A Model Predictive Control Functional Continuous Time Bayesian Network for Self-Management of Multiple Chronic Conditions
Multiple chronic conditions (MCC) are one of the biggest challenges of modern times. The evolution of MCC follows a complex stochastic process that is influenced by a variety of risk factors, ranging from pre-existing conditions to modifiable lifestyle behavioral factors (e.g. diet, exercise habits, tobacco use, alcohol use, etc.) to non-modifiable socio-demographic factors (e.g., age, gender, education, marital status, etc.). People with MCC are at an increased risk of new chronic conditions and mortality. This paper proposes a model predictive control functional continuous time Bayesian network, an online recursive method to examine the impact of various lifestyle behavioral changes on the emergence trajectories of MCC and generate strategies to minimize the risk of progression of chronic conditions in individual patients. The proposed method is validated based on the Cameron county Hispanic cohort (CCHC) dataset, which has a total of 385 patients. The dataset examines the emergence of 5 chronic conditions (diabetes, obesity, cognitive impairment, hyperlipidemia, and hypertension) based on four modifiable risk factors representing lifestyle behaviors (diet, exercise habits, tobacco use, alcohol use) and four non-modifiable risk factors, including socio-demographic information (age, gender, education, marital status). The proposed method is tested under different scenarios (e.g., age group, the prior existence of MCC), demonstrating the effective intervention strategies for improving the lifestyle behavioral risk factors to offset MCC evolution.
Code (0)
등록된 구현이 없습니다.
Tasks
ManagementModel Predictive ControlSimilar Papers 제목 키워드 기반
Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation
Treatment effect estimation in continuous time is crucial for personalized medicine. However, existing methods for this task are limited to point estimates of the potential outcomes, whereas uncertainty estimates have be…
Bayesian InferenceDecision MakingUncertainty QuantificationFunctional Stochastic Gradient MCMC for Bayesian Neural Networks
Classical parameter-space Bayesian inference for Bayesian neural networks (BNNs) suffers from several unresolved prior issues, such as knowledge encoding intractability and pathological behaviours in deep networks, which…
Bayesian InferenceUncertainty QuantificationVariational InferenceOn the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference
While parameter-efficient fine-tuning methods like low-rank adaptation (LoRA) are standard for large language models, principled estimation of epistemic uncertainty remains challenging. Recent results in the LoRA regime …
parameter-efficient fine-tuningBayesian InferenceVariational multiple shooting for Bayesian ODEs with Gaussian processes
Recent machine learning advances have proposed black-box estimation of unknown continuous-time system dynamics directly from data. However, earlier works are based on approximative ODE solutions or point estimates. We pr…
Bayesian InferenceGaussian ProcessesVariational InferenceConcentration and Calibration in Predictive Bayesian Inference
Predictive Bayesian inference (PBI) represents a model-and prior-agnostic approach to standard Bayesian inference which allows users to quantify uncertainty for a functional of interest only by specifying a forward predi…
Bayesian Inference