Multi-objective extensive hypothesis testing for the estimation of advanced crash frequency models.

Analyzing crash data is a complex and labor-intensive process that requires careful consideration of multiple interdependent modeling aspects, such as functional forms, transformations, likely contributing factors, correlations, and unobserved heterogeneity. Limited time, knowledge, and experience may lead to over-simplified, over-fitted, or misspecified models overlooking important insights. This paper proposes an extensive hypothesis testing framework including a multi-objective mathematical programming formulation and solution algorithms to estimate crash frequency models considering simultaneously likely contributing factors, transformations, non-linearities, and correlated random parameters. The mathematical programming formulation minimizes both in-sample fit and out-of-sample prediction. To address the complexity and non-convexity of the mathematical program, the proposed solution framework utilizes a variety of metaheuristic solution algorithms. Specifically, Harmony Search demonstrated minimal sensitivity to hyperparameters, enabling an efficient search for solutions without being influenced by the choice of hyperparameters. The effectiveness of the framework was evaluated using two real-world datasets and one synthetic dataset. Comparative analyses were performed using the two real-world datasets and the corresponding models published in literature by independent teams. The proposed framework showed its capability to pinpoint efficient model specifications, produce accurate estimates, and provide valuable insights for both researchers and practitioners. The proposed approach allows for the discovery of numerous insights while minimizing the time spent on model development. By considering a broader set of contributing factors, models with varied qualities can be generated. For instance, when applied to crash data from Queensland, the proposed approach revealed that the inclusion of medians on sharp curved roads can effectively reduce the occurrence of crashes, when applied to crash data from Washington, the simultaneous consideration of traffic volume and road curvature resulted in a notable reduction in crash variances but an increase in crash means.

Predicting performance of students by optimizing tree components of random forest using genetic algorithm.

Prediction of student academic performance is still a problem because of the limitations of the existing methods specifically low generalizability and lack of interpretability. This study suggests a new approach that deals with the current problems and provides more reliable predictions. The proposed approach combines the information gain (IG) and Laplacian score (LS) for feature selection. In this feature selection scheme, combination of IG and LS is used for ranking features and then, Sequential Forward Selection mechanism is used for determining the most relevant indicators. Also, combination of random forest algorithm with a genetic algorithm for is introduced for multi-class classification. This approach strives to attain more accuracy and reliability than current techniques. The case study shows the proposed strategy can predict performance of students with average accuracy of 93.11 % which shows a minimum improvement of 2.25 % compared to the baseline methods. The findings were further confirmed by the analysis of different evaluation metrics (Accuracy, Precision, Recall, F-Measure) to prove the efficiency of the proposed mechanism.

Validating the IDRIS and IDRIA: Two infrequency/frequency scales for detecting careless and insufficient effort survey responders.

To detect careless and insufficient effort (C/IE) survey responders, researchers can use infrequency items - items that almost no one agrees with (e.g., "When a friend greets me, I generally try to say nothing back") - and frequency items - items that almost everyone agrees with (e.g., "I try to listen when someone I care about is telling me something"). Here, we provide initial validation for two sets of these items: the 14-item Invalid Responding Inventory for Statements (IDRIS) and the 6-item Invalid Responding Inventory for Adjectives (IDRIA). Across six studies (N1 = 536; N2 = 701; N3 = 500; N4 = 499; N5 = 629, N6 = 562), we found consistent evidence that the IDRIS is capable of detecting C/IE responding among statement-based scales (e.g., the HEXACO-PI-R) and the IDRIA is capable of detecting C/IE responding among both adjective-based scales (e.g., the Lex-20) and adjective-derived scales (e.g., the BFI-2). These findings were robust across different analytic approaches (e.g., Pearson correlations; Spearman rank-order correlations), different indices of C/IE responding (e.g., person-total correlations; semantic synonyms; horizontal cursor variability), and different sample types (e.g., US undergraduate students; Nigerian survey panel participants). Taken together, these results provide promising evidence for the utility of the IDRIS and IDRIA in detecting C/IE responding.

Longitudinal Relationships Among Child School Engagement, Parental Monitoring, and Child Prosocial Behavior: A Child-Parent Synergistic Mechanism.

Numerous contextual factors have been identified that impact the development of children's prosocial behavior, yet the influence of child-initiated factors on prosocial behavior and its underlying mechanism remains unclear. This study employed three longitudinal models to examine in depth how children's school engagement may promote the development of their own prosocial behavior. Three-wave longitudinal data from 4691 children (M age = 9.480, SD = 0.507; 48.2% female) with 2-year intervals were used. Sequentially, a cross-lagged panel model, a random intercept cross-lagged panel model, and a parallel process latent growth model were constructed. The findings indicated that children's school engagement consistently predicted the future level, dynamic changes at within-person level, and long-term trends in their prosocial behavior, and these longitudinal relationships were partially mediated by parental monitoring. These results reveal a child-parent synergistic mechanism for the development of prosocial behavior, wherein children's school engagement both directly promotes their own prosocial behavior and simultaneously enhances prosocial behavior through eliciting increased parental monitoring.

A hybrid Machine learning and statistical modeling approach for analyzing the crash severity of mobility scooter users considering temporal instability.

One of the main objectives in improving the quality of life for individuals with disabilities, especially those experiencing mobility issues such as the elderly, is to enhance their day-to-day mobility. Enabling easy mobility contributes to their independence and access to better healthcare, leading to improvements in both physical and mental well-being. Mobility Scooters have become increasingly popular in recent years as a means of facilitating mobility, yet traffic safety issues such as crash severity have not been adequately investigated in the literature. This study addresses this knowledge gap by employing a hybrid method that combines a machine learning approach using the eXtreme Gradient Boosting (XGBoost) algorithm with Shapley Additive exPlanations (SHAP) and an advanced statistical model called Random Parameters Binary Logit accounting for heterogeneity in means and variances. Analyzing the United Kingdom mobility scooter crash data from 2018 to 2022, the study examined temporal instability using a likelihood ratio test. The results revealed that there was instability over the three distinct periods of time based on the coronavirus (COVID) pandemic, namely, pre-COVID, during COVID, and post-COVID. Moreover, the results revealed that mobility scooter crashes occurring at a give-way or uncontrolled junctions has a random effect on the severity, while factors such as mobility scooter riders aged over 80, rear-end and sideswipe crashes, and crashes during winter months increase the risk of severe injuries. Conversely, mobility scooter riders involved in crashes while riding on the footway are less likely to experience severe injuries. These findings offer valuable insights for enhancing road safety measures that can be utilized to effectively reduce the crash severity of mobility scooter riders.

Reciprocal relations between dimensions of attention-deficit/hyperactivity and anxiety disorders from preschool age to adolescence: sex differences in a birth cohort sample.

BACKGROUND: Symptoms of anxiety and attention-deficit/hyperactivity disorder (ADHD) are prospectively related from childhood to adolescence. However, whether the two dimensions of ADHD-inattention and hyperactivity-impulsivity-are differentially related to anxiety and whether there are developmental and sex/gender differences in these relations are unknown. METHODS: Two birth cohorts of Norwegian children were assessed biennially from ages 4 to 16 (N = 1,077; 49% girls) with diagnostic parent interviews used to assess symptoms of anxiety and ADHD. Data were analyzed using a random intercept cross-lagged panel model, adjusting for all unobserved time-invariant confounding effects. RESULTS: In girls, increased inattention, but not hyperactivity-impulsivity, predicted increased anxiety 2 years later across all time-points and increased anxiety at ages 12 and 14 predicted increased inattention but not hyperactivity-impulsivity. In boys, increased hyperactivity-impulsivity at ages 6 and 8, but not increased inattention, predicted increased anxiety 2 years later, whereas increased anxiety did not predict increased inattention or hyperactivity-impulsivity. CONCLUSIONS: The two ADHD dimensions were differentially related to anxiety, and the relations were sex-specific. In girls, inattention may be involved in the development of anxiety throughout childhood and adolescence and anxiety may contribute to girls developing more inattention beginning in early adolescence. In boys, hyperactivity-impulsivity may be involved in the development of anxiety during the early school years. Effective treatment of inattention symptoms in girls may reduce anxiety risk at all time-points, while addressing anxiety may decrease inattention during adolescence. Similarly, treating hyperactivity-impulsivity may reduce anxiety risk in boys during late childhood (at ages 8-10).

Impact of climate change on future flood susceptibility projections under shared socioeconomic pathway scenarios in South Asia using artificial intelligence algorithms.

This study investigated the impact of climate change on flood susceptibility in six South Asian countries Afghanistan, Bangladesh, Bhutan, Bharat (India), Nepal, and Pakistan-under two distinct Shared Socioeconomic Pathway (SSP) scenarios: SSP1-2.6 and SSP5-5.8, for 2041-2060 and 2081-2100. To predict flood susceptibility, we employed three artificial intelligence (AI) algorithms: the K-nearest neighbor (KNN), conditional inference random forest (CIRF), and regularized random forest (RRF). Predictions were based on data from 2452 historical flood events, alongside climatic variables measured over monthly, seasonal, and annual timeframes. The innovative aspect of this research is the emphasis on using climatic variables across these progressively condensed timeframes, specifically addressing eight precipitation factors. The performance evaluation, employing the area under the receiver operating characteristic curve (AUC) metric, identified the RRF model as the most accurate, with the highest AUC of 0.94 during the testing phase, followed by the CIRF (AUC = 0.91) and the KNN (AUC = 0.86). An analysis of variable importance highlighted the substantial role of certain climatic factors, namely precipitation in the warmest quarter, annual precipitation, and precipitation during the wettest month, in the modeling of flood susceptibility in South Asia. The resultant flood susceptibility maps demonstrated the influence of climate change scenarios on susceptibility classifications, signalling a dynamic landscape of flood-prone areas over time. The findings revealed variable trends under different climate change scenarios and periods, with marked differences in the percentage of areas classified as having high and very high flood susceptibility. Overall, this study advances our understanding of how climate change affects flood susceptibility in South Asia and offers an essential tool for assessing and managing flood risks in the region.

Campylobacter assessment along the Spanish food chain: Identification of key points.

AIMS: Campylobacteriosis, caused by Campylobacter spp., is one of the most important foodborne zoonotic diseases in the world and a common cause of gastroenteritis. In the European Union, campylobacteriosis is considered the most common zoonotic disease, with over 10,000 cases in 2020 alone. This high occurrence highlights the need of more efficient surveillance methods and identification of key points. METHODS AND RESULTS: Herein, we evaluated and identified key points of Campylobacter spp. occurrence along the Spanish food chain during 2015-2020, based on the following variables: product, stage and region. We analysed a dataset provided by the Spanish Agency for Food Safety and Nutrition using a machine learning algorithm (random forests). Campylobacter presence was influenced by the three selected explanatory variables, especially by product, followed by region and stage. Among the studied products, meat, especially poultry and sheep, presented the highest probability of occurrence of Campylobacter, where the bacterium was present in the initial, intermediate and final stages (e.g., wholesale, retail) of the food chain. The presence in final stages may represent direct consumer exposure to the bacteria. CONCLUSSIONS: By using the random forest method, this study contributes to the identification of Campylobacter key points and the evaluation of control efforts in the Spanish food chain.

Effect of Ozone Therapy on Diabetes-related Foot Ulcer Outcomes: A Systematic Review and Meta-analysis.

PURPOSE: This study aimed to assess the effectiveness of ozone therapy in treating Diabetes-related Foot Ulcer (DFU) and its outcomes. METHODS: A systematic search was conducted in PubMed/MEDLINE, Scopus, Web of Science, and ProQuest databases for published studies evaluating the use of ozone as an adjunct treatment for DFU, from inception to December 21, 2022. The primary outcome measure was the change in wound size after the intervention compared to pretreatment. Secondary outcomes included time to complete ulcer healing, number of healed patients, adverse events, amputation rates, and hospital length of stay. Quantitative data synthesis for the meta-analysis was performed using a random-effects model and generic inverse variance method, while overall heterogeneity analysis was conducted using a fixed-effects model. Interstudy heterogeneity was assessed using the I2 index (<50%) and the Cochrane Q statistic test. Sensitivity analysis was performed using the leave-one-out method. RESULTS: The meta-analysis included 11 studies comprising 960 patients with DFU. The results demonstrated a significant positive effect of ozone therapy on reducing foot ulcer size (Standardized Mean Difference (SMD): -25.84, 95% CI: -51.65 to -0.04, p = 0.05), shortening mean healing time (SMD: -38.59, 95% CI: -51.81 to -25.37, p < 0.001), decreasing hospital length of stay (SMD: -8.75, 95% CI: -14.81 to -2.69, p < 0.001), and reducing amputation rates (Relative Risk (RR): 0.46, 95% CI: 0.30-0.71, p < 0.001), compared to standard treatment. CONCLUSION: This meta-analysis indicates that ozone therapy has additional benefits in expediting complete DFU healing, reducing the amputation rates, and decreasing hospital length of stay, though its effects do not differ from standard treatments for complete ulcer resolution. Further research is needed to address the heterogeneity among studies and to better understand the potential beneficial effects of ozone therapy.

A morphoscopic exploration of cranial sexual dimorphism among modern South Africans using computed tomography scans.

Continual re-evaluation of standards for forensic anthropological analyses are necessary, particularly as new methods are explored or as populations change. Indian South Africans are not a new addition to the South African population; however, a paucity of skeletal material is available for analysis from medical school collections, which has resulted in a lack of information on the sexual dimorphism in the crania. For comparable data, computed tomography scans of modern Black, Coloured and White South Africans were included in addition to Indian South Africans. Four cranial morphoscopic traits, were assessed on 408 modern South Africans (equal sex and population distribution). Frequencies, Chi-squared tests, binary logistic regression and random forest modelling were used to assess the data. Males were more robust than females for all populations, while White South African males were the most robust, and Black South African females were the most gracile. Population differences were noted among most groups for at least two variables, necessitating the creation of populations-specific binary logistic regression equations. Only White and Coloured South Africans were not significantly different. Indian South Africans obtained the highest correct classifications for binary logistic regression (94.1%) and random forest modelling (95.7%) and Coloured South Africans had the lowest correct classifications (88.8% and 88.0%, respectively). This study provides a description of the patterns of sexual dimorphism in four cranial morphoscopic traits in the current South African population, as well as binary logistic regression functions for sex estimation of Black, Coloured, Indian and White South Africans.

Additional yield of random biopsy in patients with inflammatory bowel disease: A systematic review and meta-analysis.

BACKGROUND & AIMS: There is limited clinical data regarding the additional yields of random biopsies during colorectal cancer surveillance in patients with inflammatory bowel disease. To assess the additional yield of RB, a systematic review and meta-analysis was conducted. METHODS: PubMed, Embase, Web of Science, and the Cochrane Library were searched for studies investigating the preferred colonoscopy surveillance approach for IBD patients. The additional yield, detection rate, procedure time, and withdrawal time were pooled. RESULTS: Thirty-seven studies (48 arms) were included in the meta-analysis with 9051 patients. The additional yields of RB were 10.34% in per-patient analysis, and 16.20% in per-lesion analysis. The detection rate were 1.31% and 2.82% in per-patient and per-lesion analysis, respectively. Subgroup analysis showed a decline in additional yields from 14.43% to 0.42% in the per-patient analysis and from 19.20% to 5.32% in the per-lesion analysis for studies initiated before and after 2011. In per-patient analysis, the additional yields were 4.83%, 10.29%, and 56.05% for PSC proportions of 0-10%, 10-30%, and 100%, respectively. The corresponding detection rates were 0.56%, 1.40%, and 19.45%. In the per-lesion analysis, additional yields were 11.23%, 21.06%, and 45.22% for PSC proportions of 0-10%, 10-30%, and 100%, respectively. The corresponding detection rates were 2.09%, 3.58%, and 16.24%. CONCLUSIONS: The additional yields of RB were 10.34% and 16.20% for per-patient and per-lesion analyses, respectively. Considering the decreased additional yields in studies initiated after 2011, and the influence of PSC, endoscopy centers lacking full HD equipment should consider incorporating RB in the standard colonoscopy surveillance for IBD patients, especially in those with PSC.

Random survival forest for predicting the combined effects of multiple physiological risk factors on all-cause mortality.

Understanding the combined effects of risk factors on all-cause mortality is crucial for implementing effective risk stratification and designing targeted interventions, but such combined effects are understudied. We aim to use survival-tree based machine learning models as more flexible nonparametric techniques to examine the combined effects of multiple physiological risk factors on mortality. More specifically, we (1) study the combined effects between multiple physiological factors and all-cause mortality, (2) identify the five most influential factors and visualize their combined influence on all-cause mortality, and (3) compare the mortality cut-offs with the current clinical thresholds. Data from the 1999-2014 NHANES Survey were linked to National Death Index data with follow-up through 2015 for 17,790 adults. We observed that the five most influential factors affecting mortality are the tobacco smoking biomarker cotinine, glomerular filtration rate (GFR), plasma glucose, sex, and white blood cell count. Specifically, high mortality risk is associated with being male, active smoking, low GFR, elevated plasma glucose levels, and high white blood cell count. The identified mortality-based cutoffs for these factors are mostly consistent with relevant studies and current clinical thresholds. This approach enabled us to identify important cutoffs and provide enhanced risk prediction as an important basis to inform clinical practice and develop new strategies for precision medicine.

Fuzzy random sensitivity analysis for the overall structure reliability of reinforced concrete freezing wellbores in deep alluvium based on hidden Markov model.

To address the shortcomings of traditional reliability theory in characterizing the stability of deep underground structures, the advanced first order second moment of reliability was improved to obtain fuzzy random reliability, which is more consistent with the working conditions. The traditional sensitivity analysis model was optimized using fuzzy random optimization, and an analytical calculation model of the mean and standard deviation of the fuzzy random reliability sensitivity was established. A big data hidden Markov model and expectation-maximization algorithm were used to improve the digital characteristics of fuzzy random variables. The fuzzy random sensitivity optimization model was used to confirm the effect of concrete compressive strength, thick-diameter ratio, reinforcement ratio, uncertainty coefficient of calculation model, and soil depth on the overall structural reliability of a reinforced concrete double-layer wellbore in deep alluvial soil. Through numerical calculations, these characteristics were observed to be the main influencing factors. Furthermore, while the soil depth was negatively correlated, the other influencing factors were all positively correlated with the overall reliability. This study provides an effective reference for the safe construction of deep underground structures in the future.

The application of THz-TDS in the characterization of Bayan Obo magnetite ore composition.

The application of terahertz time-domain spectroscopy (THz-TDS) in the quantitative analysis of major minerals in Bayan Obo magnetite ore was explored. The positive correlation between the optical parameters of the original ore and its iron content is confirmed. The detections of three main iron containing minerals, including magnetite, pyrite, and hematite, were simulated using corresponding reagents. The random forest algorithm is used for quantitative analysis, and FeS2 is detected with precision of R2 = 0.7686 and MAE = 0.6307% in ternary mixtures. The experimental results demonstrate that THz-TDS can distinguish specific iron containing minerals and reveal the potential application value of this testing method in exploration and mineral processing fields.

Association of random glucose to albumin ratio with post-contrast acute kidney injury and clinical outcomes in patients with ST-elevation myocardial infarction.

Purpose: Both glucose and albumin are associated with chronic inflammation, which plays a vital role in post-contrast acute kidney injury (PC-AKI). To explore the relationship between random glucose to albumin ratio (RAR) and the incidence of PC-AKI after percutaneous coronary intervention (PCI) in patients with ST-elevation myocardial infarction (STEMI). Patients and methods: STEMI patients who underwent PCI were consecutively enrolled from January, 01, 2010 to February, 28, 2020. All patients were categorized into T1, T2, and T3 groups, respectively, based on RAR value (RAR < 3.377; 3.377 ≤ RAR ≤ 4.579; RAR > 4.579). The primary outcome was the incidence of PC-AKI, and the incidence of major adverse clinical events (MACE) was the second endpoint. The association between RAR and PC-AKI was assessed by multivariable logistic regression analysis. Results: A total of 2,924 patients with STEMI undergoing PCI were finally included. The incidence of PC-AKI increased with the increasing tertile of RAR (3.2% vs 4.8% vs 10.6%, P<0.001). Multivariable regression analysis demonstrated that RAR (as a continuous variable) was associated with the incidence of PC-AKI (adjusted odds ratio (OR) =1.10, 95% confidence interval (CI) =1.04 - 1.16, P<0.001) and in-hospital MACE (OR=1.07, 95% CI=1.02 - 1.14, P=0.012); RAR, as a categorical variable, was significantly associated with PC-AKI (T3 vs. T1, OR=1.70, 95% CI=1.08 - 2.67, P=0.021) and in-hospital MACE (T3 vs. T1, OR=1.63, 95% CI=1.02 - 2.60, P=0.041) in multivariable regression analyses. Receiver operating characteristic curve analysis showed that RAR exhibited a predictive value for PC-AKI (area under the curve (AUC)=0.666, 95% CI=0.625 - 0.708), and in-hospital MACE (AUC= 0.662, 95% CI =0.619 - 0.706). Conclusions: The high value of RAR was significantly associated with the increasing risk of PC-AKI and in-hospital MACE after PCI in STEMI patients, and RAR offers a good predictive value for those outcomes.

A machine learning-assisted fluorescent sensor array utilizing silver nanoclusters for coffee discrimination.

Coffee is a globally consumed commodity of substantial commercial significance. In this study, we constructed a fluorescent sensor array based on two types of polymer templated silver nanoclusters (AgNCs) for the detection of organic acids and coffees. The nanoclusters exhibited different interactions with organic acids and generated unique fluorescence response patterns. By employing principal component analysis (PCA) and random forest (RF) algorithms, the sensor array exhibited good qualitative and quantitative capabilities for organic acids. Then the sensor array was used to distinguish coffees with different processing methods or roast degrees and the recognition accuracy achieved 100%. It could also successfully identify 40 coffee samples from 12 geographical origins. Moreover, it demonstrated another satisfactory performance for the classification of pure coffee samples with their binary and ternary mixtures or other beverages. In summary, we present a novel method for detecting and identifying multiple coffees, which has considerable potential in applications such as quality control and identification of fake blended coffees.

Corrigendum: Bipartite networks represent causality better than simple networks: Evidence, algorithms, and applications.

[This corrects the article DOI: 10.3389/fgene.2024.1371607.].

Understanding the moral cognition of aggression: Longitudinal serial effects of personal relative deprivation and hostility on within-person changes in civic moral disengagement.

Moral disengagement is an important aggressive and moral cognition. The mechanisms of changes in moral disengagement remain unclear, especially at the within-person level. We attempted to clarify this by exploring the serial effects of personal relative deprivation and hostility on civic moral disengagement. We conducted a three-wave longitudinal survey with 1058 undergraduates (63.61% women; mean age = 20.97). The results of the random intercept cross-lagged panel model showed that personal relative deprivation at Wave 1 and hostility at Wave 2 formed a serial effect on the within-person changes in civic moral disengagement at Wave 3, and the longitudinal indirect effect test showed that the within-person dynamics in hostility at Wave 2 acted as a mediator. The results of multiple group analysis across genders further showed that the longitudinal indirect role of hostility at Wave 2 was only observed for men, but not for women, which indicates the moderating effect of gender. These findings facilitate an understanding of the mechanisms of aggressive cognitions at the within-person level and offer implications for the prevention and intervention of aggression from the perspective of moral cognition.

Random forest-based prediction of intracranial hypertension in patients with traumatic brain injury.

BACKGROUND: Treatment and prevention of intracranial hypertension (IH) to minimize secondary brain injury are central to the neurocritical care management of traumatic brain injury (TBI). Predicting the onset of IH in advance allows for a more aggressive prophylactic treatment. This study aimed to develop random forest (RF) models for predicting IH events in TBI patients. METHODS: We analyzed prospectively collected data from patients admitted to the intensive care unit with invasive intracranial pressure (ICP) monitoring. Patients with persistent ICP > 22 mmHg in the early postoperative period (first 6 h) were excluded to focus on IH events that had not yet occurred. ICP-related data from the initial 6 h were used to extract linear (ICP, cerebral perfusion pressure, pressure reactivity index, and cerebrospinal fluid compensatory reserve index) and nonlinear features (complexity of ICP and cerebral perfusion pressure). IH was defined as ICP > 22 mmHg for > 5 min, and severe IH (SIH) as ICP > 22 mmHg for > 1 h during the subsequent ICP monitoring period. RF models were then developed using baseline characteristics (age, sex, and initial Glasgow Coma Scale score) along with linear and nonlinear features. Fivefold cross-validation was performed to avoid overfitting. RESULTS: The study included 69 patients. Forty-three patients (62.3%) experienced an IH event, of whom 30 (43%) progressed to SIH. The median time to IH events was 9.83 h, and to SIH events, it was 11.22 h. The RF model showed acceptable performance in predicting IH with an area under the curve (AUC) of 0.76 and excellent performance in predicting SIH (AUC = 0.84). Cross-validation analysis confirmed the stability of the results. CONCLUSIONS: The presented RF model can forecast subsequent IH events, particularly severe ones, in TBI patients using ICP data from the early postoperative period. It provides researchers and clinicians with a potentially predictive pathway and framework that could help triage patients requiring more intensive neurological treatment at an early stage.

Forecasting and mapping dengue fever epidemics in China: a spatiotemporal analysis.

BACKGROUND: Dengue fever (DF) has emerged as a significant public health concern in China. The spatiotemporal patterns and underlying influencing its spread, however, remain elusive. This study aims to identify the factors driving these variations and to assess the city-level risk of DF epidemics in China. METHODS: We analyzed the frequency, intensity, and distribution of DF cases in China from 2003 to 2022 and evaluated 11 natural and socioeconomic factors as potential drivers. Using the random forest (RF) model, we assessed the contributions of these factors to local DF epidemics and predicted the corresponding city-level risk. RESULTS: Between 2003 and 2022, there was a notable correlation between local and imported DF epidemics in case numbers (r = 0.41, P < 0.01) and affected cities (r = 0.79, P < 0.01). With the increase in the frequency and intensity of imported epidemics, local epidemics have become more severe. Their occurrence has increased from five to eight months per year, with case numbers spanning from 14 to 6641 per month. The spatial distribution of city-level DF epidemics aligns with the geographical divisions defined by the Huhuanyong Line (Hu Line) and Qin Mountain-Huai River Line (Q-H Line) and matched well with the city-level time windows for either mosquito vector activity (83.59%) or DF transmission (95.74%). The RF models achieved a high performance (AUC = 0.92) when considering the time windows. Importantly, they identified imported cases as the primary influencing factor, contributing significantly (24.82%) to local DF epidemics at the city level in the eastern region of the Hu Line (E-H region). Moreover, imported cases were found to have a linear promoting impact on local epidemics, while five climatic and six socioeconomic factors exhibited nonlinear effects (promoting or inhibiting) with varying inflection values. Additionally, this model demonstrated outstanding accuracy (hitting ratio = 95.56%) in predicting the city-level risks of local epidemics in China. CONCLUSIONS: China is experiencing an increasing occurrence of sporadic local DF epidemics driven by an unavoidably higher frequency and intensity of imported DF epidemics. This research offers valuable insights for health authorities to strengthen their intervention capabilities against this disease.