| CPC G06N 5/02 (2013.01) [G06F 9/453 (2018.02); G06F 16/243 (2019.01); G06F 16/25 (2019.01); G06F 16/437 (2019.01); G06N 20/00 (2019.01); G16H 30/20 (2018.01); G16H 70/20 (2018.01)] | 17 Claims |
|
1. A computing system configured to conduct conversations with a user regarding review and analysis of medical data, the computing system comprising:
a computer processor configured to execute software instructions;
an audio input device configured to provide an audio input to the computer processor; and
one or more tangible non-transitory computer readable medium storing:
a medical knowledge database storing medical information regarding a plurality of clinical data elements, including correlations between respective medical symptoms and medical diagnoses;
a messaging backbone configured to receive messages from message producers and provide messages to message consumers; and
a plurality of compute engines including at least software code configured for execution by the computer processor, the compute engines including at least:
an utterance ingestion engine configured to convert portions of the audio input to corresponding textual input;
a conversation manager configured to dynamically update a state of a conversation between the user and the computing system;
a conversation engine configured to determine an intent of action of the user; and
a dispatcher configured to determine a first action based on the textual input, the intent of action, context of viewing activity by the user including medical images and data previously provided to the user as a result of a conversation action, information in the medical knowledge database, and the state of the conversation,
wherein the textual input includes a request for prior images of a patient represented within a currently-displayed image,
wherein the first action includes providing first speech output to the user, automatically accessing the medical knowledge base to determine images of interest to the user, automatically selecting, from image storage, a plurality of prior images of the patient, and displaying the plurality of prior images of the patient for comparison by the user,
wherein the computer processor is further configured to maintain a prioritized list of possible conversation actions, display portions of the prioritized listing in response to user input, and display at least a portion of the prioritized listing in response to a risk level to the patient exceeding a predetermined threshold, and
wherein the dispatcher is further configured to, in response to second input from the user including a workflow command determine a second action based on the second input, the second action including providing second speech output to the user prompting the user to slow down, and provide the second speech output to the user.
|