Methods and apparatus for ventilatory treatment of respiratory disorders

    公开(公告)号:US11452829B2

    公开(公告)日:2022-09-27

    申请号:US16461556

    申请日:2017-11-17

    申请人: ResMed Pty Ltd

    发明人: David John Bassin

    摘要: Disclosed is an apparatus for treating a respiratory disorder in a patient. The apparatus comprises a pressure generator configured to deliver a flow of air at positive pressure to an airway of the patient through a patient interface, a sensor configured to generate a signal representative of respiratory flow rate of the patient, and a controller. The controller is configured to control the pressure generator to deliver ventilation therapy having a base pressure and a pressure support through the patient interface, detect an apnea from the signal representative of respiratory flow rate of the patient, control the pressure generator to deliver one or more probe breaths to the patient during the apnea, determine patency of the patient's airway from a waveform of the respiratory flow rate signal in response to one of the one or more probe breaths, compute an effective duration of the apnea based on the patency of the airway, and adjust a set point for the base pressure of the ventilation therapy in response to the apnea based on the effective duration of the apnea.

    LEARNING PARAMETERS OF BAYESIAN NETWORK USING UNCERTAIN EVIDENCE

    公开(公告)号:US20220172091A1

    公开(公告)日:2022-06-02

    申请号:US17107984

    申请日:2020-12-01

    IPC分类号: G06N7/02 G06N20/00 G06N7/00

    摘要: A method, system, and computer program product for learning parameters of Bayesian network using uncertain evidence, the method comprising: receiving input comprising graph representation and at least one sample of a Bayesian network, the graph comprising plurality of nodes representing random variables and plurality of directed edges representing conditional dependencies, wherein each of the at least one sample comprising for each node a value selected from the group consisting of: a known value; an unknown value; and an uncertain value; and applying on the input a Bayesian network learning process configured for calculating estimates of conditional probability tables of the Bayesian network using probabilities inferred by applying on the input a Bayesian network uncertain inference process configured for performing inference in a Bayesian network from uncertain evidence.