Predictive modeling of deep vein thrombosis risk in hospitalized patients: A Q-learning enhanced feature selection model.

Deep vein thrombosis (DVT) represents a critical health concern due to its potential to lead to pulmonary embolism, a life-threatening complication. Early identification and prediction of DVT are crucial to prevent thromboembolic events and implement timely prophylactic measures in high-risk individuals. This study aims to examine the risk determinants associated with acute lower extremity DVT in hospitalized individuals. Additionally, it introduces an innovative approach by integrating Q-learning augmented colony predation search ant colony optimizer (QL-CPSACO) into the analysis. This algorithm, then combined with support vector machines (SVM), forms a bQL-CPSACO-SVM feature selection model dedicated to crafting a clinical risk prognostication model for DVT. The effectiveness of the proposed algorithm's optimization and the model's accuracy are assessed through experiments utilizing the CEC 2017 benchmark functions and predictive analyses on the DVT dataset. The experimental results reveal that the proposed model achieves an outstanding accuracy of 95.90% in predicting DVT. Key parameters such as D-dimer, normal plasma prothrombin time, prothrombin percentage activity, age, previously documented DVT, leukocyte count, and thrombocyte count demonstrate significant value in the prognostication of DVT. The proposed method provides a basis for risk assessment at the time of patient admission and offers substantial guidance to physicians in making therapeutic decisions.

Urinary incontinence rehabilitation of after radical prostatectomy: a systematic review and network meta-analysis.

Purpose: The aim of this study is to provide treatment for patients with urinary incontinence at different periods after radical prostatectomy. Methods: The PubMed, Embase, Cochrane, and Web of Science were searched for all literature on the effectiveness on urinary control after radical prostate cancer between the date of database creation and 15 November 2023 and performed a quality assessment. A network meta-analysis was performed using RevMan 5.3 and Stata 17.0 software and evaluated using the surface under the cumulative ranking curve. Results: The results of the network meta-analysis showed that pelvic floor muscle therapy including biofeedback with professional therapist-guided treatment demonstrated better results at 1 month to 6 months; electrical stimulation, biofeedback, and professional therapist guidance may be more effective at 3 months of treatment; professional therapist-guided recovery may be less effective at 6 months of treatment; and combined therapy demonstrated better results at 1 year of treatment. During the course of treatment, biofeedback with professional therapist-guided treatment may have significant therapeutic effects in the short term after surgery, but, in the long term, the combination of multiple treatments (pelvic floor muscle training+ routine care + biofeedback + professional therapist-guided treatment + electrical nerve stimulation therapy) may address cases of urinary incontinence that remain unrecovered long after surgery. Conclusion: In general, all treatment methods improve the different stages of functional recovery of the pelvic floor muscles. However, in the long term, there are no significant differences between the treatments. Given the cost-effectiveness, pelvic floor muscle training + routine care + biofeedback + professional therapist-guided treatment + electrical nerve stimulation therapy within 3 months and pelvic floor muscle + routine care after 3 months may be a more economical option to treat urinary incontinence. Systematic review registration: https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=331797, identifier CRD42022331797.

Systemic triplet therapy for metastatic hormone-sensitive prostate cancer: A systematic review and network meta-analysis.

Purpose: To perform a systematic review and network meta-analysis to compare the efficacy and safety of currently available docetaxel-based systemic triplet therapies for metastatic hormone-sensitive prostate cancer (mHSPC). Methods: We searched for eligible publications in PubMed, Embase, and Cochrane CENTRAL. Improvements in overall survival (OS) and radiographic progression-free time (rPFS) were compared indirectly using network meta-analysis and evaluated using the surface under the cumulative ranking curve (SUCRA). Other secondary endpoints, such as time to castration-resistant prostate cancer and/or adverse events (AEs), were also compared and evaluated. Results: Five trials were selected and analyzed using a network meta-analysis. Compared to androgen deprivation therapy (ADT) plus docetaxel, darolutamide (hazard ratio [HR]: 0.68, 95% credible interval [CrI]: 0.57-0.80) and abiraterone (HR: 0.75, 95% CrI: 0.59-0.95) triplet therapy had significantly longer OS, and darolutamide triplet therapy was the first treatment ranked. Abiraterone (HR: 0.49, 95% CrI: 0.39-0.61) and enzalutamide (HR: 0.52, 95% CrI: 0.30-0.89) had significantly better rPFS than ADT plus docetaxel; however, all three therapies, including abiraterone, apalutamide, and enzalutamide, were the best options with a similar SUCRA. At most secondary endpoints, systemic triplet therapy was superior to ADT plus docetaxel. The risk of any AEs in darolutamide or abiraterone triplet therapy was comparable with ADT plus docetaxel (odds ratio [OR]: 2.53, 95% credible interval [CrI]: 0.68-12.63; OR: 1.07, 95% CrI: 0.03-36.25). Abiraterone triplet therapy had an increased risk of grade≥3 AEs (OR: 1.56, 95% CrI: 1.15-2.11). Conclusion: Systemic triplet therapy was more effective than ADT plus docetaxel for mHSPC. Of the triplet therapy regimens, darolutamide ranked first in terms of improved OS. Abiraterone and enzalutamide triplet ranked first in terms of rFPS, however, it did not confer a statistically difference among all triplet regimens. The overall risk of AEs was comparable. More studies are required for current and potential combinations of systemic triplet therapy.

Machine Learning-Based Models Enhance the Prediction of Prostate Cancer.

Purpose: PSA is currently the most commonly used screening indicator for prostate cancer. However, it has limited specificity for the diagnosis of prostate cancer. We aim to construct machine learning-based models and enhance the prediction of prostate cancer. Methods: The data of 551 patients who underwent prostate biopsy were retrospectively retrieved and divided into training and test datasets in a 3:1 ratio. We constructed five PCa prediction models with four supervised machine learning algorithms, including tPSA univariate logistic regression (LR), multivariate LR, decision tree (DT), random forest (RF), and support vector machine (SVM). The five prediction models were compared based on model performance metrics, such as the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, calibration curve, and clinical decision curve analysis (DCA). Results: All five models had good calibration in the training dataset. In the training dataset, the RF, DT, and multivariate LR models showed better discrimination, with AUCs of 1.0, 0.922 and 0.91, respectively, than the tPSA univariate LR and SVM models. In the test dataset, the multivariate LR model exhibited the best discrimination (AUC=0.918). The multivariate LR model and SVM model had better extrapolation and generalizability, with little change in performance between the training and test datasets. Compared with the DCA curves of the tPSA LR model, the other four models exhibited better net clinical benefits. Conclusion: The results of the current retrospective study suggest that machine learning techniques can predict prostate cancer with significantly better AUC, accuracy, and net clinical benefits.