Prediction Accuracy Research Articles

Advancing Marine Surveillance: A Hybrid Approach of Physics-Infused Neural Network for Enhanced Vessel Tracking Using Automatic Identification System Data

In the domain of maritime surveillance, the continuous tracking and monitoring of vessels are imperative for the early detection of potential threats. The Automatic Identification System (AIS) database, which collects vessel movement data over time, including timestamps and other motion details, plays a crucial role in real-time maritime monitoring. However, it frequently exhibits irregular intervals of data collection and intricate, intersecting trajectories, underscoring the importance of analyzing long-term temporal patterns for effective vessel tracking. While Kalman filters and other physics-based models have been employed to tackle these issues, their effectiveness is limited by their inability to capture long-term dependence and nonlinearity in the historical data. This paper introduces a novel approach that leverages Long Short-Term Memory (LSTM), a type of recurrent neural network, renowned for its proficiency in recognizing patterns over extended periods. Recognizing the strengths and limitations of the LSTM model, we propose a hybrid machine learning algorithm that integrates LSTM with a physics-based model. This combination harnesses the physical laws governing vessel movements, thereby enhancing the predictive accuracy of vessel locations. To simulate real-world conditions, time gaps are introduced into the dataset. We evaluate the performance of both standalone and hybrid models on datasets with and without these data gaps. Our results reveal that while the LSTM model alone outperforms the physics-based model in scenarios with data gaps, the hybrid model significantly surpasses both standalone models. This study not only demonstrates the potential of combining data-driven and physics-based approaches but also sets a new benchmark for maritime vessel tracking.

Authenticating the Geographical Origin of Jingbai Pear in Northern China by Multiple Stable Isotope and Elemental Analysis

The Jingbai pear is one of the best pear species in China with high quality and nutrition values which are closely linked to its geographical origin. With the purpose of discriminating the PGI Mentougou Jingbai pear from three other producing regions, the stable isotope ratios and elemental profiles of the pears (n = 52) and the corresponding soils and groundwater were determined using isotope ratio mass spectrometry (IRMS) and inductively coupled plasma mass spectrometry (ICP-MS), respectively. The results revealed that δ15N, δ18OJ, and Li were significantly different (p < 0.05) in samples from different regions, which indicated their potential to be used in the geographical origin classification of the Jingbai pear. The nitrogen isotopic values of the pear pulp were positively correlated with the δ15N value and nitrogen content of the corresponding soils, whilst the B, Na, K, Cr, and Cd contents of the pear pulps were positively correlated with their corresponding soils. Orthogonal partial least squares discriminant analysis (OPLS-DA) was performed in combination with analysis of the stable isotopes and elemental profiles, making it possible to distinguish the cultivation regions from each other with a high prediction accuracy (a correct classification rate of 92.3%). The results of this study highlight the potential of stable isotope ratios and elemental profiles to trace the geographical origin of pears at a small spatial scale.

NSE and S100β as serum alarmins in predicting neurological outcomes after cardiac arrest

Cardiac arrest (CA) is a serious health concern that often results in mortality or severe neurological dysfunction in the case of survival. Our aim was to explore the neurological prognostic factors in patients with CA. This retrospective observational study included adult patients with CA. We investigated serum neuron-specific enolase (NSE), S100 calcium-binding protein β (S100β), and indices and parameters at 1, 3, 5, 7 and intensive care unit (ICU) discharge days after CA. The primary study endpoint was the Cerebral Performance Category (CPC) scale score at ICU discharge, which was dichotomized as good neurological outcome (CPC 1–2: full recovery or moderate disability) and poor neurological outcome (CPC 3–5: severe disability, vegetative state, or death). Of the 191 adult patients with CA, 42 (22%) had good neurological outcomes, and 149 (78%) had poor neurological outcomes. NSE at 1,3,5,7 and ICU discharge days showed excellent predictive accuracy for neurological outcomes (area under the curve [AUC]: 0.666, 0.716, 0.870, 0.739, and 0.901, respectively). However, S100β exhibited general predictive power (AUC: 0.666, 0.573, 0.607, 0.594, 0.727). Finally, the early warning model, which combined day 1 NSE, day 1 S100β, cardiac arrest time, SOFA scores, APACHE II scores, and age, was used to screen CA patients with poor neurological prognosis at early stages and had an AUC of 0.792. Serum concentrations of NSE and S100β were significantly elevated in CA patients and could be prognostic biomarkers to predict neurological outcomes. Day 1 NSE and S100β combined with multiple indicators could be a decent early warning model for poor neurological prognosis in patients with CA.

Generation Method for HVAC Systems Design Schemes in Office Buildings Based on Deep Graph Generative Models

The design process of heating, ventilation, and air conditioning (HVAC) systems is complex and time consuming due to the need to follow design codes. Since the design standards are not fixed, the final outcome often depends on the designer’s experience. The development of building information modeling (BIM) technology has made information throughout the building lifecycle more integrated. BIM-based forward design is now widely used, providing a data foundation for combining HVAC system design with machine learning. This paper proposes an unsupervised learning method based on deep graph generative models to uncover hidden design patterns and optimization strategies from the design results. We trained and validated four deep graph generative models—GAE, GNF, GAN, and diffusion—using HVAC system terminal pipeline layout data. Accuracy and precision metrics were used to compare the generated designs with automated forward design solutions, assessing the models’ ability to capture both local variations and broader changes in design logic. A graph-neural-network-based evaluation method was employed to measure the models’ capacity to detect changes. The results indicate that all four models achieved prediction accuracies exceeding 90% and precision rates above 75%. The models effectively captured both local modifications made by designers and global design changes, showing greater sensitivity to global layout adjustments than to local updates. When comparing the results generated by deep graph generative models and the actual design, it is obvious that the accuracy of the predictions varies significantly due to the complexity of the test buildings.

Trend Prediction of Vibration Signals for Pumped-Storage Units Based on BA-VMD and LSTM

Under “dual-carbon” goals and rapid renewable energy growth, increasing start-stop frequency poses new challenges to safe operations of pumped-storage power plant equipment. Ensuring equipment safety and predictive maintenance under complex conditions urgently requires vibration warnings and trend forecasting for pumped-storage units. In this study, the measured vibration-signal characteristics of pumped-storage units in a strong background-noise environment are obtained using a noise-reduction method that integrates BA-VMD and wavelet thresholding. We monitored the vibration-signal data of hydroelectric units over a long period of time, and the measured vibration-signal characteristics of pumped-storage units in a strong background-noise environment are accurately obtained using a noise-reduction method that integrates BA-VMD and wavelet thresholding. In this paper, a BP neural network prediction model, a support vector machine (SVM) prediction model, a convolutional neural network (CNN) prediction model, and a long short-term memory network (LSTM) prediction model are used to predict the trend of vibration signals of the pumped-storage unit under different operating conditions. The model prediction effect is analyzed by using the different error evaluation functions, and the prediction results are compared with the predicted results of the four different methods. By comparing the prediction effects of the four different methods, it is concluded that LSTM has higher prediction accuracy and can predict the vibration trends of hydropower units more accurately.

Fabrication of a molecularly imprinted poly(methyl methacrylate) decorated graphite electrode for detection of aloe emodin in Aloe vera

In this work, the authors represent a comprehensive approach for the development and validation of a novel graphite-supported molecularly imprinted poly(methyl methacrylate) electrode for the selective and sensitive detection of aloe emodin (AE) in aloe-based cosmetic products. The electrocatalytic activity of the electrode was evaluated using cyclic voltammetry and differential pulse voltammetry techniques in phosphate buffer saline. Surface morphology, structural characteristics, and imprinting endorsement were investigated using field emission scanning electron microscopy, Fourier-transform infrared spectroscopy, and UV-Vis spectroscopy. Under the optimal conditions, the electrode showed an oxidative differential pulse voltammetry peak at -0.2931±0.011 V (vs. Ag/AgCl, saturated KCl). The current was increased linearly with increasing concentrations of AE from 0.0005 to 350 µM, with a low detection limit of 0.0003 µM. The voltammetric analysis has been validated by reverse-phase high-performance liquid chromatography (RP-HPLC) methods. A partial least square regression model was developed to correlate the results obtained from the proposed system with the reference values obtained by RP-HPLC. The model showed a high prediction accuracy of 95.95 % for the detection of AE in cosmetic samples. The developed electrode provides a low-cost, rapid, easy, and convenient method for the detection of AE in cosmetic products, offering potential benefits for quality control and safety assessment in the cosmetic industry.

Comparative Diagnostic Value of 18F-FDG–PET–CT and Intraoperative Examination in Cervical Cancer Staging

Background and Objectives: The primary objective of this study is to assess the effectiveness of 18F-FDG–PET–CT in preoperative staging of cervical cancer, focusing on determining surgical operability and exploring the correlation between its quantitative parameters and clinicopathological characteristics. Materials and Methods: This retrospective study included 62 cervical cancer patients treated at the Department of Gynecology, Clinic for Operative Oncology at the Institute of Oncology Vojvodina between January 2016 and January 2020, where preoperative clinical examinations and 18F-FDG–PET–CT were performed to assess the extent of cancer, followed by intraoperative and pathohistological examinations of surgically removed specimens to provide a comprehensive evaluation. Results: The mean tumor size measured by 18F-FDG–PET–CT was slightly greater than that obtained through clinical examination (26.4 mm vs. 26.0 mm), with a strong linear correlation (r = 0.678, p < 0.001) observed between the two measurement methods. The overall prediction accuracy of 18F-FDG–PET–CT for primary tumors is 88.7% (55/62) [sensitivity 86.8%, specificity 100.0%, PPV 100.0%, NPV 56.2%] and for intraoperative examination is 88.7% (55/62) [sensitivity 98.1%, specificity 33.3%, PPV 89.7%, NPV 75.0%]. The agreement with histopathological examination was good for 18F-FDG–PET–CT and moderate for intraoperative examination for primary tumors. Regarding lymph nodes, the overall prediction accuracy of 18F-FDG–PET–CT is 82.2% (51/62) [sensitivity 53.8%, specificity 89.8%, PPV 58.3%, NPV 88.8%] and for intraoperative examination 66.1% (41/62) [sensitivity 76.9%, specificity 63.3%, PPV 35.7%, NPV 91.2%]. The agreement with histopathological examination was moderate for 18F-FDG–PET–CT and poor for intraoperative examination for lymph node metastasis, highlighting that the overall accuracy of 18F-FDG–PET–CT (82.1%) was significantly higher than that of intraoperative examination (66.1%) (p = 0.002). Conclusions: In conclusion, 18F-FDG–PET–CT provides high accuracy in detecting primary tumors and superior predictive value for lymph node metastases compared to intraoperative examination, highlighting the importance of incorporating this imaging modality into the preoperative evaluation process to enhance diagnostic precision and inform treatment decisions.

Artificial Neural Network to Predict Curvature Light Shelf Design Related Daylighting Optimization on Office Spaces

Energy Optimization in building design field now has been revolutionized due to AI and machine learning applications. Leveraging daylight to reduce artificial lighting consumption holds promise for significant energy savings, yet the nonlinear nature of daylight patterns poses challenges in prediction and optimization. This study proposes a novel approach to automated light shelf design using machine learning algorithms, specifically artificial neural networks (ANNs) such as recurrent neural networks (RNN) by long short term memory (LSTM), to accelerate daylighting simulation and optimization processes. The methodology employed two distinct approaches: Firstly, we employed the theoretical-analytical approach to explore methods for utilizing machine learning in natural lighting and light shelf parameters. Second, the practical and applied method involved creating a predictive model for designing the light shelf using appropriate AI and ML techniques. This model is based on an office geometry model at the El Arish weather file in Egypt, four-dimensional training room models with three internal zones-oriented south. Rhinoceros and Grasshopper, two parametric simulation tools, are used to normalize and optimize light shelf parameters like geometry cross-section, curvature surface, width, height position, depth, tilt angle, and reflectance materials. Then, the Galapagos plug-in and Colibri2 are used for dataset creation and optimization. The results demonstrate that automated light shelf operation has a significant impact on internal daylighting quality. RNNs enable rapid prediction of optimization models, reducing time consumption in the early design phase. ML facilitates decision-making by generating evaluative criteria from user-selected design options. RNNs were classified as good and bad and used LSTM to enhance prediction accuracy for efficient illuminance values metric in zones 1 and 2. Challenges include increasing the simulation procedure's efficiency. The results of model accuracy reached 99%. Hence, future research should prioritize resolving the previously identified concerns. In conclusion, this study underscores the importance of ML-driven approaches in early design phases to optimize building energy consumption and pave the way for sustainable architectural practices.

An anti‐interference decision‐making method for communication waveform based on collaborative filtering

AbstractAiming at the problem of efficient and reliable transmission for communication system in complex electromagnetic environment, an anti‐interference decision‐making method for communication waveform based on collaborative filtering (CF) is proposed here. The required minimum signal‐to‐noise ratio to meet a specific bit error rate is adopted as a key indicator to evaluate the performance of certain waveform–channel combinations. The main challenge that is solved is to predict transmission performance ratings that cannot be obtained in practice. With CF of waveform features and interference features, the missing training data can be accurately predicted. The convergence speed and prediction accuracy of the proposed algorithm are verified by simulation, and the influence of different feature quantities and different data deficiency degrees on the stability and accuracy of the algorithm is discussed.

PREDICTING PATIENT OUTCOMES USING ONE-HOUR ADULT EARLY WARNING SCORE (AEWS)

Early Warning Scores (EWS) are widely utilized tools to predict patient outcomes, particularly in critical care settings and emergency departments (ED). However, while Adult Early Warning Scores (AEWS) have been employed for general patient outcome prediction, the specific utility of a one-hour AEWS in the ED has not been thoroughly explored. Accurate early prediction of patient disposition could enhance clinical decision-making, resource allocation, and patient safety. Objective: This study aims to evaluate the effectiveness of one-hour Adult Early Warning Scores (AEWS) in predicting patient disposition (discharge, floor admission, or ICU admission) in the emergency department. Methods: A prospective observational study was conducted on 227 patients aged 16 years and above who presented to the ED of Shifa International Hospital, Islamabad, from January 2024 to June 2024. Vital signs, including heart rate, respiratory rate, blood pressure, oxygen saturation, and temperature, were recorded at the one-hour mark post-admission, and the one-hour AEWS was calculated. Patient outcomes were categorized into three groups: discharge, admission to the general floor, or admission to the ICU. Logistic regression was used to determine the relationship between one-hour AEWS and patient disposition. Receiver Operating Characteristic (ROC) curve analysis was performed to assess the predictive power of the AEWS for determining patient outcomes. Results: There was a statistically significant correlation between the one-hour AEWS and patient disposition (p<0.001). The ROC curve analysis showed an Area Under the Curve (AUC) of 0.753, demonstrating good predictive accuracy. A cutoff AEWS value of 2.5 was identified, with patients scoring below this threshold being more likely to be discharged, while those scoring above 2.5 were more likely to require hospital admission or ICU care. The sensitivity and specificity of AEWS at this cutoff were 71% and 68%, respectively. Conclusion: The one-hour AEWS has proven to be a valuable tool in predicting patient disposition in the emergency department. Its ability to distinguish between patients who can be safely discharged and those requiring further care highlights its potential utility in improving patient triage, optimizing resource use, and enhancing clinical decision-making. Further multicenter studies are needed to validate these findings and assess the integration of AEWS into routine ED practice.

Enhancing Machine Learning Models Through PCA, SMOTE-ENN, and Stochastic Weighted Averaging

Predicting survival outcomes in critical accidents has been a focal point in machine learning research. This study addresses several limitations of existing methods, including insufficient management of data imbalance, lack of emphasis on hyperparameter tuning, and proneness to overfitting. Many existing models struggle to generalize effectively on imbalanced datasets or depend on default hyperparameter settings, resulting in biased predictions. By integrating Principal Component Analysis (PCA), hyperparameter optimization, and resampling methods, as well as combining Edited Nearest Neighbors (ENN) with the Synthetic Minority Oversampling Technique (SMOTE), the model significantly improves predictive accuracy and model generalization. An ensemble model combining seven machine learning algorithms—Logistic Regression, Support Vector Machine, KNN, Random Forest, XGBoost, LightGBM, and CatBoost—was applied to predict survival outcomes. Stochastic Weighted Averaging (SWA) was applied to mitigate overfitting and enhance generalization. The accuracy increased from 91.97% to 94.89% after SWA was applied in this specific scenario. The combination of PCA-based dimensionality reduction, hyperparameter tuning, and resampling techniques (ENN + SMOTE) ensured the model handled data imbalance and optimized predictive accuracy. The final model demonstrated excellent performance, with Area Under the Curve (AUC) and Average Precision (AP) values both reaching 0.98, indicating high accuracy and precision. These improvements were validated using the Titanic dataset in a binary classification problem of predicting passenger survival. The results emphasize that ensemble learning, enhanced by SWA, offers a powerful framework for handling imbalanced and complex datasets, providing significant advancements in predictive modeling accuracy. This study provides insights into how machine learning techniques can be effectively combined to solve classification challenges in real-world scenarios.

Integrating Graph Structures into Kernel Regression Models

Kernel methods are highly flexible and powerful tools for capturing complex, nonlinear relationships in data. In this paper, we propose a substantial extension of existing network-based regression models by integrating kernel methods with graph-theoretic constraints. Our approach builds upon the foundational work of Li et al. [1], who incorporated network cohesion into generalized linear models (GLMs). We extend their framework by introducing a kernelized regression model that allows for the modeling of nonlinear interactions while leveraging network data. This kernelized framework relaxes the linearity constraints of GLMs, making the model more versatile and capable of capturing complex patterns in high-dimensional spaces. We demonstrate the effectiveness of our approach using simulated and real-world datasets, such as the Teenage Friends and Lifestyle Study. Results show that our kernelized network regression model not only outperforms traditional linear and generalized linear models in predictive accuracy but also scales efficiently to larger datasets. Our work represents a significant advancement in the modeling of network-linked data, providing a robust, scalable, and interpretable framework that extends the application of kernel methods beyond their traditional constraints. Future directions include exploring more complex graph structures, such as weighted and directed graphs, and developing optimized algorithms for even larger datasets.

Short-Term Prediction Method for Gas Concentration in Poultry Houses Under Different Feeding Patterns

Ammonia (NH3) and carbon dioxide (CO2) are the main gases that affect indoor air quality and the health of the chicken flock. Currently, the environmental control strategy for poultry houses mainly relies on real-time temperature, resulting in lag and singleness. Indoor air quality can be improved by predicting the change in CO2 concentration and proposing an optimal control strategy. Combining the advantages of seasonal-trend decomposition using loess (STL), Granger causality (GC), long short-term memory (LSTM), and extreme gradient boosting (XGBoost), an ensemble method called the STL-GC-LSTM-XGBoost model is proposed. This model can set fast response prediction results at a lower cost and has strong generalization ability. The comparative analysis shows that the proposed STL-GC-LSTM-XGBoost model achieved high prediction accuracy, performance, and confidence in predicting CO2 levels under different environmental regulation modes and data volumes. However, its prediction accuracy for NH3 was slightly lower than that of the STL-GC-LSTM model. This may be due to the limited variability and regularity of the NH3 dataset, which likely increased model complexity and decreased predictive ability with the introduction of XGBoost. Nevertheless, in general, the proposed integrated model still provides a feasible approach for gas concentration prediction and health-related risk control in poultry houses.

Prognostic nomograms for young breast cancer: A retrospective study based on the SEER and METABRIC databases.

Young breast cancer (YBC) is a subset of breast cancer that is often more aggressive, but less is known about its prognosis. In this study, we aimed to generate nomograms to predict the overall survival (OS) and breast cancer-specific survival (BCSS) of YBC patients. Data of women diagnosed with YBC between 2010 and 2020 were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. The patients were randomly allocated into a training cohort (n = 15,227) and internal validation cohort (n = 6,526) at a 7:3 ratio. With the Cox regression models, significant prognostic factors were identified and used to construct 3-, 5-, and 10-year nomograms of OS and BCSS. Data from the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) database were used as an external validation cohort (n = 90). We constructed nomograms incorporating 10 prognostic factors for OS and BCSS. These nomograms demonstrated strong predictive accuracy for OS and BCSS in the training cohort, with C-indexes of 0.806 and 0.813, respectively. The calibration curves verified that the nomograms have good prediction accuracy. Decision curve analysis demonstrated their practical clinical value for predicting YBC patient survival rates. Additionally, we provided dynamic nomograms to improve the operability of the results. The risk stratification ability assessment also showed that the OS and BCSS rates of the low-risk group were significantly better than those of the high-risk group. Here, we generated and validated more comprehensive and accurate OS and BCSS nomograms than models previously developed for YBC. These nomograms can help clinicians evaluate patient prognosis and make clinical decisions.

Alchemical insights into approximately quadratic energies of iso-electronic atoms.

Accurate quantum mechanics based predictions of property trends are so important for material design and discovery that even inexpensive approximate methods are valuable. We use the alchemical integral transform to study multi-electron atoms and to gain a better understanding of the approximately quadratic behavior of energy differences between iso-electronic atoms in their nuclear charges. Based on this, we arrive at the following simple analytical estimate of energy differences between any two iso-electronic atoms, ΔE≈-(1+2γNe-1)ΔZZ̄. Here, γ ≈ 0.3766 ± 0.0020 Ha corresponds to an empirical constant, and Ne, ΔZ, and Z̄, respectively, to electron number, nuclear charge difference, and average. We compare the formula's predictive accuracy using experimental numbers and non-relativistic, numerical results obtained via density functional theory (pbe0) for the entire periodic table up to Radon. A detailed discussion of the atomic helium-series is included.

Advanced hybrid neural network techniques for minimizing gas turbine emissions

Purpose Emissions have significant environmental impacts. Hence, minimizing emissions is essential. This study aims to use a hybrid neural network model to predict carbon monoxide (CO) and nitrogen oxide (NOx) emissions from gas turbines (GTs) to enhance emission prediction for GTs in predictive emissions monitoring systems (PEMS). Design/methodology/approach The hybrid model architecture combines convolutional neural networks (CNN) and bidirectional long-short-term memory (Bi-LSTM) networks called CNN-BiLSTM with modified extrinsic attention regression. Over five years, data from a GT power plant was uploaded to Google Colab, split into training and testing sets (80:20), and evaluated using test matrices. The model’s performance was benchmarked against state-of-the-art emissions prediction methodologies. Findings The model showed promising results for GT CO and NOx emissions. CO predictions had a slight underestimation bias of −0.01, with root mean-squared error (RMSE) of 0.064, mean absolute error (MAE) of 0.04 and R2 of 0.82. NOx predictions had an RMSE of 0.051, MAE of 0.036, R2 of 0.887 and a slight overestimation bias of +0.01. Research limitations/implications While the model demonstrates relative accuracy in CO emission predictions, there is potential for further improvement in future research. Practical implications Implementing the model in real-time PEMS and establishing a continuous feedback loop will ensure accuracy in real-world applications, enhance GT functioning and reduce emissions, fuel consumption and running costs. Social implications Accurate GT emissions predictions support stricter emission standards, promote sustainable development goals and ensure a healthier societal environment. Originality/value This paper presents a novel approach that integrates CNN and Bi-LSTM networks. It considers both spatial and temporal data to mitigate previous prediction shortcomings.

Crystal Structure Prediction Using Generative Adversarial Network with Data-Driven Latent Space Fusion Strategy.

Crystal structure prediction (CSP) is an important field of material design. Herein, we propose a novel generative adversarial network model, guided by a data-driven approach and incorporating the real physical structure of crystals, to address the complexity of high-dimensional data and improve prediction accuracy in materials science. The model, termed GAN-DDLSF, introduces a novel sampling method called data-driven latent space fusion (DDLSF), which aims to optimize the latent space of generative adversarial networks (GANs) by combining the statistical properties of real data with a standard Gaussian distribution, effectively mitigating the "mode collapse" problem prevalent in GANs. Our approach introduces a more refined generation mechanism specifically for binary crystal structures such as gallium nitride (GaN). By optimizing for the specific crystallographic features of GaN while maintaining structural rationality, we achieve higher precision and efficiency in predicting and designing structures for this particular material system. The model generates 9321 GaN binary crystal structures, with 16.59% reaching a stable state and 24.21% found to be metastable. These results can significantly enhance the accuracy of crystal structure predictions and provide valuable insights into the potential of the GAN-DDLSF approach for the discovery and design of binary, ternary, and multinary materials, offering new perspectives and methods for materials science research and applications.

Predicting Movie Box Office Based on Machine Learning, Deep Learning, and Statistical Methods

Abstract. The global film industry has been proved to impose a significant impact on both culture and the economy, with box office revenue serving as a crucial indicator of a film's commercial success. This study utilizes data from the Kaggle "TMDB Box Office Prediction" competition, encompassing 3,000 films released between 1990 and 2018, to predict movie box office revenue using Random Forest, XGBoost algorithms, and deep learning models such as Bidirectional Long Short-Term Memory (Bidirectional LSTM) and Simple Recurrent Neural Network (SimpleRNN). The goal is to develop a model that accurately predicts movie box office. By comprehensively considering multiple factors such as budget, popularity and film characteristics, this study not only significantly improves the accuracy of box office prediction, but also provides a scientific basis for the formulation of film market strategies. The results demonstrate that the Bidirectional LSTM excels in handling complex time-series data, showing strong trend-capturing capabilities, while XGBoost exhibits greater robustness in dealing with complex data and outliers. These findings can not only provide guidance for making more effective strategies on film production and distribution, but also provide new directions for future research, such as delving into the impact of social media on box office and developing more sophisticated predictive models to adapt to changing market dynamics.

Can we skip invasive biopsy of sentinel lymph nodes? A preliminary investigation to predict sentinel lymph node status using PET/CT-based radiomics

BackgroundSentinel lymph node (SLN) biopsy (SLNB) is considered the gold standard for detecting SLN metastases in patients with invasive ductal breast cancer (IDC). However, SLNB is invasive and associated with several complications. Thus, this study aimed to evaluate the diagnostic performance of a non-invasive radiomics analysis utilizing 2-deoxy-2-[18F]fluoro-d-glucose positron emission tomography/computed tomography (18F-FDG-PET/CT) for assessing SLN metastasis in IDC patients.MethodsThis retrospective study included 132 patients with biopsy-confirmed IDC, who underwent 18F-FDG PET/CT scans prior to mastectomy or breast-conserving surgery with SLNB. Tumor resection or SLNB was conducted within one-week post-scan. Clinical data and metabolic parameters were analyzed to identify independent SLN metastasis predictors. Radiomic features were extracted from each PET volume of interest (VOI) and CT-VOI. Feature selection involved univariate and multivariate logistic regression analysis, and the least absolute shrinkage and selection operator (LASSO) method. Three models were developed to predict SLN status using the random forest (RF), decision tree (DT), and k-Nearest Neighbors (KNN) classifiers. Model performance was assessed using the area under the receiver operating characteristic curve (AUC).ResultsThe study included 91 cases (32 SLN-positive and 59 SLN-negative patients) in the training cohort and 41 cases (29 SLN-positive and 12 SLN-negative patients) in the validation cohort. Multivariate logistic regression analysis identified Ki 67 and TLG as independent predictors of SLN status. Five PET-derived features, three CT-derived features, and two clinical variables were selected for model development. The AUC values of the RF, KNN, and DT models for the training cohort were 0.887, 0.849, and 0.824, respectively, and for the validation cohort were 0.856, 0.830, and 0.819, respectively. The RF model demonstrated the highest accuracy for the preoperative prediction of SLN metastasis in IDC patients.ConclusionThe PET-CT radiomics approach may offer robust and non-invasive predictors for SLN status in IDC patients, potentially aiding in the planning of personalized treatment strategies for IDC patients.

Identification and validation of M2 macrophage-related gene signature as a novel prognostic model for head and neck squamous cell carcinoma

Head and neck squamous cell carcinoma (HNSCC) is a highly heterogeneous tumor. Commonly used tumor staging don’t sufficiently and accurately assess the prognosis of HNSCC patients, resulting in a lack of guidance for clinical treatment decisions. M2 macrophage infiltration has been shown to be strongly associated with the tumor prognosis. In this study, we used the Cancer Genome Atlas (TCGA) data to screen for genes co-expressed with M2 macrophages in HNSCC. We used univariate Cox regression to screen out the genes associated with HNSCC prognosis, and constructed a HNSCC prognosis model by Lasso regression analysis. The results confirmed that the model had good predictive value and accuracy for the prognosis of HNSCC patients by survival analysis, ROC curve and nomogram. We divided the HNSCC samples into high-risk and low-risk groups according to the risk score, and the results showed that patients in the high-risk group were more prone to genetic mutations and had a higher tumor mutational burden. In addition, there were significant differences between risk groups in terms of immune cell infiltration and drug sensitivity. The HNSCC prognostic model established in this study may provide guidance for clinical therapeutic decision-making and provide a theoretical foundation for the development of new immunotherapy methods.