Are polypharmacy side effects predicted by public data still valid in real-world data?

Background and Objective: Although interest in predicting drug-drug interactions is growing, many predictions are not verified by real-world data. This study aimed to confirm whether predicted polypharmacy side effects using public data also occur in data from actual patients. Methods: We utilized a deep learning-based polypharmacy side effects prediction model to identify cefpodoxime-chlorpheniramine-lung edema combination with a high prediction score and a significant patient population. The retrospective study analyzed patients over 18 years old who were admitted to the Asan medical center between January 2000 and December 2020 and took cefpodoxime or chlorpheniramine orally. The three groups, cefpodoxime-treated, chlorpheniramine-treated, and cefpodoxime & chlorpheniramine-treated were compared using inverse probability of treatment weighting (IPTW) to balance them. Differences between the three groups were analyzed using the Kaplan-Meier method and Cox proportional hazards model. Results: The study population comprised 54,043 patients with a history of taking cefpodoxime, 203,897 patients with a history of taking chlorpheniramine, and 1,628 patients with a history of taking cefpodoxime and chlorpheniramine simultaneously. After adjustment, the 1-year cumulative incidence of lung edema in the patient group that took cefpodoxime and chlorpheniramine simultaneously was significantly higher than in the patient groups that took cefpodoxime or chlorpheniramine only (p=0.001). Patients taking cefpodoxime and chlorpheniramine together had an increased risk of lung edema compared to those taking cefpodoxime alone [hazard ratio (HR) 2.10, 95% CI 1.26-3.52, p<0.005] and those taking chlorpheniramine alone, which also increased the risk of lung edema (HR 1.64, 95% CI 0.99-2.69, p=0.05). Conclusions: Validation of polypharmacy side effect predictions with real-world data can aid patient and clinician decision-making before conducting randomized controlled trials. Simultaneous use of cefpodoxime and chlorpheniramine was associated with a higher long-term risk of lung edema compared to the use of cefpodoxime or chlorpheniramine alone.

A model-free terminal sliding mode control for robots: Achieving fixed-time prescribed performance and convergence.

This paper introduces a new control strategy for robot manipulators, specifically designed to tackle the challenges associated with traditional model-based sliding mode (SM) controller design. These challenges include the need for accurately computed system models, knowledge of disturbance upper bounds, fixed-time convergence, prescribed performance, and the generation of chattering. To overcome these obstacles, we propose the incorporation of a neural network (NN) that effectively addresses these issues by removing the constraint of a precise system model. Additionally, we introduce a novel fixed-time prescribed performance control (PPC) to enhance response performance and position-tracking accuracy, while effectively limiting overshoot and maintaining steady-state error within the predefined range. To expedite the convergence of the SM surface to its equilibrium point, we introduce a faster terminal sliding mode (TSM) surface and a novel fixed-time reaching control algorithm (RCA) with adaptable factors. By integrating these approaches, we develop a novel control strategy that successfully achieves the desired goals for robot manipulators. The effectiveness and stability of the proposed approach are validated through extensive simulations on a 3-DOF SAMSUNG FARA-AT2 robot manipulator, utilizing both Lyapunov criteria and performance evaluations. The results demonstrate improved convergence rate and tracking accuracy, reduced chattering, and enhanced controller robustness.

LDP-GAN : Generative adversarial networks with local differential privacy for patient medical records synthesis.

Electronic medical records(EMR) have considerable potential to advance healthcare technologies, including medical AI. Nevertheless, due to the privacy issues associated with the sharing of patient's personal information, it is difficult to sufficiently utilize them. Generative models based on deep learning can solve this problem by creating synthetic data similar to real patient data. However, the data used for training these deep learning models run into the risk of getting leaked because of malicious attacks. This means that traditional deep learning-based generative models cannot completely solve the privacy issues. Therefore, we suggested a method to prevent the leakage of training data by protecting the model from malicious attacks using local differential privacy(LDP). Our method was evaluated in terms of utility and privacy. Experimental results demonstrated that the proposed method can generate medical data with reasonable performance while protecting training data from malicious attacks.

Prediction of hospitalization and waiting time within 24 hours of emergency department patients with unstructured text data.

Overcrowding of emergency departments is a global concern, leading to numerous negative consequences. This study aimed to develop a useful and inexpensive tool derived from electronic medical records that supports clinical decision-making and can be easily utilized by emergency department physicians. We presented machine learning models that predicted the likelihood of hospitalizations within 24 hours and estimated waiting times. Moreover, we revealed the enhanced performance of these machine learning models compared to existing models by incorporating unstructured text data. Among several evaluated models, the extreme gradient boosting model that incorporated text data yielded the best performance. This model achieved an area under the receiver operating characteristic curve score of 0.922 and an area under the precision-recall curve score of 0.687. The mean absolute error revealed a difference of approximately 3 hours. Using this model, we classified the probability of patients not being admitted within 24 hours as Low, Medium, or High and identified important variables influencing this classification through explainable artificial intelligence. The model results are readily displayed on an electronic dashboard to support the decision-making of emergency department physicians and alleviate overcrowding, thereby resulting in socioeconomic benefits for medical facilities.

Machine learning models to predict the warfarin discharge dosage using clinical information of inpatients from South Korea.

As warfarin has a narrow therapeutic window and obvious response variability among individuals, it is difficult to rapidly determine personalized warfarin dosage. Adverse drug events(ADE) resulting from warfarin overdose can be critical, so that typically physicians adjust the warfarin dosage through the INR monitoring twice a week when starting warfarin. Our study aimed to develop machine learning (ML) models that predicts the discharge dosage of warfarin as the initial warfarin dosage using clinical data derived from electronic medical records within 2 days of hospitalization. During this retrospective study, adult patients who were prescribed warfarin at Asan Medical Center (AMC) between January 1, 2018, and October 31, 2020, were recruited as a model development cohort (n = 3168). Additionally, we created an external validation dataset (n = 891) from a Medical Information Mart for Intensive Care III (MIMIC-III). Variables for a model prediction were selected based on the clinical rationale that turned out to be associated with warfarin dosage, such as bleeding. The discharge dosage of warfarin was used the study outcome, because we assumed that patients achieved target INR at discharge. In this study, four ML models that predicted the warfarin discharge dosage were developed. We evaluated the model performance using the mean absolute error (MAE) and prediction accuracy. Finally, we compared the accuracy of the predictions of our models and the predictions of physicians for 40 data point to verify a clinical relevance of the models. The MAEs obtained using the internal validation set were as follows: XGBoost, 0.9; artificial neural network, 0.9; random forest, 1.0; linear regression, 1.0; and physicians, 1.3. As a result, our models had better prediction accuracy than the physicians, who have difficulty determining the warfarin discharge dosage using clinical information obtained within 2 days of hospitalization. We not only conducted the internal validation but also external validation. In conclusion, our ML model could help physicians predict the warfarin discharge dosage as the initial warfarin dosage from Korean population. However, conducting a successfully external validation in a further work is required for the application of the models.

Cardiovascular Event Rates in Statin-Treated Korean Patients with Cardiovascular Disease: Estimates from a Real-World Population Using Electronic Medical Record Data.

PURPOSE: To estimate the risk of recurrent cardiovascular events in a real-world population of very high-risk Korean patients with prior myocardial infarction (MI), ischemic stroke (IS), or symptomatic peripheral artery disease (sPAD), similar to the Further cardiovascular OUtcomes Research with proprotein convertase subtilisin-kexin type 9 Inhibition in subjects with Elevated Risk (FOURIER) trial population. METHODS: This retrospective study used the Asan Medical Center Heart Registry database built on electronic medical records (EMR) from 2000 to 2016. Patients with a history of clinically evident atherosclerotic cardiovascular disease (ASCVD) with multiple risk factors were followed up for 3 years. The primary endpoint was a composite of MI, stroke, hospitalization for unstable angina, coronary revascularization, and all-cause mortality. RESULTS: Among 15,820 patients, the 3-year cumulative incidence of the composite primary endpoint was 15.3% and the 3-year incidence rate was 5.7 (95% CI 5.5-5.9) per 100 person-years. At individual endpoints, the rates of deaths, MI, and IS were 0.4 (0.3-0.4), 0.9 (0.8-0.9), and 0.8 (0.7-0.9), respectively. The risk of the primary endpoint did not differ significantly between recipients of different intensities of statin therapy. Low-density lipoprotein cholesterol (LDL-C) goals were only achieved in 24.4% of patients during the first year of follow-up. CONCLUSION: By analyzing EMR data representing routine practice in Korea, we found that patients with very high-risk ASCVD were at substantial risk of further cardiovascular events in 3 years. Given the observed risk of recurrent events with suboptimal lipid management by statin, additional treatment to control LDL-C might be necessary to reduce the burden of further cardiovascular events for very high-risk ASCVD patients.

Heterogeneous graph construction and HinSAGE learning from electronic medical records.

Graph representation learning is a method for introducing how to effectively construct and learn patient embeddings using electronic medical records. Adapting the integration will support and advance the previous methods to predict the prognosis of patients in network models. This study aims to address the challenge of implementing a complex and highly heterogeneous dataset, including the following: (1) demonstrating how to build a multi-attributed and multi-relational graph model (2) and applying a downstream disease prediction task of a patient's prognosis using the HinSAGE algorithm. We present a bipartite graph schema and a graph database construction in detail. The first constructed graph database illustrates a query of a predictive network that provides analytical insights using a graph representation of a patient's journey. Moreover, we demonstrate an alternative bipartite model where we apply the model to the HinSAGE to perform the link prediction task for predicting the event occurrence. Consequently, the performance evaluation indicated that our heterogeneous graph model was successfully predicted as a baseline model. Overall, our graph database successfully demonstrated efficient real-time query performance and showed HinSAGE implementation to predict cardiovascular disease event outcomes on supervised link prediction learning.

Real-Time Implementation of the Prescribed Performance Tracking Control for Magnetic Levitation Systems.

For magnetic levitation systems subject to dynamical uncertainty and exterior perturbations, we implement a real-time Prescribed Performance Control (PPC). A modified function of Global Fast Terminal Sliding Mode Manifold (GFTSMM) based on the transformed error of the novel PPC is introduced; hence, the error variable quickly converges to the equilibrium point with the prescribed performance, which means that maximum overshoot and steady-state of the controlled errors will be in a knowledge-defined boundary. To enhance the performance of Global Fast Terminal Sliding Mode Control (GFTSMC) and to reduce chattering in the control input, a modified third-order sliding mode observer (MTOSMO) is proposed to estimate the whole uncertainty and external disturbance. The combination of the GFTSMC, PPC, and MTOSMO generates a novel solution ensuring a finite-time stable position of the controlled ball and the possibility of performing different orbit tracking missions with an impressive performance in terms of tracking accuracy, fast convergence, stabilization, and chattering reduction. It also possesses a simple design that is suitable for real-time applications. By using the Lyapunov-based method, the stable evidence of the developed method is fully verified. We implement a simulation and an experiment on the laboratory magnetic levitation model to demonstrate the improved performance of the developed control system.

An Adaptive Prescribed Performance Tracking Motion Control Methodology for Robotic Manipulators with Global Finite-Time Stability.

In this paper, the problem of an APPTMC for manipulators is investigated. During the robot's operation, the error states should be kept within an outlined range to ensure a steady-state and dynamic attitude. Firstly, we propose the modified PPFs. Afterward, a series of transformed errors is used to convert "constrained" systems into equivalent "unconstrained" ones, to facilitate control design. The modified PPFs ensure position tracking errors are managed in a pre-designed performance domain. Especially, the SSE boundaries will be symmetrical to zero, so when the transformed error is zero, the tracking error will be as well. Secondly, a modified NISMS based on the transformed errors allows for determining the highest acceptable range of the tracking errors in the steady-state, finite-time convergence index, and singularity elimination. Thirdly, a fixed-time USOSMO is proposed to directly estimate the lumped uncertainty. Fourthly, an ASTwCL is applied to deal with observer output errors and chattering. Finally, an observer-based-control solution is synthesized from the above techniques to achieve PCP in the sense of finite-time Lyapunov stability. In addition, the precision, robustness, as well as harmful chattering reduction of the proposed APPTMC are improved significantly. The Lyapunov theory is used to analyze the stability of closed-loop systems. Throughout simulations, the proposed PPTMC has been shown to perform well and be effective.

Seven Days of Bismuth-Based Quadruple Therapy Is as Effective for the First-Line Treatment of Clarithromycin-Resistant Confirmed Helicobacter pylori Infection as 14 Days of Bismuth-Based Quadruple Therapy.

BACKGROUND/AIMS: Point mutations in the 23S ribosomal RNA gene have been associated with Helicobacter pylori (H. pylori) clarithromycin resistance and bismuth-based quadruple therapy (BQT) is one of the options for the treatment of clarithromycin-resistant H. pylori. Current H. pylori treatment guidelines recommend BQT for 10-14 days. This study aims to compare the eradication extents according to 7-day and 14-day BQT treatment for treatment-naïve clarithromycin-resistant confirmed H. pylori infection. METHODS: We retrospectively investigated treatment-naïve H. pylori infection cases from March 2019 to December 2020, where patients were treated with BQT. Clarithromycin resistance was identified with a dual-priming oligonucleotide-based multiplex polymerase chain reaction method. We reviewed a total of 126 cases. Fifty-three subjects were treated with a 7-day BQT regimen (7-day group), and 73 subjects were treated with a 14-day BQT regimen (14-day group). We evaluated the total eradication extent of the BQT and compared the eradication extents of the two study groups. RESULTS: Total eradication extent of H. pylori was 83.3% (105/126). The eradication extents of the two groups were as follows: 7-day group (81.1% (43/53)), 14-day group (84.9% (62/73), p = 0.572) by intention-to-treat analysis; 7-day group (95.6% (43/45)), 14-day group (92.5% (62/67), p = 0.518) by per-protocol analysis. The moderate or severe adverse event extents during the eradication were 30.2% (16/53) in the 7-day group and 19.2% (14/73) in the 14-day group (p = 0.152). CONCLUSIONS: The 7-day BQT regimen was as effective as the 14-day BQT regimen in the eradication of treatment-naïve clarithromycin-resistant H. pylori infection.

RIDAB: Electronic medical record-integrated real world data platform for predicting and summarizing interactions in biomedical research from heterogeneous data resources.

BACKGROUND AND OBJECTIVE: With the advent of bioinformatics, biological databases have been constructed to computerize data. Biological systems can be described as interactions and relationships between elements constituting the systems, and they are organized in various biomedical open databases. These open databases have been used in approaches to predict functional interactions such as protein-protein interactions (PPI), drug-drug interactions (DDI) and disease-disease relationships (DDR). However, just combining interaction data has limited effectiveness in predicting the complex relationships occurring in a whole context. Each contributing source contains information on each element in a specific field of knowledge but there is a lack of inter-disciplinary insight in combining them. METHODS: In this study, we propose the RWD Integrated platform for Discovering Associations in Biomedical research (RIDAB) to predict interactions between biomedical entities. RIDAB is established as a graph network to construct a platform that predicts the interactions of target entities. Biomedical open database is combined with EMRs each representing a biomedical network and a real-world data. To integrate databases from different domains to build the platform, mapping of the vocabularies was required. In addition, the appropriate structure of the network and the graph embedding method to be used were needed to be selected to fit the tasks. RESULTS: The feasibility of the platform was evaluated using node similarity and link prediction for drug repositioning task, a commonly used task for biomedical network. In addition, we compared the US Food and Drug Administration (FDA)-approved repositioned drugs with the predicted result. By integrating EMR database with biomedical networks, the platform showed increased f1 score in predicting repositioned drugs, from 45.62% to 57.26%, compared to platforms based on biomedical networks alone. CONCLUSIONS: This study demonstrates that the elements of biomedical research findings can be reflected by integrating EMR data with open-source biomedical networks. In addition, showed the feasibility of using the established platform to represent the integration of biomedical networks and reflected the relationship between real world networks.

A Novel Prescribed-Performance-Tracking Control System with Finite-Time Convergence Stability for Uncertain Robotic Manipulators.

Through this article, we present an advanced prescribed performance-tracking control system with finite-time convergence stability for uncertain robotic manipulators. It is therefore necessary to define a suitable performance function and error transformation to guarantee a prescribed performance within a finite time. Following the definitions mentioned, a modified integral nonlinear sliding-mode hyperplane is constructed from the transformed errors. By using the designed nonlinear sliding-mode surface and the super-twisting reaching control law, an advanced approach to the prescribed performance control was formed for the trajectory tracking control of uncertain robotic manipulators. The proposed controller exhibits improved properties, including estimated convergence speed and a predefined upper and lower limit for maximum overshoot during transient responses. Furthermore, the maximum allowable size of the control errors at the steady-state can be predefined and these errors will inevitably converge to zero within a finite time, while the proposed controller can provide a smooth control torque without the loss of its robustness. It is shown that the proposed control system is globally stable and convergent over a finite time. A comprehensive analysis of the effectiveness of the proposed control algorithm was already conducted via the simulation of an industrial robot manipulator.

A Novel Active Fault-Tolerant Tracking Control for Robot Manipulators with Finite-Time Stability.

Many terminal sliding mode controllers (TSMCs) have been suggested to obtain exact tracking control of robotic manipulators in finite time. The ordinary method is based on TSMCs that secure trajectory tracking under the assumptions such as the known robot dynamic model and the determined upper boundary of uncertain components. Despite tracking errors that tend to zero in finite time, the weakness of TSMCs is chattering, slow convergence speed, and the need for the exact robot dynamic model. Few studies are handling the weakness of TSMCs by using the combination between TSMCs and finite-time observers. In this paper, we present a novel finite-time fault tolerance control (FTC) method for robotic manipulators. A finite-time fault detection observer (FTFDO) is proposed to estimate all uncertainties, external disturbances, and faults accurately and on time. From the estimated information of FTFDO, a novel finite-time FTC method is developed based on a new finite-time terminal sliding surface and a new finite-time reaching control law. Thanks to this approach, the proposed FTC method provides a fast convergence speed for both observation error and control error in finite time. The operation of the robot system is guaranteed with expected performance even in case of faults, including high tracking accuracy, small chattering behavior in control input signals, and fast transient response with the variation of disturbances, uncertainties, or faults. The stability and finite-time convergence of the proposed control system are verified that they are strictly guaranteed by Lyapunov theory and finite-time control theory. The simulation performance for a FARA robotic manipulator proves the proposed control theory's correctness and effectiveness.

A Robust Observer-Based Control Strategy for n-DOF Uncertain Robot Manipulators with Fixed-Time Stability.

In this paper, a robust observer-based control strategy for n-DOF uncertain robot manipulators with fixed-time stability was developed. The novel fixed-time nonsingular sliding mode surface enables control errors to converge to the equilibrium point quickly within fixed time without singularity. The development of the novel fixed-time disturbance observer based on a uniform robust exact differentiator also allows uncertain terms and exterior disturbances to be proactively addressed. The designed observer can accurately approximate uncertain terms within a fixed time and contribute to significant chattering reduction in the traditional sliding mode control. A robust observer-based control strategy was formulated, according to a combination of the fixed-time nonsingular terminal sliding mode control method and the designed observer, to yield global fixed time stability for n-DOF uncertain robot manipulators. The proposed controller proved definitively that it was able to obtain global stabilization in fixed time. The approximation capability of the proposed observer, the convergence of the proposed sliding surface, and the effectiveness of the proposed control strategy in fixed time were fully confirmed by simulation performance on an industrial robot manipulator.

Self-Training With Quantile Errors for Multivariate Missing Data Imputation for Regression Problems in Electronic Medical Records: Algorithm Development Study.

BACKGROUND: When using machine learning in the real world, the missing value problem is the first problem encountered. Methods to impute this missing value include statistical methods such as mean, expectation-maximization, and multiple imputations by chained equations (MICE) as well as machine learning methods such as multilayer perceptron, k-nearest neighbor, and decision tree. OBJECTIVE: The objective of this study was to impute numeric medical data such as physical data and laboratory data. We aimed to effectively impute data using a progressive method called self-training in the medical field where training data are scarce. METHODS: In this paper, we propose a self-training method that gradually increases the available data. Models trained with complete data predict the missing values in incomplete data. Among the incomplete data, the data in which the missing value is validly predicted are incorporated into the complete data. Using the predicted value as the actual value is called pseudolabeling. This process is repeated until the condition is satisfied. The most important part of this process is how to evaluate the accuracy of pseudolabels. They can be evaluated by observing the effect of the pseudolabeled data on the performance of the model. RESULTS: In self-training using random forest (RF), mean squared error was up to 12% lower than pure RF, and the Pearson correlation coefficient was 0.1% higher. This difference was confirmed statistically. In the Friedman test performed on MICE and RF, self-training showed a P value between .003 and .02. A Wilcoxon signed-rank test performed on the mean imputation showed the lowest possible P value, 3.05e-5, in all situations. CONCLUSIONS: Self-training showed significant results in comparing the predicted values and actual values, but it needs to be verified in an actual machine learning system. And self-training has the potential to improve performance according to the pseudolabel evaluation method, which will be the main subject of our future research.

Aortic annulus sizing in bicuspid and tricuspid aortic valves using CT in patients with surgical aortic valve replacement.

The purpose of this study was to evaluate whether bicuspid anatomy affects the discrepancy between CT-derived annular size and intraoperative size. We retrospectively analyzed annular measurements in 667 patients who underwent surgical aortic valve replacement (AVR). Preoperative CT measurements of the aortic annulus were compared to surgically implanted valve sizes. To evaluate whether the bicuspid valve affects the differences between CT annulus diameter and surgical AVR size, patients with diameter larger by > 10% (CT-Lg group) on CT, compared to surgical AVR size, were compared with those having size difference < 10% (CT-Sim group). Propensity score matching yielded 183 matched patients from each group. Bicuspid aortic valve annulus parameters significantly correlated with surgical aortic valve size (r = 0.52-0.71; for all, p < 0.01). The most representative measurements corresponded to surgical aortic valve size were area-derived diameters in tricuspid aortic valve (r = 0.69, p < 0.001) and bicuspid without raphe (r = 0.71, p < 0.001), and perimeter-derived diameter in bicuspid with raphe (r = 0.63, p < 0.001). After propensity score matching, native valve type was not different between CT-Sim and CT-Lg groups. In multivariable analysis, the difference between CT-derived diameter and surgical AVR size was affected by the operator factor and types of prosthesis. Bicuspid aortic annulus diameters measured on CT showed a significant correlation with surgical aortic valve size. The difference between CT-derived diameter and surgical AVR size is affected by operator factor and the types of prosthesis but not affected by the bicuspid valve.

CardioNet: a manually curated database for artificial intelligence-based research on cardiovascular diseases.

BACKGROUND: Cardiovascular diseases (CVDs) are difficult to diagnose early and have risk factors that are easy to overlook. Early prediction and personalization of treatment through the use of artificial intelligence (AI) may help clinicians and patients manage CVDs more effectively. However, to apply AI approaches to CVDs data, it is necessary to establish and curate a specialized database based on electronic health records (EHRs) and include pre-processed unstructured data. METHODS: To build a suitable database (CardioNet) for CVDs that can utilize AI technology, contributing to the overall care of patients with CVDs. First, we collected the anonymized records of 748,474 patients who had visited the Asan Medical Center (AMC) or Ulsan University Hospital (UUH) because of CVDs. Second, we set clinically plausible criteria to remove errors and duplication. Third, we integrated unstructured data such as readings of medical examinations with structured data sourced from EHRs to create the CardioNet. We subsequently performed natural language processing to structuralize the significant variables associated with CVDs because most results of the principal CVD-related medical examinations are free-text readings. Additionally, to ensure interoperability for convergent multi-center research, we standardized the data using several codes that correspond to the common data model. Finally, we created the descriptive table (i.e., dictionary of the CardioNet) to simplify access and utilization of data for clinicians and engineers and continuously validated the data to ensure reliability. RESULTS: CardioNet is a comprehensive database that can serve as a training set for AI models and assist in all aspects of clinical management of CVDs. It comprises information extracted from EHRs and results of readings of CVD-related digital tests. It consists of 27 tables, a code-master table, and a descriptive table. CONCLUSIONS: CardioNet database specialized in CVDs was established, with continuing data collection. We are actively supporting multi-center research, which may require further data processing, depending on the subject of the study. CardioNet will serve as the fundamental database for future CVD-related research projects.

A Deep Neural Network-Based Feature Fusion for Bearing Fault Diagnosis.

This paper presents a novel method for fusing information from multiple sensor systems for bearing fault diagnosis. In the proposed method, a convolutional neural network is exploited to handle multiple signal sources simultaneously. The most important finding of this paper is that a deep neural network with wide structure can extract automatically and efficiently discriminant features from multiple sensor signals simultaneously. The feature fusion process is integrated into the deep neural network as a layer of that network. Compared to single sensor cases and other fusion techniques, the proposed method achieves superior performance in experiments with actual bearing data.