Multiple Regression Algorithm Research Articles

Prediction of successful weaning from renal replacement therapy in critically ill patients based on machine learning

Background Predicting the successful weaning of acute kidney injury (AKI) patients from renal replacement therapy (RRT) has emerged as a research focus, and we successfully built predictive models for RRT withdrawal in patients with severe AKI by machine learning. Methods This retrospective single-center study utilized data from our general intensive care unit (ICU) Database, focusing on patients diagnosed with severe AKI who underwent RRT. We evaluated RRT weaning success based on patients being free of RRT in the subsequent week and their overall survival. Multiple logistic regression (MLR) and machine learning algorithms were adopted to construct the prediction models. Results A total of 976 patients were included, with 349 patients successfully weaned off RRT. Longer RRT duration (7.0 vs. 9.6 d, p = 0.002, OR = 0.94), higher serum cystatin C levels (1.2 vs. 3.2 mg/L, p < 0.001, OR = 0.46), and the presence of septic shock (28.1% vs. 41.5%, p < 0.001, OR = 0.63) were associated with reduced likelihood of RRT weaning. Conversely, a positive furosemide stress test (FST) (60.2% vs. 40.7%, p < 0.001, OR = 2.75) and higher total urine volume 3 d before RRT withdrawal (755 vs. 125 mL/d, p < 0.001, OR = 2.12) were associated with an increased likelihood of successful weaning from RRT. Next, we demonstrated that machine learning models, especially Random Forest and XGBoost, achieving an AUROC of 0.95. The XGBoost model exhibited superior accuracy, yielding an AUROC of 0.849. Conclusion High-risk factors for unsuccessful RRT weaning in severe AKI patients include prolonged RRT duration. Machine learning prediction models, when compared to models based on multivariate logistic regression using these indicators, offer distinct advantages in predictive accuracy.

Textile wearable system for knee angle monitoring in three planes

Introduction&#x0D; Monitoring biomechanics is crucial in sports and rehabilitation, and frontal knee angle is of special interest in these applications. Current solutions – optical motion capture (OMC), or inertial measurement units suits – are costly, spatially constrained, and impractical for use in daily life. Textile-based wearable systems are a valuable alternative for unobtrusive movement monitoring. Textile-based wearables for knee angle monitoring have mostly been used for sagittal angle prediction, however, frontal knee angle measurement is more challenging. We investigated the design and performance of a smart garment for the detection of knee joint angles in three planes during different activities.&#x0D; Methods&#x0D; We equipped a pair of tight pants with four helical auxetic yarn capacitive strain sensors (Cuthbert et al., 2022) placed close to the knees. The exact positioning was optimized with an OMC study: markers were placed in potential sensor locations (Gholami et al., 2019) and the pairs of markers whose distance had the highest mutual information with knee angles were selected for sensor placement. A healthy participant performed walking and turning around, and knee ab/adduction activities wearing the sensorized prototype. The latter activity emphasized knee motion in the frontal and transverse planes. The capacitances from the sensors were recorded with a custom electronics board that transmitted data wirelessly to a smartphone. Multiple regression algorithms were implemented to predict knee angles from the strain sensors data, with the ground truth obtained from the OMC data recorded simultaneously during the experiments.&#x0D; Results&#x0D; The optimal sensor placements were above the kneecaps, orientated as the vastus medialis and the rectus femoris. Xgboost regression algorithm yielded best performance for walking with root mean square errors (RMSE) of 10.79°, 3.77°, and 2.49° for the sagittal, frontal, and transverse angles, respectively. Linear regression performed the best for knee ab/adduction with RMSEs of 8.96°, 6.33°, and 1.58° for the sagittal, frontal, and transverse angles (Fornaciari, 2023).&#x0D; Discussion/Conclusion&#x0D; The smart garment system was overall able to track the knee angle in three planes. The larger errors, compared with previous works (Gholami et al., 2019), reported for the walking and turning around movement are likely because of high variations in the movements of the participants during turning around. Additionally, the proposed system showed capability to monitor frontal and transverse angles with an average RMSE of 3.5°. The larger error values of the sagittal angles are likely because of higher range of motion in that plane. The proposed system allows for continuous and unobtrusive knee angle monitoring outside of the laboratory settings in the comfortable form factor of smart clothing.&#x0D; References&#x0D; Cuthbert, T. J., Hannigan, B. C., Roberjot, P., Shokurov, A. V., &amp; Menon, C. (2022). HACS: Helical auxetic yarn capacitive strain sensors with sensitivity beyond the theoretical limit. Advanced materials, 35(10) Article 2209321. https://doi.org/10.1002/adma.202209321&#x0D; Fornaciari, A. (2023). Wearable technology for lower limb movement monitoring [Master’s thesis]. Politecnico di Milano.&#x0D; Gholami, M., Rezaei, A., Cuthbert, T. J., Napier, C., &amp; Menon, C. (2019). Lower body kinematics monitoring in running using fabric-based wearable sensors and deep convolutional neural networks. Sensors, 19(23), Article 5325. https://doi.org/10.3390/s19235325

Multimodal Early Birth Weight Prediction Using Multiple Kernel Learning.

In this work, a novel multimodal learning approach for early prediction of birth weight is presented. Fetal weight is one of the most relevant indicators in the assessment of fetal health status. The aim is to predict early birth weight using multimodal maternal-fetal variables from the first trimester of gestation (Anthropometric data, as well as metrics obtained from Fetal Biometry, Doppler and Maternal Ultrasound). The proposed methodology starts with the optimal selection of a subset of multimodal features using an ensemble-based approach of feature selectors. Subsequently, the selected variables feed the nonparametric Multiple Kernel Learning regression algorithm. At this stage, a set of kernels is selected and weighted to maximize performance in birth weight prediction. The proposed methodology is validated and compared with other computational learning algorithms reported in the state of the art. The obtained results (absolute error of 234 g) suggest that the proposed methodology can be useful as a tool for the early evaluation and monitoring of fetal health status through indicators such as birth weight.

Sema4D as a biomarker for Predicting rheumatoid arthritis disease activity.

The semaphorins are membrane or secreted proteins first identified in neural development. Semaphorin 4D (Sema4D) is the first family member found to have immune properties. We evaluated the potential of Sema4D as a marker for rheumatoid arthritis (RA) disease activity, singly and in combination with other known biomarkers including rheumatoid factor (RF) and C-reactive protein (CRP). Three hundred and eleven RA patients were enrolled. The patients were divided into three groups based on their disease activity in 28 joints (DAS28): mild, moderate, and severe. The healthy group included 40 healthy individuals. SerumSema4D was measured by quantitative ELISA and the specificity and sensitivity of biomarkers were evaluated by generating a receiver operating characteristic (ROC) curve to analyze their diagnostic accuracy. Serum Sema4D levels in the moderate and severe RA groups were elevated significantly above those of the controls (P < 0.01), while levels in the mild RA and control groups did not differ significantly (P > 0.05). The Sema4D cutoff threshold was 15.7ng/ml when the DAS28 was applied as a reference. Compared to the erythrocyte sedimentation rate (ESR and CRP, Sema4D had the highest specificity (96.8%) and area under the curve (0.80) for diagnosing RA activity. The highest specificity (100%) for the biomarker combinations was obtained when Sema4D was combined with CRP and anti-CCP, the combination of the Sema4D combined with ESR and anti-CCP had the highest sensitivity (99.35%). According to this result, a new model for jointly calculating RA activity of Sema4D,anti-CCP and CRP was constructed. Meanwhile another model is established by using the method of multivariate analysis.Model comparison results showed the the multiple regression algorithm method fitted the patients' disease activity better. The serum Sema 4D level effectively reflects moderate to severe RA activity. Sema4D levels can be used together with conventional RA biomarkers to increase the diagnostic power of RA activity. The multiple regression algorithm method is promising in disease activity calculation.

The Criteria for Transition of Fluid to Nonlinear Flow for Fractured Rocks: The Role of Fracture Intersection and Aperture

Understanding the fluid pattern is of special significance for estimating the hydraulic conductivity of fractured rock masses. The nonlinearity of fluid flow in discrete fracture networks (DFNs) originates from inertial effects and is enhanced by complex geometric topologies, which produces additional viscous friction and is subject to inertia effects, consequently transitioning the fluid to the nonlinear flow regime. Therefore, it is important to obtain the critical conditions for the transition of a fluid from laminar to turbulent flow. To investigate the role of fracture aperture and fracture intersection on the onset of the transition of a fluid to nonlinear flow in fractured rocks, the fluid dynamic computation was performed by solving Navier–Stokes (N–S) equations in DFN models. The results show that the flow flux initially linearly correlates with the hydraulic gradient (J) and the permeability of DFNs initially remains constant. As the hydraulic gradient increases, the flow flux presents a strong nonlinear relationship with the hydraulic gradient, and the permeability decreases dramatically. In particular, significant inertial effects appear earlier with a large fracture aperture or a dense fracture intersection. A critical hydraulic gradient (Jc) is proposed to judge the onset of nonlinear flow. The mathematical expression of Jc and Forchheimer coefficients A and B involving the fracture aperture and fracture intersection density is established through a multiple regression algorithm. Finally, the reliability of the predictive model was verified by comparing the results of the prediction and fluid dynamic computation of a series of DFN models with well-known geometric distributions. The consistency of the fitted equations and a correlation coefficient greater than 0.9 between them indicate that the predictive model proposed in this study is reliable.

Improving the Landslide Susceptibility Prediction Accuracy by Using Genetic Algorithm Optimized Machine Learning Approach

Landslide susceptibility prediction is critical in open pit mines and geotechnical fields. Prediction accuracy is very essential to reduce the risk of slope instability. Traditional statistical learning methods have been widely used in early warning systems, but they cannot thoroughly explore the coupling effect among related factors, which often results in low prediction accuracy. This paper establishes an ensemble learning prediction model optimized by a genetic algorithm (GA) to determine landslide susceptibility more quickly and efficiently. The model is based on 290 sets of slope cases containing height (H), slope angle (α), unit weight (γ), cohesion (c), friction angle (φ), and pore water pressure (ru). Two common algorithms are incorporated into the ensemble learning model: Xgboost and gradient boosting decision tree (GBDT). The area under the curve (AUC) of GA-GBDT and GA-Xgboost were found to be 0.928 and 0.933, respectively, both of which could predict landslide susceptibility better. Compared with multiple logistic regression and other machine learning algorithms, both GA-GBDT and GA-Xgboost models perform better in terms of accuracy and applicability. The study results demonstrate that the developed optimized machine learning model can accurately predict landslide susceptibility and that the parameters should be optimized on a case-by-case basis to achieve more accurate results after building a suitable machine model. The optimization model proposed in this paper can be an effective new method for the intelligent prediction of landslide susceptibility.

Machine learning algorithms for prediction of entrapment efficiency in nanomaterials.

Exploitation of machine learning in predicting performance of nanomaterials is a rapidly growing dynamic area of research. For instance, incorporation of therapeutic cargoes into nanovesicles (i.e., entrapment efficiency) is one of the critical parameters that ensures proper entrapment of drugs in the developed nanosystems. Several factors affect the entrapment efficiency of drugs and thus multiple assessments are required to ensure drug retention, and to reduce cost and time. Supervised machine learning can allow for the construction of algorithms that can mine data available from earlier studies to predict performance of specific types of nanoparticles. Comparative studies that utilize multiple regression algorithms to predict entrapment efficiency in nanomaterials are scarce. Herein, we report on a detailed methodology for prediction of entrapment efficiency in nanomaterials (e.g., niosomes) using different regression algorithms (i.e., CatBoost, linear regression, support vector regression and artificial neural network) to select the model that demonstrates the best performance for estimation of entrapment efficiency. The study concluded that CatBoost algorithm demonstrated the best performance with maximum R2 score (0.98) and mean square error (< 10-4). Among the various parameters that possess a role in entrapment efficiency of drugs into niosomes, the results obtained from CatBoost model revealed that the drug:lipid ratio is the major contributing factor affecting entrapment efficiency, followed by the lipid:surfactant molar ratio. Hence, supervised machine learning may be applied for future selection of the components of niosomes that achieve high entrapment efficiency of drugs while minimizing experimental procedures and cost.

Identification of memory B-cell-associated miRNA signature to establish a prognostic model in gastric adenocarcinoma

BackgroundMemory B cells and microRNAs (miRNAs) play important roles in the progression of gastric adenocarcinoma (GAC), also known as stomach adenocarcinoma (STAD). However, few studies have investigated the use of memory B-cell-associated miRNAs in predicting the prognosis of STAD.MethodsWe identified the marker genes of memory B cells by single-cell RNA sequencing (scRNA-seq) and identified the miRNAs associated with memory B cells by constructing an mRNA‒miRNA coexpression network. Then, univariate Cox, random survival forest (RSF), and stepwise multiple Cox regression (StepCox) algorithms were used to identify memory B-cell-associated miRNAs that were significantly related to overall survival (OS). A prognostic risk model was constructed and validated using these miRNAs, and patients were divided into a low-risk group and a high-risk group. In addition, the differences in clinicopathological features, tumour microenvironment, immune blocking therapy, and sensitivity to anticancer drugs in the two groups were analysed.ResultsFour memory B-cell-associated miRNAs (hsa-mir-145, hsa-mir-125b-2, hsa-mir-100, hsa-mir-221) with significant correlations to OS were identified and used to construct a prognostic model. Time-dependent receiver operating characteristic (ROC) curve analysis confirmed the feasibility of the model. Kaplan‒Meier (K‒M) survival curve analysis showed that the prognosis was poor in the high-risk group. Comprehensive analysis showed that patients in the high-risk group had higher immune scores, matrix scores, and immune cell infiltration and a poor immune response. In terms of drug screening, we predicted eight drugs with higher sensitivity in the high-risk group, of which CGP-60474 was associated with the greatest sensitivity.ConclusionsIn summary, we identified memory B-cell-associated miRNA prognostic features and constructed a novel risk model for STAD based on scRNA-seq data and bulk RNA-seq data. Among patients in the high-risk group, STAD showed the highest sensitivity to CGP-60474. This study provides prognostic insights into individualized and precise treatment for STAD patients.

Predicting sea levels using ML algorithms in selected locations along coastal Malaysia

In consideration of the distinct behavior of machine learning (ML) algorithms, six well-defined ML used were carried out in this study for predicting sea level on a day-to-day basis. Data compiled from 1985 to 2018 was utilized for training and testing the developed models. An assessment of the multiple statistics-driven regression algorithms resulted such that each tested location was associated with a particular preferred model. The following were the developed best models for their respective study areas: In Peninsular Malaysia, the interactions linear regression model was the best at Pulau Langkawi (RMSE = 19.066), the Matern 5/2 gaussian process regression model at Geting (RMSE = 49.891), and the trilayered artificial neural network at Pulau Pinang (RMSE = 20.026), while the linear regression model was the best at Sandakan in Sabah, East Malaysia (RMSE = 14.054). Other metrics, such as MAE and R-square, were also at their best values, each providing its best values, further substantiating the RMSE respectively, at each of the study areas. These empirical statistics (or metrics) also revealed that despite employing sea level as the sole parameter, results obtained were exceptional better when utilizing a 7-day lag, regardless of the model used. Notably, lag variables with less than a 7-day lag could degrade the model's accuracy in representing ground reality. The study emphasizes the importance of thorough training and testing of ML to aid decision-makers in developing mitigation actions for the climate change phenomena of sea level rise through reliable ML.

The use of management accounting and financial accounting in financial management based on multiple linear regression algorithm

Abstract Artificial intelligence has had varying degrees of impact on various industries, and many traditional financial tasks have been replaced by artificial robots, which will inevitably lead to the transformation of financial accounting to management accounting, which is also the key to the continuous development of enterprises. Firstly, this paper proposes a multiple linear regression algorithm, which is solved by the classical least squares method, while the parity results of the least squares method are relatively stable and generally do not have valuation drift. Then, we analyze management accounting and financial accounting, analyze the importance of using both in enterprise financial management and propose some specific application paths based on this to provide help for enterprise financial management. Finally, a multiple regression algorithm is used to analyze management accounting and financial accounting data. The regression analysis results showed that the coefficient of management accounting and financial accounting change and the degree of competition was 0.7952, t=2.4457, F=5.9813, R2=0.0520, and management accounting and financial accounting change were not significantly influenced by the size of the enterprise and competition. This study improves the traditional accounting concept, establishes a perfect accounting system, realizes the integration of organizations, and pays attention to the importance of consolidating original resources to provide some theoretical guidance for the effective improvement of enterprise financial management quality.

Retracted: Research on Injury Causes and Prevention Effect of College Rowing Athletes Based on Multiple Regression and Residual Algorithm.

[This retracts the article DOI: 10.1155/2022/4896336.].

Application Of Multiple Regression Algorithm to Price Prediction Model: Taking Sailboat Price as An Example

The sailboat market is becoming more and more mature, but market price prediction is rarely studied. Therefore, on the basis of considering the characteristics of sailboats themselves, this paper also considers the influence of regional effects on sailboat prices from three aspects: taxation, interest rate and economic conditions. Multiple linear regression model was used to fit the data, and the weight size of each index was analyzed to study the impact of each index on sailboat price. The results show that: (1) the MAE of the monolithic sailboats in the test set is 8478.0. However, the MAE of catamaran is 10,868.4. The fitting results are good, indicating that the multiple linear regression model is suitable for predicting sailboat prices. (2) The weight of the two indicators, tax change rate and GDP per capita, is higher in monolithic sailboats. The weight of the expected growth rate is high but negative, indicating that monolithic sailboats are greatly affected by regional economic factors. (3) Among catamarans, only the GDP per capita is larger than that of monolithic sailboats. The effect of the rate of tax change on catamaran prices is almost negligible. The expected growth rate, although negative, is much smaller than monolithic sailboats. (4) The monolithic sailboats is much more affected by region than the catamaran. The results can provide guidance for the simulation and prediction of sailboat market prices.

Development and application of comprehensive evaluation model based on correlation analysis algorithm, multiple logistic regression and clustering algorithm - Taking glass composition analysis and identification as an example

Take glass as an example. In ancient times, when firing glass, in addition to the raw material quartz sand, chemical components such as stabilizer and flux need to be added. During the storage process of glass, the internal elements will exchange with the environmental elements in a large amount, resulting in the weathering of the glass surface. In this paper, the composition of ancient glass is analyzed and identified by establishing correlation analysis model, multiple logistic regression and cluster model. The results show that: (1) There is a high correlation between glass type and surface weathering. Lead barium glass is easy to be weathered, and high potassium glass is not easy to be weathered. (2) High-potassium glass and lead-barium glass have the highest classification accuracy when they are divided into two sub-categories. Therefore, glass can be divided into four categories: high-potassium I, high-potassium II, lead-barium I, and lead-barium II.

Predictors of effectiveness in the implementation of personalized use of therapeutic physical factors in patients with metabolic syndrome

BACKGROUND: A personalized approach to the use of therapeutic physical factors should take into account individual predictor biomarkers, which are predictive information regarding the effectiveness of the treatment, taking into account the initial state of the patient's reserve capabilities. The metabolic syndrome was defined as a model of a pathological condition characterized by reduced functional reserves. Previous studies have shown that transcranial magnetotherapy (TMT) and pulsed low-frequency exposure to an electrostatic field (INESP) have potential effectiveness in relation to the pathogenetic manifestations of the metabolic syndrome.&#x0D; AIM: The purpose of the study is to determine the predictors of effectiveness in the implementation of personalized combined use of TMT and INESP in patients with metabolic syndrome.&#x0D; MATERIALS AND METHODS: The study involved 100 patients with a diagnosis of metabolic syndrome established in accordance with clinical guidelines. All patients were divided into four groups of 25 by simple fixed randomization. The first group (control) received a placebo effect (imitation of physiotherapeutic effects with the device turned off) for 10 days of observation. Patients of the second group (comparison group 1) were exposed to a low frequency electrostatic field (INESP). The third group (comparison group 2) received transcranial magnetic therapy with a traveling magnetic field (TMT). Patients of the fourth group (main) were subjected to a combined effect of INESP and TMT. All patients before and after a course of physiotherapy underwent a comprehensive examination using functional, biochemical and hormonal methods. Statistical processing of the obtained results was carried out using the Statistica 12.6 software package using the algorithms of correlation and regression analyses.&#x0D; RESULTS: The analysis performed using the multiple regression algorithm made it possible to identify a cluster of independent variables in the form of an autonomic balance index, microcirculation index, body mass index and catalase activity, determined in the initial value of patients. The high efficiency of the combined use of TMT and INESP is achieved with a probability of at least 95% in patients with metabolic syndrome, the initial state of which is characterized by a level of the autonomic balance index below 1.7 conventional units. units, tissue perfusion parameter more than 14 perf. units, BMI value below 29 c.u. units and catalase activity above 90 units. аct. The results of the verification of the constructed information model convincingly prove its adequacy and objectively confirm compliance with the stated forecast requirements.&#x0D; CONCLUSION: It is concluded that the identified constellation of phenotypic patterns, which characterizes the state of the pathological process, reflects the main pathogenetic mechanisms that determine the severity of clinical and functional manifestations of metabolic syndrome. Evaluation of the initial values of the autonomic balance index, microcirculation index, body mass index and catalase activity in patients with metabolic syndrome makes it possible to predict the expected effectiveness of the course combined use of TMT and INESP.

Machine learning-based bladder effusion estimation model construction on intravesical pressure data

BackgroundThe volume of the bladder effusion is a crucial metric for monitoring patients with intermittent catheterization in, and it serves as a crucial benchmark for bladder rehabilitation training. Clinically, bladder effusion is mainly estimated by ultrasound, which is not convenient for real-time monitoring. It is essential to explore a real-time method for obtaining the intravesical effusion volume to maintain bladder function and rehabilitative training for patients. PurposePrevious clinical trials have demonstrated a close correlation between intravesical pressure and bladder effusion in patients. Currently, there are devices available in clinical practice that can monitor intravesical pressure in real-time. Hence, the aim of this study is to analyze the dynamic relationship between real-time intravesical pressure and bladder effusion and develop a predictive model for bladder effusion. MethodTo validate our hypothesis, we compiled a dataset comprising intravesical pressure curves and corresponding effusion information from patients. Relevant features were extracted from the dataset, and an effusion prediction model was constructed using multiple regression algorithms. The performance of these algorithms was evaluated using the dataset. Finally, we designed a clinical experiment and verified the practical error of the above model. ResultsWe conducted sufficient comparative experiments on two datasets. The gradient boosting regression (GBR) model performs the best on the prediction set of the multi-center merged dataset. It achieved an explained variance score index of 0.84 and a mean absolute error of 23.28 ml. Additionally, actual validation experiments were conducted on 18 patients using the GBR method, confirming the feasibility of this approach in clinical practice. ConclusionThis study verified the validity of our concept and pioneered a method for effusion prediction using intravesical pressure data with promising results. This study is expected to be of great assistance in maintaining bladder function and rehabilitative training for patients.

Novel method for obtaining transfer characteristics of subway-induced ground vibrations

Aiming at the multiple-input multiple-output vibration problem in rail transit, this paper presents a novel method for obtaining transfer characteristics of vehicle-induced vibrations. To verify its accuracy and applicability, the obtained transfer coefficients are further combined with vehicle-track coupling simulations to predict environmental vibrations under different conditions. The results prove that the transfer characteristics from the vibration source to the environment target can be accurately obtained through the multiple regression algorithm and superposition algorithm. Compared with the traditional numerical simulation method composed of both the vehicle-track coupling model and the track-tunnel-soil model, the coefficient of determination R-squared of the two methods in the time domain can reach above 0.9, and errors of the environment evaluation index in the frequency domain are within 0.2 dB. However, the computational effort has been reduced significantly without establishing a complex numerical model of the tunnel-soil (structure) system. Moreover, it is found that environmental vibrations on the ground surface are mainly affected by fastening forces in the vicinity of 60 m centered by the observation point. In particular, the proposed method is expected to supply a certain reference for predicting vibrations under multi-source load in mechanical science and civil engineering.

Predictive Analysis of Hospital Stay after Caesarean Section: A Single-Center Study.

Caesarean section (CS) rate has seen a significant increase in recent years, especially in industrialized countries. There are, in fact, several causes that justify a CS; however, evidence is emerging that non-obstetric factors may contribute to the decision. In reality, CS is not a risk-free procedure. The intra-operative, post-pregnancy risks and risks for children are just a few examples. From a cost point of view, it must be considered that CS requires longer recovery times, and women often stay hospitalized for several days. This study analyzed data from 12,360 women who underwent CS at the "San Giovanni di Dio e Ruggi D'Aragona" University Hospital between 2010 and 2020 by multiple regression algorithms, including multiple linear regression (MLR), Random Forest, Gradient Boosted Tree, XGBoost, and linear regression, classification algorithms and neural network in order to study the variation of the dependent variable (total LOS) as a function of a group of independent variables. We identify the MLR model as the most suitable because it achieves an R-value of 0.845, but the neural network had the best performance (R = 0.944 for the training set). Among the independent variables, Pre-operative LOS, Cardiovascular disease, Respiratory disorders, Hypertension, Diabetes, Haemorrhage, Multiple births, Obesity, Pre-eclampsia, Complicating previous delivery, Urinary and gynaecological disorders, and Complication during surgery were the variables that significantly influence the LOS. Among the classification algorithms, the best is Random Forest, with an accuracy as high as 77%. The simple regression model allowed us to highlight the comorbidities that most influence the total LOS and to show the parameters on which the hospital management must focus for better resource management and cost reduction.

Can chronic kidney disease staging early predict outcome of large-artery ischemic stroke with impaired renal function?

Ischemic stroke poses a major threat to human beings, and a prompt intravenous thrombolytic management remains the gold standard protocol for stroke sufferers. Although the role of thrombolytic therapy (r-tPA) for ischemic stroke patients and those with underlying impaired renal function has been advocated as effective treating strategy, there is still a lack of investigation as to finding out baseline important variables that are capable of early outcome prediction. In this project, we hypothesize that the change of clinical chronic kidney disease (CKD) staging (delta stage = CKD stage after 3-month follow-up - CKD stage at admission) could serve as a crucial predictor of the prognosis of patients. This is a cohort longitudinal retrospective study. A total of 765 cerebral artery ischemic stroke patients with impaired renal function were recruited and followed up for 1 year. Among them, 116 had received the thrombolytic treatment (r-tPA) after being evaluated at the triage in the emergency department and the rest had not (non-r-tPA). Propensity-matching was applied to compare the mortality between the r-tPA and non-r-tPA groups. Multiple logistic regression (LR) and decision tree (DT) algorithm were used to identify important prediction factors for mortality as well as the improvement in neurological function. The 1-year mortality rates for r-tPA and non-r-tPA groups were 32.8% and 44.4%, respectively. The propensity-matched odds ratio of mortality for the r-tPA group compared with the non-r-tPA group is 0.469, with p = 0.003. Logistic regressions suggest that age, Hct, diabetes mellitus type 2, coronary artery disease, and delta stage are important factors for mortality for the non-r-tPA group, whereas age, diabetes mellitus type 2, chronic heart failure, hospital day, and delta stage are important factors for the r-tPA group. On the usage of antihypertensive drugs, ACEI/ARB was not associated with mortality (p = 0.198), whereas the diuretic was, with odds ratio at 1.619 (p = 0.025), indicating higher mortality after administration. Both LR and DT analyses indicate that delta stage is the most important predictor. For the r-tPA group, patients with delta stage ⩽0 had a 24% mortality, while that for delta stage >0 the mortality is 75%. For non-r-tPA patients, the corresponding mortalities were 30.9 and 66.3, respectively. Delta stage is also useful for predicting patients' improvement of neurological function, assessed by NIHSS, mRS, and Barthel Index. The areas under the curve for the three assessments are 0.83, 0.835, and 0.663, respectively. Large-artery ischemic stroke patients who received thrombolytic treatment had significantly lower mortality, even when presenting underlying impaired renal function. The change of CKD staging (delta stage) is capable of acting as a powerful clinical baseline surrogate for both r-tPA and non-r-tPA patients in terms of early outcome prediction. Long-term use of diuretics could be potentially harmful to this group of patients. Moreover, delta stage correlates well with clinical long-term neurological functionality assessment (NIHSS, mRS, and Barthel index), which is helpful in aiding urgent clinical decision-making.

Багатокласовий класифікатор на основі бінарних логістичних регресій, одержаних за принципами МГУА

Introduction. The issue of accuracy improvement in classification tasks is always topical, and various approaches have been developed, applied in accordance with the peculiarities of the problem formulation and properties of the feature space. Among the most effective models, classifiers based on multiple logistic regressions have proved themselves. Purpose. The aim of the paper is to develop an algorithm for solving multiclassification problems on the basis of binary logistic models built by the stepwise multiple logistic regression algorithm of the Stepwise type, improved according to the principles of the method of group accounting of arguments. Methods. The paper proposes a modification of the stepwise algorithm for creating binary multivariate logistic regressions Stepwise, where it is proposed to optimize the algorithm parameters in accordance with the principles of the method of group consideration of arguments: significance levels by the logarithmic likelihood ratio test for inclusion and exclusion of model arguments. The choice of optimal parameters is realized in accordance with an external criterion that takes into account the balance of classification accuracy of training and test samples and the balance of class classification accuracy. Subsequently, the binary class models obtained by the one-versus-all principle are combined into a multiclass classifier that returns the answer according to the maximum likelihood of the class. The comparison of classification models obtained by the classical Stepwise algorithm and the one proposed in the robot is carried out on the medical data of the publicly available Internet resource Kaggle. Conclusion. The paper substantiates and demonstrates the advantages of classifiers based on logistic multivariate regressions optimized according to the principles of the method of group consideration of arguments relative to the classical version of the Stepwise algorithm. The effective application of the algorithm in solving multiclass classification problem is shown.

Machine learning for the analysis of quality of life using the World Happiness Index and Human Development Indicators

Machine learning algorithms play an important role in analyzing complex data in research across various fields. In this paper, we employ multiple regression algorithms and statistical techniques to investigate the relationship between objective and subjective quality of life indicators and reveal the key factors affecting happiness at the international level based on data from the Human Development Index and the World Happiness Index covering the period from 2015 to 2021. The Pearson correlation analysis showed that happiness is related to the HDI score and GNI per capita. The best-performing model for forecasting happiness was the random forest regression, with a R2 score of 0.93667, a mean squared error of 0.0033048, and a root mean squared error of 0.05748, followed by the XGBoost regression and the Decision Tree regression, respectively. These models indicated that GNI per capita is the most significant feature in predicting happiness.