Ayappa
Indu Ayappa, New York, NY US
Patent application number | Description | Published |
---|---|---|
20160022938 | MULT-NIGHT TITRATION PRESSURE DETERMINATION - A multi-night titration (MNT) process to find an optimal single therapeutic pressure of a CPAP device. This single therapeutic pressure can then be used on an on-going basis by the patient after the titration period. The MNT process differs from current auto adjusting processes used for titration (or ongoing use) in that the MNT process does not respond locally by adjusting pressures to individual events. With existing devices, the continuous adjustment of supplied air pressure always responds to one or a small number of events and thus fails to compensate for a patient's adaptation thereto, resulting in the supply of a less than optimal therapeutic pressure to the patient. While auto adjusting processes often capture and respond well to short-term and transient conditions, the MNT process of the current disclosure seeks to capture long term trends and find the most suitable average single pressure for a patient. | 01-28-2016 |
Indu A. Ayappa, New York, NY US
Patent application number | Description | Published |
---|---|---|
20090139523 | System and Method for Automated Titration of Continuous Positive Airway Pressure Using an Obstruction Index - Described is a system including an air pressure supply arrangement, a sensor and a titration device. The air pressure supply arrangement provides air pressure to a patient's airways. The sensor detects input data corresponding to a patient's breathing patterns of a plurality of breaths. The titration device receives and analyzes the input data to determine existence of breathing disorder and corresponding characteristics. The titration device generates output data for adjusting the air pressure supplied to the patient as a function of an index of abnormal respiratory events included in the input data. | 06-04-2009 |
20120010519 | System and Method for Diagnosis and Treatment of Obstructive Sleep Apnea - A system for diagnosis and treatment of breathing disorders in a patient, comprises a flow generator supplying an air flow to an airway of a patient via a flow path, a venting arrangement moveable between (i) a closed position in which the flow path is substantially sealed between the flow generator and the patient's airway and (ii) an open position in which the flow path is open to an ambient atmosphere, a sensor detecting data corresponding to flow through the patient's airway, and a processing arrangement controlling operation of the venting arrangement and the flow generator, wherein, in a diagnostic mode, the processing arrangement maintains the venting arrangement in the open position and in a therapeutic mode, the processing arrangement maintains the venting arrangement in the closed position and controls the flow generator to supply to the patient's airway via the flow path a calculated therapeutic pressure. | 01-12-2012 |
Pooviah Ballachanda Ayappa, Bangalore IN
Patent application number | Description | Published |
---|---|---|
20150199609 | SELF-LEARNING SYSTEM FOR DETERMINING THE SENTIMENT CONVEYED BY AN INPUT TEXT - A self learning system and a method for analyzing the sentiments conveyed by an input text have been disclosed. The system includes a generator that generates an initial training set comprising a plurality of words linked to corresponding sentiments. The words and corresponding sentiments are stored in a repository. A rule based classifier segregates the input text into individual words, and compares the words with the entries in the repository, and subsequently determines a first score corresponding to the input text. The input text is also provided to a machine-learning based classifier that generates a plurality of features corresponding to the input text and subsequently generates a second score corresponding to the input text. The first score and the second score are further aggregated by an ensemble classifier which further generates a classification score indicative of the sentiment conveyed by the input text. | 07-16-2015 |