation of a semiotic meanings list of the Tree of Life in towels of Poltava region, which have been scattered in various scientific works. The article provides recommendations for compliance with the authentic content in the interpretation of the symbolic elements of the Tree of Life image in the products of modern designer clothing brands. Conclusions. The Tree of Life is a complex ornamental element of embroidery, especially evident in the Poltava region, and has a wide range of symbolic meanings: a cosmogonic model of the world, the trinity of the three worlds, Family Tree, Mother Guardian, Holy Trinity, and Our Lady Oranta. In the Poltava region, the image of the Tree of Life in towels has been a well-established tradition since the nineteenth and twentieth centuries, with characteristic details in the form of fancy flowers. One of the reasons for the levelling of the sacred and magical load of the Tree-Flower in the ornamental compositions of modern clothing brands can be considered a tendency to generally lighten the informational and philosophical content of the product following consumer tastes. Some Ukrainian designers and brands demonstrate options for models of a successful combination of folklore motifs and authentic tradition with modern fashion trends. Individual Ukrainian designers and brands demonstrate variants of models that successfully combine folklore motifs and authentic tradition with modern fashion trends. Brands recreate traditional embroidery in their own interpretation, so the variety of techniques and technologies for demonstrating embroidery has a rich potential for development.

Predicting Soluble Solids Concentration of ‘Geneva 3’ Kiwiberries Using Near Infrared Spectroscopy

Near infrared (NIR) spectroscopy can be applied to nondestructively assess soluble solids concentration (SSC) of ripening, physiologically mature ‘Geneva 3’ kiwiberries (Actinidia arguta). Spectrographic signatures were captured using a handheld NIR produce quality meter to build predictive models of internal fruit quality for ‘Geneva 3’ kiwiberries that had been held under cold storage (CS) conditions (0 to 1 °C, &gt;90% relative humidity) as well as those not subjected to CS. The CS model, constructed using scans of 133 berries following 4 to 6 weeks in CS, predicts SSC using NIR wavelengths in the range of 729 to 975 nm. A total of 507 berries fresh from the vine were used to construct a predictive model for SSC of non-CS fruit using the same wavelength range. In each case, model predictive performance was investigated using split-half cross-validation, resulting in mean absolute error (MAE) values of 1.2% and 0.8% SSC for the CS and non-CS model, respectively. Each full model was then used to predict SSC of kiwiberries subjected to the alternative CS condition. The non-CS model maintained a low MAE (1.6% SSC) when applied to CS fruit, but the MAE of the CS model applied to non-CS fruit rose considerably (4.5% SSC). The performance of a combined model was tested against both CS and non-CS models, and a benefit to using tailored, CS-specific models was found, particularly in light of cross-seasonal results. As it has proven in many crops, NIR spectroscopy appears to be a promising tool for nondestructively assessing SSC in ‘Geneva 3’ kiwiberry fruit, with accuracy being enhanced by training models specific to postharvest regimes and/or defined ranges of SSC.

Handwritten Character Recognition using Deep Learning Algorithm with Machine Learning Classifier

Handwritten character recognition is a problem that has been worked on for many mainstream languages. Handwritten letter recognition has been proven to achieve promising results. Several studies using deep learning models have been conducted to achieve better accuracies. In this paper, the authors conducted two experiments on the EMNIST Letters dataset: Wavemix-Lite and CoAtNet. The Wavemix-Lite model uses Two-Dimensional Discrete Wavelet Transform Level 1 to reduce the parameters and speed up the runtime. The CoAtNet is a combined model of CNN and Visual Transformer where the image is broken down into fixed-size patches. The feature extraction part of the model is used to embed the input image into a feature vector. From those two models, the authors hooked the value of the features of the Global Average Pool layer using EMNIST Letters data. The features hooked from the training results of the two models, such as SVM, Random Forest, and XGBoost models, were used to train the machine learning classifier. The experiments conducted by the authors show that the best machine-learning model is the Random Forest, with 96.03% accuracy using the Wavemix-Lite model and 97.90% accuracy using the CoAtNet model. These results showcased the benefit of using a machine learning model for classifying image features that are extracted using a deep learning model.

Abstract 2820: The effect of Pten haploinsufficiency on genomic and transcriptomic profiles in combined genetically-engineered mouse models for colonic neoplasia based on Apc inactivation

Abstract Background and Aim: We have reported genetically-engineered mouse models for colonic neoplasia by using our novel CDX2P-Cre mice, in which Cre is restrictedly expressed in colonic epithelial cells. Although colonic tumors are generated in CDX2P-Cre;Apcflox/+ (CPC;Apc) mice with highly penetrant rate, greater number and deeper invasion of colonic tumors were observed in CDX2P-Cre;Apcflox/+;Ptenflox/+ (CPC;Apc+Pten), possibly resulting from haploinsufficiency of Pten gene. We have also confirmed shorter lifespan in CPC;Apc+Pten than that in CPC;Apc (AACR Annual Meeting 2018). Here, we test if these phenotypes come from one copy loss of Pten itself or secondary genetic and/or transcriptomic alterations induced by Pten loss by using whole genome sequence (WGS) and RNA sequence from macroscopically-dissected colonic tumors (bulk RNA-seq). Methods: WGS for five tumors and five livers as counterpart controls in each mouse model was performed by DNBSEQ platforms. Bulk RNA-seq was performed for three tumors in each model. Results: In the analysis using B-allele frequency, copy-neutral LOH occurred in chromosome 18 including Apc loci specifically in colonic neoplasia in both CPC;Apc and CPC;Apc+Pten mice. In contrast, LOH was not observed in chromosome 19 including Pten loci in CPC;Apc+Pten mice. We also confirmed remarkably decreased coverage of reads in reference mapping in Apc locus, and there was a slight decrease of coverage in Pten locus. There were no additional driver gene mutations in CPC;Apc or CPC;Apc+Pten in WGS. All these results suggested just one copy loss of Pten resulting in aggressive tumor phenotype in CPC;Apc+Pten mice. In RNA-seq and subsequent GSEA comparing colonic tumors in CPC;Apc+Pten with those in CPC;Apc revealed upregulation of some signal pathways including mTORC1. Supporting this observation, number of colon tumors, especially adenocarcinomas, were decreased by rapamycin administration to CPC;Apc+Pten. Similarly, rapamycin was more effective in tumorids from CPC;Apc+Pten those from CPC;Apc. Conclusion: WGS reveals one copy loss of Pten locus is the only genetic alteration in CPC;Apc+Pten when compared with CPC;Apc. One copy loss of Pten is sufficient to upregulate mTORC1 pathway in a CPC;Apc+Pten mouse model, resulting in promotion of tumor formation and invasion. Citation Format: Haruki Sada, Hiroaki Niitsu, Hikaru Nakahara, Naoya Sakamoto, Hirotaka Tashiro, Hideki Ohdan, Takao Hinoi. The effect of Pten haploinsufficiency on genomic and transcriptomic profiles in combined genetically-engineered mouse models for colonic neoplasia based on Apc inactivation [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2820.

Clinical study on the prediction of ALN metastasis based on intratumoral and peritumoral DCE-MRI radiomics and clinico-radiological characteristics in breast cancer.

To investigate the value of predicting axillary lymph node (ALN) metastasis based on intratumoral and peritumoral dynamic contrast-enhanced MRI (DCE-MRI) radiomics and clinico-radiological characteristics in breast cancer. A total of 473 breast cancer patients who underwent preoperative DCE-MRI from Jan 2017 to Dec 2020 were enrolled. These patients were randomly divided into training (n=378) and testing sets (n=95) at 8:2 ratio. Intratumoral regions (ITRs) of interest were manually delineated, and peritumoral regions of 3mm (3 mmPTRs) were automatically obtained by morphologically dilating the ITR. Radiomics features were extracted, and ALN metastasis-related radiomics features were selected by the Mann-Whitney U test, Z score normalization, variance thresholding, K-best algorithm and least absolute shrinkage and selection operator (LASSO) algorithm. Clinico-radiological risk factors were selected by logistic regression and were also used to construct predictive models combined with radiomics features. Then, 5 models were constructed, including ITR, 3 mmPTR, ITR+3 mmPTR, clinico-radiological and combined (ITR+3 mmPTR+ clinico-radiological) models. The performance of models was assessed by sensitivity, specificity, accuracy, F1 score and area under the curve (AUC) of receiver operating characteristic (ROC), calibration curves and decision curve analysis (DCA). A total of 2264 radiomics features were extracted from each region of interest (ROI), 3 and 10 radiomics features were selected for the ITR and 3 mmPTR, respectively. 5 clinico-radiological risk factors were selected, including lesion size, human epidermal growth factor receptor 2 (HER2) expression, vascular cancer thrombus status, MR-reported ALN status, and time-signal intensity curve (TIC) type. In the testing set, the combined model showed the highest AUC (0.839), specificity (74.2%), accuracy (75.8%) and F1 Score (69.3%) among the 5 models. DCA showed that it had the greatest net clinical benefit compared to the other models. The intra- and peritumoral radiomics models based on DCE-MRI could be used to predict ALN metastasis in breast cancer, especially for the combined model with clinico-radiological characteristics showing promising clinical application value.

Exploring a multiparameter MRI-based radiomics approach to predict tumor proliferation status of serous ovarian carcinoma.

To develop a multiparameter magnetic resonance imaging (MRI)-based radiomics approach that can accurately predict the tumor cell proliferation status of serous ovarian carcinoma (SOC). A total of 134 patients with SOC who met the inclusion and exclusion criteria were retrospectively screened from institution A, spanning from January 2016 to March 2022. Additionally, an external validation set comprising 42 SOC patients from institution B was also included. The region of interest was determined by drawing each ovarian mass boundaries manually slice-by-slice on T2-weighted imaging fat-suppressed fast spin-echo (T2FSE) and T1 with contrast enhancement (T1CE) images using ITK-SNAP software. The handcrafted radiomic features were extracted, and then were selected using variance threshold algorithm, SelectKBest algorithm, and least absolute shrinkage and selection operator. The optimal radiomic scores and the clinical/radiological independent predictors were integrated as a combined model. Compared with the area under the curve (AUC) values of each radiomic signature of T2FSE and T1CE, respectively, the AUC value of the radiomic signature (T1CE-T2FSE) was the highest in the training set (0.999 vs. 0.965 and 0.860). The homogeneous solid component of the ovarian mass was considered the only independent predictor of tumor cell proliferation status among the clinical/radiological variables. The AUC of the radiomic-radiological model was 0.999. The radiomic-radiological model combining radiomic scores and the homogeneous solid component of the ovarian mass can accurately predict tumor cell proliferation status of SOC which has high repeatability and may enable more targeted and effective treatment strategies. The proposed radiomic-radiological model combining radiomic scores and the homogeneous solid component of the ovarian mass can predict tumor cell proliferation status of SOC which has high repeatability and may guide individualized treatment programs. • The radiomic-radiological nomogram may guide individualized treatment programs of SOC. • This radiomic-radiological nomogram showed a favorable prediction ability. • Homogeneous slightly higher signal intensity on T2FSE is vital for Ki-67.

Preoperatively predicting vessels encapsulating tumor clusters in hepatocellular carcinoma: Machine learning model based on contrast-enhanced computed tomography.

Recently, vessels encapsulating tumor clusters (VETC) was considered as a distinct pattern of tumor vascularization which can primarily facilitate the entry of the whole tumor cluster into the bloodstream in an invasion independent manner, and was regarded as an independent risk factor for poor prognosis in hepatocellular carcinoma (HCC). To develop and validate a preoperative nomogram using contrast-enhanced computed tomography (CECT) to predict the presence of VETC+ in HCC. We retrospectively evaluated 190 patients with pathologically confirmed HCC who underwent CECT scanning and immunochemical staining for cluster of differentiation 34 at two medical centers. Radiomics analysis was conducted on intratumoral and peritumoral regions in the portal vein phase. Radiomics features, essential for identifying VETC+ HCC, were extracted and utilized to develop a radiomics model using machine learning algorithms in the training set. The model's performance was validated on two separate test sets. Receiver operating characteristic (ROC) analysis was employed to compare the identified performance of three models in predicting the VETC status of HCC on both training and test sets. The most predictive model was then used to constructed a radiomics nomogram that integrated the independent clinical-radiological features. ROC and decision curve analysis were used to assess the performance characteristics of the clinical-radiological features, the radiomics features and the radiomics nomogram. The study included 190 individuals from two independent centers, with the majority being male (81%) and a median age of 57 years (interquartile range: 51-66). The area under the curve (AUC) for the combined radiomics features selected from the intratumoral and peritumoral areas were 0.825, 0.788, and 0.680 in the training set and the two test sets. A total of 13 features were selected to construct the Rad-score. The nomogram, combining clinical-radiological and combined radiomics features could accurately predict VETC+ in all three sets, with AUC values of 0.859, 0.848 and 0.757. Decision curve analysis revealed that the radiomics nomogram was more clinically useful than both the clinical-radiological feature and the combined radiomics models. This study demonstrates the potential utility of a CECT-based radiomics nomogram, incorporating clinical-radiological features and combined radiomics features, in the identification of VETC+ HCC.

Two-way pharmacodynamic modeling of drug combinations and its application to pairs of repurposed Ebola and SARS-CoV-2 agents.

Existing pharmacodynamic (PD) mathematical models for drug combinations discriminate antagonistic, additive, multiplicative, and synergistic effects, but fail to consider how concentration-dependent drug interaction effects may vary across an entire dose-response matrix. We developed a two-way pharmacodynamic (TWPD) model to capture the PD of two-drug combinations. TWPD captures interactions between upstream and downstream drugs that act on different stages of viral replication, by quantifying upstream drug efficacy and concentration-dependent effects on downstream drug pharmacodynamic parameters. We applied TWPD to previously published in vitro drug matrixes for repurposed potential anti-Ebola and anti-SARS-CoV-2 drug pairs. Depending on the drug pairing, the model recapitulated combined efficacies as or more accurately than existing models and can be used to infer efficacy at untested drug concentrations. TWPD fits the data slightly better in one direction for all drug pairs, meaning that we can tentatively infer the upstream drug. Based on its high accuracy, TWPD could be used in concert with PK models to estimate the therapeutic effects of drug pairs in vivo.

Short term power load forecasting system based on improved neural network deep learning model

AbstractThe electricity load prediction is closely related to production and daily life. The electricity load prediction is also a very important task. With the widespread application of smart grids, load data shows an exponential growth trend. The huge amount of data in the load makes power prediction even more difficult. On the basis of traditional prediction algorithms, a power load prediction model based on machine learning and neural networks is designed. Because the single model prediction has the unstable results, a combined model is obtained based on the ensemble learning idea and two single model prediction method. The prediction results are detected by the load data. From the experimental results, the mean absolute percentage error (MAPE) of the AdaBoost‐GRU data fusion model is 0.066%. Compared to the AdaBoost‐GRU data fusion model, the MAPE decreases by 1.59% and 1.12%, respectively. The relative mass scores of the two groups decrease by 132.57% and 89.14%, respectively. The prediction accuracy is improved, which has advantages compared to traditional combination models. It can effectively enhance the accuracy of short‐term power grid load forecasting. It is an important scientific and practical reference for power grid decision‐making.

Prediction of water-level variations in an alluvial aquifer surrounded by karstic formations using a combined time series-geostatistical model: a case study from Iran

Prediction of water-level variations in an alluvial aquifer surrounded by karstic formations using a combined time series-geostatistical model: a case study from Iran