[Predict the effect of the number of positive preoperative serum tumor markers on the surgical method and prognosis of intrahepatic cholangiocarcinoma patients based on mediation analysis].

Objective: To investigate the effect of the number of positive preoperative serological tumor markers on the surgical approach and prognosis of patients with intrahepatic cholangiocarcinoma. Methods: This is a retrospective case-series study. Data from 548 patients with intrahepatic cholangiocarcinoma after radical resection from October 2010 to April 2019 were retrospectively collected in 10 hospitals of China. There were 277 males and 271 females with an age of (57.8±10.2)years(range:23 to 84 years). Four hundred and twenty-six patients(77.7%) had at least one positive preoperative serum tumor marker. The data collection included the results of 4 preoperative serological tumor markers,other preoperative indicators(5 prodromal symptoms, 6 medical history,8 preoperative serological indicators,5 preoperative imaging indicators,and 14 preoperative pathological examination indicators),baseline data (gender and age),surgical methods,and prognostic follow-up data. Four preoperative results of serologic tumor marker and surgical procedure were converted into categorical variables. The number of positive preoperative serum tumor markers was used as the treatment variable,the surgical method was used as the mediating variable,and the survival time was used as the outcome variable. Univariate and multivariate analysis were used to screen for other preoperative indicators which were independent factors that influenced the surgical procedure and the prognosis of patients as covariates to analyze the mediating effect. Results: Of the 548 patients included in the study, 176 patients (32.1%) underwent partial hepatectomy,151 patients(27.5%) underwent hemihepatectomy, and 221 patients(40.3%) underwent partial hepatectomy or hemihepatectomy combined with other treatments. The results of the univariate and multivariate analysis showed that the number of positive serum tumor markers,intrahepatic bile duct dilatation,portal vein invasion,pathological differentiation,pathological type,vascular invasion,T stage,N stage and maximum tumor diameter were independent factors influencing the surgical procedure(all P<0.05). Intrahepatic bile duct dilatation,pathological differentiation and T stage were independent prognostic factors for patients with intrahepatic cholangiocarcinoma(all P<0.05). Intrahepatic bile duct dilatation,differentiation and T stage were included as covariates in the mediation effect model. The results showed that the number of positive serum tumor markers before surgery had a negative predictive effect on the survival time of patients with intrahepatic cholangiocarcinoma (ß=-0.092, P=0.039),and had a positive predictive effect on the surgical method (ß=0.244,P<0.01). The number of positive serum tumor markers had a negative predictive effect on the survival time of patients with intrahepatic cholangiocarcinoma (ß=-0.151, P=0.002). Direct and indirect effects accounted for 71.3% and 28.7% of total effects,respectively. Conclusions: The higher the positive number of preoperative tumor markers,the worse the prognosis of patients with intrahepatic cholangiocarcinoma. The number of positive cells not only directly affects the prognosis of patients,but also indirectly affects the prognosis of patients by affecting the surgical method.

[Prediction of prognosis of patients with radical resection of intrahepatic cholangiocarcinoma based on single cell omics].

Objectives: To analyze the survival benefit of intrahepatic cholangiocarcinoma (ICC) radical resection based on single cell omics. Methods: This is a retrospective case-series study. ICC single-cell sequencing was integrated from four data sets in the Gene Expression Omnibus Database, with a total of 46 patients undergoing radical resection, to explore the characteristics of the microenvironment. Microarray data of 100 ICC cases was analyzed in the EMBI database with survival data. The infiltration abundance of each epithelial cell cluster was calculated in each microarray data sample using the ssGSEA algorithm. The key epithelial cell cluster associated with poor patient outcomes was explored. The clinical value of key marker genes in this subgroup was studied. Prognostic marker genes were selected using the univariate and multivariate Cox proportional hazards(CoxPH) model. The The CoxPH model was constructed by the target genes and a nomogram was drawn. Kaplan-Meier survival analysis was used to verify the relationship between score and prognosis of patients. The predictive power of the model was evaluated by receiver operating characteristic(ROC) curves, calibration curves, and decision curve analysis (DCA). Results: Epithelial cell clusters infiltrated almost exclusively in tumor tissue. The MT2A+ epithelial cell subset was associated with a poorer prognosis for patients with a high invasion abundance and patients characterized by infiltration of this group were defined as antioxidant. After screening marker genes in this cluster using a univariate and multivariate CoxPH model, the following genes were found to be independent prognostic factors: FILPIL, NFKBIA, PEG10, SERPINB5. The CoxPH model was constructed using the four gene expression levels, and the survival rate of patients in the high-risk group was significantly lower than those in the low-risk group (all P<0.05). The constructed nomogram had good discrimination and validity. The ROC curve showed that the predicted area under the curve was 0.779, 0.844 and 0.845 at 1, 3 and 5 years, respectively. Compared to clinical indicators, the model had better predictive power using the calibration curve and the DCA test. Conclusions: The MT2A+ epithelial cell group may be associated with the prognosis of patients with ICC, and the concept of ICC tissue typing of antioxidant and non-antioxidant types is proposed. The type of antioxidant may predict the poor prognosis of the patients, and postoperative adjuvant therapy and other means could be considered to improve the survival of the patients.

[New advances in the diagnosis and treatment of intrahepatic cholangiocarcinoma].

Intrahepatic cholangiocarcinoma (ICC) is a type of primary liver cancer, which has shown an increasing trend in incidence and mortality in recent years, with a poor prognosis. The clinical diagnosis and treatment of ICC currently face the challenges of low detection rate, high mortality rate, poor treatment outcome, and urgently need more in-depth research to promote the improvement of clinical diagnosis and treatment level. In recent years, ICC diagnosis and treatment related research has made new progress in many aspects, and the knowledge about these new clinical diagnosis and treatment advances should be updated in a timely manner. This article reviewed the latest research results in recent years, summarized some new views on ICC typing, prevention and diagnosis staging that have been proposed recently, as well as the new progress made in surgical treatment and systemic treatment, and briefly discussed the potential of ICC individualized precision treatment and the occurrence of rare complications caused by combined treatment.

Deep learning for computer-aided abnormalities classification in digital mammogram: A data-centric perspective.

Breast cancer is the most common type of cancer in women, and early abnormality detection using mammography can significantly improve breast cancer survival rates. Diverse datasets are required to improve the training and validation of deep learning (DL) systems for autonomous breast cancer diagnosis. However, only a small number of mammography datasets are publicly available. This constraint has created challenges when comparing different DL models using the same dataset. The primary contribution of this study is the comprehensive description of a selection of currently available public mammography datasets. The information available on publicly accessible datasets is summarized and their usability reviewed to enable more effective models to be developed for breast cancer detection and to improve understanding of existing models trained using these datasets. This study aims to bridge the existing knowledge gap by offering researchers and practitioners a valuable resource to develop and assess DL models in breast cancer diagnosis.

Towards a Machine Learning Driven Trust Management Heuristic for the Internet of Vehicles.

The rapid proliferation of the emerging yet promising notion of the Internet-of-Vehicles (IoV) has led to the development of a variety of conventional trust assessment schemes to tackle insider attackers. The primary reliance of these frameworks is on the accumulation of individual trust attributes. While aggregating these influential parameters, weights are often associated with each individual attribute to reflect its impact on the final trust score. It is of paramount importance that such weights be precise to lead to an accurate trust assessment. Moreover, the value of the minimum acceptable trust threshold employed for the identification of dishonest vehicles needs to be carefully defined to avoid delayed or erroneous detection. This paper employs an IoT data set from CRAWDAD by suitably transforming it into an IoV format. This data set encompasses information regarding 18,226 interactions among 76 nodes, both honest and dishonest. First, the influencing parameters (i.e., packet delivery ratio, familiarity, timeliness and interaction frequency) were computed, and two feature matrices were formed. The first matrix (FM1) takes into account all the pairwise individual parameters as individual features, whereas the second matrix (FM2) considers the average of all pairwise computations performed for each individual parameter as one feature. Subsequently, unsupervised learning is employed to achieve the ground truth prior to applying supervised machine learning algorithms for classification purposes. It is worth noting that Subspace KNN yielded a perfect precision, recall, and the F1-score equal to 1 for individual parametric scores, whereas Subspace Discriminant returned an ideal precision, recall, and the F1-score equal to 1 for mean parametric scores. It is also evident from extensive simulations that FM2 yielded more accurate classification results compared to FM1. Furthermore, decision boundaries among honest and dishonest vehicles have also been computed for respective feature matrices.

[Exploring the significance of chemotherapy in the perioperative application of biliary tract carcinomas].

Biliary tract cancer is extremely malignant with a poor prognosis. At the moment, the only curative method available is radical resection. Targeted and immunotherapy are currently advancing quickly, but chemotherapy still holds a key role in the perioperative management of biliary cancer. Perioperative chemotherapy aims to decrease tumor volume before surgery so that patients can have their tumors surgically removed or have a higher radical resection rate. It also aims to remove any tumor cells that remain after surgery and prevent the growth of new tumors. Chemotherapy-based combination treatment techniques have been increasingly investigated in recent years to improve perioperative care and patient survival. From the standpoint of chemotherapy regimens and clinical trial success in the perioperative phase of radical surgery, the value of chemotherapy in the perioperative period of biliary tract cancer were explored in this paper.

[Survival analysis of patients with intrahepatic cholangiocarcinoma treated with adjuvant chemotherapy after radical resection based on CoxPH model and deep learning algorithm].

Objective: To establish a predictive model for survival benefit of patients with intrahepatic cholangiocarcinoma (ICC) who received adjuvant chemotherapy after radical resection. Methods: The clinical and pathological data of 249 patients with ICC who underwent radical resection and adjuvant chemotherapy at 8 hospitals in China from January 2010 to December 2018 were retrospectively collected. There were 121 males and 128 females,with 88 cases>60 years old and 161 cases≤60 years old. Feature selection was performed by univariate and multivariate Cox regression analysis. Overall survival time and survival status were used as outcome indicators,then target clinical features were selected. Patients were stratified into high-risk group and low-risk group,survival differences between the two groups were analyzed. Using the selected clinical features, the traditional CoxPH model and deep learning DeepSurv survival prediction model were constructed, and the performance of the models were evaluated according to concordance index(C-index). Results: Portal vein invasion, carcinoembryonic antigen>5 µg/L,abnormal lymphocyte count, low grade tumor pathological differentiation and positive lymph nodes>0 were independent adverse prognostic factors for overall survival in 249 patients with adjuvant chemotherapy after radical resection (all P<0.05). The survival benefit of adjuvant chemotherapy in the high-risk group was significantly lower than that in the low-risk group (P<0.05). Using the above five features, the traditional CoxPH model and the deep learning DeepSurv survival prediction model were constructed. The C-index values of the training set were 0.687 and 0.770, and the C-index values of the test set were 0.606 and 0.763,respectively. Conclusion: Compared with the traditional Cox model, the DeepSurv model can more accurately predict the survival probability of patients with ICC undergoing adjuvant chemotherapy at a certain time point, and more accurately judge the survival benefit of adjuvant chemotherapy.

[A nomogram for preoperative prediction of lymph node metastasis in patients with intrahepatic cholangiocarcinoma based on inflammation-related markers].

Objectives: To construct a nomogram for prediction of intrahepatic cholangiocarcinoma (ICC) lymph node metastasis based on inflammation-related markers,and to conduct its clinical verification. Methods: Clinical and pathological data of 858 ICC patients who underwent radical resection were retrospectively collected at 10 domestic tertiary hospitals in China from January 2010 to December 2018. Among the 508 patients who underwent lymph node dissection,207 cases had complete variable clinical data for constructing the nomogram,including 84 males,123 females,109 patients≥60 years old,98 patients<60 years old and 69 patients were pathologically diagnosed with positive lymph nodes after surgery. Receiver operating characteristic curve was drawn to calculate the accuracy of preoperative imaging examinations to determine lymph node status,and the difference in overall survival time was compared by Log-rank test. Partial regression squares and statistically significant preoperative variables were screened by backward stepwise regression analysis. R software was applied to construct a nomogram,clinical decision curve and clinical influence curve,and Bootstrap method was used for internal verification. Moreover,retrospectively collecting clinical information of 107 ICC patients with intraoperative lymph node dissection admitted to 9 tertiary hospitals in China from January 2019 to June 2021 was for external verification to verify the accuracy of the nomogram. 80 patients with complete clinical data but without lymph node dissection were divided into lymph node metastasis high-risk group and low-risk group according to the score of the nomogram among the 858 patients. Log-rank test was used to compare the overall survival of patients with or without lymph node metastasis diagnosed by pathology. Results: The area under the curve of preoperative imaging examinations for lymph node status assessment of 440 patients was 0.615,with a false negative rate of 62.8% (113/180) and a false positive rate of 14.2% (37/260). The median survival time of 207 patients used to construct a nomogram with positive or negative postoperative pathological lymph node metastases was 18.5 months and 27.1 months,respectively (P<0.05). Five variables related to lymph node metastasis were screened out by backward stepwise regression analysis,which were combined calculi,neutrophil/lymphocyte ratio,albumin,liver capsule invasion and systemic immune inflammation index,according to which a nomogram was constructed with concordance index(C-index) of 0.737 (95%CI: 0.667 to 0.806). The C-index of external verification was 0.674 (95%CI:0.569 to 0.779). The calibration prediction curve was in good agreement with the reference curve. The results of the clinical decision curve showed that when the risk threshold of high lymph node metastasis in the nomogram was set to about 0.32,the maximum net benefit could be obtained by 0.11,and the cost/benefit ratio was 1∶2. The results of clinical influence curve showed that when the risk threshold of high lymph node metastasis in the nomogram was set to about 0.6,the probability of correctly predicting lymph node metastasis could reach more than 90%. There was no significant difference in overall survival time between patients with high/low risk of lymph node metastasis assessed by the nomogram and those with pathologically confirmed lymph node metastasis or without lymph node metastasis (Log-rank test:P=0.082 and 0.510,respectively). Conclusion: The prediction accuracy of preoperative nomogram for ICC lymph node metastasis based on inflammation-related markers is satisfactory,which can be used as a supplementary method for preoperative diagnosis of lymph node metastasis and is helpful for clinicians to make personalized decision of lymph node dissection for patients with ICC.

Beyond CNNs: Exploiting Further Inherent Symmetries in Medical Image Segmentation.

Automatic tumor or lesion segmentation is a crucial step in medical image analysis for computer-aided diagnosis. Although the existing methods based on convolutional neural networks (CNNs) have achieved the state-of-the-art performance, many challenges still remain in medical tumor segmentation. This is because, although the human visual system can detect symmetries in 2-D images effectively, regular CNNs can only exploit translation invariance, overlooking further inherent symmetries existing in medical images, such as rotations and reflections. To solve this problem, we propose a novel group equivariant segmentation framework by encoding those inherent symmetries for learning more precise representations. First, kernel-based equivariant operations are devised on each orientation, which allows it to effectively address the gaps of learning symmetries in existing approaches. Then, to keep segmentation networks globally equivariant, we design distinctive group layers with layer-wise symmetry constraints. Finally, based on our novel framework, extensive experiments conducted on real-world clinical data demonstrate that a group equivariant Res-UNet (called GER-UNet) outperforms its regular CNN-based counterpart and the state-of-the-art segmentation methods in the tasks of hepatic tumor segmentation, COVID-19 lung infection segmentation, and retinal vessel detection. More importantly, the newly built GER-UNet also shows potential in reducing the sample complexity and the redundancy of filters, upgrading current segmentation CNNs, and delineating organs on other medical imaging modalities.

Deep graph level anomaly detection with contrastive learning.

Graph level anomaly detection (GLAD) aims to spot anomalous graphs that structure pattern and feature information are different from most normal graphs in a graph set, which is rarely studied by other researchers but has significant application value. For instance, GLAD can be used to distinguish some different characteristic molecules in drug discovery and chemical analysis. However, GLAD mainly faces the following three challenges: (1) learning more comprehensive graph level representations to differ normal graphs and abnormal graphs, (2) designing an effective graph anomaly evaluation paradigm to capture graph anomalies from the local and global graph perspectives, (3) overcoming the number imbalance problem of normal and abnormal graphs. In this paper, we combine graph neural networks and contrastive learning to build an end-to-end GLAD framework for solving the three challenges above. We aim to design a new graph level anomaly evaluation way, which first utilizes the contrastive learning strategy to enhance different level representations of normal graphs from node and graph levels by a graph convolution autoencoder with perturbed graph encoder. Then, we evaluate the error of them with corresponding representations of the generated reconstruction graph to detect anomalous graphs. Extensive experiments on ten real-world datasets from three areas, such as molecular, protein and social network anomaly graphs, show that our model can effectively detect graph level anomaly from the majority and outperform existing advanced methods.

Perturb and optimize users' location privacy using geo-indistinguishability and location semantics.

Location-based services (LBS) are capable of providing location-based information retrieval, traffic navigation, entertainment services, emergency rescues, and several similar services primarily on the premise of the geographic location of users or mobile devices. However, in the process of introducing a new user experience, it is also easy to expose users' specific location which can result in more private information leakage. Hence, the protection of location privacy remains one of the critical issues of the location-based services. Moreover, the areas where humans work and live have different location semantics and sensitivities according to their different social functions. Although the privacy protection of a user's real location can be achieved by the perturbation algorithm, the attackers may employ the semantics information of the perturbed location to infer a user's real location semantics in an attempt to spy on a user's privacy to certain extent. In order to mitigate the above semantics inference attack, and further improve the quality of the location-based services, this paper hereby proposes a user side location perturbation and optimization algorithm based on geo-indistinguishability and location semantics. The perturbation area satisfying geo-indistinguishability is thus generated according to the planar Laplace mechanism and optimized by combining the semantics information and time characteristics of the location. The optimum perturbed location that is able to satisfy the minimum loss of location-based service quality is selected via a linear programming method, and can be employed to replace the real location of the user so as to prevent the leakage of the privacy. Experimental comparison of the actual road network and location semantics dataset manifests that the proposed method reduces approximately 37% perturbation distance in contrast to the other state-of-the-art methods, maintains considerably lower similarity of location semantics, and improves region counting query accuracy by a margin of around 40%.

[Progress in clinical diagnosis and treatment of gallbladder cancer].

Due to the lack of effective early diagnosis and treatment, gallbladder cancer(GBC) remains a malignant tumor with extremely high malignancy and poor prognosis. Therefore, high quality studies are required to break through the bottleneck in GBC diagnosis and treatment. This article reviewed the domestic and foreign GBC research published in 2021, presenting a comprehensive summary of the important advances in the field of clinical diagnosis and treatment. Latest epidemiological data and risk factors, emerging diagnostic methods of peripheral blood laboratory tests and imaging, new pathologic classification system, hot topics and controversies of surgical treatment as well as the dynamics of systemic treatment of GBC are reviewed in the article. The present findings may contribute to a more efficient means of diagnosis and treatment for GBC and hold the promise of improved outcomes for patients with GBC.

Adversarial Robustness of Deep Reinforcement Learning Based Dynamic Recommender Systems.

Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding space of those techniques makes adversarial attacks challenging to detect at an early stage. Recent advance in causality shows that counterfactual can also be considered one of the ways to generate the adversarial samples drawn from different distribution as the training samples. We propose to explore adversarial examples and attack agnostic detection on reinforcement learning (RL)-based interactive recommendation systems. We first craft different types of adversarial examples by adding perturbations to the input and intervening on the casual factors. Then, we augment recommendation systems by detecting potential attacks with a deep learning-based classifier based on the crafted data. Finally, we study the attack strength and frequency of adversarial examples and evaluate our model on standard datasets with multiple crafting methods. Our extensive experiments show that most adversarial attacks are effective, and both attack strength and attack frequency impact the attack performance. The strategically-timed attack achieves comparative attack performance with only 1/3 to 1/2 attack frequency. Besides, our white-box detector trained with one crafting method has the generalization ability over several other crafting methods.

A Comprehensive Survey on Community Detection With Deep Learning.

Detecting a community in a network is a matter of discerning the distinct features and connections of a group of members that are different from those in other communities. The ability to do this is of great significance in network analysis. However, beyond the classic spectral clustering and statistical inference methods, there have been significant developments with deep learning techniques for community detection in recent years--particularly when it comes to handling high-dimensional network data. Hence, a comprehensive review of the latest progress in community detection through deep learning is timely. To frame the survey, we have devised a new taxonomy covering different state-of-the-art methods, including deep learning models based on deep neural networks (DNNs), deep nonnegative matrix factorization, and deep sparse filtering. The main category, i.e., DNNs, is further divided into convolutional networks, graph attention networks, generative adversarial networks, and autoencoders. The popular benchmark datasets, evaluation metrics, and open-source implementations to address experimentation settings are also summarized. This is followed by a discussion on the practical applications of community detection in various domains. The survey concludes with suggestions of challenging topics that would make for fruitful future research directions in this fast-growing deep learning field.

[Significance of combination of targeted therapy and immunotherapy in conversion therapy of biliary tract cancer].

Biliary tract cancer has insidious onset and high degree of malignancy, and radical resection is often impossible when it is diagnosed.Conversion therapy can achieve tumor downgrading, so that patients who were initially unresectable have a chance to achieve R0 resection.However, due to the high heterogeneity and complex immune microenvironment of biliary tract cancer, conversion therapy is still in the stage of active exploration.As a new type of conversion therapy, combination of targeted therapy and immunotherapy is of great significance to effectively improve the efficiency of conversion therapy.Further exploration of combination mechanism and improvement of immune microenvironment are expected to become the future direction of combination of targeted therapy and immunotherapy.

Adaptive Observer Based Fault Tolerant Control for Sensor and Actuator Faults in Wind Turbines.

The installed wind energy generation capacity has been increasing dramatically all over the world. However, most wind turbines are installed in hostile environments, where regular operation needs to be ensured by effective fault tolerant control methods. An adaptive observer-based fault tolerant control scheme is proposed in this article to address the sensor and actuator faults that usually occur on the core subsystems of wind turbines. The fast adaptive fault estimation (FAFE) algorithm is adopted in the adaptive observers to accurately and rapidly located the faults. Based on the states and faults estimated by the adaptive observers, the state feedback fault tolerant controllers are designed to stabilize the system and compensate for the faults. The gain matrices of the controllers are calculated by the pole placement method. Simulation results illustrate that the proposed fault tolerant control scheme with the FAFE algorithm stabilizes the faulty system effectively and performs better than the baseline on the benchmark model of wind turbines.

Dataset for toothbrushing activity using brush-attached and wearable sensors.

Maintaining oral hygiene is very important for a healthy life. Poor toothbrushing is one of the leading causes of tooth decay and other gum problems. Many people do not brush their teeth properly. There is very limited technology available to help in assessing the quality of toothbrushing. Human Activity Recognition (HAR) applications have seen a tremendous growth in recent years. In this work, we treat the adherence to standard toothbrushing practice as an activity recognition problem. We investigate this problem and collect experimental data using a brush-attached and a wearable sensor when the users brush their teeth. In this paper, we extend our previous dataset [1] for toothbrushing activity by including more experiments and adding a new sensor. We discuss and analyse the collection of the dataset. We use an Inertial Measurement Unit (IMU) sensor to collect the time-series data for toothbrushing activity. We recruited 22 healthy participants and collected the data in two different settings when they brushed their teeth in five different locations using both electric and manual brushes. In total, we have recorded 120 toothbrushing sessions using both brush-attached sensor and the wearable sensor.

Machine learning research towards combating COVID-19: Virus detection, spread prevention, and medical assistance.

COVID-19 was first discovered in December 2019 and has continued to rapidly spread across countries worldwide infecting thousands and millions of people. The virus is deadly, and people who are suffering from prior illnesses or are older than the age of 60 are at a higher risk of mortality. Medicine and Healthcare industries have surged towards finding a cure, and different policies have been amended to mitigate the spread of the virus. While Machine Learning (ML) methods have been widely used in other domains, there is now a high demand for ML-aided diagnosis systems for screening, tracking, predicting the spread of COVID-19 and finding a cure against it. In this paper, we present a journey of what role ML has played so far in combating the virus, mainly looking at it from a screening, forecasting, and vaccine perspective. We present a comprehensive survey of the ML algorithms and models that can be used on this expedition and aid with battling the virus.

[Conversion therapy of biliary tract cancer from the perspective of tumor heterogeneity].

Biliary tract cancer is found in the middle and advanced stages mostly and patients will deprive surgical indications. Conversion therapy can make the stage of some patients down and thus make radical resection feasible. Biliary tract cancer is highly heterogeneous in clinical features, cell origin, histology, molecular biology and other aspects, resulting in a lack of specific and effective conversion therapy strategies. Currently, it is the important development direction to evaluate and classify different individual conditions and select individualized conversion therapy regimens. With the deepening of the research on the pathogenesis and the improvement of treatment protocols, the future conversion therapy will undoubtedly develop towards the direction of individualization and precision.

Zoledronic acid and fracture risk: a meta-analysis of 12 randomized controlled trials.

OBJECTIVE: Zoledronic acid is widely used in patients with osteoporosis, and this meta-analysis aims to explore the influence of zoledronic acid on fracture risk and mortality in patients with osteoporosis or osteopenia. MATERIALS AND METHODS: We searched PubMed, Google Scholar, and Cochrane Library for randomized clinical trials comparing zoledronic acid with control intervention (i.e., placebo or nothing) for osteoporosis or osteopenia. The fracture and mortality were estimated using the random-effect model. RESULTS: 12 randomized trials were included in this meta-analysis. Compared to control intervention, zoledronic acid was associated with significantly reduced incidence of fracture at the follow-up of 12 months, 24 months, 36 months and 72 months. In addition, zoledronic acid could remarkably reduce mortality at 12 months and 24 months than control intervention but revealed no influence on mortality at 36 months or 72 months. In terms of adverse events, zoledronic acid might result in the increase in serious atrial fibrillation and death from stroke than control intervention. CONCLUSIONS: Zoledronic acid is beneficial to reduce the incidence of fracture, while its benefits to reduce the mortality are only observed at the follow-up time of 24 months.