APPARATUS, METHOD AND COMPUTER READABLE CODE FOR FORECASTING THE ONSET OF POTENTIALLY LIFE-THREATENING DISEASE

• US 20150141771A1
• Filed: 12/30/2014
• Published: 05/21/2015
• Est. Priority Date: 07/18/2005
• Status: Active Grant

• Current Assignee: Integralis Ltd. (Nippon Telegraph and Telephone Corporation)
• Original Assignee: Integralis Ltd. (Nippon Telegraph and Telephone Corporation)
• Inventors: INBAR, Michael
• Granted Patent: US 9,462,980 B2
• Time in Patent Office: Days
• US Class Current: 600/301
• CPC Class Codes: A61B 5/0008 Temperature signals
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/02411 of foetuses
• CPC Class Codes: A61B 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: A61B 5/0826 Detecting or evaluating apnoea events A61B5/4818 takes precedence
• CPC Class Codes: A61B 5/083 Measuring rate of metabolism by using breath test, e.g. measuring rate of oxygen consumption
• CPC Class Codes: A61B 5/087 Measuring breath flow
• CPC Class Codes: A61B 5/14542 for measuring blood gases A61B5/14551 takes precedence
• CPC Class Codes: A61B 5/363 Detecting tachycardia or bradycardia
• CPC Class Codes: A61B 5/412 Detecting or monitoring sepsis
• CPC Class Codes: 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
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Methods, systems and computer-readable code for generating a forecast of a life-threatening condition, for example sepsis, in a subject, for example an infant, are disclosed. According to some embodiments, the forecast is generated in accordance with measurement values for a plurality of different vital sign parameters. In exemplary embodiments, vital sign parameters from a plurality of physiological systems are used to generate the forecast of the life-threatening condition. In exemplary embodiments, at least one vital sign parameter is other than a cardiac parameter. Non-limiting exemplary vital sign parameters may include one or more of a heart rate parameter, a respiration rate parameter, a bradycardia parameter, a desaturation parameter, a temperature parameter (for example, body temperature) and a body mass parameter.

Claims

1. A method of advancing detection of a condition of sepsis in a premature infant by at least 18 hours, comprising:

a) using physiological sensors to acquire a plurality of different vital sign parameters of an infant, the physiological sensors connected to one or more processors and providing measurement values to the one or more processors of the plurality of different vital sign parameters of the infant, the plurality of different vital signs including a temperature parameter, a heart rate parameter, a respiration parameter, a desaturation parameter, a bradycardia parameter and a body weight parameter;

b) the one or more processors normalizing measurement values of the plurality of different vital signs including, for each of the different vital sign parameters of the infant that is not a bradycardia parameter, normalizing the each of the different vital sign parameters against historical values for said infant, the one or more processors transforming said normalized or un-normalized value;

c) the one or more processors combining the transformed measurement values of the plurality of different vital sign parameters and thereby generating a single sepsis parameter, the single sepsis parameter comprising a single variable having a variable numerical value;

d) the one or more processors monitoring the single sepsis parameter of the infant over time; and

e) the one or more processors detecting a deviation from a normal range indicating the condition of sepsis in the infant from said single sepsis parameter when the single sepsis parameter moves beyond the normal range, said detecting the deviation advancing detection of the condition of sepsis in the infant by at least 18 hours.

2. The method of claim 1 further comprising generating an alarm signal when the one or more processors detecting the deviation from the normal range indicating the condition of sepsis in the infant.

3. The method of claim 1 further comprising the one or more processors detecting onset of late-onset infant sepsis.

4. The method of claim 1 wherein said infant is a very low birth weight infant.

5. The method of claim 1 wherein the one or more processors generates the forecast at least in part by a relation between a measured value of a first said vital sign parameter and at least one threshold value associated with said first vital sign, and at least one said threshold value for said first vital sign depends at least in part on a said measured value of a second vital sign different from said first vital sign.

6. The method of claim 1 wherein providing measurement values includes providing values for at least one said vital sign parameter that are acquired for a plurality of times, and said forecast is determined at least in part by said values for said plurality of times.

7. The method of claim 1 wherein providing measurement values includes providing at least one said vital sign parameter indicative of a state of the skin.

8. The method of claim 1 further comprising acquiring an age parameter of the infant and providing measurement values to the one or more processors of the age of the infant;

and further comprising the one or more processors normalizing the measurement values of at least one of the particular vital sign parameters against the age of the infant.

9. The method of claim 1 wherein providing measurement values includes providing at least one said vital sign parameter that is a metabolic parameter.

10. The method of claim 1 wherein providing measurement values includes providing at least one said vital sign parameter that is indicative of a rate of gas exchange.

11. The method of claim 1 wherein providing measurement values includes providing at least one said vital sign parameter that is indicative of a concentration of a substance in a biological fluid.

12. The method of claim 1 wherein providing measurement values includes providing at least one said vital sign parameter that is indicative of a increase or decrease in tissue mass.

13. The method of claim 1 wherein providing measurement values includes providing at least one said vital sign parameter that is indicative of a cell replication.

14. The method of claim 1 wherein providing measurement values includes providing at least one said vital sign parameter that is a parameter indicative of an apnea condition.

15. The method of claim 1 wherein providing measurement values includes providing at least one said vital sign parameter that is a respiration rate parameter.

16. The method of claim 1 wherein providing measurement values includes providing at least one said vital sign parameter that is a digestion parameter.

17. The method of claim 1 wherein providing measurement values includes providing at least one said vital sign parameter that is indicative of a stable relationship between the infant and the external environment.

18. The method of claim 1 further comprising acquiring an age parameter and a body mass parameter of the infant and providing measurement values to the one or more processors of the age and body mass of the infant;

and further comprising the one or more processors normalizing the measurement values of at least one of the particular vital sign parameters against the age and body mass of the infant.

19. The method of claim 1 wherein said generating of said forecast includes normalizing more than one of said plurality of said vital sign parameters in accordance with a respective normalization function that is different for each said vital sign parameter of said plurality.

20. The method of claim 1 wherein said generating of said forecast includes acquiring a temperature parameter and a cardiac parameter and wherein the temperature parameter and the cardiac parameter are normalized using different functions.

21. The method of claim 1 further comprising:

continuing to monitor the single sepsis parameter after the single sepsis parameter reaches into the normal range, and discontinuing a course of treatment.

22. An apparatus for detecting a condition of sepsis in a premature infant, the apparatus comprising:

a) a data storage unit for storing measurement values for a plurality of different vital sign parameters of an infant, the data storage unit connected to physiological sensors for acquiring the plurality of different vital sign parameters; and

b) a data processing unit in communication with the data storage unit to receive the measurement values, the data processing unit including one or more processors configured to normalize each measurement value, for each of the different vital sign parameters that is not a bradycardia parameter, against historical values for said infant, the one or more processors configured to transform or leave untransformed each of said normalized or un-normalized values,

the one or more processors also configured to combine any said transformed and untransformed normalized values and any said transformed and untransformed un-normalized values, of the plurality of different vital sign parameters and thereby generate a single sepsis parameter, the single sepsis parameter comprising a single variable having a variable numerical value, and

the data processing unit also configured to monitor the single sepsis parameter of the premature infant over time and generate an output indicating a likelihood of the condition of sepsis in the infant from said single sepsis parameter when the single sepsis parameter reaches beyond a normal range, said generating the output advancing detection of the condition of sepsis in the infant by at least 18 hours.

23. The apparatus of claim 22, wherein the data storage unit is connected to physiological sensors for acquiring a temperature parameter, a desaturation parameter, a heart rate parameter, a bradycardia parameter, and a respiration rate parameter and a body weight of the infant.

24. The apparatus of claim 22, further comprising the one or more processors configured to normalize more than one vital sign parameter of said plurality of said different vital sign parameters in accordance with a respective normalization function that is different for each said vital sign parameter of said plurality.

25. A non-transitory computer readable medium comprising program instructions for detecting a condition of sepsis in a premature infant, wherein when executed by one or more processors the program instructions are operable to:

a) access measurement values of a plurality of different vital sign parameters of an infant, the plurality of different vital signs including a temperature parameter, a heart rate parameter, a respiration parameter, a desaturation parameter, a bradycardia parameter and a body weight parameter;

b) normalize each of the temperature parameter, the heart rate parameter, the respiration parameter, the desaturation parameter, and the body weight parameter against historical values of the infant and transform said normalized or un-normalized values;

combine the transformed measurement values of the plurality of different vital sign parameters and thereby generate a single sepsis parameter, the single sepsis parameter comprising a single variable having a variable numerical value; and

c) generate a forecast of the life-threatening condition of sepsis in the infant from said single sepsis parameter when the single sepsis parameter reaches beyond a normal range, said forecast defined as occurring at least 18 hours in advance of a diagnosis derived from clinical and laboratory evidence.