The roles of predictors in cardiovascular risk models - a question of modeling culture?

Pre-treatment risk predictors of valproic acid-induced dyslipidemia in pediatric patients with epilepsy

Background: Valproic acid (VPA) stands as one of the most frequently prescribed medications in children with newly diagnosed epilepsy. Despite its infrequent adverse effects within therapeutic range, prolonged VPA usage may result in metabolic disturbances including insulin resistance and dyslipidemia. These metabolic dysregulations in childhood are notably linked to heightened cardiovascular risk in adulthood. Therefore, identification and effective management of dyslipidemia in children hold paramount significance. Methods: In this retrospective cohort study, we explored the potential associations between physiological factors, medication situation, biochemical parameters before the first dose of VPA (baseline) and VPA-induced dyslipidemia (VID) in pediatric patients. Binary logistic regression was utilized to construct a predictive model for blood lipid disorders, aiming to identify independent pre-treatment risk factors. Additionally, The Receiver Operating Characteristic (ROC) curve was used to evaluate the performance of the model. Results: Through binary logistic regression analysis, we identified for the first time that direct bilirubin (DBIL) (odds ratios (OR) = 0.511, p = 0.01), duration of medication (OR = 0.357, p = 0.009), serum albumin (ALB) (OR = 0.913, p = 0.043), BMI (OR = 1.140, p = 0.045), and aspartate aminotransferase (AST) (OR = 1.038, p = 0.026) at baseline were independent risk factors for VID in pediatric patients with epilepsy. Notably, the predictive ability of DBIL (AUC = 0.690, p < 0.0001) surpassed that of other individual factors. Furthermore, when combined into a predictive model, incorporating all five risk factors, the predictive capacity significantly increased (AUC = 0.777, p < 0.0001), enabling the forecast of 77.7% of dyslipidemia events. Conclusion: DBIL emerges as the most potent predictor, and in conjunction with the other four factors, can effectively forecast VID in pediatric patients with epilepsy. This insight can guide the formulation of individualized strategies for the clinical administration of VPA in children.

Recent developments in machine learning modeling methods for hypertension treatment

Hypertension is the leading cause of cardiovascular complications. This review focuses on the advancements in medical artificial intelligence (AI) models aimed at individualized treatment for hypertension, with particular emphasis on the approach to time-series big data on blood pressure and the development of interpretable medical AI models. The digitalization of daily blood pressure records and the downsizing of measurement devices enable the accumulation and utilization of time-series data. As mainstream blood pressure data shift from snapshots to time series, the clinical significance of blood pressure variability will be clarified. The time-series blood pressure prediction model demonstrated the capability to forecast blood pressure variabilities with a reasonable degree of accuracy for up to four weeks in advance. In recent years, various explainable AI techniques have been proposed for different purposes of model interpretation. It is essential to select the appropriate technique based on the clinical aspects; for example, actionable path-planning techniques can present individualized intervention plans to efficiently improve outcomes such as hypertension. Despite considerable progress in this field, challenges remain, such as the need for the prospective validation of AI-driven interventions and the development of comprehensive systems that integrate multiple AI methods. Future research should focus on addressing these challenges and refining the AI models to ensure their practical applicability in real-world clinical settings. Furthermore, the implementation of interdisciplinary collaborations among AI experts, clinicians, and healthcare providers are crucial to further optimizing and validate AI-driven solutions for hypertension management.

Sample size and predictive performance of machine learning methods with survival data: A simulation study

Prediction models are increasingly developed and used in diagnostic and prognostic studies, where the use of machine learning (ML) methods is becoming more and more popular over traditional regression techniques. For survival outcomes the Cox proportional hazards model is generally used and it has been proven to achieve good prediction performances with few strong covariates. The possibility to improve the model performance by including nonlinearities, covariate interactions and time-varying effects while controlling for overfitting must be carefully considered during the model building phase. On the other hand, ML techniques are able to learn complexities from data at the cost of hyper-parameter tuning and interpretability. One aspect of special interest is the sample size needed for developing a survival prediction model. While there is guidance when using traditional statistical models, the same does not apply when using ML techniques. This work develops a time-to-event simulation framework to evaluate performances of Cox regression compared, among others, to tuned random survival forest, gradient boosting, and neural networks at varying sample sizes. Simulations were based on replications of subjects from publicly available databases, where event times were simulated according to a Cox model with nonlinearities on continuous variables and time-varying effects and on the SEER registry data.

A scoping methodological review of simulation studies comparing statistical and machine learning approaches to risk prediction for time-to-event data

BACKGROUND

There is substantial interest in the adaptation and application of so-called machine learning approaches to prognostic modelling of censored time-to-event data. These methods must be compared and evaluated against existing methods in a variety of scenarios to determine their predictive performance. A scoping review of how machine learning methods have been compared to traditional survival models is important to identify the comparisons that have been made and issues where they are lacking, biased towards one approach or misleading.

METHODS

We conducted a scoping review of research articles published between 1 January 2000 and 2 December 2020 using PubMed. Eligible articles were those that used simulation studies to compare statistical and machine learning methods for risk prediction with a time-to-event outcome in a medical/healthcare setting. We focus on data-generating mechanisms (DGMs), the methods that have been compared, the estimands of the simulation studies, and the performance measures used to evaluate them.

RESULTS

A total of ten articles were identified as eligible for the review. Six of the articles evaluated a method that was developed by the authors, four of which were machine learning methods, and the results almost always stated that this developed method's performance was equivalent to or better than the other methods compared. Comparisons were often biased towards the novel approach, with the majority only comparing against a basic Cox proportional hazards model, and in scenarios where it is clear it would not perform well. In many of the articles reviewed, key information was unclear, such as the number of simulation repetitions and how performance measures were calculated.

CONCLUSION

It is vital that method comparisons are unbiased and comprehensive, and this should be the goal even if realising it is difficult. Fully assessing how newly developed methods perform and how they compare to a variety of traditional statistical methods for prognostic modelling is imperative as these methods are already being applied in clinical contexts. Evaluations of the performance and usefulness of recently developed methods for risk prediction should be continued and reporting standards improved as these methods become increasingly popular.