An artificial neural network−pharmacokinetic model and its interpretation using Shapley additive explanations

Ogami, Chika; Tsuji, Yasuhiro; Seki, Hiroto; Kawano, Hideaki; To, Hideto; Matsumoto, Yoshiaki; Hosono, Hiroyuki

doi:10.1002/psp4.12643

Cited by 47 publications

(35 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also assessed the agreement between predicted probabilities and observed frequencies of NICU mortality by calibration belts [24]. Finally, we used Shapley additive explanation (SHAP) values to examine the accurate contribution of each feature or input within the best prediction model [25]. All P values were two-sided, and a value of less than 0.05 was considered significant.…”

Section: Discussionmentioning

confidence: 99%

“…Using machine learning algorithms to help clinicians has formed a major emerging research trend in the past decade [18][19][20][24][25][26][27]. The mortality of critically ill neonates with respiratory failure has previously been difficult to predict because most neonates can survive the initial critical period and various life-threatening events may occur during their long-term hospital courses [28].…”

Section: Discussionmentioning

confidence: 99%

“…In addition, we also applied SHAP to calculate the contribution of each feature to the RF model. The concept of SHAP is to average the difference between the predicted values with and without the effect of adding each feature for all combinations and examine the influence of inputs after machine learning [25,37]. SHAP was used in this study because most ensemble ML methods have the disadvantage of decreased interpretability after achieving high accuracy.…”

Section: Discussionmentioning

confidence: 99%

“…SHAP was used in this study because most ensemble ML methods have the disadvantage of decreased interpretability after achieving high accuracy. Because ensemble learning methods are usually more complex than traditional learning methods, SHAP can be applied to understand the importance of each feature and which direction the feature affects [25,37]. Thus, we can build a highly predictive model with good transparency for the outcomes.…”

Section: Discussionmentioning

confidence: 99%

“…In our institute, all neonatologists follow the standard guideline that mechanical intubation will be done if we fail to maintain PaO 2 > 60, a pH value > 7. 25, and the requirement of fraction of inspired oxygenation (FiO 2 ) > 60 using a noninvasive ventilator. Neonates who had severe congenital anomalies (n = 8), those with missing data on outcomes (n = 18), and those who died within the first day after intubation were excluded.…”

Section: Patients Setting and Study Designmentioning

confidence: 99%

See 4 more Smart Citations

Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure

et al. 2021

View full text Add to dashboard Cite

Background: Early identification of critically ill neonates with poor outcomes can optimize therapeutic strategies. We aimed to examine whether machine learning (ML) methods can improve mortality prediction for neonatal intensive care unit (NICU) patients on intubation for respiratory failure. Methods: A total of 1734 neonates with respiratory failure were randomly divided into training (70%, n = 1214) and test (30%, n = 520) sets. The primary outcome was the probability of NICU mortality. The areas under the receiver operating characteristic curves (AUCs) of several ML algorithms were compared with those of the conventional neonatal illness severity scoring systems including the NTISS and SNAPPE-II. Results: For NICU mortality, the random forest (RF) model showed the highest AUC (0.939 (0.921–0.958)) for the prediction of neonates with respiratory failure, and the bagged classification and regression tree model demonstrated the next best results (0.915 (0.891–0.939)). The AUCs of both models were significantly better than the traditional NTISS (0.836 (0.800–0.871)) and SNAPPE-II scores (0.805 (0.766–0.843)). The superior performances were confirmed by higher accuracy and F1 score and better calibration, and the superior and net benefit was confirmed by decision curve analysis. In addition, Shapley additive explanation (SHAP) values were utilized to explain the RF prediction model. Conclusions: Machine learning algorithms increase the accuracy and predictive ability for mortality of neonates with respiratory failure compared with conventional neonatal illness severity scores. The RF model is suitable for clinical use in the NICU, and clinicians can gain insights and have better communication with families in advance.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Patients Setting and Study Designmentioning

confidence: 99%

See 3 more Smart Citations

Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure

et al. 2021

View full text Add to dashboard Cite

show abstract

Machine Learning as a Novel Method to Support Therapeutic Drug Management and Precision Dosing

Gelder

Vinks

2021

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

Machine Learning: A New Approach for Dose Individualization

Li,

Tang,

et al. 2023

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

The application of machine learning (ML) has shown promising results in precision medicine due to its exceptional performance in dealing with complex multidimensional data. However, using ML for individualized dosing of medicines is still in its early stage, meriting further exploration. A systematic review of study designs and modeling details of using ML for individualized dosing of different drugs was performed. We have summarized the status of the study populations, predictive targets, and data sources for ML modeling, the selection of ML algorithms and features, and the evaluation and validation of their predictive performance. We also used the Prediction model Risk of Bias Assessment Tool (PROBAST) to assess the risk of bias of included studies. Currently, ML can be used for both a priori and a posteriori dose selection and optimization, and it can also assist the implementation of therapeutic drug monitoring. However, studies are mainly focused on drugs with narrow therapeutic windows, predominantly immunosuppressants (N=23, 35.9%) and anti‐infectives (N=21, 32.8%), and there is currently only very limited attention for special populations such as children (N=22, 34.4%). Most studies showed poor methodological quality and a high risk of bias. The lack of external validation and clinical utility evaluation currently limits the further clinical implementation of ML for dose individualization. We therefore have proposed several ways to improve the clinical relevance of the studies and facilitate the translation of ML models into clinical practice.

show abstract

An artificial neural network−pharmacokinetic model and its interpretation using Shapley additive explanations

Abstract: This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

Cited by 47 publications

References 31 publications

Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure

Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure

Machine Learning as a Novel Method to Support Therapeutic Drug Management and Precision Dosing

Machine Learning: A New Approach for Dose Individualization

Contact Info

Product

Resources

About