Classical Prediction Models Research Articles

Predicting cytogenetic risk in multiple myeloma using conventional whole-body MRI, spinal dynamic contrast-enhanced MRI, and spinal diffusion-weighted imaging

ObjectivesCytogenetic abnormalities are predictors of poor prognosis in multiple myeloma (MM). This paper aims to build and validate a multiparametric conventional and functional whole-body MRI-based prediction model for cytogenetic risk classification in newly diagnosed MM.MethodsPatients with newly diagnosed MM who underwent multiparametric conventional whole-body MRI, spinal dynamic contrast-enhanced (DCE-)MRI, spinal diffusion-weighted MRI (DWI) and had genetic analysis were retrospectively included (2011–2020/Ghent University Hospital/Belgium). Patients were stratified into standard versus intermediate/high cytogenetic risk groups. After segmentation, 303 MRI features were extracted. Univariate and model-based methods were evaluated for feature and model selection. Testing was performed using receiver operating characteristic (ROC) and precision-recall curves. Models comparing the performance for genetic risk classification of the entire MRI protocol and of all MRI sequences separately were evaluated, including all features. Four final models, including only the top three most predictive features, were evaluated.ResultsThirty-one patients were enrolled (mean age 66 ± 7 years, 15 men, 13 intermediate-/high-risk genetics). None of the univariate models and none of the models with all features included achieved good performance. The best performing model with only the three most predictive features and including all MRI sequences reached a ROC-area-under-the-curve of 0.80 and precision-recall-area-under-the-curve of 0.79. The highest statistical performance was reached when all three MRI sequences were combined (conventional whole-body MRI + DCE-MRI + DWI). Conventional MRI always outperformed the other sequences. DCE-MRI always outperformed DWI, except for specificity.ConclusionsA multiparametric MRI-based model has a better performance in the noninvasive prediction of high-risk cytogenetics in newly diagnosed MM than conventional MRI alone.Critical relevance statementAn elaborate multiparametric MRI-based model performs better than conventional MRI alone for the noninvasive prediction of high-risk cytogenetics in newly diagnosed multiple myeloma; this opens opportunities to assess genetic heterogeneity thus overcoming sampling bias.Key points• Standard genetic techniques in multiple myeloma patients suffer from sampling bias due to tumoral heterogeneity.• Multiparametric MRI noninvasively predicts genetic risk in multiple myeloma.• Combined conventional anatomical MRI, DCE-MRI, and DWI had the highest statistical performance to predict genetic risk.• Conventional MRI alone always outperformed DCE-MRI and DWI separately to predict genetic risk. DCE-MRI alone always outperformed DWI separately, except for the parameter specificity to predict genetic risk.• This multiparametric MRI-based genetic risk prediction model opens opportunities to noninvasively assess genetic heterogeneity thereby overcoming sampling bias in predicting genetic risk in multiple myeloma.Graphical

Performance of European prediction models for classification of type 1 and type 2 diabetes in Indians

Performance of European prediction models for classification of type 1 and type 2 diabetes in Indians

A tensile properties-related fatigue strength predicted machine learning framework for alloys used in aerospace

A tensile properties-related fatigue strength prediction framework based on machine learning (ML) methods was proposed. Firstly, 200 data containing six materials used in aerospace were collected. Secondly, tensile properties-related ML framework, including residual neural network (ResNet) model, gradient boosting decision tree (GBDT) model and LightGBM (LGB) model, was established to predict fatigue strength under symmetric cycles (R = -1) after features correlation analysis. Then, Gaussian noise was introduced into the features to prove the robustness and feature sensitivity of proposed ML framework. Finally, materials characteristics of fatigue resistance in the next generation were discussed after the analysis of the correlation between the tensile properties and fatigue strength. Compared with ± 50 % error band of classical prediction models, the prediction results of proposed ML framework located in the ± 10 % error band, especially for special crystal orientations and stress ratios. In practical applications, the tensile properties-related ML framework could be applied efficiently to materials fatigue strength prediction used in aerospace due to its robust prediction accuracy and generalization ability without additional parameters fitting.

Machine Learning Based Classification Model for Prediction of Bank Loan Approval

Abstract: In this paper we creating and testing a smart loan prediction system using a special type of classifier called gradient boosting. Our methodology is meticulously laid out, covering a spectrum of essential stages including data pre-processing methodologies, in-depth exploratory analysis, and rigorous model training leveraging a dataset meticulously curated from Kaggle. Our model, with 300 estimators, a learning rate of 0.05, and a maximum of six features, achieves an astounding 98.03% accuracy. We utilize the pickle module to serialize our trained model, consequently deploying it as a web application. This application, which is powered by React for the front end and Flask for the back end, offers users a simple interface for entering loan application details and receiving real-time forecasts on loan acceptance or denial. Our research shows that gradient boosting classified the well in predicting the loans to the users.

Remaining useful life prediction of lithium-ion batteries combined with SVD-SDAE and support vector quantile regression

Lithium-ion batteries are important energy storage materials, and the prediction of their remaining useful life has practical importance. Since traditional feature extraction methods depend on parameter settings and have poor adaptability, singular value decomposition was used to extract 15 health indicators from the degradation data of lithium-ion batteries. To eliminate redundancy among the extracted health indicators, Spearman correlation analysis was subsequently used to determine the most appropriate health indicators. On this basis, the selected health indicators were processed by the denoising stack autoencoder, and a fusion health indicator was obtained. Finally, the support vector quantile regression model was used to predict the battery capacity interval by the fusion health indicator. The National Aeronautics and Space Administration battery dataset and Massachusetts Institute of Technology battery dataset were used to verify the validity and generalizability of our proposed model, and our proposed model was compared with the existing four classical prediction models. The experimental results showed that our proposed prediction model had higher prediction accuracy and better robustness than the other models and could effectively improve the prediction effect of the remaining useful life of batteries. The mean value of the root mean square error of the predicted results using our proposed model remained within 1.3%, and the mean value of the coefficient of determination was above 0.97.

Risk prediction and analysis of gallbladder polyps with deep neural network

The aim of this study is to analyze the risk factors associated with the development of adenomatous and malignant polyps in the gallbladder. Adenomatous polyps of the gallbladder are considered precancerous and have a high likelihood of progressing into malignancy. Preoperatively, distinguishing between benign gallbladder polyps, adenomatous polyps, and malignant polyps is challenging. Therefore, the objective is to develop a neural network model that utilizes these risk factors to accurately predict the nature of polyps. This predictive model can be employed to differentiate the nature of polyps before surgery, enhancing diagnostic accuracy. A retrospective study was done on patients who had cholecystectomy surgeries at the Department of Hepatobiliary Surgery of the Second People’s Hospital of Shenzhen between January 2017 and December 2022. The patients’ clinical characteristics, lab results, and ultrasonographic indices were examined. Using risk variables for the growth of adenomatous and malignant polyps in the gallbladder, a neural network model for predicting the kind of polyps will be created. A normalized confusion matrix, PR, and ROC curve were used to evaluate the performance of the model. In this comprehensive study, we meticulously analyzed a total of 287 cases of benign gallbladder polyps, 15 cases of adenomatous polyps, and 27 cases of malignant polyps. The data analysis revealed several significant findings. Specifically, hepatitis B core antibody (95% CI −0.237 to 0.061, p < 0.001), number of polyps (95% CI −0.214 to −0.052, p = 0.001), polyp size (95% CI 0.038 to 0.051, p < 0.001), wall thickness (95% CI 0.042 to 0.081, p < 0.001), and gallbladder size (95% CI 0.185 to 0.367, p < 0.001) emerged as independent predictors for gallbladder adenomatous polyps and malignant polyps. Based on these significant findings, we developed a predictive classification model for gallbladder polyps, represented as follows, Predictive classification model for GBPs = −0.149 * core antibody − 0.033 * number of polyps + 0.045 * polyp size + 0.061 * wall thickness + 0.276 * gallbladder size − 4.313. To assess the predictive efficiency of the model, we employed precision-recall (PR) and receiver operating characteristic (ROC) curves. The area under the curve (AUC) for the prediction model was 0.945 and 0.930, respectively, indicating excellent predictive capability. We determined that a polyp size of 10 mm served as the optimal cutoff value for diagnosing gallbladder adenoma, with a sensitivity of 81.5% and specificity of 60.0%. For the diagnosis of gallbladder cancer, the sensitivity and specificity were 81.5% and 92.5%, respectively. These findings highlight the potential of our predictive model and provide valuable insights into accurate diagnosis and risk assessment for gallbladder polyps. We identified several risk factors associated with the development of adenomatous and malignant polyps in the gallbladder, including hepatitis B core antibodies, polyp number, polyp size, wall thickness, and gallbladder size. To address the need for accurate prediction, we introduced a novel neural network learning algorithm. This algorithm utilizes the aforementioned risk factors to predict the nature of gallbladder polyps. By accurately identifying the nature of these polyps, our model can assist patients in making informed decisions regarding their treatment and management strategies. This innovative approach aims to improve patient outcomes and enhance the overall effectiveness of care.

A novel SCNN-LSTM model for predicting the SNR confidence interval in wearable wireless sensor network

Accurate real-time prediction of link quality is crucial for enhancing the reliable responsiveness of wearable devices within Wireless Wearable Sensor Networks (WWSNs). Specifically, the Signal-to-Noise Ratio (SNR), a pivotal parameter for predicting link quality, exhibits complex temporal characteristics influenced by stochastic and non-stochastic factors. To improve the accuracy of link quality prediction in WWSNs, we aim to explore a novel predictive model, introducing a filtering layer that seeks to enhance the precision of predicting upper and lower boundaries of link reliability confidence intervals. First, we adopt the SNR time series as the evaluation metric and decompose the SNR sequences into time-varying and stochastic standard deviation sequences by wavelet decomposition. Subsequently, we propose an innovative SCNN-LSTM model, incorporating the SincNet filtering layer to extract specific frequency components from the input SNR sequences. Afterward, integrating standard deviation sequences, the model predicts upper and lower boundaries of link reliability confidence intervals. Finally, we conduct the validation experiments on the public dataset LightGBM-LQP and our WWSN dataset Basketball shot. Compared to BPNN, ARIMA, and WNN, the evaluation matrices of MAE, RMSE, R2 in SCNN-LSTM have been improved, and the deviation between the predicted standard deviation and the actual standard deviation has reached the minimum of 0.1. The results demonstrate that SCNN-LSTM outperforms classical prediction models in predicting upper and lower limits of link reliability confidence intervals in WWSNs.

A gene signature linked to fibroblast differentiation for prognostic prediction of mesothelioma

BackgroundMalignant mesothelioma is a type of infrequent tumor that is substantially related to asbestos exposure and has a terrible prognosis. We tried to produce a fibroblast differentiation-related gene set for creating a novel classification and prognostic prediction model of MESO.MethodThree databases, including NCBI-GEO, TCGA, and MET-500, separately provide single-cell RNA sequencing data, bulk RNA sequencing profiles of MESO, and RNA sequencing information on bone metastatic tumors. Dimensionality reduction and clustering analysis were leveraged to acquire fibroblast subtypes in the MESO microenvironment. The fibroblast differentiation-related genes (FDGs), which were associated with survival and subsequently utilized to generate the MESO categorization and prognostic prediction model, were selected in combination with pseudotime analysis and survival information from the TCGA database. Then, regulatory network was constructed for each MESO subtype, and candidate inhibitors were predicted. Clinical specimens were collected for further validation.ResultA total of six fibroblast subtypes, three differentiation states, and 39 FDGs were identified. Based on the expression level of FDGs, three MESO subtypes were distinguished in the fibroblast differentiation-based classification (FDBC). In the multivariate prognostic prediction model, the risk score that was dependent on the expression level of several important FDGs, was verified to be an independently effective prognostic factor and worked well in internal cohorts. Finally, we predicted 24 potential drugs for the treatment of MESO. Moreover, immunohistochemical staining and statistical analysis provided further validation.ConclusionFibroblast differentiation-related genes (FDGs), especially those in low-differentiation states, might participate in the proliferation and invasion of MESO. Hopefully, the raised clinical subtyping of MESO would provide references for clinical practitioners.

Enhancing Predictive Models: An In-depth Analysis of Feature Selection Techniques Coupled with Boosting Algorithms

This research addresses the critical need to enhance predictive models for fetal health classification using Cardiotocography (CTG) data. The literature review underscores challenges in imbalanced labels, feature selection, and efficient data handling. This paper aims to enhance predictive models for fetal health classification using Cardiotocography (CTG) data by addressing challenges related to imbalanced labels, feature selection, and efficient data handling. The study uses Recursive Feature Elimination (RFE) and boosting algorithms (XGBoost, AdaBoost, LightGBM, CATBoost, and Histogram-Based Boosting) to refine model performance. The results reveal notable variations in precision, Recall, F1-Score, accuracy, and AUC across different algorithms and RFE applications. Notably, Random Forest with XGBoost exhibits superior performance in precision (0.940), Recall (0.890), F1-Score (0.920), accuracy (0.950), and AUC (0.960). Conversely, Logistic Regression with AdaBoost demonstrates lower performance. The absence of RFE also impacts model effectiveness. In conclusion, the study successfully employs RFE and boosting algorithms to enhance fetal health classification models, contributing valuable insights for improved prenatal diagnosis.

Measuring user influence in real-time on twitter using behavioural features

Identifying influential users in online social networks, specifically Twitter, has drawn considerable research interest due to their profound influence on real-world events. Existing studies have primarily focused on topological aspects to identify influential users, which necessitate a complete network structure and ignore the behavioural aspects of the users. However, real-world network structure can be challenging to obtain. Thus, this study presents the BehaviourRank Influence (BRI) method, which focuses on evaluating Twitter user influence by analysing behavioural characteristics instead of traditional network structures. This approach acquires data in real-time to derive six behavioural characteristics by employing new metrics to achieve accurate and uniform characterizations. The proposed metrics are compared to baseline metrics from the literature using a user classification prediction model to validate their predictive ability. It also ranked behavioural characteristics by importance using SHAP and Information Gain approaches. To determine overall influence, a unique Rank-based Exponential Smoothing algorithm is proposed. The findings indicate that most features incorporating proposed measures exhibited superior performance compared to features with baseline metrics across all three datasets. The proposed feature sets achieved accuracy scores of 86.67%, 73.47%, and 85.87% in the respective datasets, while the baselined feature sets attained scores of 64.23%, 63.30%, and 66.30%. Moreover, the Rank-Based influence measurements algorithm provides a detailed and adaptable structure for measuring influence, recognising the significance of feature ranks in capturing the evolving nature of user behaviour.

Machine Learning Models for Prediction of Xenobiotic Chemicals with High Propensity to Transfer into Human Milk.

Breast milk serves as a vital source of essential nutrients for infants. However, human milk contamination via the transfer of environmental chemicals from maternal exposome is a significant concern for infant health. The milk to plasma concentration (M/P) ratio is a critical metric that quantifies the extent to which these chemicals transfer from maternal plasma into breast milk, impacting infant exposure. Machine learning-based predictive toxicology models can be valuable in predicting chemicals with a high propensity to transfer into human milk. To this end, we build such classification- and regression-based models by employing multiple machine learning algorithms and leveraging the largest curated data set, to date, of 375 chemicals with known milk-to-plasma concentration (M/P) ratios. Our support vector machine (SVM)-based classifier outperforms other models in terms of different performance metrics, when evaluated on both (internal) test data and an external test data set. Specifically, the SVM-based classifier on (internal) test data achieved a classification accuracy of 77.33%, a specificity of 84%, a sensitivity of 64%, and an F-score of 65.31%. When evaluated on an external test data set, our SVM-based classifier is found to be generalizable with a sensitivity of 77.78%. While we were able to build highly predictive classification models, our best regression models for predicting the M/P ratio of chemicals could achieve only moderate R2 values on the (internal) test data. As noted in the earlier literature, our study also highlights the challenges in developing accurate regression models for predicting the M/P ratio of xenobiotic chemicals. Overall, this study attests to the immense potential of predictive computational toxicology models in characterizing the myriad of chemicals in the human exposome.

A novel adaptively combined model based on induced ordered weighted averaging for wind power forecasting

Accurate wind power prediction is a vital factor in day-ahead dispatch and increasing the high penetration of renewable energy integration. Some combined prediction models based on weight are proposed to provide uncertain information about wind power. However, the optimal weight issues to be addressed are still a tough problem. This paper proposes an adaptively combined prediction model based on the induced ordered weighted averaging operator. First, four classical prediction models are used as a predictor to forecast wind power. Second, the optimal weight is expressed as an optimization problem to minimize the prediction errors with the nonnegative constraints and summation constraint of weights, and the optimal optimization problem is transformed into a quadratic programming model, which can be easily solved to determine the optimal weights for multiple prediction models. Third, an interval prediction mode based on errors distribution produced by the proposed combined model with different confidence intervals is constructed, which can perform deterministic and probabilistic prediction of wind power simultaneously. Furthermore, the model's effectiveness is comprehensively evaluated using both deterministic and probabilistic approaches. This analysis is further enriched with a comprehensive examination of a year-round dataset obtained from a wind farm cluster in Ningxia, China. The data, recorded at 15-min intervals, offer robust evidence of the combined model's superior performance. The results show that the proposed approach can achieve higher accuracy than other benchmark prediction models, further verifying its reliability for wind power dispatch.

Structure Optimization and Data Processing Method of Electronic Nose Bionic Chamber for Detecting Ammonia Emissions from Livestock Excrement Fermentation.

In areas where livestock are bred, there is a demand for accurate, real-time, and stable monitoring of ammonia concentration in the breeding environment. However, existing electronic nose systems have slow response times and limited detection accuracy. In this study, we introduce a novel solution: the bionic chamber construction of the electronic nose is optimized, and the sensor response data in the chamber are analyzed using an intelligent algorithm. We analyze the structure of the biomimetic chamber and the surface airflow of the sensor array to determine the sensing units of the system. The system employs an electronic nose to detect ammonia and ethanol gases in a circulating airflow within a closed box. The captured signals are processed, followed by the application of classification and regression models for data prediction. Our results suggest that the system, leveraging the biomimetic chamber, offers rapid gas detection response times. A high classification prediction accuracy, with a determination coefficient R2 value of 0.99 for single-output regression and over 0.98 for multi-output regression predictions, is achieved by incorporating a backpropagation (BP) neural network algorithm. These outcomes demonstrate the effectiveness of the electronic nose, based on an optimized bionic chamber combined with a BP neural network algorithm, in accurately detecting ammonia emitted during livestock excreta fermentation, satisfying the ammonia detection requirements of breeding farms.

Cluster Based Classification Model for Trend Prediction in Time Series Data

Abstract: Real-time stock market trend prediction plays a essential role in the technical analysis for trend prediction process. Traditional historical technical indicators are difficult to trace and predict the trend due to noise or uncertainty in the training dataset. Since, most of the traditional homogeneous or heterogeneous stocks are used to predict the overall market sentiment for the institutions or retailors. Also, traditional approaches are difficult to find the outliers in the technical indicators data for the clustering process. These models only consider the static metrics or static outlier meaures due to variation in data distribution according to time basis. In this work, a hybrid knn classifier is used to predict the trend of the stock.

Risk assessment and classification prediction for water environment treatment PPP projects.

Water treatment public-private partnership (PPP) projects are pivotal for sustainable water management but are often challenged by complex risk factors. Efficient risk management in these projects is crucial, yet traditional methodologies often fall short of addressing the dynamic and intricate nature of these risks. Addressing this gap, this comprehensive study introduces an advanced risk classification prediction model tailored for water treatment PPP projects, aimed at enhancing risk management capabilities. The proposed model encompasses an intricate evaluation of crucial risk areas: the natural and ecological environments, socio-economic factors, and engineering entities. It delves into the complex relationships between these risk elements and the overall risk profile of projects. Grounded in a sophisticated ensemble learning framework employing stacking, our model is further refined through a weighted voting mechanism, significantly elevating its predictive accuracy. Rigorous validation using data from the Jiujiang City water environment system project Phase I confirms the model's superiority over standard machine learning models. The development of this model marks a significant stride in risk classification for water treatment PPP projects, offering a powerful tool for enhancing risk management practices. Beyond accurately predicting project risks, this model also aids in developing effective government risk management strategies.

Inspection of antimicrobial particles in milk using RGB-laser scattering imaging combined with chemometric procedures

The immobilisation of phytochemicals on inert particles has demonstrated high potential to develop new formulations of natural antimicrobials for preserving liquid foods such as milk. This work aimed to test the capability of the laser scattering imaging technique combined with chemometric procedures to inspect antimicrobial particles in milk matrices non-destructively. The RGB laser's interactions with the milk matrix were captured as diffraction patterns in digital images, from which data were extracted after imaging processing and modelled by chemometric procedures. The antimicrobials were based on solid inorganic particles (silica) functionalised with a plant essential oil (eugenol). The effect of the natural variability from five types of milk was studied (cow 0, 1.5 and 3.5% lipids, goat and sheep). The inspection functions focused on predicting the type of milk, presence of antimicrobial particles, functionalisation of particles and type of inorganic structure. PLS-DA was applied to perform classification models for each property prediction, combined with pre-processing and variable selection procedures to isolate the variability of the property of interest. The results revealed a high classification capacity for milk types. The properties of antimicrobials were also successfully predicted. In this case, data pre-processing and variable selection procedures had to be applied to reduce structural noise and improve the models from raw data. Combining imaging and chemometrics techniques could capture and model the variability generated by antimicrobial particles independently of the nature of milk. It established the basis for developing a possible non-destructive inspection system to control liquid food containing these new antimicrobials.

Predictive model for acute myocardial infarction in working-age population: a machine learning approach

Cardiovascular diseases are the leading cause of mortality in Latin America, particularly acute myocardial infarction (AMI), which is the primary cause of atherosclerotic cardiovascular morbidity. This study aims to develop a predictive model for the probability of AMI occurrence in the working-age population, based on atherogenic indices, paraclinical variables, and anthropometric measures. The research conducted a cross-sectional study involving 427 workers aged 40 years or older in Popayán, Colombia. Out of this population, 202 individuals were screened with a 95% confidence interval and a 5% error margin. Epidemiological, anthropometric, and paraclinical data were collected. A binary logistic regression model was employed to identify variables directly associated with the probability of AMI. Predictive classification models were generated using statistical software JASP and the programming language Python. During the training stage, JASP produced a model with an accuracy of 87.5%, while Python generated a model with an accuracy of 90.2%. In the validation stage, JASP achieved an accuracy of 93%, and Python reached 95%. These results establish an effective model for predicting the probability of AMI in the working population.

Machine learning predictions of code-based seismic vulnerability for reinforced concrete and masonry buildings: Insights from a 300-building database

This paper proposes a data-driven model for predicting the code-based seismic vulnerability index calibrated on a dataset comprising almost 300 buildings. The vulnerability index, estimated following the Italian Seismic Code, involved rigorous investigations, including geometric surveys, experimental tests, and numerical modelling. Leveraging data from these investigations, encompassing approximately 15 categorical and numerical explanatory variables, the authors developed several regression and classification predictive models, such as Logistic Regression and Artificial Neural Networks (ANN). The optimal models perform binary classification to determine the categorization into two macro-classes, defined by an arbitrary vulnerability threshold. The ANN model stands out as the best performer. When adjusting the vulnerability threshold to obtain a balanced dataset, such a model achieves an accuracy higher than 85%. The paper also discusses the importance of each feature by calculating the SHapley Additive exPlanations (SHAP) values. The proposed model can aid decision-makers in allocating resources effectively to mitigate seismic risks of built environments.

Expert-augmented machine learning to accelerate the discovery of copolymers for anion exchange membrane

We constructed an automated machine learning pipeline to screen the broad chemical space of candidate copolymers for anion exchange membranes (AEMs). The pipeline utilizes a genetic algorithm integrated twelve machine learning algorithms, to screen copolymers that are potentially capable to improve AEM performance through the evolution of polymer hydrophobic and hydrophilic backbones and cation groups. An exhaustive data mining accumulated 749 experimentally reported AEMs, then the pipeline automatically generated over 172 million hypothetical copolymers, and 2519 potential candidates were screened out according to their predicted performance metrics including the OH− conductivity, the conductivity – dimensional stability trade-off coefficient, and the LUMO of cations in Pareto frontier set. Expert experience was adopted in the construction of robust regression and classification predictive models, and the importance of physical, chemical and topological features were illustrated from Shapley additive explanations (SHAP) analysis. We have released a standalone software that integrates these predictive models and the screened copolymer candidates with predicted AEM performance metrics at https://github.com/polySML/polySML-AEM. This study can facilitate the development of advanced AEMs through rational design of copolymers.

[Optimization of prediction model for personalized water pills based on semantic analysis of traditional Chinese medicine materials].

This study aims to optimize the prediction model of personalized water pills that has been established by our research group. Dioscoreae Rhizoma, Leonuri Herba, Codonopsis Radix, Armeniacae Semen Amarum, and calcined Oyster were selected as model medicines of powdery, fibrous, sugary, oily, and brittle materials, respectively. The model prescriptions were obtained by uniform mixing design. With hydroxypropyl methylcellulose E5(HPMC-E5) aqueous solution as the adhesive, personalized water pills were prepared by extrusion and spheronizaition. The evaluation indexes in the pill preparation process and the multi-model statistical analysis were employed to optimize and evaluate the prediction model of personalized water pills. The prediction equation of the adhesive concentration was obtained as follows: Y_1=-4.172+3.63X_A+15.057X_B+1.838X_C-0.997X_D(adhesive concentration of 10% when Y_1&lt;0, and 20% when Y_1&gt;0). The overall accuracy of the prediction model for adhesive concentration was 96.0%. The prediction equation of adhesive dosage was Y_2=6.051+94.944X_A~(1.5)+161.977X_B+70.078X_C~2+12.016X_D~(0.3)+27.493X_E~(0.3)-2.168X_F~(-1)(R~2=0.954, P&lt;0.001). Furthermore, the semantic prediction model for material classification of traditional Chinese medicines was used to classify the materials contained in the prescription, and thus the prediction model of personalized water pills was evaluated. The results showed that the prescriptions for model evaluation can be prepared with one-time molding, and the forming quality was better than that established by the research group earlier. This study has achieved the optimization of the prediction model of personalized water pills.