Predicting a likelihood of a fall based on walking but not talking

1 . A system comprising:

accelerometer circuitry configured to generate at least one signal indicative of a person walking;

a microphone configured to capture a voice of the person;

a memory; and

processing circuitry communicatively coupled to the accelerometer circuitry, the microphone, and the memory configured to:

determine when the person is walking based on the at least one signal;

store, in the memory, a start time and a stop time of the determined walking;

determine when the person is talking based on the captured voice;

store, in the memory, a start time and a stop time of the determined talking;

compare the start time and the stop time of the determined walking to the start time and the stop time of the determined talking;

determine an amount of overlap in the determined walking and the determined talking based on the comparison;

determine a risk of falling based on the amount of overlap in the determined walking and the determined talking; and

output an indication of the risk of falling.

2 . The system of claim 1 , wherein as part of determining when the person is talking, the processing circuitry is configured to compare the captured voice to a voice template stored in the memory.

3 . The system of claim 1 , wherein as part of determining the risk of falling, the processing circuitry is configured to determine a risk of falling score based on the determined amount of overlap.

4 . The system of claim 3 , further comprising a user interface configured to output the indication of the risk of falling, wherein to output the indication of the risk of falling, the user interface is configured to communicate the risk of falling score to a user.

5 . The system of claim 3 , further comprising communication circuitry configured to output the indication of the risk of falling, wherein to output the indication of the risk of falling, the communication circuitry is configured to transmit an alert comprising the risk of falling score to a clinician device.

6 . The system of claim 5 , wherein the processing circuitry is further configured to:

determine a new risk of falling score; and

determine a level of efficacy of an intervention of a clinician after the intervention based on the new risk of falling score,

wherein the intervention is in response to the transmitted alert.

7 . The system of claim 1 , wherein as part of determining when the person is talking, the processing circuitry is configured to continuously monitor a signal from the microphone.

8 . The system of claim 1 , wherein the processing circuitry is configured to determine the risk of falling on a periodic basis.

9 . A method comprising:

determining, by processing circuitry, when a person is walking based on at least one signal from accelerometer circuitry;

storing, in memory, a start time and a stop time of the determined walking;

determining, by processing circuitry, when the person is talking based on a captured voice from a microphone;

storing, in memory, a start time and a stop time of the determined talking;

comparing the start time and the stop time of the determined walking to the start time and the stop time of the determined talking;

determining an amount of overlap in the determined walking and the determined talking based on the comparison;

determining a risk of falling based on the amount of overlap in the determined walking and the determined talking; and

outputting an indication of the risk of falling.

10 . The method of claim 9 , wherein determining when the person is talking comprises comparing the captured voice to a voice template stored in memory.

11 . The method of claim 9 , wherein determining the risk of falling comprises determining a risk of falling score based on the determined amount of overlap.

12 . The method of claim 11 , wherein outputting the indication of the risk of falling comprises:

communicating, via a user interface, the risk of falling score to a user.

13 . The method of claim 11 , wherein outputting the indication of the risk of falling comprises:

transmitting, via communication circuitry, an alert comprising the risk of falling score to a clinician device.

14 . The method of claim 13 , further comprising:

determining a new risk of falling score; and

determining a level of efficacy of an intervention of a clinician after the intervention based on the new risk of falling score,

wherein the intervention is in response to the transmitted alert.

15 . The method of claim 9 , wherein the determining the risk of falling is performed on a periodic basis.

16 . A non-transitory computer-readable storage medium comprising instructions, that when executed by processing circuitry of a device, cause the device to:

determine when a person is walking based on at least one signal for accelerometer circuitry;

store, in a memory, a start time and a stop time of the determined walking;

determine when the person is talking based on a captured voice from a microphone;

store, in the memory, a start time and a stop time of the determined talking;

compare the start time and the stop time of the determined walking to the start time and the stop time of the determined talking;

determine an amount of overlap in the determined walking and the determined talking based on the comparison;

determine a risk of falling based on the amount of overlap in the determined walking and the determined talking; and

output an indication of the risk of falling.