Stimuli for symptom detection
AssigneeCurieAI, Inc.
InventorsRamin Anushiravani, Sridhar Krishna Nemala, Ravi Kiran Yalamanchili, Navya Swetha Davuluri
Life of this patent
Estimating the term…
Abstract
Embodiments are disclosed for health assessment and diagnosis implemented in an artificial intelligence (AI) system. In an embodiment, a method comprises: obtaining, using one or more processors of a device, a speech sample from a user uttering a first sentence; processing the speech sample through a neural network to predict a first set of one or more disease-related symptoms of the user; and generating, using the one or more processors, a second sentence to predict a second set of one or more disease-related symptoms or confirm the first set of disease-related symptoms.
Claims22
A method comprising:
- obtaining, using one or more processors of a device, a first speech recording of a pre-determined first sentence uttered by a user, the pre-determined first sentence designed to detect a pre-defined set of disease-related symptoms exhibited by the user;
- predicting, using a neural network with the first speech recording as input a first set of one or more disease-related symptoms of the user, the neural network trained on features extracted from user utterances as input and corresponding symptoms as output;
- and
- designing, using an unsupervised learning technique, a second sentence, the second sentence designed to emphasize one or more features of the first pre-determined sentence;
- obtaining a second speech recording of the second sentence uttered by the user;
- and
- processing the second speech recording through the neural network to predict symptoms using the second sentence.
A system comprising:
- one or more processors;
- memory storing instructions that when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- obtaining a first speech recording of a pre-determined first sentence uttered by a user, the pre-determined first sentence designed to detect a pre-defined set of disease-related symptoms exhibited by the user;
- predicting, using a neural network with the first speech recording as input a first set of one or more disease-related symptoms of the user, the neural network trained on features extracted from user utterances as input and corresponding symptoms as output;
- and
- designing, using an unsupervised learning technique, a second sentence, the second sentence designed to emphasize one or more features of the pre-determined first sentence;
- obtaining a second speech recording of the second sentence uttered by the user;
- and
- processing the second speech recording through the neural network to predict symptoms using the second sentence.
Dependencies are inferred from the claim text.