Classical Prediction Models Research Articles

Selection and validation of a novel set of specific differential methylation markers and construction of a random forestprediction model for the accurate tissue origin identifications of body fluids involving young and middle-aged group of Chinese Han population.

The identification of tissue origin of body fluid is helpful to the determination of the case nature and the reproduction of the case process. It has been confirmed that tissue-specific differential methylation markers could be used to identify the tissue origins of different body fluids. To select suitable tissue-specific differential methylation markers and establish the efficient typing system which could be applied to the identifications of body fluids in forensic cases involving Chinese Han individuals of young and middle-aged group, a total of 125 body fluids (venous blood, semen, vaginal fluid, saliva, and menstrual blood) were collected from healthy Chinese Han volunteers aged 20-45years old. After genome-wide explorations of DNA methylation patterns in these five kinds of body fluids based on the Illumina Infinium Methylation EPIC BeadChip, 15 novel body fluid-specific differential CpGs were selected and verified based on the pyrosequencing method. And these identification efficiencies for target body fluids were verified by ROC curves. The pyrosequencing results indicated that the average methylation rates of nine CpGs were consistent with those of DNA methylation chip detection results, and the other five CpGs (except for cg12152558) were still helpful for the tissue origin identifications of target body fluids. Finally, a random forest classification prediction model based on these 14 CpGs was constructed to successfully identify five kinds of body fluids, and the tested accuracy rates all reached 100%.

Predicting Vault and Size of Posterior Chamber Phakic Intraocular Lens Using Sulcus to Sulcus-Optimized Artificial Intelligence Technology

To investigate the accuracy of posterior chamber phakic intraocular lens (PIOL) vault and size prediction models based on sulcus to sulcus (STS) optimized artificial intelligence and big data analysis technology. Big data and artificial intelligence prediction model. We included 5873 eyes with posterior chamber PIOL implantation, and the postoperative vault was measured using an anterior segment analyzer (Pentacam AXL) 1 month postoperatively. A random forest regression model and classification model were used to predict the postoperative vault and PIOL size. The postoperative vault and PIOL size were set as output features; other vault-related eye parameters were set as input features. The influence of white to white (WTW), horizontal sulcus to sulcus (STS), and vertical STS on predicting postoperative vault and PIOL size was analyzed and compared. The mean preoperative WTW diameter was 11.64 ± 0.37 mm, the mean horizontal STS diameter was 11.85 ± 0.47 mm, and the mean vertical STS diameter was 12.39 ± 0.52 mm. In the regression model for numerical prediction of the vault, the combination of WTW, horizontal STS, and vertical STS was the most optimal for vault prediction (R2=0.3091, root mean square error [RMSE]=0.1705); solely relying on WTW was the least optimal (R2=0.2849, RMSE=0.1735). Among the models for classification prediction of the vault, the combination of WTW, horizontal STS, and vertical STS was the most accurate (accuracy, 0.6302; mean area under the curve, 0.8008; and mean precision recall rate, 0.6940). Moreover, the combination of WTW, horizontal STS, and vertical STS exhibited the highest accuracy for classification prediction of PIOL size (accuracy, 0.8170; mean area under the curve, 0.9540; and mean precision recall rate, 0.8864). Whether in the regression prediction models of vault values or in the classification prediction models of vault and PIOL size, the accuracy of STS optimized model was significantly improved compared with the traditional WTW model (P < .001). Artificial intelligence combined with STS optimization contributes to the accuracy of PIOL size and vault prediction models. The random forest machine-learning model optimized by STS is superior to the traditional WTW model.

Identification of adulterated honey with different varieties and concentrations based on hyperspectral imaging technology combined with deep learning

Honey is an important agricultural and sideline product in China, which contains the high nutritional value and commercial value. An advanced honey adulteration identification model can help beekeepers and consumers better identify honey and avoid losses. Given the complex operation and high technical requirements of traditional honey identification experimental instruments, a new model for quickly and efficiently identifying honey adulteration with different kinds and concentrations was developed in this study. Based on the data of adulterated honey with different varieties and concentrations obtained by hyperspectral imaging technology, a large number of regions of interest were randomly selected as samples. Then, the classification model is established by adopting preprocessing methods such as standardization, centralization, multivariate scattering correction, standard variable transformation, first-order difference, and second-order difference, combining the advantages of convolutional neural network and support vector machine. Finally, the accuracy of the results is compared, and D1-CNN-SVM is determined as the best classification prediction model, with an accuracy rate of 100%. At the same time, through the analysis of the confusion matrix of experimental results, this study summarizes the difficulties in identifying adulterated honey of different varieties and concentrations.

Analysis of Baseline Serum Lipid Profile for Predicting Clinical Outcomes of Patients with Extensive-Stage Small Cell Lung Cancer.

Serum lipids were reported to be the prognostic factors of various cancers, but their prognostic value in small cell lung cancer (SCLC) patients remains unclear. This study investigated the relationship between lipid profiles and clinical outcomes in extensive-stage (ES) SCLC by establishing a predictive risk classification model. We retrospectively analyzed the prognostic values of pretreatment serum lipids and their derivatives in patients with a confirmed diagnosis ES-SCLC. Independent factors of progression-free survival (PFS) were determined by univariate and multivariate cox analysis. Then, prognostic nomograms were established, of which predictive performance was evaluated by concordance index (C-index), calibration curves, receiver operating characteristic (ROC) curves, and decision curve analyses (DCA). A total of 158 patients was included in this study. Four optimal PFS-related factors, total cholesterol (TC) ≥ 5.30, high-density lipoprotein cholesterol (HDL-C) > 1.30, triglycerides (TG)/HDL-C > 2.18, and ki67 expression > 70%, were included to construct the predictive nomogram. The C-indexes in training and validation sets were 0.758 and 0.792, respectively. ROC curves, calibration plots, and DCA all suggested favorable discrimination and predictive ability. Besides, the nomogram also performed better predictive ability than ki67 expression. Nomogram-related risk score divided the patients into two groups with significant progression disparities. The promising prognostic nomogram based on lipid parameters could help clinicians to conveniently and accurately evaluate the prognosis of ES-SCLC patients and identify high-risk groups, so as to formulate individualized therapeutic regimens and follow-up strategies in time.

Application of machine learning for evaluating and predicting fault seals: A case study in the Huimin depression, Bohai Bay Basin, Eastern China

Fault seal is of great significance for hydrocarbon migration, accumulation, and further hydrocarbon reservoir production. Approximate 32% petroleum resource is confirmed to be related to the faults. However, the existing fault seal evaluation methods based on statistical analysis cannot accurately predict fault seal which is influenced by multiple factors in a complex way. It is necessary to improve the fault seal evaluation methods for enhancing the exploration success rate. In this study, a new fault seal evaluation and prediction method based on decision tree (DT) and random forest (RF) is introduced. First, the original dataset was set by quantification and feature engineering work. Second, the nonlinear classification models for fault seal evaluation and prediction using a binary decision tree named the classification and regression tree (CART) were constructed and improved by overfitting calibration. Third, the random forest algorithm was selected as an ensemble learning method to improve the faut seal evaluation and prediction accuracy. Third, the evaluation metrics and cross-validation were used to evaluate the performance of the model. Finally, the validation test is applied for testing the reliability of the model. The result showed that among the 100,000 models constructed in this study, the DT best model could evaluate and predict the fault seal with a cross-validation accuracy of 80.60% after overfitting calibration by pruning. The best RF model showed the highest test accuracy of 86.54%, which is higher than that of the DT model. The models were used for predicting fault seals in another district in the Huimin Depression, and the prediction accuracy reached 90% and 95% for the DT and RF model, respectively. This study not only introduced a new method for fault seal evaluation and prediction, but also provided guidance for the application and development of machine learning in petroleum exploration and exploitation field and industry.

The Association of Metabolomic Profiles of a Healthy Lifestyle with Heart Failure Risk in a Prospective Study.

Lifestyle has been linked to the incidence of heart failure, but the underlying biological mechanisms remain unclear. Using the metabolomic, lifestyle, and heart failure data of the UK Biobank, we identified and validated healthy lifestyle-related metabolites in a matched case-control and cohort study, respectively. We then evaluated the association of healthy lifestyle-related metabolites with heart failure (HF) risk and the added predictivity of these healthy lifestyle-associated metabolites for HF. Of 161 metabolites, 8 were identified to be significantly related to healthy lifestyle. Notably, omega-3 fatty acids and docosahexaenoic acid (DHA) positively associated with a healthy lifestyle score (HLS) and exhibited a negative association with heart failure risk. Conversely, creatinine negatively associated with a HLS, but was positively correlated with the risk of HF. Adding these three metabolites to the classical risk factor prediction model, the prediction accuracy of heart failure incidence can be improved as assessed by the C-statistic (increasing from 0.806 [95% CI, 0.796-0.816] to 0.844 [95% CI, 0.834-0.854], p-value < 0.001). A healthy lifestyle is associated with significant metabolic alterations, among which metabolites related to healthy lifestyle may be critical for the relationship between healthy lifestyle and HF. Healthy lifestyle-related metabolites might enhance HF prediction, but additional validation studies are necessary.

Construction and evaluation of in-house methylation-sensitive SNaPshot system and three classification prediction models for identifying the tissue origin of body fluid.

The identification of tissue origin of body fluid can provide clues and evidence for criminal case investigations. To establish an efficient method for identifying body fluid in forensic cases, eight novel body fluid-specific DNA methylation markers were selected in this study, and a multiplex singlebase extension reaction (SNaPshot) system for these markers was constructed for the identification of five common body fluids (venous blood, saliva, menstrual blood, vaginal fluid, and semen). The results indicated that the in-house system showed good species specificity, sensitivity, and ability to identify mixed biological samples. At the same time, an artificial body fluid prediction model and two machine learning prediction models based on the support vector machine (SVM) and random forest (RF) algorithms were constructed using previous research data, and these models were validated using the detection data obtained in this study (n=95). The accuracy of the prediction model based on experience was 95.79%; the prediction accuracy of the SVM prediction model was 100.00% for four kinds of body fluids except saliva (96.84%); and the prediction accuracy of the RF prediction model was 100.00% for all five kinds of body fluids. In conclusion, the in-house SNaPshot system and RF prediction model could achieve accurate tissue origin identification of body fluids.

DeepASDPred: a CNN-LSTM-based deep learning method for Autism spectrum disorders risk RNA identification

BackgroundAutism spectrum disorders (ASD) are a group of neurodevelopmental disorders characterized by difficulty communicating with society and others, behavioral difficulties, and a brain that processes information differently than normal. Genetics has a strong impact on ASD associated with early onset and distinctive signs. Currently, all known ASD risk genes are able to encode proteins, and some de novo mutations disrupting protein-coding genes have been demonstrated to cause ASD. Next-generation sequencing technology enables high-throughput identification of ASD risk RNAs. However, these efforts are time-consuming and expensive, so an efficient computational model for ASD risk gene prediction is necessary.ResultsIn this study, we propose DeepASDPerd, a predictor for ASD risk RNA based on deep learning. Firstly, we use K-mer to feature encode the RNA transcript sequences, and then fuse them with corresponding gene expression values to construct a feature matrix. After combining chi-square test and logistic regression to select the best feature subset, we input them into a binary classification prediction model constructed by convolutional neural network and long short-term memory for training and classification. The results of the tenfold cross-validation proved our method outperformed the state-of-the-art methods. Dataset and source code are available at https://github.com/Onebear-X/DeepASDPred is freely available.ConclusionsOur experimental results show that DeepASDPred has outstanding performance in identifying ASD risk RNA genes.

Investigation of the low-frequency chatter in robotic milling

In robotic milling with large allowance process, low-frequency chatter (LFC) is an important factor observed in high-speed and low-speed milling, affecting the processing efficiency and quality. Previous research has used the regenerative chatter theory, ignoring modulated tool-workpiece engagement conditions, or mode coupling theory under the assumption of threading operations to explain the LFC mechanism and predict the stability boundary. However, these models overlook or inaccurately characterize the modulation effect, leading to inaccurate modeling of dynamic chip thickness changes during milling, making it difficult to understand the mechanism of LFC. Here, we propose an LFC stability model that considers modulated tool-workpiece engagement conditions and the mode coupling effect of the robotic structure for robotic milling. This approach allows us to reveal the mechanism of LFC and identify the characteristic signal of low-frequency vibration, which is the sideband frequency signal. Initially, the evolution of LFC is analyzed, and its characteristics are summarized. Further, a surface renewal (SR) model is proposed to accurately calculate the dynamic cutting force caused by modulated tool-workpiece engagement conditions in LFC. Furthermore, the LFC stability model, considering the modulated tool-workpiece engagement conditions and mode coupling effect, is established based on impulse response function (IRF) method. Finally, we verify the accuracy of our model through milling experiments and compare it with that of the classical stability prediction model. Our results show that LFC is highly dependent on speed, and our stability model can effectively predict the stability boundary of LFC in robotic milling with large allowance process.

Band gap predictions of double perovskite oxides using machine learning

The compositional and structural variety inherent to oxide perovskites spawn wide-ranging applications. In perovskites, the band gap Eg, a key material parameter for these applications, can be optimally controlled by varying the composition. Here, we implement a hierarchical screening process in which two cross-validated and predictive machine learning models for band gap classification and regression, trained using exhaustive datasets that span 68 elements of the periodic table, are applied sequentially. The classification model separates wide band gap materials, with Eg ≥ 0.5 eV, from materials which have zero or relatively small band gaps, namely Eg < 0.5 eV, and the second regression model quantitatively predicts the gap value of the wide band gap compounds. The study down-selects 13,589 cubic oxide perovskite compositions that are predicted to be experimentally formable, thermodynamically stable, and have a wide band gap. Of these, a subset of 310 compounds, which are predicted to be stable and formable with a confidence greater than 90%, are identified for further investigation. Our models are methodically analyzed via performance metrics and inter-dependence of model features to gain physical insight into the band gap prediction problem. Design maps to identify the variation of band gap with substitution of different elements are also presented.

Deep learning-based classification model for GPR151 activator activity prediction

BackgroundGPR151 is a kind of protein belonging to G protein-coupled receptor family that is closely associated with a variety of physiological and pathological processes.The potential use of GPR151 as a therapeutic target for the management of metabolic disorders has been demonstrated in several studies, highlighting the demand to explore its activators further. Activity prediction serves as a vital preliminary step in drug discovery, which is both costly and time-consuming. Thus, the development of reliable activity classification model has become an essential way in the process of drug discovery, aiming to enhance the efficiency of virtual screening.ResultsWe propose a learning-based method based on feature extractor and deep neural network to predict the activity of GPR151 activators. We first introduce a new molecular feature extraction algorithm which utilizes the idea of bag-of-words model in natural language to densify the sparse fingerprint vector. Mol2vec method is also used to extract diverse features. Then, we construct three classical feature selection algorithms and three types of deep learning model to enhance the representational capacity of molecules and predict activity label by five different classifiers. We conduct experiments using our own dataset of GPR151 activators. The results demonstrate high classification accuracy and stability, with the optimal model Mol2vec-CNN significantly improving performance across multiple classifiers. The svm classifier achieves the best accuracy of 0.92 and F1 score of 0.76 which indicates promising applications for our method in the field of activity prediction.ConclusionThe results suggest that the experimental design of this study is appropriate and well-conceived. The deep learning-based feature extraction algorithm established in this study outperforms traditional feature selection algorithm for activity prediction. The model developed can be effectively utilized in the pre-screening stage of drug virtual screening.

A Machine Learning Approach for Prediction of Diabetes Mellitus

Diabetes Mellitus is among chronic diseases and lots of people are suffering with this disease. It may cause many complications and have a high risk of diseases like heart disease, kidney disease, stroke, eye problem, nerve damage, etc. There is no doubt that this alarming figure needs great attention. With the rapid development of Machine Learning, machine learning has been applied to many aspects of medical health. There are several Machine learning algorithms that are used to perform predictive analysis in various fields. Predictive analysis in healthcare is a challenging task but ultimately can help practitioners make data informed about a patient's health and treatment. In this project, for experiment purposes, we have taken a dataset which is originally from the National Institute of diabetes and digestive and kidney diseases. All patients here are females at least 21 years old of Pima Indian heritage. By studying the dataset, we must find hidden information, hidden patterns to discover knowledge from the data and predict outcomes accordingly. The objective of this project is to diagnostically predict whether the patient has diabetes or not, based on certain diagnostic measurements included in the dataset. We have proposed a diabetes prediction model for better classification of diabetes by applying some popular machine learning algorithms namely, Logistic Regression, Random Forest Algorithm and KNN Algorithm to predict Diabetes.

Multivariate Grey Prediction Model Application in Civil Aviation Carbon Emission Based on Fractional Order Accumulation and Background Value Optimization

The GM(1,N) model, as a classical multivariate grey prediction model, can make a holistic and dynamic analysis of multiple factors and reflect the dynamic change relationship between the variable series and the related factor series. However, numerous works in the literature show that the GM(1,N) model has mechanistic defects, parametric defects, and structural defects. Therefore, the thesis establishes the OGM(1,N) model based on the GM(1,N) model by adding the linear correction term and the amount of grey action. According to the principle of dynamic optimization, the PSO algorithm is used to determine the background value. On this basis, the fractional order idea is introduced to push the model order from the integer field to the real field, and the FOBGM(1,N) model is established to systematically reduce the model error. Second, the literature in the ScienceDirect database for the last ten years is reviewed, and the carbon emission impact factors of civil aviation are selected. The calculated carbon emission values are taken as sample data based on Method 2 of Civil Aviation in Volume 2 of the 2006 IPCC Guide to National Greenhouse Gas Inventories. The results show that the prediction accuracy of the model has an increasing trend after multi-layer and multi-angle optimization. Among them, the MAPE of the OGM model and FOBGM model decreased by 24.40% and 31.86% compared with the GM(1,N) model. The 5-year average prediction accuracy of the FOBGM model reaches 99.996%, which verifies the effectiveness and practicality of the model improvement and has certain practical significance and application prospects.

A Concentration Prediction and Gas Classification Model Based on LSTM-Attention Multi-task Learning Framework Network

The electronic nose (E-nose), a bionic olfactory system, has been widely used in gas identification and concentration prediction. However, these tasks are usually based on separate systems, leading to high detection costs. To address this issue, a multi-task learning network model based on LSTM-Attention (MTL-LSTMA) as a skeleton has been proposed to simultaneously train both species recognition and concentration prediction tasks. The introduction of an attention mechanism greatly reduces interference in gas feature information, improving the electronic nose pattern recognition algorithm’s efficiency. The MTL-LSTMA model was tested through five sets of comparison experiments, showing the best performance in both concentration prediction and species identification. The proposed model has broad application prospects and may revolutionize gas detection technology.

Investigation of Variables Affecting PISA Success Levels of Countries with Different Success Levels with Data Mining Methods

The aim of this research is to determine the important variables that predict the PISA 2018 reading comprehension achievement score of countries with different achievement levels, using 34 independent variables obtained from the student questionnaire given to the students who participated in PISA in 2018. For this purpose, 79 countries that participated PISA were ranked according to their success percentages then, these countries were sorted into lower, middle and upper group countries. A sample of lower, middle and upper group countries was formed then, three countries were selected from each of the lower group, middle group and upper group countries and a sample of lower, middle and upper group countries was formed. Data mining analyzes were carried out on the samples obtained by using the Classification and Regression Tree and Random Forest methods. It has been observed that the number of important variables that predict reading comprehension success can be reduced from 34 to three to eight. Like this; Data mining classification prediction models, which can predict the success level of PISA, were obtained by using a small number of variables. It has been determined that the models obtained have an acceptable level of predictive performance in predicting success in three categories (low, medium-high). The most important predictor variables obtained from the models are information and communication technologies resources, perception of reading difficulty, professional status expected from the student, perception of difficulty in the PISA test, reading pleasure, weekly test language learning time, disciplinary climate, socio-economic status index.

An innovative index for separating the effects of temperature and precipitation on global vegetation change

Temperature and precipitation changes are among the vital climatic driving forces of global vegetation change. However, the strategy to separate the relative contributions of these two critical climatic factors is still lacking. Here, we propose an index CRTP (contribution ratio of temperature and precipitation) to quantify their impacts on vegetation and then construct the CRTP classification prediction models based on climatic, geographic, and environmental factors using the Random Forest classifier. We find that precipitation predominates more than 70% of the significant vegetation change, mainly located in the low and middle latitudes during 2000-2021. Precipitation will remain the dominant climatic factor affecting global vegetation change in the coming six decades, whereas areas with temperature-dominated vegetation change will expand under higher radiative forcings. Hopefully, the promising index CRTP will be applied in the research about climatic attribution for regional vegetation degradation, monitoring drought-type conversion, and alarming the potential ecological risk.

Concept Drift in Software Defect Prediction: A Method for Detecting and Handling the Drift

Software Defect Prediction (SDP) is crucial towards software quality assurance in software engineering. SDP analyzes the software metrics data for timely prediction of defect prone software modules. Prediction process is automated by constructing defect prediction classification models using machine learning techniques. These models are trained using metrics data from historical projects of similar types. Based on the learned experience, models are used to predict defect prone modules in currently tested software. These models perform well if the concept is stationary in a dynamic software development environment. But their performance degrades unexpectedly in the presence of change in concept (Concept Drift). Therefore, concept drift (CD) detection is an important activity for improving the overall accuracy of the prediction model. Previous studies on SDP have shown that CD may occur in software defect data and the used defect prediction model may require to be updated to deal with CD. This phenomenon of handling the CD is known as CD adaptation. It is observed that still efforts need to be done in this direction in the SDP domain. In this article, we have proposed a pair of paired learners (PoPL) approach for handling CD in SDP. We combined the drift detection capabilities of two independent paired learners and used the paired learner (PL) with the best performance in recent time for next prediction. We experimented on various publicly available software defect datasets garnered from public data repositories. Experimentation results showed that our proposed approach performed better than the existing similar works and the base PL model based on various performance measures.

A WOA-CNN-BiLSTM-based multi-feature classification prediction model for smart grid financial markets

Introduction: Smart grid financial market forecasting is an important topic in deep learning. The traditional LSTM network is widely used in time series forecasting because of its ability to model and forecast time series data. However, in long-term time series forecasting, the lack of historical data may lead to a decline in forecasting performance. This is a difficult problem for traditional LSTM networks to overcome.Methods: In this paper, we propose a new deep-learning model to address this problem. This WOA-CNN-BiLSTM model combines bidirectional long short-term memory network BiLSTM and convolution Advantages of Neural Network CNN. We replace the traditional LSTM network with a bidirectional long short-term memory network, BiLSTM, to exploit its ability in capturing long-term dependencies. It can capture long-term dependencies in time series and is bidirectional modelling. At the same time, we use a convolutional neural network (CNN) to extract features of time series data to better represent and capture patterns and regularity in the data. This method combining BiLSTM and CNN can learn the characteristics of time series data more comprehensively, thus improving the accuracy of prediction. Then,to further improve the performance of the CNN-BiLSTM model, we optimize the model using the whale algorithm WOA. This algorithm is a new optimization algorithm, which has good global search ability and convergence speed, and can complete the optimization of the model in a short time.Results: Optimizing the CNN-BiLSTM model through the WOA algorithm can reduce its calculation and training speed, improve the prediction accuracy of the smart grid financial market, and improve the prediction ability of the smart grid financial market. Experimental results show that our proposed CNN-BiLSTM model has better prediction accuracy than other models and can effectively deal with the problem of missing historical data in long-term sequence forecasting.Discussion: This provides necessary help for the development of smart grid financial markets and risk management services, and can promote the development and growth of the smart grid industry. Our research results are of great significance in deep learning, and provide an effective method and idea for solving the financial market forecasting problem of smart grid.

MWD Data-Based Marble Quality Class Prediction Models Using ML Algorithms

Brønnøy Kalk AS operates an open pit mine in Norway producing marble, mainly used by the paper industry. The final product is used as filler and pigment for paper production. Therefore, the quality of the product has utmost importance. In the mine, the primary quality indicator, called TAPPI, is quantified through a laborious sampling process and laboratory experiments. As a part of digital transformation, measurement while drilling (MWD) data have been collected in the mine. The purpose of this paper is to use the recorded MWD data for the prediction of marble quality to facilitate quality blending in the pit. For this purpose, two supervised classification modelling algorithms such as conventional logistic regression and random forest have been employed. The results show that the random forest classification model presents significantly higher statistical performance, and it can be used as a tool for fast and efficient marble quality assessment.

Classification of the immune microenvironment associated with 12 cell death modes and construction of a prognostic model for squamous cell lung cancer.

An increasing number of patients with lung squamous cell carcinoma (LUSC) are benefiting from immunotherapy. However, the individual immune profile of patients who respond to treatment is unclear. Multiple programmed cell death (PCD) patterns play an important role in the proliferation and differentiation of tumor cells, predicting the efficacy of immunotherapy using a risk model for programmed cell death gene combinations LUSC risk model. Genes associated with 12 types of PCD were analyzed to establish a prognostic model. Risk scores were calculated using PCDG-based expression profiles, and LUSC patients were classified into two groups. Tumor immune microenvironment (TIME) characteristics and immunotherapy responses were compared between the two groups. Finally, staging was predicted using the extreme gradient boosting tree algorithm (eXtreme Gradient Boosting, XGBoost), and an algorithmic model was constructed to predict the prognosis of LUSC patients based on the PCDG risk score. A stepwise downscaling of 1256 PCDGs was performed to screen out 16 genes associated with LUSC prognosis to construct a risk model. Immune cell infiltration levels, the immunotherapy response, and prognostic differences were different between these two groups of patients. The classification prediction model based on the XGBoost algorithm and the prognostic model based on the risk score were able to distinguish the risk subtypes and individual prognosis of LUSC patients, respectively. PCD patterns exert a crucial effect on the development of LUSC. An evaluation of different PCD patterns in LUSC improves the understanding of the characteristics of infiltrating immune cells and mutational features of the TIME, distinguishes LUSC patients who might benefit from immunotherapy, and predicts their future survival.