WO1997033512A1 - Procede et appareil de mesure de l'endurance a l'effort - Google Patents

Procede et appareil de mesure de l'endurance a l'effort Download PDF

Info

Publication number
WO1997033512A1
WO1997033512A1 PCT/FI1997/000163 FI9700163W WO9733512A1 WO 1997033512 A1 WO1997033512 A1 WO 1997033512A1 FI 9700163 W FI9700163 W FI 9700163W WO 9733512 A1 WO9733512 A1 WO 9733512A1
Authority
WO
WIPO (PCT)
Prior art keywords
heartbeat
parameters
calculation
exertion
measured
Prior art date
Application number
PCT/FI1997/000163
Other languages
English (en)
Inventor
Seppo NISSILÄ
Juha Röning
Antti Ruha
Kauko Väinämö
Original Assignee
Polar Electro Oy
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Polar Electro Oy filed Critical Polar Electro Oy
Priority to DE19781642T priority Critical patent/DE19781642T1/de
Priority to DE19781642A priority patent/DE19781642B4/de
Priority to GB9819760A priority patent/GB2326240B/en
Priority to US09/142,444 priority patent/US6277080B1/en
Publication of WO1997033512A1 publication Critical patent/WO1997033512A1/fr
Priority to HK99102020A priority patent/HK1016857A1/xx

Links

Classifications

    • 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
    • A61B5/6802—Sensor mounted on worn items
    • A61B5/681—Wristwatch-type devices
    • 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
    • A61B5/0004—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by the type of physiological signal transmitted
    • A61B5/0006—ECG or EEG signals
    • 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
    • A61B5/68—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
    • A61B5/683—Means for maintaining contact with the body
    • A61B5/6831—Straps, bands or harnesses
    • 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
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • 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
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Definitions

  • the invention relates to a method for measuring exercise condition, especially to a method for measuring an exertion endurance indicator representing exercise condition of a subject to be measured, such as maximal oxygen uptake or any such exertion endurance indicator representing exercise condition.
  • the invention further relates to an apparatus for measuring exercise condition, especially to an apparatus for measuring an exertion endurance indicator representing exercise condition of a subject to be measured, such as maximal oxygen uptake or any such exertion endurance indicator representing exercise condition.
  • Condition classification representing exercise exertion based on measuring maximal oxygen uptake is used as an indicator of physical exercise condition, that is, exertion endurance, for example to measure human physical performance, such as exertion endurance.
  • Prior art solutions for determining and measuring an exercise condition class are either direct exertion measurement or indirect measure ⁇ ment.
  • direct exertion measurement the maximal oxygen uptake ability is measured directly from respiratory gases under maximum exertion by means of a running mat or a bicycle ergometer, for example.
  • indirect measurement the work performed is measured within a specific period of time, such as in so- called Cooper test where a distance run during 12 minutes is measured.
  • Cooper test where a distance run during 12 minutes is measured.
  • the measurement of exercise condition takes place by means measurement of an active performance, wherefore these methods are laborious, difficult and expensive to arrange in order to determine condition.
  • Average resting heartbeat is considered to be one indicator of condition, but it does not give reliable results as the correlation of resting heartbeat to maximal oxygen uptake ability is only at the rate of 0.4 to 0.45. Other heartbeat parameters do not either attain better correlations to maximal oxygen uptake ability.
  • the object of the present invention is to introduce a new method that will avoid the problems associated with prior art methods.
  • ⁇ neural network is used for measuring an exertion endurance indicator representing exercise condition, to which formula input parameters represent ⁇ ing the subject to be measured are supplied, the input parameters comprising at least one or more of the following physiological parameters, such as sex, age, height, weight, and from which calculation formula one or more output parameters representing the exertion endurance indicator representing the exercise condition of the subject to be measured are obtained as a result, the neural network construction used for formulating the calculation formula being trained with a sufficiently large number of real measuring results comprising similar input parameters and one or more similar output parameters, and that in addition to the physiological parameters, one or more resting heartbeat parameters measured specifically from resting heartbeat are used as the input parameters of the calculation formula, and that similar resting heartbeat parameters are used in the training of the neural network used in formulating the calculation formula of the exertion endurance indicator representing exercise condition.
  • a predetermined calculation formula is used to which physiological input parameters representing the subject to be measured are supplied, the input parameters comprising at least one or more of the following physiological parameters, such as sex, age, height, weight, and from which calculation formula one or more output parameters representing the exertion endurance indicator, such as maximal oxygen uptake ability or any other such exertion endurance indicator representing the exercise condition of the subject to be measured are obtained as a result, and that in addition to the physiological parameters, one or more resting heartbeat parameters measured from resting heartbeat are used as input parameters of the calculation formula.
  • the apparatus of the invention is characterized in that the apparatus comprises means for detecting resting heartbeat and for sending it to a calculation unit also included in the apparatus, and that the apparatus comprises means for supplying physiological parameters representing the subject to be measured to the calculation unit for calculating the output quantity representing condition exertion endurance representing exercise condition, such as maximal oxygen uptake ability, condition classification or any such physical condition exertion endurance indicator, on the basis of hysiological features and resting heartbeat data also supplied to the calculation unit, and means, such as a display and/or a memory, for indicating and/or storing the physical condition obtained on the basis of calculation.
  • condition exertion endurance representing exercise condition
  • a display and/or a memory for indicating and/or storing the physical condition obtained on the basis of calculation.
  • the method and apparatus of the invention are based on the idea that resting heartbeat parameters are used as input data of exercise exertion endurance, and a calculation formula predetermined preferably by means of the neural network is used, to which formula resting heartbeat parameters and human physical parameters are supplied as input data and e.g. maximal oxygen uptake is calculated as output data representing human physical exercise condition, that is, exertion endurance.
  • the preferably used neural network is trained by corresponding data by using an extensive real measurement material. Different parameters of a person's heartbeat and heartbeat variation measured during a few minutes are needed as measurement data and in addition to the parameters obtained from their heartbeat, human physical measurement parameters, such as weight, length, age and sex, are utilized.
  • the data measured from resting heartbeat and personal pre-data are provided to the calculation formula as supply data.
  • different rules have been made by means of fuzzy logic, that is, the effect of different variables or variable combinations on the end result, that is, on the condition class is made fuzzy.
  • the calculation formula determined by means of the neural network calculates by weightings obtained on the basis of training material the maximal oxygen uptake ability of a person from the new supply data and determines a corresponding condition class.
  • Neural networks are known per se, and they have been used previously for measuring a patient's condition of health, the seriousness of a person's infarct, the risk of death for elderly persons or a person's blood pressure. These solutions have been disclosed e.g. in reference EP-555591.
  • Reference DE-4307545 further discloses an apparatus that determines the location and the extent of a person's infarct.
  • This apparatus employs multi-channel EKG measurement and infarct determination is based on the trained use and classification of neural network construction in the apparatus.
  • Reference EP-650742 discloses an apparatus which controls a pacemaker, i.e. a defibrillator by means of a neural network. This apparatus measures the EKG curve, compares it to the data bank and decides if a pacemaker pulse is needed.
  • Reference WO-92/03094 discloses an apparatus with which a patient's heart is diagnozed by means of heart sounds by using a neural network construction.
  • Reference US-5251626 discloses an apparatus for detecting and classifying arrhythmias which is similar to that in EP 650742 cited above.
  • Reference US-5280792 discloses an apparatus for detecting and classifying arrhythmias, which is similar to what is disclosed in EP 650742 and US 5251626 cited above.
  • Reference DE-4338958 discloses an apparatus and a method for determining a person's optimal exercise heartbeat.
  • an optimal exercise heartbeat is searched by using an iterative method where first an initial heartbeat level/load is determined by using known formulae and then heartbeat level under load is measured. The difference between assumed and measured heartbeat level is used to optimize the correct heartbeat level/load level.
  • the result can be further specified by taking other variables and factors into account by using a neural network and/or a multi-variable analysis.
  • the disadvantage of the solution in the reference cited is also that heartbeat has to be measured during loading. This solution refers to a maximal oxygen uptake ability but in this solution maximal oxygen uptake is used as input data and not as calculation output data as in the solution of the invention.
  • RR interval parameters such as mean heartbeat interval, standard deviation of heartbeat intervals or maximum heartbeat interval
  • the method of the invention is very accurate, simple, advantageous in its costs and easy to implement as a method for measuring physical exercise condition, that is, exertion endurance, such as maximal oxygen uptake ability.
  • the method of the invention is very useful for testing and determining exercise condition for ordinary persons who exercise because it is easy to record resting heartbeat during a few minutes and find out the physical parameters and supply them to the necessary measurement apparatus as no exertion test need be done.
  • the new, accurate and easy method of the invention can also be used by sportsmen/sportswomen for monitoring changes in exercise condition. More accurate direct tests can be made less often as reference.
  • the method of the invention will also save expenses, which are considerable in a direct test.
  • Figure 1 shows a graphical representation of a neural network construction
  • Figure 2 shows a neural network construction in a matrix form
  • Figure 3 shows one neural network construction used for determining a calculation formula of physical condition
  • Figure 4 shows a membership function in a fuzzy group
  • Figure 5 shows coefficient and bias matrixes determined on the basis of the neural network construction and the large test material supplied thereto
  • Figure 6 shows an apparatus solution applying the method
  • FIG. 7 shows resting heartbeat
  • Figure 8 shows the apparatus used by a human being.
  • FIG 7 shows a typical EKG signal caused by heartbeat.
  • P, Q, R, S, T and U waves can be identified in each signal by accurate measuring.
  • R wave is formed by polarization of ventricles of the heart and generally represents a peak value. Peak value R represents the maximum point of the EKG signal and the interval R-R represents a beat interval. The beat can be measured from a pressure pulse or optically.
  • Figure 6 shows an example of a heartrate monitor equipment applied in the invention, preferably a heartrate monitor is formed of a heartbeat transmitter A attached to the chest of a person to be examined and a receiver B receiving heartbeat signals wirelessly where heartbeat measurement and analysis functions are included.
  • one exemplary equipment in Figure 6 is also formed of a transmitter A comprising an EKG pre-amplifier 1 to which heartbeat identifying electrodes 1a, 1b are connected.
  • the signal of the pre-amplifier 1 is amplified in an AGC amplifier 2 and further in a power amplifier 3 where a heartbeat signal controlling windings 4 is produced, in which signal the interval between the pulses in the signal is the same as the interval of heartbeats.
  • a magnetic field varying at the rate of heartbeat is thus generated to the windings 4.
  • the magnetic field provided by a transmitting coil 4 is detected by a coil 5 of the receiver B forming the other part of the equipment.
  • the coils 4 and 5 form an inductive coupling, which operates by means of the magnetic field, between the transmitter unit A and the receiver unit B.
  • the received signal is amplified by means of amplifier circuits 6 and 7 in the similar way as in the transmitter.
  • the amplified signal is conveyed to a microprocessor 8 that calculates from the heartbeat signal desired factors.
  • a memory 9 and a display device 10 are attached to the microprocessor. In these respects the apparatus is similar to known heartrate monitors.
  • a new feature in Figure 6 is that it comprises both a calculation unit
  • the calculation unit 200 is supplied with resting heartbeat parameters calculated on the one hand by the microprocessor 8 and on the other hand, by supply means 201 , a person supplies physiological input parameters describing the person, such as sex, age, height, weight.
  • the invention thus relates to a method for measuring physical exercise condition, that is, condition, that is, preferably human physical exercise condition, that is, exertion endurance, that is, performance of a subject to be measured.
  • a specific predetermined calculation formula is used in the calculation unit 200 to which physiological input parameters representing the subject to be measured are supplied, said input parameters comprising at least one or more of the following physiological parameters, such as sex, age, height, weight, and from which calculation formula one or more output parameters, such as maximal oxygen uptake ability representing the condition of the subject to be measured are obtained as a result.
  • the method is such that in addition to physiological parameters one or more resting heartbeat parameters measured from the resting heartbeat are used as an input parameter of the calculation formula.
  • the calculation formula may be implemented in Figure 6 by the calculation unit 200 which can be integrated as a program of the microprocessor 8 of the heartrate monitor B.
  • the method is such that the resting heartbeat is measured during a period of a few minutes, most preferably during a period of 2 to 5 minutes.
  • measurement is easy to perform, but on the other hand, it is long enough for the measurement to be reliable when information about heartbeat variation is obtained.
  • the method is such that one or more of the following resting heartbeat parameters such as mean heartbeat interval, standard deviation of heartbeat intervals, maximum mean heartbeat interval, are determined as input parameters from resting heartbeat. These parameters can be calculated in the microprocessor 8 of the receiver part B of the heartrate monitor, for example.
  • the method is such that by combining input parameters, one or more input parameter combinations are formed.
  • Some examined input parameters are shown in Table 1.
  • Table 1 Features, i.e. input parameters used in the method
  • one or more different rules are formed by means of fuzzy logic with which rules the effect of one or more input parameters and/or one or more input parameter combinations on the output parameter, that is, on maximal oxygen uptake ability representing condition is made fuzzy.
  • the unit litre per minute (l/min) and/or millilitre per kilogram per minute (ml/kg/min) can be used as a unit of maximal oxygen uptake ability.
  • the method comprises preclassification and an actual calculation after it.
  • the method is such that preclassification is carried out by means of one or more physiological input parameters, in which the possible solution area is searched on which the value of the output parameter to be calculated is estimated to lie, and that at the actual calculation stage, the input parameters of resting heartbeat are also used, whereby at the calculation stage, the value of the output parameter representing the physical condition of the subject to be measured is moved towards the correct value on the basis of the input parameters of resting heartbeat.
  • one or more input parameters which are made fuzzy are also used in addition to the physio ⁇ logical input parameters. This is illustrated in Figure 4 which shows membership function in a fuzzy set "old".
  • Figure 4 is a graphical representation of the concept membership function of fuzzy logic.
  • the membership function shows at how great proportion in this example a person of a certain age belongs to the set old.
  • Fuzzy logic represents a way of thinking where membership to a certain set is a continuous concept.
  • a middle-aged person belongs partly to the set young and partly to the set old.
  • new parameters that is, features of heartbeat parameters and a person's weight, height, age and sex are formed to the input vector VR which can be seen in Figure 2.
  • the input vector VR comprises the input parameters present in Table 1.
  • the method in the preferred embodiment is such that the value of maximal oxygen uptake ability corresponding to input parameters and/or condition classification representing oxygen uptake ability or any other such value representing physical exercise exertion endurance is obtained as an output parameter as a result of calculation.
  • known empirical data is used in the calculation formula, and empirical data is combined to the calculation formula according to fuzzy rules.
  • one or more of the following pieces of information are used as empirical data; "an older person is probably in a poorer condition", “the weight of a person correlates with the condition of the person best in the person set non-medium weight”, “the person with a great mean heartbeat interval is probably in a good condition”.
  • the method is implemented by the calculation unit 200, and the calculation unit 200 implementing this method is integrated into a heartrate monitor B, that is, into a receiver wrist strap B.
  • the calculation unit 200 implementing this method is integrated into a heartrate monitor B, that is, into a receiver wrist strap B.
  • the calculation unit 200 implementing the method is integrated into a heartrate monitor B or to any other such apparatus, and resting heartbeat is measured by means of measuring means A, 1 to 4 in connection with the apparatus or connected to it by a wireless or contact coupling, and the physiological input parameters, such as sex, age, height, weight, are supplied to the calculation unit 200 included in this heartrate monitor B or any other such apparatus by means of supply means 201 in connection with the apparatus or connected to it by a wireless or contact coupling, and the calculation result is shown on the display 10 and/or is stored in the memory 9 as in Figure 6. In the preferred embodiment of the invention, the calculation result is shown on the display 10 included in the heartrate monitor B or any other such apparatus.
  • said heartrate monitor or any other such apparatus is a heartrate monitor or some other apparatus B kept on a person's wrist.
  • the heartrate monitor means A, 1 to 4 can have, as in Figure 6, that is, a wireless, such as inductive coupling to the heartrate monitor B, but they could also be in the case of the heartrate monitor B, or otherwise in a wireless coupling, or in some other contact coupling to the heartrate monitor B, that is, to the receiver part B.
  • the supply means 201 of physiological input parameters can also be as in Figure 6, that is, in a wireless or otherwise contact coupling to the heartrate monitor B in the case of the heartrate monitor B, but they could be implemented in some other way, too.
  • the Applicant has observed that the simplest and most reliable method is to integrate the supply means 201 in connection with the receiver part B of the heartrate monitor.
  • the neural network construction NN shown in Figure 3 is utilized in a preferred embodiment of the invention.
  • the method in the preferred embodiment of the invention is such that the method uses a calculation formula which is obtained by means of the neural network construction NN to which input parameters representing the subject to be measured are supplied.
  • the input parameters comprise at least one or more of the following physiological parameters, such as sex, age, height, weight, and from which calculation formula one or more output parameter representing the exercise condition, that is, exertion endurance of a subject to be measured is obtained as a result.
  • the neural network construction NN used for forming the calculation formula has been trained with a sufficiently large number of real measurement results, such as clinical measurement results of 200 test subjects comprising corresponding input parameters and one or more similar output parameters as those that the calculation unit 200 uses in calculation.
  • one or more resting heartbeat parameters measured from resting heartbeat are used as input parameters of the calculation formula in addition to the physiological parameters.
  • Corresponding resting heartbeat parameters are used in training the neural network NN used for formulating the calculation formula.
  • a preferred embodiment connected with the use of the neural network NN is such that in the method such a calculation formula is used which is provided by realizing the calculation matrixes obtained as a result of training the neural network construction NN used for formulating the calculation formula.
  • the calculation matrixes obtained as a result of training the neural network construction are realized as a calculation formula by using known activation functions, and multiplication and addition.
  • the neural network NN comprises an input layer, an output layer and a hidden layer. There may be several neurons in each layer. Each cell parameter forms one input neuron in the input layer. There are as many neurons in the output layer as output variables. The number of neurons in the intermediate layer depends on the structure of the network. The signals of the neurons in the network are calculated by combining the variables and/or neurons of the previous layer by using linear or non-linear activation functions.
  • a simple neural network construction NN is disclosed in Figure 1.
  • the structure includes an input layer, one hidden layer and an output layer. There are three cells in the input layer that are not neurons but illustrate values of the input vector. In the hidden layer there are two neurons to which the cells in the input layer are completely connected. The connections comprise weighting coefficients with which the strength of the signal is weighted in summing in the following layer. Each hidden layer and input layer can be associated with a bias vector which has been omitted in this presentation for the sake of simplicity.
  • Figure 1 also shows the algebraic formulae of the neural network example.
  • the neural network construction NN is shown by using matrix and vector formulae. Bias vectors b which improve the operation of the neural network construction NN are also added to the figure.
  • the determination of the weighting coefficients of the neural network takes place by using general training algorithms of neural calculation.
  • a coefficient matrix and a bias vector b are obtained for each neuron layer as a result of the training of the network.
  • the neural network can after this be realized by using mathematical functions, multiplication and summing in a simple programmable form as a computer program.
  • the neural network construction NN comprises two sections: a preclassifier and an actual calculation structure.
  • Physiological and fuzzy features according to Table 1 are used in the preclassification.
  • An advantage of preclassification is that the physiological features define the possible solution area, a small woman, for example, cannot have the lung capacity of a big man.
  • the model of the neural network NN is shown in Figure 3 where the features shown in Table 1 are input quantities. The size of the correlation to the quantity to be measured, that is, to maximal oxygen uptake ability is examined in selecting the features.
  • a backpropagation method for example, or any such suitable method has been used in the training of the neural network NN.
  • Coefficient and bias tables in matrix form according to Figure 5 are obtained as a result.
  • the matrixes of the preclassifier have an identifier F and the matrixes of the basic structure B. Weighting coefficient matrixes are identified by w index and bias vectors by b index. The numerical index notifies the number of the layer.
  • the indication p represents features, that is, input parameters.
  • the invention can be disclosed briefly in such a manner that at first a person's heartbeat at rest is measured for example in a sitting position during a few minutes.
  • Various heartbeat and heartbeat interval parameters such as mean heartbeat, standard deviation, maximum of successive beats and minimum intervals and/or other parameters, are calculated from the heartbeat data by means of software in the microprocessor 8, for example. These parameters are used as supply data in the calculation unit 200.
  • Other data such as age, sex, weight and height, obtained from the supply means 201 is also used as supply data for the calculation unit 200. By combining this data by using different rules, new parameters are derived which can further be made fuzzy by means of fuzzy logic.
  • the invention relates thus to an apparatus A, B for measuring the physical exercise condition, that is, exertion endurance, that is, performance of a subject to be measured.
  • the apparatus comprises means 1 to 4 for detecting resting heartbeat and for sending it to the calculation unit 8, 200 included also in the apparatus.
  • the apparatus also comprises means 201 for supplying physiological input parameters representing the subject to be measured to the calculation unit 8, 200 for calculating an output quantity representing condition, such as maximal oxygen uptake ability, condition classification or any other such indicator of physical exercise condition, on the basis of the physiological features and the heartbeat data also supplied to the calculation unit 8, 200.
  • the apparatus also comprises means 10, such as a display 10 and/or a memory 9, for indicating and/or storing physical exercise condition, that is, exertion endurance obtained as a result of calculation.
  • the apparatus A, B comprises a transmitter unit A and a receiver unit B connected thereto by an inductive, optical or some other wireless telemetric coupling.
  • the transmitter unit A comprises means 1 to 4 for detecting and sending heartbeat signals
  • the receiver unit B comprises means 5 for receiving heartbeat signals from the transmitter unit A, and said calculation unit 8, 200, and said means 201 for supplying the physiological input parameters to the calculation unit 8, 200, and said means 10 for displaying and/or storing the result of calculation.
  • the apparatus A, B implementing the method can be realized in many ways but the Applicant has observed that the most practical and advantageous method is as in Figure 8 which concerns a wrist strap of the heartrate monitor B.
  • the apparatus is integrated as a heartrate monitor B at least for the calculation unit 8, 200, the supply means 201 of physiological data and the display and/or the memory 10.
  • the transmitter unit A included in the apparatus has a wireless coupling to the wrist strap of the heartrate monitor B.
  • the operation of the transmitter unit A can be integrated into the wrist strap of the heartrate monitor B if the measurement of heartbeat on the wrist, for example, is reliable enough.
  • the wrist strap of the heartrate monitor B is on a wrist 600 of a human being 500
  • the transmitter unit A is on the human body, especially on a chest 700 of the human being 500 as a so-called electrode belt.
  • the apparatus preferably the calculation unit 8, 200 comprises means 8 by which one or more of the following resting heartbeat parameters, such as mean heartbeat interval, standard deviation of heartbeat intervals, maximum heartbeat interval, are determined as input parameters from resting heartbeat.
  • resting heartbeat parameters such as mean heartbeat interval, standard deviation of heartbeat intervals, maximum heartbeat interval
  • the calculation unit 200 comprises a calculation formula determined by the neural network construction NN.
  • the apparatus can also be realized by using a portable, transferable or fixed computer equipment to which input parameters are supplied directly or indirectly.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Veterinary Medicine (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Physiology (AREA)
  • Cardiology (AREA)
  • Signal Processing (AREA)
  • Psychiatry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

Procédé et appareil de mesure d'une condition d'un sujet pendant un exercice physique, en particulier procédé de mesure d'un indicateur d'endurance à l'effort représentant une condition d'un sujet à contrôler pendant un exercice, tel que l'absorption d'oxygène maximale ou tout autre indicateur d'endurance du même type représentant une telle condition. Ce procédé se caractérise en ce qu'une formule de calcul prédéterminée est utilisée, de préférence au moyen d'un réseau neuronal, des paramètres physiologiques représentant le sujet à contrôler étant appliqués à cette formule. Ces paramètres d'entrée comprennent au moins l'un des paramètres suivants, à savoir, le sexe, l'âge, la taille, le poids. Un ou plusieurs paramètres de sortie représentant l'indicateur d'endurance à l'effort, lui-même représentant la condition du sujet à contrôler pendant un exercice sont obtenus à partir de la formule de calcul. Outre les paramètres physiologiques, un ou plusieurs paramètres se rapportant aux pulsations cardiaques au repos, mesurés spécifiquement à partir des pulsations cardiaques au repos, sont utilisés comme paramètres d'entrée de la formule de calcul. Dans le mode préféré de réalisation de l'invention, cette formule de calcul est obtenue au moyen d'une structure de réseau neuronal.
PCT/FI1997/000163 1996-03-12 1997-03-12 Procede et appareil de mesure de l'endurance a l'effort WO1997033512A1 (fr)

Priority Applications (5)

Application Number Priority Date Filing Date Title
DE19781642T DE19781642T1 (de) 1996-03-12 1997-03-12 Verfahren und Vorrichtung zum Messen der Ausdauer bei Anstrengungen
DE19781642A DE19781642B4 (de) 1996-03-12 1997-03-12 Verfahren zum Bestimmen eines die maximale Sauerstoffaufnahme beschreibenden Wertes eines zu beurteilenden Lebenswesens
GB9819760A GB2326240B (en) 1996-03-12 1997-03-12 Method for measuring the physical condition of a subject to be measured
US09/142,444 US6277080B1 (en) 1996-03-12 1997-03-12 Method and apparatus for measuring exertion endurance
HK99102020A HK1016857A1 (en) 1996-03-12 1999-05-05 Method for measuring the physical condition of a subject to be measured

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FI961148 1996-03-12
FI961148A FI111514B (fi) 1996-03-12 1996-03-12 Menetelmä mitattavan kohteen fyysisen kunnon mittaamiseksi

Publications (1)

Publication Number Publication Date
WO1997033512A1 true WO1997033512A1 (fr) 1997-09-18

Family

ID=8545638

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/FI1997/000163 WO1997033512A1 (fr) 1996-03-12 1997-03-12 Procede et appareil de mesure de l'endurance a l'effort

Country Status (5)

Country Link
DE (2) DE19781642T1 (fr)
FI (1) FI111514B (fr)
GB (1) GB2326240B (fr)
HK (1) HK1016857A1 (fr)
WO (1) WO1997033512A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1998055022A1 (fr) * 1997-05-21 1998-12-10 Polar Electro Oy Dispositif de mesure non effractif a plusieurs modes de fonctionnement
US6540686B2 (en) 2000-02-23 2003-04-01 Polar Electro Oy Measurement relating to human body
CN106295805A (zh) * 2016-08-16 2017-01-04 王伟 基于bp神经网络的人体最大摄氧量评价方法及其应用

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070260483A1 (en) 2006-05-08 2007-11-08 Marja-Leena Nurmela Mobile communication terminal and method

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE3920526A1 (de) * 1989-06-22 1991-01-10 Lepic Gottlieb Verfahren und vorrichtung zur ermittlung des konditionszustandes einer testperson
DE3922026A1 (de) * 1989-07-05 1991-01-17 Wolfgang Prof Dr Ing Rienecker Mess- und auswertevorrichtung fuer den menschlichen gesundheitszustand
DE4338958A1 (de) * 1992-11-16 1994-05-19 Matsushita Electric Works Ltd Verfahren zum Festlegen einer für das Einhalten einer Sollpulszahl optimalen Leistung und Übungsgerät hierfür

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4566461A (en) * 1983-02-15 1986-01-28 Michael Lubell Health fitness monitor
US5251626A (en) * 1990-07-03 1993-10-12 Telectronics Pacing Systems, Inc. Apparatus and method for the detection and treatment of arrhythmias using a neural network
FR2665831B1 (fr) * 1990-08-17 1992-10-09 Thomson Csf Procede et dispositif d'aide au diagnostic par analyse des bruits du cóoeur.
US5280792A (en) * 1991-09-20 1994-01-25 The University Of Sydney Method and system for automatically classifying intracardiac electrograms
JP3081043B2 (ja) * 1991-12-27 2000-08-28 シスメックス株式会社 脳梗塞の診断方法
DE4307545A1 (de) * 1993-03-10 1994-09-15 Siemens Ag Gerät und Verfahren zur Bestimmung des Ortes und/oder der Ausdehnung von Ischämien und/oder Infarkten im Herzen eines Lebewesens
DE4337110C1 (de) * 1993-10-29 1994-11-03 Michael A J Dietl Verfahren und Vorrichtung zum Betreiben eines Defibrillators

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE3920526A1 (de) * 1989-06-22 1991-01-10 Lepic Gottlieb Verfahren und vorrichtung zur ermittlung des konditionszustandes einer testperson
DE3922026A1 (de) * 1989-07-05 1991-01-17 Wolfgang Prof Dr Ing Rienecker Mess- und auswertevorrichtung fuer den menschlichen gesundheitszustand
DE4338958A1 (de) * 1992-11-16 1994-05-19 Matsushita Electric Works Ltd Verfahren zum Festlegen einer für das Einhalten einer Sollpulszahl optimalen Leistung und Übungsgerät hierfür

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1998055022A1 (fr) * 1997-05-21 1998-12-10 Polar Electro Oy Dispositif de mesure non effractif a plusieurs modes de fonctionnement
EP1405594A1 (fr) * 1997-05-21 2004-04-07 Polar Electro Oy Dispositif de mesure non effractif a plusieurs modes de fonctionnement
US6540686B2 (en) 2000-02-23 2003-04-01 Polar Electro Oy Measurement relating to human body
CN106295805A (zh) * 2016-08-16 2017-01-04 王伟 基于bp神经网络的人体最大摄氧量评价方法及其应用

Also Published As

Publication number Publication date
HK1016857A1 (en) 1999-11-12
GB2326240B (en) 2000-08-23
GB2326240A8 (en) 1999-05-21
FI961148A (fi) 1997-12-12
FI111514B (fi) 2003-08-15
FI961148A0 (fi) 1996-03-12
GB9819760D0 (en) 1998-11-04
DE19781642B4 (de) 2008-01-03
GB2326240A (en) 1998-12-16
DE19781642T1 (de) 1999-03-11

Similar Documents

Publication Publication Date Title
US6277080B1 (en) Method and apparatus for measuring exertion endurance
EP1127542B1 (fr) Commande d'exercice de condition physique
US7366565B2 (en) Exercise machine, physical strength evaluation method and pulse rate meter
US6104947A (en) Method and apparatus for determining exertion levels in fitness or athletic training and for determining the stress caused by training
US6540686B2 (en) Measurement relating to human body
EP1127543B1 (fr) Evaluation non-invasive de la concentration de lactate dans un corps en relation avec un exercice corporel
US4938228A (en) Wrist worn heart rate monitor
US9855007B2 (en) Method and system for determining a ventilatory threshold
US5622180A (en) Device for measuring heartbeat rate
US6217525B1 (en) Reduced lead set device and method for detecting acute cardiac ischemic conditions
EP1147790B1 (fr) Procédé et équipement pour mesurer des paramètres physiologiques
US8292820B2 (en) Apparatus and device for performance monitoring
EP2296540B1 (fr) Procédé et appareil utiles dans le cadre de l'exercice physique
GB2443935A (en) A method and device for monitoring exercise using hemodynamic sensors mounted in a wristop device
CN106725394A (zh) 一种血压数据采集装置及方法
US20200260965A1 (en) System and Method for Estimating the Stroke Volume and/or the Cardiac Output of a Patient
WO1995000070A1 (fr) Dispositif de mesure de quantites liees a la circulation sanguine
WO1997033512A1 (fr) Procede et appareil de mesure de l'endurance a l'effort
JP3250622B2 (ja) カロリー計付き心拍測定装置
US6934577B2 (en) Risk monitoring
RU2226355C2 (ru) Способ определения тренированности спортсмена

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): DE GB US

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): AT BE CH DE DK ES FI FR GB GR IE IT LU MC NL PT SE

DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
121 Ep: the epo has been informed by wipo that ep was designated in this application
ENP Entry into the national phase

Ref document number: 9819760

Country of ref document: GB

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 09142444

Country of ref document: US

RET De translation (de og part 6b)

Ref document number: 19781642

Country of ref document: DE

Date of ref document: 19990311

WWE Wipo information: entry into national phase

Ref document number: 19781642

Country of ref document: DE

122 Ep: pct application non-entry in european phase
REG Reference to national code

Ref country code: DE

Ref legal event code: 8607