暂无摘要。

Using mathematical models of physiological systems in medicine has allowed for the development of diagnostic, treatment, and medical educational tools. However, their complexity restricts, in most cases, their application for predictive, preventive, and personalized purposes. Although there are strategies that reduce the complexity of applying models based on fitting techniques, most of them are focused on a single instant of time, neglecting the effect of the system\'s temporal evolution. The objective of this research was to introduce a dynamic fitting strategy for physiological models with an extensive array of parameters and a constrained amount of experimental data. The proposed strategy focused on obtaining better predictions based on the temporal trends in the system\'s parameters and being capable of predicting future states. The study utilized a cardiorespiratory model as a case study. Experimental data from a longitudinal study of healthy adult subjects undergoing aerobic exercise were used for fitting and validation. The model predictions obtained in a steady state using the proposed strategy and the traditional single-fit approach were compared. The most successful outcomes were primarily linked to the proposed strategy, exhibiting better overall results regarding accuracy and behavior than the traditional population fitting approach at a single instant in time. The results evidenced the usefulness of the dynamic fitting strategy, highlighting its use for predictive, preventive, and personalized applications.

Soil erodibility (K) is an essential component in estimating soil loss indicating the soil\'s susceptibility to detach and transport. Data Computing and processing methods, such as artificial neural networks (ANNs) and multiple linear regression (MLR), have proven to be helpful in the development of predictive models for natural hazards. The present case study aims to assess the efficiency of MLR and ANN models to forecast soil erodibility in Peninsular Malaysia. A total of 103 samples were collected from various sites and K values were calculated using the Tew equation developed for Malaysian soil. From several extracted parameters, the outcomes of correlation and principal component analysis (PCA) revealed the influencing factors to be used in the development of ANN and MLR models. Based on the correlation and PCA results, two sets of influencing factors were employed to develop predictive models. Two MLR (MLR-1 and MLR-2) models and four neural networks (NN-1, NN-2, NN-3, and NN-4) optimized using Levenberg-Marquardt (LM) and scaled conjugate gradient (SCG) were developed and evaluated. The model performance validation was conducted using the coefficient of determination (R2), mean squared error (MSE), root mean squared error (RMSE), and Nash-Sutcliffe efficiency coefficient (NSE). The analysis showed that ANN models outperformed MLR models. The R2 values of 0.446 (MLR-1), 0.430 (MLR-2), 0.894 (NN-1), 0.855 (NN-2), 0.940 (NN-3), and 0.826 (NN-4); MSE values of 0.0000306 (MLR-1), 0.0000315 (MLR-2), 0.0000158 (NN-1), 0.0000261 (NN-2), 0.0000318 (NN-3), and 0.0000216 (NN-4) suggested the higher accuracy and lower modelling error of ANN models as compared with MLR. This study could provide an empirical basis and methodological support for K factor estimation in the region.

UNASSIGNED: Acquisition of dosimetric knowledge by radiation therapy planners is a protracted and complex process. This study delves into the impact of empirical predictive models based on the knowledge-based planning (KBP) methodology, aimed at detecting suboptimal results and homogenizing and improving existing practices for prostate cancer. Moreover, the dosimetric effect of implementing these models into routine clinical practice was also assessed.
UNASSIGNED: Based on the KBP method, we analyzed 25 prostate treatment plans performed using VMAT by expert operators, aiming to correlate dose indicators with patient geometry. The DavgCav(Gy), V45GyCav(cc), and V15GyCav(cc) of the peritoneal cavity and the V60Gy(%) and V70Gy(%) of the rectum and bladder were linked to geometric characteristics such as the distance from the planning target volume (PTV) to the organs at risk (OAR), the volume of the OAR, or the overlap between the PTV and the OAR. In the second phase, the KBP was used in routine clinical practice in a prospective cohort of 25 patients and compared with the 41 patient plans calculated before implementing the tool.
UNASSIGNED: Using linear regression, we identified strong geometric predictive factors for the peritoneal cavity, rectum, and bladder (R2 > 0.8), with an average prescribed dose of 97.8%, covering 95% of the target volume. The use of the model led to a significant dose reduction (Δ) for all evaluated OARs. This trend was most notable for ΔV15GyCav=-171.5 cc (p=0.003). Significant reductions were also obtained in average doses to the rectum and bladder, ΔDavgRect= -2.3 Gy (p=0.040), and ΔDavgVess= -3.3 Gy (p=0.039) respectively. Based on this model, we reduced the number of plans with OAR constraints above the clinical recommendations from 19% to 8%.
UNASSIGNED: The KBP methodology established a robust and personalized predictive model for dose estimation to organs at risk in prostate cancer. Implementing the model resulted in improved sparing of these organs. Notably, it yields a solid foundation for harmonizing dosimetric practices, alerting us to suboptimal results, and improving our knowledge.

This study aims to employ the supervised machine learning algorithms to examine factors that negatively impacted academic performance among college students on probation (underperforming students). We used the Knowledge Discovery in Databases (KDD) methodology on a sample of N = 6514 college students spanning 11 years (from 2009 to 2019) provided by a major public university in Oman. We used the Information Gain (InfoGain) algorithm to select the most effective features and ensemble methods to compare the accuracy with more robust algorithms, including Logit Boost, Vote, and Bagging. The algorithms were evaluated based on the performance evaluation metrics such as accuracy, precision, recall, F-measure, and ROC curve, and then validated using 10-folds cross-validation. The study revealed that the main identified factors affecting student academic achievement include study duration in the university and previous performance in secondary school. Based on the experimental results, these features were consistently ranked as the top factors that negatively impacted academic performance. The study also indicated that gender, estimated graduation year, cohort, and academic specialization significantly contributed to whether a student was under probation. Domain experts and other students were involved in verifying some of the results. The theoretical and practical implications of this study are discussed.

Pregnane X receptor (PXR), extensively expressed in human tissues related to digestion and metabolism, is responsible for recognizing and detoxifying diverse xenobiotics encountered by humans. To comprehend the promiscuous nature of PXR and its ability to bind a variety of ligands, computational approaches, viz., quantitative structure-activity relationship (QSAR) models, aid in the rapid dereplication of potential toxicological agents and mitigate the number of animals used to establish a meaningful regulatory decision. Recent advancements in machine learning techniques accommodating larger datasets are expected to aid in developing effective predictive models for complex mixtures (viz., dietary supplements) before undertaking in-depth experiments. Five hundred structurally diverse PXR ligands were used to develop traditional two-dimensional (2D) QSAR, machine-learning-based 2D-QSAR, field-based three-dimensional (3D) QSAR, and machine-learning-based 3D-QSAR models to establish the utility of predictive machine learning methods. Additionally, the applicability domain of the agonists was established to ensure the generation of robust QSAR models. A prediction set of dietary PXR agonists was used to externally-validate generated QSAR models. QSAR data analysis revealed that machine-learning 3D-QSAR techniques were more accurate in predicting the activity of external terpenes with an external validation squared correlation coefficient (R2) of 0.70 versus an R2 of 0.52 in machine-learning 2D-QSAR. Additionally, a visual summary of the binding pocket of PXR was assembled from the field 3D-QSAR models. By developing multiple QSAR models in this study, a robust groundwork for assessing PXR agonism from various chemical backbones has been established in anticipation of the identification of potential causative agents in complex mixtures.

BACKGROUND: This study evaluates the effectiveness of a targeted telephone-based case management service that aimed to reduce ED attendance amongst frequent attenders, known to disproportionately contribute to demand. Evidence on the effectiveness of these services varies.
METHODS: A 24-month controlled before-and-after study, following 808 patients (128 cases and 680 controls (41 were non-compliant)) who were offered the service in the first four months of operation within a UK ED department. Patients stratified as high-risk of reattending ED within 6 months by a predictive model were manually screened. Those positively reviewed were offered a non-clinical, nurse-led, telephone-based health coaching, consisting of care planning, coordination and goal setting for up to 9 months. Service effectiveness was estimated using a difference-in-differences (DiD) analysis. Incident rate of ED and Minor Injury Unit (MIU) attendances and average length of stay in intervention recipients and controls over 12 months after receiving their service offer following ED attendance were compared, adjusting for the prior 12-month period, sex and age, to give an incidence rate ratio (IRR).
RESULTS: Intervention recipients were more likely to be female (63.3% versus 55.4%), younger (mean of 69 years versus 76 years), and have higher levels of ED activity (except for MIU) than controls. Mean rates fell between periods for all outcomes (except for MIU attendance). The Intention-to-Treat analysis indicated non-statistically significant effect of the intervention in reducing all outcomes, except for MIU attendances, with IRRs: ED attendances, 0.856 (95% CI: 0.631, 1.160); ED admissions, 0.871 (95% CI: 0.628, 1.208); length of stay for emergency and elective admissions: 0.844 (95% CI: 0.619, 1.151) and 0.781 (95% CI: 0.420, 1.454). MIU attendance increased with an IRR: 2.638 (95% CI: 1.041, 6.680).
CONCLUSIONS: Telephone-based health coaching appears to be effective in reducing ED attendances and admissions, with shorter lengths of stay, in intervention recipients over controls. Future studies need to capture outcomes beyond acute activity, and better understand how services like this provide added value.

Industry 4.0 constitutes a major application domain for sensor data analytics. Industrial furnaces (IFs) are complex machines made with special thermodynamic materials and technologies used in industrial production applications that require special heat treatment cycles. One of the most critical issues while operating IFs is the emission of black carbon (EoBC), which is due to a large number of factors such as the quality and amount of fuel, furnace efficiency, technology used for the process, operation practices, type of loads and other aspects related to the process conditions or mechanical properties of fluids at furnace operation. This paper presents a methodological approach to predict EoBC during the operation of IFs with the use of predictive models of machine learning (ML). We make use of a real data set with historical operation to train ML models, and through evaluation with real data we identify the most suitable approach that best fits the characteristics of the data set and implementation constraints in real production environments. The evaluation results confirm that it is possible to predict the undesirable EoBC well in advance, by means of a predictive model. To the best of our knowledge, this paper is the first approach to detail machine-learning concepts for predicting EoBC in the IF industry.

BACKGROUND: Fluoropyrimidine plus platinum chemotherapy remains the standard first line treatment for gastric cancer (GC). Guidelines exist for the clinical interpretation of four DPYD genotypes related to severe fluoropyrimidine toxicity within European populations. However, the frequency of these single nucleotide polymorphisms (SNPs) in the Latin American population is low (< 0.7%). No guidelines have been development for platinum. Herein, we present association between clinical factors and common SNPs in the development of grade 3-4 toxicity.
METHODS: Retrospectively, 224 clinical records of GC patient were screened, of which 93 patients were incorporated into the study. Eleven SNPs with minor allelic frequency above 5% in GSTP1, ERCC2, ERCC1, TP53, UMPS, SHMT1, MTHFR, ABCC2 and DPYD were assessed. Association between patient clinical characteristics and toxicity was estimated using logistic regression models and classification algorithms.
RESULTS: Reported grade ≤ 2 and 3-4 toxicities were 64.6% (61/93) and 34.4% (32/93) respectively. Selected DPYD SNPs were associated with higher toxicity (rs1801265; OR = 4.20; 95% CI = 1.70-10.95, p = 0.002), while others displayed a trend towards lower toxicity (rs1801159; OR = 0.45; 95% CI = 0.19-1.08; p = 0.071). Combination of paired SNPs demonstrated significant associations in DPYD (rs1801265), UMPS (rs1801019), ABCC2 (rs717620) and SHMT1 (rs1979277). Using multivariate logistic regression that combined age, sex, peri-operative chemotherapy, 5-FU regimen, the binary combination of the SNPs DPYD (rs1801265) + ABCC2 (rs717620), and DPYD (rs1801159) displayed the best predictive performance. A nomogram was constructed to assess the risk of developing overall toxicity.
CONCLUSIONS: Pending further validation, this model could predict chemotherapy associated toxicity and improve GC patient quality of life.

Disinfection is an important process to make the water free from harmful pathogenic substances, but sometimes it results in the formation of harmful by-products. Development of predictive models is required to define the concentration of THMs in pool water. Majority of studies reported inhalation to be the most significant THMs exposure route which is more likely to be dependent upon the concentration of THMs in pool water and in air. THMs concentration in the analyzed pool water samples and in air was found to be 197.18 ± 16.31 μg L-1 and 0.033 μg m3-1, respectively. Statistical parameters such as high correlation coefficients, high R2 values, low standard error, and low mean square error of prediction indicated the validity of MLR based linear model over non-linear model. Therefore, linear model can be most suitably used to pre-assess and predict the THMs levels in swimming pool water. Risk estimation studies was conducted by using the united states environmental protection agency (USEPA) Swimmer Exposure Assessment Model (SWIMODEL). The lifetime time cancer risk values related to chloroform exceeded 10-6 for both the sub-population. Inhalation exposure leads to maximum risk and contributed up to 99% to total cancer risk. Risk due to other exposure pathways like accidental ingestion and skin contact was found to be negligible and insignificant. Monte Carlo simulation results revealed that the simulated THMs risk values for the studied exposure pathways lies within ±3.1% of the average risk values obtained using SWIMODEL. Hence, the risk estimates obtained using SWIMODEL seemed to be appropriate in determining the potential risk exposure of THMs on human health. Variation in input parameters like body weight (BW) and skin surface area (SA) leads to difference in risk estimates for the studied population. Non cancer risk was found to be insignificant as represented by low hazard quotient (HQ < 1) values. Through monitoring and regulations on control of THMs in swimming pool water is required to minimize the risk associated.