Integrating Mechanistic and Toxicokinetic Information in Predictive Models of Cholestasis

Drug development involves the thorough assessment of the candidate's safety and efficacy. In silico toxicology (IST) methods can contribute to the assessment, complementing in vitro and in vivo experimental methods, since they have many advantages in terms of cost and time. Also, they are less demanding concerning the requirements of product and experimental animals. One of these methods, Quantitative Structure-Activity Relationships (QSAR), has been proven successful in predicting simple toxicity end points but has more difficulties in predicting end points involving more complex phenomena. We hypothesize that QSAR models can produce better predictions of these end points by combining multiple QSAR models describing simpler biological phenomena and incorporating pharmacokinetic (PK) information, using quantitative in vitro to in vivo extrapolation (QIVIVE) models. In this study, we applied our methodology to the prediction of cholestasis and compared it with direct QSAR models. Our results show a clear increase in sensitivity. The predictive quality of the models was further assessed to mimic realistic conditions where the query compounds show low similarity with the training series. Again, our methodology shows clear advantages over direct QSAR models in these situations. We conclude that the proposed methodology could improve existing methodologies and could be suitable for being applied to other toxicity end points.

A machine learning approach to identify groups of patients with hematological malignant disorders

BACKGROUND AND OBJECTIVE

Vaccination against SARS-CoV-2 in immunocompromised patients with hematologic malignancies (HM) is crucial to reduce the severity of COVID-19. Despite vaccination efforts, over a third of HM patients remain unresponsive, increasing their risk of severe breakthrough infections. This study aims to leverage machine learning's adaptability to COVID-19 dynamics, efficiently selecting patient-specific features to enhance predictions and improve healthcare strategies. Highlighting the complex COVID-hematology connection, the focus is on interpretable machine learning to provide valuable insights to clinicians and biologists.

METHODS

The study evaluated a dataset with 1166 patients with hematological diseases. The output was the achievement or non-achievement of a serological response after full COVID-19 vaccination. Various machine learning methods were applied, with the best model selected based on metrics such as the Area Under the Curve (AUC), Sensitivity, Specificity, and Matthew Correlation Coefficient (MCC). Individual SHAP values were obtained for the best model, and Principal Component Analysis (PCA) was applied to these values. The patient profiles were then analyzed within identified clusters.

RESULTS

Support vector machine (SVM) emerged as the best-performing model. PCA applied to SVM-derived SHAP values resulted in four perfectly separated clusters. These clusters are characterized by the proportion of patients that generate antibodies (PPGA). Cluster 1, with the second-highest PPGA (69.91%), included patients with aggressive diseases and factors contributing to increased immunodeficiency. Cluster 2 had the lowest PPGA (33.3%), but the small sample size limited conclusive findings. Cluster 3, representing the majority of the population, exhibited a high rate of antibody generation (84.39%) and a better prognosis compared to cluster 1. Cluster 4, with a PPGA of 66.33%, included patients with B-cell non-Hodgkin's lymphoma on corticosteroid therapy.

CONCLUSIONS

The methodology successfully identified four separate patient clusters using Machine Learning and Explainable AI (XAI). We then analyzed each cluster based on the percentage of HM patients who generated antibodies after COVID-19 vaccination. The study suggests the methodology's potential applicability to other diseases, highlighting the importance of interpretable ML in healthcare research and decision-making.

Usage of model combination in computational toxicology

New Approach Methodologies (NAMs) have ushered in a new era in the field of toxicology, aiming to replace animal testing. However, despite these advancements, they are not exempt from the inherent complexities associated with the study's endpoint. In this review, we have identified three major groups of complexities: mechanistic, chemical space, and methodological. The mechanistic complexity arises from interconnected biological processes within a network that are challenging to model in a single step. In the second group, chemical space complexity exhibits significant dissimilarity between compounds in the training and test series. The third group encompasses algorithmic and molecular descriptor limitations and typical class imbalance problems. To address these complexities, this work provides a guide to the usage of a combination of predictive Quantitative Structure-Activity Relationship (QSAR) models, known as metamodels. This combination of low-level models (LLMs) enables a more precise approach to the problem by focusing on different sub-mechanisms or sub-processes. For mechanistic complexity, multiple Molecular Initiating Events (MIEs) or levels of information are combined to form a mechanistic-based metamodel. Regarding the complexity arising from chemical space, two types of approaches were reviewed to construct a fragment-based chemical space metamodel: those with and without structure sharing. Metamodels with structure sharing utilize unsupervised strategies to identify data patterns and build low-level models for each cluster, which are then combined. For situations without structure sharing due to pharmaceutical industry intellectual property, the use of prediction sharing, and federated learning approaches have been reviewed. Lastly, to tackle methodological complexity, various algorithms are combined to overcome their limitations, diverse descriptors are employed to enhance problem definition and balanced dataset combinations are used to address class imbalance issues (methodological-based metamodels). Remarkably, metamodels consistently outperformed classical QSAR models across all cases, highlighting the importance of alternatives to classical QSAR models when faced with such complexities.

Exploring the Heterogeneity and Trajectories of Positive Functioning Variables, Emotional Distress, and Post-traumatic Growth During Strict Confinement Due to COVID-19

COVID-19 pandemic-related confinement may be a fruitful opportunity to use individual resources to deal with it or experience psychological functioning changes. This study aimed to analyze the evolution of different psychological variables during the first coronavirus wave to identify the different psychological response clusters, as well as to keep a follow-up on the changes among these clusters. The sample included 459 Spanish residents (77.8% female, M_age = 35.21 years, SD_age = 13.00). Participants completed several online self-reported questionnaires to assess positive functioning variables (MLQ, Steger et al. in J Loss Trauma 13(6):511-527, 2006. 10.1080/15325020802173660; GQ-6, McCullough et al. in J Person Soc Psychol 82:112-127, 2002. 10.1037/0022-3514.82.1.112; CD-RISC, Campbell-Sills and Stein in J Traum Stress 20(6):1019-1028, 2007. 10.1002/jts.20271; CLS-H, Chiesi et al. in BMC Psychol 8(1):1-9, 2020. 10.1186/s40359-020-0386-9; SWLS; Diener et al. in J Person Assess, 49(1), 71-75, 1985), emotional distress (PHQ-2, Kroenke et al. in Med Care 41(11):1284-1292, 2003. 10.1097/01.MLR.0000093487.78664.3C; GAD-2, Kroenke et al. in Ann Internal Med 146(5):317-325, 2007. 10.7326/0003-4819-146-5-200703060-00004; PANAS, Watson et al. in J Person Soc Psychol 47:1063-1070, 1988; Perceived Stress, ad hoc), and post-traumatic growth (PTGI-SF; Cann et al. in Anxiety Stress Coping 23(2):127-137, 2010. 10.1080/10615800903094273), four times throughout the 3 months of the confinement. Linear mixed models showed that the scores on positive functioning variables worsened from the beginning of the confinement, while emotional distress and personal strength improved by the end of the state of alarm. Clustering analyses revealed four different patterns of psychological response: "Survival", "Resurgent", "Resilient", and "Thriving" individuals. Four different profiles were identified during mandatory confinement and most participants remained in the same cluster. The "Resilient" cluster gathered the largest number of individuals (30-37%). We conclude that both the heterogeneity of psychological profiles and analysis of positive functioning variables, emotional distress, and post-traumatic growth must be considered to better understand the response to prolonged adverse situations.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s10902-021-00469-z.

Machine Learning for Mortality Analysis in Patients with COVID-19

This paper analyzes a sample of patients hospitalized with COVID-19 in the region of Madrid (Spain). Survival analysis, logistic regression, and machine learning techniques (both supervised and unsupervised) are applied to carry out the analysis where the endpoint variable is the reason for hospital discharge (home or deceased). The different methods applied show the importance of variables such as age, O2 saturation at Emergency Rooms (ER), and whether the patient comes from a nursing home. In addition, biclustering is used to globally analyze the patient-drug dataset, extracting segments of patients. We highlight the validity of the classifiers developed to predict the mortality, reaching an appreciable accuracy. Finally, interpretable decision rules for estimating the risk of mortality of patients can be obtained from the decision tree, which can be crucial in the prioritization of medical care and resources.

Physical Activity Monitoring and Acceptance of a Commercial Activity Tracker in Adult Patients with Haemophilia

Physical activity (PA) is highly beneficial for people with haemophilia (PWH), however, studies that objectively monitor the PA in this population are scarce. This study aimed to monitor the daily PA and analyse its evolution over time in a cohort of PWH using a commercial activity tracker. In addition, this work analyses the relationship between PA levels, demographics, and joint health status, as well as the acceptance and adherence to the activity tracker. Twenty-six PWH were asked to wear a Fitbit Charge HR for 13 weeks. According to the steps/day in the first week, data were divided into two groups: Active Group (AG; ≥10,000 steps/day) and Non-Active Group (NAG; <10,000 steps/day). Correlations between PA and patient characteristics were studied using the Pearson coefficient. Participants' user experience was analysed with a questionnaire. The 10,000 steps/day was reached by 57.7% of participants, with 12,603 (1525) and 7495 (1626) being the mean steps/day of the AG and NAG, respectively. In general, no significant variations (p > 0.05) in PA levels or adherence to wristband were produced. Only the correlation between very active minutes and arthropathy was significant (r = -0.40, p = 0.045). Results of the questionnaire showed a high level of satisfaction. In summary, PWH are able to comply with the PA recommendations, and the Fitbit wristband is a valid tool for a continuous and long-term monitoring of PA. However, by itself, the use of a wristband is not enough motivation to increase PA levels.

HemoKinect: A Microsoft Kinect V2 Based Exergaming Software to Supervise Physical Exercise of Patients with Hemophilia

Patients with hemophilia need to strictly follow exercise routines to minimize their risk of suffering bleeding in joints, known as hemarthrosis. This paper introduces and validates a new exergaming software tool called HemoKinect that intends to keep track of exercises using Microsoft Kinect V2's body tracking capabilities. The software has been developed in C++ and MATLAB. The Kinect SDK V2.0 libraries have been used to obtain 3D joint positions from the Kinect color and depth sensors. Performing angle calculations and center-of-mass (COM) estimations using these joint positions, HemoKinect can evaluate the following exercises: elbow flexion/extension, knee flexion/extension (squat), step climb (ankle exercise) and multi-directional balance based on COM. The software generates reports and progress graphs and is able to directly send the results to the physician via email. Exercises have been validated with 10 controls and eight patients. HemoKinect successfully registered elbow and knee exercises, while displaying real-time joint angle measurements. Additionally, steps were successfully counted in up to 78% of the cases. Regarding balance, differences were found in the scores according to the difficulty level and direction. HemoKinect supposes a significant leap forward in terms of exergaming applicability to rehabilitation of patients with hemophilia, allowing remote supervision.

ELM Regularized Method for Classification Problems

Extreme Learning Machine (ELM) is a recently proposed algorithm, efficient and fast for learning the parameters of single layer neural structures. One of the main problems of this algorithm is to choose the optimal architecture for a given problem solution. To solve this limitation several solutions have been proposed in the literature, including the regularization of the structure. However, to the best of our knowledge, there are no works where such adjustment is applied to classification problems in the presence of a non-linearity in the output; all published works tackle modelling or regression problems. Our proposal has been applied to a series of standard databases for the evaluation of machine learning techniques. Results obtained in terms of classification success rate and training time, are compared to the original ELM, to the well known Least Square Support Vector Machine (LS-SVM) algorithm and with two other methods based on the ELM regularization: Optimally Pruned Extreme Learning Machine (OP-ELM) and Bayesian Extreme Learning Machine (BELM). The obtained results clearly demonstrate the usefulness of the proposed method and its superiority over a classical approach.

Support vector machine classification of brain metastasis and radiation necrosis based on texture analysis in MRI

PURPOSE

To develop a classification model using texture features and support vector machine in contrast-enhanced T1-weighted images to differentiate between brain metastasis and radiation necrosis.

METHODS

Texture features were extracted from 115 lesions: 32 of them previously diagnosed as radiation necrosis, 23 as radiation-treated metastasis and 60 untreated metastases; including a total of 179 features derived from six texture analysis methods. A feature selection technique based on support vector machine was used to obtain a subset of features that provide optimal performance.

RESULTS

The highest classification accuracy evaluated over test sets was achieved with a subset of ten features when the untreated metastases were not considered; and with a subset of seven features when the classifier was trained with untreated metastases and tested on treated ones. Receiver operating characteristic curves provided area-under-the-curve (mean ± standard deviation) of 0.94 ± 0.07 in the first case, and 0.93 ± 0.02 in the second.

CONCLUSION

High classification accuracy (AUC > 0.9) was obtained using texture features and a support vector machine classifier in an approach based on conventional MRI to differentiate between brain metastasis and radiation necrosis.

Prediction of the hemoglobin level in hemodialysis patients using machine learning techniques

Patients who suffer from chronic renal failure (CRF) tend to suffer from an associated anemia as well. Therefore, it is essential to know the hemoglobin (Hb) levels in these patients. The aim of this paper is to predict the hemoglobin (Hb) value using a database of European hemodialysis patients provided by Fresenius Medical Care (FMC) for improving the treatment of this kind of patients. For the prediction of Hb, both analytical measurements and medication dosage of patients suffering from chronic renal failure (CRF) are used. Two kinds of models were trained, global and local models. In the case of local models, clustering techniques based on hierarchical approaches and the adaptive resonance theory (ART) were used as a first step, and then, a different predictor was used for each obtained cluster. Different global models have been applied to the dataset such as Linear Models, Artificial Neural Networks (ANNs), Support Vector Machines (SVM) and Regression Trees among others. Also a relevance analysis has been carried out for each predictor model, thus finding those features that are most relevant for the given prediction.

Optimization of anemia treatment in hemodialysis patients via reinforcement learning

OBJECTIVE

Anemia is a frequent comorbidity in hemodialysis patients that can be successfully treated by administering erythropoiesis-stimulating agents (ESAs). ESAs dosing is currently based on clinical protocols that often do not account for the high inter- and intra-individual variability in the patient's response. As a result, the hemoglobin level of some patients oscillates around the target range, which is associated with multiple risks and side-effects. This work proposes a methodology based on reinforcement learning (RL) to optimize ESA therapy.

METHODS

RL is a data-driven approach for solving sequential decision-making problems that are formulated as Markov decision processes (MDPs). Computing optimal drug administration strategies for chronic diseases is a sequential decision-making problem in which the goal is to find the best sequence of drug doses. MDPs are particularly suitable for modeling these problems due to their ability to capture the uncertainty associated with the outcome of the treatment and the stochastic nature of the underlying process. The RL algorithm employed in the proposed methodology is fitted Q iteration, which stands out for its ability to make an efficient use of data.

RESULTS

The experiments reported here are based on a computational model that describes the effect of ESAs on the hemoglobin level. The performance of the proposed method is evaluated and compared with the well-known Q-learning algorithm and with a standard protocol. Simulation results show that the performance of Q-learning is substantially lower than FQI and the protocol. When comparing FQI and the protocol, FQI achieves an increment of 27.6% in the proportion of patients that are within the targeted range of hemoglobin during the period of treatment. In addition, the quantity of drug needed is reduced by 5.13%, which indicates a more efficient use of ESAs.

CONCLUSION

Although prospective validation is required, promising results demonstrate the potential of RL to become an alternative to current protocols.

Visual data mining with self-organising maps for ventricular fibrillation analysis

Detection of ventricular fibrillation (VF) at an early stage is being deeply studied in order to lower the risk of sudden death and allows the specialist to have greater reaction time to give the patient a good recovering therapy. Some works are focusing on detecting VF based on numerical analysis of time-frequency distributions, but in general the methods used do not provide insight into the problem. However, this study proposes a new methodology in order to obtain information about this problem. This work uses a supervised self-organising map (SOM) to obtain visually information among four important groups of patients: VF (ventricular fibrillation), VT (ventricular tachycardia), HP (healthy patients) and AHR (other anomalous heart rates and noise). A total number of 27 variables were obtained from continuous surface ECG recordings in standard databases (MIT and AHA), providing information in the time, frequency, and time-frequency domains. self-organising maps (SOMs), trained with 11 of the 27 variables, were used to extract knowledge about the variable values for each group of patients. Results show that the SOM technique allows to determine the profile of each group of patients, assisting in gaining a deeper understanding of this clinical problem. Additionally, information about the most relevant variables is given by the SOM analysis.

BELM: Bayesian extreme learning machine

The theory of extreme learning machine (ELM) has become very popular on the last few years. ELM is a new approach for learning the parameters of the hidden layers of a multilayer neural network (as the multilayer perceptron or the radial basis function neural network). Its main advantage is the lower computational cost, which is especially relevant when dealing with many patterns defined in a high-dimensional space. This brief proposes a bayesian approach to ELM, which presents some advantages over other approaches: it allows the introduction of a priori knowledge; obtains the confidence intervals (CIs) without the need of applying methods that are computationally intensive, e.g., bootstrap; and presents high generalization capabilities. Bayesian ELM is benchmarked against classical ELM in several artificial and real datasets that are widely used for the evaluation of machine learning algorithms. Achieved results show that the proposed approach produces a competitive accuracy with some additional advantages, namely, automatic production of CIs, reduction of probability of model overfitting, and use of a priori knowledge.

Upport vector machines for nonlinear kernel ARMA system identification

Nonlinear system identification based on support vector machines (SVM) has been usually addressed by means of the standard SVM regression (SVR), which can be seen as an implicit nonlinear autoregressive and moving average (ARMA) model in some reproducing kernel Hilbert space (RKHS). The proposal of this letter is twofold. First, the explicit consideration of an ARMA model in an RKHS (SVM-ARMA2K) is proposed. We show that stating the ARMA equations in an RKHS leads to solving the regularized normal equations in that RKHS, in terms of the autocorrelation and cross correlation of the (nonlinearly) transformed input and output discrete time processes. Second, a general class of SVM-based system identification nonlinear models is presented, based on the use of composite Mercer's kernels. This general class can improve model flexibility by emphasizing the input-output cross information (SVM-ARMA4K), which leads to straightforward and natural combinations of implicit and explicit ARMA models (SVR-ARMA2K and SVR-ARMA4K). Capabilities of these different SVM-based system identification schemes are illustrated with two benchmark problems.

Foetal ECG recovery using dynamic neural networks

Non-invasive electrocardiography has proven to be a very interesting method for obtaining information about the foetus state and thus to assure its well-being during pregnancy. One of the main applications in this field is foetal electrocardiogram (ECG) recovery by means of automatic methods. Evident problems found in the literature are the limited number of available registers, the lack of performance indicators, and the limited use of non-linear adaptive methods. In order to circumvent these problems, we first introduce the generation of synthetic registers and discuss the influence of different kinds of noise to the modelling. Second, a method which is based on numerical (correlation coefficient) and statistical (analysis of variance, ANOVA) measures allows us to select the best recovery model. Finally, finite impulse response (FIR) and gamma neural networks are included in the adaptive noise cancellation (ANC) scheme in order to provide highly non-linear, dynamic capabilities to the recovery model. Neural networks are benchmarked with classical adaptive methods such as the least mean squares (LMS) and the normalized LMS (NLMS) algorithms in simulated and real registers and some conclusions are drawn. For synthetic registers, the most determinant factor in the identification of the models is the foetal-maternal signal-to-noise ratio (SNR). In addition, as the electromyogram contribution becomes more relevant, neural networks clearly outperform the LMS-based algorithm. From the ANOVA test, we found statistical differences between LMS-based models and neural models when complex situations (high foetal-maternal and foetal-noise SNRs) were present. These conclusions were confirmed after doing robustness tests on synthetic registers, visual inspection of the recovered signals and calculation of the recognition rates of foetal R-peaks for real situations. Finally, the best compromise between model complexity and outcomes was provided by the FIR neural network. Both the methodology for selecting a model and the introduction of advanced neural models are the main contributions of this paper.

Dosage individualization of erythropoietin using a profile-dependent support vector regression

The external administration of recombinant human erythropoietin is the chosen treatment for those patients with secondary anemia due to chronic renal failure in periodic hemodialysis. The objective of this paper is to carry out an individualized prediction of the EPO dosage to be administered to those patients. The high cost of this medication, its side-effects and the phenomenon of potential resistance which some individuals suffer all justify the need for a model which is capable of optimizing dosage individualization. A group of 110 patients and several patient factors were used to develop the models. The support vector regressor (SVR) is benchmarked with the classical multilayer perceptron (MLP) and the Autoregressive Conditional Heteroskedasticity (ARCH) model. We introduce a priori knowledge by relaxing or tightening the epsilon-insensitive region and the penalization parameter depending on the time period of the patients' follow-up. The so-called profile-dependent SVR (PD-SVR) improves results of the standard SVR method and the MLP. We perform sensitivity analysis on the MLP and inspect the distribution of the support vectors in the input and feature spaces in order to gain knowledge about the problem.

Prediction of cyclosporine dosage in patients after kidney transplantation using neural networks

This paper proposes the use of neural networks for individualizing the dosage of cyclosporine A (CyA) in patients who have undergone kidney transplantation. Since the dosing of CyA usually requires intensive therapeutic drug monitoring, the accurate prediction of CyA blood concentrations would decrease the monitoring frequency and, thus, improve clinical outcomes. Thirty-two patients and different factors were studied to obtain the models. Three kinds of networks (multilayer perceptron, finite impulse response (FIR) network, and Elman recurrent network) and the formation of neural-network ensembles are used in a scheme of two chained models where the blood concentration predicted by the first model constitutes an input to the dosage prediction model. This approach is designed to aid in the process of clinical decision making. The FIR network, yielding root-mean-square errors (RMSEs) of 52.80 ng/mL and mean errors (MEs) of 0.18 ng/mL in validation (10 patients) showed the best blood concentration predictions and a committee of trained networks improved the results (RMSE = 46.97 ng/mL, ME = 0.091 ng/mL). The Elman network was the selected model for dosage prediction (RMSE = 0.27 mg/Kg/d, ME = 0.07 mg/Kg/d). However, in both cases, no statistical differences on the accuracy of neural methods were found. The models' robustness is also analyzed by evaluating their performance when noise is introduced at input nodes, and it results in a helpful test for models' selection. We conclude that neural networks can be used to predict both dose and blood concentrations of cyclosporine in steady-state. This novel approach has produced accurate and validated models to be used as decision-aid tools.

Application of adaptive signal processing for determining the limits of P and T waves in an ECG

A new algorithm for the determination of the limits of P and T waves is proposed, and its foundations are mathematically analyzed. The algorithm performs an adaptive filtering so that the searched point corresponds to a minimum. Crucial properties of its performance are discussed, i.e., immunity to base line drifts and full adaptation to any cardiological criteria. A series of tests are made involving real registers with different morphologies for P and T-waves.