Method and system for computer-aided triage of stroke
A system for computer-aided triage includes a router, a remote computing system, and a client application. Additionally or alternatively, the system 100 can include any number of computing systems, servers, storage, lookup table, memory, and/or any other suitable components. A method for computer-aided triage includes receiving a data packet associated with a patient and taken at a first point of care; checking for a suspected condition associated with the data packet; in an event that the suspected condition is detected, determining a recipient based on the suspected condition; and transmitting information to a device associated with the recipient.
1 . A method, comprising:
generating a set of trained models, comprising:
performing a first training process, comprising training the set of trained models based on a first set of images labeled as positive with respect to a hemorrhage and a second set of images labeled as negative with respect to a hemorrhage;
processing a third set of images using the set of trained models to produce a set of outputs, wherein the set of outputs comprises a set of false positive hemorrhage determinations; and
updating the set of trained models by performing a second training process, comprising training the set of trained models based on the third set of images;
receiving a set of images associated with a patient;
processing the set of images with the set of trained models to detect a suspected hemorrhage, wherein, prior to processing the set of images with the set of trained models, an exclusion criterion is evaluated based on the set of images, comprising checking for a false positive hemorrhage determination caused by a non-physiological event; and
in response to detecting the suspected hemorrhage, triggering an action, the action operable to improve an efficiency of triage of the patient.
2 . The method of claim 1 , wherein training the set of trained models based on the third set of images comprises labeling the third set of images based on the set of false positive hemorrhage determinations and training the set of trained models based on the labeled third set of images.
3 . The method of claim 1 , wherein generating the set of trained models further comprises identifying that the set of outputs comprises the set of false positive determinations.
4 . The method of claim 3 , wherein the set of false positive determinations are identified based on an input from a specialist.
5 . The method of claim 1 , wherein the suspected hemorrhage comprises at least one of: an intracerebral hemorrhage, an intraventricular hemorrhage, an extradural hemorrhage, or a subdural hemorrhage.
6 . The method of claim 1 , wherein the set of trained models comprises a convolutional neural network.
7 . The method of claim 1 , wherein the action is triggered at a user device associated with a specialist.
8 . The method of claim 1 , wherein receiving the set of images, processing the set of images, and triggering the action are performed during triage of the patient.
9 . The method of claim 1 , wherein the second training process is performed after the first training process.
10 . The method of claim 1 , wherein the set of images associated with the patient comprise a set of non-contrast computed tomography (NCCT) images.
11 . A system, comprising:
a computing system, wherein the computing system:
receives a set of images associated with a patient;
automatically detects a potential brain hemorrhage from the set of images using a set of trained models, wherein, prior to detecting the potential brain hemorrhage from the set of images using the set of trained models, an exclusion criterion is evaluated based on the set of images, comprising checking for a false positive hemorrhage determination caused by a non-physiological event;
identifies a set of specialists based on based on the potential brain hemorrhage; and
transmits, to each application of a set of applications, a notification and a set of compressed images based on the set of images; and
the set of applications, each application executing on a mobile user device and associated with a specialist in the set of specialists, wherein each application is configured to display the notification, wherein each application comprises:
a viewer displaying the set of compressed images; and
a messaging center configured to transmit messages between specialists in the set of specialists.
12 . The system of claim 11 , wherein automatically detecting the potential brain hemorrhage from the set of images comprises: segmenting a hyperdense region from the set of images using the set of trained models; and calculating a volume of the segmented hyperdense region.
13 . The system of claim 12 , wherein the volume of the segmented hyperdense region is displayed at the set of applications.
14 . The system of claim 12 , wherein the potential brain hemorrhage is detected upon determining that the volume exceeds a predetermined volume threshold.
15 . The system of claim 14 , wherein the predetermined volume threshold is a value between 0.1 mL and 0.4 mL.
16 . The system of claim 11 , wherein the set of images are recorded during triage of the patient at a first point of care, wherein an application in the set of applications is configured to receive an input from a specialist associated with a second point of care remote from the first point of care, wherein a transfer of the patient from the first point of care to the second point of care is initiated based on the input from the specialist.
17 . The system of claim 11 , wherein the set of images are associated with a first time, wherein the computing system is further configured to:
receive a second set of images associated with the patient, the second set of images associated with a second time, wherein the potential brain hemorrhage has progressed between the first time and the second time; and
determine a comparison based on the first set of images and the second set of images.
18 . The system of claim 11 , wherein the computing system is further configured to receive a read receipt upon a specialist in the set of specialists opening the notification.
19 . The system of claim 11 , wherein the potential brain hemorrhage comprises at least one of: an intracerebral hemorrhage, an intraventricular hemorrhage, an extradural hemorrhage, or a subdural hemorrhage.
20 . The system of claim 11 , wherein the set of images associated with the patient comprise a set of non-contrast computed tomography (NCCT) images.