Explore the vast range of titles available.

Data stream mining has recently grown in popularity, thanks to an increasing number of applications which need continuous and fast analysis of streaming data. Such data are generally produced in application domains that require immediate reactions with strict temporal constraints. These particular characteristics make problematic the use of classical machine learning algorithms for mining knowledge from these fast data streams and call for appropriate techniques. In this paper, based on the well-known Hoeffding Decision Tree (HDT) for streaming data classification, we introduce FHDT, a fuzzy HDT that extends HDT with fuzziness, thus making HDT more robust to noisy and vague data. We tested FHDT on three synthetic datasets, usually adopted for analyzing concept drifts in data stream classification, and two real-world datasets, already exploited in some recent researches on fuzzy systems for streaming data. We show that FHDT outperforms HDT, especially in presence of concept drift. Furthermore, FHDT is characterized by a high level of interpretability, thanks to the linguistic rules that can be extracted from it.

This study aimed to identify independent predictors for the risk of hemorrhagic transformation (HT) in arterial ischemic stroke (AIS) patients. Consecutive patients with AIS due to large artery occlusion in the anterior circulation treated with mechanical thrombectomy (MT) were enrolled in a tertiary stroke center. Demographic and medical history data, admission lab results, and Circle of Willis (CoW) variations were collected from all patients. Altogether, 90 patients were included in this study; among them, 34 (37.8%) had HT after MT. The final pruned decision tree (DT) model consisted of collateral score and platelet to lymphocyte ratios (PLR) as predictors. Confusion matrix analysis showed that 82.2% (74/90) were correctly classified by the model (sensitivity, 79.4%; specificity, 83.9%). The area under the ROC curve (AUC) was 81.7%. The DT model demonstrated that participants with collateral scores of 2-4 had a 75.0% probability of HT. For participants with collateral scores of 0-1, if PLR at admission was <302, participants had a 13.0% probability of HT; otherwise, participants had an 75.0% probability of HT. The final adjusted multivariate logistic regression analysis indicated that collateral score 0-1 (OR, 10.186; 95% CI, 3.029-34.248; p < 0.001), PLR (OR, 1.005; 95% CI, 1.001-1.010; p = 0.040), and NIHSS at admission (OR, 1.106; 95% CI, 1.014-1.205; p = 0.022) could be used to predict HT. The AUC for the model was 0.855, with 83.3% (75/90) were correctly classified (sensitivity, 79.4%; specificity, 87.3%). Less patients with HT achieved independent outcomes (mRS, 0-2) in 90 days (20.6% vs. 64.3%, p < 0.001). Rate of poor outcomes (mRS, 4-6) was significantly higher in patients with HT (73.5% vs. 19.6%; p < 0.001). Both the DT model and multivariate logistic regression model confirmed that the lower collateral status and the higher PLR were significantly associated with an increased risk for HT in AIS patients after MT. PLR may be one of the cost-effective and practical predictors for HT. Further prospective multicenter studies are needed to validate our findings.

Background As China's population ages, its disease spectrum is changing, and the coexistence of multiple chronic diseases has become the norm with respect to the health status of its elderly population. However, the health institution choices of older patients with multimorbidity in stabilization period remains underresearched. This study investigate the factors influencing the choices of older patients with multimorbidity to provide references for the rational allocation of healthcare resources. Methods A multistage, stratified, whole‐group random‐sampling method was used to select eligible older patients from September to December of 2022 who attended the Community Health Service Center of Guangdong Province. We adopted a self‐designed questionnaire to collect patients' general, disease‐related, social‐support information, their intention to choose a healthcare provider. A binary logistic regression and decision tree model based on the Chi‐squared automatic interaction detector algorithm were implemented to analyze the associated factors involved. Results A total of 998 patients in stabilization period were included in the study, of which 593 (59.42%) chose hospital and 405 (40.58%) chose primary care. Our binary logistic regression results revealed that age, sex, individual average annual income, educational level, self‐reported health status, activities of daily living, alcohol consumption, family doctor contracting, and family supervision of medication or exercise were the principal factors influencing the choice of medical institutions for older patients with multimorbidity (p < 0.05). The decision‐tree model reflected three levels and 11 nodes, and we screened a total of four influencing factors: activities of daily living, age, a family doctor contract, and patient sex. The data showed that the logistic regression model possessed an accuracy of 72.9% and that the decision tree model exhibited an accuracy of 68.7%. Prediction using the binary logistic regression was thus statistically superior to the categorical decision‐tree model based on the Chi‐squared automatic interaction detector algorithm (Z = 3.238, p = 0.001). Conclusion More than half of older patients with multimorbidity in stabilization period chose hospitals for healthcare. Efforts should be made to improve the quality of healthcare services and increase the medical contracting rate and recognition of family doctors so as to attract older patients with multimorbidity to primary medical institutions.

Background Robust data are essential for clinical and epidemiological research, yet in chronic spontaneous urticaria (CSU), certain patient groups, such as the elderly or comorbid patients, are often underrepresented. In clinical trials, strict inclusion and exclusion criteria frequently limit recruitment, making it difficult to achieve sufficient statistical power. Similarly, real‐world observational studies may lack sufficient sample sizes for robust analysis. To address these limitations, we generated synthetic patient data that reflect these groups’ clinical characteristics and variability. This approach enables more comprehensive analyses, facilitates hypothesis testing in otherwise inaccessible populations, and supports the generation of evidence where traditional data sources are insufficient. Methods A tree‐based decision model was applied to generate synthetic data based on an existing set of real‐world data (RWD) from the Chronic Urticaria Registry (CURE). Descriptive characteristics and association strength between relevant RWD variables and their synthetic counterparts were analyzed as indicators of replication accuracy, providing insight into how closely the synthetic data aligns with the RWD. Finally, we determined the minimum sample size required to generate high‐quality synthetic data. Results The algorithm produced extensive synthetic data records, closely mirroring patient demographics and disease clinical characteristics. Smaller subgroups of the data were equally replicated and followed the same distribution as RWD. Known associations and correlations between disease‐specific factors (disease control) and risk factors (age) yielded similar results, with no significant difference (p > 0.05). The lowest threshold at which synthetic data could be generated while maintaining high accuracy in RWD was identified to be 25%, enabling a fourfold increase in the synthetic population. Conclusion Synthetic data could replicate RWD with reasonable accuracy for patients with CSU down to 25% of the original population size. This method has the potential to extend small patient subgroups in clinical and epidemiological research.

Background Many effective therapies for psoriasis are being applied in clinical practice in recent years, however, some patients still can’t achieve satisfied effect even with biologics. Therefore, it is crucial to identify factors associated with the treatment efficacy among psoriasis patients. This study aims to explore factors influencing the treatment efficacy of psoriasis patients based on decision tree model and logistic regression. Methods We implemented an observational study and recruited 512 psoriasis patients in Shanghai Skin Diseases Hospital from 2021 to 2022. We used face-to-face questionnaire interview and physical examination to collect data. Influencing factors of treatment efficacy were analyzed by using logistic regression, and decision tree model based on the CART algorithm. The receiver operator curve (ROC) was plotted for model evaluation and the statistical significance was set at P  < 0.05. Results The 512 patients were predominately males (72.1%), with a median age of 47.5 years. In this study, 245 patients achieved ≥ 75% improvement in psoriasis area and severity index (PASI) score in week 8 and was identified as treatment success (47.9%). Logistic regression analysis showed that patients with senior high school and above, without psoriasis family history, without tobacco smoking and alcohol drinking had higher percentage of treatment success in patients with psoriasis. The final decision tree model contained four layers with a total of seventeen nodes. Nine classification rules were extracted and five factors associated with treatment efficacy were screened, which indicated tobacco smoking was the most critical variable for treatment efficacy prediction. Model evaluation by ROC showed that the area under curve (AUC) was 0.79 (95%CI: 0.75 ~ 0.83) both for logistic regression model (0.80 sensitivity and 0.69 specificity) and decision tree model (0.77 sensitivity and 0.73 specificity). Conclusion Psoriasis patients with higher education, without tobacco smoking, alcohol drinking and psoriasis family history had better treatment efficacy. Decision tree model had similar predicting effect with the logistic regression model, but with higher feasibility due to the nature of simple, intuitive, and easy to understand.

Maternal syphilis not only seriously affects the quality of life of pregnant women themselves but also may cause various adverse pregnancy outcomes (APOs). This study aimed to analyse the association between the related factors and APOs in maternal syphilis. 7,030 pregnant women infected with syphilis in Henan Province between January 2016 and December 2022 were selected as participants. Information on their demographic and clinical characteristics, treatment status, and pregnancy outcomes was collected. Multivariate logistic regression models and chi-squared automatic interaction detector (CHAID) decision tree models were used to analyse the factors associated with APOs. The multivariate logistic regression results showed that the syphilis infection history (OR = 1.207, 95% CI, 1.035–1.409), the occurrence of abnormality during pregnancy (OR = 5.001, 95% CI, 4.203–5.951), not receiving standard treatment (OR = 1.370, 95% CI, 1.095–1.716), not receiving any treatment (OR = 1.313, 95% CI, 1.105–1.559), and a titre ≥1:8 at diagnosis (OR = 1.350, 95%CI, 1.079–1.690) and before delivery (OR = 1.985, 95%CI, 1.463–2.694) were risk factors. A total of six influencing factors of APOs in syphilis-infected women were screened using the CHAID decision tree model. Integrated prevention measures such as early screening, scientific eugenics assessment, and standard syphilis treatment are of great significance in reducing the incidence of APOs for pregnant women infected with syphilis.

The present study aimed to determine the prevalence of localized gingival enlargements (LGEs) and their clinical characteristics in a group of Thai patients, as well as utilize this information to develop a clinical diagnostic guide for predicting malignant LGEs. All LGE cases were retrospectively reviewed during a 20-year period. Clinical diagnoses, pathological diagnoses, patient demographic data, and clinical information were analyzed. The prevalence of LGEs was determined and categorized based on their nature, and concordance rates between clinical and pathological diagnoses among the groups were evaluated. Finally, a diagnostic guide was developed using clinical information through a decision tree model. Of 14,487 biopsied cases, 946 cases (6.53%) were identified as LGEs. The majority of LGEs were reactive lesions (72.62%), while a small subset was malignant tumors (7.51%). Diagnostic concordance rates were lower in malignant LGEs (54.93%) compared to non-malignant LGEs (80.69%). Size, consistency, color, duration, and patient age were identified as pivotal factors to formulate a clinical diagnostic guide for distinguishing between malignant and non-malignant LGEs. Using a decision tree model, we propose a novel diagnostic guide to assist clinicians in enhancing the accuracy of clinical differentiation between malignant and non-malignant LGEs.

PurposeAn accurate postoperative assessment is pivotal to inform postoperative 131I treatment in patients with differentiated thyroid cancer (DTC). We developed a predictive model for post-treatment whole-body scintigraphy (PT-WBS) results (as a proxy for persistent disease) by adopting a decision tree model.MethodsAge, sex, histology, T stage, N stage, risk classes, remnant estimation, TSH, and Tg were identified as potential predictors and were put into regression algorithm (conditional inference tree, ctree) to develop a risk stratification model for predicting the presence of metastases in PT-WBS.ResultsThe lymph node (N) stage identified a partition of the population into two subgroups (N-positive vs N-negative). Among N-positive patients, a Tg value  > 23.3 ng/mL conferred a 83% probability to have metastatic disease compared to those with lower Tg values. Additionally, N-negative patients were further substratified in three subgroups with different risk rates according to their Tg values. The model remained stable and reproducible in the iterative process of cross validation.ConclusionsWe developed a simple and robust decision tree model able to provide reliable informations on the probability of persistent/metastatic DTC after surgery. These information may guide post-surgery 131I administration and select patients requiring curative rather than adjuvant 131I therapy schedules.

In this paper, the original two-level planning problem is transformed into a single-level optimization problem by combining the penalty function method for the large amount of data processing involved in the training process of the decision tree model, setting the output as a classification tree in the iterative process of the CART decision tree, and recursively building the CART classification tree with the training set to find the optimal solution set for the nonlinear two-level planning problem. It is verified that the proposed solution method is also stable at a convergence index of 1.0 with a maximum accuracy of 95.37%, which can provide an efficient solution method for nonlinear two-level programming problems oriented to decision tree models.

•Respiratory syncytial virus (RSV) remains a leading cause of medically-attended (MA) lower respiratory tract infection (LRTI) and non-LRTI episodes in the US in infants and children.•The vast majority (>80 %) of medically-attended RSV LRTIs and non-LRTIs occur among healthy full-term infants.•The long-acting mAb intervention is the most effective at reducing the number of MA-RSV episodes, especially in older infants (≥6 months old).•Our model is unique in simultaneously accounting for gestational age at birth, birth month, and RSV seasonality. Respiratory syncytial virus (RSV) remains a leading cause of medically-attended acute respiratory infection in infants and children. With multiple preventative interventions under development, accurate estimates of health care resource utilization are essential for policy decision making. We developed a literature-based decision-tree model that estimated annual medically-attended RSV (MA-RSV) lower respiratory tract infection (LRTI) and non-LRTI episodes in the US for all infants and for high-risk toddlers. The model accounted for the gestational age and birth-month of infants, and the seasonal variation in RSV incidence. The impact of no prophylaxis, palivizumab, maternal vaccine, and long-acting monoclonal antibody (mAb) interventions was estimated. We estimated 1.23 million (range: 0.96 million–1.40 million) annual MA-RSV LRTI/non-LRTI episodes comprised of 1.19 million (range: 0.93 million–1.36 million) emergency department (ED) and outpatient visits, and 39,040 (range: 32,726–45,851) hospitalizations. Outpatient and ED visits were comprised of 586,034 (range: 430,595–718,868) LRTIs and 608,733 (range: 495,705–644,658) non-LRTIs. The long-acting mAb intervention resulted in the greatest number of averted outpatient and ED episodes (310,997 [53%] LRTIs; 284,305 [47%] non-LRTIs) and hospitalizations (21,845 [56%]). Full-term infants constitute the highest proportion of episodes across all interventions. MA-RSV disease is substantial in infants and high-risk toddlers. Long-acting mAbs are most effective at reducing the number of MA-RSV LRTI/non-LRTI episodes, and the only intervention that prevents disease in older infants (≥6 months old).