Systems and methods for quantification and prediction of smoking behavior

Abstract

The present invention relates to systems and methods for quantification and prediction of smoking behavior. Systems and methods for monitoring biometrics and contextual variables to help screen for smoking behavior, quantify and predict smoking behavior, and help stop smoking are described.

Description

[0001] This application is a divisional application of an application filed on April 6, 2016, with application number 201680032613.0 and invention name “System and method for quantifying and predicting smoking behavior”.

[0002] Related Applications

[0003] This application is a non-provisional application of U.S. Provisional Application No. 62 / 143,924 filed on April 7, 2015, the entire contents of which are incorporated by reference. Field of the Invention

[0004] The present disclosure relates to systems and methods for monitoring biometrics and contextual variables to help screen for smoking cessation. Systems and methods can non-invasively detect a patient's smoking behavior. Systems and methods can quantify and / or predict a patient's smoking behavior. Systems and methods may help to stop smoking. In some embodiments, systems and methods provide for screening the general population during medical and dental visits and other appropriate health-related appointments. In some embodiments, systems and methods provide for starting and setting up smoking cessation programs for smoking patients. In some embodiments, systems and methods provide follow-up programs after a patient successfully quits smoking. background

[0005] The health problems associated with smoking are well known. Cigarette smoke contains nicotine as well as many other compounds and additives. Tobacco smoke exposes individuals to carbon monoxide as well as these other compounds, many of which are carcinogenic and toxic to the smoker and those around the smoker. The presence and level of carbon monoxide in a smoker's exhaled breath can provide a marker for identifying the individual's overall smoking behavior and provide a marker for their overall exposure to other toxic compounds.

[0006] Because of the health risks and problems associated with smoking, in addition to the effects of smoking on exposed non-smokers, many programs exist to help individuals stop smoking or at least reduce the amount they smoke per day.

[0007] Smoking cessation programs and products often attempt to reduce patients’ smoking without fully understanding smoking behaviors that may vary between patients. Furthermore, it may be difficult to understand patients’ smoking behaviors given that self-reporting of smoking behaviors relies on strict adherence to reporting smoking activities. And in many cases, individuals may not strictly adhere to reporting such activities due to shame, carelessness, and / or human error associated with tracking and assessing smoking.

[0008] There remains a need for addressing an individual's smoking by first understanding the individual's smoking behavior and then engaging the individual in effective means for reducing and terminating smoking based on this understanding. SUMMARY OF THE INVENTION

[0009] The system and method described herein allow the multi-stage method that makes the individual of smoking participate and quantify its smoking behavior to better help the individual finally achieve the goal of stopping smoking.The method and system described herein allow even before the individual is given the difficult task of trying to quit smoking, the measurement and quantification of the improvement of smoker's behavior.For example, the system and method described herein can be used for using objective criteria to identify the smoker group from a larger group.Once the individual smoker is identified, the same method and system allow the learning and exploration stage that the specific smoking behavior of the individual can be tracked and quantified.The method and system also allow tracking the behavioral data of the individual, to identify the potential triggering factors of smoking, or just educate the individual for the degree of its smoking.The method and system also allow the individual who has decided to participate in the "quit smoking" project to be monitored more actively, wherein this monitoring allows the individual to carry out self-monitoring and monitor by companion, coach or counselor.Finally, the method and system disclosed herein can be used for monitoring the individual of successful quitting smoking, to ensure that smoking behavior no longer occurs.

[0010] Systems and methods for evaluating an individual's smoking behavior are described herein. The system can allow for quantification of an individual's smoking behavior by measuring biometric data and evaluating factors attributed to cigarette smoke and evaluating behavioral data associated with smoking or the individual's general activities.

[0011] The system and method can detect and quantify the smoking behavior of the patient based on one or more (such as, CO level or exhaled CO level) of measuring the biometric data of the patient non-invasively. However, other biometric data can also be used. These data include carboxyhemoglobin (SpCO), oxygenated hemoglobin (SpO2), heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse speed, skin galvanic response, pupil size, geographic location, environment, ambient temperature, stressor, life events and other suitable parameters. Such measurement or data collection can use a portable measurement unit or a fixed measurement unit, any of which communicates with one or more electronic devices for performing quantitative analysis. Optionally, analysis can be performed in a portable / fixed unit. For example, the portable unit can be coupled to a keychain, an individual's cigarette lighter, a mobile phone or other items that will often be with the individual. Optionally, the portable unit can be a stand-alone unit, or it can be worn by the individual.

[0012] In one variation, the methods described herein allow for quantifying an individual's smoking behavior by: obtaining multiple samples of exhaled breath from an individual over a period of time and recording the collection time associated with each sample of exhaled breath; measuring the amount of exhaled carbon monoxide for each of the samples of exhaled breath; compiling a data set including the amount of exhaled carbon monoxide and the collection time for each sample of exhaled breath; using the data set to quantify the exposure to exhaled carbon monoxide over time intervals within the period of time, and assigning the exhaled carbon monoxide load to the time intervals; and displaying the exhaled carbon monoxide load. Displaying the quantified results can occur at one or more locations to provide feedback to the individual, a caregiver, or any other individual associated with understanding and / or reducing the individual's smoking behavior.

[0013] In further variations, obtaining the plurality of samples of exhaled breath from an individual over a period of time and recording the time of collection of each sample of exhaled breath includes obtaining the plurality of samples of exhaled breath sequentially.

[0014] Quantifying the exposure of exhaled carbon monoxide may include using the data set to correlate the exhaled carbon monoxide with respect to the function of time during the time period. Alternatively, the quantification may include the mathematical product of the CO level and time over the time interval. Such quantification allows for improved observation of smoking behavior because it allows for observation of the body's overall exposure to CO over a given time interval.

[0015] In further variations, the method further includes obtaining an area of ​​exhaled carbon monoxide and time over the time interval according to a curve defined by the function.

[0016] The method and system may also include generating a signal, for example using a portable device that utilizes the individual's location, to remind the individual to provide at least one sample of exhaled breath. In further variations, the method may include alerting the individual on a recurring basis to provide a sample of exhaled breath within a period of time.

[0017] The above method may also include receiving input data from the individual and recording the time of the input. Such data may include behavioral data such as a count of a portion of cigarettes smoked by the individual. Optionally, the data may include information about location (via a GPS unit), diet, activity (e.g., driving, watching TV, dining, working, socializing, etc.).

[0018] The method may include visually displaying any of the input data. Including the sum of counts of partial cigarettes smoked by an individual. Such data may also allow for display of calculated information. For example, cigarette counts may be used to determine an individual's nicotine exposure from cigarettes when direct biometrics may also erroneously measure nicotine from a nicotine patch or nicotine gum. Additionally, cigarette data may be used to estimate the cost associated with the number of cigarettes smoked by an individual and display such cigarette cost.

[0019] The method may also include determining a nicotine estimate using the count of portions of the cigarette smoked by the individual and displaying the nicotine estimate.

[0020] The method may further include providing a visual display of the exhaled carbon monoxide load over a period of time associated with the visual display time interval. Additionally, the method may include providing a visual display of a count of the number of the plurality of exhaled breath samples.

[0021] The method may also include determining a series of exhaled carbon monoxide loads for a series of time intervals over a period of time.In addition to the information discussed herein, these values ​​may also be displayed.

[0022] In the method, measuring the amount of exhaled carbon monoxide may include using a portable sensor.

[0023] The method may also include transmitting the collection time and the amount of exhaled carbon monoxide associated with each sample of exhaled breath from the portable sensor to the electronic device.

[0024] The method may also include obtaining a location of the individual when obtaining at least one of the plurality of exhaled breath samples.

[0025] The method may also include obtaining results of a behavioral questionnaire from the individual and displaying the results of the behavioral questionnaire with the exhaled carbon monoxide load.

[0026] In the method, quantifying the exposure to exhaled carbon monoxide over time intervals within a time period may include estimating a decay rate of the carbon monoxide.

[0027] In the method, quantifying the exposure to exhaled carbon monoxide over time intervals within a time period may include estimating an increase in the rate of carbon monoxide while the individual smokes a cigarette.

[0028] Another variation of quantifying an individual's smoking behavior may include obtaining multiple samples of carbon monoxide from the individual over a period of time and recording the collection time associated with each sample of carbon monoxide; compiling a data set including the collection time for each sample of carbon monoxide and the amount of carbon monoxide; quantifying exposure to carbon monoxide over time intervals over the period of time and assigning carbon monoxide burden to the time intervals using the data set; and displaying the carbon monoxide burden. In this case, the amount of carbon monoxide is determined based on any type of measurement that identifies the level of carbon monoxide in the body.

[0029] The method may also include obtaining multiple samples of carbon monoxide, which includes obtaining multiple samples of exhaled breath from the individual over time and measuring the amount of exhaled carbon monoxide for each of the samples of exhaled breath, and wherein recording the collection time associated with each sample of carbon monoxide includes recording the collection time associated with each sample of exhaled breath.

[0030] The present disclosure also includes a device for obtaining data to quantify an individual's smoking behavior. Such a device may assist or perform the functions described herein.

[0031] In one example, the device includes a portable breathing unit configured to receive multiple samples of exhaled breath from an individual over a period of time and configured to record a collection time associated with each sample of exhaled breath; a sensor located within the unit and configured to measure the amount of exhaled carbon monoxide for each of the samples of exhaled breath; at least one input switch configured to record input data from the individual; a storage unit configured to store at least the amount of exhaled carbon monoxide and the collection time; a transmitter configured to transmit the amount of exhaled carbon monoxide, the collection time, and the input data to an external electronic device; and an alarm unit configured to provide an alarm to a user to submit multiple samples of exhaled breath.

[0032] The methods described herein may also include methods for developing a program to help patients who smoke to stop smoking. For example, the method may include measuring at least one biological indicator that determines whether the patient smokes; capturing multiple patient data, wherein the patient data includes information related to when the patient smokes in time; combining at least one of the multiple patient data and at least one biological indicator to determine the patient's smoking behavior model during a first test period; evaluating the smoking behavior model to evaluate the degree of intervention required for the smoking cessation program; and providing a summary report of the smoking behavior model and the degree of intervention.

[0033] In another variation, the present disclosure includes a system for preventing a patient from smoking. For example, the system may include a sensor for measuring at least one biological indicator for determining whether a patient is smoking; a data collection device configured to capture a plurality of patient data, wherein the patient data includes information related to when the patient is smoking in time; a processor in communication with the sensor and the data collection device, the processor being configured to compile a plurality of patient data and at least one biological indicator to determine a smoking behavior model of the patient within a first test period; the processor being configured to generate at least one disturbance signal before a second test period, and wherein the processor analyzes at least one of the patient data captured within the second test period to determine a smoking behavior of the test; and wherein the processor compares the smoking behavior of the test with the model smoking behavior to determine whether the patient is prevented from smoking.

[0034] The present disclosure also includes a method for preventing a patient from smoking. For example, such a method may include measuring at least one biological indicator for determining whether a patient smokes; collecting a plurality of patient data, wherein the patient data includes information related to when the patient smokes in time; compiling a plurality of patient data and at least one biological indicator to determine a smoking behavior model of the patient; generating at least one disturbance signal before a second test period, wherein at least one disturbance signal affects the patient; analyzing at least one of the patient data captured during the second test period to determine a tested smoking behavior; and comparing the tested smoking behavior with the model smoking behavior to determine a change from the smoking behavior model, thereby determining whether the patient is prevented from smoking.

[0035] In another embodiment, a system for preventing a patient from smoking may include: a database containing a smoking behavior model of the patient, wherein the smoking behavior model includes multiple historical patient data temporally correlated with when the patient smoked; a sensor for measuring at least one biological indicator for determining whether the patient smokes; a processor configured to determine an expected smoking event when analyzing the smoking behavior model, and after determining the expected smoking event, the processor generates at least one disturbance signal before a test period; the processor is configured to check at least one biological indicator during the test period to determine whether the patient is prevented from smoking during the test period; and wherein after determining whether the patient is prevented from smoking during the test period, the processor updates the database containing the smoking behavior model.

[0036] Another variation of a method for deterring smoking may include: accessing a database containing a smoking behavior model of a patient, wherein the smoking behavior model includes a plurality of historical patient data temporally correlated with when the patient smokes; estimating expected smoking events when analyzing the smoking behavior model; generating at least one disturbance signal before a test period after a processor determines the expected smoking event; measuring at least one biological indicator that determines whether the patient smokes during the test period; checking at least one biological indicator during the test period to determine whether the patient is deterred from smoking during the test period; and updating the database containing the smoking behavior model after determining whether the patient is deterred from smoking during the test period.

[0037] The above is a brief description of some methods and systems for quantifying smoking behavior and projects for effectively stopping smoking. Other features, advantages and embodiments of the present invention will become apparent to those skilled in the art from the following description and drawings, in which specific forms of the present invention are described in detail for illustrative purposes only. Variations of the access devices and processes described herein include combinations of features of the various embodiments or combinations of the embodiments themselves (where possible).

[0038] Although the disclosure discusses cigarettes in various examples, the methods, systems and improvements disclosed herein can be applied to any type of tobacco smoke or other inhaled smoke. In this case, the disclosure contemplates replacing "cigarettes" with appropriate types of tobacco or smoke generating products (including but not limited to cigars, pipes, etc.). BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 depicts an illustrative system including a wearable device, a mobile device, and a remote server in communication with the wearable device and the mobile device according to some embodiments of the present disclosure;

[0040] Figure 2 Another illustrative system including a wearable device and a remote server in communication with the wearable device according to some embodiments of the present disclosure is depicted;

[0041] Figure 3 depicts illustrative light absorption curves for various types of hemoglobin that allow for measurement of carboxyhemoglobin (SpCO) and oxyhemoglobin (SpO2) levels using a photoplethysmography (PPG) sensor in accordance with some embodiments of the present disclosure;

[0042] Figure 4 depicts a graph of different SpCO levels for a patient over a typical five day monitoring period prior to beginning a smoking cessation program according to some embodiments of the present disclosure;

[0043] Figure 5depicts a trend graph of a patient's SpCO levels and smoking triggers during a typical day before starting a smoking cessation program according to some embodiments of the present disclosure;

[0044] Figure 6 depicts a data structure for storing SpCO levels and smoking triggers for a patient during a typical day according to some embodiments of the present disclosure;

[0045] Figure 7 depicts an illustrative flow chart for detecting a patient's smoking behavior according to some embodiments of the present disclosure;

[0046] Figure 8 depicts a sample report after five days of evaluating a patient according to some embodiments of the present disclosure;

[0047] Fig. 9 An illustrative graph depicting patient SpCO levels during a run-in and smoking cessation program according to some embodiments of the present disclosure;

[0048] Fig.10 depicts an illustrative smartphone application screen displaying measurements such as SpCO, SpO2, heart rate, respiratory rate, blood pressure, and temperature in accordance with some embodiments of the present disclosure;

[0049] Fig.11 depicts an illustrative smartphone application screen for receiving patient-entered data according to some embodiments of the present disclosure;

[0050] Fig.12 depicts an illustrative smartphone application screen implementing a smoking prevention regimen in accordance with some embodiments of the present disclosure;

[0051] Fig.13 depicts an illustrative smartphone application screen for presenting the smoking cessation process as a game for a patient in accordance with some embodiments of the present disclosure;

[0052] Fig.14 depicts an illustrative flow chart for predicting and preventing anticipated smoking events according to some embodiments of the present disclosure;

[0053] Fig.15 Describes some embodiments of the present disclosure Fig.14 illustrative flow chart of step 1414 for determining whether a prevention regimen was successful;

[0054] Fig.16 depicts an illustrative flow chart of a measurement of a patient's SpCO level using a PPG sensor according to some embodiments of the present disclosure;

[0055] Fig.17 depicts an illustrative flow chart for detecting a smoking event according to some embodiments of the present disclosure; and

[0056] Fig.18 An illustrative flow chart for applying one or more perturbations to a model of a patient's smoking behavior is depicted, according to some embodiments of the present disclosure.

[0057] Fig.19 Another variation of a system and / or method for influencing an individual's smoking behavior and further quantifying an individual's exposure to cigarette smoke using aspects described herein is shown.

[0058] Fig. 20A Shows that it is possible to use Fig.19 A visual representation of the data collected by a variation of the system shown.

[0059] Fig. 20B Shows that it is possible to use Fig.19 A visual representation of the data collected by a variation of the system shown.

[0060] Fig.21 An example of a data set for determining an eCO profile over a period of time is shown, where the eCO attributable to an individual's smoking behavior may be quantified over various time intervals to determine an eCO burden or eCO load for each interval.

[0061] Fig. 22 Examples are shown that display biometric data and various other information used to assess an individual's smoking behavior.

[0062] Fig.23 Shows the display and Fig. 22 The information shown in is another variation of the dashboard with similar information.

[0063] FIG. 24A to FIG. 24C Another variation of a data set is shown that includes exhaled carbon monoxide, collection time, and cigarette data that are quantified and displayed to benefit individuals seeking to understand their smoking behavior.

[0064] Detailed Description of the Invention

[0065] Systems and methods for smoking cessation using interactive screening are described. The systems and methods are based on measuring one or more of the patient's carbon monoxide level, exhaled carbon monoxide level (eCO), carboxyhemoglobin (SpCO), oxyhemoglobin (SpO2), heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters to non-invasively detect and quantify the patient's smoking behavior. It is worth noting that SpCO and eCO are two ways to measure CO levels in the patient's blood.

[0066] In some embodiments, systems and methods described herein provide for screening the general population during medical and dental visits and other suitable health-related appointments. Wearable devices can be applied to patients during, for example, their annual visits to detect recent smoking behavior, and if positive, recommend smokers to undergo further testing and ultimately to quit smoking programs. In some embodiments, wearable devices are applied as disposable field measurements. In some embodiments, patients are provided with wearable devices to wear a time period as outpatients, such as a day, a week, or another appropriate time period. Longer wearing times may provide higher sensitivity when detecting smoking behavior, and provide higher accuracy when quantifying variables related to smoking behavior.

[0067] When the wearable device is worn in an appropriate time period (e.g., five days), multiple parameters can be measured in real time or near real time. These parameters may include, but are not limited to, CO, eCO, SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse speed, skin galvanic response, pupil size, geographic location, environment, ambient temperature, stressor, life events, and other suitable parameters. Data from the wearable device can be sent to a smart phone or cloud server or another suitable device in real time, near real time, at the end of each day, or according to another suitable time interval. Wearable devices or smart phones can measure parameters, including but not limited to movement, position, time of day, data entered by the patient, and other suitable parameters. The data entered by the patient may include stressors, life events, positions, daily events, the use of nicotine patches or other nicotine formulations, the use of other smoking cessation drugs, and other suitable patient input data. For example, some of the data entered by the patient may include information about phone calls, exercise, work, sports, pressure, gender, drinking, smoking, and other suitable patient input data. The received data may be compiled, trended, and correlated in real time or after a time period has been completed.

[0068] According to the parameters measured above, information about smoking can be obtained via a processor located in a wearable device, a smart phone, a cloud server or another suitable device.For example, the processor can analyze information to determine CO, eCO, SpCO trends, mean values, peak values, changes, specific curve features, slopes of changes and other types of changes, and determine the association with other biometrics and situational variable trends during a day, and how these variables change before, during and after smoking.The processor can analyze CO, eCO, SpCO trends to determine parameters, such as the total number of smoking, the average number of smoking per day, the maximum number of smoking per day, the intensity of each cigarette sucked, the amount (quantity) of each cigarette sucked, the time of sucking each cigarette, the time of the day, the day of the week, the associated stressors, geography, position and motion.For example, the total number of peak values ​​in a given day can indicate the number of smoking, and the shape and size of each peak value and other characteristics can indicate the intensity and amount of each cigarette sucked.The processor can analyze heart rate and / or pulse rate data to determine the correlation between trend, mean value and peak value and patient smoking behavior. For example, the processor may correlate changes in heart rate (such as tachycardia or heart rate variability) that occur before or during a smoking event that may predict when the patient will smoke. This information can be used to preempt smoking events during a smoking cessation program. For example, if a smoking event is predicted to occur within the next 10 minutes, the patient may be notified to deliver a dose of nicotine by any of a number of mechanisms, such as delivery via a transdermal patch or transdermal transfer from a reservoir of nicotine stored in a wearable device.

[0069] In some embodiments, the system and method described herein provide for evaluating the smoking behavior of the patient in two test periods. During the first test period, the patient behaves as he usually does. A processor located in a wearable device, a smart phone, a cloud server or other suitable device receives patient data related to the patient's smoking behavior. Since the purpose of the test period is to observe the patient's smoking pattern, the patient hardly participates. Before the second test period, the processor determines a model of how the patient smokes.

[0070] During the second test period, the processor applies a series of perturbations to the model to see if the smoking behavior changes. Perturbations can be applied to the model using a machine learning process. The machine learning process delivers the perturbations, tests the results, and adjusts the perturbations accordingly. The processor determines the most effective way to achieve the identified behavior change by trying options through the machine learning process.

[0071] There may be several types of disturbances, each of which has several dimensions. For example, a disturbance may be whether a text message sent before or during a smoking event causes a smoking event to be avoided or shortened. The dimension in the disturbance may be different senders, different timings and / or different contents for a text message. In another example, a disturbance may be whether a telephone call at a certain time of day or before or during a smoking event causes a smoking event to be avoided or shortened. The dimension in the disturbance may be different callers, different timings and / or different contents for a telephone call. In yet another example, a disturbance may be to warn a patient to check their smoking behavior at several points in the day to avoid smoking in a time period thereafter. The dimension may include determining whether and when to eliminate the avoidance. In other examples, a disturbance may be a reward, team action or other suitable trigger to avoid or shorten the patient's smoking event.

[0072] In some embodiments, the systems and methods described herein provide patients with a method for starting and setting up a smoking cessation program. After the patient completes a five-day assessment while wearing a wearable device, the complete data set is compiled and analyzed by the system and delivered to the patient or doctor for use in a smoking cessation program. For example, a sample report may indicate that from October 1 to October 6, Mr. Jones smoked a total of 175 cigarettes, an average of 35 cigarettes per day, and the maximum number of cigarettes smoked in a day was 45. Mr. Jones's CO level averaged 5.5%, with a maximum of 20.7%, and was continuously above 4% for 60% of the five-day assessment period. Mr. Jones' triggers include work, family stressors, and commuting. Given Mr. Jones's smoking habits, the report recommends high-dose and frequent nicotine level predictions for starting nicotine replacement therapy. If the treatment plan is customized to the patient's needs from the beginning, this may achieve a higher probability of patient compliance in a smoking cessation program.

[0073] In some embodiments, data collected during a five-day assessment period while the patient was smoking conventionally and prior to a smoking cessation program is used to establish a baseline for the patient's vital signs, such as CO, eCO, SpCO levels. The system can generate a baseline curve for the patient's vital signs based on the differences in CO, eCO, SpCO levels in the collected data. The baseline curve can serve as a reference for comparison with future measurements of the patient's CO, eCO, SpCO levels.

[0074] In some embodiments, patients work with their physicians or counselors to begin the process of entering a smoking cessation program. Having objective data in front of physicians and patients can aid in the setup of smoking cessation programs and in developing medication and counseling plans. In some embodiments, the system automatically sets up a smoking cessation program based on data from the evaluation period. The collected data may affect the initiation and setup of a smoking cessation program for patients just before they enter the program by assisting with medication selection and dispensing. For example, indications of higher and more frequent smoking may prompt the start of a higher nicotine replacement therapy dose or multiple medications (e.g., adding a medication for treating nicotine addiction, such as varenicline).

[0075] The data collected may influence the initiation and setting of smoking cessation programs by determining the frequency, type, and duration of counseling required for patients. The data may lead to a stratification of smoker needs. For example, smokers at the highest risk of the highest use may receive more intervention, while smokers at lower risk may receive less intervention. Intervention may include a text message, phone call, social network message, or another suitable event from the patient's spouse, friend, doctor, or another suitable stakeholder at a specific time of the day when the patient is likely to smoke.

[0076] The data collected may affect the start and setting of smoking cessation programs by combining smoking behavior with all the above variables (such as, the stressors that prompt smoking, the time of day, and other appropriate variables for consulting patients in advance to be aware of these triggers). Consultation intervention may be directed to these stressors. Intervention can be directed to patients at those times of the day, such as text messages or phone calls at those times of the day. The data collected may affect the start and setting of smoking cessation programs by allocating peer groups based on smoking behavior. The data collected can be used to predict and / or avoid smoking events. For example, if tachycardia or heart rate variability occurs before most smoking events, this can sound an alarm, and the patient can take a dose of medication, or can receive a phone call from a peer group, a doctor, or a counselor to avoid smoking events.

[0077] In some embodiments, the systems and methods described herein provide for maintaining patient participation in a smoking cessation program. Once in a smoking cessation program, the patient may continue to wear a wearable device for monitoring. The system may use analytical tools, such as setting a CO, eCO, SpCO baseline and tracking progress against the baseline. For example, a trend may drop to zero and stay there (indicating no more smoking). A trend may slowly drop with peaks and valleys (indicating a reduction in smoking). A trend may drop to zero and then spike again (indicating a relapse).

[0078] The system can present the patient's progress as a game and increase visibility of progress. For example, the system can offer a small reward to the patient in exchange for quitting smoking within a certain period of time. In some embodiments, the system can transmit data to healthcare providers in real time for remote monitoring and allow providers to effectively monitor and adjust patient care without having the patient appear in the office every day.

[0079] In some embodiments, the systems and methods described herein provide a follow-up program after a patient successfully quits smoking. After successful quitting smoking verified by the system, the patient wears the wearable device for an extended period of time, such as several months to two years, as an early detection system for relapse. The system can collect data and employ a counseling strategy for a smoking cessation program as described above.

[0080] In some embodiments, the systems and methods described herein provide a system that includes one or more mobile devices and a server in communication with the mobile devices. Figure 1 An exemplary embodiment 100 for such a system including a device 102, a device 104, and a server 106 in communication with the device 102 and the device 104 is shown. The device 102 assists in detecting the smoking behavior of the patient. The device 102 includes a processor, a memory, and a communication link for sending and receiving data from the device 104 and / or the server 106. The device 102 includes one or more sensors to measure the smoking behavior of the patient based on measuring one or more of the patient's CO, eCO, SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters. For example, the device 102 may include PPG-based sensors for measuring CO, eCO, SpCO, and SpO2, electrocardiogram-based sensors for measuring heart rate and blood pressure, acoustic signal processing-based sensors for measuring respiratory rate, wearable temperature sensors for measuring body temperature, skin conductance, electroencephalogram-based sensors for measuring skin electrical activity, implantable sensors placed in the skin, fat, or muscle to measure CO and other variables, intraoral CO sensors, ambient CO sensors, and other suitable sensors. These sensors may have various locations on or in the body for optimal monitoring.

[0081] Device 102 may be portable or wearable. For example, device 102 may be wearable in a manner similar to a wristwatch. In another example, device 102 may be portable or wearable and attached to a fingertip, earlobe, auricle, toe, chest, ankle, arm, skin fold, or another appropriate body part. Device 102 may be attached to a suitable body part via a clip, a strip, a belt, an adhesively applied sensor pad, or other suitable medium. For example, device 102 may be attached to a fingertip via a finger clip. In another example, device 102 may be attached to an earlobe or auricle via an ear clip. In yet another example, device 102 may be attached to a toe via a toe clip. In yet another example, device 102 may be attached to a chest via a chest strap. In yet another example, device 102 may be attached to an ankle via an ankle strap. In yet another example, device 102 may be attached to an arm via a biceps or triceps strap. In yet another example, device 102 may be attached to a skin fold via a sensor pad.

[0082] The device 102 may prompt the patient for a sample or the device (if worn) may perform sampling without the patient's consent. Sampling may be sporadic, continuous, nearly continuous, periodic, or based on any other suitable interval. In some embodiments, sampling is performed continuously whenever the sensor is capable of taking a measurement. In some embodiments, sampling is performed continuously after a set time interval (such as five minutes or fifteen minutes) or another suitable time interval.

[0083] In some embodiments, device 102 includes one or more sensors that monitor SpCO using a transcutaneous method such as PPG. Transcutaneous monitoring can use a transmissive or reflective method. Device 104 can be a smart phone or another suitable mobile device. Device 104 includes a processor, a memory, and a communication link for sending and receiving data from device 102 and / or server 106. Device 104 can receive data from device 102. Device 104 may include an accelerometer, a global positioning system-based sensor, a gyroscopic sensor, and other suitable sensors for tracking the described parameters. Device 104 can measure specific parameters, including but not limited to movement, location, time of day, patient-entered data, and other suitable parameters.

[0084] The data of patient input received by device 104 may include stressors, life events, geographic location, daily events, the application of nicotine patches or other formulations, the application of other drugs for smoking cessation, and other suitable patient input data. For example, some of the data input by the patient may include information about phone calls, sports, work, sports, stress, gender, drinking, smoking, and other suitable patient input data. The patient's smart phone for texting, calling, surfing the Internet, playing games, and other suitable uses may also be associated with smoking behavior, and these associations are used to predict behavior and change behavior. Device 104 or server 106 (after receiving data) can compile data in real time or after the specified time period is completed, perform trend analysis on data, and associate data. Server 106 includes a processor, a memory, and a communication link for sending and receiving data from device 102 and / or device 104. Server 106 can be located at a location away from devices 102 and 104, such as a healthcare provider site or another suitable location.

[0085] Figure 2 An exemplary embodiment 200 for a system including a device 202 and a server 204 communicating with the device 202 is shown. The device 202 assists in detecting the smoking behavior of the patient. The device 202 includes a processor, a memory, and a communication link for sending and receiving data from the server 204. The device 202 can be portable or wearable. For example, the device 202 can be wearable in a manner similar to a wristwatch. The device 202 includes one or more sensors 206 to measure the smoking behavior of the patient based on one or more of measuring the CO, eCO, SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse speed, skin galvanic response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters of the patient.

[0086] Device 202 may include one or more sensors 208 to measure specific parameters, including but not limited to movement, position, time of day, patient input data and other suitable parameters. The data input by the patient may include stressors, life events, positions, daily events, the application of nicotine patches or other formulations, the application of other smoking cessation drugs and other suitable patient input data. The data input by the patient may be received on a mobile device (such as device 104) in response to a prompt to the patient, or may be input without prompting according to the patient's wishes. For example, some of the data input by the patient may include information about phone calls, sports, work, sports, stress, gender, drinking, smoking and other suitable patient input data. Device 202 or server 204 (after receiving the data) may compile data, analyze data to obtain trends and correlate data in real time or after a specified time period is completed. Server 204 includes a processor, a memory and a communication link for sending and receiving data from device 202. Server 204 may be located at a location away from device 202, such as a healthcare provider site or another suitable location.

[0087] In some embodiments, device 102 or 202 includes a detector unit and a communication unit. Device 102 or 202 may include a user interface suitable for its specific function. The user interface may receive input via a touch screen, a keyboard or another suitable input mechanism. The detector unit includes at least one test element, which is capable of using input from a patient's biological parameters to detect a substance indicating smoking behavior. The detector unit analyzes biological input from the patient, such as exhaled gas from the lungs, saliva or the wavelength of light guided through the tissue or reflected by the tissue. In some embodiments, the detector unit uses PPG to monitor the patient's SpCO. The detector unit may optionally measure multiple other variables, including but not limited to SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse speed, skin galvanic response, pupil size, geographic location, environment, ambient temperature, stressor, life events and other suitable parameters. For a sensor based on breathing, the patient input may include blowing into a tube as a part of the detector unit. For saliva or other body fluid-based sensors, the patient input may include placing a fluid sample in a test chamber disposed in the detector unit.

[0088] For light-based sensors such as PPG, patient input may include placing an emitter-detector on a finger or other area of ​​exposed skin. The detector unit records the date and time of day, quantifies the presence of the target substance, and stores the data for future analysis and / or sends the data to another location for analysis, such as device 104 or server 106. The communication unit includes appropriate circuitry for establishing a communication link with another device (e.g., device 104) via a wired or wireless connection. The wireless connection may be established using WI-FI, Bluetooth, radio frequency, or other suitable schemes.

[0089] Figure 3 An illustrative embodiment 300 of suitable wavelengths for analyzing SpO2 and SpCO using a light-based sensor is depicted. The patient's SpCO can be measured by intermittently testing the patient's exhaled breath using a suitable sensor. In another example, a transcutaneous method such as photoplethysmography (PPG) can be used to measure the patient's SpCO. SpCO is detected by passing light through patient tissue (e.g., earlobe, pinna, fingertip, toe, skin fold, or another appropriate body part) and analyzing the attenuation of various wavelengths. SpO2 is typically measured using two wavelengths (e.g., 302 (660 nm) and 306 (940 nm). SpCO may be measured using three wavelengths (e.g., 302 (660 nm), 304 (810 nm), and 306 (940 nm)) or up to seven or more wavelengths (e.g., a range of 500-1000 nm). Such a PPG sensor may be implemented via a finger clip, a strip, an adhesively applied sensor pad, or another suitable medium. The PPG sensor may be transmissive, such as used in many pulse oximeters. In a transmissive PPG sensor, two or more waveforms of light are transmitted through patient tissue (e.g., a finger), and a sensor / receiver on the other side of the target analyzes the received waveforms to determine SpCO. Alternatively, the PPG sensor may be reflective. In a reflective PPG sensor, light shines onto a target (e.g., a finger), and a receiver / sensor picks up the reflected light to determine a measurement of SpCO. More details are provided below.

[0090] Transcutaneous or transmucosal sensors can non-invasively determine blood CO levels and other parameters based on analysis of the attenuation of light signals passing through tissue. Transmissive sensors are typically placed against a thin body part, such as an earlobe, auricle, fingertip, toe, skin fold, or another appropriate body part. Light is shone from one side of the tissue and detected on the other side. The light emitting diodes on one side are tuned to a specific set of wavelengths. The receiver or detector on the other side detects which waveforms are transmitted and how much they are attenuated. This information is used to determine the percentage of O2 and / or CO bound to hemoglobin molecules, i.e., SpO2 and / or SpCO.

[0091] Reflection sensors can be used for thicker body parts, such as the wrist. Light irradiated at the surface is not measured on the other side, but is measured on the same side in the form of light reflected from the surface. The wavelength and attenuation of the reflected light are used to determine SpO2 and / or SpCO. In some embodiments, an accelerometer is used to correct problems caused by movement of the patient's wrist. For example, information from the accelerometer is used to correct errors in SpO2 and SpCO values ​​due to movement. An example of such a sensor is disclosed in U.S. Patent No. 8,224,411, entitled "Noninvasive Multi-Parameter Patient Monitor". Another example of a suitable sensor is disclosed in U.S. Patent No. 8,311,601, entitled "Reflectance and / or Transmissive PulseOximeter". Both of these U.S. patents are incorporated herein by reference in their entirety, including all materials incorporated therein by reference.

[0092] In some embodiments, device 102 or 202 is configured to identify unique features of the patient, such as fingerprints, retinal scans, voice tags or other biometric identifiers to prevent having proxy responses to signaling and test prompts that render the system inoperable. To this end, a patient identification subunit may be included in device 102 or 202. One of ordinary skill in the art may configure the identification subunit as needed to include one or more of a fingerprint scanner, retinal scanner, voice analyzer or facial recognition known in the art. Examples of suitable identification subunits are disclosed in, for example, U.S. Patent No. 7,716,383 entitled "Flash-interfaced Fingerprint Sensor" and U.S. Patent Application Publication No. 2007 / 0005988 entitled "Multimodal Authentication", each of which is incorporated herein by reference in its entirety.

[0093] The identification subunit may include a built-in still or video camera for automatically recording a picture or video of the patient while the biometric input is provided to the test element. Regardless of the type of identification scheme used, the device 102 or 202 may associate an identification with a particular biometric input, such as by a time reference, and may store that information along with other information about the particular biometric input for later analysis.

[0094] The patient may also attempt to disable the detector by blowing air into the detector with a pump, bladder, billow or other device, for example, when testing the exhaled breath. In an embodiment of the saliva test, the patient may attempt to replace a clean liquid such as water. For a light-based sensor, the patient may ask a friend to replace him or her. Means to disable these attempts can be incorporated into the system. For example, the device 102 or 202 may include the ability to distinguish between real and simulated exhaled breath delivery. This function can be incorporated by configuring the detector unit to sense oxygen and carbon dioxide and target substances (e.g., carbon monoxide). In this way, the detector unit can confirm that the gas analyzed comes from exhaled breath with lower oxygen and higher carbon dioxide than ambient air. In another example, the detector unit can be configured to detect enzymes naturally present in saliva to distinguish saliva from other liquids. In yet another example, a light-based sensor can be used to measure blood chemistry parameters other than CO levels, and the results can be compared with known samples representing the patient's blood chemistry.

[0095] In some embodiments, device 104 (e.g., a smart phone) receives measurements from device 102 (e.g., a wearable device) periodically, in real time, or in near real time according to appropriate intervals. Device 104 may provide a user interface for prompting the patient for certain inputs. Device 104 may provide a user interface for displaying certain outputs of the collected data. Device 104 may allow the patient to enter information that the patient believes is relevant to his or her condition without prompting or responding to prompts. Such information may include information about the patient's psychological state, such as feeling stressed or anxious. Such unprompted information may be associated with a biological input based on a predetermined algorithm, such as being associated with the biological input that is closest in time to the unprompted input, or being associated with the first biological input that occurs after the unprompted input. Server 106 (e.g., a healthcare database server) may receive such data from one or both of devices 102 and 104. In some embodiments, the data may be stored on a combination of one or more of devices 102, 104, and 106. The data may be reported to various stakeholders, such as the patient, the patient's doctor, peer group, family, counselor, employer, and other appropriate stakeholders.

[0096] In some embodiments, a wearable device such as device 102 or 202 can be applied to a patient during, for example, a patient's typical annual visit to the doctor to detect smoking behavior and then refer the smoker to a smoking cessation program. The patient is provided with a wearable device to wear as an outpatient for a period of time, such as a day, a week, or another suitable period of time. Longer wearing times may provide greater sensitivity in detecting smoking behavior and greater accuracy in quantifying variables related to smoking behavior. Figure 7 An illustrative flow chart for detecting smoking behavior is provided below and will be described in more detail below.

[0097] In some embodiments, employers ask employees to voluntarily wear wearable devices for a period of time, such as a day, a week, or another suitable period of time. Incentive programs can be similar to programs for biometric screening of obesity, hyperlipidemia, diabetes, hypertension, and other suitable health conditions. In some embodiments, health insurance companies require their subscribers to wear wearable devices for appropriate time periods to detect smoking behavior. Based on the quantified smoking behavior, these patients can be recommended to smoking cessation programs as described in the present disclosure.

[0098] When the wearable device is worn for an appropriate period of time (e.g., five days), multiple parameters may be measured in real time or near real time. These parameters may include, but are not limited to, CO, eCO, SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters. Figure 4 An illustrative chart 400 of the SpCO level of a patient's change in a typical five-day monitoring cycle is shown. Data points 402 and 404 indicate high CO levels, which in turn are likely to indicate high smoking events. Data points 406 and 408 indicate low CO levels, which are likely because the patient is asleep or busy with other things. One or more algorithms can be applied to the granular data points on the curve to detect smoking events with sufficient sensitivity and specificity. For example, the algorithm can analyze one or more of the shape, starting point, upslope, peak, increment, downslope, upslope, time of change, area under the curve, and other appropriate factors of the SpCO curve to detect smoking events.

[0099] Data from the wearable device can be sent to a smart phone (e.g., device 104) or a cloud server (e.g., server 106 or 204) in real time, at the end of each day, or according to another suitable time interval. The smart phone can measure parameters, including but not limited to movement, location, time of day, patient-entered data, and other suitable parameters. The patient-entered data may include stressors, life events, locations, daily events, the application of nicotine patches or other formulations, the application of other smoking cessation medications, and other suitable patient-entered data. For example, some of the patient-entered data may include information about phone calls, exercise, work, sports, stress, gender, drinking, smoking, and other suitable patient-entered data. The received data may be compiled, trended, and associated in real time or after a time period is completed.

[0100] Based on the parameters measured above, information about smoking can be obtained via a processor located in, for example, device 102, 104, or 202 or server 106 or 204. For example, the processor can analyze the information to determine CO trends, averages, peaks and correlations throughout the day, other vital sign trends, and how these vital organs change before, during, and after smoking. Figure 5 An illustration 500 of the information analyzed is shown. Figure 4 Zooming in on a given day in Figure 5 Data point 502 indicates SpCO levels when the patient is asleep. Data point 504 shows that SpCO levels are lowest when the patient is awake. Data points 506, 508, and 510 indicate that high SpCO levels are associated with triggers such as work breaks, lunch, and commuting. The processor may analyze Figure 5 SpCO trends in the patient's smoking history to determine parameters such as total number of cigarettes smoked, average number of cigarettes smoked per day, maximum number of cigarettes smoked per day, intensity of each cigarette smoked, amount of each cigarette smoked, what the patient's smoking events look like on a curve for subsequent use in a smoking cessation program, time of day, day of the week, associated stressors, geography, location, and exercise. For example, the total number of peaks on a given day can indicate the number of cigarettes smoked, while the gradient of each peak can indicate the intensity of each cigarette smoked.

[0101] Figure 6 An illustrative data structure for storing patient data is depicted. In this embodiment, data structure 600 shows Figure 5 602 associated with a data point in the data set (e.g., data point 508). The patient data 602 includes identification information for the patient, such as the patient's name 604 and the patient's age 606. The patient data 602 includes information corresponding to Figure 5 608 for a curve in the present invention. For example, the curve data 608 includes a curve identifier 610 corresponding to the data point 508. The data corresponding to the data point 508 can be collected by the device 102, 104 or 202, and / or the server 106 or 204, or a combination thereof. The data associated with the curve identifier 610 includes date, time, and location information 612. The data includes patient vital signs, such as CO and O2 levels 614. The data includes patient-entered data, such as triggers 616. The patient-entered data can be entered in response to a prompt to the patient on, for example, the device 104, or can be entered without a prompt according to the patient's wishes. The curve data 608 includes the data corresponding to the data point 508. Figure 5 The data structure 600 may be adapted as appropriate for storing patient data.

[0102] Figure 7Describe the illustrative flow chart 700 for detecting the smoking behavior of the patient in a suitable evaluation period. When the patient wears the wearable device in a suitable time period (e.g., five days), multiple parameters can be measured in real time, near real time, at the end of each day, or according to another suitable time interval. These parameters may include, but are not limited to, CO, eCO, SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse speed, skin galvanic response, pupil size, geographical location, environment, ambient temperature, stressor, life events, and other suitable parameters. Wearable device or another suitable device can measure parameters, including but not limited to movement, position, time of day, and other suitable parameters.

[0103] At step 702, a processor in a smart phone (e.g., device 104) or a cloud server (e.g., server 106 or 204) receives the described patient data. At step 704, the processor receives patient input data in response to a prompt displayed to the patient on, for example, a smart phone and / or patient data entered without prompting according to the patient's wishes. The patient input data may include stressors, life events, locations, daily events, administration of nicotine patches or other formulations, administration of other smoking cessation medications, and other suitable patient input data. At step 706, the processor sends instructions to update a patient database with the received data. For example, the processor can transmit the patient data to a healthcare provider server or cloud server that hosts the patient database.

[0104] At step 708, the processor analyzes the patient data to determine the smoking event. The processor can compile data in real time or after the evaluation period is completed, trend analysis and correlation data to the data. For example, the processor can analyze information to determine the CO trend, mean value, peak value, curve shape and association, other vital signs trends, and how these vital organs change before, during and after smoking during the day. The processor can analyze the SpCO trend to determine parameters, such as the total number of smoking, the average number of smoking every day, the maximum number of smoking every day, the intensity of each cigarette sucked, the time of the day, the day of the week, the associated stressors, geography, position and movement. For example, the total number of peak values ​​in a given day can indicate the number of smoking, and the gradient of each peak value can indicate the intensity of each cigarette sucked.

[0105] At step 710, the processor transmits the determined smoking events and related analysis to the patient database for storage. At step 712, the processor determines whether the evaluation period has ended. For example, the evaluation period can be five days or another suitable time period. If the evaluation period has not ended, the processor returns to step 702 to receive additional patient data, analyze the data, and update the patient database accordingly. If the evaluation period has ended, then at step 714, the processor ends data collection and analysis. For example, the processor can evaluate all collected data at the end of the evaluation period to prepare for the following discussion of Figure 8 Describe the report.

[0106] It is conceivable that Figure 7 The steps or descriptions of can be used with any other embodiments of the present disclosure. Figure 7 The steps and descriptions described may be performed in alternate orders or in parallel to facilitate the purposes of the present disclosure. For example, each of these steps may be performed in any order or in parallel or substantially simultaneously, as appropriate, to reduce latency or increase the speed of the system or method. In addition, it should be noted that with respect to Figure 1 (e.g., device 102, 104, or 106) or Figure 2 Any of the devices or apparatuses discussed (e.g., device 202 or 204) may be used to perform Figure 7 One or more of the steps in .

[0107] In some embodiments, the systems and methods described herein provide a patient with a method for starting and setting up a smoking cessation program. After the patient completes a five-day assessment while wearing a wearable device (e.g., device 102 or 202), the complete data set is compiled and analyzed by the system and delivered to the patient or physician for use in a smoking cessation program. Figure 8 An illustrative embodiment 800 of a sample report from the analysis is shown. For example, the report indicates that from October 1 to October 6, Mr. Jones smoked a total of 175 cigarettes, an average of 35 cigarettes per day, and the maximum number of cigarettes smoked in a day was 45. Mr. Jones' CO level averaged 5.5%, with a maximum of 20.7%, and was continuously above 4% for 60% of the five-day evaluation period. Mr. Jones' triggers include work, family stressors, and commuting. Given Mr. Jones' smoking habits, the report recommends high doses and frequent nicotine level forecasts for starting nicotine replacement therapy.

[0108] In some embodiments, the patient works with their physician or counselor to begin the process of entering a smoking cessation program. In some embodiments, the system automatically sets up a smoking cessation program based on data from an evaluation period. Figure 8The sample report in is an example of measuring SpCO and generating a report on CO exposure, associated stressors, and predicting the need for starting nicotine dosage. For example, heavy and high-intensity smokers may be more dependent on nicotine when entering a smoking cessation program, and the processor can estimate based on five-day behavior, and the smoking cessation program will start the patient with a higher dose of nicotine replacement therapy. This may avoid many patients from failing early in the smoking cessation program due to withdrawal symptoms. Based on report data including the average and maximum amount of cigarettes smoked, SpCO levels, and triggers, the processor can determine the dose of nicotine to be administered to the patient. For example, the processor can determine a high dose of nicotine for patients who smoke more than a threshold number of cigarettes per day on average. The processor can also update the dose of nicotine when the report data is updated.

[0109] The data collected can influence the initiation and setup of a smoking cessation program for patients by assisting with medication selection and dispensing, immediately before they enter the program. For example, higher indications of smoking may prompt the start of higher nicotine replacement therapy doses or multiple medications (e.g., adding medications used to treat nicotine addiction, such as varenicline). The data collected can influence the initiation and setup of a smoking cessation program by determining the frequency, type, and duration of counseling required for the patient. The data may lead to a stratification of smoker needs. For example, smokers at the highest risk for the highest use may receive more intervention, while smokers at lower risk may receive less intervention. For example, an intervention may include a text message, phone call, social network message, or another suitable event from the patient's spouse, friend, doctor, or another suitable stakeholder at a specific moment when the patient is likely to smoke.

[0110] The data collected may affect the start and setting of a smoking cessation program by associating smoking behavior with all of the above variables (such as, the stressors that prompt smoking, the time of day, and other appropriate variables for consulting patients in advance to be aware of these triggers). Consultation interventions may be directed to these stressors, and there may be interventions for patients at those times of the day, such as text messages or calls at those times of the day. The data collected may affect the start and setting of a smoking cessation program by allocating peer groups based on smoking behavior. The data collected can be used to predict and / or avoid smoking events. For example, if tachycardia or heart rate variability or an appropriate set of variables occur before most smoking events, this will sound an alarm, and the patient can take a dose of medication, or can receive a call from a peer group, a doctor, or a counselor. Fig.12 An illustrative embodiment of anticipating a smoking event is shown and discussed in greater detail below. Fig.14 and Fig.15 An illustrative flow chart for predicting and preventing anticipated smoking events is shown and discussed in more detail below.

[0111] In some embodiments, the systems and methods described herein provide for maintaining patient participation in a smoking cessation program. Once in a smoking cessation program, the patient may continue to wear a wearable device (e.g., device 102 or 202) for monitoring. The system may employ analytical tools, such as setting an SpCO baseline and tracking progress against the baseline. The trend may drop to zero and stay there (indicating no more smoking). The trend may drop slowly with peaks and valleys (indicating reduced smoking). The trend may drop to zero and then spike again (indicating relapse).

[0112] The system can employ patient engagement strategies by offering small, infrequent rewards for group or individual progress to get patients involved. The system can offer incentives from employers, payers, spouses, or peer groups to get patients involved. The system can present the patient's progress as a game and increase visibility of progress. Fig.13 Illustrative embodiments of such user interfaces are provided, and will be discussed in more detail below. In certain embodiments, the system can transmit data to a healthcare provider in real time for remote monitoring and allow the provider to effectively monitor and adjust patient care without having to be in the office every day. For example, the provider can send instructions to the system to adjust the type of medication and dosage, change the intensity of consultation, calls, and text messages for actively encouraging progress, or trigger intervention if the patient cannot suppress smoking. This may replace the expensive smoking cessation telephone lines of hired personnel, and the process can be effectively automated. The system can improve the patient's results with increased intensity and frequency. The system can encourage the patient through support from a spouse, employer, healthcare provider, companion, friend, and other appropriate parties via a predetermined phone call, text message, or other suitable communications.

[0113] Fig. 9 An illustrative diagram 900 is shown for tracking the average daily SpCO trend for patients who reach and then enter a smoking cessation program. The average trend is tracked daily as it improves. A doctor or counselor can zoom in on a specific day (now or in the past) to view the granular details of CO and the association of CO with other parameters measured and associated stressors 910. The visibility of the trend of CO that changes over time in a smoking cessation program may prevent patients from dropping out, prevent smoking relapse, titrate medications and counseling, and improve outcomes. For example, data point 902 indicates the CO level before the patient enters the smoking cessation program. Data points 904 and 906 indicate the CO level when nicotine replacement therapy and varenicline therapy are administered during the smoking cessation program. Data point 908 indicates that the patient has successfully quit smoking. At this point, the system can recommend that the patient enter a recidivism prevention program to prevent relapse.

[0114] In some embodiments, the systems and methods described herein provide a follow-up program after the patient successfully quits smoking. After successful smoking cessation verified by the system, the patient will wear a wearable device (e.g., device 102 or 202) for an extended period of time, such as several months to two years, as an early detection system for relapse. The system can collect data and adopt a consulting strategy for a smoking cessation program as described above.

[0115] In some embodiments, patients receive a wearable device (e.g., device 102 or 202) and an application for their smartphone (e.g., device 104) that allows them to remotely and privately assess their health by tracking several different parameters. Patients can submit breath samples or place their fingers in or on sensors on the wearable device several times a day as needed. They can wear the wearable device to obtain more frequent or even continuous measurements. At the end of the test period, such as five to seven days or another suitable time period, the processor in the smartphone can calculate their CO exposure and related parameters. Fig.10 An exemplary application screen 1000 is shown showing measurements such as SpCO 1002, SpO2 1004, heart rate 1006, respiratory rate 1008, blood pressure 1010, and temperature 1012. Warning indicators 1014 and 1016 may be provided for atypical measurements that may indicate the effects of smoking on the body. When warning indicators 1014 or 1016 are activated, the system may prompt the patient with an alarm.

[0116] The system can recommend patients to enter smoking cessation programs and provide options for these programs. The patient may agree to enter the smoking cessation program after seeing this objective evidence of smoking. The system can share this data with the patient's spouse, their doctor, or another suitable stakeholder participating in the patient's smoking cessation program. For example, the system can share data with the application of the stakeholder's mobile device, or send a message including data via email, phone, social network or another suitable media. The trigger that makes the patient join the smoking cessation program may include spouse advice, employer incentives, peer pressure, personal choice, disease or another suitable trigger. The patient can start the smoking cessation program on his own or provide the data to the doctor to receive assistance for joining the smoking cessation program.

[0117] When the patient is initiated in the smoking cessation program, the wearable device (e.g., device 102 or 202) can continue to monitor the patient's health parameters (such as heart rate, movement, location before smoking behavior) and transmit the data to the patient and / or his doctor to improve treatment. For example, a smart phone application on device 104 can receive patient-entered data, including but not limited to stressors, life events, location, daily events, application of nicotine patches or other formulations, application of other medications for smoking cessation, and other suitable patient-entered data.

[0118] Fig.11 The illustrative embodiment of the application screen 1100 for receiving the data input by the patient is shown.When the smart phone application receives the indication of the smoking event (for example, due to the spike of the CO level of the patient), the application screen 1100 can be displayed.Application screen 1100 prompts the user to input the trigger for the smoking event.For example, the patient can select or select option 1110 from one of the options 1102, 1104, 1106 and 1108 as the trigger smoking event and provide further information about the trigger.Other triggers for the smoking event can include the data input by telephone call, competitive sports, sports, pressure, sex and other suitable patients.The patient can also voluntarily call application screen 1100 to input the trigger information for the smoking event.In certain embodiments, the application screen 1100 for receiving patient data is displayed to the patient during the five-day evaluation period, to collect information about smoking behavior before the patient enters the smoking cessation project.

[0119] In some embodiments, the data collected are used by smart phone applications to avoid smoking events. The processor running the application or another device (such as, device 102 or 202 or server 106 or 204) can analyze the information about what happened to heart rate and other vital signs in the period before the smoking event. The processor can be associated with changes in heart rate (such as tachycardia), which can predict when the patient will smoke. This information can be used to start a preventive program for stopping smoking events. For example, a preventive program can include a pill for delivering nicotine. Nicotine can be delivered via a transdermal patch or from the transdermal transfer of the storage depot of nicotine stored in a wearable device (such as device 102 or 202). In another example, a preventive program can include a doctor, a companion group or another suitable stakeholder calling the patient. The processor can send instructions to initiate a call to an automatic call system, such as a server 106 or 204. Fig.14 and Fig.15 A flow chart for predicting smoking events based on patient vital signs is provided and will be described in more detail below.

[0120] Fig.12An illustrative embodiment of an application screen 1200 that implements such a preventive regimen is shown. For example, if the patient tends to become tachycardic twenty minutes before each cigarette, the processor can detect the tachycardia and prompt the patient to apply nicotine via option 1202. The patient can change the nicotine dosage via option 1204. In some embodiments, nicotine is automatically applied. The amount can be determined based on the patient's current SpCO level or another suitable parameter. The patient can receive a call from a peer group via option 1206, a call from a doctor or another suitable stakeholder via 1208. The caller can provide the patient with encouragement to quit smoking and suggest finding other activities to divert the patient's attention.

[0121] In some embodiments, the smartphone app presents the patient's process as a game to increase visibility of progress. The app can employ a patient engagement strategy by offering small, common or rare rewards for group or individual progress to get patients involved. The app can offer incentives from employers, payers, spouses or peer groups to get patients involved. Fig.13 An illustrative application screen 1300 for such an embodiment is shown. Application screen 1300 provides a reward for abstaining from smoking for fifteen days for the patient. Prompt 1302 challenges the patient to further abstain for another fifteen days. The patient can select option 1304 to accept the reward and continue to monitor progress while he remains smoke-free. However, the patient may have difficulty abstaining and can select option 1306 to contact a peer group, counselor, family member, doctor, or another appropriate party.

[0122] In some embodiments, the patient is a companion and supporter of others in their group. The group can track each other's progress and give support. For example, group members may be part of a social network that allows them to view each other's statistics and provide encouragement to quit smoking. In another example, when it is detected that the patient is smoking, a message (e.g., a tweet) can be sent to the group members (e.g., followers) of the patient's social network. The message can notify group members that the patient needs help. The group can be connected to the patient in various ways to provide help. This interaction can enable the patient to further quit smoking that day.

[0123] In some embodiments, during a primary care visit, the patient provides a sample and is asked if they smoke. For example, a wearable device (e.g., device 102 or 202) is applied to the patient and receives a sample for a spot measurement of the patient's SpCO level. The SpCO level may exceed a certain threshold, which suggests that the patient smokes. Fig.16A flow chart is provided for taking a single measurement of a patient's SpCO level. The patient may be provided with a wearable device to wear as an outpatient for a period of time, such as a day, a week, or another suitable period of time. Longer wearing times may provide greater sensitivity in detecting smoking behavior and greater precision in quantifying variables related to smoking behavior.

[0124] The wearable device, such as device 102 or 202, and the smartphone application, such as on device 104, can continue to monitor the patient's health parameters (such as SpCO levels) in real time or near real time, and process the data for viewing by the patient, a physician, or any other suitable party. The smartphone application can also provide the data in an easily understandable form for daily or weekly use by the patient and / or physician. For example, the smartphone application can generate a video similar to Fig. 9 A display showing daily progress with the option to zoom in on a specific day for viewing further details. The physician may store the patient record in a healthcare database, such as at a server 106 or 204 in communication with the mobile device running the smartphone application, and continue to receive data from the smartphone application via the Internet or another suitable communication link. The smartphone application may receive data from the sensor via a wired connection to the mobile device running the application or via a wireless connection (such as WI-FI, Bluetooth, radio frequency) or another suitable communication link.

[0125] The patient and the doctor can set a future quit date and send the patient home without any medication or with medication to help the patient quit smoking. The patient can start working towards the agreed quit date. Feedback from the wearable device and / or smartphone application can help the patient be better prepared to actually quit smoking at the quit date, and smoke less at the quit date than when they started. Once the patient starts the quit program, they may get daily or weekly feedback from their spouse, doctor, nurse, counselor, companion, friend, or any other suitable party.

[0126] Medication (if prescribed) can be based on the doctor or can be automatically adjusted based on patient performance. For example, a doctor can remotely increase or decrease nicotine dosing based on the patient's CO, eCO, SpCO levels. In another example, a processor in a wearable device (e.g., device 102 or 202), a smart phone (e.g., device 104), or a remote server (e.g., server 106 or 204) can increase or decrease nicotine dosing based on CO trends from past measurements of the patient. Similarly, medication can be shortened or extended in duration based on the collected data.

[0127] Fig.14An illustrative flow chart 1400 for predicting a smoking event based on a patient's CO, eCO, SpCO measurements and other suitable factors is depicted. A patient may be given a wearable device (e.g., device 102 or 202) and a smartphone application for their mobile phone (e.g., device 104). The wearable device may include a PPG sensor for measuring the patient's SpCO level. At step 1402, a processor in the wearable device or the patient's mobile phone receives a PPG measurement of the patient's SpCO level and the associated time and location. The processor may also receive other information such as heart rate, respiratory rate, and other suitable factors when predicting a smoking event.

[0128] At step 1404, the processor updates a patient database (such as a healthcare database in server 106) stored locally or at a remote location using the received patient data. At step 1406, the processor analyzes the current and previous measurements of the patient parameters and determines whether a smoking event is expected. For example, the SpCO trend may be in a local minimum, which indicates that the user may smoke to increase his SpCO level. The processor can apply a gradient descent algorithm to determine the local minimum. At step 1408, the processor determines whether the SpCO trend indicates an expected smoking event. If the processor determines that a smoking event is not expected, then at step 1410, the processor determines whether the time and / or location indicate an expected smoking event. For example, the processor can determine that when the patient wakes up around 7 o'clock in the morning, the patient usually smokes. In another example, the processor can determine that the patient usually smokes soon after they arrive at work. In yet another example, the processor can determine that whenever the patient visits a specific restaurant or bar at night, they usually smoke.

[0129] If the processor determines from step 1408 or 1410 that a smoking event is expected, then at step 1412, the processor initiates a prevention program for the patient to prevent the smoking event. Information about the prevention program may be stored in a memory of the device 102, 104, or 202 or the server 106 or 204, or a combination thereof. The information for the prevention program may include instructions about one or more intervention options to be initiated when the patient is about to smoke. For example, the processor may activate an alarm in the patient's mobile phone and display a message similar to Fig.12The application screen may provide the patient with the option of administering nicotine or receiving a call from a peer group, a doctor, or another appropriate party. Alternatively, the prevention regimen may include automatically administering a nicotine pill to the patient from a reservoir of nicotine stored in the patient's wearable device. In another example, the application screen may indicate that a message (e.g., a tweet) will be sent to group members (e.g., followers) of the patient's social network when failure to quit smoking is detected. The patient may refrain from smoking to prevent messages indicating their failure from being sent.

[0130] In some embodiments, steps 1408 and 1410 are combined into one step, or include two or more steps for the processor to determine whether a smoking event is expected. For example, the processor can determine whether a smoking event is expected based on a combination of SpCO trends, the patient's position and / or the current time. In another example, the processor can determine whether a smoking event is expected based on a series of steps for analyzing one or more of the patient's SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse speed, skin galvanic response, pupil size, geographic location, environment, ambient temperature, stressors, life events and other suitable parameters.

[0131] At step 1414, the processor determines whether the prevention program was successful. If a smoking event occurred, then at step 1418, the processor updates the patient database to indicate that the prevention program was not successful. If no smoking event occurred, then at step 1416, the processor updates the patient database to indicate that the prevention program was successful. The processor returns to step 1402 to continue receiving PPG measurements of the patient's SpCO level and associated data. The processor can continuously monitor the patient's vital signs to ensure that the patient does not relapse into a smoking event.

[0132] It is conceivable that Fig.14 The steps or descriptions of can be used with any other embodiments of the present disclosure. Fig.14 The steps and descriptions described may be performed in alternate orders or in parallel to facilitate the purposes of the present disclosure. For example, each of these steps may be performed in any order or in parallel or substantially simultaneously, as appropriate, to reduce latency or increase the speed of the system or method. In addition, it should be noted that with respect to Figure 1 The device 102, 104 or 106 discussed or Figure 2 Any of the devices or apparatuses discussed (e.g., device 202 or 204) may be used to perform Fig.14 One or more of the steps in .

[0133] Fig.15 Describes about Fig.141414 in step 1500 for determining whether the prevention program is successful. At step 1502, the processor receives patient data for determining whether a smoking event has occurred. At step 1504, the processor analyzes the currently received patient data and the previously received patient data. At step 1506, the processor determines whether a smoking event has occurred based on the analysis. For example, if nicotine is not administered, but the patient's SpCO level is currently higher than the previous SpCO level, the processor can determine that the patient relapsed and smoked. In this case, at step 1508, the processor returns a message indicating that the prevention program was not successful. In another example, if the patient's vital signs indicate that the SpCO level has not risen or fallen, the processor can determine that no smoking event has occurred. In this case, at step 1510, the processor returns a message indicating that the prevention program has been successful.

[0134] It is conceivable that Fig.15 The steps or descriptions of can be used with any other embodiments of the present disclosure. Fig.15 The steps and descriptions described may be performed in alternate orders or in parallel to facilitate the purposes of the present disclosure. For example, each of these steps may be performed in any order or in parallel or substantially simultaneously, as appropriate, to reduce latency or increase the speed of the system or method. In addition, it should be noted that with respect to Figure 1 The device 102, 104 or 106 discussed or Figure 2 Any of the devices or apparatuses discussed (e.g., device 202 or 204) may be used to perform Fig.15 One or more of the steps in .

[0135] Fig.16 An illustrative flow chart 1600 for a single measurement of a patient's SpCO level using a PPG sensor is depicted. For example, a wearable device (e.g., device 102 or 202) is applied to a patient and receives a sample for a single measurement of the patient's SpCO level. At step 1602, a processor in the wearable device receives a PPG measurement of the patient's SpCO level and any other suitable data, such as time, location, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters. At step 1604, the processor analyzes the received data to determine a recent smoking event. For example, an elevated SpCO level that exceeds a certain threshold may indicate that the patient has recently smoked.

[0136] At step 1606, the processor determines whether the patient's SpCO level indicates that a smoking event has occurred. For example, an SpCO level that exceeds a specified threshold may indicate a smoking event. In another example, one or more of the shape, starting point, upslope, peak, increment, downslope, upslope, time of change, area under the curve, and other appropriate factors of the SpCO curve may indicate a smoking event. One or more of these factors may assist in the quantification of smoking events. For example, the total number of peaks in a given day may indicate the number of cigarettes smoked, while the gradient shape and size of each peak and other characteristics may indicate the intensity and amount of each cigarette smoked. If the processor determines that the SpCO level indicates that no smoking event has occurred, then at step 1608, the processor returns a denial message indicating that the patient has no recent smoking event. The patient's doctor may find this information useful for evaluating the patient's smoking behavior. If the processor determines that the SpCO level indicates that a smoking event has occurred, then at step 1610, the processor returns a confirmation message indicating that the patient does have a recent smoking event. In this case, as described above, the collected data can be used to set up a smoking cessation program for the patient.

[0137] After step 1608 or 1610, at step 1612, the processor updates the patient database to record the information. At step 1614, the processor terminates the SpCO level assessment for the patient. The patient may be provided with a wearable device to wear as an outpatient for a period of time, such as a day, a week, or another suitable period of time. Longer wearing times may provide greater sensitivity in detecting smoking behavior and greater accuracy in quantifying variables related to smoking behavior.

[0138] It is conceivable that Fig.16 The steps or descriptions of can be used with any other embodiments of the present disclosure. Fig.16 The steps and descriptions described may be performed in alternate orders or in parallel to facilitate the purposes of the present disclosure. For example, each of these steps may be performed in any order or in parallel or substantially simultaneously, as appropriate, to reduce latency or increase the speed of the system or method. In addition, it should be noted that with respect to Figure 1 The device or equipment in question (e.g., device 102, 104, or 106) or Figure 2 Any of the devices or apparatuses discussed (e.g., device 202 or 204) may be used to perform Fig.16 One or more of the steps in .

[0139] In some embodiments, data from one or more devices such as devices 102 and 104 or device 202 associated with the patient are received at a central location such as server 106 or 204. The patient device records multiple biometrics and context variables in real time or near real time. For example, biometric variables may include CO, eCO, SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse speed, skin galvanic response, pupil size and other suitable biometric variables. For example, context variables may include GPS location, patient activity (e.g., sports, fitness, shopping or another suitable patient activity), patient environment (e.g., at work, at home, in a car, in a bar or another suitable patient environment), stressors, life events and other suitable context variables. The collected data may also include personal observations of the patient's smoking behavior. Spouses or friends or partners may be able to input the data of their patient smoking, and the data are associated with SpCO readings to determine accuracy.

[0140] Server 106 includes a processor for receiving data for multiple patients within a time period, and for trend analysis data occurring near the time of actual smoking event. Based on trend, the processor determines the diagnosis and / or detection test for smoking event. The test may include one or more algorithms applied to data determined by the processor. For example, the processor may analyze the spike of the CO level of the patient. Detection spike may include determining that the CO level is higher than a certain specified level. Detection spike may include a relative increase in the CO level of the patient according to the baseline detection of the previous measurement. The processor may detect the spike as the change of the slope of the CO trend of the patient within a time period. For example, the CO trend moving from a negative slope to a positive slope may indicate the spike of the CO level. In another example, the processor may apply one or more algorithms to the change of heart rate variation, increased heart rate variability, blood pressure variation or other suitable data, so as to detect smoking event.

[0141] Fig.17Depicted is an illustrative flow chart 1700 for detecting a smoking event as described above. A processor (e.g., in a server 106 or 204) can determine a diagnosis and / or detection test for a smoking event according to flow chart 1700. At step 1702, the processor receives current patient data. At step 1704, the processor obtains previously stored patient data from a database (e.g., a patient database stored at a server 106 or 204). At step 1706, the processor compares current and previous patient data to detect a smoking event. For example, the processor can analyze a spike in the CO level of the patient. Detecting a spike can include detecting a relative increase in the CO level of the patient according to a previously measured baseline. The processor can detect a spike as a change in the slope of the CO trend of the patient over a period of time. For example, a CO trend moving from a negative slope to a positive slope can indicate smoking behavior. In another example, the processor can apply one or more algorithms to changes in heart rate changes, increased heart rate variability, blood pressure changes, or other suitable data to detect a smoking event. At step 1708, the processor determines whether a puff event occurred as described based on, for example, a spike in the patient's CO level. If no puff event was detected, then at step 1710, the processor returns a message indicating that no puff event occurred. If a puff event was detected, then at step 1712, the processor returns a message indicating that a puff event occurred. At step 1714, the processor updates the patient database with the results from step 1710 or 1712.

[0142] It is conceivable that Fig.17 The steps or descriptions of can be used with any other embodiments of the present disclosure. Fig.17 The steps and descriptions described may be performed in alternate orders or in parallel to facilitate the purposes of the present disclosure. For example, each of these steps may be performed in any order or in parallel or substantially simultaneously, as appropriate, to reduce latency or increase the speed of the system or method. In addition, it should be noted that with respect to Figure 1 The device or equipment in question (e.g., device 102, 104, or 106) or Figure 2 Any of the devices or apparatuses discussed (e.g., device 202 or 204) may be used to perform Fig.17 One or more of the steps in .

[0143] In some embodiments, the processor analyzes the data initially received to measure when people smoke and associates the algorithm with the variable that triggers the algorithm for diagnosing and / or detecting smoking events. When additional patient data is received, the processor continues to analyze other variables. The processor can determine another variable that changes when the patient smokes, and instead uses the variable to trigger the algorithm. For example, the processor can choose to use another variable because it is less invasive or easier to measure than the variable initially selected.

[0144] In some embodiments, the algorithm for detecting smoking events has high sensitivity. Sensitivity is defined as the percentage of the actual number of smoking events detected by the sensor and algorithm. For example, if the patient smokes 20 times in a day and the algorithm recognizes each smoking event, it is 100% sensitive.

[0145] In some embodiments, the algorithm for detecting smoking events has high specificity. Specificity is defined as the ability of the test to not make false positive calls for smoking events (i.e., a positive test where no smoking events exist). If the sensor and algorithm do not make any false positive calls in a day, it has 100% specificity.

[0146] In another example, if the patient smokes 20 times and the algorithm identifies 18 of the 20 actual smoking events and indicates 20 other false smoking events, it has 90% sensitivity (i.e., detects 90% of the smoking events) and 50% specificity (i.e., estimates the number of smoking events to be more than 2 times).

[0147] In some embodiments, after the processor determines one or more algorithms and applies them to the SpCO measurement to detect smoking events with sufficient sensitivity and specificity, the processor determines whether there is an association of other biometric variables or contextual variables with the SpCO results that can be used independently (without SpCO) to detect smoking events. The processor can determine another variable that changes when the patient smokes, and use that variable to trigger the algorithm instead. For example, the processor can choose to use another variable because it is less invasive or easier to measure or more reliable than the initially selected variable.

[0148] In certain embodiments, the processor analyzes the received patient data to predict the possibility of a smoking event before the smoking event occurs. The processor can analyze the received patient data in a time period before the smoking event (for example, five minutes, 10 minutes, 15 minutes, 20 minutes or another suitable time interval), to determine one or more triggers. For example, some smoking events can be before situation triggers (for example, in a bar, before, during or after eating, before, during or after sexual behavior or another suitable situation trigger). In another example, some smoking events can be before the change of biometric variables such as heart rate or another suitable biometric variable. The variable determined may overlap with the variable selected for diagnosis and detection, so it can also be used for prediction. Alternatively, the variable determined may not overlap with the variable selected for diagnosis.

[0149] The processor can notify the patient of the likelihood of a smoking event and trigger (e.g., as described in relation to Fig.14 and Fig.15 The processor detects smoking events for the patient as entered in, for example, a smoking cessation program, and tracks and analyzes trends in the received patient data. The processor can determine the patient's goals and, when he reaches the set goals (e.g., as discussed in relation to Fig.13 The processor can predict when the patient will smoke and reward them by suggesting a call to a peer group or physician or by administering a nicotine pill (e.g., as discussed in Fig.12 discussed) to intervene in a timely manner.

[0150] In one example, the processor predicts the patient's smoking events based on 75% of the patient's smoking events preceded by an accelerated heart rate (or a suitable change of another variable) during diagnosis. During a smoking cessation program, the processor may apply one or more algorithms to received patient data to predict smoking events and initiate a prevention program. For example, a prevention program may involve the patient in a timely manner by contacting a supporter such as a doctor, counselor, companion, team member, nurse, spouse, friend, robot, or another suitable supporter. In some embodiments, the processor applies an algorithm to each patient based on its five-day run-in diagnosis period to adjust settings such as baseline, threshold, sensitivity, and other suitable settings. The processor may then use these customized algorithms for a smoking cessation program for a specific patient. The described combination of techniques for changing a patient's smoking behavior may be referred to as a digital drug.

[0151] In some embodiments, the processor detects smoking with positive or negative indication in a binary manner. The processor initially uses observational studies and SpCO measurements from the patient to detect smoking behavior. For example, the processor receives data about true positives for smoking events from the observational data of the patient's smoking behavior. The processor determines whether the detection based on SpCO measurement matches the true positive of smoking events. If there is a match, the processor applies the algorithm to other received patient data, including the patient's SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweating, heart rate variability, electrical rhythm, pulse speed, skin galvanic response, pupil size, geographical location, environment, ambient temperature, stressor, life events and other suitable parameters. The processor determines whether any pattern in the non-SpCO variable data also indicates a smoking event. These variables can be used for algorithms for non-SpCO devices (such as wearable smart watches or heart rate monitoring belts or other devices) to detect smoking events.

[0152] When the smoking behavior is detected based on the received patient data, the processor can quantify the smoking behavior. For example, the processor analyzes the SpCO data trend to indicate the intensity of each cigarette sucked by the patient, how many cigarettes the patient sucks in a day, how much each cigarette sucks and / or how long each cigarette sucks. The processor can also use other biometrics or situational variables for indication. The processor uses the received patient data to predict the possibility of a smoking event occurring in the near future, for example, within the next 10 minutes. The processor can analyze the received patient data in the previous time period before the smoking event (for example, five minutes, 10 minutes, 15 minutes, 20 minutes or another suitable time interval) to determine one or more triggers.

[0153] In certain embodiments, system and method as described herein are provided for assessing the smoking behavior of the patient. During the five-day test period, the patient behaves as he usually does. Equipment 102,104 and / or 106 or equipment 202 and / or server 204 receive the patient data relevant to the patient's smoking behavior. Because the purpose of the test period is to observe the patient's smoking pattern, the patient hardly participates. If necessary, the test period can be extended to the second five-day period. Optionally, the first and second periods can be shorter (for example, two or three days) or longer (for example, one week or longer). Before the second test period, the processor determines the model of how the patient smokes.

[0154] In the second test phase, the processor applies a series of disturbances to the model to see whether the smoking behavior changes. There may be several types of disturbances, each of which has several dimensions. For example, a disturbance may be whether a text message is sent before or during a smoking event to cause a smoking event to be avoided or shortened. The dimension in the disturbance may be different senders, different timings, and / or different contents for text messages. In another example, a disturbance may be whether a telephone call at a certain time of the day or before or during a smoking event causes a smoking event to be avoided or shortened. The dimension in the disturbance may be different callers, different timings, and / or different contents for a telephone call. In yet another example, a disturbance may be to warn patients to check whether their smoking behavior at several points in the day avoids smoking in a time period thereafter. The dimension may include determining whether and when to eliminate the avoidance. In other examples, a disturbance may be a reward, team action or other suitable triggers to avoid or shorten the patient's smoking event.

[0155] In some embodiments, the processor uses a machine learning process to deliver disturbances to the patient's smoking model. The machine learning process transmits disturbances, test results, and adjusts the disturbances accordingly. The processor determines the most effective way to achieve the identified behavioral changes by trying options through the machine learning process. The machine learning process can be applied as a slight disturbance during the second testing phase. The machine learning process can also be applied during the patient's smoking cessation phase with significant disturbances to increase the effort to try to make the patient quit smoking or continue to quit smoking.

[0156] Fig.18 Describe the illustrative flow chart 1800 for applying one or more disturbances to the smoking model of the patient in the second test phase.At step 1802, the processor in the wearable device 102 or 202, the mobile device 104 or the server 106 or 204 receives the patient data related to the smoking behavior of the patient in the first test phase.At step 1804, the processor analyzes the received patient data to determine the model for the smoking behavior of the patient.At step 1806, the processor applies one or more disturbances to the model to see whether the smoking behavior changes.The disturbance can be applied to the model using a machine learning process.There may be several types of disturbances, each of which has several dimensions.For example, the disturbance may be whether sending a text message before or during a smoking event causes the smoking event to be avoided or shortened.The dimension within the disturbance may be different senders, different timings, and / or different contents for the text message.

[0157] At step 1808, the processor determines whether the disturbance changes the patient's smoking behavior. For example, the processor determines whether receiving a text message before or during a smoking event causes the patient to quit or shorten his smoking. If the disturbance causes the patient's smoking behavior to change, then at step 1810, the processor updates the model of the patient's smoking behavior to reflect the positive results of the disturbance applied. The processor then proceeds to step 1812. Otherwise, the processor proceeds directly to step 1812 from step 1808 and determines whether to apply additional disturbances or changes in the dimensions of the current disturbance. The processor can use a machine learning process to determine whether to apply additional disturbances to the model. If no more disturbances need to be applied, then at step 1814, the processor ends the process of applying disturbances.

[0158] If more disturbances need to be applied, then at step 1816, the processor determines another disturbance to apply to the model. For example, the processor can adjust the current disturbance to send a text message to the patient at a different time or with different content. In another example, the processor can apply a different disturbance by initiating a phone call to the patient before or during a smoking event. The processor returns to step 1806 to apply the disturbance to the model. The processor can use a machine learning process to pass the disturbance, test the results, and adjust the disturbance or another selected disturbance accordingly. In this way, the processor determines the most effective way to achieve the identified behavioral changes for the patient by trying different options through a machine learning process.

[0159] It is conceivable that Fig.18 The steps or descriptions of can be used with any other embodiments of the present disclosure. Fig.18 The steps and descriptions described may be performed in alternate orders or in parallel to facilitate the purposes of the present disclosure. For example, each of these steps may be performed in any order or in parallel or substantially simultaneously, as appropriate, to reduce latency or increase the speed of the system or method. In addition, it should be noted that with respect to Figure 1 The device or equipment discussed (e.g., device 102, 104, or 106) or Figure 2 Any of the devices or apparatuses discussed (e.g., device 202 or 204) may be used to perform Fig.18 One or more of the steps in .

[0160] In the illustrative example, a 52-year-old male patient is motivated by his employer to screen smoking behavior. The patient entered the assessment project on June 1, 2015. The patient reported smoking 20 cigarettes a day. A project coordinator (such as a physician or a consultant) loads the application to the patient's smart phone (e.g., mobile device 104) and provides the patient with a connected sensor (e.g., wearable device 102 or 202). The coordinator notifies the patient to smoke normally and behave during the five-day test period, and responds to the prompt from the application when the prompt appears. After the five-day period ends, the coordinator allows the patient to enter a supplementary test period, in which the application prompts more frequently (e.g., to apply a disturbance). The coordinator notifies the patient that he decides whether to respond at this moment, although he hopes that the patient responds. The coordinator sets up a target date of June 10, 2015 to include a 10-day test.

[0161] After the five-day testing period, the coordinator receives a report (e.g., Figure 8The report noted that 150 smoking events using CO detection were compared to 100 smoking events based on patient estimates. The report noted that associated contextual variables included alcohol, location, stress, and other appropriate data. The report noted that associated biometric variables included increased heart rate in the absence of exercise, as preceded 50% of the smoking events. The report noted that prompts for stress level showed increased stress in 20% of the smoking events.

[0162] During the supplementary five-day test period, a processor in a mobile device (e.g., device 104), a wearable device (e.g., device 102 or 202), or a remote server (e.g., server 106 or 204) applies perturbations via a machine learning process. For example, the mobile device prompts the patient four times a day with a display including the number of cigarettes smoked, the intensity of smoking, and the time of day. As the day progresses, the prompts cause the patient to reduce smoking over a longer period of time. The effective effect is that the patient smokes less in the second half of the day compared to the first half of the day. In another example, the mobile device prompts the patient at 10 a.m. every day with a display including the number of cigarettes smoked the previous day. The effective effect of studying how prompts affect the patient's smoking behavior for the rest of the day. The machine learning process can adjust the time and content of the display as needed to change the perturbation dimension.

[0163] In another example, the processor applies a perturbation in the form of a text message sent to the patient during a smoking event via a machine learning process. The machine learning process changes the dimension of the perturbation by having different senders, different timing, sending before or during smoking, different content of the message, different images in the message, and / or different rewards for quitting. In another example, the processor applies a perturbation in the form of a phone call during a smoking event via a machine learning process. The machine learning process changes the dimension of the perturbation by having different callers, different timing, calls before or during smoking, different call content, different tones in the call, and / or different rewards for quitting.

[0164] In another example, the processor applies a perturbation in the form of a prompt on the patient's mobile device for a specific activity via a machine learning process. The prompt indicates that the patient is smoking, but should consider smoking only half a cigarette and then going out. During the long periods of time between cigarette events, or when an event is predicted, the machine learning process applies a perturbation to try to avoid the smoking event altogether. For example, the mobile device displays a prompt notifying the patient that they are in a high-risk area and should consider alternative activities or locations or call a friend.

[0165] After the test period, the coordinator allows the patient to enter the smoking cessation program. During the smoking cessation period, the processor receives patient data and applies the algorithm to the data. The processor uses all data from the first and second test periods to customize the algorithm and start the program and smoking cessation program intervention for a specific patient. The diagnosis and detection algorithm can use one or more biometric variables (such as SpCO) of the patient to detect smoking behavior. The smoking cessation program includes a nicotine regimen as a part of nicotine replacement therapy from the first day. Nicotine can be delivered via a transdermal patch or a transdermal transfer from a reservoir of nicotine stored in a wearable device provided to the patient. The processor applies an algorithm to the received patient data to determine the most effective intervention. The processor applies the intervention and further adjusts them as needed. The processor can set a target event count and determine which method is most effective for changing the patient's smoking behavior. The processor can call multiple personalized interventions from stakeholders as disturbances via a machine learning process, and test which is most effective for changing the patient's smoking behavior. The disturbance that has the greatest impact on the patient's smoking model may be retained, while the disturbance that has less or no impact may not be used further.

[0166] While the exemplary embodiments of the systems and methods described above focus on smoking behavior, examples of which include, but are not limited to, tobacco inhalation via cigarettes, pipes, cigars, and hookahs, as well as alcohol-related behavior, it will be apparent to those skilled in the art that the teachings of the present invention are equally applicable to any number of other undesirable behaviors. These other examples include: oral placement of certain substances, with specific examples including, but not limited to, placing chewing tobacco and snuff in the mouth, transdermal absorption of certain substances, with specific examples including, but not limited to, application of certain creams, ointments, gels, patches on the skin.

[0167] Typically, the basic configuration of devices 102 and 104 or device 202 and the associated steps and methods disclosed herein will be similar between the different behaviors being addressed. Devices may differ in design to account for different target substances required for testing or different testing methods necessitated by different markers associated with a particular undesirable behavior.

[0168] Those skilled in the art will also recognize that patients participating in formal smoking cessation programs can utilize the systems and methods disclosed herein as an aid to smoking cessation programs. It will also be recognized that patients can independently self-motivate and therefore advantageously use the systems and methods for unilaterally quitting undesirable behaviors outside of formal smoking cessation programs.

[0169] In further exemplary embodiments, the systems and methods disclosed herein can be readily adapted for data collection, and in particular, for collection of reliable and verifiable data for studies relating to undesirable behaviors that the present invention is well suited to testing. Such studies can be accomplished with no substantial modification to the underlying apparatus or methods, except where treatment is not included, the need to update test protocols or treatment protocols based on user input will not be necessary.

[0170] Fig.19 Another variation of the system and / or method for influencing individual smoking behavior and further quantifying individual exposure to cigarette smoke using multiple aspects described herein is shown. In the illustrated example, samples of multiple biometric data are obtained from individuals and analyzed to quantify individual exposure to cigarette smoke, so that the quantified information can be forwarded to individuals, medical caregivers, and / or other parties with health interests of individuals. The example discussed below adopts a portable device 1900, which obtains multiple samples of exhaled breath from individuals, with a generally available sensor for measuring the amount of carbon monoxide (also referred to as exhaled carbon monoxide or ECO) in the sample of exhaled breath. However, quantification and information transfer are not limited to exposure based on smoke of exhaled breath. As mentioned above, there are many sampling devices for obtaining individual smoking exposure. The method and apparatus described in this example can be combined with such a sampling device or supplemented by it when possible, while still maintaining the scope of the present invention. In addition, although this example discusses the use of a portable sampling unit, the method and process described herein can be used with a dedicated or non-portable sampling unit.

[0171] It is known that the measurement of exhaled CO levels is used as an instant non-invasive method to assess an individual's smoking status. See, for example, The Measurement of Exhaled Carbon Monoxide in Healthy Smokers and Non-smokers, published by S. Erhan Devecia et al., Department of Public Health, Faculty of Medicine, Firat University, Elazig, Turkey, in 2003, and Comparison of Tests Used to Distinguish Smokers from Nonsmokers, published by MJ Jarvis et al., Vol. 77, No. 11, American Journal of Public Health, November 1987. These articles discuss that the exhaled CO ("eCO") level for non-smokers can be between 3.61ppm and 5.6ppm. In one example, the cutoff level for eCO is above 8-10ppm to identify smokers.

[0172] return Fig.19As shown, the portable or personal sampling unit 1900 communicates with a personal electronic device 110 or a computer 112. The personal electronic device 110 includes, but is not limited to, a smart phone, a regular phone, a cellular phone, or other personal transmission device specifically designed to receive data from the personal sampling unit 1900. Similarly, the computer 112 is intended to include a personal computer, a local server, or a remote server. The transmission of data 114 from the personal sampling unit 1900 can occur to both or either of the personal electronic device 110 and / or the computer 112. In addition, synchronization 116 between the personal electronic device 110 and the computer 112 is optional. As described herein, any of the personal electronic device 110, the computer 112, and / or the personal sampling unit 1900 can transmit data to a remote server for data analysis. Optionally, the data analysis can be performed in whole or in part in a local device (such as a computer or personal electronic device). In any case, the personal electronic device 110 and / or the computer 112 can provide information to an individual, a caretaker, or other individual, such as Fig.19 shown.

[0173] exist Fig.19 In the depicted example of , the personal sampling unit 1900 receives a sample 108 of exhaled breath from an individual via a collection tube 1902. The hardware within the personal sampling unit 1900 includes any commercially available electrochemical gas sensor that detects carbon monoxide (CO) gas within the exhaled breath sample, and commercially available transmission hardware that transmits data 114 (e.g., via Bluetooth, cellular, or other radio waves that provide data transmission). The transmitted data and associated measurements and quantifications are then displayed on either (or both) a computer display 112 or a personal electronic device 110. Alternatively or in combination, any information can be selectively displayed on the portable sampling unit 1900.

[0174] The personal sampling unit (or personal breathing unit) may also employ standard ports to allow direct wired communication with the respective devices 110 and 112. In certain variations, the personal sampling unit 1900 may also include a removable or built-in memory storage, such memory allowing the recording of data and the separate transmission of data. Optionally, the personal sampling unit may allow for simultaneous storage and transmission of data. Other variations of the device 1900 do not require a storage device. In addition, the unit 1900 may employ any number of GPS components, inertial sensors (to track movement), and / or other sensors that provide additional information about the patient's behavior.

[0175] The personal sampling unit 1900 may also include any number of input triggers (such as switches or sensors) 1904, 1906. As described below, the input triggers 1904, 1906 allow individuals to prepare the device 1900 in advance for delivering breath samples 108 or recording other information about cigarettes (such as the amount of smoking, intensity, etc.). In addition, variations of the personal sampling unit 1900 also associate the timestamp of any input to the device 1900. For example, the personal sampling unit 1900 may associate the time of providing the sample and provide the measured or input data and the measurement time when transmitting the data 114. Alternatively, the personal sampling device 1900 may use an alternative device to identify the time when the sample is obtained. For example, considering a series of samples, instead of recording the timestamp for each sample, the time period between each sample in the series may be recorded. Therefore, the identification of the timestamp of any one sample allows the timestamp for each sample in the series to be determined.

[0176] In some variations, the personal sampling unit 1900 is designed so that it has a minimum profile and can be easily carried by an individual with minimal effort. Therefore, the input trigger 1904 can include a low-profile tactile switch, an optical switch, a capacitive touch switch or any commonly used switch or sensor. The portable sampling unit 1900 can also provide feedback or information to the user using any number of known technologies. For example, as shown in the figure, the portable sampling unit 1900 can include a screen 1908 that displays the selection information discussed below. Alternatively or in addition, feedback can take the form of a vibration element, an audible element and a visual element (e.g., an illumination source of one or more colors). Any one of the feedback components can be configured to provide an alarm to the individual, which can be used as a reminder to provide a sample and / or provide feedback related to the measurement of smoking behavior. In addition, the feedback component can provide an alarm to the individual on a repeated basis, in an effort to remind the individual to provide a periodic sample of exhaled breath, to extend the time period of the system capturing biometrics (such as, eCO, CO levels, etc.) and other behavioral data (such as, manually or via the location, number of cigarettes or other triggers input by the GPS component coupled to the unit). In some cases, reminders can be triggered at a higher frequency during an initial project or data capture. Once sufficient data is obtained, the reminder frequency can be reduced.

[0177] Fig. 20A Shows that it is possible to use Fig.19 . As discussed above, the individual provides a breath sample using a portable sampling unit. Depending on the nature of the treatment or intervention program, the individual may be reminded periodically or at random intervals. Each sample is evaluated by one or more sensors within the portable sampling unit to measure the amount of CO. The CO measurement typically corresponds to Fig. 20AThe inflection point 410 on the graph of CO is shown. Each CO measurement 410 corresponds to a time stamp as shown on the horizontal axis. The data accumulated via the portable sampling unit allows for the collection of a data set including at least the CO measurements and the time of the sample, which can be plotted to obtain an eCO curve indicating the amount of CO attributable to the individual's smoking behavior over the course of the time period.

[0178] As described herein, individuals can further track additional information such as the smoking of cigarettes. The smoking of cigarettes can be associated with its own timestamp as shown in column 414. In a variation of the method and system under the present disclosure, individuals can use an input trigger on a portable sampling unit to input the number of cigarettes smoked or a portion thereof. For example, each actuation of the input trigger can be associated with a small number of cigarettes (e.g., 1 / 2, 1 / 3, 1 / 4, etc.).

[0179] Fig. 20B A portion of a graphical representation of data collected as described above is shown. However, in this variation, quantification of an individual's smoking behavior may use behavioral data to better approximate CO values ​​between eCO readings. For example, in some variations, the eCO measurement between any two points 410 may be approximated using a linear approximation between the two points. However, it is known that CO levels decay within the bloodstream in the absence of exposure to new CO. This decay may be approximated using a standard rate, a rate based on the patient's biometric information (weight, heart rate, activity, etc.). As Fig. 20B As shown, when the patient is between cigarettes 414, the calculated CO level can follow a decay rate 440. Once the individual records a cigarette 414, the CO increase 442 can be approximated again by using a standard rate or a value calculated using the biometric data as discussed above, or based on the intensity, duration, and amount of smoking. Therefore, the methods and systems described herein can optionally use an improved (or approximated) eCO curve 438 that utilizes the behavioral data discussed above. This improved eCO rate can also be used to determine an improved eCO curve 438 while the individual is sleeping. This improved eCO curve can then provide an improved eCO load as described herein. The biometric information used to determine the decay rate can be measured by a portable sampling device or by an external biometric measurement device that communicates with the system.

[0180] This approximate or improved eCO curve 438 can be displayed to the individual (or to a third party) as a means of assisting in behavior modification, as the individual can view the real-time approximate CO level (i.e., the rate of decrease when not smoking and the rate of increase when smoking). Additional information can also be displayed, for example, the system can also calculate the CO increase for each cigarette based on its starting CO value.

[0181] Fig.21An example of a data set for determining an eCO curve 412 over a period of time is shown, wherein the eCO attributable to the smoking behavior of an individual can be quantified in different time intervals to determine the eCO burden or eCO load for each interval. As shown, the time period extends along the horizontal axis and includes historical and ongoing data captured / transmitted by a portable sampling unit. In order to provide more effective feedback about its smoking behavior to an individual, the eCO curve 412 during a specific time interval can be quantified. In the example shown, the time interval between time 416 and 418 includes an interval of 24 hours. The subsequent 24-hour interval is defined between time 418 and 420. The interval of time or the time interval can include any time between two points in the time period spanned by the data set. In most cases, the time interval will be compared with other time intervals with the same duration (that is, each interval can include M minutes, H hours, D days, etc.).

[0182] One method of quantifying the eCO burden / load over a time interval is to use the data set to obtain the area defined by or below the eCO curve 412 between a given time interval (e.g., 416 to 418, 418 to 420, etc.), such as Fig.21 . In the example shown, the eCO burden / load 422 for the first interval (416 to 418) includes 41 (measured in COppm*t), while the eCO burden 422 for the second interval (418 to 420) includes 37. As described above, along with the eCO burden / load 422, the data set may include the number of cigarettes smoked 414 along with the timestamp of each cigarette. For any given time interval, this cigarette data may also be summarized as 426 along with the eCO burden / load 422. In the example shown, the eCO burden / load is a daily load, which allows an individual to track their CO exposure. Determining the CO load is a more accurate reflection of total smoke exposure than just counting cigarettes because smokers smoke differently. One smoker may smoke an entire cigarette completely, deeply and intensely, while another smoker smokes less deeply and intensely. Although both individuals may smoke a pack of cigarettes per day, the former will have a much higher daily CO load due to the intensity of the smoke inhaled. CO load is also important when an individual becomes a patient in a smoking cessation program. In this case, quantification allows a caregiver or counselor to track the patient as the patient reduces his or her smoking activity. For example, the patient may reduce from 20 cigarettes per day to 18 to 16, and so on. However, at 10 cigarettes per day, the patient may still have an unreduced daily CO load because they are compensating when inhaling a reduced number of cigarettes (i.e., the patient smokes more violently and more deeply and more intensely). The patient's reduced smoking exposure occurs only when his or her CO load is reduced.

[0183] Fig.21 The data shown in is for illustrative purposes only, and the duration of the time period for a given data set depends on the amount of time an individual has used the portable sampling unit to capture biometric and behavioral data. Quantifying exposure to exhaled carbon monoxide includes correlating exhaled carbon monoxide as a function of time over a time period using the data set and obtaining the area under the eCO curve 412. In variations of the methods and systems, the eCO curve may be calculated or approximated.

[0184] Fig. 22 Examples are shown that display biometric data and various other information for the benefit of a user, caregiver, or other party in assessing an individual's smoking behavior. Fig. 22 The data shown in is for illustrative purposes and may be displayed on a portable electronic device (e.g., see Fig.19 110) or one or more computers. In addition, any of the biometric data or other data can be displayed on the portable sampling unit 1900.

[0185] Fig. 22 A "dashboard" view 118 of an individual's smoking behavior data is shown, including a graphical output 120 of an eCO curve 412 over a period of time and a cigarette count for any given time interval during the period of time. The graphical output 120 may also provide a measured or calculated nicotine trend 424. Such a nicotine trend 424 may be determined based on the number of puffs 426, rather than a direct measurement of nicotine.

[0186] Fig. 22 Also shown is a second graphical output display 122 of an eCO curve 412 over an alternative time period. In this example, the first graphical display 120 displays the eCO curve 412 over a 7-day period, while the second display 122 displays data over a 3-day period. The dashboard view 118 may also include additional information including the latest eCO burden / load 124 (or the latest eCO reading from the latest sample), the number of cigarettes 126 within a defined period such as the day, and the amount of nicotine 128. In addition, the dashboard 118 may also include a count of the number of samples 130 provided by the individual within a defined period (such as a daily to monthly count).

[0187] The dashboard 118 may also display information that may help an individual reduce or stop smoking. For example, Fig. 22 Also shown is the cost of cigarettes 132 using a count of the portion of the cigarette inhaled by the individual 126 or 426. The dashboard may also display social connections 146, 142, 140 to help stop smoking. For example, the dashboard may display a doctor or counselor 140 that can be directly messaged. Additionally, information may also be displayed to social acquaintances 142 who are also trying to reduce their own smoking behavior.

[0188] As described above, the dashboard 118 may also display information about smoking triggers 134 to serve as a reminder to the individual to avoid the triggers. The dashboard may also provide the user with additional behavioral information, including but not limited to the results of a behavioral questionnaire 136 previously completed by the individual with his / her doctor or counselor.

[0189] Dashboard 118 can also selectively display any information discussed herein based on the analysis of individual.For example, individual smoking behavior can be characterized, and such behavior is associated with some effective means in helping individual to reduce or stop smoking.In these cases, individual behavior allows classification in one or more phenotypes (individual observable quality allows classification in one or more groups).Dashboard can display the information that is found to be effective for this particular phenotype.In addition, the user can selectively adjust the information on the dashboard to allow individual discovery to be customized effectively as a non-smoking incentive.

[0190] Fig.23 Shows the display and Fig. 22 Another variation of the dashboard 118 with similar information is shown. As described above, the information displayed is customizable. For example, this variation illustrates an eCO load 140 in a graphical display showing historical data (yesterday's load), the current eCO burden or load, and a target level of load for a non-smoker. Fig. 22 and Fig.23 As shown, an individual's previous attempts at quitting smoking 138 may be displayed. In addition, a graphical representation 120 of an eCO trend 412 may be displayed with the individual's eCO readings (of the corresponding sample), wherein information regarding puff times 426 may be displayed as well as a graphical representation showing the time or duration of puffs (as shown by circles of different diameters). As described above, such information may be input by the portable sampling unit and displayed in additional forms, such as shown at 126 and 127, which show historical and current data regarding the number of puffs and the number of whole cigarettes smoked, respectively.

[0191] FIG. 24A to FIG. 24C Another variation of a data set is shown that includes exhaled carbon monoxide, collection time, and cigarette data that are quantified and displayed to benefit individuals seeking to understand their smoking behavior. Fig.24A An example is shown in which a patient collects breath samples over the course of multiple days. FIG. 24A to FIG. 24C The example data shown indicates data displayed over a 21 day period, but any time range is within the scope of the systems and methods described herein.

[0192] like Fig.24AAs shown, a time period 432 is shown along the horizontal axis, where the time interval is each day within the time period. Although not shown, during the early stages of sample collection, the time period itself may include one or more days, where the time interval is a multiple of hours or minutes. Obviously, the longer the time period, the greater the ability of the project to select meaningful time intervals within the time period.

[0193] Fig.24A A variation of the dashboard 118 is shown in which smoking data (including the total number of cigarettes 428 and associated curve 430) is superimposed on a graph showing the eCO curve 412. As described above, the individual provides a breath sample on a periodic or random basis. In some variations, a portable sampling unit (not shown) prompts the individual to provide a sample for measuring CO. The portable sampling unit allows the sample to be associated with a timestamp and transmits other user-generated data as discussed above. The CO data is then quantized to provide time intervals (e.g., as described above). Fig.24A Exposure values ​​for CO (eCO of exhaled CO) for each day) are shown.

[0194] Fig.24A Also shown is the ability to display historical data simultaneously with current data. For example, CO load data 140 shows the CO load for the previous day along with the highest CO reading, lowest CO reading, and average CO reading. A similar history is shown for cigarette data and smoking cessation questionnaire results 136.

[0195] Fig. 24B and Fig.24C A data set in graphical form is shown as an individual reduces his / her smoking behavior. Fig.24C As shown, as the individual continues to provide samples for measuring CO, the graphical representation of the data set shows the individual's self-report of smoking less, which is verified by the decreasing value of CO load 124.

[0196] System and method as described herein (that is, the quantification and display of smoking behavior and other behavioral data) can provide basis for the effective project designed to reduce the impact of cigarette smoke for health care professionals.For example, system and method described herein can be used for identifying smoker colony only from common group.Once this colony is determined, just can set up data set for the smoking behavior specific to this individual before attempting to register the individual in the smoking cessation program.As mentioned above, the quantification of smoking burden (or CO burden) together with the time data of smoking activity can be combined with other behavioral data to identify the smoking trigger unique to this individual.Therefore, before selecting the smoking cessation program, medical care health professionals can understand the smoking behavior of individual well.In addition, system and method as described herein are easily applicable to once individual enters the smoking cessation program and just detects the behavior of this individual, and once they stop smoking, just can monitor individual, to ensure that the smoking cessation program remains effective, and individual suppresses smoking.

[0197] Furthermore, the above-described systems and methods for quantifying smoking behavior may be used to build, update, and improve the models of smoking behavior discussed above, and provide perturbations to help ultimately reduce an individual's smoking behavior.

[0198] Many embodiments of the present invention have been described. However, it will be appreciated that various modifications may be made without departing from the spirit and scope of the present invention. Combinations of aspects of the variations discussed above, as well as combinations of the variations themselves, are intended to be within the scope of the present disclosure.

[0199] Without departing from the true spirit and scope of the present invention, various changes can be made to the described present invention, and equivalents (for the sake of brevity, whether or not recorded herein or not included) are replaced. In addition, any optional features of the modification of the present invention can be independently elaborated and advocated, or combined with any one or more features of the features described herein. Therefore, where possible, the present invention contemplates the combination of the various aspects of the embodiment or the combination of the embodiment itself. Reference to a single item includes the possibility of the existence of the plural number of the same item. More specifically, as used in this article and in the appended claims, unless the context clearly stipulates otherwise, the singular form "one (a)", "one (and)", "said (said)" and "the (the)" include plural references.

Claims

1. A method for quantifying an individual's smoking behavior, the method comprising: obtaining a plurality of samples of exhaled breath from the individual over a period of time and recording a collection time associated with each sample of exhaled breath; measuring an amount of exhaled carbon monoxide for each of the samples of exhaled breath; compiling a data set comprising, for each sample of exhaled breath, the amount of exhaled carbon monoxide and the time of collection; quantifying the exposure to exhaled carbon monoxide over the time period, wherein quantifying the exposure to exhaled carbon monoxide comprises correlating a function of exhaled carbon monoxide with respect to time over the time period using the data set, and obtaining an area of ​​exhaled carbon monoxide and time under a curve defined by the function over the time period, and assigning exhaled carbon monoxide burden to a plurality of time intervals over the time period based on the area; and displaying the exhaled carbon monoxide load for at least one time interval of the plurality of time intervals; The smoking behavior of the individual is quantified by the exhaled carbon monoxide burden.

2. The method according to claim 1, wherein: Obtaining a plurality of samples of exhaled breath from the individual over a period of time and recording a time of collection of each sample of exhaled breath includes obtaining the plurality of samples of exhaled breath sequentially.

3. The method of claim 1, further comprising generating a signal to the individual to provide at least one sample of exhaled breath.

4. The method of claim 1, further comprising alerting the individual on a recurring basis to provide a sample of the exhaled breath within the time period.

5. The method of claim 1 further comprising receiving input data from the individual and recording the time of the input.

6. The method according to claim 5, wherein: The input data includes at least a count of a portion of a cigarette smoked by the individual.

7. The method of claim 6, further comprising visually displaying a sum of the counts of portions of cigarettes smoked by the individual.

8. The method of claim 6, further comprising determining a cigarette cost using the count of portions of cigarettes smoked by the individual and displaying the cigarette cost.

9. The method of claim 6, further comprising determining a nicotine estimate using the count of portions of a cigarette smoked by the individual and displaying the nicotine estimate.

10. The method according to claim 5, wherein: The input data includes behavioral information of the individual.

11. The method of claim 1 further comprising providing a visual display of the exhaled carbon monoxide load associated with visual display time intervals during the period of time.

12. The method of claim 1, further comprising providing a visual display of a count of the number of samples of the plurality of exhaled breath.

13. The method of claim 1, further comprising determining a series of exhaled carbon monoxide loads for a series of time intervals within the time period.

14. The method of claim 13, further comprising displaying the series of exhaled carbon monoxide loads for the series of time intervals.

15. The method according to claim 1, wherein: Measuring the amount of exhaled carbon monoxide includes using a portable sensor.

16. The method of claim 15, further comprising transmitting the amount of exhaled carbon monoxide and the collection time associated with each sample of exhaled breath from the portable sensor to an electronic device.

17. The method of claim 1, further comprising obtaining a location of the individual when obtaining at least one of the plurality of exhaled breath samples.

18. The method of claim 1, further comprising obtaining results of a behavioral questionnaire from the individual and displaying the results of the behavioral questionnaire with the exhaled carbon monoxide load.

Images