Personalized health care wearable sensor system

1. A monitoring and feedback platform comprising:

a processor;

a database containing a plurality of baseline profiles,

wherein each of said plurality of baseline profiles indexed to a physiological parameter;

a communications component configured to receive a set of physiological data collected from a wearable monitoring device including a network of sensors capable of measuring one or more physiological parameters including respiration rate and blood oxygen level;

an evaluation module configured to:

identify said measured physiological parameters;

retrieve from said database one of said plurality of baseline profiles based on said measured physiological parameters;

apply one or more machine learning algorithms to said set of physiological data;

compare said set of physiological data of said measured physiological parameters to said baseline profile retrieved from said database; and

generate a health status by comparing said measured physiological parameters to said baseline profile retrieved from said database,

wherein said health status comprises a pediatric asthma score based on said measured physiological parameters, and

wherein said measured physiological parameters comprise respiratory rate and pulse oximetry.

2. The monitoring and feedback platform of claim 1 , wherein the evaluation module generates an alert sent to a monitoring device when said health status falls below a threshold, said threshold automatically set by said evaluation module based on nonnative variation in said baseline profile.

3. The monitoring and feedback platform of claim 1 , further comprising an analysis engine to aggregate baseline profiles from multiple users and a machine learning algorithm applied to identify key variables that would change the health status.

4. The monitoring and feedback platform of claim 1 , wherein said measured physiological parameter further includes one or more of: heart rate, body moisture, and body temperature.

5. The monitoring and feedback platform of claim 4 , collecting environmental data including one more of: environmental particulate data, ambient air temperature data, and geospatial location data.

6. The monitoring and feedback platform of claim 1 , wherein said predicted pediatric asthma score based on said measured physiological parameters of respiration rate and blood oxygen level and by applying said machine learning algorithm, as follows:

f

=

∑

6

i

=

1

⁢

w

i

⁢

f

i

∑

6

i

=

1

⁢

w

i

wherein

f=w 1 f 1 +w 2 f 2

w 1 =μ 1 ( p 1 )*μ 1 ( p 2 )

w 2 =μ 2 ( p 1 )*μ 2 ( p 2 )

and wherein each of the input data measurements has membership weight value (wi) calculated:

w

i

=

∏

j

=

1

⁢

μ

⁡

(

P

⁢

j

)

wherein μ(p 1 ) comprises a membership function, wherein:

p 1 is the measurement value of RR, wherein RR is input 1 (in1)

p 2 is the measurement value of SpO2, wherein SpO2 is input 2 (in2), and wherein:

If p 1 is in1cluster1 and SpO2 is in2cluster1, then f 1 =μ 1 ( p 1 ) p 1 +μ 1 ( p 2 ) p 2 +r 1

If p 1 is in1cluster2 and SpO2 is in2cluster2, then f 2 =μ 2 ( p 1 ) p 1 +μ 2 ( p 2 ) p 2 +r 2

wherein μ 1 (p 1 ) is the membership function of input p1 or input 1 in said cluster 1; and

wherein μ 2 (p 1 ) is the membership function of input p1 or input 1 in said cluster 2.

7. The monitoring and feedback platform of claim 1 , wherein said predicted pediatric asthma score based on said measured physiological parameters comprising: blood oxygen level, fraction of inspired oxygen, heart rate, and respiratory rate, and wherein each of said physiological parameters includes a plurality of data measurements having a membership in one of a plurality of clusters, and wherein the machine learning algorithm is applied to the data measurements based on membership within said plurality of clusters to obtain a final output, as follows:

f

=

∑

6

i

=

1

⁢

w

i

⁢

f

i

∑

6

i

=

1

⁢

w

i

and wherein each of the input data measurements each have a membership weight value (wi) calculated:

w

i

=

∏

j

=

1

6

⁢

μ

i

⁡

(

p

j

)

.

8. A monitoring and feedback platform, comprising:

a processor;

a database containing a plurality of baseline profiles,

wherein each of said plurality of baseline profiles indexed to a physiological parameter;

a communications component configured to:

collect environmental data from an external monitoring station, wherein said environmental data includes concentration of oxygen in the air;

collect a set of physiological data from a wearable monitoring device including a network of sensors capable of measuring one or more physiological parameters including respiration rate, blood oxygen level, and fraction of inspired oxygen;

an evaluation module configured to:

identify measured physiological parameters, wherein said measured physiological parameters comprise respiration rate and blood oxygen level based on said physiological data collected from said wearable monitoring device, and fraction of inspired oxygen based on the said environmental data collected from said external monitoring station;

retrieve from said database one of said plurality of baseline profiles based on said measured physiological parameters;

apply one or more machine learning algorithms to said set of physiological data;

compare said set of physiological data of said one or more measured physiological parameters to said baseline profile retrieved from said database; and

generate a health status by comparing said measured physiological parameters to said baseline profile retrieved from said database.

9. The monitoring and feedback platform of claim 8 , wherein health status comprises a predicted pediatric asthma score.

10. The monitoring and feedback platform of claim 9 , wherein said predicted pediatric asthma score based on said measured physiological parameters of respiration rate and blood oxygen level and by applying said machine learning algorithm, as follows:

f

=

∑

6

i

=

1

⁢

w

i

⁢

f

i

∑

6

i

=

1

⁢

w

i

wherein

f=w 1 f 1 +w 2 f 2

w 1 =μ 1 ( p 1 )*μ 1 ( p 2 )

w 2 =μ 2 ( p 1 )*μ 2 ( p 2 )

and wherein each of the input data measurements has membership weight value (w calculated:

w

i

=

∏

j

=

1

⁢

μ

⁡

(

P

⁢

j

)

wherein μ(p j ) comprises a membership function, wherein:

p 1 is the measurement value of RR, wherein RR is input 1 (in1)

p 2 is the measurement value of SpO2, wherein SpO2 is input 2 (in2), and wherein:

If p 1 is in1cluster1 and SpO2 is in2cluster1, then f 1 =μ 1 ( p 1 ) p 1 +μ 1 ( p 2 ) p 2 +r 1

If p 1 is in1cluster2 and SpO2 is in2cluster2, then f 2 =μ 2 ( p 1 ) p 1 +μ 2 ( p 2 ) p 2 +r 2

wherein μ 1 (p 1 ) is the membership function of input p1 or input 1 in said cluster 1; and

wherein μ 2 (p 1 ) is the membership function of input p1 or input 1 in said cluster 2.

11. The monitoring and feedback platform of claim 9 , wherein said predicted pediatric asthma score based on said measured physiological parameters comprising: blood oxygen level, fraction of inspired oxygen, heart rate, and respiratory rate, and wherein each of said physiological parameters includes a plurality of data measurements having a membership in one of a plurality of clusters, and wherein the machine learning algorithm is applied to the data measurements based on membership within said plurality of clusters to obtain a final output, as follows:

f

=

∑

6

i

=

1

⁢

w

i

⁢

f

i

∑

6

i

=

1

⁢

w

i

and wherein each of the input data measurements each have a membership weight value (wi) calculated:

w

i

=

∏

j

=

1

6

⁢

μ

i

⁡

(

p

j

)

.