Personal emergency response system with predictive emergency dispatch risk assessment

• US 10,181,252 B2
• Filed: 06/09/2015
• Issued: 01/15/2019
• Est. Priority Date: 06/11/2014
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Pauws, Steffen Clarence, Nassabi, Mohammad Hossein, Schertzer, Linda, Smits, Tine, Op Den Buijs, Jorn, Van Deursen, Patrick William
• Primary Examiner(s): Torres, Marcos
• Application Number:
  US15/317,440
• Publication Number:
  US 20170124852A1
• Time in Patent Office: 1,316 Days
• CPC Class Codes: G08B 25/016 Personal emergency signalling and security systems emergency non-personal manually actuated alarm activators G08B25/12
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 80/00 ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04W 4/90 Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]

Abstract

In a Personal Emergency Response System (PERS) service, activation of a wearable call device (10) by a PERS client causes a speakerphone console (12) to connect with a PERS call center (18) to enable the PERS client to converse with a call center operator while a PERS client profile is retrieved from a PERS database (52) and displayed on a display component (44) at the PERS call center. From the profile, values of a set of features are generated for the PERS client. An emergency dispatch risk prediction or other risk prediction is computed over a future time horizon for the PERS client based on the generated values of the set of features, and is displayed on the display component. The risk prediction may be wirelessly sent to a mobile device (80) for display on the mobile device.

Claims

1. A Personal Emergency Response System operating in conjunction with a Personal Emergency Response System (PERS) database storing profiles for PERS clients including at least demographic information and information on past calls to a PERS call center wherein the information on past calls includes information on past emergency dispatch events initiated by the PERS call center, the Personal Emergency Response System comprising:

a PERS server system comprising a PERS server computer programmed to perform operations including;

retrieving a profile of a given PERS client from the PERS database;

generating values of a set of features for the given PERS client, based on the retrieved profile of the given PERS client, wherein the set of features includes at least one emergency dispatch event recency feature;

computing, based on the values of the set of features, an emergency dispatch risk prediction for the PERS client over a future time horizon using an emergency dispatch risk regression model trained on the profiles for the PERS clients stored in the PERS database;

receiving one or more incoming calls from one or more PERS clients, including a call from the given PERS client;

ranking the one or more incoming calls from the one or more PERS clients, including the given PERS client, based on the emergency dispatch risk prediction;

prioritizing, based on the ranking, an automated allocation of emergency resources to the one or more PERS clients, including the given PERS client; and

automatically allocating the emergency resources in accordance with the prioritizing.

2. The Personal Emergency Response System of claim 1 further comprising:

a PERS call center computer including a display component;

wherein the PERS server computer is programmed to perform the further operation of communicating the computed emergency dispatch risk prediction and a portion or all of the profile retrieved in retrieving a profile of the given PERS client from the PERS database to the PERS call center computer; and

wherein the PERS call center computer is programmed to display on the display component of the PERS call center computer the computed emergency dispatch risk prediction and the communicated portion or all of the profile.

3. The Personal Emergency Response System of claim 2 further comprising:

a plurality of wearable call devices; and

a plurality of speakerphone consoles disposed in residences of PERS clients wherein each speakerphone console is wirelessly activated by a corresponding one of the wearable call devices;

wherein the speakerphone consoles are telephonically connected with the PERS call center to enable a PERS client to converse with an operator at the PERS call center.

4. The Personal Emergency Response System of claim 1 wherein the PERS server computer is programmed to perform the further operations of:

repeating the retrieving, generating, and computing steps further to compute emergency dispatch risk predictions over the future time horizon for a population of PERS clients whose profiles are stored in the PERS database;

ranking the PERS clients to identify a sub-set of the population of PERS clients having the highest computed emergency dispatch risk predictions; and

at least one of displaying and printing a hard copy of the identified sub-set of the population of PERS clients having the highest computed emergency dispatch risk predictions.

5. The Personal Emergency Response System of claim 1 wherein the PERS server computer is programmed to perform the further operations of:

repeating the retrieving, generating, and computing steps further to compute emergency dispatch risk predictions over the future time horizon for a population of PERS clients whose profiles are stored in the PERS database;

computing an expected number of PERS clients with one or more emergency dispatch events over the future time horizon for the population or subset of the population of PERS clients based on the computed emergency dispatch predictions for the population of PERS clients; and

at least one of displaying and printing a hard copy of the expected number of subscribers with one or more emergency dispatch events over the future time horizon for the population of PERS clients.

6. The Personal Emergency Response System of claim 1 wherein the set of features further includes at least one emergency dispatch event frequency feature.

7. The Personal Emergency Response System of claim 1 wherein the set of features includes a plurality of different emergency dispatch event recency features, each different emergency dispatch event recency feature indicating recency of an emergency dispatch for a different type of medical event.

8. The Personal Emergency Response System of claim 1 wherein the set of features further includes a check-in call frequency feature and the emergency dispatch risk regression model is trained to positively correlate a higher check-in call frequency with a higher emergency dispatch risk prediction.

9. The Personal Emergency Response System of claim 1 wherein the set of features further includes an accidental call frequency feature and the emergency dispatch risk regression model is trained to positively correlate a higher accidental call frequency with a higher emergency dispatch risk prediction.

10. The method of claim 1, wherein prioritizing, based on the ranking, the automated allocation of emergency resources includes prioritizing incoming calls to the PERS call center.

11. The method of claim 1, wherein prioritizing, based on the ranking, the automated allocation of emergency resources includes prioritizing incoming calls to an Emergency Dispatch.

12. The method of claim 1, wherein prioritizing, based on the ranking, the automated allocation of emergency resources includes prioritizing incoming calls to the Emergency Medical Service vehicles.

13. A method performed in conjunction with a Personal Emergency Response System (PERS) service in which activation of a wearable call device by a PERS client causes a speakerphone console to connect with a PERS call center to enable the PERS client to converse with an operator at the PERS call center while a profile of the PERS client is retrieved from a PERS database and information contained in the profile is displayed on a display component at the PERS call center, the method comprising:

retrieving the profile of a given PERS client from the PERS database;

generating values of a set of features for the given PERS client using a computer, based on the retrieved profile of the given PERS client;

computing, based on the values of the set of features, an emergency dispatch risk prediction for the given PERS client over a future time horizon using an emergency dispatch risk regression model and the generated values of the set of features for the given PERS client using the computer; and

displaying on the display component the computed emergency dispatch risk prediction for the given PERS client together with the displayed information contained in the profile;

receiving one or more incoming calls from one or more PERS clients, including a call from the given PERS client;

ranking the one or more incoming calls from the one or more PERS clients, including the given PERS client, based on the emergency dispatch risk prediction;

prioritizing, based on the ranking, an automated allocation of emergency resources to the one or more PERS clients, including the given PERS client; and

automatically allocating the emergency resources based on the prioritizing of the automated allocation of emergency resources.

14. The method of claim 13 wherein the computing further includes computing one of:

a risk prediction that the PERS client will require an emergency dispatch of an emergency medical service (EMS) vehicle over the future time horizon;

a risk prediction that the PERS client will require an emergency dispatch in which the PERS client is transported to a hospital over the future time horizon;

or

a risk prediction that the PERS client will be admitted to a full-time care facility over the future time horizon.

15. The method of claim 13 wherein:

the generating further includes generating a value for at least one feature quantifying past emergency dispatch for the PERS client initiated by the PERS call center; and

the computing further includes computing an emergency dispatch risk prediction using an emergency dispatch risk regression model configured to receive as input values of the set of features including the at least one feature quantifying past emergency dispatch for the PERS client initiated by the PERS call center.

16. The method of claim 15 wherein the at least one feature quantifying past emergency dispatch for the given PERS client initiated by the PERS call center includes:

an emergency dispatch event recency feature quantifying time since the last emergency dispatch event for the given PERS client initiated by the PERS call center; and

an emergency dispatch event frequency feature quantifying a number or frequency of emergency dispatch events for the given PERS client initiated by the PERS call center.

17. The method of claim 16 wherein:

the generating further includes generating a value for a check-in call frequency feature quantifying a number or frequency of check-in calls made by the PERS client to the PERS call center (18); and

the computing further includes computing the emergency dispatch risk prediction using the emergency dispatch risk regression model configured to receive as input values of the set of features further including the check-in call frequency feature, wherein the emergency dispatch risk regression model positively correlates a higher number or frequency of check-in calls with higher emergency dispatch risk prediction.

18. The method of claim 16 wherein:

the generating further includes generating a value for an accidental call frequency feature quantifying a number or frequency of accidental calls made by the PERS client to the PERS call center; and

the computing further includes computing the emergency dispatch risk prediction using the emergency dispatch risk regression model configured to receive as input values of the set of features further including the accidental call frequency feature, wherein the emergency dispatch risk regression model positively correlates a higher number or frequency of accidental calls with higher emergency dispatch risk prediction.