Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment

• URL: http://arxiv.org/abs/2101.08477v2
• Date: Tue, 2 Feb 2021 05:55:47 GMT
• Title: Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment
• Authors: Thesath Nanayakkara, Gilles Clermont, Christopher James Langmead, and David Swigon
• Abstract summary: There is no universally agreed upon strategy for vasopressor and fluid administration. Sepsis is the leading cause of mortality in the ICU, responsible for 6% of all hospitalizations and 35% of all in-hospital deaths in USA. We propose a novel approach, exploiting and unifying complementary strengths of Mathematical Modelling, Deep Learning, Reinforcement Learning and Uncertainty Quantification.
• Score: 0.2399911126932526
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sepsis is the leading cause of mortality in the ICU, responsible for 6% of all hospitalizations and 35% of all in-hospital deaths in USA. However, there is no universally agreed upon strategy for vasopressor and fluid administration. It has also been observed that different patients respond differently to treatment, highlighting the need for individualized treatment. Vasopressors and fluids are administrated with specific effects to cardiovascular physiology in mind and medical research has suggested that physiologic, hemodynamically guided, approaches to treatment. Thus we propose a novel approach, exploiting and unifying complementary strengths of Mathematical Modelling, Deep Learning, Reinforcement Learning and Uncertainty Quantification, to learn individualized, safe, and uncertainty aware treatment strategies. We first infer patient-specific, dynamic cardiovascular states using a novel physiology-driven recurrent neural network trained in an unsupervised manner. This information, along with a learned low dimensional representation of the patient's lab history and observable data, is then used to derive value distributions using Batch Distributional Reinforcement Learning. Moreover in a safety critical domain it is essential to know what our agent does and does not know, for this we also quantify the model uncertainty associated with each patient state and action, and propose a general framework for uncertainty aware, interpretable treatment policies. This framework can be tweaked easily, to reflect a clinician's own confidence of the framework, and can be easily modified to factor in human expert opinion, whenever it's accessible. Using representative patients and a validation cohort, we show that our method has learned physiologically interpretable generalizable policies.

Related papers

• Deciphering Cardiac Destiny: Unveiling Future Risks Through Cutting-Edge Machine Learning Approaches [0.0]
  This project aims to develop and assess predictive models for the timely identification of cardiac arrest incidents. We employ machine learning algorithms like XGBoost, Gradient Boosting, and Naive Bayes, alongside a deep learning (DL) approach with Recurrent Neural Networks (RNNs) Rigorous experimentation and validation revealed the superior performance of the RNN model.
  arXiv  Detail & Related papers  (2024-09-03T19:18:16Z)
• Leveraging Federated Learning for Automatic Detection of Clopidogrel Treatment Failures [0.8132630541462695]
  In this study, we leverage federated learning strategies to address clopidogrel treatment failure detection. We partitioned the data based on geographic centers and evaluated the performance of federated learning. Our findings underscore the potential of federated learning in addressing clopidogrel treatment failure detection.
  arXiv  Detail & Related papers  (2024-03-05T23:31:07Z)
• Safe and Interpretable Estimation of Optimal Treatment Regimes [54.257304443780434]
  We operationalize a safe and interpretable framework to identify optimal treatment regimes. Our findings support personalized treatment strategies based on a patient's medical history and pharmacological features.
  arXiv  Detail & Related papers  (2023-10-23T19:59:10Z)
• Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability [82.29775890542967]
  Estimating personalized effects of treatments is a complex, yet pervasive problem. Recent developments in the machine learning literature on heterogeneous treatment effect estimation gave rise to many sophisticated, but opaque, tools. We use post-hoc feature importance methods to identify features that influence the model's predictions.
  arXiv  Detail & Related papers  (2022-06-16T17:59:05Z)
• COVID-Net Biochem: An Explainability-driven Framework to Building Machine Learning Models for Predicting Survival and Kidney Injury of COVID-19 Patients from Clinical and Biochemistry Data [66.43957431843324]
  We introduce COVID-Net Biochem, a versatile and explainable framework for constructing machine learning models. We apply this framework to predict COVID-19 patient survival and the likelihood of developing Acute Kidney Injury during hospitalization.
  arXiv  Detail & Related papers  (2022-04-24T07:38:37Z)
• Optimal discharge of patients from intensive care via a data-driven policy learning framework [58.720142291102135]
  It is important that the patient discharge task addresses the nuanced trade-off between decreasing a patient's length of stay and the risk of readmission or even death following the discharge decision. This work introduces an end-to-end general framework for capturing this trade-off to recommend optimal discharge timing decisions. A data-driven approach is used to derive a parsimonious, discrete state space representation that captures a patient's physiological condition.
  arXiv  Detail & Related papers  (2021-12-17T04:39:33Z)
• Offline reinforcement learning with uncertainty for treatment strategies in sepsis [0.0]
  We present a novel application of reinforcement learning in which we identify optimal recommendations for sepsis treatment from data. Rather than a single recommendation, our method can present several treatment options. We examine learned policies and discover that reinforcement learning is biased against aggressive intervention due to the confounding relationship between mortality and level of treatment received.
  arXiv  Detail & Related papers  (2021-07-09T15:29:05Z)
• Estimating and Improving Fairness with Adversarial Learning [65.99330614802388]
  We propose an adversarial multi-task training strategy to simultaneously mitigate and detect bias in the deep learning-based medical image analysis system. Specifically, we propose to add a discrimination module against bias and a critical module that predicts unfairness within the base classification model. We evaluate our framework on a large-scale public-available skin lesion dataset.
  arXiv  Detail & Related papers  (2021-03-07T03:10:32Z)
• Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration [55.88616573143478]
  Outcome prediction from clinical text can prevent doctors from overlooking possible risks. Diagnoses at discharge, procedures performed, in-hospital mortality and length-of-stay prediction are four common outcome prediction targets. We propose clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources.
  arXiv  Detail & Related papers  (2021-02-08T10:26:44Z)
• Optimizing Medical Treatment for Sepsis in Intensive Care: from Reinforcement Learning to Pre-Trial Evaluation [2.908482270923597]
  Our aim is to establish a framework where reinforcement learning (RL) of optimizing interventions retrospectively allows us a regulatory compliant pathway to prospective clinical testing of the learned policies. We focus on infections in intensive care units which are one of the major causes of death and difficult to treat because of the complex and opaque patient dynamics.
  arXiv  Detail & Related papers  (2020-03-13T20:31:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.