Fall prediction based on electroencephalography and gait analysis data
A method, a computer-readable storage device, and an apparatus for predicting a fall are disclosed. In one example, a method performed by a processor deployed in a communications network includes collecting gait information associated with a user from a first wearable device worn by the user, collecting electroencephalography information associated with the user from a second wearable device worn by the user, calculating a likelihood that the user will fall within a threshold period of time from a current time, wherein the calculating is based on a combination of the gait information and the electroencephalography information; and sending an instruction to an endpoint device associated with the user when the likelihood exceeds a predefined threshold, wherein the instruction instructs the endpoint device to generate an alert alerting the user that a fall is likely.
1. A method, comprising:
collecting, by a processor deployed in a communications network, gait information associated with a user from a first wearable device worn by the user;
collecting, by the processor, electroencephalography information associated with the user from a second wearable device worn by the user;
calculating, by the processor, a likelihood that the user will fall within a threshold period of time from a current time, wherein the calculating is based on a combination of the gait information and the electroencephalography information, wherein the likelihood is calculated as (|L b −L u |)*(|S b −S u |)*(|A b −A u |)*(|O b −O u |), where L b represents a baseline stride length, L u represents a stride length of the user, S b represents a baseline speed for a mode of motion indicated by the gait information, S u represents a speed of the user, A b represents a baseline acceleration for the mode of motion, A u represents an acceleration of the user, O b represents a baseline neural oscillation, and O u represents a neural oscillation of the user; and
sending, by the processor, an instruction to an endpoint device associated with the user when the likelihood exceeds a predefined threshold, wherein the instruction instructs the endpoint device to generate an alert alerting the user that a fall is likely.
2. The method of claim 1 , wherein the first wearable device comprises an insole worn in a shoe of the user.
3. The method of claim 2 , wherein the insole comprises a plurality of force resisting sensors.
4. The method of claim 1 , wherein the second wearable device comprises an electroencephalography headset worn on a head of the user.
5. The method of claim 4 , wherein the electroencephalography headset comprises a plurality of electrodes.
6. The method of claim 1 , wherein at least one of the first wearable device and the second wearable device includes a notification means for generating the alert.
7. The method of claim 1 , wherein the gait information comprises a raw measurement of at least one of: pressure information, acceleration information, gyroscopic information, elevation information, a time, a temperature, and a fluid content.
8. The method of claim 1 , wherein the electroencephalography information comprises a raw measurement of at least one of: brain electrical activity, acceleration information, gyroscopic information, elevation information, a time, and a location.
9. The method of claim 1 , wherein the calculating the likelihood further accounts for at least one physical characteristic of the user.
10. The method of claim 9 , wherein the at least one physical characteristic comprises at least one of: a height of the user, a weight of the user, a body mass index of the user, an age of the user, and a known medical condition of the user.
11. The method of claim 1 , wherein at least one selected from a group of: the baseline stride length, the baseline speed for the mode of motion, the baseline acceleration for the mode of motion, and the baseline neural oscillation is user-specific.
12. The method of claim 1 , wherein the baseline neural oscillation is associated with a specific health condition.
13. The method of claim 1 , wherein the predefined threshold is specific to the user.
14. The method of claim 1 , wherein the predefined threshold is specific to the mode of motion.
15. The method of claim 1 , wherein the predefined threshold is specific to a known health condition of the user.
16. The method of claim 1 , wherein (|L b −L u |), (|S b −S u |), (|A b −A u |), and (|O b −O u |), are assigned different weights that are specific to the user.
17. The method of claim 1 , wherein (|L b −L u |), (|S b −S u |), (|A b −A u |), and (|O b −O u |), are assigned different weights that are specific to the mode of motion.
18. The method of claim 1 , wherein (|L b −L u |), (|S b −S u |), (|A b −A u |), and (|O b −O u |), are assigned different weights that are specific to a known health condition of the user.
19. A non-transitory computer-readable storage device storing instructions which, when executed by a processor deployed in a communication network, cause the processor to perform operations, the operations comprising:
collecting gait information associated with a user from a first wearable device worn by the user;
collecting electroencephalography information associated with the user from a second wearable device worn by the user;
calculating a likelihood that the user will fall within a threshold period of time from a current time, wherein the calculating is based on a combination of the gait information and the electroencephalography information, wherein the likelihood is calculated as (|L b −L u |)*(|S b −S u |)*(|A b −A u |)*(|O b −O u |), where L b represents a baseline stride length, L u represents a stride length of the user, S b represents a baseline speed for a mode of motion indicated by the gait information, S u represents a speed of the user, A b represents a baseline acceleration for the mode of motion, A u represents an acceleration of the user, O b represents a baseline neural oscillation, and O u represents a neural oscillation of the user; and
sending an instruction to an endpoint device associated with the user when the likelihood exceeds a predefined threshold, wherein the instruction instructs the endpoint device to generate an alert alerting the user that a fall is likely.
20. An apparatus, comprising:
a processor deployed in a communication network; and
a non-transitory computer-readable medium storing instructions which, when executed by the processor, cause the processor to perform operations, the operations comprising:
collecting gait information associated with a user from a first wearable device worn by the user;
collecting electroencephalography information associated with the user from a second wearable device worn by the user;
calculating a likelihood that the user will fall within a threshold period of time from a current time, wherein the calculating is based on a combination of the gait information and the electroencephalography information, wherein the likelihood is calculated as (|L b −L u |)*(|S b −S u |)*(|A b −A u |)*(|O b −O u |), where L b represents a baseline stride length, L u represents a stride length of the user, S b represents a baseline speed for a mode of motion indicated by the gait information, S u represents a speed of the user, A b represents a baseline acceleration for the mode of motion, A u represents an acceleration of the user, O b represents a baseline neural oscillation, and O u represents a neural oscillation of the user; and
sending an instruction to an endpoint device associated with the user when the likelihood exceeds a predefined threshold, wherein the instruction instructs the endpoint device to generate an alert alerting the user that a fall is likely.