Temporal Logic Based Monitoring of Assisted Ventilation in Intensive Care Patients

@inproceedings{Bufo2014TemporalLB,
  title={Temporal Logic Based Monitoring of Assisted Ventilation in Intensive Care Patients},
  author={Sara Bufo and Ezio Bartocci and Guido Sanguinetti and Massimo Borelli and Umberto Lucangelo and Luca Bortolussi},
  booktitle={ISoLA},
  year={2014}
}
We introduce a novel approach to automatically detect ineffective breathing efforts in patients in intensive care subject to assisted ventilation. The method is based on synthesising from data temporal logic formulae which are able to discriminate between normal and ineffective breaths. The learning procedure consists in first constructing statistical models of normal and abnormal breath signals, and then in looking for an optimally discriminating formula. The space of formula structures, and… 

Respiratory mechanics and patient effort in mechanical ventilation

TLDR
This research presents a model that allows resistance to vary linearly with pressure, which offers similar performance to a more complex respiratory mechanics model.

A Logic-Based Learning Approach to Explore Diabetes Patient Behaviors

TLDR
T1D patient behaviors using a Signal Temporal Logic (STL) based learning approach characterize behavior patterns that may result in varying glycemic control, and can provide feedback to clinicians and patients about behavioral changes that patients may implement to improve T1D control.

Quantitative Regular Expressions for Arrhythmia Detection

TLDR
It is shown that QREs are more suitable than classical temporal logics to express in a concise and easy way a range of peak detectors and various discriminators at the heart of today's arrhythmia detection devices.

A Robust Genetic Algorithm for Learning Temporal Specifications from Data

TLDR
A systematic approach to synthesize both the syntactical structure and the parameters of the temporal logic formula using a two-steps procedure and indicates that the proposed approach outperforms the previous work w.r.t. the decision-tree based approach with a comparable speed and accuracy.

Online Learning of Temporal Logic Formulae for Signal Classification

TLDR
This paper introduces a method for online inference of temporal logic properties from data that allows the refinement of the current formula when more data is acquired and offers insights on the trade-off between formula complexity and classification accuracy.

A Decision Tree Approach to Data Classification using Signal Temporal Logic

TLDR
This paper introduces a framework for inference of timed temporal logic properties from data, and proposes extensions of the usual impurity measures from machine learning literature to handle classification of system traces by leveraging upon the robustness degree concept.

Regular Expressions for Irregular Rhythms

TLDR
A wavelet-based characterization of peaks that occur in cardiac electrograms is presented, along with two peak-detection algorithms based on this characterization that are easily expressible in Quantitative Regular Expressions (QREs), a formal language based on regular expressions for specifying complex numerical queries over data streams.

Quantitative Regular Expressions for Arrhythmia Detection Algorithms

TLDR
This work presents a formalization of arrhythmia-detection algorithms in the language of Quantitative Regular Expressions, a flexible formal language for specifying complex numerical queries over data streams, with provable runtime and memory consumption guarantees.

Offline and Online Learning of Signal Temporal Logic Formulae Using Decision Trees

TLDR
A decision-tree-based framework is devised that outputs an STL formula that can distinguish the traces of a system and is interpretable and can be used in other phases of the system’s operation, such as monitoring and control.

Uncertainty-Aware Signal Temporal Logic Inference

TLDR
This paper investigates the uncertainties associated with trajectories of a system and represents such uncertainties in the form of interval trajectories, and proposes two uncertaintyaware signal temporal logic (STL) inference approaches to classify the undesired behaviors and desired behaviors of a systems.

References

SHOWING 1-10 OF 46 REFERENCES

Automated detection of asynchrony in patient-ventilator interaction

TLDR
An automated classification algorithm for the detection of expiratory ineffective efforts in patient-ventilator interaction is developed and validated and demonstrates the viability of using pattern classification techniques to automatically detect the presence of asynchrony between a patient and their ventilator.

Automatic detection of ineffective triggering and double triggering during mechanical ventilation

TLDR
The feasibility, sensitivity and specificity of an algorithm embedded in a ventilator system that is able to automatically detect the occurrence of ineffective triggering and double triggering in real time are assessed.

Validation of the Better Care® system to detect ineffective efforts during expiration in mechanically ventilated patients: a pilot study

TLDR
This pilot study validated mathematical algorithms that automatically detect IEE in a computerized system that obtains and processes data from intensive care unit (ICU) ventilators in real time.

An automated and standardized neural index to quantify patient-ventilator interaction

TLDR
The present study introduces an automated method and the NeuroSync index to determine patient-ventilator interaction with a more sensitive analysis method than those previously described, and introduces a dashboard-style of graphical display.

Patient–ventilator asynchrony during non-invasive ventilation for acute respiratory failure: a multicenter study

TLDR
The results suggest that leaks play a major role in generating patient–ventilator asynchrony and discomfort, and point the way to further research to determine if ventilator functions designed to cope with leaks can reduce as synchrony in the clinical setting.

A Noninvasive Method to Identify Ineffective Triggering in Patients with Noninvasive Pressure Support Ventilation

TLDR
A nonin invasive analysis of flow and airway pressure can reliably identify ineffective triggering efforts during noninvasive pressure support ventilation and may be a valuable tool for evaluating patient-ventilator interactions and their consequences during long-term recordings.

Learning Temporal Logical Properties Discriminating ECG models of Cardiac Arrhytmias

TLDR
A novel approach to learn the formulae characterising the emergent behaviour of a dynamical system from system observations, which enables us to quantitatively determine the diagnostic power of a formula in discriminating between different cardiac conditions.

Identifying and relieving asynchrony during mechanical ventilation

TLDR
Close inspection of pressure, volume and flow waveforms – displayed by modern ventilators – may help the physician to recognize and act appropriately to minimize patient–ventilator asynchrony.

Detecting ineffective triggering in the expiratory phase in mechanically ventilated patients based on airway flow and pressure deflection: Feasibility of using a computer algorithm*

TLDR
It is concluded that accurately detecting and quantifying ITEs is feasible using a computerized algorithm based on Fdef and Pdef and might be helpful for adjusting ventilator settings in an intensive care unit.

Patient-ventilator asynchrony during assisted mechanical ventilation

TLDR
One-fourth of patients exhibit a high incidence of asynchrony during assisted ventilation, which is associated with a prolonged duration of mechanical ventilation and with excessive levels of ventilatory support.