A comparison of program complexity prediction models

Objective: The present study aimed to analyze the treatment outcomes and develop a predictive model of surgical treatment for gastric cancer, taking into account the comorbidity of patients. Material and Methods. The treatment outcomes were studied in 477 (100 %) gastric cancer patients. Patients were stratifed into two groups according to the Age-Adjusted Charlson Comorbidity Index (ACCI) (0–4 points – 311 (65,2 %), more than 4 points – 166 (34,8 %) patients). Two hundred and seventy six patients (57.9 %) underwent distal or total gastrectomy, 178 (37.3 %) total gastrectomy, 19 (4 %) minimally invasive gastrectomy, and 4 (0.8 %) patients underwent extirpation of the gastric stump. The construction of models for the prognosis of surgical treatment was carried out using binary logistic regression, the comparison of models – by analyzing error curves (ROC-analysis). Results. The incidence rate of postoperative complications (grade III-V) according to the Clavien-Dindo classifcation was signifcantly higher in group 2 (9.9 %, 47/477) compared to group 1 (2.1 %, 10/477) (χ2 =64.79, p<0.001; OR 11.9 [5.82–24.3]). Postoperative mortality rate was 0.2 % (1/477) in group 1 and 1.9 % (9/477) in group 2 (χ2 =13.7, p<0.001; OR 17.8 [2.23–142]). In a comparative analysis, the prognostic model, taking into account the ACCI of the patient, allowed prediction of the development of postoperative grade III–V complications according to the Clavien-Dindo with the greatest accuracy. The area under the curve (AUC) was 0.921 ± 0.01 (95 % CI: 0,96–0,998), sensitivity – 71.9 %, specifcity – 99.8 %, diagnostic accuracy – 96.4 %. Conclusion. The inclusion of comorbidity in gastric cancer patients in the predictive concept makes it possible to improve the accuracy of prediction of postoperative complications of III–V grade according to Clavien-Dindo.

This study presents a comprehensive comparison of multiple time-series models applied to physiological metric predictions. It aims to explore the effectiveness of both statistical prediction models and pharmacokinetic-pharmacodynamic prediction model and modern deep learning approaches. Specifically, the study focuses on predicting the bispectral index (BIS), a vital metric in anesthesia used to assess the depth of sedation during surgery, using datasets collected from real-life surgeries. The goal is to evaluate and compare model performance considering both univariate and multivariate schemes. Accurate BIS prediction is essential for avoiding under- or over-sedation, which can lead to adverse outcomes. The study investigates a range of models: The traditional mathematical models include the pharmacokinetic-pharmacodynamic model and statistical models such as autoregressive integrated moving average (ARIMA) and vector autoregression (VAR). The deep learning models encompass recurrent neural networks (RNNs), specifically Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), as well as Temporal Convolutional Networks (TCNs) and Transformer models. The analysis focuses on evaluating model performance in predicting the BIS using two distinct datasets of physiological metrics collected from actual surgical procedures. It explores both univariate and multivariate prediction schemes and investigates how different combinations of features and input sequence lengths impact model accuracy. The experimental findings reveal significant performance differences among the models: In univariate prediction scenarios for predicting BIS, the LSTM model demonstrates a 2.88% improvement over the second-best performing model. For multivariate predictions, the LSTM model outperforms others by 6.67% compared to the next best model. Furthermore, the addition of Electromyography (EMG) and Mean Arterial Pressure (MAP) brings significant accuracy improvement when predicting BIS. The study emphasizes the importance of selecting and building appropriate time-series models to achieve accurate predictions in biomedical applications. This research provides insights to guide future efforts in improving vital sign prediction methodologies for clinical and research purposes. Clinically, with improvements in the prediction of physiological parameters, clinicians can be informed of interventions if an anomaly is detected or predicted.

The leaf spotting diseases in wheat that include Septoria tritici blotch (STB) caused by , Stagonospora nodorum blotch (SNB) caused by , and tan spot (TS) caused by pose challenges to breeding programs in selecting for resistance. A promising approach that could enable selection prior to phenotyping is genomic selection that uses genome-wide markers to estimate breeding values (BVs) for quantitative traits. To evaluate this approach for seedling and/or adult plant resistance (APR) to STB, SNB, and TS, we compared the predictive ability of least-squares (LS) approach with genomic-enabled prediction models including genomic best linear unbiased predictor (GBLUP), Bayesian ridge regression (BRR), Bayes A (BA), Bayes B (BB), Bayes Cπ (BC), Bayesian least absolute shrinkage and selection operator (BL), and reproducing kernel Hilbert spaces markers (RKHS-M), a pedigree-based model (RKHS-P) and RKHS markers and pedigree (RKHS-MP). We observed that LS gave the lowest prediction accuracies and RKHS-MP, the highest. The genomic-enabled prediction models and RKHS-P gave similar accuracies. The increase in accuracy using genomic prediction models over LS was 48%. The mean genomic prediction accuracies were 0.45 for STB (APR), 0.55 for SNB (seedling), 0.66 for TS (seedling) and 0.48 for TS (APR). We also compared markers from two whole-genome profiling approaches: genotyping by sequencing (GBS) and diversity arrays technology sequencing (DArTseq) for prediction. While, GBS markers performed slightly better than DArTseq, combining markers from the two approaches did not improve accuracies. We conclude that implementing GS in breeding for these diseases would help to achieve higher accuracies and rapid gains from selection.

Students who are not-active will affect the number of students who graduate on time. Prevention of not-active students can be done by predicting student performance. The study was conducted by comparing the KNN, SVM, and Decision Tree algorithms to obtain the best predictive model. The model making process was carried out by the following steps: data collecting, pre-processing, model building, comparison of models, and evaluation. The results show that the SVM algorithm has the best accuracy in predicting with a precision value of 95%. The Decision Tree algorithm has a prediction accuracy of 93% and the KNN algorithm has a prediction accuracy value of 92%.

With the disclosure of the important role of substructural alerts (SA) in drug development and toxicity evaluation, many automatic substructure extraction tools based on different theoretical knowledge have been reported in recent years. To compare the emphasis of various substructure extraction methods and the reliability of their results, we were encouraged to conduct a comprehensive analysis of seven representative tools to find the best one. In this paper, we introduced a well-designed evaluation of seven popular tools (Bioalerts, KRFP, MoSS, PySmash_circular, PySmash_group, PySmash_path, and SARpy) based on 43 toxicity datasets, consisting of four components: comparison of substructures derived by different methods, comparison of predictive models based on substructural rules, comparison of the efficiency of extracting toxic substructures, and the effect of SAs on quantitative structure-activity relationship (QSAR) predictive models. The results demonstrated that PySmash_circular performed best overall, with satisfactory results in substructure information carrying and the rule-based predictive models. PySmash_path and Bioalerts were also recommended for their similar performance to PySmash_circular, but the main problem was that they took too much time and generated too many substructures. Specifically, Bioalerts and PySmash_circular could obtain substructures carrying richer information, while SARpy had the best predictive rule-based models, but it only focuses on precision (PR) value in the evaluation of individual SA. More than that, the substructures obtained by all 7 methods can enhance the recognition ability of the QSAR models for toxic compounds and make them interpretable. Finally, we have also made a baseline substructure set of 43 toxicity endpoints available to the public to facilitate further development of drug research and environmental safety assessment in a rapid and accurate direction.Scientific Contribution: Based on 43 toxicity datasets, we conducted a comprehensive evaluation of 7 representative substructure extraction tools from both the perspective of individual substructure and substructure-based models. This work not only enables users to make more autonomous choices of the optimal substructure extraction tool, but also provides the public with a benchmark substructure set of 43 toxicity endpoints, promoting the further development of computational toxicology.

Sepsis is one of the major causes of neonatal deaths worldwide. Majority of these neonatal deaths occurs in resource-poor countries due to inaccessibility of hospitals and absence of laboratories. Blood culture which is the gold standard to confirm sepsis is time-consuming and requires the presence of a laboratory. To start the antimicrobial therapy at the earliest, prediction models have been developed. A vast number of available prediction models require laboratory tests and cannot be used in the developing countries where such facilities do not exist. Therefore, there is a need for non-invasive prediction models. The objectives of this study are as follows: - (i) to train and test non-invasive prediction models for neonatal sepsis (ii) to compare the performance of the invasive with non-invasive prediction models. For this retrospective study, we extracted the data of 1446 neonates from the Medical Information Mart for Intensive Care (MIMIC) III data set. We trained and tested six prediction models using this data set. Three of these six models were trained using non-invasive parameters (model LR(NI), model ANN(NI) and model MDA(NI)) and three were trained using invasive and non-invasive parameters (model LR(O), model ANN(O) and model MDA(O)). The sensitivity of model LR(NI), model ANN(NI), model MDA(NI), model LR(O), model ANN(O) and model MDA(O) at their optimum threshold values were 81.68%, 79.39%, 82.44%, 77.10%, 79.39% and 78.63% respectively. Whereas, specificity of the above mentioned models were 82.27%, 81.82%, 80.00%, 84.77%, 82.05% and 78.30% respectively. To decrease the neonatal mortality rate in resource-poor areas one may use non-invasive prediction models where invasive parameters are not available due to lack of resources, as shown by our study that non-invasive prediction models can achieve similar predictive capability as the invasive prediction models.

Machine learning facilitates predictive maintenance due to the advantages it holds over traditional methods of maintaining semi-conductor devices such as preventive and breakdown maintenance. Several predictive models using machine learning on the Semiconductor Manufacturing process dataset (SECOM) will be applied in this paper. The dataset contains the information related to semiconductor manufacturing process, with the attributes corresponding to signals collected from semiconductor devices. Due to the high-dimensionality of the data and class imbalance problem in the SECOM dataset, it poses several challenges related to data pre-processing, which is an essential step incorporated in this work while applying various machine learning models. Comparison and analysis of various predictive machine learning classification models were carried out based on the performance metrics like, accuracy and Receiver Operating Characteristic (ROC) curve.

Autocorrelation offsets zero-inflation in models of tropical saplings density

The paper presents a predictive models management system called DeVisa that offers online services such as: scoring, model composition, model comparison, search and statistics. For the purpose of interaction between the consumer applications and the DeVisa system a XML-based language called PMQL is defined. The paper focuses on the scoring service as an online knowledge provider, analyzes the challenges in achieving this objective and the solutions that were found. From a technological perspective DeVisa uses a native XML database system for storing the predictive models expressed in PMML and an XQuery library for processing the models. All the functionality is provided via Web Services.

This study aims to identify the most accurate prediction model for the possibility of victory from the annual average data of 25 seasons (1993–2017) of the Ladies Professional Golf Association (LPGA), and to determine the importance of the predicting factors. The four prediction models considered in this study were a decision tree, discriminant analysis, logistic regression, and artificial neural network analysis. The mean difference in the classification accuracy of these models was analyzed using SPSS 22.0 software (IBM Corp., Armonk, NY, USA) and the one-way analysis of variance (ANOVA). When the prediction was based on technical variables, the most important predicting variables for determining victory were greens in regulation (GIR) and putting average (PA) in all four prediction models. When the prediction was based on the output of the technical variables, the most important predicting variable for determining victory was birdies in all four prediction models. When the prediction was based on the season outcome, the most important predicting variables for determining victory were the top 10 finish% (T10) and official money. A significant mean difference in classification accuracy was observed while performing the one-way ANOVA, and the least significant difference post-hoc test showed that artificial neural network analysis exhibited higher accuracy than the other models, especially, for larger data sizes. From the results of this study, it can be inferred that the player who wants to win the LPGA should aim to increase GIR, reduce PA, and improve driving distance and accuracy through training to increase the birdies chance at each hole, which can lead to lower average strokes and increased possibility of being within T10.

Aim: To compare the value of predictive power of the models for central cervical lymph node metastasis (CLNM) in papillary thyroid carcinomas (PTCs). Patients & methods: 220 PTCs were prospectively enrolled into the study with pathological examination. We established a new risk model with univariate and multivariate analyses and receiver-operating characteristic curves were plotted. Z-test was performed to compare the area under two curves and validated the predictive model for central CLNM in PTCs. The comparison of previous and new predictive model was analyzed. Results: Microcalcification, capsule contact or involvement, internal flow and BRAFV600E mutation were four independent risk factors for PTCs with central CLNMs. The area under the curves for the new and the previous model were 0.948 and 0.934 (p = 0.572), respectively. Conclusion: Two predictive models showed strong consistency in predicting central CLNM in PTCs. The predictive model may be helpful in selecting appropriate treatment method in PTCs.

Objective: Objectively and efficiently measuring physical activity is a common issue facing the fields of medicine, public health, education, and sports worldwide. In response to the problem of low accuracy in predicting energy consumption during human motion using accelerometers, a prediction model for asynchronous energy consumption in the human body is established through various algorithms, and the accuracy of the model is evaluated. The optimal energy consumption prediction model is selected to provide theoretical reference for selecting reasonable algorithms to predict energy consumption during human motion. Methods: A total of 100 subjects aged 18-30years participated in the study. Experimental data for all subjects are randomly divided into the modeling group (n = 70) and validation group (n = 30). Each participant wore a triaxial accelerometer, COSMED Quark pulmonary function tester (Quark PFT), and heart rate band at the same time, and completed the tasks of walking (speed range: 2km/h, 3km/h, 4km/h, 5km/h, and 6km/h) and running (speed range: 7km/h, 8km/h, and 9km/h) sequentially. The prediction models were built using accelerometer data as the independent variable and the metabolic equivalents (METs) as the dependent variable. To calculate the prediction accuracy of the models, root mean square error (RMSE) and bias were used, and the consistency of each prediction model was evaluated based on Bland-Altman analysis. Results: The linear equation, logarithmic equation, cubic equation, artificial neural network (ANN) model, and walking-and-running two-stage model were established. According to the validation results, our proposed walking-and-running two-stage model showed the smallest overall EE prediction error (RMSE = 0.76METs, Bias = 0.02METs) and the best performance in Bland-Altman analysis. Additionally, it had the lowest error in predicting EE during walking (RMSE = 0.66METs, Bias = 0.03METs) and running (RMSE = 0.90METs, Bias < 0.01METs) separately, as well as high accuracy in predicting EE at each single speed. Conclusion: The ANN-based walking-and-running two-stage model established by separating walking and running can better estimate the walking and running EE, the improvement of energy consumption prediction accuracy will be conducive to more accurate to monitor the energy consumption of PA.

Introduction: This study will systematically search and evaluate the prediction models for unplanned interruption of continuous renal replacement treatment (CRRT) and to provide a reference for building a higher quality prediction model for unplanned interruption of CRRT. Methods: PubMed, Embase, Cochrane Library, CINAHL, China National Knowledge Infrastructure (CNKI), SinoMed, and Wanfang Database were systematically searched for studies on prediction models for unexpected interruption of CRRT. The languages were limited to Chinese and English. The search time limit was from the establishment of the database to June 30, 2023. Two researchers screened the literature and extracted the data independently, and the risk of bias and applicability of the included literature were analyzed using the risk of bias assessment tool for predictive model studies. Results: A total of nine studies were included, and the area under the receiver operating characteristic curve ranged from 0.679 to 0.997. The applicability of the prediction model in seven studies was good and in two studies was poor. Conclusion: More attention should be paid to the effectiveness of different risk assessment methods in future construction, so as to obtain better risk prediction models with high accuracy and provide certain reference and basis for formulating relevant prevention strategies.

BackgroundCancer prognosis prediction is valuable for patients and clinicians because it allows them to appropriately manage care. A promising direction for improving the performance and interpretation of expression-based predictive models involves the aggregation of gene-level data into biological pathways. While many studies have used pathway-level predictors for cancer survival analysis, a comprehensive comparison of pathway-level and gene-level prognostic models has not been performed. To address this gap, we characterized the performance of penalized Cox proportional hazard models built using either pathway- or gene-level predictors for the cancers profiled in The Cancer Genome Atlas (TCGA) and pathways from the Molecular Signatures Database (MSigDB).ResultsWhen analyzing TCGA data, we found that pathway-level models are more parsimonious, more robust, more computationally efficient and easier to interpret than gene-level models with similar predictive performance. For example, both pathway-level and gene-level models have an average Cox concordance index of ~ 0.85 for the TCGA glioma cohort, however, the gene-level model has twice as many predictors on average, the predictor composition is less stable across cross-validation folds and estimation takes 40 times as long as compared to the pathway-level model. When the complex correlation structure of the data is broken by permutation, the pathway-level model has greater predictive performance while still retaining superior interpretative power, robustness, parsimony and computational efficiency relative to the gene-level models. For example, the average concordance index of the pathway-level model increases to 0.88 while the gene-level model falls to 0.56 for the TCGA glioma cohort using survival times simulated from uncorrelated gene expression data.ConclusionThe results of this study show that when the correlations among gene expression values are low, pathway-level analyses can yield better predictive performance, greater interpretative power, more robust models and less computational cost relative to a gene-level model. When correlations among genes are high, a pathway-level analysis provides equivalent predictive power compared to a gene-level analysis while retaining the advantages of interpretability, robustness and computational efficiency.

Commentary: Machine learning and cardiac surgery risk prediction