Dynamic treatment selection and modification for personalised blood pressure therapy using a Markov decision process model: a cost-effectiveness analysis

Abstract

ObjectivePersonalised medicine seeks to select and modify treatments based on individual patient characteristics and preferences. We sought to develop an automated strategy to select and modify blood pressure treatments, incorporating the likelihood that patients with different characteristics would benefit from different types of medications and dosages and the potential severity and impact of different side effects among patients with different characteristics.Design, setting and participantsWe developed a Markov decision process (MDP) model to incorporate meta-analytic data and estimate the optimal treatment for maximising discounted lifetime quality-adjusted life-years (QALYs) based on individual patient characteristics, incorporating medication adjustment choices when a patient incurs side effects. We compared the MDP to current US blood pressure treatment guidelines (the Eighth Joint National Committee, JNC8) and a variant of current guidelines that incorporates results of a major recent trial of intensive treatment (Intensive JNC8). We used a microsimulation model of patient demographics, cardiovascular disease risk factors and side effect probabilities, sampling from the National Health and Nutrition Examination Survey (2003–2014), to compare the expected population outcomes from adopting the MDP versus guideline-based strategies.Main outcome measuresCosts and QALYs for the MDP-based treatment (MDPT), JNC8 and Intensive JNC8 strategies.ResultsCompared with the JNC8 guideline, the MDPT strategy would be cost-saving from a societal perspective with discounted savings of US$1187 per capita (95% CI 1178 to 1209) and an estimated discounted gain of 0.06 QALYs per capita (95% CI 0.04 to 0.08) among the US adult population. QALY gains would largely accrue from reductions in severe side effects associated with higher treatment doses later in life. The Intensive JNC8 strategy was dominated by the MDPT strategy.ConclusionsAn MDP-based approach can aid decision-making by incorporating meta-analytic evidence to personalise blood pressure treatment and improve overall population health compared with current blood pressure treatment guidelines.

Machine Learning Applied to Neuroreabilitation: A Systematic Mapping

“…Markov Decision Process (MDP) is a model where the results are partially under control of a decision maker based on high-quality probabilistic calculations with meta-analytic data [12]. Random Forest Algorithm (RFA) searches for relevant important characteristics during classification, being a technique that seeks to achieve a maximum classification accuracy rate [13].…”

Markov Clustering Analysis-Based Validation for Traditional Chinese Medicine Syndrome Patterns of Poststroke Cognitive Impairment

“…33 In addition, a series of parameters have to be set artificially in MCL and thus analyst blinding can hardly be achieved. 43 Current findings need to be further validated and expanded by other data mining approaches. 34 Strengths of this study design should also be noted.…”

“…Therefore, it has an ability to describe the internal property and external relevance with high efficiency in a dimension-reducing process (typically TCM syndrome patterns validation). 42,43 ''Memorylessness'' in MCL refers to an assumption that the properties of variables related to the future depend only on their current state, not upon the sequence of events that preceded it. 44 The major limitation of the MCL model is ''memorylessness,'' since diagnosis and prognosis for each patient usually rest on the history of previous diseases due to the Markov property of nonafter effect, which may affect the sensitivity and validity of results.…”

Projecting effectiveness after ending a randomized controlled trial: a two-state Markov microsimulation model

“…Recent literature discussed various efforts on constructing and expediting models with dramatically complex structures. However, there are scarce discussions about fundamental parameters such as cycle lengths, half-a-cycle age correction and background probabilities (7)(8)(9)(10)(11)(12)(13)(14)(15)(16)(17)(18). Moreover, these parameters have been used without justification in many recent implementations and applications of Markov microsimulation models (4)(5)(6).…”