Combining Kernel and Model Based Learning for HIV Therapy Selection

By Sonali Parbhoo, Jasmina Bogojeska, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez. 2017

84 citations recorded by the source corpus.

We present a mixture-of-experts approach for HIV therapy selection. The heterogeneity in patient data makes it difficult for one particular model to succeed at providing suitable therapy predictions for all patients. An appropriate means for addressing this heterogeneity is through combining kernel and model-based techniques. These methods capture different kinds of information: kernel-based methods are able to identify clusters of similar patients, and work well when modelling the viral response for these groups. In contrast, model-based methods capture the sequential process of decision making, and are able to find simpler, yet accurate patterns in response for patients outside these groups. We take advantage of this information by proposing a mixture-of-experts model that automatically selects between the methods in order to assign the most appropriate therapy choice to an individual. Overall, we verify that therapy combinations proposed using this approach significantly outperform previous methods.

Subfields: Statistical Learning Theory, Medical & Health AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistical Learning Theory

In Medical & Health AI

Citations in the corpus

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “, 2008), for HIV therapy (Parbhoo et al., 2017), and for managing type-1 diabetes (Javad et al.”
Reinforcement Learning in Healthcare: A Survey (2019, methodology): “ Gaussian processes and DRL to directly learn from sparsely sampled and frequently missing multivariate time series ICU data. Most recently, Peng et al. [201] applied the mixture-of-experts framework [147] in sepsis treatment by automatically switching between kernel learning and DRL depending on pa”
Inverse reinforcement learning for intelligent mechanical ventilation and sedative dosing in intensive care units (2019, background): “…learning (RL) [1] has achieved tremendous achievements in solving complex sequential decision making problems in various health care domains, including treatment in HIV [2], cancer [3], diabetics [4], anaemia [5], schizophrenia [6], epilepsy [7], anesthesia [8], and sepsis [9], just to name a few.”
Incorporating causal factors into reinforcement learning for dynamic treatment regimes in HIV (2019, methodology): “A mixture-of-experts approach was proposed in [2] to combine the strengths of both kernel-based regression methods (i.e., history-alignment model) and RL (i.e., model-based Bayesian POMDP model) for HIV therapy selection.”
Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs (2020, background): “Establishing effective treatment strategies for HIV-infected patients based on markers from blood tests can be cast as an RL problem [Ernst et al., 2006, Parbhoo et al., 2017, Killian et al., 2017].”
Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models (2019, methodology): “optimistically, are there lives which could have been saved? This question becomes increasingly relevant, with growing interest in applying RL to everything from HIV therapy (Parbhoo et al., 2017) to epilepsy (Guez et al.”