High-quality Models Research Articles

Development and validation of a high-quality simulator with exchangeable peritoneum for transabdominal preperitoneal laparoscopic inguinal hernia repair.

Practical simulation training with proper haptic feedback and the fragility of the human body is required to overcome the long learning curve associated with laparoscopic inguinal hernia repair (LIHR). However, few hernia models accurately reflect the texture and fragility of the human body. Therefore, in this study, we developed a novel model for transabdominal preperitoneal (TAPP) LIHR training and evaluated its validity. We developed a high-quality mock peritoneum with a hydrated polyvinyl alcohol layer and a unique two-way crossing cellulose fiber layer. To complete the simulation, the peritoneum was adhered to a urethane foam inguinal base with surgical landmarks. Participants could perform all the procedures required for the TAPP LIHR. Twenty-four surgeons performed TAPP LIHR simulation using a novel simulator. Their opinions were rated on a 5-point Likert scale. Additionally, 6 surgical residents and 10 surgical experts performed the procedure. Their performance was evaluated using the TAPP checklist score and procedure time. Most participants strongly agreed that the TAPP LIHR simulator with an exchangeable peritoneum model was useful. The participants agreed on the model fidelity for tactile sensation, forceps handling, and humanlike anatomy. In comparisons between surgical residents and experts, the experts had significantly higher scores (10.6 vs. 17.2, p < 0.05) and shorter procedure times (92.3 vs. 55.9 min; p < .05) than did surgical residents. We developed a high-quality exchangeable peritoneal model that mimics the human peritoneum's texture and fragility. This model enhances laparoscopic simulation training, potentially shortening TAPP LIHR learning curves.

Development and evaluation of vesicourethral anastomosis bench-top model for measurement of traction force on urethra in robotic surgery.

In vesicourethral anastomosis (VUA), which is part of robot-assisted radical prostatectomy, surgeons must proceed carefully to avoid urethral damage. We developed and evaluated a VUA bench-top model that can measure the traction force on the urethra during robotic surgery. The VUA model included the urethra, bladder, pelvic bones, and a small force sensor that was capable of measuring the traction force on the urethra. Eight skilled and eight novice urologists performed a VUA task in robotic surgery. The skilled surgeons assessed the model's realism and usefulness as a training tool using a 5-point Likert scale. The evaluation items [task time, maximum force, force volume, and length of time that specific excessive forces were applied to the urethra (2, 3, 4, and ≥ 5 N)] were compared between the skilled and novice surgeons using the Mann-Whitney U test. Measurements were conducted in four directions with respect to the maximum force on the urethra: 11-1, 2-4, 5-7, and 8-10 o'clock. The quality of the model was scored 3.7 to 4.9 points for all 16 items in 4 domains except for "Usefulness compared with animal models." There were differences in the task time and almost all force parameters between the skilled and novice surgeons. We developed a relatively high-quality VUA bench-top model that measures traction force on the urethra, and we have revealed differences in the forces of action on the urethra in two groups of surgeons with different skill levels.

Crow Search Algorithm for Modelling an Anaerobic Digestion Process: Algorithm Parameter Influence

Corn steep liquor is a waste product from the process of treating corn grain for starch extraction. It is used as a substrate in anaerobic digestion with simultaneous hydrogen and methane production in a cascade of two anaerobic bioreactors. For process research and optimisation, adequate mathematical models are required. So, the authors aim to present a high-quality model of the corn steep liquor process for the sequential production of H2 and CH4. This paper proposes a technique for identifying the best mathematical model of the process using the metaheuristics crow search algorithm (CSA). The CSA was applied for the first time to mathematical modelling of the considered two-stage anaerobic digestion process, using real experimental data. Based on the analysis of the numerical data from the model parameter identification procedures, the influence of the main CSA parameters—the flight length, fl, and the awareness probability, AP—was investigated. Applying classical statistical tests and an innovative approach, InterCriteria Analysis, recommendations about the optimal CSA parameter tuning were proposed. The best CSA algorithm performance was achieved for the AP = 0.05, fl = 3.0, followed by AP = 0.10, fl = 2.5, and AP = 0.15, fl = 3.0. The optimal tuning of the CSA parameters resulted in a 29% improvement in solution accuracy. As a result, a mathematical model of the considered two-stage anaerobic digestion process with a high degree of accuracy was developed.

Empirical insights into AI-assisted game development: A case study on the integration of generative AI tools in creative pipelines

&lt;p&gt;This study conducts an empirical exploration of generative Artificial Intelligence (AI) tools across the game development pipeline, from concept art creation to 3D model integration in a game engine. Employing AI generators like Leonardo AI, Scenario AI, Alpha 3D, and Luma AI, the research investigates their application in generating game assets. The process, documented in a diary-like format, ranges from producing concept art using fantasy game prompts to optimizing 3D models in Blender and applying them in Unreal Engine 5. The findings highlight the potential of AI to enhance the conceptualization phase and identify challenges in producing optimized, high-quality 3D models suitable for game development. This study reveals the current limitations and ethical considerations of AI in game design, suggesting that while generative AI tools hold significant promise for transforming game development, their full integration depends on overcoming these hurdles and gaining broader industry acceptance.&lt;strong&gt;&lt;/strong&gt;&lt;/p&gt;

Accurate model and ensemble refinement using cryo-electron microscopy maps and Bayesian inference.

Converting cryo-electron microscopy (cryo-EM) data into high-quality structural models is a challenging problem of outstanding importance. Current refinement methods often generate unbalanced models in which physico-chemical quality is sacrificed for excellent fit to the data. Furthermore, these techniques struggle to represent the conformational heterogeneity averaged out in low-resolution regions of density maps. Here we introduce EMMIVox, a Bayesian inference approach to determine single-structure models as well as structural ensembles from cryo-EM maps. EMMIVox automatically balances experimental information with accurate physico-chemical models of the system and the surrounding environment, including waters, lipids, and ions. Explicit treatment of data correlation and noise as well as inference of accurate B-factors enable determination of structural models and ensembles with both excellent fit to the data and high stereochemical quality, thus outperforming state-of-the-art refinement techniques. EMMIVox represents a flexible approach to determine high-quality structural models that will contribute to advancing our understanding of the molecular mechanisms underlying biological functions.

A deep learning-based toolkit for 3D nuclei segmentation and quantitative analysis in cellular and tissue context.

We present a new set of computational tools that enable accurate and widely applicable 3D segmentation of nuclei in various 3D digital organs. We have developed an approach for ground truth generation and iterative training of 3D nuclear segmentation models, which we applied to popular CellPose, PlantSeg and StarDist algorithms. We provide two high-quality models trained on plant nuclei that enable 3D segmentation of nuclei in datasets obtained from fixed or live samples, acquired from different plant and animal tissues, and stained with various nuclear stains or fluorescent protein-based nuclear reporters. We also share a diverse high-quality training dataset of about 10,000 nuclei. Furthermore, we advanced the MorphoGraphX analysis and visualization software by, among other things, providing a method for linking 3D segmented nuclei to their surrounding cells in 3D digital organs. We found that the nuclear-to-cell volume ratio varies between different ovule tissues and during the development of a tissue. Finally, we extended the PlantSeg 3D segmentation pipeline with a proofreading tool that uses 3D segmented nuclei as seeds to correct cell segmentation errors in difficult-to-segment tissues.

Principles of Creating Multi-objective Quality Models for Software Systems

This article proposes an original approach at a mathematical level to the creation of multi- objective quality models for software systems. The research is based on the study and generalization of quality modeling trends of software systems and user needs in order to determine optimal principles for constructing such models. The article provides mathematical explanations that play a key role in identifying and formalizing the principles of creating multi-objective quality models of software. An important aspect is the consideration of quality model construction principles at the mathematical level, allowing for a more precise assessment and analysis of various aspects of software quality. The research results indicate that incorporating mathematical principles into the creation of multi-objective quality models for software systems can have a significant practical impact. It is established that on a practical level of developing multi-objective quality models for software systems, consideration of the principles of creating multi-objective quality models can have numerous practical implications. Specifically, the application of metrics within established principles allows for a comprehensive view of software quality and identifies areas requiring attention and improvement. This helps developers and software quality engineers make informed decisions regarding system improvement and optimization. The research has shown that creating high-quality models of quality requires attention to various aspects, from user needs to testing and continuous improvement, as well as the use of mathematical methods for their formalization and analysis. The developed principles of creating multi-objective quality models at the level of mathematical models allow the use of these models to assess and analyze various aspects of software quality, representing each model using a corresponding function that determines the relationship between quality metrics and the quality of the software itself. It is expected that further development and implementation of these principles will contribute to improving software development processes and ensure high quality of the resulting software.

Effect analysis of applying high-quality service model to surgical nursing.

Surgical care of the hand plays a crucial role in the medical field, as problems with the hand can profoundly affect a patient's quality of life and function. In order to meet the needs of patients, improve patient satisfaction and improve treatment outcomes, high-quality service models have been introduced in the field of nursing. To explore the effect analysis of applying high-quality service model to surgical nursing. We conducted a retrospective study of patients who underwent hand surgery at our hospital between 2019 and 2022, using a quality service model that included improved patient education, pain management, care team collaboration, and effective communication. Another group of patients received traditional care as a control group. We compared postoperative recovery, satisfaction, complication rate, and length of hospital stay between the two groups. Inferential statistics were used to compare the difference between the two groups by independent sample t test, Chi-square test and other methods to evaluate the effect of intervention measures. Postoperative recovery time decreased from 17.8 ± 2.3 d to 14.5 ± 2.1 d, pain score decreased from 4.7 ± 1.9 to 3.2 ± 1.4, and hand function score increased from 78.4 ± 7.1 to 88.5 ± 6.2. In terms of patient satisfaction, the quality service model group scored 87.3 ± 5.6 points, which was significantly higher than that of the traditional care group (74.6 ± 6.3 points). At the same time, patients' understanding of medical information also improved from 6.9 ± 1.4 to 8.6 ± 1.2. In terms of postoperative complications, the application of the quality service model reduced the incidence of postoperative complications from 26% to 10%, the incidence of infection from 12% to 5%, and the incidence of bleeding from 10% to 3%. The reduction in these data indicates that the quality service model plays a positive role in reducing the risk of complications. In addition, the average hospital stay of patients in the quality service model group was shortened from 6.8 ± 1.5 d to 5.2 ± 1.3 d, and the hospitalization cost was also reduced from 2800 ± 600 yuan to 2500 ± 500 yuan. Applying a quality service model to hand surgery care can significantly improve patient clinical outcomes, including faster recovery, less pain, greater satisfaction, and reduced complication rates.

Reciprocal Federated Learning Framework: Balancing incentives for model and data owners

In the evolving landscape of Web 3.0, 5G/6G, and real-world applications, federated learning faces unique challenges. Traditional incentive mechanisms struggle to address the need to motivate both data owners to provide high-quality data and model experts to optimize model performance. To navigate this complex scenario, we introduce the Reciprocal Federated Learning Framework (RFLF). This innovative approach fosters a fair and dynamic reward structure that incentivizes both high-quality data contributions and optimal model development. Extensive experiments on benchmark datasets demonstrate that the RFLF significantly enhances fairness and efficiency within federated learning. These results showcase the RFLF’s potential to transform data-driven technologies, promoting both efficiency and equitable outcomes.

Derivation and validation of the first web-based nomogram to predict the spontaneous pregnancy after reproductive surgery using machine learning models.

Infertility remains a significant global burden over the years. Reproductive surgery is an effective strategy for infertile women. Early prediction of spontaneous pregnancy after reproductive surgery is of high interest for the patients seeking the infertility treatment. However, there are no high-quality models and clinical applicable tools to predict the probability of natural conception after reproductive surgery. The eligible data involving 1013 patients who operated for infertility between June 2016 and June 2021 in Yantai Yuhuangding Hospital in China, were randomly divided into training and internal testing cohorts. 195 subjects from the Linyi People's Hospital in China were considered for external validation. Both univariate combining with multivariate logistic regression and the least absolute shrinkage and selection operator (LASSO) algorithm were performed to identify independent predictors. Multiple common machine learning algorithms, namely logistic regression, decision tree, random forest, support vector machine, k-nearest neighbor, and extreme gradient boosting, were employed to construct the predictive models. The optimal model was verified by evaluating the model performance in both the internal and external validation datasets. Six clinical indicators, including female age, infertility type, duration of infertility, intraoperative diagnosis, ovulation monitoring, and anti-Müllerian hormone (AMH) level, were screened out. Based on the logistic regression model's superior clinical predictive value, as indicated by the area under the receiver operating characteristic curve (AUC) in both the internal (0.870) and external (0.880) validation sets, we ultimately selected it as the optimal model. Consequently, we utilized it to generate a web-based nomogram for predicting the probability of spontaneous pregnancy after reproductive surgery. Furthermore, the calibration curve, Hosmer-Lemeshow (H-L) test, the decision curve analysis (DCA) and clinical impact curve analysis (CIC) demonstrated that the model has superior calibration degree, clinical net benefit and generalization ability, which were confirmed by both internal and external validations. Overall, our developed first nomogram with online operation provides an early and accurate prediction for the probability of natural conception after reproductive surgery, which helps clinicians and infertile couples make sensible decision of choosing the mode of subsequent conception, natural or IVF, to further improve the clinical practices of infertility treatment.

Auction-based client selection for online Federated Learning

Federated Learning (FL) has become a popular decentralized learning paradigm to train a machine learning model using distributed mobile devices without compromising user privacy. Despite its advantages, there are several technical challenges to achieving efficient FL. First, clients may have different amount of data with various quality, thus leading to different quality of model updates. In an online setting, it is challenging to select clients having high-quality models in advance or to adjust the selection on the fly. Second, it is an impractical assumption that the clients can selflessly engage in model training without incentives. Meanwhile, the training cost is often considered as private information which is not easily accessible. Under incomplete information, how we design an effective incentive mechanism to achieve the expected economic properties? Third, due to the lack of prior knowledge, managing long-run expenditures in real time is challenging. To this end, we propose a combinatorial multi-armed bandit- and auction-based client selection algorithm named CACS to achieve highly efficient model training. Specifically, CACS divides the client selection process into exploration and exploitation. In the former, CACS employs the upper confidence bound (UCB) quality to estimate the learning quality of clients. In the latter, CACS determines winners based on the UCB quality-bid-ratio and adopts the key payment as the payment. Theoretical analysis shows that CACS obtains the sub-linear regret and economic properties, and can be computationally efficient and ensure the convergence of global model. Extensive simulation experiments also confirm the practical advantages of CACS over state-of-the-art client selection approaches for FL.

Photogrammetry scans for neuroanatomy education-a new multi-camera system: technical note.

Photogrammetry scans has directed attention to the development of advanced camera systems to improve the creation of three-dimensional (3D) models, especially for educational and medical-related purposes. This could be a potential cost-effective method for neuroanatomy education, especially when access to laboratory-based learning is limited. The aim of this study was to describe a new photogrammetry system based on a 5 Digital Single-Lens Reflex (DSLR) cameras setup to optimize accuracy of neuroanatomical 3D models. One formalin-fixed brain and specimen and one dry skull were used for dissections and scanning using the photogrammetry technique. After each dissection, the specimens were placed inside a new MedCreator® scanner (MedReality, Thyng, Chicago, IL) to be scanned with the final 3D model being displayed on SketchFab® (Epic, Cary, NC) and MedReality® platforms. The scanner consisted of 5 cameras arranged vertically facing the specimen, which was positioned on a platform in the center of the scanner. The new multi-camera system contains automated software packages, which allowed for quick rendering and creation of a high-quality 3D models. Following uploading the 3D models to the SketchFab® and MedReality® platforms for display, the models can be freely manipulated in various angles and magnifications in any devices free of charge for users. Therefore, photogrammetry scans with this new multi-camera system have the potential to enhance the accuracy and resolution of the 3D models, along with shortening creation time of the models. This system can serve as an important tool to optimize neuroanatomy education and ultimately, improve patient outcomes.

Education and education with values in the face of contemporary challenges

The current reality, with its multidimensionality and challenges related to the increasingly experienced diversity, affects the sense of stability and security among children and adolescents. Assuming that school is a place where every student has a chance to develop adaptive skills, it is this environment that should provide high-quality role models as well as a focus on stable values that will build social sensitivity and mental strength of students. In this text, we present practical solutions on how to explore the essence of values and at the same time put them into practice. We encourage educators, teachers and caregivers to consider education with values as a way to develop in students a certain philosophy of life that supports their maturation, full development and decisions, and thus fosters inclusion in the community with respect, trust and a sense of meaning. The material contains a theoretical part referring to the assumptions of positive psychology and several ideas, such as exercises on implementing key values.

Practice of distributed machine learning in clinical modeling for chronic obstructive pulmonary disease

BackgroundThe high prevalence, morbidity and mortality, and disease heterogeneity of chronic obstructive pulmonary disease (COPD) result in the scattered data derived from patient visits in different medical units. The huge cost of integrating the scattered data for analysis and modeling, as well as the legal demand for patient privacy protection lead to the emergence of data island. ObjectivesOn the premise of protecting patient privacy, integrating scattered data of patients from different medical units for high-quality modeling is beneficial to promoting the development of digital health. Based on this, we develop a distributed COPD disease diagnosis system termed COPD average federated learning (COPD_AVG_FL) using FedAvg. MethodsFirst, to build the COPD_AVG_FL, the clinical data of COPD patients from the real world is collected and the data pre-processing is performed to clean the incorrect data, outlier samples and missing values. Then, a classical federated learning architecture is designed as COPD_AVG_FL. Finally, to evaluate the established COPD_AVG_FL system, we develop Centralized Machine Learning (CML). ConclusionsOur results suggest that, with the assistance of COPD_AVG_FL, the absolute improvement rates are 13.4% (accuracy), 13.3% (precision), 12.8% (recall), 13.1% (F1-Score) and 12.9% (AUC) on the test data, respectively. The decoupling between model training and raw training data protects the patients' privacy, and helps to securely integrate more COPD data from different medical units to generate a more comprehensive model COPD_AVG_FL. This approach promotes the landing of wise information technology of medicine for COPD in the real clinical world. Code for our model will be made available at https://github.com/Cczhh/COPD_AVG_FL/tree/master.

Development and validation of a multi-parameter nomogram for venous thromboembolism in gastric cancer patients: a retrospective analysis.

Gastric cancer (GC), one of the highest venous thromboembolism (VTE) incidence rates in cancer, contributes to considerable morbidity, mortality, and, prominently, extra cost. However, up to now, there is not a high-quality VTE model to steadily predict the risk for VTE in China. Consequently, setting up a prediction model to predict the VTE risk is imperative. Data from 3,092 patients from December 15, 2017, to December 31, 2022, were retrospectively analyzed. Multiple logistic regression analysis was performed to assess risk factors for GC, and a nomogram was constructed based on screened risk factors. A receiver operating curve (ROC) and calibration plot was created to evaluate the accuracy of the nomogram. The risk factors of suffering from VTE were older age (OR = 1.02, 95% CI [1.00-1.04]), Karnofsky Performance Status (KPS) ≥ 70 (OR = 0.45, 95% CI [0.25-0.83]), Blood transfusion (OR = 2.37, 95% CI [1.47-3.84]), advanced clinical stage (OR = 3.98, 95% CI [1.59-9.99]), central venous catheterization (CVC) (OR = 4.27, 95% CI [2.03-8.99]), operation (OR = 2.72, 95% CI [1.55-4.77]), fibrinogen degradation product (FDP) >5 µg/mL (OR = 1.92, 95% CI [1.13-3.25]), and D-dimer > 0.5 mg/L (OR = 2.50, 95% CI [1.19-5.28]). The area under the ROC curve (AUC) was 0.82 in the training set and 0.85 in the validation set. Our prediction model can accurately predict the risk of the appearance of VTE in gastric cancer patients and can be used as a robust and efficient tool for evaluating the possibility of VTE.

Exploring the Abilities-Cultivation Model for Students in Undergraduate Academies in China

Based on the external impetus of social development and the internal demand for universities to return to the cultivation of abilities, modern universities are actively exploring the reform of the academy system, constructing high-quality ability-cultivation models, doing “addition” in the process of learning and living, and doing “subtraction” in the evaluation of the results of cultivation, achieving certain educational results. However, at the same time, the construction of academies is also facing difficulties in changing concepts, allocating quality resources, and the realistic dilemma of collaborative education between “academy” and “college”. The bottleneck of academy development should be addressed by actively exploring the school’s distinctive model, optimising top-level design, and enriching its spiritual culture. Facing the wave of reform in the academy system, universities should promote the localisation of the academy system in an orderly manner through deliberate thinking.

Highly Accurate and Explainable Predictions of Small-Molecule Antioxidants for Eight In Vitro Assays Simultaneously through an Alternating Multitask Learning Strategy.

Small molecule antioxidants can inhibit or retard oxidation reactions and protect against free radical damage to cells, thus playing a key role in food, cosmetics, pharmaceuticals, the environment, as well as materials. Experimentally driven antioxidant discovery is a major paradigm, and computationally assisted antioxidants are rarely reported. In this study, a functional-group-based alternating multitask self-supervised molecular representation learning method is proposed to simultaneously predict the antioxidant activities of small molecules for eight commonly used in vitro antioxidant assays. Extensive evaluation results reveal that compared with the baseline models, the multitask FG-BERT model achieves the best overall predictive performance, with the highest average F1, BA, ROC-AUC, and PRC-AUC values of 0.860, 0.880, 0.954, and 0.937 for the test sets, respectively. The Y-scrambling testing results further demonstrate that such a deep learning model was not constructed by accident and that it has reliable predictive capabilities. Additionally, the excellent interpretability of the multitask FG-BERT model makes it easy to identify key structural fragments/groups that contribute significantly to the antioxidant effect of a given molecule. Finally, an online antioxidant activity prediction platform called AOP (freely available at https://aop.idruglab.cn/) and its local version were developed based on the high-quality multitask FG-BERT model for experts and nonexperts in the field. We anticipate that it will contribute to the discovery of novel small-molecule antioxidants.

Fair and Robust Federated Learning via Decentralized and Adaptive Aggregation based on Blockchain

As an emerging learning paradigm, Federated Learning (FL) enables data owners to collaborate training a model while keeps data locally. However, classic FL methods are susceptible to model poisoning attacks and Byzantine failures. Despite several defense methods proposed to mitigate such concerns, it is challenging to balance adverse effects while allowing that each credible node contributes to the learning process. To this end, a Fair and Robust FL method is proposed for defense against model poisoning attack from malicious nodes, namely FRFL. FRFL can learn a high-quality model even if some nodes are malicious. In particular, we first classify each participant into three categories: training node, validation node, and blockchain node. Among these, blockchain nodes replace the central server in classic FL methods while enabling secure aggregation. Then, a fairness-aware role rotation method is proposed to periodically alter the sets of training and validation nodes in order to utilize the valuable information included in local datasets of credible nodes. Finally, a decentralized and adaptive aggregation mechanism cooperating with blockchain nodes is designed to detect and discard malicious nodes and produce a high-quality model. The results show the effectiveness of FRFL in enhancing model performance while defending against malicious nodes.

The HADDOCK2.4 web server for integrative modeling of biomolecular complexes.

Interactions between macromolecules, such as proteins and nucleic acids, are essential for cellular functions. Experimental methods can fail to provide all the information required to fully model biomolecular complexes at atomic resolution, particularly for large and heterogeneous assemblies. Integrative computational approaches have, therefore, gained popularity, complementing traditional experimental methods in structural biology. Here, we introduce HADDOCK2.4, an integrative modeling platform, and its updated web interface ( https://wenmr.science.uu.nl/haddock2.4 ). The platform seamlessly integrates diverse experimental and theoretical data to generate high-quality models of macromolecular complexes. The user-friendly web server offers automated parameter settings, access to distributed computing resources, and pre- and post-processing steps that enhance the user experience. To present the web server's various interfaces and features, we demonstrate two different applications: (i) we predict the structure of an antibody-antigen complex by using NMR data for the antigen and knowledge of the hypervariable loops for the antibody, and (ii) we perform coarse-grained modeling of PRC1 with a nucleosome particle guided by mutagenesis and functional data. The described protocols require some basic familiarity with molecular modeling and the Linux command shell. This new version of our widely used HADDOCK web server allows structural biologists and non-experts to explore intricate macromolecular assemblies encompassing various molecule types.

Prediction models for urinary incontinence after robotic-assisted laparoscopic radical prostatectomy: a systematic review.

Even though robotic-assisted laparoscopic radical prostatectomy (RARP) is superior to open surgery in reducing postoperative complications, 6-20% of patients still experience urinary incontinence (UI) after surgery. Therefore, many researchers have established predictive models for UI occurrence after RARP, but the predictive performance of these models is inconsistent. This study aims to systematically review and critically evaluate the published prediction models of UI risk for patients after RARP. We conducted a comprehensive literature search in the databases of PubMed, Cochrane Library, Web of Science, and Embase. Literature published from inception to March 20, 2024, which reported the development and/or validation of clinical prediction models for the occurrence of UI after RARP. We identified seven studies with eight models that met our inclusion criteria. Most of the studies used logistic regression models to predict the occurrence of UI after RARP. The most common predictors included age, body mass index, and nerve sparing procedure. The model performance ranged from poor to good, with the area under the receiver operating characteristic curves ranging from 0.64 to 0.98 in studies. Allthe studies have a high risk of bias. Despite their potential for predicting UI after RARP, clinical prediction models are restricted by their limited accuracy and high risk of bias. In the future, the study design should be improved, the potential predictors should be considered from larger and representative samples comprehensively, and high-quality risk prediction models should be established. And externally validating models performance to enhance their clinical accuracy and applicability.