Clinical application of artificial neural network (ANN) modeling to predict pharmacokinetic parameters of severely ill patients

Application of Northern Goshawk Back-Propagation Artificial Neural Network in the Prediction of Monohydroxycarbazepine Concentration in Patients with Epilepsy

INTRODUCTION

A northern goshawk back-propagation artificial neural network (NGO-BPANN) model was established to predict monohydroxycarbazepine (MHD) concentration in patients with epilepsy.

METHODS

The data were collected from 108 Han Chinese patients with epilepsy on oxcarbazepine monotherapy. The results of 14 genotype variates were selected as the input layer in the first BPANN model, and the variables that had a more significant impact on the plasma concentration of MHD were retained. With demographic characteristics and clinical laboratory test results, the genotypes of SCN1A rs2298771 and SCN2A rs17183814 were used to construct the BPANN model. The BPANN model was comprehensively validated and used to predict the MHD plasma concentration of five patients with epilepsy in our hospital.

RESULTS

The model demonstrated favorable fitness metrics, including a mean squared error of 0.00662, a gradient magnitude of 0.00753, an absence of validation tests amounting to zero, and a correlation coefficient of 0.980. Sex, BMI, and the genotype SCN1A rs2298771 were ranked highest by the absolute mean impact value (MIV), which is primarily associated with the concentration of MHD. The test group exhibited a range of - 20.84% to 31.03% bias between the predicted and measured values, with a correlation coefficient of 0.941 between the two. With BPANN, the MHD nadir concentration could be predicted precisely.

CONCLUSION

The NGO-BPANN model exhibits exceptional predictive capability and can be a practical instrument for forecasting MHD concentration in patients with epilepsy.

CLINICAL TRIAL REGISTRATION

www.chiCTR-OOC-17012141 .

Comparison of simulation and predictive efficacy for hemorrhagic fever with renal syndrome incidence in mainland China based on five time series models

Background

Hemorrhagic fever with renal syndrome (HFRS) is a zoonotic infectious disease commonly found in Asia and Europe, characterized by fever, hemorrhage, shock, and renal failure. China is the most severely affected region, necessitating an analysis of the temporal incidence patterns in the country.

Methods

We employed Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Nonlinear AutoRegressive with eXogenous inputs (NARX), and a hybrid CNN-LSTM model to model and forecast time series data spanning from January 2009 to November 2023 in the mainland China. By comparing the simulated performance of these models on training and testing sets, we determined the most suitable model.

Results

Overall, the CNN-LSTM model demonstrated optimal fitting performance (with Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Error (MAE) of 93.77/270.66, 7.59%/38.96%, and 64.37/189.73 for the training and testing sets, respectively, lower than those of individual CNN or LSTM models).

Conclusion

The hybrid CNN-LSTM model seamlessly integrates CNN's data feature extraction and LSTM's recurrent prediction capabilities, rendering it theoretically applicable for simulating diverse distributed time series data. We recommend that the CNN-LSTM model be considered as a valuable time series analysis tool for disease prediction by policy-makers.

Interpretable classifiers for prediction of disability trajectories using a nationwide longitudinal database

OBJECTIVES

To explore the heterogeneous disability trajectories and construct explainable machine learning models for effective prediction of long-term disability trajectories and understanding the mechanisms of predictions among the elderly Chinese at community level.

METHODS

This study retrospectively collected data from the Chinese Longitudinal Healthy Longevity and Happy Family Study between 2002 and 2018. A total of 4149 subjects aged 65 + in 2002 with completed activities of daily living (ADL) information for at least three waves were included. The mixed growth model was used to identify disability trajectories, and five machine learning models were further established to predict disability trajectories using epidemiological variables. An explainable approach was deployed to understand the model's decisions.

RESULTS

Three distinct disability trajectories, including normal class (77.3%), progressive class (15.5%), and high-onset class (7.2%), were identified for three-class prediction. The latter two were further merged into abnormal class, accompanied by normal class for two-class prediction. Machine learning, especially random forest and extreme gradient boosting achieved good performance in both two tasks. ADL, age, leisure activity, cognitive function, and blood pressure were key predictors.

CONCLUSION

The findings suggest that machine learning showed good performance and maybe of additional value in analyzing quality indicators in predicting disability trajectories, thereby providing basis to personalize intervention measures.

A hybrid resampling algorithms SMOTE and ENN based deep learning models for identification of Marburg virus inhibitors

Background: Marburg virus (MARV) is a sporadic outbreak of a zoonotic disease that causes lethal hemorrhagic fever in humans. We propose a deep learning model with resampling techniques and predict the inhibitory activity of MARV from unknown compounds in the virtual screening process. Methodology & results: We applied resampling techniques to solve the imbalanced data problem. The classifier model comparisons revealed that the hybrid model of synthetic minority oversampling technique - edited nearest neighbor and artificial neural network (SMOTE-ENN + ANN) achieved better classification performance with 95% overall accuracy. The trained SMOTE-ENN+ANN hybrid model predicted as lead molecules; 25 out of 87,043 from ChemDiv, four out of 340 from ChEMBL anti-viral library, three out of 918 from Phytochemical database, and seven out of 419 from Natural products from NCI divsetIV, and 214 out of 1,12,267 from Natural compounds ZINC database for MARV. Conclusion: Our studies reveal that the proposed SMOTE-ENN + ANN hybrid model can improve overall accuracy more effectively and predict new lead molecules against MARV.

A comprehensive review of integrative pharmacology-based investigation: A paradigm shift in traditional Chinese medicine

Over the past decade, traditional Chinese medicine (TCM) has widely embraced systems biology and its various data integration approaches to promote its modernization. Thus, integrative pharmacology-based traditional Chinese medicine (TCMIP) was proposed as a paradigm shift in TCM. This review focuses on the presentation of this novel concept and the main research contents, methodologies and applications of TCMIP. First, TCMIP is an interdisciplinary science that can establish qualitative and quantitative pharmacokinetics-pharmacodynamics (PK-PD) correlations through the integration of knowledge from multiple disciplines and techniques and from different PK-PD processes in vivo. Then, the main research contents of TCMIP are introduced as follows: chemical and ADME/PK profiles of TCM formulas; confirming the three forms of active substances and the three action modes; establishing the qualitative PK-PD correlation; and building the quantitative PK-PD correlations, etc. After that, we summarize the existing data resources, computational models and experimental methods of TCMIP and highlight the urgent establishment of mathematical modeling and experimental methods. Finally, we further discuss the applications of TCMIP for the improvement of TCM quality control, clarification of the molecular mechanisms underlying the actions of TCMs and discovery of potential new drugs, especially TCM-related combination drug discovery.

Industry 4.0 for pharmaceutical manufacturing: Preparing for the smart factories of the future

Over the last two centuries, medicines have evolved from crude herbal and botanical preparations into more complex manufacturing of sophisticated drug products and dosage forms. Along with the evolution of medicines, the manufacturing practices for their production have advanced from small-scale manual processing with simple tools to large-scale production as part of a trillion-dollar pharmaceutical industry. Today's pharmaceutical manufacturing technologies continue to evolve as the internet of things, artificial intelligence, robotics, and advanced computing begin to challenge the traditional approaches, practices, and business models for the manufacture of pharmaceuticals. The application of these technologies has the potential to dramatically increase the agility, efficiency, flexibility, and quality of the industrial production of medicines. How these technologies are deployed on the journey from data collection to the hallmark digital maturity of Industry 4.0 will define the next generation of pharmaceutical manufacturing. Acheiving the benefits of this future requires a vision for it and an understanding of the extant regulatory, technical, and logistical barriers to realizing it.

Development of LC-MS/MS determination method and backpropagation artificial neural networks pharmacokinetic model of febuxostat in healthy subjects

WHAT IS KNOWN AND OBJECTIVE

Febuxostat is a well-known drug for treating hyperuricemia and gout. The published methods for determination of febuxostat in human plasma might be unsuitable for high-throughput determination and widespread application. We need to develop a highly selective, sensitive and rapid liquid chromatography-tandem mass spectrometry method.

METHODS

The chromatographic separation was achieved on a Hypersil Gold-C18 (2.1 mm × 100 mm, 1.9 μm) column with mobile phase A (Water containing 0.1% formic acid) and mobile phase B (acetonitrile containing 0.1% formic acid). Multiple reaction monitoring (MRM) mode was used for quantification using target ions at m/z 315.3 → m/z 271.3 for febuxostat and m/z 324.3 → m/z 280.3 for Febuxostat-d₉ (IS). A backpropagation artificial neural network (BPANN) pharmacokinetic model was constructed by the data of bioequivalence study.

RESULTS AND DISCUSSION

After the LC-MS/MS method validated, it was successfully applied to the bioequivalence study of 30 human volunteers under fed condition. The predicted concentrations generated by BPANN model had a high correlation coefficient with experimental values.

WHAT IS NEW AND CONCLUSION

A sensitive LC-MS/MS method had been developed and validated for determination of febuxostat in healthy subjects under fed condition, and a BPANN model was developed that can be used to predict the plasma concentration of febuxostat.

Pharmacokinetic-pharmacodynamic modeling for Moutan Cortex/Moutan Cortex charcoal and the contributions of the chemical component using support vector regression with particle swarm optimization

Moutan Cortex (MC) and Moutan Cortex charcoal (MCC) are two kinds of Chinese medicinal materials widely used in traditional Chinese medicine (TCM) with opposite drug efficacy. And the contributions of the chemical component to the drug efficacy are still not clear. In our study, a support vector regression (SVR) model with particle swarm optimization (PSO) has been developed for simultaneously characterizing the pharmacokinetics (PK) and pharmacodynamics (PD) of MC/MCC. Then the contributions of the chemical component to the drug efficacy of MC/MCC are calculated by the weight analysis of SVR. The experimental results show that the effective substances found by the PSO-SVR model in MC and MCC are consistent with TCM theory. And the PSO-SVR model is a better model for PK-PD compared with the back-propagation neural network (BPNN). In conclusion, the PSO-SVR is a valuable tool that linked PK and PD profiles of MC/MCC with multiple components and identified the contributions of multiple therapeutic materials to the drug efficacy.

Predicting the physiological response of Tivela stultorum hearts with digoxin from cardiac parameters using artificial neural networks

Multi-layer perceptron artificial neural networks (MLP-ANNs) were used to predict the concentration of digoxin needed to obtain a cardio-activity of specific biophysical parameters in Tivela stultorum hearts. The inputs of the neural networks were the minimum and maximum values of heart contraction force, the time of ventricular filling, the volume used for dilution, heart rate and weight, volume, length and width of the heart, while the output was the digoxin concentration in dilution necessary to obtain a desired physiological response. ANNs were trained, validated and tested with the dataset of the in vivo experiment results. To select the optimal network, predictions for all the dataset for each configuration of ANNs were made, a maximum 5% relative error for the digoxin concentration was set and the diagnostic accuracy of the predictions made was evaluated. The double-layer perceptron had a barely higher performance than the single-layer perceptron; therefore, both had a good predictive ability. The double-layer perceptron was able to obtain the most accurate predictions of digoxin concentration required in the hearts of T. stultorum using MLP-ANNs.

Effect of zishenpingchan granule on neurobehavioral manifestations and the activity and gene expression of striatal dopamine d1 and d2 receptors of rats with levodopa-induced dyskinesias

This study was performed to observe the effects of Zishenpingchan granule on neurobehavioral manifestations and the activity and gene expression of striatal dopamine D1 and D2 receptors of rats with levodopa-induced dyskinesias (LID). We established normal control group, LID model group, and TCM intervention group. Each group received treatment for 4 weeks. Artificial neural network (ANN) was applied to excavate the main factor influencing variation in neurobehavioral manifestations of rats with LID. The results showed that overactivation in direct pathway mediated by dopamine D1 receptor and overinhibition in indirect pathway mediated by dopamine D2 receptor may be the main mechanism of LID. TCM increased the efficacy time of LD to ameliorate LID symptoms effectively mainly by upregulating dopamine D2 receptor gene expression.

Dexamethasone-releasing cochlear implant coatings: application of artificial neural networks for modelling of formulation parameters and drug release profile

Objectives

Over the past few decades, mathematical modelling and simulation of drug delivery systems has been steadily gained interest as a focus for academic and industrial attention. Here, simulation of dexamethasone (DEX, a corticosteroid anti-inflammatory agent) release profile from drug-eluting cochlear implant coatings is reported using artificial neural networks.

Methods

The devices were fabricated as monolithic dispersions of the pharmaceutically active ingredient in a silicone rubber matrix. A two-phase exponential model was fitted on the experimentally obtained DEX release profiles. An artificial neural network (ANN) was trained to determine formulation parameters (i.e. DEX loading percentage, the devices surface area and their geometry) for a specific experimentally obtained drug release profile. In a reverse strategy, an ANN was trained for determining expected drug release profiles for the same set of formulation parameters.

Key findings

An algorithm was developed by combining the two previously developed ANNs in a serial manner, and this was successfully used for simulating the developed drug-eluting cochlear implant coatings. The models were validated by a leave-one-out method and performing new experiments.

Conclusions

The developed ANN algorithms were capable to bilaterally predict drug release profile for a known set of formulation parameters or find out the levels for input formulation parameters to obtain a desired DEX release profile.

Prediction of intracerebral hemorrhage following thrombolytic therapy for acute ischemic stroke using multiple artificial neural networks

OBJECTIVES

Artificial neural networks (ANNs) have been increasingly used in diagnosis and the prediction of outcome, mortality, and risk factors in ischemic stroke. Each model may have different accuracy, sensitivity, and specificity in processing the same clinical information. Thus, using only one model of ANNs may mislead the prediction. The present study aimed to predict symptomatic intracerebral hemorrhage (SICH) following thrombolysis in acute ischemic stroke based on clinical, laboratory, and imaging data using multiple ANN models.

METHODS

Models for radial basis function (RBF), multilayer perceptron (MLP), probabilistic neural network (PNN), and support vector machine (SVM) were generated to analyze 194 datasets with 29 predictive variables. The relative importance of each predictor variable was calculated using sensitivity analysis.

RESULTS

Comparison among the models based on the areas under the receiver operating characteristic curves (AUC) showed no significantly statistical difference in predictive performance among RBF, MLP, and PNN. PNN showed significantly better performance than SVM. With a minimum importance score of 50 together with an AUC value ≥0·50, three models identified stroke subtype as an important predictive variable for SICH. Other potential predictors were stroke location, prothrombin time, low-density-lipoprotein cholesterol, diastolic blood pressure, International Normalized Ratio, and brain computed tomography findings.

DISCUSSION

Although ANN models showed similar performance, the classification results were not totally alike, suggesting an advantage of using multiple classification models over a single model. The predictive results are supported by previous statistical studies on different datasets, suggesting generalizability of the utility of ANN analyses.

Prediction of effect of pegylated interferon alpha-2b plus ribavirin combination therapy in patients with chronic hepatitis C infection

Treatment with pegylated interferon alpha-2b (PEGIFN) plus ribavirin (RBV) is standard therapy for patients with chronic hepatitis C. Although the effectiveness, patients with high titres of group Ib hepatitis C virus (HCV) respond poorly compared to other genotypes. At present, we cannot predict the effect in an individual. Previous studies have used traditional statistical analysis by assuming a linear relationship between clinical features, but most phenomena in the clinical situation are not linearly related. The aim of this study is to predict the effect of PEG IFN plus RBV therapy on an individual patient level using an artificial neural network system (ANN). 156 patients with HCV group 1b from multiple centres were treated with PEGIFN (1.5 µg/kg) plus RBV (400–1000 mg) for 48 weeks. Data on the patients' demographics, laboratory tests, PEGIFN, and RBV doses, early viral responses (EVR), and sustained viral responses were collected. Clinical data were randomly divided into training data set and validation data set and analyzed using multiple logistic regression analysis (MLRs) and ANN to predict individual outcomes. The sensitivities of predictive expression were 0.45 for the MLRs models and 0.82 for the ANNs and specificities were 0.55 for the MLR and 0.88 for the ANN. Non-linear relation analysis showed that EVR, serum creatinine, initial dose of Ribavirin, gender and age were important predictive factors, suggesting non-linearly related to outcome. In conclusion, ANN was more accurate than MLRs in predicting the outcome of PEGIFN plus RBV therapy in patients with group 1b HCV.

Comparison between two PCR-based bacterial identification methods through artificial neural network data analysis

The 16S ribosomal ribonucleic acid (rRNA) and 16S-23S rRNA spacer region genes are commonly used as taxonomic and phylogenetic tools. In this study, two pairs of fluorescent-labeled primers for 16S rRNA genes and one pair of primers for 16S-23S rRNA spacer region genes were selected to amplify target sequences of 317 isolates from positive blood cultures. The polymerase chain reaction (PCR) products of both were then subjected to restriction fragment length polymorphism (RFLP) analysis by capillary electrophoresis after incomplete digestion by Hae III. For products of 16S rRNA genes, single-strand conformation polymorphism (SSCP) analysis was also performed directly. When the data were processed by artificial neural network (ANN), the accuracy of prediction based on 16S-23S rRNA spacer region gene RFLP data was much higher than that of prediction based on 16S rRNA gene SSCP analysis data (98.0% vs. 79.6%). This study proved that the utilization of ANN as a pattern recognition method was a valuable strategy to simplify bacterial identification when relatively complex data were encountered.

A bio-mathematical model of time prediction in corneal angiogenesis after alkali burn

BACKGROUND

The determination of angiogenesis time is the key prerequisite to obtaining a balance between valid repair and excessive angiogenesis in wound healing. The aim of the investigation was to establish a bio-mathematical model predicting corneal angiogenesis time after alkali burn by back propagation neural network (BP neural network).

METHODS

The corneas of mice in 24 groups were burned by 0.01 mol/l NaOH. Five mice in each group were sacrificed at 6h after alkali burn. The expression levels of vegf and tsp2, determined by real-time quantitive PCR, were used as input vectors in BP neural network. Meanwhile, the corneal angiogenesis of other mice, inspected every 3h in 24 groups till the angiogenesis time were determined, served as output vectors. The data of 18 groups were randomly chosen for network adaptation while that of other 6 groups for simulation forecasting with functions of minmax (), postreg, prepca, trapca, respectively.

RESULTS

A bio-mathematical model of two-level BP neural network was established, for its purpose to predict the angiogenesis time through the expression values of vegf and tsp2. The performance index (0.00999996) was smaller than the target value (0.01) after adapting 36,557 times and the accuracy rate of this predict system was 83.33%. Furthermore, the ideal regression line and the optimization regression line were almost coincident (R=0.988 in network adaptation and R=0.793 in simulation forecasting).

CONCLUSIONS

The investigation indicated that the bio-mathematical model had available performance of simulation and forecasting. It might provide a novel method to solve clinical problems.

Spline functions in convolutional modeling of verapamil bioavailability and bioequivalence. I: conceptual and numerical issues

A cubic spline function for describing the verapamil concentration profile, resulting from the verapamil absorption input to be evaluated, has been used. With this method, the knots are taken to be the data points, which has the advantage of being computationally less complex. Because of its inherently low algorhythmic errors, the spline method is less distorted and more suitable for further data analysis than others. The method has been evaluated using simulated verapamil delayed release tablet concentration data containing various degrees of random noise. The accuracy of the method was determined by how well the estimates of input rate and extent represented the true values. It was found that the accuracy of the method was of the same order of magnitude as the noise level of the data. Spline functions in convolutional modeling of verapamil formulation bioavailability and bioequivalence, as shown in the numerical simulation investigation, are very powerful additional tools for assessing the quality of new verapamil formulations in order to ensure that they are of the same quality as already registered formulations of the drug. The development of such models provides the possibility to avoid additional or larger bioequivalence and/or clinical trials and to thus help shorten the investigation time and registration period.

New Mathematical Methods in Pharmacokinetic Modeling

In recent years, several new methods for the mathematical modeling have gradually emerged in pharmacokinetics, and the development of pharmacokinetic models based on these methods has become one of the most rapidly growing and exciting application-oriented sub-disciplines of the mathematical modeling. The goals of our MiniReview are twofold: i) to briefly outline fundamental ideas of some new modeling methods that have not been widely utilized in pharmacokinetics as yet, i.e. the methods based on the following concepts: linear time-invariant dynamic system, artificial-neural-network, fuzzy-logic, and fractal; ii) to arouse the interest of pharmacological, toxicological, and pharmaceutical scientists in the given methods, by sketching some application examples which indicate the good performance and perspective of these methods in solving pharmacokinetic problems.

Artificial neural network modeling to predict the plasma concentration of aminoglycosides in burn patients

The goal was to use an artificial neural network model to predict the plasma concentration of aminoglycosides in burn patients and identify patients whose plasma antibiotic concentration would be sub-therapeutic based on the patients' physiological data and taking into account burn severity. Physiological data and some indicators of burn severity were collected from 30 burn patients who received arbekacin. A three-layer artificial neural network with five neurons in the hidden layer was used to predict the plasma concentration of arbekacin. Linear modeling for prediction of plasma concentration and logistic regression modeling for the classification of patients were also used and the predictive performance was compared to results from the artificial neural network model. Dose, body mass index, serum creatinine concentration and amount of parenteral fluid were selected as covariates for the plasma concentration of arbekacin. Area of burn after skin graft was a good covariate for indicating burn severity. Predictive performance of the artificial neural network model including burn severity was much better than linear modeling and logistic regression analysis. An artificial neural network model should be helpful for the prediction of plasma concentration using patients' physiological data, and burn severity should be included for improved prediction in burn patients. Because the relationship between burn severity and plasma concentration of aminoglycosides is thought to be nonlinear, it is not surprising that the artificial neural network model showed better predictive performance compared to the linear or logistic regression models.