Classifications

• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
  • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
  • A61B5/02416—Detecting, measuring or recording pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
  • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
  • A61B5/02438—Detecting, measuring or recording pulse rate or heart rate with portable devices, e.g. worn by the patient
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
  • A61B5/7271—Specific aspects of physiological measurement analysis
  • A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• • G—PHYSICS
  • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
  • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
  • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
  • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B2503/00—Evaluating a particular growth phase or type of persons or animals
  • A61B2503/12—Healthy persons not otherwise provided for, e.g. subjects of a marketing survey
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
  • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
  • A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
  • A61B5/0015—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by features of the telemetry system
  • A61B5/0024—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by features of the telemetry system for multiple sensor units attached to the patient, e.g. using a body or personal area network
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
  • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
  • A61B5/021—Measuring pressure in heart or blood vessels
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
  • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
  • A61B5/1118—Determining activity level
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
  • A61B5/14532—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring glucose, e.g. by tissue impedance measurement
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
  • A61B5/14542—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring blood gases
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/48—Other medical applications
  • A61B5/4866—Evaluating metabolism
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
  • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
  • A61B5/6813—Specially adapted to be attached to a specific body part
  • A61B5/6824—Arm or wrist
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
  • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
  • A61B5/6813—Specially adapted to be attached to a specific body part
  • A61B5/6828—Leg
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
  • A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
  • A61B5/6898—Portable consumer electronic devices, e.g. music players, telephones, tablet computers
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
  • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
  • A61B5/7235—Details of waveform analysis
  • A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters

Definitions

• the present disclosure relates to the conversion of biometric data to meaningful heath risk indications.
• aspects of the disclosure relate to a method and system for determining a health risk indicator for a user from heart rate data.
• Fitness monitoring devices such as pedometers are available. However, many fitness monitoring devices are based on motion sensing alone, which can lead to inaccurate estimation of activity levels. For example a wrist-worn accelerometer could indicate a higher activity level for a period during which a user is eating than a period during which they are climbing stairs.
• While some fitness monitoring devices are based on personal heart rate monitors these tend to be aimed at fitness enthusiasts wishing to track their training. As data acquisition and tracking is the main focus, these devices do not provide meaningful information in terms of assessing health impact from physical activity (e.g. risk of cardiovascular diseases or premature death). Achieving good health is a common motivation for exercising. For older people in particular it is often the primary motivation. There is a need to interpret biometric sensor data, such as heart rate, to an easily understandable metric, which directly links to an individuals' health.
• a method of determining a health risk indicator for a user by: obtaining heart rate data for the user recorded over a monitoring period of at least one day; processing said heart rate data in dependence on biometric data for the user to determine an aggregate heartbeat value for the user over said monitoring period; and determining said health risk indicator in dependence on said aggregate heartbeat value.
• Said biometric data could comprise a resting heart rate value for the user and a maximum heart rate value for the user.
• the health risk indicator could be provided to the user.
• the monitoring period could be at least two days.
• the monitoring period could be at least three days.
• the monitoring period could be at least five days.
• the monitoring period could be one week.
• the monitoring period could be a fortnight.
• the monitoring period could be one month.
• the monitoring period could be configurable by the user and/or a health professional.
• the method could further comprise sensing the user's pulse over the monitoring period to produce a series of pulse measurements and determining the aggregate heartbeat value from said series of pulse measurements.
• the method could further comprise, before determining the aggregate heartbeat value, applying a model-based estimator to the series of pulse measurements, and excluding from further processing any individual pulse measurements from said series that do not meet a quality criterion.
• Said model-based estimator could be a Kalman filter.
• Said method could comprise noise estimation, and said quality criterion could depend on a resulting noise estimate.
• the series of pulse measurements (following application of the model-based estimator, if present) could be extrapolated to produce an evenly distributed series of data points or a continuous heart rate function over the monitoring period.
• Said processing could further comprise normalising the heart rate data, an evenly distributed series of data points derived from the heart rate data or a continuous function derived from the heart rate data by subtracting said resting heart rate value and dividing the result by the difference between said maximum heart rate value and the resting heart rate value.
• Such processing could be to calculate an intensity value.
• the aggregate heartbeat value might not be a pure sum of heartbeats; the aggregate heartbeat value weighting heart rate values such that the higher the heart rate value, the more weight it is given. Intensity values could also be weighted in this manner to provide intensity scores.
• Said intensity scores could be calculated as exponential powers of the intensity values.
• the aggregate heartbeat value could be determined by summing intensity scores derived from the heart rate data over the monitoring period.
• An activity score could be determined by summing discrete intensity scores or integrating a continuous function derived from the heart rate data over the monitoring period.
• the health risk indicator could be determined by statistical fitting of the aggregate heartbeat value with population survey data.
• the sensing could be periodic.
• a sampling rate of said periodic sensing could be variable over time. Said sampling rate could be increased in response to a determination that the user's heart rate has increased above a first predetermined threshold value; and/or said sampling rate could be decreased in response to a determination that the user's heart rate has decreased below a second predetermined threshold value.
• the method could further comprise obtaining data indicating movement of the user over the monitoring period; and reducing the weighting applied to heart rate values determined to be greater than a predetermined threshold higher than predetermined expected heart rate values associated with the data indicating movement of the user for the time those heart rate values correspond to.
• the method could be repeated periodically.
• a repetition period could be equal to the monitoring period such that the method is repeated consecutively.
• a repetition period could be less than the monitoring period such that the method is performed in a sliding window.
• the health risk indicator could comprise an indication of whether or not the user is classed as being physically active enough in order to substantially reduce the risk of developing one or more lifestyle-related diseases.
• the method could further comprise estimating the user's peak aerobic capacity using a first order low pass filter on the aggregate heartbeat value or a value derived therefrom and biometric data for the user.
• Said biometric data could comprise one or more of resting heart rate, gender, age and body mass index.
• a computer program product comprising computer-executable instructions for performing the method of the first aspect.
• a system for determining a health risk indicator for a user comprising: a data input configured to receive heart rate data for the user over a monitoring period of at least one day; and a processor configured to: process said heart rate data in dependence on biometric data for the user to determine an aggregate heartbeat value for the user over said monitoring period; and determine said health risk indicator in dependence on said aggregate heartbeat value.
• Said biometric data could comprise a resting heart rate value for the user and a maximum heart rate value for the user.
• Said system could comprise a user interface configured to provide the health risk indicator to the user.
• the system could further comprise: a sensor configured to sense the user's pulse over said monitoring period to produce a series of pulse measurements; and a processor configured to determine the heart rate data from said series of pulse measurements.
• a method of determining a health risk indicator for a user by: receiving a series of heart rate measurements taken from the user over a monitoring period of at least five days at intervals of no more than fifteen minutes; processing each of said measurements using the user's rest and maximum heart rates to produce a series of normalised heart rate values; weighting each normalised heart rate value to produce a series of weighted heart rate values; aggregating said weighted heart rate values over said monitoring period to produce a heartbeat aggregate; and determining said health risk indicator by statistical fitting of said heartbeat aggregate with population study data.
• the health risk indicator can then be provided to the user.
• the user's pulse can be sensed over the monitoring period to produce the series of heart rate measurements.
• a system for determining a health risk indicator comprising: a data input configured to receive a series of heart rate measurements taken from a user over a monitoring period of at least five days at intervals of no more than fifteen minutes; and a processor configured to: process each of said measurements using the user's rest and maximum heart rates to produce a series of normalised heart rate values; weight each normalised heart rate value to produce a series of weighted heart rate values; aggregate said weighted heart rate values over said monitoring period to produce a heartbeat aggregate; and determine said health risk indicator by statistical fitting of said heartbeat aggregate with population study data.
• a user interface can be configured to provide the health risk indicator to the user.
• a sensor can be configured to sense the user's pulse over said monitoring period to produce the series of heart rate measurements.
• Figure 1 sets out a general method
• FIG. 2 illustrates an example system
• Figure 3 sets out an example sample rate variation scheme
• Figure 4 sets out an example method
• Figure 5 shows an example user interface
• Figures 6a to 6d and 7a to 7b illustrate example data.
• Monitoring heart rate provides a more accurate way to track activity level for the purpose of improving health than, for example, number of steps taken.
• the former rates walking uphill higher than walking the same number of steps on a flat surface, whereas the latter will rate these activities as the same (or even lower during uphill walking for some gaits) despite the significant difference in physical exertion required.
• an aggregate heartbeat based system will rate a long hike in the mountains equally with high intensity interval training, if both activities promote the same aggregate heartbeat value, making a system based on aggregate heartbeat measurement suitable for use for health improvement across the population regardless of age or physical capability.
• FIG. 1 is a flowchart of a general method 100 for determining a health risk indicator for a user from heart rate data collected from them.
• heart rate data for the user recorded over a monitoring period of at least five days, for example 1 week is obtained.
• that heart rate data is processed in dependence on a resting heart rate value for the user and a maximum heart rate value for the user to determine an aggregate heartbeat value for the user over the monitoring period.
• a health risk indicator is determined in dependence on the aggregate heartbeat value.
• FIG. 2 is a schematic of an example system for providing a user with a health risk indicator.
• Biometric data including at least heart rate data is collected from a user by one or more sensors comprised in a sensor device 210.
• Sensor device 210 could be a wearable device, for example a sensor wristband or chest strap.
• Heart rate data could be collected by, for example, a photoplethysmography (PPG) sensor.
• PPG photoplethysmography
• Other kinds of sensors could also be provided, for example an accelerometer (motion sensor), blood pressure sensor, glucose sensor, blood gas sensor, pressure sensor or any other sensors which could be used to measure user activity, physiological or environmental parameters. Data obtained from such sensors could be taken into account in determining health risk indicators and/or could be part of a wider health/fitness monitoring suite enabling a user or healthcare professional to obtain more detailed health indication information if required.
• Resting heart rate can be obtained by determining the lowest heart rate value measured by sensor device 210 over the monitoring period. Alternatively, resting heart rate could be measured by the user or a healthcare professional by any known method and manually input to the system via a user interface.
• Maximum heart rate can be obtained by determining the highest heart rate value measured by sensor device 210 over the monitoring period. Alternatively maximum heart rate could be measured by the user or a healthcare professional by any known method and manually input to the system via a user interface.
• the sensor device 210 could comprise a user interface 21 1 and/or could comprise means for transferring data to a user device 220 having a user interface 221 such as a mobile phone (e.g. a smartphone), tablet, laptop or personal computer.
• a user device 220 having a user interface 221 such as a mobile phone (e.g. a smartphone), tablet, laptop or personal computer.
• Such data transfer means could comprise a wired connection such as a Universal Serial Bus (USB) line or a wireless link such as a Wi-Fi or BluetoothTM connection between a transmitter and associated antenna comprised in the sensor device 210 and a receiver and associated antenna comprised in the user device 220.
• the sensor device 210 and/or the user device 220 could each run software suitable for implementing part or all of the method described herein by means of memories 212 and 222 and processors 213 and 223 respectively.
• the user device 220 could run a dedicated application or could run a general-purpose web browser through which a web-based application could be accessed.
• Suitable user interfaces include at least touchscreens, keyboards and/or touchpads or mice or microphones with associated voice recognition capabilities.
• the system could have a calibration mode to collect resting and maximum heart rate from the user without requiring the assistance of a healthcare professional.
• software run on the sensor device 210 or user device 220 could cause a user interface of one of those devices to prompt a user to perform a calibration on first switching on sensor device 210 or opening an associated application with user device 220.
• the user could also be presented with an option to skip the calibration at that point but, if they select the skip option, they could be prompted to perform the calibration at the end of the monitoring period.
• the user When the user selects calibration mode, they can be instructed by a user interface to get into a comfortable position for measuring resting heart rate and start a timer when ready. While the timer is running they could be instructed not to perform any physical activity until the timer, which can for example be displayed on a visual user interface of the device, expires. The timer could for example be for one minute. Towards the end of the timer period the sensor device 210 could take a heart rate reading and record this as the user's resting heart rate. Alternatively, sensor device 210 could monitor the user's heart rate over some or all of the timer period, for example at 5 second intervals, and select the lowest measured rate to record as the user's resting heart rate.
• the user could be prompted to get on to some gym equipment (e.g. a treadmill, cross- trainer, rowing machine or exercise bike), or find somewhere to run, cycle or similar and start another timer when ready. While the timer is running they could be instructed to exercise at maximum exertion (e.g. run as fast as possible). The timer could for example be for 5 minutes.
• Sensor device 210 could monitor the user's heart rate over some or all of the timer period and select the highest measured rate to record as the user's maximum heart rate.
• sensor device 210 can monitor the user's heart rate continuously or sample at intervals. If sensor device 210 is battery powered, the monitoring could be arranged such that a fully charged battery will outlast the monitoring period. Interval sampling could be periodic. A typical sampling rate could be once per minute. A minimum sampling rate could be once every 15 minutes.
• the sensor device 210 could store the heart rate data in local memory 212. Alternatively or additionally the sensor device 210 could be provided with data transfer means such as those described above to convey the heart rate data to a user device 220 for storing in its local memory 222 or upload it directly to a network 240 such as the internet for transmission to a server 230.
• the heart rate data can be processed by an internal processor 213 of the sensor device 210, a processor 223 of the user device 220, at the server 230 or by any combination of these performing any suitable combination of the processing steps.
• Sampling rate could be variable. This can help to achieve a suitable balance between data accuracy and (battery) power consumption. For example if heart rate is determined to have risen above a first predetermined threshold value (indicating that physical activity is being undertaken), for example 60% of the user's maximum heart rate relative to their resting heart rate, the sampling rate could be increased, for example to once every 15 seconds. The sampling rate could be returned to its standard value when the user's heart rate is determined to have fallen below the first threshold, or to have stayed below the first threshold for a predetermined period, for example 5 minutes.
• the sampling rate could be decreased, for example to once every 10 minutes.
• the sampling rate could be returned to its standard value when the user's heart rate is determined to have exceeded the second threshold again.
• FIG. 3 is a flowchart showing an example scheme for varying sampling rate.
• a sample counter k is set to zero.
• the user's current heart rate is measured and recorded as y k .
• y k is compared to Ay, the heat rate range of the user where:
• Ay y max - y rest (1 ) i.e. the difference between the user's resting and maximum heart rates as previously recorded. If the current heart rate value is less than 5% of Ay, then a sampling interval At is set to 10 minutes at 304a. If the current heart rate value is between 5% and 60% of Ay, then At is set to 1 minute at 304b. If the current heart rate value is greater than 60% of Ay, then At is set to 15 seconds at 304c. At 305, a timer is set to wait for At, and when it has expired the value of k is incremented by 1 and the process returns to 302.
• An example processing method 400 is set out in Figure 4.
• a continuous heart rate function y(f) could be extrapolated from the series of heart rate values.
• the heart rate values are (is) converted to a series of intensity values y k (or an intensity value function (t))- This could be done using a linear intensity scaling.
• intensity conversion is a normalisation with respect to the user's heart rate range (from resting heart rate y ms t to maximum heart rate y max ). This produces a series of normalised heart rate values y k (or a continuous normalised heart rate function y(t)) according to equations 2. This gives an indication of instantaneous exertion over the monitoring period.
• inter-sample data points can optionally be extrapolated between samples for periods when the sampling rate was at less than its maximum value to produce a series of data points at constant intervals. For example linear interpolation between the two (temporally) nearest sampled heart rate values to each desired extrapolated data point could be used. This extrapolation can be performed before or after intensity scaling. Alternatively, if no extrapolation of inter-sample data points is performed, then variable sampling rates as described above, with higher sampling rates used during periods of greater exertion, would result in higher weighting of heartbeats during exercise on calculation of activity score as described below.
• the intensity values are (is) converted to a series of intensity scores z k (or an intensity score function z(f)). This could be done using a power function.
• intensity score calculation is done using an exponential function according to equations 3:
• the activity score, P is then computed at step 423.
• the activity score is a heartbeat aggregate over the monitoring period, T, for example the Euler integration sum (or definite integral) of the intensity scores (or intensity function) over the monitoring period as per equations 4.
• a health-predictive activity score, V is determined as an explicit function of activity score P, for example according to equation 5:
• the health-predictive activity score can be statistically linked to peak oxygen uptake of population study subjects since peak oxygen uptake is a good predictor of cardiovascular health. (Peak oxygen uptake of the user need not necessarily be known, but the health-predictive activity score can be compared with the activity score needed to achieve a certain peak oxygen uptake over time to determine a health risk indicator.)
• any or all of constants Ci to c 4 could be chosen from a plurality of options according to biometric data for the user such as one or more of: gender, age, weight, height etc.
• One or more health risk indicators can be derived from the health-predictive activity score at step 432.
• a health risk indicator could be a linear scaling of the health-predictive activity score, where complete inactivity gives the value 0 and the value 100 indicates minimal risk of developing lifestyle-related diseases.
• the health risk indicator could be expressed relative to a threshold for reduced/increased risk to health. For example, a health risk indicator of greater than 45 for men, or 35 for women, could indicate reduced risk, while a health risk indicator below that threshold could indicate increased risk.
• a health risk indicator could be expressed as a personal activity index, PAI, as defined in equation 6:
• PAI ⁇ oiv-c 3 ) (6 )
• V thresho i d is a constant which could optionally be chosen from a plurality of options according to biometric data for the user such as one or more of: gender, age, weight, height etc. It could for example be 45 for a male user or 35 for a female user.
• a health risk indicator could be a binary indication of whether or not the user has been physically active enough over the monitoring period to improve their activity score compared to a previous monitoring period. Alternatively, it could be a binary indication of whether or not the user has been active enough over the monitoring period to reduce their general risk of developing lifestyle-related diseases compared to a previous monitoring period. If a greater level of detail is desired, one or more binary health risk indicators could be provided to indicate whether or not the user has been active enough over the monitoring period to reduce their risk of developing a corresponding one or more specific lifestyle-related diseases/conditions compared to a previous monitoring period. For example, individual health risk indicators could be provided for metabolic syndrome, atherosclerosis, hypertension, high blood glucose, unfavourable blood lipid profile, obesity etc.
• a percentage general risk factor for developing lifestyle-related diseases could be provided, or one or more percentage risk factors for developing specific lifestyle-related diseases.
• a binary indication could be provided whether or not the user has been active enough over the monitoring period to increase their life expectancy, or a life expectancy could be provided.
• the provision of these indicators comprises comparison with population study data, and the provision of some comprise taking into account additional data relating to the user such as age, weight, body mass index, smoking and alcohol drinking habits and diet and/or monitoring of other biometric parameters.
• the health risk indicator is provided to the user or a medical professional, for example via a user interface, at the end of a first monitoring period.
• a report, or an alert that a report can be accessed by, for example, selecting a hyperlink or opening an application could be text messaged or emailed to an account of the user or medical professional, or an application running in the background of a user device could automatically open or trigger an alert.
• the user or medical professional could be required to manually request a report when desired.
• the system's software could provide the user with an opportunity to share each or every report on linked social media accounts.
• a graphical user interface displaying a health risk indicator could for example be as shown in Figure 5.
• the PAI is indicated at the top and graphically represented below by coloured bars indicating risk of developing lifestyle-related diseases. In the example shown, the PAI is 125, above the threshold for sufficient activity for minimal risk (100), so the coloured bars fill up to the green zone above the upper divider line.
• a second monitoring period could follow consecutively from the first such that up to date health risk indicators are available at a frequency of one divided by the monitoring period, for example once per week.
• the monitoring period could be a sliding window so that, for example, up to date health risk indicators are available daily based on data collected over the preceding 7 days.
• the aggregate heartbeat value could be calculated by use of a function that lowers the weighting of higher activity scores.
• sensor device 210 or an additional sensor device comprises a motion sensor such as a tri-axis accelerometer
• this can be taken into account in determination of the health risk indicator. For example if a user's heart rate is high (with respect to their resting and maximum heart rate) but they do not appear to be moving, this could be due to emotional stress rather than physical exertion. Therefore the high weighting which would be given to the heartbeats in that high heart rate period according to the method above could provide a false indication of activity level.
• the weighting applied could therefore be reduced, for example by 15%, for periods during which the measured (or extrapolated) heart rate is higher than would be expected for the activity level suggested by the motion sensor, for example by a predetermined margin such as 30 beats per minute.
• a relatively high measured heart rate (with respect to the user's resting and maximum heart rates) during a period in which a motion sensor suggests the user is not moving could be an indication of heart disease, especially if sustained over hours (Nauman et al, JAMA 201 1 ). If this condition is determined to be sustained over a predetermined period of, for example, two hours the system could inform the user to contact his/her physician for a medical follow-up.
• a wrist-worn motion sensor could result in inappropriate decreased weighting of heart rate data collected during cycling, whereas an ankle-worn motion sensor would not.
• the system could alert the user via a user interface if heart rate data and motion sensor data do not indicate similar activity levels, for example if measured (or extrapolated) heart rate is higher than would be expected for the activity level suggested by the motion sensor by said predetermined margin.
• Such an indication could, for example encourage the user to switch the motion sensor to a more appropriate part of their body during exercise (e.g. transfer a band-based motion sensor from wrist to ankle for cycling), or could indicate to heart patients that they are under undesirable emotional stress and should rest if possible.
• a model-based estimator (such as a Kalman filter) can be used.
• the detected signal can be filtered and/or the noise component extracted to judge whether individual data points should be included in further processing at all. Sensor data that does not meet predetermined quality criteria can thereby be rejected.
• the estimator can be arranged to ensure data passed on for further processing represents physiologically and physically reasonable changes in heart rate over time.
• a further parameter that can be determined from the heart rate data is the user's peak aerobic capacity, or peakV0 2 , a measure of cardiorespiratory fitness.
• An aggregate heartbeat value for example the health-predictive activity score, V, can be statistically fitted to data that includes peakVC>2.
• peakVC>2 evolves over time, increasing slowly with an elevated physical activity profile and decreasing slowly with absence of (or lowered) physical activity.
• persistence of a certain activity score V will converge towards a peakVC>2 value determined from the data fitting of V the model.
• An activity- induced peakV0 2 estimate, AlpeakV02 k could be estimated by a low pass filter on V, for example a first order low pass filter as per equation 7:
• AIpeakV02 k aV k + (1 - a)A ⁇ -peaW02 k _ x (7)
• a is a constant given by the time constant expressing the individual's response to training
• a can be an average value determined from a population study and/or individually fitted by analysing the slowly-varying changes in resting heart rate of the user.
• the activity-induced peakVC>2 estimate could be further corrected to a true peakVC>2 estimate by using the user's age, resting heart rate and/or waistline measurement/body mass index (Nes et al 201 1 & Nes et al, unpublished data).
• Figures 6a to 6d show how health-predictive activity score, V, as calculated according to equation 5 relates to peakV0 2 for test subjects respectively performing various amounts of exercise per week at 50, 70, 80 and 90% of peak oxygen uptake.
• Figure 7 shows how age-adjusted PAI predicts survival in a large population study of women (Figure 7a) and men (Figure 7b).

Landscapes

• Health & Medical Sciences (AREA)
• Life Sciences & Earth Sciences (AREA)
• Engineering & Computer Science (AREA)
• Medical Informatics (AREA)
• Public Health (AREA)
• Cardiology (AREA)
• General Health & Medical Sciences (AREA)
• Pathology (AREA)
• Biomedical Technology (AREA)
• Surgery (AREA)
• Heart & Thoracic Surgery (AREA)
• Molecular Biology (AREA)
• Biophysics (AREA)
• Animal Behavior & Ethology (AREA)
• Physics & Mathematics (AREA)
• Physiology (AREA)
• Veterinary Medicine (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Artificial Intelligence (AREA)
• Psychiatry (AREA)
• Signal Processing (AREA)
• Data Mining & Analysis (AREA)
• Databases & Information Systems (AREA)
• Epidemiology (AREA)
• Primary Health Care (AREA)
• Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
• Measuring And Recording Apparatus For Diagnosis (AREA)

Priority Applications (6)

Applications Claiming Priority (2)

Publications (1)

Family

ID=50345863

Family Applications (1)

Country Status (11)

Cited By (1)

Families Citing this family (18)

Citations (1)

Family Cites Families (21)

• 2014
  • 2014-03-20 NO NO14160936A patent/NO2921105T3/no unknown
  • 2014-03-20 EP EP14160936.2A patent/EP2921105B1/en active Active
  • 2014-03-20 EP EP17201543.0A patent/EP3348186A1/en not_active Withdrawn
  • 2014-03-20 DK DK14160936.2T patent/DK2921105T3/en active
  • 2014-12-10 US US14/565,860 patent/US10973421B2/en active Active
• 2015
  • 2015-03-20 CN CN201580014985.6A patent/CN107077523B/zh active Active
  • 2015-03-20 AU AU2015233337A patent/AU2015233337B2/en active Active
  • 2015-03-20 CA CA2943260A patent/CA2943260C/en active Active
  • 2015-03-20 MX MX2016012133A patent/MX2016012133A/es active IP Right Grant
  • 2015-03-20 WO PCT/EP2015/056025 patent/WO2015140338A1/en active Application Filing
  • 2015-03-20 BR BR112016021493-5A patent/BR112016021493B1/pt active IP Right Grant
  • 2015-03-20 JP JP2017500438A patent/JP6531161B2/ja active Active
• 2021
  • 2021-02-04 US US17/167,704 patent/US11806120B2/en active Active

Patent Citations (1)

Non-Patent Citations (3)

Also Published As

Similar Documents

Legal Events