Inhaler system

1. A system for determining a probability of an asthma exacerbation, the system comprising:

a first inhaler configured to deliver a rescue medicament to a user, the first inhaler comprising a processor, a memory, a transceiver, and a sensor, wherein the processor of the first inhaler is configured to:

detect, via the sensor, rescue inhalations performed by the user using the first inhaler;

measure airflow parameters for each of the rescue inhalations, wherein the airflow parameter for each of the rescue inhalations from the first inhaler is at least one of a peak inhalation flow, an inhalation volume, or an inhalation duration; and

transmit, via the transceiver, indications of the airflow parameters for each of the rescue inhalations; and

an external device comprising a processor, a memory, and a transceiver, the processor of the external device configured to:

receive the indications of the airflow parameters for each of the rescue inhalations from the first inhaler,

determine the airflow parameters for each of the rescue inhalations of the first inhaler and a number of rescue inhalations performed by the user using the first inhaler;

train a machine learning model with training data that comprises a normalized number of rescue inhalations for each of a plurality of different users over a predetermined previous number of days and measured airflow parameters for each of the rescue inhalations of the plurality of different users;

determine the probability of the asthma exacerbation for the user using the trained machine learning model based on the airflow parameters for each of the rescue inhalations of the first inhaler and the number of rescue inhalations performed by the user using the first inhaler; and

generate a notification, via a display device, indicating the probability of the asthma exacerbation for the user.

2. The system of claim 1 , wherein the training data further comprises an absolute number of inhalations for each of the plurality of different users, and wherein the processor of the external device is further configured to determine, using the machine learning model, the probability of the asthma exacerbation for the user based on an absolute number of inhalations for the user.

3. The system of claim 2 , wherein the absolute number of inhalations for the user is an absolute number of inhalation for the user over the past three days.

4. The system according to claim 1 , wherein the airflow parameter comprises peak inhalation flow; and

wherein the processor of the external device is further configured to:

determine a change in peak inhalation flow for the user; and

determine, using the machine learning model, the probability of the asthma exacerbation for the user further based on the change in peak inhalation flow for the user.

5. The system of claim 1 , wherein the training data further comprises a baseline peak inhalation flow for each of the plurality of different users, and wherein the processor of the external device is further configured to:

determine a baseline peak inhalation flow for the user; and

determine, using the machine learning model, the probability of the asthma exacerbation for the user further based on a normalized peak inhalation flow for the user.

6. The system of claim 1 , wherein the airflow parameters comprise inhalation volume; and

wherein the processor of the external device is further configured to:

determine a change in inhalation volume for the user; and

determine, using the machine learning model, the probability of the asthma exacerbation for the user further based on the change in inhalation volume for the user.

7. The system of claim 1 , wherein the processor of the external device is further configured to:

determine a baseline inhalation volume for the user; and

determine, using the machine learning model, the probability of the asthma exacerbation for the user further based on a normalized inhalation volume for the user.

8. The system of claim 1 , wherein the airflow parameters comprise inhalation volumes; and

wherein the processor of the external device is further configured to:

determine a change in inhalation duration for the user; and

determine, using the machine learning model, the probability of the asthma exacerbation for the user further based on the change in inhalation duration for the user.

9. The system of claim 1 , wherein the processor of the external device is further configured to:

determine a baseline inhalation duration for the user; and

determine, using the machine learning model, the probability of the asthma exacerbation for the user further based on a normalized inhalation duration for the user.

10. The system of claim 1 , wherein the processor of the external device is further configured to:

determine that the probability of the asthma exacerbation is greater than a predetermined upper threshold; and

update a treatment regimen associated with a subject in response to the determination that the probability of the asthma exacerbation is greater than the predetermined upper threshold, wherein the updated treatment regimen comprises the administration of a biologics medication to the subject.

11. The system of claim 10 , wherein the updated treatment regimen comprises the administration of one or more of mepolizumab, reslizumab, benralizumab, or dupilumab.

12. The system of claim 1 , wherein the processor of the external device is further configured to:

receive status indications via a user interface from the user in response to a questionnaire; and

determine, using the machine learning model, the probability of the asthma exacerbation for the user further based on the received status indications.

13. The system of claim 1 , wherein the display device is comprised in a personal computer, a tablet computer, or a smart phone associated with the user.

14. The system of claim 2 , wherein the absolute number of inhalations for the user is an absolute number of inhalation for the user over the past three days.

15. The system of claim 1 , further comprising:

a second inhaler configured to deliver a maintenance medicament to the user that is delivered during routine inhalations, the second inhaler comprising a processor, a memory, a transceiver, and a sensor, wherein the processor of the second inhaler is configured to:

detect, via the sensor, routine inhalations performed by the second inhaler by the user;

measure airflow parameters for each of the routine inhalations; and

transmit, via the transceiver, indications of the airflow parameters for each of the routine inhalations; and

wherein the processor of the external device is configured to:

receive the indications of the airflow parameters for each of the routine inhalations from the second inhaler by the user; and

determine, using the machine learning model, the probability of the asthma exacerbation for the user further based on the number of routine inhalations and the airflow parameter for each of the routine inhalations, wherein the training data further comprises a number of routine inhalations and airflow parameters for each of the routine inhalations for each of the plurality of different users.

16. The system of claim 1 , wherein the processor of the external device is further configured to determine, using the machine learning model, the probability of the asthma exacerbation for the user based on a percentage change in number of rescue inhalations today for the user as compared to a previous number of days.

17. The system of claim 1 , wherein an exacerbation comprises moderate or severe clinical asthma exacerbations (CAE), wherein a severe CAE is characterized as an event that requires oral steroid for at least three days and hospitalization, and a moderate CAE is characterized as an event that requires oral steroid for at least three days or hospitalization.

18. The system of claim 1 , wherein the number of rescue inhalations from the plurality of different users has a greater importance in the machine learning model for predicting the exacerbation than the airflow parameter for each of the plurality of rescue inhalations from the plurality of different users.

19. The system of claim 16 , wherein the previous number of days is three days.

20. The system of claim 1 , wherein the display device is comprised within a personal computer of a health care professional of the user.

21. The system of claim 1 , wherein the probability of the asthma exacerbation is associated within an exacerbation period of time that is within the next one to ten days.

22. The system of claim 1 , wherein the probability of the asthma exacerbation is associated within an exacerbation period of time that is within the next five days.

23. A computer-readable medium having stored thereon instructions that, when executed by a control circuit, cause the control circuit to:

receive a plurality of airflow parameters for each of a plurality of rescue inhalations associated with a plurality of different users, wherein the airflow parameter for each of the plurality of the rescue inhalations is at least one of a peak inhalation flow, an inhalation volume, or an inhalation duration;

determine a normalized number of rescue inhalations for each of the plurality of different users over a predetermined previous number of days;

train a machine learning model with training data that comprises the normalized number rescue inhalations for each of the plurality of different users over the predetermined previous number of days and the airflow parameters for each of the plurality of rescue inhalations associate with the plurality of different users;

receive airflow parameters for each of a plurality of rescue inhalations associated with an inhaler of a user;

determine the probability of the asthma exacerbation for the user using the trained machine learning model based on the airflow parameters for each of the rescue inhalations associated with inhaler of the user and the number of rescue inhalations performed by the user using the inhaler; and

generate a notification, via a display device, indicating the probability of the asthma exacerbation for the user.

24. The computer-readable medium of claim 23 , wherein the computer-readable medium has stored thereon instructions that, when executed by the control circuit, cause the control circuit to:

determine that the probability of the asthma exacerbation is greater than a predetermined upper threshold; and

update a treatment regimen associated with a subject in response to the determination that the probability of the asthma exacerbation is greater than the predetermined upper threshold, wherein the updated treatment regimen comprises the administration of a biologics medication to the subject.

25. The computer-readable medium of claim 24 , wherein the updated treatment regimen comprises the administration of one or more of mepolizumab, reslizumab, benralizumab, or dupilumab.