Explore the vast range of titles available.

Architectural heritage assessment increasingly relies on automated visual analysis, yet existing deep learning approaches often lack interpretability and provide limited insight into how cultural value judgments are formed. To address this gap, this study proposes an interpretable multi-task framework—YOLOv11-CVHP—for architectural heritage image recognition and integrated value classification. The model incorporates a lightweight backbone network (RepGhostNet), an enhanced attention module (ArchDetectAttn), and the WIoU loss function to improve detection accuracy and robustness. Based on the architectural components and semantic attributes detected by YOLOv11-CVHP, seven visual–cultural variables were constructed to quantify heritage characteristics. A Random Forest classifier was then applied to predict four-level integrated value grades. Although Random Forest is commonly regarded as a black-box model, interpretability is achieved through the incorporation of SHAP, which attributes the contribution of each visual–cultural feature to the final value grade, allowing transparent analysis of the decision process. Results indicate that Cultural Value (Intellectual) consistently serves as the dominant discriminative factor across all levels, while Historical Period and Structural Integrity play critical roles in differentiating between higher value categories. The classifier demonstrates strong generalization, with five-fold Precision–Recall curves showing stable performance and ROC–AUC scores exceeding 0.90 on both training and test sets. In conclusion, the integrated YOLOv11-CVHP and SHAP-enhanced Random Forest framework provides both high accuracy and clear interpretability, offering a practical and explainable solution for automated architectural heritage identification and value assessment.

Several dimensional impairments regarding Comprehensive Geriatric Assessment (CGA) have been shown to be associated with the prognosis of older patients. The purpose of this study is to investigate mortality prediction factors based upon clinical characteristics and test in CGA, and then subsequently develop a prediction model to classify both short- and long-term mortality risk in hospitalized older patients after discharge. A total of 1565 older patients with a median age of 81 years (74.0–86.0) were consecutively enrolled. The CGA, which included assessment of clinical, cognitive, functional, nutritional, and social parameters during hospitalization, as well as clinical information on each patient was recorded. Within the one-year follow up period, 110 patients (7.0%) had died. Using simple Cox regression analysis, it was shown that a patient’s Length of Stay (LOS), previous hospitalization history, admission Barthel Index (BI) score, Instrumental Activity of Daily Living (IADL) score, Mini Nutritional Assessment (MNA) score, and Charlson’s Comorbidity Index (CCI) score were all associated with one-year mortality after discharge. When these parameters were dichotomized, we discovered that those who were aged ≥90 years, had a LOS ≥ 12 days, an MNA score < 17, a CCI ≥ 2, and a previous admission history were all independently associated with one-year mortality using multiple cox regression analyses. By applying individual scores to these risk factors, the area under the receiver operating characteristics curve (AUC) was 0.691 with a cut-off value score ≧ 3 for one year mortality, 0.801 for within 30-day mortality, and 0.748 for within 90-day mortality. It is suggested that older hospitalized patients with varying risks of mortality may be stratified by a prediction model, with tailored planning being subsequently implemented.

This study was designed to investigate the effect of the comprehensive geriatric assessment on the short-term prognosis of the elderly heart failure patients (EHFP), analyze the relevant risk factors, and construct an effective risk prediction model. According to the selection and exclusion criteria, 617 patients were filtered from 800 patients from the cadre ward database of the first Hospital of Jilin University. The EHFP were randomly divided into the model group (432 cases) and the validation group (185 cases). A retrospective study on the general clinical data of patients in the model group was conducted to analyze the risk factors associated with the short-term outcomes of EHFP. Based on the risk factors, the risk prediction model was established and validated through the validation group. In the model group, the following independent risk factors were identified for the short-term outcomes in EHFP in the light of univariate logistic and cox regression analysis: female (β = 0.989, OR = 1.277, 95% CI: 1.090–1.847, P = 0.024), age (65–75 years, β = 0.654, OR = 2.320, 95% CI: 1.135–3.136, P = 0.012; 75–85 years, β = 1.123, OR = 3.159, 95% CI: 1.532–5.189, P = 0.001; age > 85 years old, β = 1.513, OR = 4.895, 95% CI: 1.866–979, P = 0.001), frailty (β = 1.015, OR = 2.761, 95% CI: 1.097–6.945, P = 0.031), malnutrition (β = 1.271, OR = 3.560, 95% CI: 1.122–11.325, P = 0.002), and EF≦40% (β = 1.250, OR = 3.498, 95% CI: 1.898–6.447, P = 0.001). The simple risk prediction score was set up in line with the five risk factors, including range (1–7), the area under ROC curve (0.771, 95% CI: 0.723–0.819), and H–L test (P = 0.393), so patients were divided into the low-risk group (1–3) and the high-risk group (4–8). As a result, the number of EHFP in the high-risk group was significantly much more than that in the low-risk group (70.1% versus 29.9%, P < 0.001). Besides, the area under ROC curve (0.758, 95% CI: 0.682–0.835) and H–L test (P = 0.669) of the validation group indicated that this model could be a promising prediction model for the short-term outcomes of EHFP. Female, age, frailty, malnutrition, and EF ≦ 40% are independent risk factors for short-term outcomes of EHFP. The risk prediction model based on the five risk factors provided compelling clinic predictive value for the short-term prognosis of EHFP.

Gains and losses reported as other comprehensive income (OCI) and as special items (SI) are often viewed as similar in nature: transitory items with little ability to predict future cash flows and minimal implications for company value. However, current accounting standards require SI gains and losses to be recognized in net income, while OCI gains and losses are deferred until realized. This study empirically compares OCI and SI gains and losses using a model that jointly estimates value relevance, predictive value, and persistence. Results show that both SI and OCI gains and losses are valuerelevant, but SI gains and losses exhibit zero persistence (i.e., are transitory), while OCI gains and losses exhibit negative persistence (i.e., partially reverse over time). Further, we find that SI gains and losses have strong predictive value for forecasting both future net income and future cash flows, while OCI gains and losses have weaker predictive value.

Waterlogging stress is one of the major abiotic stresses that negatively affect chrysanthemum (Chrysanthemum morifolium Ramat.) growth and development, thus reducing its productivity. Therefore, there is a need to develop waterlogging-tolerant chrysanthemum germplasms to deal with this problem, and the identification of tolerant wild chrysanthemum (C. indicum) is relevant to the improvement of cultivated chrysanthemum targeting resistance traits. In the current study, we aimed to evaluate the waterlogging tolerance of wild chrysanthemums by using the membership function value of waterlogging (MFVW) and multiple regression analysis based on seven morphological traits related to waterlogging tolerance. By MFVW, the investigated 19 C. indicum accessions were classified into five grades: one waterlogging-tolerant accession, 12 moderately waterlogging-tolerant accessions, and every two accessions for highly waterlogging-tolerant, waterlogging-sensitive, and highly waterlogging-sensitive types, respectively. Of all traits tested, Score, shoot fresh weight, and root fresh weight are considered reliable indicators, exhibiting a higher correlation with waterlogging tolerance. The mathematical evaluation model of waterlogging tolerance based on MFVW proved robust by comparing the observed MFVW and predicted Y values in two interspecific segregating F1 populations derived from C. indicum and C. japonense, with average R2 ranging between 0.957 and 0.982. The method established in the current study provides a reference for the rapid identification and accurate prediction of waterlogging tolerance in chrysanthemum germplasms, and the highly waterlogging-tolerant wild chrysanthemum germplasms identified herein help widen the genetic base for breeding chrysanthemum cultivars with desirable waterlogging tolerance.

Rock burst is a multifaceted phenomenon that involves various intricate factors. A precise evaluation of its risk encounters numerous challenges. To address this issue, the present paper proposed a multilevel fuzzy comprehensive evaluation model based on the Analytic Hierarchy Process–Fuzzy Comprehensive Evaluation (AHP-FCE) method. Three primary influencing factors and twelve secondary influencing factors that impact the rock burst risk were identified. The mechanisms by which each influencing factor affects the rock burst were analyzed and the membership degree for each factor was calculated accordingly. The weight of each influencing factor was determined through the AHP. To obtain a quantitative evaluation result, the evaluation model was calculated using the second-order fuzzy mathematics calculation method. The application of the model was demonstrated on the 310 working face of the Tingnan Coal Mine, and the evaluation results were consistent with those achieved through the use of the comprehensive index method and the probability index method. All of the results exhibited consistent alignment with the actual circumstances. The verification process confirmed the scientific, effective, and practical nature of the model.

Background Prolonged dependence on mechanical ventilation is a common occurrence in clinical ICU patients and presents significant challenges for patient care and resource allocation. Predicting prolonged dependence on mechanical ventilation is crucial for improving patient outcomes, preventing ventilator-associated complications, and guiding targeted clinical interventions. However, specific tools for predicting prolonged mechanical ventilation among ICU patients, particularly those with critical orthopaedic trauma, are currently lacking. The purpose of the study was to establish and validate an artificial intelligence (AI) platform to assess the prolonged dependence on mechanical ventilation among patients with critical orthopaedic trauma. Methods This study analyzed 1400 patients with critical orthopaedic trauma who received mechanical ventilation, and the prolonged dependence on mechanical ventilation was defined as not weaning from mechanical ventilation for ≧ 7 days. Patients were randomly classified into a training cohort and a validation cohort based on the ratio of 8:2. Patients in the training cohort were used to establish models using machine learning techniques, including logistic regression (LR), extreme gradient boosting machine (eXGBM), decision tree (DT), random forest (RF), support vector machine (SVM), and light gradient boosting machine (LightGBM), whereas patients in the validation cohort were used to validate these models. The prediction performance of these models was evaluated using discrimination and calibration. A scoring system was used to comprehensively assess and compare the prediction performance of the models, based on ten evaluation metrics. External validation of the model was performed in 122 patients with critical orthopaedic trauma from a university teaching hospital. Furthermore, the optimal model was deployed as an AI calculator, which was accessible online, to assess the risk of prolonged dependence on mechanical ventilation. Results Among the developed models, the eXGBM model had the highest score of 50, followed by the LightGBM model (48) and the RF model (37). In detail, the eXGBM model outperformed other models in terms of recall (0.892), Brier score (0.088), log loss (0.291), and calibration slope (0.999), and the model was the second best in terms of area under the curve value (0.949, 95%: 0.933–0.961), accuracy (0.871), F1 score (0.873), and discrimination slope (0.647). The SHAP revealed that the most important five features were respiratory rate, lower limb fracture, glucose, PaO2, and PaCO2. External validation of the eXGBM model also demonstrated favorable prediction performance, with an AUC value of 0.893 (95%CI: 0.819–0.967). The eXGBM model was successfully deployed as an AI platform, which was at https://prolongedmechanicalventilation-lqsfm6ecky6dpd4ybkvohu.streamlit.app/ . By simply clicking the link and inputting features, users were able to obtain the risk of experiencing prolonged dependence on mechanical ventilation for individuals. Based on the risk of prolonged dependence on mechanical ventilation, patients were stratified into the high-risk or the low-risk groups, and corresponding therapeutic interventions were recommended, accordingly. Conclusions The AI model shows potential as a valuable tool for stratifying patients with a high risk of prolonged dependence on mechanical ventilation. The AI model may offer a promising approach for optimizing patient care and resource allocation in critical care settings. Clinical trial number Not applicable.

Previous studies focused on a limited number of determinants of food label use. We therefore tested a comprehensive model of food label use consisting of sociodemographic, health-related and motivating variables. These three predictor groups were chosen based on the previous literature and completed with new predictors not yet examined in a comprehensive study of frequency of label use. We sent questionnaires to a random sample of households in the German-speaking part of Switzerland. The respondents filled in the questionnaire at home and returned it by mail. We analysed the data of 1162 filled-in questionnaires (response rate = 38 %). Of the respondents, 637 were women (55 %), and their mean age was 53·54 (sd 15·68) years. Health-related variables were the most important group of predictors of label use, followed by motivating factors and sociodemographic variables. Placing importance on health, healthy eating and nutritional value of food, perceived vulnerability for diet-related diseases, nutrition knowledge, numeracy and gender were positively associated with frequency of food label use whereas shopping habits and seeing eating as something positive were negative predictors of frequency of label use. People's health consciousness should be raised in order to increase the frequency of food label use. Furthermore, it should be stressed that reading labels and keeping a healthy diet do not contradict 'good eating', and that both of these aspects can be combined with the help of food labels.

Background Frailty indicators can operate in dynamic amalgamations of disease conditions, clinical symptoms, biomarkers, medical signals, cognitive characteristics, and even health beliefs and practices. This study is the first to evaluate which, among these multiple frailty-related indicators, are important and differential predictors of clinical cohorts that represent progression along an Alzheimer’s disease (AD) spectrum. We applied machine-learning technology to such indicators in order to identify the leading predictors of three AD spectrum cohorts; viz., subjective cognitive impairment (SCI), mild cognitive impairment (MCI), and AD. The common benchmark was a cohort of cognitively unimpaired (CU) older adults. Methods The four cohorts were from the cross-sectional Comprehensive Assessment of Neurodegeneration and Dementia dataset. We used random forest analysis (Python 3.7) to simultaneously test the relative importance of 83 multi-modal frailty indicators in discriminating the cohorts. We performed an explainable artificial intelligence method (Tree Shapley Additive exPlanation values) for deep interpretation of prediction effects. Results We observed strong concurrent prediction results, with clusters varying across cohorts. The SCI model demonstrated excellent prediction accuracy (AUC = 0.89). Three leading predictors were poorer quality of life ([QoL]; memory), abnormal lymphocyte count, and abnormal neutrophil count. The MCI model demonstrated a similarly high AUC (0.88). Five leading predictors were poorer QoL (memory, leisure), male sex, abnormal lymphocyte count, and poorer self-rated eyesight. The AD model demonstrated outstanding prediction accuracy (AUC = 0.98). Ten leading predictors were poorer QoL (memory), reduced olfaction, male sex, increased dependence in activities of daily living ( n  = 6), and poorer visual contrast. Conclusions Both convergent and cohort-specific frailty factors discriminated the AD spectrum cohorts. Convergence was observed as all cohorts were marked by lower quality of life (memory), supporting recent research and clinical attention to subjective experiences of memory aging and their potentially broad ramifications. Diversity was displayed in that, of the 14 leading predictors extracted across models, 11 were selectively sensitive to one cohort. A morbidity intensity trend was indicated by an increasing number and diversity of predictors corresponding to clinical severity, especially in AD. Knowledge of differential deficit predictors across AD clinical cohorts may promote precision interventions.

With the aim to the quantification of anomaly identification and extraction for observed or analyzed records, we present two statistical methods of earthquake corresponding relevancy spectrum (ECRS) and sliding mean relevancy (SMR). With ECRS method, we can obtain the abnormal confidence attribute of data in different value ranges. Based on the relevancy spectrum in different studied time-intervals, we convert the original time sequence into relevancy time sequence, and can obtain the SMR time series by using the multi-point cumulative sliding mean method. Then we can identify the seismic precursor anomaly. We test this method by taking the time sequence of η -value in the northern Tianshan region as original data. The result shows that when the studied time-interval is 18 months, the precursor anomaly can be identified better from sliding mean relevancy. The anomaly corresponding rate is 83 percent, the earthquake corresponding rate is 86 percent, and the anomaly is characteristic of the middle term. To try the research on multi-parameter comprehensive application, we take the Kalpin tectonic block in Xinjiang as our studied region, and analyze the spatial and temporal abnormal characters of multi-parameter sliding extreme-value relevancy (MSER) before mid-strong earthquakes in the Kalpin block. The result indicates that ECRS and SMR sequence in different time-intervals can not only be used to identify the precursor anomaly of single-item data, but also offer the data of quantitative single-item anomaly for comprehensive earthquake analysis and prediction.