Development and evaluation of uncertainty quantifying machine learning models to predict piperacillin plasma concentrations in critically ill patients

Antibiotic dose optimisation in the critically ill: targets, evidence and future strategies

PURPOSE OF REVIEW

To highlight the recent evidence for antibiotic pharmacokinetics and pharmacodynamics (PK/PD) in enhancing patient outcomes in sepsis and septic shock. We also summarise the limitations of available data and describe future directions for research to support translation of antibiotic dose optimisation to the clinical setting.

RECENT FINDINGS

Sepsis and septic shock are associated with poor outcomes and require antibiotic dose optimisation, mostly due to significantly altered pharmacokinetics. Many studies, including some randomised controlled trials have been conducted to measure the clinical outcome effects of antibiotic dose optimisation interventions including use of therapeutic drug monitoring. Current data support antibiotic dose optimisation for the critically ill. Further investigation is required to evolve more timely and robust precision antibiotic dose optimisation approaches, and to clearly quantify whether any clinical and health-economic benefits support expanded use of this treatment intervention.

SUMMARY

Antibiotic dose optimisation appears to improve outcomes in critically ill patients with sepsis and septic shock, however further research is required to quantify the level of benefit and develop a stronger knowledge of the role of new technologies to facilitate optimised dosing.

Comparative study of ten machine learning algorithms for short-term forecasting in gas warning systems

This research aims to explore more efficient machine learning (ML) algorithms with better performance for short-term forecasting. Up-to-date literature shows a lack of research on selecting practical ML algorithms for short-term forecasting in real-time industrial applications. This research uses a quantitative and qualitative mixed method combining two rounds of literature reviews, a case study, and a comparative analysis. Ten widely used ML algorithms are selected to conduct a comparative study of gas warning systems in a case study mine. We propose a new assessment visualization tool: a 2D space-based quadrant diagram can be used to visually map prediction error assessment and predictive performance assessment for tested algorithms. Overall, this visualization tool indicates that LR, RF, and SVM are more efficient ML algorithms with overall prediction performance for short-term forecasting. This research indicates ten tested algorithms can be visually mapped onto optimal (LR, RF, and SVM), efficient (ARIMA), suboptimal (BP-SOG, KNN, and Perceptron), and inefficient algorithms (RNN, BP_Resilient, and LSTM). The case study finds results that differ from previous studies regarding the ML efficiency of ARIMA, KNN, LR, LSTM, and SVM. This study finds different views on the prediction performance of a few paired algorithms compared with previous studies, including RF and LR, SVM and RF, KNN and ARIMA, KNN and SVM, RNN and ARIMA, and LSTM and SVM. This study also suggests that ARIMA, KNN, LR, and LSTM should be investigated further with additional prediction error assessments. Overall, no single algorithm can fit all applications. This study raises 20 valuable questions for further research.

Knowledge mapping of graph neural networks for drug discovery: a bibliometric and visualized analysis

Introduction

In recent years, graph neural network has been extensively applied to drug discovery research. Although researchers have made significant progress in this field, there is less research on bibliometrics. The purpose of this study is to conduct a comprehensive bibliometric analysis of graph neural network applications in drug discovery in order to identify current research hotspots and trends, as well as serve as a reference for future research.

Methods

Publications from 2017 to 2023 about the application of graph neural network in drug discovery were collected from the Web of Science Core Collection. Bibliometrix, VOSviewer, and Citespace were mainly used for bibliometric studies.

Results and Discussion

In this paper, a total of 652 papers from 48 countries/regions were included. Research interest in this field is continuously increasing. China and the United States have a significant advantage in terms of funding, the number of publications, and collaborations with other institutions and countries. Although some cooperation networks have been formed in this field, extensive worldwide cooperation still needs to be strengthened. The results of the keyword analysis clarified that graph neural network has primarily been applied to drug-target interaction, drug repurposing, and drug-drug interaction, while graph convolutional neural network and its related optimization methods are currently the core algorithms in this field. Data availability and ethical supervision, balancing computing resources, and developing novel graph neural network models with better interpretability are the key technical issues currently faced. This paper analyzes the current state, hot spots, and trends of graph neural network applications in drug discovery through bibliometric approaches, as well as the current issues and challenges in this field. These findings provide researchers with valuable insights on the current status and future directions of this field.

Machine Learning: A New Approach for Dose Individualization

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.

Artificial intelligence-based model for dose prediction of sertraline in adolescents: a real-world study

BACKGROUND

Variability exists in sertraline pharmacokinetic parameters in individuals, especially obvious in adolescents. We aimed to establish an individualized dosing model of sertraline for adolescents with depression based on artificial intelligence (AI) techniques.

METHODS

Data were collected from 258 adolescent patients treated at the First Hospital of Hebei Medical University between December 2019 to July 2022. Nine different algorithms were used for modeling to compare the prediction abilities on sertraline daily dose, including XGBoost, LGBM, CatBoost, GBDT, SVM, ANN, TabNet, KNN, and DT. Performance of four dose subgroups (50 mg, 100 mg, 150 mg, and 200 mg) were analyzed.

RESULTS

CatBoost was chosen to establish the individualized medication model with the best performance. Six important variables were found to be correlated with sertraline dose, including plasma concentration, PLT, MPV, GL, A/G, and LDH. The ROC curve and confusion matrix exhibited the good prediction performance of CatBoost model in four dose subgroups (the AUC of 50 mg, 100 mg, 150 mg, and 200 mg were 0.93, 0.81, 0.93, and 0.93, respectively).

CONCLUSION

The AI-based dose prediction model of sertraline in adolescents with depression had a good prediction ability, which provides guidance for clinicians to propose the optimal medication regimen.

Generalizable calibrated machine learning models for real-time atrial fibrillation risk prediction in ICU patients

BACKGROUND

Atrial Fibrillation (AF) is the most common arrhythmia in the intensive care unit (ICU) and is associated with increased morbidity and mortality. Identification of patients at risk for AF is not routinely performed as AF prediction models are almost solely developed for the general population or for particular ICU populations. However, early AF risk identification could help to take targeted preemptive actions and possibly reduce morbidity and mortality. Predictive models need to be validated across hospitals with different standards of care and convey their predictions in a clinically useful manner. Therefore, we designed AF risk models for ICU patients using uncertainty quantification to provide a risk score and evaluated them on multiple ICU datasets.

METHODS

Three CatBoost models, utilizing feature windows comprising data 1.5-13.5, 6-18, or 12-24 hours before AF occurrence, were built using 2-repeat-10-fold cross-validation on AmsterdamUMCdb, the first freely available European ICU database. Furthermore, AF Patients were matched with no-AF patients for training. Transferability was validated using a direct and a recalibration evaluation on two independent external datasets, MIMIC-IV and GUH. The calibration of the predicted probability, used as an AF risk score, was measured using the Expected Calibration Error (ECE) and the presented Expected Signed Calibration Error (ESCE). Additionally, all models were evaluated across time during the ICU stay.

RESULTS

The model performance reached Areas Under the Curve (AUCs) of 0.81 at internal validation. Direct external validation showed partial generalizability with AUCs reaching 0.77. However, recalibration resulted in performances matching or exceeding that of the internal validation. All models furthermore showed calibration capabilities demonstrating adequate risk prediction competence.

CONCLUSION

Ultimately, recalibrating models reduces the challenge of generalization to unseen datasets. Moreover, utilizing the patient-matching methodology together with the assessment of uncertainty calibration can serve as a step toward the development of clinical AF prediction models.