Improve Prediction Accuracy Research Articles

In a prospective, multicenter study, the 31-GEP identified patients at increased risk of tumor recurrence and added significant prognostic value to AJCC staging

Cutaneous melanoma (CM) guidelines base management decisions on a patient’s American Joint Committee on Cancer (AJCC) tumor stage. However, limitations in staging accuracy suggest additional tools could improve risk-aligned patient management decisions. The 31-gene expression profile (GEP) test identifies patients with CM with low (Class 1A), intermediate (Class 1B/2A), or high (Class 2B) risk for sentinel lymph node (SLN) positivity, recurrence, metastasis, and death. In this multicenter, prospective study, we validated the 31-GEP for risk of recurrence and demonstrated the added value of 31-GEP to AJCC staging. Patients were included in the prospective CONNECTION study if they were tested with the 31-GEP from 2018 to the present (n=876). Survival was estimated using Kaplan-Meier analysis and 31-GEP stratification tested with the log-rank test. Cox regression was performed to identify predictors of recurrence. ANOVA was used to compare Cox models for the most accurate recurrence prediction. Patients with a Class 1A result had significantly higher 3-year recurrence-free survival than those with a Class 1B/2A or Class 2B result (98.5% vs. 80.8% vs. 63.0%, p<0.001). The 31-GEP had higher sensitivity (75.0% vs. 37.5%) and negative predictive value (98.6% vs. 96.9%) than AJCC staging. Multivariable analysis demonstrated that Class 1B/2A (hazard ratio, HR=3.12, p=0.037) and Class 2B (HR=5.91, p=0.002) were significant predictors of recurrence in addition to stage IB (HR=4.02, p=0.02), IIA (HR=6.06, p=0.006), IIC (HR=17.14, p<0.001), and III (HR=8.84, p<0.001). Stage IIB (HR=4.63, p=0.057) was not significant. Comparing a staging-only model to a 31-GEP+staging model showed that adding 31-GEP to staging significantly improved prediction accuracy over staging alone (ANOVA: c2=10.58, p=0.005). In this prospective study, the 31-GEP stratified risk of recurrence, was a significant predictor of recurrence, and added significant predictive value to AJCC staging. The 31-GEP identifies patients at high risk of recurrence who should be managed more intensely, and adding 31-GEP to staging allows better risk-aligned care decisions, which can lead to improved patient outcomes.

Integrating Multi-Source Remote Sensing Data for Forest Fire Risk Assessment

Forest fires are a frequent and destructive phenomenon in Southwestern China, posing significant threats to ecological systems and human lives and property. In response to the growing need for effective forest fire prevention, this study introduces an innovative method for predicting and assessing forest fire risk. By integrating multi-source data, including optical and microwave remote sensing, meteorological, topographic, and human activity data, the approach enhances the sensitivity of risk models to vegetation water content and other critical factors. The vegetation water content is derived from both Vegetation Optical Depth and optical remote sensing data, allowing for a more accurate assessment of changes in vegetation moisture that influence fire risk. A time series prediction model, incorporating attention mechanisms, is used to assess the probability of fire occurrence. Additionally, the method includes fire spread simulations based on Cellular Automaton and Monte Carlo approaches to evaluate potential burn areas. This combined approach can provide a comprehensive fire risk assessment using the probability of both fire occurrence and potential fire spread. Experimental results show that the integration of microwave data and attention mechanisms improves prediction accuracy by 2.8%. This method offers valuable insights for forest fire management, aiding in targeted prevention strategies and resource allocation.

Predicting Chronic Liver Disease and Jaundice Detection an Integrated Approach Using Statistical Feature Extraction and Machine Learning Algorithms

An important health concern with chronic liver disease is early identification, which is essential for management and therapy. This work suggests an integrated method to identify tattoo-induced jaundice and forecast chronic liver disease by combining statistical feature extraction with machine learning techniques. First, we use statistical techniques based on projections to extract pertinent aspects from patient data, such as test results and clinical markers. We then use Artificial Neural Networks (ANN), KNN, and Naive Bayes to categorize individuals according to the probability that they have chronic liver illness and to pinpoint jaundice episodes associated with tattooing. The KNN technique offers interpretability, managing categorical data is made simple by Naive Bayes, and complicated patterns are captured by ANN using layers of neural networks. These models' performance is assessed using the following metrics: F1 score, recall, accuracy, and precision. Our research aims to improve prediction accuracy and offer practical advice for early diagnosis and individualized treatment plans. By utilizing advanced data analysis and machine learning instruments, the integrated strategy shows promise in enhancing healthcare outcomes.

Prediction of automotive response using supervised machine learning in antilock braking systems and comparison with different models for improved vehicle safety

Abstract Previous research on predicting automotive response in antilock braking systems faced several common drawbacks. Limited availability of high-quality datasets and computational constraints hindered the models' ability to generalize and perform effectively in real-time. Additionally, integrating these models into existing vehicle systems is challenging, often requiring extensive calibration and testing to ensure reliability and safety. This study focuses on enhancing automotive safety through the integration of machine learning with advanced braking systems. An antilock braking system model is developed using MATLAB, accounting for key parameters such as speed, mass, wheel radius, and moment of inertia. Various probability ranges are simulated to evaluate the system's real-time response in dynamic environments. A supervised machine learning approach is applied, with lasso regression used for model validation. Braking response was evaluated at three speeds: 25 km/h, 45 km/h, and 65 km/h. To assess model accuracy, error analysis was conducted using metrics such as mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE), and mean squared error (MSE). Results showed a significant improvement in prediction accuracy, with MAPE reduced to 3.2%, MAE to 0.15 seconds, RMSE to 0.25 seconds, and MSE to 0.06 seconds.A comparative analysis is done using the Python Jupyter Framework, further validating the findings. The machine learning model successfully forecasts braking response times, and validates its prediction against random datasets.

ENSO predictive analytics based on layered rendering

AbstractEl Niño-Southern Oscillation (ENSO) is a periodic climate phenomenon in the equatorial Pacific that significantly influences global climate patterns. Accurate prediction and monitoring of ENSO events are essential for meteorological agencies and governmental institutions. This study introduces a content-guided attention module within a convolutional neural network to improve prediction accuracy. This module models inter-channel relationships and enhances information interaction by integrating channel and spatial attention weights. These advancements substantially improve prediction accuracy and help overcome the spring prediction barrier in ENSO forecasting. The research emphasizes global feature modeling and proposes a novel content-guided ENSO prediction model. It also includes an ocean data generation model utilizing global attention. Furthermore, a layered rendering technique is employed to invert ocean data, facilitating detailed analysis and contributing to the development of an ocean synthetic dataset.

Impact of nuclear level density and radiative strength function models on the S factors of (α,γ) reactions relevant to p-nuclei production

Abstract 
Abstract. The astrophysical S factors of (α,γ) reactions are crucial inputs to nuclear reaction network simulations for studying p-nuclei production. Previous work revealed considerable discrepancies between theoretical and experimental S factors using different nuclear level densities (NLD) and radiative strength functions (RSF). Accordingly, in this article, we studied the influence of six RSF and four NLD models on the astrophysical S factors of (α, γ) reactions on 16 target nuclei. The microscopic NLD and RSF models under investigation are based on the Hartree-Fock + Bardeen-Cooper- Schrieffer (HFBCS) and Hartree-Fock-Bogulubov (HFB) models. The obtained results have shown that within the α-OMP proposed in Ref. [1], RSF and NLD models used in the S factor computation yield root mean square (rms) deviations of less than 0.750, and phenomenological NLD and RSF models predict astrophysical S better than microscopic ones in all cases considered. More research is needed on NLD and RSF models to improve prediction accuracy and reduce deviations in calculations of the S factors of radiative α captures.

Accuracy of adult height predictions in patients with axial leg deviations using the Modified and the Abbreviated Modified Fels Knee System.

The accurate estimation of residual growth is crucial for the appropriate timing of growth-guiding surgery in patients with axial leg deviations. Skeletal age methods such as the Modified and the Abbreviated Modified Fels Knee System were developed on historical patient cohorts and the applicability to the modern pediatric population with axial leg deviation has not yet been evaluated. Are both final adult height prediction methods (the Modified Fels Knee System (FKS) and the Abbreviated Modified Fels Knee System (aFKS)) accurate to determine SA and the final adult height on long leg radiographs in patients with axial leg deviations?Which multiplier table shows highest association between predicted and true final adult body height?Do FKS- and aFKS- skeletal age determination methods improve final adult body height prediction accuracy compared to the simple use of chronological age? A single center, retrospective study of 31 patients who underwent temporary hemiepiphysiodesis due to axial leg deviations in the frontal plane between 2018 and 2020 was conducted. Skeletal age at the time of surgery was determined on an anterior-posterior long leg X-ray using FKS and aFKS. Adult height predictions were calculated using three different multiplier tables (Paley et al., Sanders-Greulich and Pyle (SGP), Sanders-Peak Height Velocity (PHV)). The accuracy of adult height prediction was determined by comparing the mean differences and mean absolute differences between predicted and true adult height. All adult height predictions overestimated the true adult height. The final height prediction using aFKS and the SGP multiplier showed the lowest overestimation (mean 3.2 cm, SD 5.5 cm). The PHV multiplier table showed the highest correlation between predicted and true adult height (FHPRE_FKS_PHV: r = 0.913, p < 0.001 and FHPRE_aFKS_PHV: r = 0.862, p < 0.001). The simple use of chronological age at the time of surgical intervention (CASI) with the Paley multiplier table showed the highest median delta absolute values and lowest correlations with true adult height (median 7.4 cm, 25%-75% percentile: 3.5-10.0 cm, r = 0.838, p < 0.001). Nevertheless, no significant differences in delta absolute values between various adult height predictions methods could be shown. Overall, the results of the present retrospective cohort study show that there was no significant improvement in final height prediction accuracy when using the FKS or the aFKS method compared to the simple use of chronological age. One reason could be that patients with varus/valgus malalignment have specific growth characteristics that are not accounted for in multiplier tables or the FKS and aFKS method. Since there is no significant difference in prediction accuracy between the methods, the choice of method may depend on other factors, such as clinical preference or availability of resources. However, due to the small sample size, the study cannot definitively rule out potential differences between the prediction methods, and larger studies are required to validate these findings.

The Role of AI in Personalizing Insurance Policies

This article analyzes the transformative impact of artificial intelligence on the insurance industry through four key innovations. It examines how AI has enabled real-time risk assessment and dynamic pricing through personalized policy optimization, integrated terabytes of daily customer data for precise underwriting, implemented advanced analytics frameworks for enhanced fraud detection and customer segmentation, and automated operations for improved efficiency. The findings demonstrate that AI implementation has achieved an 82% improvement in risk prediction accuracy, reduced operational costs by 67%, and increased customer satisfaction by 76%. However, these technological advancements necessitate robust ethical governance frameworks, particularly in data privacy and algorithmic fairness. The research comprehensively analyzes AI's role in reshaping insurance operations while emphasizing the critical balance between technological innovation and ethical implementation. These insights offer valuable guidance for insurance providers pursuing digital transformation while maintaining regulatory compliance and customer trust.

Explainable early detection of Alzheimer's disease using ROIs and an ensemble of 138 3D vision transformers.

Early detection and accurate diagnosis of brain morphological abnormalities are essential for the effective management and treatment of Alzheimer's disease (AD) and mild cognitive impairment (MCI). Structural magnetic resonance imaging (MRI) is a powerful support tool to aid in disease diagnosis and prediction. In this research study, we present an innovative approach to predict Alzheimer's disease (AD) and mild cognitive impairment (MCI) using MRI data, which integrates regional interest (ROI)-based methodology and deep learning within a comprehensible framework. The proposed method involves dividing the brain into 138 predetermined sections based on anatomical information. Next, we apply three-dimensional vision transformers (3D-ViTs) to each ROI individually, harnessing the power of deep learning. To improve prediction accuracy, we employ a deep belief network (DBN) as an ensemble learning model. Evaluating our approach on the baseline structural MRI dataset obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort, and comparing it against five other competing models, we demonstrate its performance across four binary classification tasks and a three-class classification test (AD vs MCI vs CN (Cognitively Normal)). The proposed system outperforms existing models and provides interpretable insights into the brain regions that significantly contribute to solving each classification problem. Our findings align with the existing body of literature and hold promise for guiding future research directions in this domain.

Enhancing Fine Aerosol Simulations in the Remote Atmosphere with Machine Learning

Global aerosol models often underestimate the mass concentration of aerosols in the remote troposphere, as evidenced by aircraft measurements. This study leveraged data from the NASA Atmospheric Tomography Mission (ATom), which provides remote aerosol concentrations, to refine algorithms for simulating these concentrations. Using the GEOS-Chem model, we simulate five fine aerosol types and enhance the simulation results using five machine-learning algorithms: Random Forest, XGBoost, SVM, KNN, and LightGBM, and compare the performance of these algorithms. Additionally, we evaluate the refinement effect of algorithms based on decision trees on a validation dataset. The results demonstrate that GEOS-Chem generally underestimated aerosol mass concentration. Among the tested algorithms, algorithms based on decision trees, particularly the Random Forest algorithm and the LightGBM algorithm, exhibited a superior performance, significantly improving prediction accuracy and computational efficiency in both the training and testing phases, as well as on the validation dataset.

Beyond xG: A Dual Prediction Model for Analyzing Player Performance Through Expected and Actual Goals in European Soccer Leagues

Soccer is evolving into a science rather than just a sport, driven by intense competition between professional teams. This transformation requires efforts beyond physical training, including strategic planning, data analysis, and advanced metrics. Coaches and teams increasingly use sophisticated methods and data-driven insights to enhance decision-making. Analyzing team performance is crucial to prepare players and coaches, enabling targeted training and strategic adjustments. Expected goals (xG) analysis plays a key role in assessing team and individual player performance, providing nuanced insights into on-field actions and opportunities. This approach allows coaches to optimize tactics and lineup choices beyond traditional scorelines. However, relying solely on xG might not provide a full picture of player performance, as a higher xG does not always translate into more goals due to the intricacies and variabilities of in-game situations. This paper seeks to refine performance assessments by incorporating predictions for both expected goals (xG) and actual goals (aG). Using this new model, we consider a wider variety of factors to provide a more comprehensive evaluation of players and teams. Another major focus of our study is to present a method for selecting and categorizing players based on their predicted xG and aG performance. Additionally, this paper discusses expected goals and actual goals for each individual game; consequently, we use expected goals per game (xGg) and actual goals per game (aGg) to reflect them. Moreover, we employ regression machine learning models, particularly ridge regression, which demonstrates strong performance in forecasting xGg and aGg, outperforming other models in our comparative assessment. Ridge regression’s ability to handle overlapping and correlated variables makes it an ideal choice for our analysis. This approach improves prediction accuracy and provides actionable insights for coaches and analysts to optimize team performance. By using constructed features from various methods in the dataset, we improve our model’s performance by as much as 12%. These features offer a more detailed understanding of player performance in specific leagues and roles, improving the model’s accuracy from 83% to nearly 95%, as indicated by the R-squared metric. Furthermore, our research introduces a player selection methodology based on their predicted xG and aG, as determined by our proposed model. According to our model’s classification, we categorize top players into two groups: efficient scorers and consistent performers. These precise forecasts can guide strategic decisions, player selection, and training approaches, ultimately enhancing team performance and success.

Abstract 4139199: Quantifying the Burden of High Polygenic Risk for Cardiometabolic Disease in a US-based Healthcare System Biobank

Background: Healthcare systems are increasingly collecting genotype data on patients. Polygenic risk scores (PRS), which quantify inherited risk of a given disease, have the potential to leverage this data to identify high risk individuals. While PRS for single traits have often been evaluated, the same data can be used to calculate PRSs across traits and evaluate the overall burden of high cardiometabolic polygenic risk using a single test. Methods: We examined the association of cardiometabolic PRS from the Polygenic Score Catalog among 236,393 All of Us (AoU) participants for 6 target traits of interest, using all available PRS for coronary artery disease (CAD; 57 PRS), atrial fibrillation (AF; 30 PRS), heart failure (HF; 9 PRS), type 2 diabetes mellitus (T2DM; 133 PRS), venous thromboembolism (VTE; 9 PRS), and thoracic aortic aneurysm (TAA; 2 PRS). PRSMix is a tool that incorporates information across several PRS for a given trait to improve prediction accuracy for a target population. We generated a PRSMix for each trait and externally benchmarked its performance against individual PRS in the Mass General Brigham Biobank (MGBB). Phenotypes were ascertained using hospital diagnosis and procedural codes. Logistic regression was performed, adjusting for age, sex, and the first 10 principal components of inferred genetic similarity. Results: Of the 53,306 genotyped MGBB participants, 55.6% are female, mean enrollment age is 53 ± 17 years. Each trait-specific PRSMix demonstrated generally stronger associations with the target trait compared to any individual contributing score. This included trait-specific PRSMix associations (OR/SD, [95%CI]) of 2.07 [1.99-2.15] for CAD, 1.88 [1.82-1.95] for AF, 1.47 [1.43-1.51] for HF, 2.07 [2.00-2.14] for T2DM, 1.43 [1.39-1.47] for VTE, and 1.40 [1.34-1.46] for TAA. Findings were consistent across inferred genetically similar ancestry groups, with stronger PRSMix associations for CAD detected in the EUR group (2.14 [2.05-2.22]) compared to the AFR group (1.43 [1.21-1.70]). Approximately 37% of people in MGBB have 3-fold greater risk of at least one cardiometabolic disease, with 22% at risk for CAD, 14% for T2DM, 13% for Afib, 3% for VTE, 2% for HF and &lt;1% for TAA. Conclusion: We developed PRSMix scores for cardiometabolic traits in AoU and validated them in MGBB. We identified 37% of biobank participants with at least 3-fold greater disease risk associated with high polygenic scores for at least one cardiometabolic outcome.

Improving Trauma Surgeons Prospective Estimation of the Injury Severity Score.

Injury Severity Score (ISS) as a prospective predictive variable is limited, as it is scored post-discharge by registrars. We followed a phase 1 pilot investigation of the feasibility of prospective ISS estimation (eISS) by trauma surgeons within 1 day of admission with an investigation of the impact of a simple educational aid on the accuracy of these estimations. Eleven surgeons evaluated 178 patients in phase 2. With the educational aid, ISS concordance improved from 74.6% to 85.1% for non-severe (abstracted ISS, aISS <16) injuries and from 78.8% to 83.1% for severe (aISS ≥16) injuries; weighted k improved from 0.53 to 0.72. Abbreviated Injury Scale (AIS) concordance similarly improved in five of seven body regions. The ability to prospectively document ISS has important clinical and research implications. There remains opportunity to refine educational aides and harness the EHR to further improve prediction accuracy and facilitate adoption in standard clinical workflows.

Revolutionizing Cardio Vascular Disease Diagnosis Through Lasso Regression Model

Cardiovascular diseases (CVDs) are among the most prevalent and fatal health conditions globally, necessitating early and accurate diagnosis to mitigate risk and enhance treatment outcomes. Traditional diagnostic methods often rely on a combination of clinical assessments and static risk models, which can be constrained by their inability to handle the complexity and interrelationships of multiple risk factors. In this research, we propose a novel approach to revolutionizing cardiovascular disease diagnosis through the application of the Lasso (Least Absolute Shrinkage and Selection Operator) regression model, a powerful machine learning technique for feature selection and predictive modeling. The Lasso regression model is particularly advantageous for high-dimensional medical datasets, where multiple clinical features may be correlated. By applying Lasso, we aim to address two critical challenges in cardiovascular disease prediction: identifying the most relevant predictors from large and complex datasets and reducing model over-fitting, which is common when working with a large number of co-variates. Our results demonstrated that the Lasso model significantly improves prediction accuracy when compared to traditional logistic regression and other machine learning models. Lasso regression has the potential to revolutionize cardiovascular disease diagnosis by providing a data-driven, efficient, and interpretable solution that bridges complex medical datasets with practical clinical decision-making. Keywords: Cardio vascular diseases (CVD), Machine learning models, Losso regression model.

Global Spatial Projections of Forest Soil Respiration and Associated Uncertainties

The accurate prediction of global forest soil respiration (Rs) is critical for climate change research. Rs consists of autotrophic (Ra) and heterotrophic (Rh) respiration, which respond differently to environmental factors. Predicting Rs as a single flux can be biased; therefore, Ra and Rh should be predicted separately to improve prediction accuracy. In this study, we used the SRDB_V5 database and the random forest model to analyze the uncertainty in predicting Rs using a single global model (SGM) and Ra/Rh using a specific categorical model (SCM) and predicted the spatial dynamics of the distribution pattern of forest Ra, Rh, and Rs in the future under the two different climate patterns. The results show that Rs is higher under tropical and inland climatic conditions, while Rh fluctuates less than Ra and Rs. In addition, the SCM predictions better capture key environmental factors and are more consistent with actual data. In the SSP585 (high emissions) scenario, Rs is projected to increase by 19.59 percent, while in the SSP126 (low emissions) scenario, Rs increases by only 3.76 percent over 80 years, which underlines the need for SCM in future projections.

Leveraging artificial intelligence in economics and finance: Enhancing decision-making and market efficiency

Abstract. Artificial Intelligence (AI) has revolutionized the fields of economics and finance by providing advanced tools for decision-making, predictive analysis, and market efficiency. This paper examines the integration of AI technologies such as machine learning and natural language processing with mathematical models, specifically ARIMA for economic forecasting, Black-Scholes for option pricing, and logistic regression for credit risk assessment. By enhancing these models with AI, we demonstrate significant improvements in prediction accuracy and decision-making capabilities. Case studies illustrate a 15% improvement in GDP growth prediction accuracy, a 20% reduction in option pricing errors, and a 20% decrease in credit default rates. The paper also discusses the future prospects of AI, including advancements in quantum computing and ethical considerations like data privacy and algorithmic bias. Implementation challenges such as high costs and data integration issues are addressed, providing a comprehensive roadmap for organizations to effectively leverage AI. This study underscores the transformative potential of AI in shaping the future of economic and financial landscapes, driving innovation and operational efficiency.

Monitoring soil salinity in coastal wetlands with Sentinel-2 MSI data: Combining fractional-order derivatives and stacked machine learning models

Monitoring soil salinity is essential for understanding the behavior of coastal wetland ecosystems and implementing effective management strategies. Despite the advantages of the Multi-Spectral Instrument (MSI) data for large-scale, high-frequency soil salinity monitoring, challenges remain in data preprocessing and model construction. We combined fractional-order derivative (FOD) technology with stacked machine learning models to monitor and map soil salinity using Sentinel-2 MSI data. The base models included Elastic Net Regression, Support Vector Regression, Artificial Neural Network, Extreme Gradient Boosting, and Random Forest, with Non-Negative Least Squares as the meta-learner. The results showed that low-order FOD enhanced image gradients and maintained a high peak signal-to-noise ratio, thereby improving the correlation with soil salinity. Notably, the 0.25-order FOD showed the best performance, increasing the correlation coefficient with soil salinity by up to 13 %. The stacked machine learning models effectively combined the strengths of different base models, enhancing prediction accuracy by more than 8 % compared to single models. Furthermore, combining stacked models with FOD further improved prediction accuracy, with an increase in R² of up to 9 %. The combination of 0.25-order FOD and the stacked machine learning model achieved the best performance (R² = 0.82, RMSE = 10.19 ppt, RPD = 2.38, RPIQ = 4.69). This approach provides a reference for rapid and effective large-scale digital mapping of soil salinity in coastal wetlands.

Graph-based machine learning model for weight prediction in protein–protein networks

Proteins interact with each other in complex ways to perform significant biological functions. These interactions, known as protein–protein interactions (PPIs), can be depicted as a graph where proteins are nodes and their interactions are edges. The development of high-throughput experimental technologies allows for the generation of numerous data which permits increasing the sophistication of PPI models. However, despite significant progress, current PPI networks remain incomplete. Discovering missing interactions through experimental techniques can be costly, time-consuming, and challenging. Therefore, computational approaches have emerged as valuable tools for predicting missing interactions. In PPI networks, a graph is usually used to model the interactions between proteins. An edge between two proteins indicates a known interaction, while the absence of an edge means the interaction is not known or missed. However, this binary representation overlooks the reliability of known interactions when predicting new ones. To address this challenge, we propose a novel approach for link prediction in weighted protein–protein networks, where interaction weights denote confidence scores. By leveraging data from the yeast Saccharomyces cerevisiae obtained from the STRING database, we introduce a new model that combines similarity-based algorithms and aggregated confidence score weights for accurate link prediction purposes. Our model significantly improves prediction accuracy, surpassing traditional approaches in terms of Mean Absolute Error, Mean Relative Absolute Error, and Root Mean Square Error. Our proposed approach holds the potential for improved accuracy in predicting PPIs, which is crucial for better understanding the underlying biological processes.

Enhancing Lung Cancer Screening with Bidirectional LSTM and GRU Models

Abstract. This study aims to enhance lung cancer patient screening by developing and evaluating bidirectional Long Short-Term Memory (LSTM) and bidirectional Gated Recurrent Unit (GRU) models using the Lung Cancer dataset from Kaggle. The dataset includes 16 features related to patient symptoms and lung cancer status, providing a broad spectrum of symptoms to improve model accuracy. The research advances Artificial Intelligence (AI)-driven healthcare by integrating these sophisticated machine learning techniques into diagnostic processes. The methodology involves four main steps: preprocessing the dataset for model compatibility, defining the model architecture with bidirectional LSTM and GRU layers and evaluating its performance. The results show an overall accuracy of 52.17%, with accuracy, recall, and F1 scores for both cancerous and non-cancerous categories around 50%. Despite the hybrid model's average performance, it establishes a basis for future enhancements. Optimizing model parameters and exploring additional other techniques to improve prediction accuracy and clinical applicability will be done in the future.

Forecasts of Video Game Sales based on the ARIMA Model

Abstract. With the rapid development of the digital age, video games have become an important component of the cultural industry, and their sales forecasting has become a focus of industry attention. This article aims to predict the sales of video games based on the ARIMA model and explore effective methods to improve prediction accuracy. Through in-depth research, this article found that the ARIMA model performs well in capturing the time series characteristics of sales data and can accurately predict future sales trends. The ARIMA model provides a systematic and scientific method for predicting the future market performance of video games by comprehensively considering the trends, seasonality, and random changes in historical sales data. This research achievement not only provides strong decision support for game developers, publishers, and platform operators but also promotes the optimization of resource allocation and market risk avoidance in the video games industry, which is of great significance for promoting the healthy and sustainable development of the industry.