# US 2020/0390399 A1 · Method and apparatus providing an ongoing and real time indicator for survival and major medical events

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0390399 A1
- Document ID: US20200390399A1
- Status: Published application
- Kind: A1
- Application number: 16/900,961
- Filed: 2020-06-14
- Published: 2020-12-17
- Earliest claimed: 2019-06-14
- Assignees: AiCare Corporation
- Applicants: AiCare Corporation
- Inventors: John Fee; Chih-Hao Liu; Phillip C. Yang; Alokkumar Jha
- Web page: https://patentgrep.com/patent/US20200390399A1

## CPC

- A61B 5/7275: {Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor}
- A61B 5/0022: {Monitoring a patient using a global network, e.g. telephone networks, internet}
- A61B 5/02055: {Simultaneously evaluating both cardiovascular condition and temperature}
- A61B 5/4836: {Diagnosis combined with treatment in closed-loop systems or methods (A61B5/0036 takes precedence)}
- A61B 5/4839: {combined with drug delivery}
- A61B 5/486: {Biofeedback (using electroencephalography [EEG] A61B5/375)}
- A61B 5/7267: {involving training the classification device}
- A61B 5/746: {Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms}
- A61B 5/7475: {User input or interface means, e.g. keyboard, pointing device, joystick}
- G16H 40/67: for remote operation
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/30: for calculating health indices; for individual health risk assessment
- A61B 5/1118: {Determining activity level}
- A61B 5/332: Portable devices specially adapted therefor
- A61B 2503/08: Elderly
- A61B 2560/0214: of power generation or supply
- A61B 2562/0219: Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

The present invention includes a method and apparatus providing an ongoing and real time indicator for prediction of health conditions during the usual lifetime of a person by providing an ongoing and real time indicator for predicting remaining lifetimes for one or more patients comprising: providing a monitoring system connected to the cloud, a Wi-Fi or Bluetooth network which is connected to a wearable device; and providing a wearable device which contains one or more accelerometers, temperature monitoring devices, EKG monitoring devices and other useful devices; wherein the wearable device is powered internally by a battery or other such appropriate energy sources.

## Claims

### Claim 1

A method for providing an ongoing and real time indicator for predicting remaining lifetime or risk of health deterioration for one or more patients comprising:
providing a monitoring system connected to the cloud, a Wi-Fi or Bluetooth network which is connected to a wearable device; and
providing a wearable device which contains one or more accelerometers, temperature monitoring devices, EKG monitoring devices and other useful devices;
wherein the wearable device is powered internally by a battery or other such appropriate energy sources.

### Claim 2 (depends on 1)

The method of claim 1, further comprising defining the energy difference as daytime energy minus nighttime energy.

### Claim 3 (depends on 1)

The method of claim 1, further comprising defining the day and night active percentage differences as the change in daytime activity level percentage minus the change in nighttime activity percentage.

### Claim 4 (depends on 1)

The method of claim 1, further comprising defining the net daytime active percentage level as the daytime activity percentage minus the daytime resting percentage.

### Claim 5 (depends on 1)

The method of claim 1, further comprising providing sliding windows for any number of consecutive seconds, minutes, hours, days, week, two weeks, months, or years and any other combination or sub division of these time periods.

### Claim 6 (depends on 1)

The method of claim 1, further comprising optimizing the correlation coefficient R squared and slope using different time sampling windows and/or data distribution sampling rates.

### Claim 7 (depends on 1)

The method of claim 1, further comprising using the slope and r2 value from linear regression model are being updated weekly, and the final slope and r2 value for data analysis will be obtained after the third week cycled.

### Claim 8 (depends on 1)

The method of claim 1, further comprising providing sliding windows for any number of consecutive sub seconds two weeks, months, or years and any other combination or sub division of these time periods.

### Claim 9 (depends on 1)

The method of claim 1, further comprising optimizing the correlation coefficient R squared value (or adjusted R-squared value) and slope using different sampling windows and/or data sampling rates.

### Claim 10

A device comprising:
accelerometers for one gravity (1G), two gravity (2G) and three gravity (3G) measurement capabilities;
wherein the accelerometers are capable to monitoring in any continuous time basis from the sub millisecond or microsecond range up to days weeks or months or more; and
apply a sliding or moving window from sub seconds to days or weeks or months or more, and to apply calculations to the raw data generated by the accelerometers;
having an ability to monitor day, night, activity levels of the patient; and
an ability to monitor little to no day, night activity levels of the patient.

### Claim 11 (depends on 10)

The device of claim 10, wherein the capability of transmitting the moving window data from microseconds increments to days or weeks or months to the cloud or the Wi-Fi or Bluetooth device containing storage of the raw or timestamped data.

### Claim 12 (depends on 10)

The device of claim 10, wherein the device is capable of timestamping the data in any incremental size as needed.

### Claim 13 (depends on 10)

The device of claim 10, wherein the device is capable of calculating activity levels such as daytime active percentage, daytime resting percentage, nighttime active percentage, and nighttime resting percentage.

### Claim 14 (depends on 10)

The device of claim 10, wherein the device is capable of providing and measure daytime energy levels and nighttime energy levels.

### Claim 15 (depends on 10)

The device of claim 10, wherein the device is capable of providing high daytime and low night time resting energy levels, resting percentage of daytime energy, high day time percentage levels and low daytime resting percentage, Low night time active percentage levels, activity or movement percentage levels, absolute moving percentage levels, R squared and negative slope Night time energy level increase, daytime activity percentage, nighttime activity percentage, the intersection of any and all of either energy levels or percentage levels, the daytime or nighttime active percentage levels going below the 0% level, the high daytime activity percentage levels plus low day time resting levels, low nighttime active percentage+high nighttime percentage resting levels.

### Claim 16 (depends on 10)

The device of claim 10, wherein the device is capable of defining morning, noon, night or any other such definition and description of a particular energy level in a predetermined time period.

### Claim 17 (depends on 10)

The device of claim 10, wherein the device is capable of defining the energy difference as daytime energy minus nighttime energy.

### Claim 18 (depends on 10)

The device of claim 10, wherein the device is capable of defining the day and night active percentage differences as the change in daytime activity level percentage minus the change in nighttime activity percentage.

### Claim 19 (depends on 10)

The device of claim 10, wherein the device is capable of defining the net daytime active percentage level as the daytime activity percentage minus the daytime resting percentage.

### Claim 20 (depends on 10)

The device of claim 10, wherein the device is capable of providing sliding windows for any number of consecutive sub seconds two weeks, months, or years and any other combination or sub division of these time periods.

### Claim 21 (depends on 10)

The device of claim 10, wherein the device is capable of optimizing the correlation coefficient R squared and slope using different sampling windows and/or data sampling rates.

### Claim 22 (depends on 10)

The device of claim 10, wherein the device is able to use exponential regression using linear model, linear regression, moving averages of any type and sampling rates of any type and the usage of any of the regression and moving averages to provide additional analyzable results.

### Claim 23 (depends on 10)

The device of claim 10, wherein the device is capable of recalling any of the fit algorithms and or sampling size to apply as the optimum solution for the sampled data set from the accelerometers.

### Claim 24 (depends on 10)

The device of claim 10, wherein the device is capable of using the combinations of any of the above plus other such capabilities to predict the last living days of a senior.

### Claim 25

An apparatus for providing an ongoing in real-time indicator for prediction of survival, major medical events, or both comprising:
providing an ongoing and real time indicator for predicting remaining lifetimes for one or more patients comprising:
providing a monitoring system connected to the cloud, a Wi-Fi or Bluetooth network which is connected to a wearable device; and
providing a wearable device which contains one or more accelerometers, temperature monitoring devices, EKG monitoring devices and other useful devices;
wherein the wearable device is powered internally by a battery or other such appropriate energy sources.

### Claim 26

A method for providing an ongoing in real-time indicator to determine a time interval and duration for predicting a change of an active and a resting phase in one or more subjects comprising:
sampling a time duration of the active and the resting phase of the one or more subjects recursively for various time intervals of 1 h to Nth hour and time duration of N hour to N+1 hour to obtain active and resting phase data;
using an eXtreme Gradient Boosting (XGBoost) algorithm on the active and resting phase data to convert weak learners to stronger learners using learners trained against a predictive model;
training the model for a maximum time duration and a time interval sufficient to predict a significant change in the activity of the active and the resting phase of the subject; and
triggering an alarm when the activity measured for the active and resting phase data drops<50% from a critical level.

### Claim 27 (depends on 26)

The method of claim 26, wherein setting an alarm level is based on a change in a phase exchange of an active and a resting phase in which the signals overlap.

### Claim 28 (depends on 26)

The method of claim 26, wherein the active and resting phase data were unnormalized.

### Claim 29 (depends on 26)

The method of claim 26, wherein the algorithm operates without generating independent dummy variables.

### Claim 30 (depends on 26)

The method of claim 26, wherein one or more pre-computed categories are used to avoid a random split of the tree for selection of variables, and the active and resting phase data was used as split point prior to performing the classification into categories.

### Claim 31 (depends on 26)

The method of claim 26, wherein a sample interval is selected so that a trajectory of the resting and active phases cross and are personalized to set an alarm for each of the one or more subjects.

### Claim 32 (depends on 26)

The method of claim 26, wherein a minimum is identified for each of the one or more subjects that triggers a subject-specific sedentary analysis or treatment interventions.

### Claim 33 (depends on 26)

The method of claim 26, wherein when the alarm is triggered then providing a treatment intervention selected from: waking up the subject, diagnosing the subject, resuscitation, administration of a medication, administration of a remedy, administration of a nutritional supplement, administration of a vitamin, exercise, physical therapy, massage, stretching, consumption of food, rest, sleep, and any combination thereof.

### Claim 34

A non-transitory computer readable medium for providing an ongoing and real time indicator for predicting remaining lifetimes for one or more patients, comprising instructions stored thereon, that when executed by a computer having a communications interface, one or more databases and one or more processors communicably coupled to the interface and one or more databases, perform the steps comprising:
providing a monitoring system connected to the cloud, a Wi-Fi or Bluetooth network which is connected to a wearable device; and
providing a wearable device which contains one or more accelerometers, temperature monitoring devices, EKG monitoring devices and other useful devices;
wherein the wearable device is powered internally by a battery or other such appropriate energy sources.

### Claim 35

An apparatus for providing an ongoing and real time indicator for predicting remaining lifetimes for one or more patients comprising:
a device that samples a time duration of the active and the resting phase of patient recursively for consecutive time intervals of 1 h to Nth hour and time duration of N hour to N+1 hour to obtain an active and resting phase data;
a processor comprising a non-transitory computer readable medium connected or connectable to the device to provide an ongoing and real time indicator for predicting a remaining lifetime or a major medical event for one or more patients, comprising instructions stored thereon, that when executed by a computer having a communications interface, one or more databases and one or more processors communicably coupled to the interface and one or more databases, perform the steps comprising:
using an eXtreme Gradient Boosting (XGBoost) algorithm on the active and resting phase data to convert weak learners to stronger learners using learners trained against a predictive model;
training the model for a maximum time duration and a time interval sufficient to predict a significant change in the activity of the active and the resting phase of the patient; and
triggering an alarm when the activity measured for the active and resting phase data drops<50% from a critical level.

### Claim 36 (depends on 35)

The apparatus of claim 35, wherein setting an alarm level is based on a change in a phase exchange of an active and a resting phase in which the signals overlap.

### Claim 37 (depends on 35)

The apparatus of claim 35, wherein setting the alarm level is based on a change in a phase exchange of an active and a resting phase in which the signals overlap.

### Claim 38 (depends on 35)

The apparatus of claim 35, wherein the active and resting phase data were unnormalized.

### Claim 39 (depends on 35)

The apparatus of claim 35, wherein the algorithm operates without generating independent dummy variables.

### Claim 40 (depends on 35)

The apparatus of claim 35, wherein pre-computed categories are used to avoid a random split of the tree for selection of variables, and the active and resting phase data was used as split point prior to performing the classification into categories.

### Claim 41 (depends on 35)

The apparatus of claim 35, wherein a sample interval is selected so that a trajectory of the resting and active phases cross and are personalized to set an alarm for each of the one or more subjects.

### Claim 42 (depends on 35)

The apparatus of claim 35, wherein a minimum is identified for each of the one or more subjects that triggers a subject-specific sedentary analysis or treatment interventions.

### Claim 43 (depends on 35)

The apparatus of claim 35, wherein when the alarm is triggered then providing a treatment intervention selected from: waking up the subject, diagnosing the subject, resuscitation, administration of a medication, administration of a remedy, administration of a nutritional supplement, administration of a vitamin, exercise, physical therapy, massage, stretching, consumption of food, rest, sleep, and any combination thereof.
