Comparison of multivariate linear regression and a machine learning algorithm developed for prediction of precision warfarin dosing in a Korean population

Warfarin-A natural anticoagulant: A review of research trends for precision medication

BACKGROUND

Warfarin is a widely prescribed anticoagulant in the clinic. It has a more considerable individual variability, and many factors affect its variability. Mathematical models can quantify the quantitative impact of these factors on individual variability.

PURPOSE

The aim is to comprehensively analyze the advanced warfarin dosing algorithm based on pharmacometrics and machine learning models of personalized warfarin dosage.

METHODS

A bibliometric analysis of the literature retrieved from PubMed and Scopus was performed using VOSviewer. The relevant literature that reported the precise dosage of warfarin calculation was retrieved from the database. The multiple linear regression (MLR) algorithm was excluded because a recent systematic review that mainly reviewed this algorithm has been reported. The following terms of quantitative systems pharmacology, mechanistic model, physiologically based pharmacokinetic model, artificial intelligence, machine learning, pharmacokinetic, pharmacodynamic, pharmacokinetics, pharmacodynamics, and warfarin were added as MeSH Terms or appearing in Title/Abstract into query box of PubMed, then humans and English as filter were added to retrieve the literature.

RESULTS

Bibliometric analysis revealed important co-occuring MeShH and index keywords. Further, the United States, China, and the United Kingdom were among the top countries contributing in this domain. Some studies have established personalized warfarin dosage models using pharmacometrics and machine learning-based algorithms. There were 54 related studies, including 14 pharmacometric models, 31 artificial intelligence models, and 9 model evaluations. Each model has its advantages and disadvantages. The pharmacometric model contains biological or pharmacological mechanisms in structure. The process of pharmacometric model development is very time- and labor-intensive. Machine learning is a purely data-driven approach; its parameters are more mathematical and have less biological interpretation. However, it is faster, more efficient, and less time-consuming. Most published models of machine learning algorithms were established based on cross-sectional data sourced from the database.

CONCLUSION

Future research on personalized warfarin medication should focus on combining the advantages of machine learning and pharmacometrics algorithms to establish a more robust warfarin dosage algorithm. Randomized controlled trials should be performed to evaluate the established algorithm of warfarin dosage. Moreover, a more user-friendly and accessible warfarin precision medicine platform should be developed.

Optimizing warfarin dosing for patients with atrial fibrillation using machine learning

While novel oral anticoagulants are increasingly used to reduce risk of stroke in patients with atrial fibrillation, vitamin K antagonists such as warfarin continue to be used extensively for stroke prevention across the world. While effective in reducing the risk of strokes, the complex pharmacodynamics of warfarin make it difficult to use clinically, with many patients experiencing under- and/or over- anticoagulation. In this study we employed a novel implementation of deep reinforcement learning to provide clinical decision support to optimize time in therapeutic International Normalized Ratio (INR) range. We used a novel semi-Markov decision process formulation of the Batch-Constrained deep Q-learning algorithm to develop a reinforcement learning model to dynamically recommend optimal warfarin dosing to achieve INR of 2.0-3.0 for patients with atrial fibrillation. The model was developed using data from 22,502 patients in the warfarin treated groups of the pivotal randomized clinical trials of edoxaban (ENGAGE AF-TIMI 48), apixaban (ARISTOTLE) and rivaroxaban (ROCKET AF). The model was externally validated on data from 5730 warfarin-treated patients in a fourth trial of dabigatran (RE-LY) using multilevel regression models to estimate the relationship between center-level algorithm consistent dosing, time in therapeutic INR range (TTR), and a composite clinical outcome of stroke, systemic embolism or major hemorrhage. External validation showed a positive association between center-level algorithm-consistent dosing and TTR (R2 = 0.56). Each 10% increase in algorithm-consistent dosing at the center level independently predicted a 6.78% improvement in TTR (95% CI 6.29, 7.28; p < 0.001) and a 11% decrease in the composite clinical outcome (HR 0.89; 95% CI 0.81, 1.00; p = 0.015). These results were comparable to those of a rules-based clinical algorithm used for benchmarking, for which each 10% increase in algorithm-consistent dosing independently predicted a 6.10% increase in TTR (95% CI 5.67, 6.54, p < 0.001) and a 10% decrease in the composite outcome (HR 0.90; 95% CI 0.83, 0.98, p = 0.018). Our findings suggest that a deep reinforcement learning algorithm can optimize time in therapeutic range for patients taking warfarin. A digital clinical decision support system to promote algorithm-consistent warfarin dosing could optimize time in therapeutic range and improve clinical outcomes in atrial fibrillation globally.

Improved stacking ensemble learning based on feature selection to accurately predict warfarin dose

Background

With the rapid development of artificial intelligence, prediction of warfarin dose via machine learning has received more and more attention. Since the dose prediction involve both linear and nonlinear problems, traditional machine learning algorithms are ineffective to solve such problems at one time.

Objective

Based on the characteristics of clinical data of Chinese warfarin patients, an improved stacking ensemble learning can achieve higher prediction accuracy.

Methods

Information of 641 patients from southern China who had reached a steady state on warfarin was collected, including demographic information, medical history, genotype, and co-medication status. The dataset was randomly divided into a training set (90%) and a test set (10%). The predictive capability is evaluated on a new test set generated by stacking ensemble learning. Additional factors associated with warfarin dose were discovered by feature selection methods.

Results

A newly proposed heuristic-stacking ensemble learning performs better than traditional-stacking ensemble learning in key metrics such as accuracy of ideal dose (73.44%, 71.88%), mean absolute errors (0.11 mg/day, 0.13 mg/day), root mean square errors (0.18 mg/day, 0.20 mg/day) and R2 (0.87, 0.82).

Conclusions

The developed heuristic-stacking ensemble learning can satisfactorily predict warfarin dose with high accuracy. A relationship between hypertension, a history of severe preoperative embolism, and warfarin dose is found, which provides a useful reference for the warfarin dose administration in the future.

Machine learning model for predicting physical activity related bleeding risk in Chinese boys with haemophilia A

BACKGROUND

Physical activity is a crucial part of an active lifestyle for haemophiliac children. However, the fear of bleeds has been identified as barriers to participating physical activity for haemophiliac children even with prophylaxis. Lack of evidence and metrics driven by data is key problem.

OBJECTIVES

We aim to develop machine learning models based on clinical data with multiple potential factors considered to predict risk of physical activity bleeding for haemophilia children with prophylaxis.

METHODS

From this cohort study, we collected information on 98 haemophiliac children with adequate prophylaxis (trough FVIII:C level > 1 %). The involved potential predictor variables include demographic information, treatment information, physical activity, joint evaluation, and pharmacokinetic parameters, etc. We applied CoxPH, Random Survival Forests (RSF) and DeepSurv to construct prediction models for the risk of bleeding during physical activities. All three survival analysis models were internally and externally validated.

RESULTS

A total of 98 patients were enrolled in this study. Their median age was 7.9 (5.5, 10.2) years. The CoxPH, RSF and DeepSurv models' discriminative and calibration abilities were all high, and the RSF model had the best performance (Internal validation: C-index, 0.7648 ± 0.0139; Brier Score, 0.1098 ± 0.0015; External validation: C-index, 0.7260 ± 0.0154; Brier Score, 0.0930 ± 0.0018). The prediction curves demonstrated that the developed RSF model can distinguish the risks well between bleeding and non-bleeding patients, as well as patients with different levels of physical activity. Meanwhile, the feature importance analysis confirmed that physical activity bleeding was deduced by comprehensive effects of various factors, and the importance of different factors on bleeding outcome is discrepant.

CONCLUSIONS

This study revealed from the mechanism that it is necessary to incorporate multiple factors to accurately predict physical activity related bleeding risk. In clinical practice, the designed machine learning models can provide guidance for children with haemophilia A to positively participate in physical activity.

Field evaluation of semi-automated moisture estimation from geophysics using machine learning

Geophysical methods can provide three-dimensional (3D), spatially continuous estimates of soil moisture. However, point-to-point comparisons of geophysical properties to measure soil moisture data are frequently unsatisfactory, resulting in geophysics being used for qualitative purposes only. This is because (1) geophysics requires models that relate geophysical signals to soil moisture, (2) geophysical methods have potential uncertainties resulting from smoothing and artifacts introduced from processing and inversion, and (3) results from multiple geophysical methods are not easily combined within a single soil moisture estimation framework. To investigate these potential limitations, an irrigation experiment was performed wherein soil moisture was monitored through time, and several surface geophysical datasets indirectly sensitive to soil moisture were collected before and after irrigation: ground penetrating radar, electrical resistivity tomography (ERT), and frequency domain electromagnetics (FDEM). Data were exported in both raw and processed form, and then snapped to a common 3D grid to facilitate moisture prediction by standard calibration techniques, multivariate regression, and machine learning. A combination of inverted ERT data, raw FDEM, and inverted FDEM data was most informative for predicting soil moisture using a random regression forest model (one-thousand 60/40 training/test cross-validation folds produced root mean squared errors ranging from 0.025-0.046 cm3/cm3). This cross-validated model was further supported by a separate evaluation using a test set from a physically separate portion of the study area. Machine learning was conducive to a semi-automated model-selection process that could be used for other sites and datasets to locally improve accuracy.

Evaluation of supervised machine learning algorithms in predicting the poor anticoagulation control and stable weekly doses of warfarin

BACKGROUND

Machine learning algorithms (MLAs) carry a huge potential in identifying predicting factors and are being explored for their utility in the field of personalized medicine.

AIM

We aimed to investigate MLAs for identifying predictors (clinical and genetic) of poor anticoagulation status (ACS) and stable weekly warfarin dose (SWWD).

METHOD

Clinical factors, in addition to the CYP2C9, VKORC1, and CYP4F2 genotypes, were obtained for patients receiving warfarin for at least the previous six months. The C5.0 decision tree classification algorithm was used to predict poor ACS while classification and regression tree analysis (CART), in addition to the Chi-square automatic interaction detector (CHAID), was used to predict SWWD. The percentage of patients within 20% of the actual dose, root mean squared error (RMSE), and area under the receiver-operating characteristics curve (AUROC) were identified as performance indicators of the models.

RESULTS

In the C5.0 classification decision tree, the CYP4F2 genotype was the strongest predictor of ACS (AUROC = 0.53). In the CART analysis of SWWD, VKORC1 polymorphisms were the most significant predictor, followed by the CYP2C9 genotype (percentage of patients within 20% of the actual dose = 38.2%, RMSE = 13.6). For the CHAID algorithm, the percentage of patients within 20% of the actual dose was 49%, while the RMSE was found to be 13.4.

CONCLUSION

Genetic and non-genetic predictive factors were identified by the MLAs for ACS and SWWD. Further, the need to externally validate the MLAs in a prospective study was highlighted.

Automated warfarin dose prediction for Asian, American, and Caucasian populations using a deep neural network

Existing warfarin dose prediction algorithms based on pharmacogenetics and clinical parameters have not been used clinically due to the absence of external validation, lack of assessment for clinical utility, and high risk of bias. Moreover, given the high degree of heterogeneity across different datasets used to develop these algorithms, it is unsurprising that prediction errors remain high, and dosing accuracy is dependent on specific ethnic populations. To circumvent these challenges, deep neural models are increasingly used to improve the precision and accuracy of warfarin dose predictions. Hence, this study sought to develop a deep learning-based model using a well-established curated dataset of over 6000 patients from the International Warfarin Pharmacogenomics Consortium (IWPC). Clinically-relevant input data such as physical attributes, medical conditions, concomitant medications, genotype status of functional warfarin genetic polymorphisms, and therapeutic INR were entered followed by applying a unique and robust training and validation method. The deep model yielded a low average mean absolute error (MAE) of 7.6 mg/week and a relatively low mean percentage of error of 40.9% in Asians, 14.2 mg/week MAE and 36.9% in African Americans, and 12.7 mg/week MAE and 45.4% mean percentage of error in White Caucasians. This model also resulted in 36.4% of all patients with a predicted dose within 20% of the administered dose. Hence, our proposed deep model provides an alternative to predicting warfarin dose in the clinical setting upon validation in ethnically-similar datasets.

Building and analyzing machine learning-based warfarin dose prediction models using scikit-learn

For personalized drug dosing, prediction models may be utilized to overcome the inter-individual variability. Multiple linear regression has been used as a conventional method to model the relationship between patient features and optimal drug dose. However, linear regression cannot capture non-linear relationships and may be adversely affected by non-normal distribution and collinearity of data. To overcome this hurdle, machine learning models have been extensively adapted in drug dose prediction. In this tutorial, random forest and neural network models will be trained in tandem with a multiple linear regression model on the International Warfarin Pharmacogenetics Consortium dataset using the scikit-learn python library. Subsequent model analyses including performance comparison, permutation feature importance computation and partial dependence plotting will be demonstrated. The basic methods of model training and analysis discussed in this article may be implemented in drug dose-related studies.

A rapid, non-invasive method for fatigue detection based on voice information

Fatigue results from a series of physiological and psychological changes due to continuous energy consumption. It can affect the physiological states of operators, thereby reducing their labor capacity. Fatigue can also reduce efficiency and, in serious cases, cause severe accidents. In addition, it can trigger pathological-related changes. By establishing appropriate methods to closely monitor the fatigue status of personnel and relieve the fatigue on time, operation-related injuries can be reduced. Existing fatigue detection methods mostly include subjective methods, such as fatigue scales, or those involving the use of professional instruments, which are more demanding for operators and cannot detect fatigue levels in real time. Speech contains information that can be used as acoustic biomarkers to monitor physiological and psychological statuses. In this study, we constructed a fatigue model based on the method of sleep deprivation by collecting various physiological indexes, such as P300 and glucocorticoid level in saliva, as well as fatigue questionnaires filled by 15 participants under different fatigue procedures and graded the fatigue levels accordingly. We then extracted the speech features at different instances and constructed a model to match the speech features and the degree of fatigue using a machine learning algorithm. Thus, we established a method to rapidly judge the degree of fatigue based on speech. The accuracy of the judgment based on unitary voice could reach 94%, whereas that based on long speech could reach 81%. Our fatigue detection method based on acoustic information can easily and rapidly determine the fatigue levels of the participants. This method can operate in real time and is non-invasive and efficient. Moreover, it can be combined with the advantages of information technology and big data to expand its applicability.

Nonlinear Machine Learning in Warfarin Dose Prediction: Insights from Contemporary Modelling Studies

Objective: This study aimed to systematically assess the characteristics and risk of bias of previous studies that have investigated nonlinear machine learning algorithms for warfarin dose prediction. Methods: We systematically searched PubMed, Embase, Cochrane Library, Chinese National Knowledge Infrastructure (CNKI), China Biology Medicine (CBM), China Science and Technology Journal Database (VIP), and Wanfang Database up to March 2022. We assessed the general characteristics of the included studies with respect to the participants, predictors, model development, and model evaluation. The methodological quality of the studies was determined, and the risk of bias was evaluated using the Prediction model Risk of Bias Assessment Tool (PROBAST). Results: From a total of 8996 studies, 23 were assessed in this study, of which 23 (100%) were retrospective, and 11 studies focused on the Asian population. The most common demographic and clinical predictors were age (21/23, 91%), weight (17/23, 74%), height (12/23, 52%), and amiodarone combination (11/23, 48%), while CYP2C9 (14/23, 61%), VKORC1 (14/23, 61%), and CYP4F2 (5/23, 22%) were the most common genetic predictors. Of the included studies, the MAE ranged from 1.47 to 10.86 mg/week in model development studies, from 2.42 to 5.18 mg/week in model development with external validation (same data) studies, from 12.07 to 17.59 mg/week in model development with external validation (another data) studies, and from 4.40 to 4.84 mg/week in model external validation studies. All studies were evaluated as having a high risk of bias. Factors contributing to the risk of bias include inappropriate exclusion of participants (10/23, 43%), small sample size (15/23, 65%), poor handling of missing data (20/23, 87%), and incorrect method of selecting predictors (8/23, 35%). Conclusions: Most studies on nonlinear-machine-learning-based warfarin prediction models show poor methodological quality and have a high risk of bias. The analysis domain is the major contributor to the overall high risk of bias. External validity and model reproducibility are lacking in most studies. Future studies should focus on external validity, diminish risk of bias, and enhance real-world clinical relevance.

Automatic Decision-Making Style Recognition Method Using Kinect Technology

In recent years, somatosensory interaction technology, represented by Microsoft's Kinect hardware platform, has been widely used in various fields, such as entertainment, education, and medicine. Kinect technology can easily capture and record behavioral data, which provides new opportunities for behavioral and psychological correlation analysis research. In this paper, an automatic decision-style recognition method is proposed. Experiments involving 240 subjects were conducted to obtain face data and individual decision-making style score. The face data was obtained using the Kinect camera, and the decision-style score were obtained via a questionnaire. To realize automatic recognition of an individual decision-making style, machine learning was employed to establish the mapping relationship between the face data and a scaled evaluation of the decision-making style score. This study adopts a variety of classical machine learning algorithms, including Linear regression, Support vector machine regression, Ridge regression, and Bayesian ridge regression. The experimental results show that the linear regression model returns the best results. The correlation coefficient between the linear regression model evaluation results and the scale evaluation results was 0.6, which represents a medium and higher correlation. The results verify the feasibility of automatic decision-making style recognition method based on facial analysis.