AI Models to Assist Vancomycin Dosage Titration

Abstract

Background: Effective treatment using antibiotic vancomycin requires close monitoring of serum drug levels due to its narrow therapeutic index. In the current practice, physicians use various dosing algorithms for dosage titration, but these algorithms reported low success in achieving therapeutic targets. We explored using artificial intelligent to assist vancomycin dosage titration.Methods: We used a novel method to generate the label for each record and only included records with appropriate label data to generate a clean cohort with 2,282 patients and 7,912 injection records. Among them, 64% of patients were used to train two machine learning models, one for initial dose recommendation and another for subsequent dose recommendation. The model performance was evaluated using two metrics: PAR, a pharmacology meaningful metric defined by us, and Mean Absolute Error (MAE), a commonly used regression metric.Results: In our 3-year data, only a small portion (34.1%) of current injection doses could reach the desired vancomycin trough level (14–20 mcg/ml). Both PAR and MAE of our machine learning models were better than the classical pharmacokinetic models. Our model also showed better performance than the other previously developed machine learning models in our test data.Conclusion: We developed machine learning models to recommend vancomycin dosage. Our results show that the new AI-assisted dosage titration approach has the potential to improve the traditional approaches. This is especially useful to guide decision making for inexperienced doctors in making consistent and safe dosing recommendations for high-risk medications like vancomycin.

Machine Learning: A New Approach for Dose Individualization

“…After removing duplicated articles, 3,346 studies were screened by the title and/or abstract, 3,175 irrelevant studies were excluded and 171 articles were included for full‐text review. Finally, 64 articles related to precision dosing using ML were included for analysis 11–74 . The PRISMA flow diagram representing the study selection process and review results is presented in Figure .…”

Personalized Web Services Composition Using Artificial Intelligence

“…We compare our approach in Table 2 here with several works that are worked on maching learning: 89.40 Yalçın N 2022 [20] 90. 20 Wang Z [21] 91.20 Van Laere S [22] 94.79 Yalçın N 2023 [23] 91.90 Corny J [24] 81.00 Kessler, S [25] 83.65 Dos Santos HD [26] 87.1 We compare our approach here with several works that are worked on maching learning: 3 details the comparison of our best results with those obtained by other authors in the web servises composition using Artificial Intelligence. Figure 6 compares the proposed Drug-AI model with other benchmark models in terms of accuracy, and it can be seen that the accuracy of Drug-AI is higher than that of the other models.…”

Artificial intelligence and machine learning for clinical pharmacology

“…23,24 A decision-tree-based model was used to personalize vancomycin dosing regimens using data from electronic health records, and similar techniques have been suggested for other drugs with a narrow therapeutic index. 74 In a large multicentre study, a reinforcement learning tool was developed to suggest the dose of erythropoietin for patients receiving haemodialysis, aiming to improve the haemoglobin level while minimizing the total doses of erythropoietin given. 75 A systematic review identified eight studies reporting machine learning models to support personalized dosing of intravenous unfractionated heparin.…”

“…AI methods can support pharmacokinetic and pharmacodynamic analyses to guide drug dosing 23,24 . A decision‐tree‐based model was used to personalize vancomycin dosing regimens using data from electronic health records, and similar techniques have been suggested for other drugs with a narrow therapeutic index 74 . In a large multicentre study, a reinforcement learning tool was developed to suggest the dose of erythropoietin for patients receiving haemodialysis, aiming to improve the haemoglobin level while minimizing the total doses of erythropoietin given 75 …”