Artificial intelligence-guided precision treatment of chronic kidney disease-mineral bone disorder

Systematic literature review on reinforcement learning in non-communicable disease interventions

There is evidence that reducing modifiable risk factors and strengthening medical and health interventions can reduce early mortality and economic losses from non-communicable diseases (NCDs). Machine learning (ML) algorithms have been successfully applied to preventing and controlling NCDs. Reinforcement learning (RL) is the most promising of these approaches because of its ability to dynamically adapt interventions to NCD disease progression and its commitment to achieving long-term intervention goals. This paper reviews the preferred algorithms, data sources, design details, and obstacles to clinical application in existing studies to facilitate the early application of RL algorithms in clinical practice research for NCD interventions. We screened 40 relevant papers for quantitative and qualitative analysis using the PRISMA review flow diagram. The results show that researchers tend to use Deep Q-Network (DQN) and Actor-Critic as well as their improved or hybrid algorithms to train and validate RL models on retrospective datasets. Often, the patient's physical condition is the main defining parameter of the state space, while interventions are the main defining parameter of the action space. Mostly, changes in the patient's physical condition are used as a basis for immediate rewards to the agent. Various attempts have been made to address the challenges to clinical application, and several approaches have been proposed from existing research. However, as there is currently no universally accepted solution, the use of RL algorithms in clinical practice for NCD interventions necessitates more comprehensive responses to the issues addressed in this paper, which are safety, interpretability, training efficiency, and the technical aspect of exploitation and exploration in RL algorithms.

Application of artificial intelligence to chronic kidney disease mineral bone disorder

The global derangement of mineral metabolism that accompanies chronic kidney disease (CKD-MBD) is a major driver of the accelerated mortality for individuals with kidney disease. Advances in the delivery of dialysis, in the composition of phosphate binders, and in the therapies directed towards secondary hyperparathyroidism have failed to improve the cardiovascular event profile in this population. Many obstacles have prevented progress in this field including the incomplete understanding of pathophysiology, the lack of clinical targets for early stages of chronic kidney disease, and the remarkably wide diversity in clinical manifestations. We describe in this review a novel approach to CKD-MBD combining mathematical modelling of biologic processes with machine learning artificial intelligence techniques as a tool for the generation of new hypotheses and for the development of innovative therapeutic approaches to this syndrome. Clinicians need alternative targets of therapy, tools for risk profile assessment, and new therapies to address complications early in the course of disease and to personalize therapy to each individual. The complexity of CKD-MBD suggests that incorporating artificial intelligence techniques into the diagnostic, therapeutic, and research armamentarium could accelerate the achievement of these goals.

Using Machine Learning to Individualize Treatment Effect Estimation: Challenges and Opportunities

The use of data from randomized clinical trials to justify treatment decisions for real-world patients is the current state of the art. It relies on the assumption that average treatment effects from the trial can be extrapolated to patients with personal and/or disease characteristics different from those treated in the trial. Yet, because of heterogeneity of treatment effects between patients and between the trial population and real-world patients, this assumption may not be correct for many patients. Using machine learning to estimate the expected conditional average treatment effect (CATE) in individual patients from observational data offers the potential for more accurate estimation of the expected treatment effects in each patient based on their observed characteristics. In this review, we discuss some of the challenges and opportunities for machine learning to estimate CATE, including ensuring identification assumptions are met, managing covariate shift, and learning without access to the true label of interest. We also discuss the potential applications as well as future work and collaborations needed to further improve identification and utilization of CATE estimates to increase patient benefit.

Beyond Population-Level Targets for Drug Concentrations: Precision Dosing Needs Individual-Level Targets that Include Superior Biomarkers of Drug Responses

The purpose of precision dosing is to increase the chances of therapeutic success in individual patients. This is achieved in practice by adjusting doses to reach precision dosing targets determined previously in relevant populations, ideally with robust supportive evidence showing improved clinical outcomes compared with standard dosing. But is this implicit assumption of translatable population-level precision dosing targets correct and the best for all patients? In this review, the types of precision dosing targets and how they are determined are outlined, problems with the translatability of these targets to individual patients are identified, and ways forward to address these challengers are proposed. Achieving improved clinical outcomes to support precision dosing over standard dosing is currently hampered by applying population-level targets to all patients. Just as "one-dose-fits-all" may be an inappropriate philosophy for drug treatment overall, a "one-target-fits-all" philosophy may limit the broad clinical benefits of precision dosing. Defining individual-level precision dosing targets may be needed for greatest therapeutic success. Superior future precision dosing targets will integrate several biomarkers that together account for the multiple sources of drug response variability.