Systems and methods for quantifying and predicting smoking behavior - Patents.com

Abstract

To provide a system and a method for supporting screening, quantification, and prediction of a smoking action and monitoring a biometrics variable and a context variable for supporting non-smoking.SOLUTION: A method for identifying a smoking action of a person; includes the steps of: recording data of plural pieces of non-biological actions supplied by the person; acquiring plural pieces of biological data from the person; quantifying smoking exposure of the person by using plural pieces of biological data; editing an action summary including at least one of the plural pieces of data of the actions and the smoking exposure; and providing the action summary with a user interface formed to permit the person to observe data in the actin summary and notify the person of how the action of the person will affect the smoking action and display at least one piece of the plural pieces of data of the actions related to the smoking exposure.SELECTED DRAWING: Figure 25A

Description

[Technical field]

[0001] (Related Applications) This application is a continuation of U.S. patent application Ser. No. 15 / 729,529, filed Oct. 10, 2017, which is related to U.S. patent application Ser. No. 15 / 258,921, filed Sep. 7, 2016, which is a continuation of U.S. patent application Ser. No. 15 / 092,475, filed April 6, 2016, which is a non-provisional application of U.S. provisional application Ser. No. 62 / 143,924, filed April 7, 2015, each of which is incorporated by reference in its entirety.

[0002] The present disclosure relates to systems and methods for monitoring biometric and contextual variables to aid in screening for smoking cessation. The systems and methods can non-invasively detect a patient's smoking behavior. The systems and methods can quantify and / or predict a patient's smoking behavior. The systems and methods can aid in smoking cessation. In some embodiments, the systems and methods are provided for screening the general population during physician and dental visits and other health-related appointments. In some embodiments, the systems and methods are provided for initiating and setting up smoking cessation programs for patients who smoke. In some embodiments, the systems and methods are provided for following up on the programs after a patient has successfully quit smoking. [Background technology]

[0003] The health problems associated with tobacco smoking are well known. Tobacco smoke contains nicotine as well as several 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 him / her. The presence and levels of carbon monoxide in a smoker's breath can provide a marker for their overall exposure to other toxic compounds as well as a marker for identifying the overall smoking behavior of the individual.

[0004] Because of the health risks and problems associated with smoking, as well as the effects of smoke on exposed non-smokers, several programs exist to assist individuals in quitting smoking, or at least reducing the amount they smoke on a daily basis.

[0005] Smoking cessation programs and products typically attempt to reduce patients' smoking without a full understanding of smoking behavior, which can vary among patients. Also, understanding a patient's smoking behavior may be difficult given that self-reports of smoking behavior depend on strict adherence to reporting smoking activities. And in many cases, individuals may not adhere strictly to reporting such activities due to shame, carelessness, and / or human error associated with tracking and assessing cigarette smoking.

[0006] There remains a need to focus on the individual who smokes by first understanding his or her smoking behavior and then, based on this understanding, engage that individual in effective measures to reduce and ultimately quit smoking. Summary of the Invention [Problem to be solved by the invention]

[0007] The systems and methods described herein enable a multi-tiered approach to engage individuals who smoke and quantify their smoking behavior to ultimately help individuals reach the goal of quitting smoking. [Means for solving the problem]

[0008] In a first example, the methods and systems described herein can provide a method for identifying an individual's smoking behavior, and the smoking behavior or smoking profile can assist the individual in quitting smoking.

[0009] For example, such a method may include recording a plurality of behavioral data from the individual, obtaining a plurality of biological data from the individual, quantifying the individual's smoking exposure using the plurality of biological data, compiling the behavioral summary where the behavioral summary includes at least one of the plurality of behavioral data and the smoking exposure, and visually displaying at least a portion of the behavioral summary to the individual to inform the individual regarding their smoking behavior.

[0010] In other variations, the method may include identifying an individual's smoking behavior and obtaining a plurality of biological data from the individual, quantifying the individual's smoking exposure using the plurality of biological data, generating a behavioral summary by correlating the individual's plurality of behavioral data with the smoking exposure, and displaying at least a portion of the behavioral summary to the individual to warn the individual about the smoking behavior.

[0011] In a variation of the method, visually displaying at least a portion of the behavioral summary includes displaying trends in the behavioral data or trends in smoking exposure.

[0012] The methods described herein allow an individual to select a behavioral summary over a subset timespan within a first timespan. The behavioral data from the individual may include tracking the number of cigarettes the individual smoked, obtaining the individual's geographic location during smoking events, determining time between cigarettes, and estimating smoking costs.

[0013] The step of visually displaying may include displaying at least intermediate results of the plurality of biological data.

[0014] The methods described herein may include facilitating interactive communication between a counselor and the individual, and the counselor is optionally provided with access to the behavior summary. In some variations, facilitating interactive communication between one or more counselors and the individual occurs after a first program phase that builds the individual's smoking profile or smoking behavior. In other variations, interactive communication between one or more counselors and the individual occurs during the first program, but the interaction does not include the counselor attempting to moderate or influence smoking behavior until the end of the first phase of the program.

[0015] The method may further include providing an interactive activity to engage the individual. Such interactive activity may include obtaining a plurality of responses to a plurality of solicitations related to the individual's smoking behavior. The method may also include the steps of compiling the individual's story and displaying the individual's story, the individual's story including the plurality of responses related to the behavioral data.

[0016] The time span for analyzing data under the method described herein may be a first program phase, and the method further displays a plurality of smoking cessation skills in a second program phase after the first program phase. The method may include any number of additional program phases. For example, a subsequent program phase may display a subject of information focused on quitting smoking to prepare the individual to quit smoking, may monitor the individual to quit smoking, and displays a subject of information focused on preventing relapse of smoking behavior.

[0017] The methods and systems described herein allow for improved measurement and quantification of a smoker's behavior before the individual is given the difficult task of trying to quit smoking. Also, for example, the systems and methods described herein are useful for identifying a population of smokers from within a larger population using objective criteria. Once an individual smoker is identified, the same methods and systems allow for learning, exploring a phase where the individual's specific smoking behavior can be tracked and quantified. The methods and systems allow for the data of tracked individual's behavior to identify potential triggers to smoke or simply educate the individual regarding the extent of their smoking. The methods and systems also allow for more active monitoring of individuals who decide to participate in a "smoke-free" program, such monitoring allowing the individual to self-monitor along with monitoring by peers, coaches or counselors. Finally, the methods and systems presented herein may be used to monitor individuals who have successfully quit smoking to ensure that smoking behavior does not reoccur.

[0018] A system and method for the assessment of an individual's smoking behavior is described herein. The system can assess behavioral data related to smoking or an individual's usual activities, as well as quantify an individual's smoking behavior by measuring biometric data and assessing the factors attributable to tobacco smoke.

[0019] The system and method can non-invasively detect and quantify a patient's smoking behavior based on one or more measurements of biometric data, such as the patient's CO level or exhaled CO level. However, other biometric data can also be used. Such data include carboxyhemoglobin (SpCO), oxyhemoglobin (SpO2), heart rate, respiratory rate, blood pressure, body temperature, sweat, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters. Such measurements or data collection can use a portable measurement unit or a fixed measurement unit, either of which communicates with one or more electronic devices to perform the quantitative analysis. Alternatively, the analysis can be performed by a portable / fixed unit. For example, the portable unit can be tethered to a key fob, a personal lighter, a mobile phone, or other item that the individual carries on a regular basis. Alternatively, the portable unit can be a standalone unit or worn by the individual.

[0020] In one variation, the methods described herein allow for quantifying an individual's smoking behavior by obtaining multiple samples of breath from an individual over a period of time and recording the collection time associated with each breath sample, measuring the amount of exhaled carbon monoxide for each of the breath samples, compiling a data set including the amount of exhaled carbon monoxide and the collection time of each breath sample, quantifying the exhaled carbon monoxide exposure over intervals of time within the period of time, using the data set to assign exhaled carbon monoxide burdens to the intervals of time, and displaying the exhaled carbon monoxide burdens. Displaying the quantified results may occur in one or more locations to provide feedback to the individual, a caregiver, or other individuals with a stake in understanding and / or reducing the individual's smoking behavior.

[0021] In other variations, obtaining multiple samples of exhaled breath from the individual over a period of time and recording the collection time of each sample of exhaled breath includes obtaining multiple samples of exhaled breath consecutively.

[0022] Quantifying the exhaled carbon monoxide exposure may include correlating a function of exhaled carbon monoxide and time over a period of time using the data set. Alternatively, the quantification may include the mathematical product of CO levels and time over an interval of time. Such quantification allows for improved observation of smoking behavior because it allows for observation of the body's total exposure to CO over a given period of time.

[0023] In another variation, the method further comprises obtaining an area under the curve of exhaled carbon monoxide and time defined by the function over an interval of time.

[0024] The method and system may further include generating a signal, for example using a portable device located on the individual, to remind the individual to provide at least one sample of exhaled breath. In other variations, the method may include alerting the individual to provide samples of exhaled breath over a period of time in a recurring manner.

[0025] The method may include receiving input data from an individual and recording the time of the input. Such data may include behavioral data, such as counting the number of cigarettes smoked by the individual. Alternatively, the data may include information about location (via a GPS unit), diet, and activity (e.g., driving, watching television, eating, working, participating in social activities, etc.).

[0026] The method may include visually displaying any of the input data, including a calculated total of the portions of cigarettes smoked by the individual. Such data may also enable the counted information to be displayed. For example, cigarette counts may be used to determine an individual's nicotine exposure from cigarettes, where direct biological measurements may also erroneously measure nicotine from nicotine patches or nicotine gum. The cigarette data may also be used to assess costs associated with the number of cigarettes smoked by an individual and display such cigarette costs.

[0027] The method may further include providing a visual display of the exhaled carbon monoxide loading associated with a visual display interval of time within the period of time. The method may also include providing a visual display of a calculation of the number of the multiple samples of exhaled breath.

[0028] The method may include determining a series of exhaled carbon monoxide loads for a series of intervals of time within the period of time. These values ​​may be displayed in addition to the information discussed herein.

[0029] The method may further include transmitting the amount of exhaled carbon monoxide and a collection time associated with each exhaled breath sample from the portable sensor to an electronic device.

[0030] Other variations for quantifying an individual's smoking behavior may include obtaining multiple samples of carbon monoxide from an individual over a period of time and recording the collection time associated with each carbon monoxide sample, compiling a data set including the amount of carbon monoxide and the collection time of each carbon monoxide sample, quantifying carbon monoxide exposure over intervals of time within the period of time and using the data set to assign a carbon monoxide burden to the intervals of time and display the carbon monoxide burden. In such cases, the amount of carbon monoxide is determined from any type of measurement that identifies carbon monoxide levels in the body.

[0031] The method may further include and facilitate obtaining multiple samples of carbon monoxide, including obtaining multiple samples of exhaled breath from the individual over time and measuring the amount of exhaled carbon monoxide for each sample of exhaled breath, and recording a collection time associated with each sample of carbon monoxide includes recording a collection time associated with each of the exhaled breath samples.

[0032] The present disclosure also includes devices for obtaining data to quantify an individual's smoking behavior. Such devices may support or perform the functions described herein.

[0033] In one embodiment, 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 disposed within the unit and configured to measure an amount of exhaled carbon monoxide for each of the exhaled breath samples, at least one input switch configured to record input data from the individual, a memory device 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 and the collection time and the input data to external electronics, and an alarm configured to provide a warning to a user to submit multiple samples of exhaled breath.

[0034] The method described herein may also include a method for preparing a smoking cessation support program for a patient who smokes tobacco.For example, the method may include the steps of measuring at least one biological indicator that determines whether the patient smokes a cigarette, capturing a plurality of patient data including information associated with the time when the patient smokes a cigarette, combining at least one of the plurality of patient data and the at least one biological indicator to determine a smoking behavior model of the patient in a first test period, evaluating the smoking behavior model to evaluate the degree of intervention required for a smoking cessation program, and providing a summary report of the smoking behavior model and the degree of intervention.

[0035] In another variation, the present disclosure includes a system for discouraging a patient from smoking. For example, the system may include a sensor for measuring at least one biological indicator for determining whether the patient smoked a cigarette, and a data collection device configured to capture a plurality of patient data including information temporally related to the time when the patient smoked a cigarette. A processor in communication with the sensor and the data collection device, the processor is configured to collect the plurality of patient data and the at least one biological indicator, and determine a model of the patient's smoking behavior over a first test period, the processor is configured to generate at least one perturbation signal before a second test period, the processor analyzes at least one of the patient data captured over the second test period to determine a tested smoking behavior, and the processor compares the tested smoking behavior with the model smoking behavior to determine whether the patient has been discouraged from smoking.

[0036] The present disclosure also includes a method for discouraging a patient from smoking. For example, such a method may include the steps of measuring at least one biological indicator for determining whether the patient smoked a cigarette, collecting a plurality of patient data including information temporally related to the time when the patient smoked a cigarette, compiling the plurality of patient data with the at least one biological indicator to determine a smoking behavior model of the patient, generating at least one perturbation signal that affects the patient before a second test period, analyzing at least one of the patient data captured during the second test period to determine a tested smoking behavior, comparing the tested smoking behavior with the model smoking behavior, determining a change from the smoking behavior model, and determining whether the patient has been discouraged from smoking.

[0037] In another variation, a system for discouraging a patient from smoking may include a database including a patient smoking behavior model including a plurality of patient historical data temporally related times when the patient smoked a cigarette, a sensor for measuring at least one biological indicator for determining whether the patient has smoked a cigarette, and a processor configured to determine an expected smoking event when analyzing the smoking behavior model and when determining an expected smoking event the processor generates at least one perturbation signal prior to the test period, configured to examine the at least one biological indicator during the test period to determine whether the patient has been discouraged from smoking during the test period, and updating the database including the smoking behavior model after determining whether the patient has been discouraged from smoking during the test period.

[0038] Other variations of the method for preventing smoking may include accessing a database including a patient's smoking behavior model including a plurality of patient history data temporally associated with times when the patient smoked a cigarette, evaluating an expected smoking event when analyzing the smoking behavior model, generating at least one perturbation signal prior to the test period when determining the expected smoking event, measuring at least one biological indicator to determine whether the patient smoked a cigarette during the test period, examining the at least one biological indicator during the test period to determine whether the patient was deterred from smoking during the test period, and updating the database including the smoking behavior model after determining whether the patient was deterred from smoking during the test period.

[0039] The above is a brief description of some of the methods and systems for quantifying smoking behavior in conjunction with an effective smoking cessation program. Other features and advantages and embodiments of the invention will be apparent to those skilled in the art from the following description and accompanying drawings, in which, for purposes of illustration only, specific forms of the invention are described in detail. Variations of the access devices and procedures described herein include combinations of features of the various embodiments or the embodiments themselves wherever possible.

[0040] Although this disclosure discusses cigarettes in various examples, the methods, systems, and improvements presented herein may be applied to any type of tobacco smoke or other inhaled types of smoke, and in such cases, this disclosure contemplates the substitution of "cigarette" with the appropriate type of tobacco or smoke producing product (including, but not limited to, cigars, pipes, etc.). [Brief description of the drawings]

[0041] [Figure 1] FIG. 1 illustrates an illustrative system including a wearable device, a mobile device, and a remote server in communication with the wearable device and the mobile device, in accordance with some embodiments of the present disclosure. [Diagram 2] FIG. 2 is a diagram illustrating another illustrative system including a wearable device and a remote server in communication with the wearable device in accordance with some embodiments of the present disclosure. [Diagram 3] FIG. 3 illustrates illustrative light absorption curves for various types of hemoglobin, allowing for measurement of carboxyhemoglobin (SpCO) and oxyhemoglobin (SpO2) levels using a photoplethysmography (PPG) sensor, in accordance with some embodiments of the present disclosure. [Figure 4] FIG. 4 illustrates a chart of a patient's change levels of SpCO during a typical five-day monitoring period prior to beginning a smoking cessation program, according to some embodiments of the present disclosure. [Diagram 5] FIG. 5 illustrates trends in SpCO levels and patient smoking triggers over typical days prior to starting a smoking cessation program, according to some embodiments of the present disclosure. [Figure 6] FIG. 6 illustrates a data structure for storing SpCO levels and smoking triggers for a patient over a typical day, according to some embodiments of the present disclosure. [Figure 7] FIG. 7 shows an illustrative flow chart for detecting a patient's smoking behavior according to some embodiments of the present disclosure. [Figure 8] FIG. 8 illustrates a sample report after a five-day evaluation for a patient according to some embodiments of the present disclosure. [Figure 9] FIG. 9 shows an illustrative chart of a patient's SpCO levels during a habituation and smoking cessation program according to some embodiments of the present disclosure. [Figure 10] FIG. 10 shows an illustrative smartphone application screen showing measurements such as SpCO, SpO2, heart rate, respiratory rate, blood pressure and temperature according to some embodiments of the present disclosure. [Figure 11] FIG. 11 shows an illustrative smartphone application screen for receiving patient-entered data according to some embodiments of the present disclosure. [Figure 12] FIG. 12 shows a screen of an illustrative smartphone application for implementing a smoking prevention protocol according to some embodiments of the present disclosure. [Figure 13] FIG. 13 shows screens of an illustrative smartphone application for representing the smoking cessation process as a game for patients, according to some embodiments of the present disclosure. [Figure 14] FIG. 14 shows an illustrative flow chart for predicting and preventing predicted smoking events according to some embodiments of the present disclosure. [Figure 15] FIG. 15 shows an illustrative flow chart of step 1414 of FIG. 14 for determining whether a preventative protocol was successful, according to some embodiments of the present disclosure. [Figure 16] FIG. 16 shows an illustrative flow chart for a single measurement of a patient's SpCO level using a PPG sensor according to some embodiments of the present disclosure. [Figure 17] FIG. 17 shows an illustrative flow chart for detecting a smoking event according to some embodiments of the present disclosure. [Figure 18]FIG. 18 shows an illustrative flowchart for applying one or more perturbations to a model for a patient's smoking behavior, according to some embodiments of the present disclosure. [Figure 19] FIG. 19 illustrates another variation of a system and / or method for further quantifying an individual's exposure to tobacco smoke and influencing an individual's smoking behavior using multiple embodiments described herein. [Figure 20A] FIG. 20A illustrates a visual representation of data that can be collected with the variation of the system shown in FIG. [Figure 20B] FIG. 20B illustrates a visual representation of data that can be collected with the variation of the system shown in FIG. [Figure 21] FIG. 21 shows an example of a data set used to determine an eCO curve over a period of time, where the eCO due to an individual's smoking behavior can be quantified over various time intervals to determine the eCO burden or eCO load for each interval. [Figure 22] FIG. 22 is a diagram illustrating an example of displaying biometric data as well as various other information for assessing an individual's smoking behavior. [Diagram 23] FIG. 23 is a diagram showing another modified example in which information similar to that shown in FIG. 22 is displayed on a dashboard. [Figure 24A] 24A-C illustrate other variations of data sets including exhaled carbon monoxide, collection time, and tobacco data that are quantified and displayed to aid individuals attempting to understand their smoking behavior. [Figure 24B] 24A-C illustrate other variations of data sets including exhaled carbon monoxide, collection time, and tobacco data that are quantified and displayed to aid individuals attempting to understand their smoking behavior. [Figure 24C]24A-C illustrate other variations of data sets including exhaled carbon monoxide, collection time, and tobacco data that are quantified and displayed to aid individuals attempting to understand their smoking behavior. [Figure 25A] 25A-25H are diagrams illustrating other variations of the above systems and methods used to implement a treatment plan for identifying an individual's smoking behavior to ultimately assist in smoking cessation and maintain the individual's status as a non-smoker. [Figure 25B] 25A-25H are diagrams illustrating other variations of the above systems and methods used to implement a treatment plan for identifying an individual's smoking behavior to ultimately assist in smoking cessation and maintain the individual's status as a non-smoker. [Figure 25C] 25A-25H are diagrams illustrating other variations of the above systems and methods used to implement a treatment plan for identifying an individual's smoking behavior to ultimately assist in smoking cessation and maintain the individual's status as a non-smoker. [Figure 25D] 25A-25H are diagrams illustrating other variations of the above systems and methods used to implement a treatment plan for identifying an individual's smoking behavior to ultimately assist in smoking cessation and maintain the individual's status as a non-smoker. [Figure 25E] 25A-25H are diagrams illustrating other variations of the above systems and methods used to implement a treatment plan for identifying an individual's smoking behavior to ultimately assist in smoking cessation and maintain the individual's status as a non-smoker. [Figure 25F] 25A-25H are diagrams illustrating other variations of the above systems and methods used to implement a treatment plan for identifying an individual's smoking behavior to ultimately assist in smoking cessation and maintain the individual's status as a non-smoker. [Figure 25G]25A-25H are diagrams illustrating other variations of the above systems and methods used to implement a treatment plan for identifying an individual's smoking behavior to ultimately assist in smoking cessation and maintain the individual's status as a non-smoker. [Fig. 25H] 25A-25H are diagrams illustrating other variations of the above systems and methods used to implement a treatment plan for identifying an individual's smoking behavior to ultimately assist in smoking cessation and maintain the individual's status as a non-smoker. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0042] A smoking cessation system and method with interactive screening is described that non-invasively detects and quantifies a patient's smoking cessation based on one or more measurements of the patient's carbon monoxide level, exhaled carbon monoxide level (eCO), carboxyhemoglobin (SpCO), oxyhemoglobin (SpO2), heart rate, respiratory rate, blood pressure, body temperature, sweat, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters, where SpCO and eCO are two methods of measuring CO levels in a patient's blood.

[0043] In some embodiments, the systems and methods described herein provide for screening the general population when visiting a doctor, dentist or other health-related appointment. The wearable device can also be applied to the patient, for example during an annual visit, to detect recent smoking behavior, and if positive, refer the smoker to further testing and ultimately to a smoking cessation program. In some embodiments, the wearable device is applied as a one-time on-site measurement. In some embodiments, the patient is provided with a wearable device to wear as an outpatient for a period of time, for example, a day, a week or other suitable period of time. The longer the wearing time, the more sensitive the detection of smoking behavior and the more accurate it may be in quantifying variables related to smoking behavior.

[0044] Upon wearing the wearable device for a suitable period of time (e.g., 5 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, sweat, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters. Data from the wearable device can be transmitted to a smartphone or cloud server or other suitable device in real-time at the end of each day, near real-time, or by other suitable time intervals. The wearable device or smartphone can measure parameters including, but are not limited to, movement, location, time of day, patient-entered data, and other suitable parameters. Patient-entered data may include stressors, life events, location, daily events, administration of nicotine patches or other nicotine preparations, administration of other medications for smoking cessation, and other suitable patient-entered data. For example, some of the patient entered data may include information regarding calls, exercise, work, sports, stress, sex, alcohol consumption, smoking, and other suitable patient entered data. The received data may be compiled, analyzed for trends, and correlated either in real time or after a period of time has elapsed.

[0045] From the above measured parameters, information regarding smoking may be derived by a processor located in a wearable device, a smartphone, a cloud server or other suitable device. For example, the processor may analyze the information to determine CO, eCO, SpCO trends, averages, peaks, fluctuations, characteristics of certain curves, slope of change and other types of changes, and may determine associations with other biometric and contextual variable trends throughout the day, and how those variables change before, during and after smoking. The processor may analyze the CO, eCO, SpCO trends to determine parameters such as the total number of cigarettes smoked, the average number of cigarettes smoked per day, the maximum number of cigarettes smoked per day, the strength of each cigarette smoked, the amount of each cigarette smoked, the time each cigarette is smoked, the time of day, the day of the week, associated stressors, geography, location and movement, etc. For example, the total number of peaks for a given day may include the number of cigarettes smoked, while the shape and size of each peak, and other characteristics may indicate the strength and amount of each cigarette smoked. The processor can analyze the heart rate and / or pulse rate data to determine trends, averages and peaks, and correlations between patient smoking behavior. For example, the processor can correlate changes in heart rate, such as tachycardia or heart rate variability, that occur before or during a smoking event that can predict when the patient will smoke a cigarette. This information can be used to preempt smoking events during smoking cessation programs. For example, if a smoking event is predicted to occur within the next 10 minutes, the patient can be notified to deliver a dose of nicotine by any of a number of mechanisms, such as delivery by transdermal patch or transdermal delivery from a reservoir of nicotine stored in the wearable device.

[0046] In some embodiments, the system and method described herein provide an assessment of a patient's smoking behavior for two test periods. In the first test period, the patient behaves as he or she normally does. A processor located in a wearable device, a smartphone, 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, there is little or no patient participation. Before the second test period, the processor determines a model of how the patient smokes.

[0047] During another test period, the processor applies a series of perturbations to the model to see if the smoking behavior changes. The perturbations can be applied to the model using a machine learning process. The machine learning process propagates the perturbations, tests the results, and adjusts the perturbations accordingly. The processor determines what works best to achieve the behavior change identified by the machine learning process by trying options.

[0048] There may be several types of perturbations, each in several dimensions. For example, a perturbation may be that sending a text message before or during a smoking event avoids or shortens the smoking event. The dimensions within the perturbation may be different senders, different timings, and / or different content for the text message. In another example, a perturbation may be that a call before or during a smoking event at a certain number of times during the day avoids or shortens the smoking event. The dimensions within the perturbation may be different callers, different timings, and / or different content for the call. In yet another example, a perturbation may be that warning the patient to reflect on the patient's smoking behavior at several points in the day subsequently avoids smoking for a period of time. The dimensions may include determining whether and when the avoidance is extinguished. In another example, a perturbation may be a reward, a team play, or other suitable trigger for avoiding or shortening the patient's smoking event.

[0049] In some embodiments, the systems and methods described herein provide for initiating and setting up a smoking cessation program for a patient. After the patient completes a five-day assessment while wearing the wearable device, a sufficient data set is compiled, analyzed by the system, and delivered to the patient or physician for a smoking cessation program. For example, a sample report may show that from October 1 to October 6, Mr. Jones smoked 175 total cigarettes, an average of 35 cigarettes per day, and a maximum of 45 cigarettes per day. Mr. Jones' CO levels averaged 5.5%, with a maximum of 20.7%, and remained above 4% for 60% of the five-day assessment period. Mr. Jones' triggers included work, home stressors, and commuting. The report recommends high-dose and frequency nicotine level predictions for initiating nicotine replacement treatment, taking into account Mr. Jones' smoking habits. This can realize a higher likelihood of patient compliance during a smoking cessation program if the treatment regimen is customized to the patient's needs from the beginning.

[0050] In some embodiments, data collected during the 5-day assessment is used to establish a baseline for the patient's vital signs, such as CO, eCO, and SpCO levels, while the patient smokes normally and prior to a smoking cessation program. The system can generate a baseline curve for the patient's vital signs based on the fluctuations in CO, eCO, and SpCO levels in the collected data. The baseline curve can serve as a reference for comparison against future measurements of the patient's CO, eCO, and SpCO levels.

[0051] In some embodiments, the patient collaborates with a physician or counselor to begin the process of entering a smoking cessation program. Having objective data before the physician and patient can assist in the setting up of the smoking cessation program and for setting medications and advising plans. In some embodiments, the system automatically sets up a smoking cessation program based on data from the evaluation period. The collected data can influence the initiation of the smoking cessation program and set up for the patient just before entering the program by assisting in medication selection and dose determination. For example, indications of higher and more frequent smoking can prompt the initiation of higher nicotine replacement therapy doses or multiple medications (e.g., adding a drug used to treat nicotine addiction, such as varenicline).

[0052] The data collected can influence and set smoking cessation program initiation by determining the frequency, type, and duration of counseling required of the patient. The data can be linked to stratification of smoker needs. For example, smokers at highest risk who smoke the highest doses will receive more intervention, while smokers at lower risk will receive less intervention. Interventions can include text messages, calls, social networking messages, or other suitable events from the patient's spouse, friends, physician, or other suitable stakeholders at certain times of the day when the patient is likely to smoke a cigarette.

[0053] The collected data can influence the initiation and initiation of smoking cessation programs by linking smoking behavior with all the variables mentioned above (such as the stressors that prompt smoking, the time of day, and other appropriate variables used to pre-counseling the patient to recognize these triggers). Counseling interventions can target these stressors. Interventions can target the time of the patient's day, such as text messages or phone calls during these times. The collected data can influence the initiation and initiation of smoking cessation programs by assigning peer groups based on smoking behavior. The collected data can be used to predict and / or avoid smoking events. For example, if tachycardia or heart rate variability precedes most smoking events, this can sound an alarm and the patient can manage their medication dosage or receive a call from a peer group, doctor, or counselor, thereby avoiding the smoking event.

[0054] In some embodiments, the systems and methods described herein provide for maintaining participation in a smoking cessation program for a patient. Once in the smoking cessation program, the patient can continue to wear a wearable device for monitoring. The system can employ analytical tools such as setting a CO, eCO, SpCO baseline and tracking progress against this baseline. For example, the trend can drop to 0 and stay there (indicating no more smoking). The trend can gradually decline with peaks and valleys (indicating a reduction in smoking). The trend can drop to zero and then spike relapse (indicating a relapse).

[0055] The system can gamify the process for the patient, improving visibility of progress. For example, the system can offer the patient a small reward in exchange for quitting smoking for a certain period of time. In some embodiments, the system transmits data in real time to healthcare providers for remote monitoring, allowing providers to efficiently monitor and adjust patient care without having to be in the office every day with the patient.

[0056] In some embodiments, the system and method described herein provide a follow-up program after the patient has successfully quit smoking. After the patient has successfully quit smoking and been verified by the system, the patient wears the wearable device for a long period of time (e.g., several months to two years) as an early detection system for relapse. The system can collect data and adopt advisory strategies as described above for smoking cessation programs.

[0057] In some embodiments, the systems and methods described herein provide a system including one or more mobile devices in communication with a mobile device and a server. FIG. 1 shows an exemplary embodiment 100 of such a system including a device 102, a device 104, and a server 106 in communication with the devices 102 and 104. The device 102 assists in detecting a patient's smoking behavior. The device 102 includes a processor, memory, and a communication link for transmitting and receiving data from the device 104 and / or the server 106. The device 102 includes one or more sensors that measure the patient's smoking behavior based on one or more measurements of the patient's CO, eCO, SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweat, 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, device 102 may include PPG-based sensors for measuring CO, eCO, SpCO, and SpO2, ECG-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, electrodermal activity-based sensors for measuring skin conductance, brainwaves, implantable sensors placed in the skin, fat or muscle to measure CO and other variables, oral CO sensors, ambient CO sensors, and other suitable sensors. These sensors can be placed at various locations on or within the body for optimal monitoring.

[0058] The device 102 may be portable or wearable. For example, the device 102 may be wearable in a manner similar to a wristwatch. In other examples, the device 102 may be portable or wearable and may be attached to a fingertip, earlobe, pinna, toe, chest, ankle, arm, skin fold, or other suitable body part. The device 102 may be attached to a suitable body part via a clip, band, strap, adhesive applied sensor pad, or other suitable medium. For example, the device 102 may be attached to a fingertip by a finger clip. In other examples, the device 102 may be attached to an earlobe or pinna by an ear clip. In yet other examples, the device 102 may be attached to a toe by a toe clip. In yet other examples, the device 102 may be attached to a chest by a chest strap. In yet other examples, the device 102 may be attached to an ankle by an ankle band. In yet other examples, the device 102 may be attached to an arm by a biceps or triceps strap. In yet other examples, the device 102 may be attached to a skin fold by a sensor pad.

[0059] The device 102 can request a sample from the patient, or the device, if worn, can take a sample without the patient's consent. Sampling can be sporadic, continuous, near-continuous, periodic, or based on other suitable intervals. In some embodiments, sampling is performed continuously as often as the sensors can perform measurements. In some embodiments, sampling is performed continuously after a set time interval, such as 5 minutes, 15 minutes, or other suitable time interval.

[0060] The device 102 includes one or more sensors for monitoring SpCO using a transcutaneous method such as PPG. The transcutaneous monitoring can employ a transmission or reflection method. The device 104 can be a smartphone or other suitable mobile device. The device 104 includes a processor, memory, and a communication link for sending and receiving data from the device 102 and / or the server 106. The device 104 can receive data from the device 102. The device 104 can include an accelerometer, a global positioning system-based sensor, a gyroscope sensor, and other suitable sensors for tracking the described parameters. The device 104 can measure certain parameters, including but not limited to movement, location, time, patient-entered data, and other suitable parameters.

[0061] The patient-entered data received by the device 104 may include stressors, life events, geographic location, daily events, administration of nicotine patches or other prescriptions, administration of other medications for smoking cessation, and other suitable patient-entered data. For example, some of the patient-entered data may include information regarding phone calls, exercise, work, sports, stress, sex, drinking, smoking, and other suitable patient-entered data. The patient's use of a smartphone for texting, calling, surfing, gaming, and other suitable uses may also be correlated with smoking behavior, and these correlations are utilized in predicting behavior and changing behavior. The device 104 or the server 106 (after receiving the data) may compile the data, analyze the data for trends, and correlate the data in real-time or after a specified period of time is completed. The server 106 includes a processor, memory, and communications links for transmitting and receiving data to and from the device 102 and / or the device 104. The server 106 may be located remotely from the devices 102 and 104, for example, at a healthcare provider's site or other suitable location.

[0062] FIG. 2 illustrates an exemplary embodiment 200 of a system including a device 202 and a server 204 in communication with the device 202. The device 202 assists in detecting a patient's smoking behavior. The device 202 includes a processor, memory, and a communication link for transmitting data to and receiving data from the server 204. The device 202 may be portable or wearable. For example, the device 202 may be wearable in a manner similar to a wristwatch. The device 202 includes one or more sensors 206 that measure the patient's smoking behavior based on one or more measurements of the patient's CO, eCO, SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweat, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters.

[0063] The device 202 may include one or more sensors 208 for measuring certain parameters, including, but not limited to, movement, location, time of day, patient-entered data, and other suitable parameters. Patient-entered data may include stressors, life events, location, daily events, administration of nicotine patches or other prescriptions, administration of other medications for smoking cessation, and other suitable patient-entered data. The patient-entered data may be received in response to a prompt to the patient on a mobile device, such as the device 104, or may be entered without a prompt at the patient's will. For example, some of the patient-entered data may include information regarding phone calls, exercise, work, sports, stress, sex, alcohol consumption, smoking, and other suitable patient-entered data. The device 202 or the server 204 (after receiving the data) may compile the data, analyze the data for trends, and correlate the data in real time or after a specified period of time is completed. The server 204 includes a processor, memory, and communication links for receiving and transmitting data from the device 202. The server 204 may be located remotely to the device 202, for example, at a healthcare provider site, or other suitable location.

[0064] In some embodiments, the device 102 or 202 includes a detector unit and a communication unit. The device 102 or 202 may include a user interface appropriate to its particular function. The user interface may receive input by a touch screen, keyboard or other suitable input mechanism. The detector unit includes at least one test element capable of detecting a substance using input of a biological parameter from the patient indicative of smoking behavior. The detector unit analyzes biological input from the patient, such as wavelengths of light passing through or reflecting from exhaled breath from the lungs, saliva, or tissue. In some embodiments, the detector unit monitors the patient SpCO using PPG. The detector unit may optionally measure many other variables, including but not limited to 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. In the case of a respiratory sensor, the patient input includes blowing into a tube as part of the detector unit. In the case of a saliva or other body fluid based sensor, patient input involves placing a fluid sample into a test chamber provided in the detector unit.

[0065] In the case of an optical-based sensor such as PPG, patient input may include placement of an emitter-detector on a finger or other area of ​​exposed skin. The detector unit records the date and time, quantifies the presence of the target substance, stores the data for future analysis, and / or transmits the data elsewhere for analysis, such as the device 104 or server 106. The communication unit includes appropriate circuitry for establishing a communication link with another device, such as the device 104, via a wired or wireless connection. A wireless connection may be established using WI-FI, BLUETOOTH, radio frequency, or other suitable protocol.

[0066] FIG. 3 illustrates an exemplary embodiment 300 of suitable wavelengths for analyzing SpO2 and SpCO using light-based sensors. A patient's SpCO can be measured by intermittently testing the patient's exhaled breath with a suitable sensor. In another example, a patient's SpCO can be measured using a transcutaneous method such as photoplethysmography (PPG). SpCO is detected by passing light through a patient's tissue, e.g., earlobe, pinna, fingertip, toe, skin fold, or other suitable body part, and analyzing the attenuation of various wavelengths. SpO2 is typically measured using two wavelengths, such as 302 (660 nm) and 306 (940 nm). SpCO can be measured using three wavelengths, e.g., 302 (660 nm), 304 (810 nm), and 306 (940 nm), or seven or more wavelengths, e.g., in the range of 500-1000 nm. Such PPG sensors can be implemented via finger clips, bands, adhesive applied sensor pads, or other suitable media. PPG sensors can be transmissive, as used in many pulse oximeters. In a transmissive PPG sensor, two or more light waveforms are sent through the patient's tissue (such as a finger), and a sensor / receiver on the other side of the target analyzes the received waveforms to determine SpCO. Alternatively, PPG sensors can be reflective. In a reflective PPG sensor, light is shone towards a target (e.g., a finger), and a receiver / sensor acquires the reflected light to determine a measurement of SpCO. Further details are provided below.

[0067] Transcutaneous or transmucosal sensors can non-invasively determine blood CO levels and other parameters based on the analysis of the attenuation of a light signal passing through tissue. Transmissive sensors are typically placed against a thin body part such as an earlobe, pinna, fingertip, toe, skin fold, or other suitable body part. Light is shone from one side of the tissue and detected on the other side. A photodiode on one side is tuned to a specific set of wavelengths. A receiver or detector on the other side detects the waveform being transmitted and the amount that is attenuated. This information is used to determine the rate of binding of O2 and / or CO to hemoglobin molecules, i.e., SpO2 and / or SpCO.

[0068] Reflectance sensors can be used on thicker body parts such as the wrist. Light shone on the surface is not measured on the opposite side, but instead on the same side in the form of light reflected from the surface. The wavelength and attenuation of the reflected light is used to determine SpO2 and / or SpCO. In some embodiments, problems due to movement of the patient's wrist are corrected using an accelerometer. For example, information from the accelerometer is used to correct errors in SpO2 and SpCO values ​​due to motion. An example of such a sensor is disclosed in U.S. Patent No. 8,224,411, entitled "Non-Invasive 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 Pulse Oximeter." These two U.S. patents are incorporated herein by reference in their entirety, including all material incorporated herein by reference.

[0069] The device 102 or 202 is configured to recognize unique characteristics of the patient, such as a fingerprint, retina scan, voice label or other biometric identifier, to prevent the representative from responding to test prompts or having test signaling that attempts to defeat the system. To this end, a patient identification subunit may be included in the device 102 or 202. One skilled in the art may configure the identification subunit as needed to include one or more of a fingerprint scanner, a retina scanner, a voice analyzer, or facial recognition, as known in the art. Examples of suitable identification subunits are disclosed, for example, in U.S. Pat. No. 7,716,383, entitled "Flash-Interfaced Fingerprint Sensor," and U.S. Patent Application Publication No. 2007 / 0005988, entitled "Multimodal Authentication," both of which are incorporated herein by reference in their entireties.

[0070] The identification subunit may include a built-in still or video camera for automatically recording a photograph or video of the patient as the biological input is provided to the test element. Regardless of the type of identification protocol used, the device 102 or 202 may associate the identification with a particular biological input, for example, by time reference, and store that information along with other information regarding that particular biological input for later analysis.

[0071] The patient may also attempt to defeat the detector, for example, by blowing into the detector with a pump, bladder, billows, or other device when the breath is tested. In saliva test embodiments, the patient may attempt to substitute a clean liquid, such as water. For optical based sensors, the patient may ask a friend to stand in for him or her. Means to overcome these attempts may be incorporated into the system. For example, the device 102 or 202 may incorporate functionality to distinguish between real and simulated breath delivery. This functionality may be incorporated by configuring the detector unit to detect oxygen and carbon dioxide, and the target substance (such as carbon monoxide). In this way, the detector unit may confirm that the gas being analyzed is coming from breath that has less oxygen and more carbon dioxide than the surrounding air. In other examples, the detector unit may be configured to detect enzymes that occur naturally in saliva to distinguish between saliva and other liquids. In still other examples, the optical based sensor may be used to measure blood chemistry parameters other than CO levels, and thus the results may be compared to known samples representative of the patient's blood chemistry.

[0072] In some embodiments, the device 104 (e.g., a smartphone) receives measurements from the device 102 (e.g., a wearable device) in real time, near real time, or periodically according to a suitable interval. The device 104 can provide a user interface to prompt the patient for certain inputs. The device 104 can provide a user interface to display certain outputs of collected data. The device 104 can allow the patient to input information that the patient believes is relevant to their condition, without prompting or in response to a prompt. Such information can include information about the patient's state of mind, such as feeling stressed or anxious. Such unprompted information can be correlated to the biological input based on a predetermined algorithm, such as associated with the biological input closest in time to the unprompted input, or associated with the first biological input occurring after the unprompted input. The server 106 (e.g., a healthcare database server) can receive such data from one or both of the devices 102 and 104. In some embodiments, the data can be stored in one or more combinations of the devices 102, 104, and 106. The data may be reported to a variety of stakeholders, such as the patient, the patient's physician, peer groups, family members, counselors, employers, or other appropriate stakeholders.

[0073] In some embodiments, the wearable device, e.g., device 102 or 202, can be applied to a patient, e.g., during a normal annual visit, to detect smoking behavior and then instruct the smoker to discontinue the program. The patient is provided with the wearable device to wear as an outpatient for a period of time, e.g., a day, a week, or other suitable period of time. Wearing for a longer period of time can provide greater sensitivity in detecting smoking behavior and greater accuracy in quantifying variables related to smoking behavior. Figure 7 below provides an exemplary flow diagram for detecting smoking behavior and is described in more detail below.

[0074] In some embodiments, employers ask employees to voluntarily wear the wearable device for a day, a week, or other suitable period of time. Incentive programs may be similar to programs for biometric screening of obesity, hyperlipidemia, diabetes, hypertension, and other suitable health conditions. In some embodiments, health care insurance companies ask subscribers to wear the wearable device for an appropriate period of time to detect smoking behavior. Based on the smoking behavior being quantified, these patients may be referred to smoking cessation programs as described in this disclosure.

[0075] When the wearable device is worn for a suitable period of time, e.g., five days, several 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. FIG. 4 shows an exemplary chart 400 for various levels of SpCO for a patient over a typical five-day monitoring period. Data points 402 and 404 indicate high levels of CO, likely indicating a high smoking event. Data points 406 and 408 indicate a low level of CO because the patient was asleep or otherwise occupied. One or more algorithms may be applied to the fine data points on the curve to detect smoking events with appropriate sensitivity and specificity. For example, the algorithm may analyze the shape, onset, rise, slope, peak, delta, decline slope, rise slope, time of change, area under the curve, and other suitable factors of the SpCO curve to detect smoking events.

[0076] Data from the wearable device may be transmitted in real time, at the end of each day, or according to other suitable time intervals to a smartphone (e.g., device 104), or a cloud server (e.g., server 106 or 204). The smartphone may measure parameters including, but not limited to, movement, location, time of day, patient-entered data, and other suitable parameters. Patient-entered data may include stressors, life events, location, daily events, administration of nicotine patches or other prescriptions, administration of other medications for smoking cessation, and other suitable patient-entered data. For example, some of the patient-entered data may include information regarding phone calls, exercise, work, sports, stress, sex, alcohol consumption, smoking, and other suitable patient-entered data. The received data may be compiled, analyzed for trends, and correlated in real time or after a period is completed.

[0077] From the parameters measured above, information regarding smoking may be derived, for example, via a processor located in the device 102, 104, or 202, or the server 106 or 204. For example, the processor may analyze the information to determine trends in CO, averages, peaks, correlations, trends in other vital signs during the day, and how these vitals change before, during, and after smoking. FIG. 5 shows an exemplary diagram 500 of the analyzed information. A patient may arrive at FIG. 5 by zooming in on a given day in FIG. 4. Data point 502 shows SpCO levels when the patient is asleep. Data point 504 shows that SpCO levels are lowest when the patient wakes up. Data points 506, 508, and 510 show that high SpCO levels are associated with triggers such as breaks, lunch, commuting, etc. The processor can analyze the SpCO trend of Figure 5 and determine parameters such as the total number of cigarettes, the average number of cigarettes per day, the maximum number of cigarettes per day, the strength of each cigarette, the quantity of each cigarette, how the patient's smoking events look on a curve that is later used in a smoking cessation program, time of day, day of week, associated stressors, geography, location, movement, etc. For example, the total number of peaks on a given day can indicate the number of cigarettes smoked, while the slope of each peak can indicate the strength of each cigarette smoked.

[0078] FIG. 6 illustrates an exemplary data structure for storing patient data. In this embodiment, the data structure 600 represents patient data 602 associated with a data point, such as data point 508, in FIG. 5. The patient data 602 includes identifying information for the patient, such as patient name 604 and patient age 606. The patient data 602 includes curve data 608 corresponding to the curve in FIG. 5. For example, the curve data 608 includes a curve identifier 610 corresponding to data point 508. The data corresponding to data point 508 may be collected by device 102, 104, or 202, and / or 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 may be entered, for example, in response to a prompt to the patient at device 104, or may be entered without a prompt at the patient's will. The curve data 608 includes a curve identifier 618 for the additional data points of Figure 5. The data structure 600 may be suitably adapted for storing patient data.

[0079] FIG. 7 illustrates an exemplary flow diagram 700 for detecting a patient's smoking behavior over a suitable evaluation period. Once the patient wears the wearable device for a suitable period, e.g., 5 days, a number of parameters are measured in real time, near real time, at the end of each day, or according to other suitable time intervals. These parameters include, but are not limited to, CO, eCO, SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweat, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters. The wearable device or other suitable device may measure parameters including, but not limited to, movement, location, time of day, and other suitable parameters.

[0080] At step 702, a processor in the smartphone (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 data entered by the patient, for example, in response to a prompt displayed to the patient on the smartphone, and / or entered without a prompt regarding the patient's will. The patient-entered data includes stressors, life events, locations, daily events, administration of nicotine patches or other prescriptions, administration of other medications for smoking cessation, and other suitable patient-entered data. At step 706, the processor transmits 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 a cloud server that hosts the patient database.

[0081] At step 708, the processor analyzes the patient data to determine smoking events. The processor can compile the data, analyze the data for trends, and correlate the data in real time or after the evaluation period is completed. For example, the processor analyzes the information to determine trends in CO, averages, peaks, shape of the curve, associations, trends in other vital signs during the day, and changes in vitals before and after smoking. The processor analyzes trends in SpCO to determine parameters such as total number of cigarettes smoked, average number of cigarettes per day, maximum number of cigarettes per day, strength of each cigarette, time of day, day of week, associated stressors, geography, location, movement, etc. For example, the total number of peaks on a particular day indicates the number of cigarettes smoked and the slope of each peak indicates the strength of each cigarette smoked.

[0082] At step 710, the processor transmits the determined smoking events and associated analysis to a patient database for storage. At step 712, the processor determines if the evaluation period has expired. For example, the evaluation period may be five days or other suitable period. If the evaluation period has not expired, 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 expired, at step 714, the processor terminates data collection and analysis. For example, the processor may evaluate all data collected at the end of the evaluation period to generate a report, as described below with reference to FIG. 8.

[0083] It is contemplated that the steps or descriptions of FIG. 7 may be used with any other embodiment of the present disclosure. Also, the steps and descriptions described in connection with FIG. 7 may be performed in alternative orders or in parallel to further the objectives of the present disclosure. For example, each of these steps may be performed in any order, in parallel, or substantially simultaneously, as needed to reduce delays or increase the speed of the system or method. Furthermore, it should be noted that any of the devices or equipment described in connection with FIG. 1 (e.g., devices 102, 104, or 106) or devices of FIG. 2 (e.g., devices 202 or 204) may be used to perform one or more of the steps of FIG. 7.

[0084] In some embodiments, the systems and methods described herein provide for initiating and setting up a smoking cessation program for a patient. After the patient completes a five-day assessment while wearing a wearable device (such as device 102 or 202), the complete data set is compiled and analyzed by the system and delivered to the patient or physician for smoking cessation programming. FIG. 8 shows an illustrative embodiment 800 of a sample report from the analysis. For example, the report shows that from October 1 to October 6, Mr. Jones smoked a total of 175 cigarettes, with an average of 35 cigarettes per day and a maximum of 45 cigarettes per day. Mr. Jones' CO levels averaged 5.5% with a maximum of 20.7%, and were above 4% for 60% of the five-day assessment period. Mr. Jones' triggers included work, stress at home, and commuting. Given Mr. Jones' smoking habits, the report recommends a high dose and high frequency nicotine level prediction for initiating nicotine replacement therapy.

[0085] In some embodiments, the patient works with a 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. The sample report in FIG. 8 is an example of measuring SpCO, generating reports on CO exposure, associated stressors, and predicting starting nicotine dose requirements. For example, smokers who smoke more heavily may be more nicotine dependent at the start of a smoking cessation program, which the processor can estimate based on 5 days of behavior, and the smoking cessation program starts the patient on a higher nicotine replacement therapy dose. This can prevent many patients from failing early in the smoking cessation program due to withdrawal symptoms. Based on the report data, such as the average and maximum number of cigarettes smoked, SpCO levels, and triggers, the processor determines the dosage of nicotine for the patient. For example, the processor can determine a high dose of nicotine for patients who smoke above a threshold number of cigarettes per day on average. As the report data is updated, the processor can also update the nicotine dosage.

[0086] The collected data may influence the initiation and setting of a smoking cessation program for a patient immediately prior to entering the program by aiding in the selection and administration of medications. For example, higher smoking indications may prompt starting with a higher nicotine replacement therapy dose or multiple medications (e.g., the addition of a medication used to treat nicotine addiction, such as varenicline). The collected data may influence the initiation and setting of a smoking cessation program by determining the frequency, type, and duration of counseling required for the patient. The data may lead to stratification of smokers' needs. For example, smokers at highest risk may have higher rates of use and receive more interventions, while lower-risk smokers receive less interventions. For example, interventions may include text messages, phone calls, social networking messages, or other appropriate events from the patient's spouse, friends, doctor, or other appropriate stakeholders on specific days when the patient is more likely to smoke.

[0087] The collected data may influence the initiation and setup of smoking cessation programs by correlating smoking behavior with all the variables mentioned above (such as the stressors that prompt smoking, the time of day, and other suitable variables used to pre-counse the patient to recognize these triggers). Counseling interventions may target these stressors, and interventions may be targeted to the time of the patient's day, such as text messages or phone calls during that time of day. The collected data may influence the initiation and setup of smoking cessation programs by assigning peer groups based on smoking behavior. The collected data may be used to predict and / or avoid smoking events. For example, if tachycardia or heart rate variability, or a suitable set of variables, precedes most smoking events, this may sound an alarm and the patient may manage a dose of medication or receive a call from a peer group, a doctor, or a counselor. FIG. 12 illustrates an exemplary embodiment for pre-empting smoking events, and is discussed in more detail below. FIG. 14 and FIG. 15 illustrate an exemplary flow diagram for predicting and preventing anticipated smoking events, and are discussed in more detail below.

[0088] In some embodiments, the systems and methods described herein provide for maintaining participation in a smoking cessation program for a patient. Once in the smoking cessation program, the patient can continue to wear a wearable device, e.g., device 102 or 202, for monitoring. The system can use analytical tools such as setting up an SpCO baseline and tracking progress against this baseline. The trend may drop to zero and stay there (indicating no more smoking). The trend may gradually decline with peaks and valleys (indicating a reduction in smoking). The trend may drop to zero and then spike relapse (indicating relapse).

[0089] The system may employ patient engagement strategies by offering small and infrequent rewards for group or individual progress to engage patients. The system may offer employer rewards, payer, spouse, or peer group rewards for engaging patients. The system may present the process for patients as a game, improving visibility of progress. FIG. 13 provides an exemplary embodiment of such a user interface, which is discussed in more detail below. In some embodiments, the system may transmit data in real time to healthcare providers for remote monitoring, allowing providers to efficiently monitor and adjust patients without needing to be in the office every day. For example, providers may send instructions to the system to adjust medication types and doses, change counseling intensity, call or text to provide positive encouragement, or trigger interventions if patients fail to abstain from smoking. This may replace staffed quit lines that are expensive and can efficiently automate the process. The system may employ increased intensity and frequency to improve patient outcomes. The system may encourage patients via scheduled calls, text messages, or other appropriate communications, with support from spouses, employers, healthcare providers, colleagues, friends, and other appropriate parties.

[0090] FIG. 9 shows an exemplary graph 900 for tracking average daily SpCO trends until a patient enters a habituation and smoking cessation program. As the SpCO trend improves, the average trend is tracked daily. A physician or counselor can zoom in on a specific day (current or past) to see detailed CO and the association of CO with other measured parameters and associated stressors 910. Visibility of CO trends over time in a smoking cessation program may prevent patient dropout, prevent smoking relapse, titrate medication and counseling, and improve outcomes. For example, data point 902 shows the CO levels before the patient entered a smoking cessation program. Data points 904 and 906 show the CO levels when nicotine replacement therapy and varenicline therapy were administered during the smoking cessation program. Data point 908 shows that the patient successfully quit smoking. At this point, the system may recommend that the patient participate in a relapse prevention program to prevent relapse.

[0091] In some embodiments, the systems and methods described herein provide a follow-up program after a patient has successfully quit smoking. After successful quitting and verified by the system, the patient wears a wearable device (such as device 102 or 202) for an extended period of time (e.g., several months to two years) as an early detection system for relapse. The system can collect data and employ counseling strategies as described above for smoking cessation programs.

[0092] In some embodiments, patients receive a wearable device (e.g., device 102 or 202) and an app for their smartphone (e.g., device 104) to remotely and personally assess their health by tracking several different parameters. Patients can optionally submit breath samples or place their finger on the sensor of the wearable device several times a day. They may also wear the wearable device for more frequent or continuous measurements. At the end of the test period, e.g., 5-7 days or other suitable period, the smartphone's processor can calculate their CO exposure and related parameters. FIG. 10 shows an exemplary app screen 1000 showing measurements such as SpCO 1002, SpO2 1004, heart rate 1006, respiratory rate 1008, blood pressure 1010, and temperature 1012. Alert indicators 1014 and 1016 are provided for atypical measurements, potentially indicating the effects of smoking on the body. The system can prompt the patient with an alert when the alert indicator 1014 or 1016 is activated.

[0093] The system may encourage the patient to participate in a smoking cessation program and provide options for such a program. The patient may agree to enter into a smoking cessation program upon seeing such objective evidence of smoking. The system may share this data with the patient's spouse, physician, or other appropriate stakeholder involved in the patient's smoking cessation program. For example, the system may share the data with an application on the stakeholder's mobile device, or send a message including the data via email, phone, social networking, or other appropriate medium. Triggers for the patient to participate in the smoking cessation program include spouse suggestion, employer incentives, peer pressure, personal choice, illness, or other appropriate triggers. The patient may start the smoking cessation program on their own or bring the data to their physician for assistance in participating in the smoking cessation program.

[0094] While the patient is initiated in a smoking cessation program, the wearable device (e.g., device 102 or 202) continues to monitor the patient's health parameters, such as heart rate, movement, location, etc., that precede smoking behavior and transmits the data to the patient and / or his physician to improve treatment. For example, a smartphone app on device 104 can receive patient-entered data, including, but not limited to, stressors, life events, locations, daily events, administration of nicotine patches or other prescriptions, administration of other medications for smoking cessation, and other suitable patient-entered data.

[0095] FIG. 11 shows an exemplary embodiment of an app screen 1100 for receiving patient-entered data. The app screen 1100 may be displayed when the smartphone app receives an indication of a smoking event, for example, due to a spike in the patient's CO level. The app screen 1100 prompts the user to enter a smoking event trigger. For example, the patient can select from one of options 1102, 1104, 1106, and 1108 as triggering the smoking event, or select option 1110 to provide further information regarding the trigger. Other triggers of a smoking event include phone calls, exercise, sports, stress, sex, and other suitable patient-entered data. The patient can also voluntarily invoke the app screen 1100 to enter smoking event trigger information. In some embodiments, the app screen 1100 for receiving patient data is displayed to the patient during a five-day evaluation period to collect information regarding smoking behavior before the patient enters a smoking cessation program.

[0096] In some embodiments, the collected data is used by the smartphone app to avoid smoking events. A processor running the app or a processor of another device, such as the device 102 or 202 or server 106 or 204, can analyze information about what is happening to the heart rate and other vital signs in the period leading up to a smoking event. The processor can correlate changes in heart rate, such as tachycardia, that can predict when a patient will smoke. This information can be used to initiate a prevention protocol to stop a smoking event. For example, the prevention protocol can include delivering a bolus of nicotine. The nicotine may be delivered via transdermal delivery from a transdermal patch or a wearable device, e.g., a reservoir of nicotine stored in the device 102 or 202. In other examples, the prevention protocol can include placing a call to the patient's physician, peer group, or other appropriate stakeholder. The processor can, for example, send instructions to an automated call system resident on the server 106 or 204 to initiate the call. Figures 14 and 15 provide a flow diagram for predicting a smoking event based on a patient's vital signs, and are described in more detail below.

[0097] FIG. 12 shows an exemplary embodiment of an app screen 1200 implementing such a prevention protocol. For example, if the patient is prone to tachycardia 20 minutes before every cigarette, the processor can detect the tachycardia and instruct the patient to administer nicotine via option 1202. The patient may vary the nicotine dose via option 1204. In some embodiments, the nicotine is administered automatically. The amount can be determined based on the patient's current SpCO level or other appropriate parameters. The patient can receive calls from a peer group via option 1206, a physician via 1208, or other appropriate stakeholders. The callers can encourage the patient to quit smoking and suggest finding other activities to divert the patient's attention.

[0098] In some embodiments, the smartphone app presents the process for the patient as a game to improve visibility of progress. The app can employ patient engagement strategies by offering small frequent or infrequent rewards for group or individual progress to engage the patient. The app may offer employer rewards, payer, spouse, or peer group to engage the patient. FIG. 13 shows an illustrative app screen 1300 for such an embodiment. The app screen 1300 offers a reward to a patient who has abstained for 15 days. A prompt 1302 prompts the patient to abstain for another 15 days. The patient can select option 1304 to accept the reward and continue to monitor progress without smoking. However, the patient may have difficulty abstaining from smoking and can select option 1306 to contact a peer group, counselor, family member, doctor, or other appropriate party.

[0099] In some embodiments, the patient is another peer and supporter of their group. The groups can track each other's progress and provide support. For example, group members may be part of a social network where they can view each other's statistics and encourage each other to quit smoking. In another example, when the patient is detected smoking, a message, such as a tweet, is sent to group members of the patient's social network, such as followers. The message can inform the group members that the patient needs help. The group can engage the patient in various ways to provide support. This interaction can help the patient to further abstain from smoking for the day.

[0100] 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 one-time, on-site measurement of the patient's SpCO level. The SpCO level may exceed a certain threshold that suggests the patient is smoking. FIG. 16 provides a flow diagram for a one-time 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, e.g., a day, a week, or other suitable period of time. A longer period of wear may provide greater sensitivity in detecting smoking behavior and greater accuracy in quantifying variables related to smoking behavior.

[0101] The wearable device (such as device 102 or 202) and smartphone device (such as device 104) 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, physician, or other appropriate party. The smartphone app can also provide the data in a digestible form for daily or weekly consumption by the patient and / or physician. For example, the smartphone app may generate a display similar to FIG. 9 showing daily progress with an option to zoom in on a particular day to see details. The physician can communicate with the mobile device running the smartphone app to log the patient into a healthcare database stored, for example, on server 106 or 204, and continue to receive data from the smartphone app via the Internet or other suitable communications link. The smartphone app can receive data from the sensor via a wired connection to the mobile device running the app, or via a wireless connection, such as WI-FI, BLUETOOTH, radio frequency, or other suitable communications link.

[0102] The patient and physician can set a future quit date and send the patient home without or with medication to help the patient quit. The patient can begin working toward the agreed upon quit date. Feedback from a wearable device or smartphone app can help the patient smoke less than when they first begin quitting and be more prepared for the quit date when they actually quit. Once the patient begins the smoking cessation program, they can get daily or weekly feedback from a spouse, physician, nurse, counselor, colleague, friend, or other appropriate party.

[0103] The drug therapy, if prescribed, can be administered by a physician or can be adjusted automatically based on the patient's performance. For example, a physician can remotely increase or decrease the nicotine dosage based on the patient's CO, eCO, and SpCO levels. In other examples, a processor in a wearable device, e.g., device 102 or 202, a smartphone, e.g., device 104, or a remote server, e.g., server 106 or 204, can increase or decrease the nicotine dosage from the patient's past measurements based on CO trends. Similarly, the drug therapy may be shortened or extended in duration according to collected data.

[0104] FIG. 14 shows an example flow diagram 1400 for predicting a smoking event based on a patient's CO, eCO, SpCO measurements and other suitable factors. The patient may be provided with a wearable device, e.g., device 102 or 202, and a smartphone app 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 the PPG measurements of the patient's SpCO level and associated time and location. The processor may also receive other information, such as heart rate, respiratory rate, and other suitable factors in predicting a smoking event.

[0105] At step 1404, the processor updates a patient database stored locally or at a remote location, e.g., a health care database at the server 106, with the received patient data. At step 1406, the processor analyzes current and previous measurements of patient parameters to determine whether a smoking event is expected. For example, the SpCO trend may be at a local minimum. This indicates that the user may reach for a cigarette to increase the SpCO level. The processor may 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, at step 1410, the processor determines whether the time and / or location indicates an expected smoking event. For example, the processor may determine that the patient typically smokes when the patient wakes up around 7:00 a.m. In other examples, the processor may determine that the patient typically smokes right after the patient goes to work. In yet other examples, the processor may determine that the patient typically smokes in the evening whenever the patient visits a particular restaurant or bar.

[0106] If the processor determines from either step 1408 or 1410 that a smoking event is expected, then in step 1412, the processor initiates a prevention protocol for the patient to prevent the smoking event. Information regarding the prevention protocol may be stored in memory of the device 102, 104, or 202, or the server 106 or 204, or a combination thereof. The information regarding the prevention protocol may include instructions for one or more intervention options to initiate when the patient is about to smoke. For example, the processor may initiate an alarm on the patient's mobile phone and display an app screen similar to FIG. 12. The app screen may display patient options for managing nicotine or receiving calls from colleagues, physicians, or other appropriate parties. Alternatively, the prevention protocol may include automatically administering a bolus of nicotine to the patient from a reservoir of nicotine stored on the patient's wearable device. In other examples, the app screen may indicate that a message (e.g., a tweet) is sent to group members (e.g., followers) of the patient's social network when it is detected that the patient has not stopped smoking. The patient may refrain from smoking to avoid sending messages indicating his or her failure.

[0107] In some embodiments, steps 1408 and 1410 are combined into one step or include two or more steps for the processor to determine that a smoking event is expected. For example, the processor may determine that a smoking event is expected based on a combination of SpCO trend, patient location, and / or current time. In other examples, the processor may determine that a smoking event is expected based on a series of steps analyzing one or more of the patient's SpCO, SpO2, heart rate, respiratory rate, blood pressure, temperature, sweat, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters.

[0108] At step 1414, the processor determines whether the prevention protocol was successful. If a smoking event occurred, at step 1418, the processor updates the patient database to indicate that the prevention protocol was not successful. If a smoking event did not occur, at step 1416, the processor updates the patient database to indicate that the prevention protocol was successful. The processor returns to step 1402 and continues to receive PPG measurements of the patient's SpCO level and related data. The processor may continue to monitor the patient's vital signs to ensure that the patient does not relapse into a smoking event.

[0109] It is contemplated that the steps or descriptions of FIG. 14 may be used with any other embodiment of the present disclosure. Additionally, the steps and descriptions described in connection with FIG. 14 may be performed in alternate orders or in parallel to further the objectives of the present disclosure. For example, each of these steps may be performed in any order, or in parallel, or substantially simultaneously, as necessary, to reduce delays or increase the speed of the system or method. Additionally, any of the devices (e.g., devices 102, 104, or 106) or apparatus described in connection with FIG. 1 or devices (e.g., devices 202 or 204) described in connection with FIG. 2 may be used to perform one or more of the steps of FIG. 14.

[0110] FIG. 15 illustrates an exemplary flow diagram 1500 for determining whether a prevention protocol was successful in connection with step 1414 of FIG. 14. In step 1502, the processor receives patient data for determining whether a smoking event occurred. In step 1504, the processor analyzes the currently received patient data and the previously received patient data. In step 1506, the processor determines whether a smoking event occurred based on the analysis. For example, if nicotine was not administered but the patient's SpCO level is now higher than the previous SpCO level, the processor may determine that the patient has relapsed and smoked a cigarette. In such a situation, in step 1508, the processor returns a message indicating that the prevention protocol was not successful. In another example, if the patient's vital signs do not indicate an increase or decrease in SpCO level, the processor may determine that a smoking event did not occur. In such a situation, in step 1510, the processor returns a message indicating that the prevention protocol was successful.

[0111] It is contemplated that the steps or descriptions of FIG. 15 may be used with any other embodiment of the present disclosure. Additionally, the steps and descriptions described in connection with FIG. 15 may be performed in alternate orders or in parallel to further the objectives of the present disclosure. For example, each of these steps may be performed in any order, or in parallel, or substantially simultaneously, as necessary, to reduce delays or increase the speed of the system or method. Additionally, any of the devices or apparatuses described in connection with FIG. 1 (e.g., devices 102, 104, or 106) or devices or apparatuses described in connection with FIG. 2 (e.g., devices 202 or 204) may be used to perform one or more of the steps of FIG. 15.

[0112] FIG. 16 illustrates an exemplary flow diagram 1600 for one-time measurement of a patient's SpCO level using a PPG sensor. For example, a wearable device, e.g., device 102 or 202, is applied to a patient and receives a sample for one-time measurement of the patient's SpCO level. At step 1602, a processor in the wearable device receives the PPG measurement of the patient's SpCO level and other suitable data, such as time, location, SpO2, heart rate, respiratory rate, blood pressure, temperature, sweat, 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 increase in SpCO level above a certain threshold may suggest that the patient recently smoked a cigarette.

[0113] In step 1606, the processor determines whether the patient's SpCO level indicates that a smoking event has occurred. For example, an SpCO level above a specified threshold may indicate a smoking event. In other examples, one or more of the shape, onset, rise, slope, peak, delta, fall slope, rise slope, time of change, area under the curve, and other suitable factors of the SpCO curve may indicate a smoking event. One or more of these factors may assist in quantifying the smoking event. For example, the total number of peaks on a particular day may indicate the number of cigarettes smoked, and the shape and size of the slope 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 a smoking event has not occurred, in step 1608, the processor returns a negative message indicating that the patient has not had a recent smoking event. The patient's physician may find this information useful in assessing the patient's smoking behavior. If the processor determines that the SpCO level indicates that a smoking event has occurred, in step 1610, the processor returns a confirmation message indicating that the patient has had a recent smoking event. In this case, the collected data may be used to set up a smoking cessation program for the patient as described above.

[0114] After steps 1608 or 1610, in step 1612 the processor updates the patient database to record this information. In step 1614, the processor finishes evaluating the patient's SpCO level. The patient may be provided with a wearable device to wear as an outpatient for a period of time, e.g., a day, a week, or other suitable period. Longer periods of wear may provide greater sensitivity in detecting smoking behavior and greater accuracy in quantifying variables related to smoking behavior.

[0115] It is contemplated that the steps or descriptions of FIG. 16 may be used with any other embodiment of the present disclosure. Also, the steps and descriptions described in connection with FIG. 16 may be performed in alternative orders or in parallel to further the objectives of the present disclosure. For example, each of these steps may be performed in any order, in parallel, or substantially simultaneously as necessary to reduce delays or increase the speed of the system or method. Furthermore, any of the devices or equipment described in connection with FIG. 1 (e.g., devices 102, 104, or 106) or devices or equipment described in connection with FIG. 2 (e.g., devices 202 or 204) may be used to perform one or more of the steps of FIG. 16.

[0116] In some embodiments, data from one or more devices associated with the patient, such as devices 102 and 104 or device 202, is received at a central location, such as server 106 or 204. The patient's devices log multiple biometric and contextual variables in real time or near real time. For example, biometric variables include CO, eCO, SpCO, SpO2, heart rate, respiratory rate, blood pressure, temperature, sweat, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, and other suitable biometric variables. For example, contextual variables may include GPS location, patient activity (e.g., sports, gym, shopping, or other suitable patient activity), patient environment (e.g., at work, at home, in the car, at a bar, or other suitable patient environment), stressors, life events, and other suitable situational variables. Data collected may also include in-person observations of the patient's smoking behavior. A spouse, friend, or peer may enter data about the patient's smoking and correlate that data with the SpCO measurement to determine accuracy.

[0117] The server 106 includes a processor for receiving data for a plurality of patients over a period of time and analyzes the data for trends occurring around the time of an actual smoking event. Based on the trends, the processor determines diagnostic and / or detection tests for the smoking event. The tests include one or more algorithms that are applied to the data determined by the processor. For example, the processor may analyze a spike in the patient's CO level. Detecting a spike may include determining that the CO level is above a certain specified level. Detecting a spike may include detecting a relative increase in the patient's CO level from a previously measured baseline. The processor may detect the spike as a change in the slope of the patient's CO trend over a period of time. For example, a CO trend moving from a negative slope to a positive slope may indicate a sudden increase in CO levels. In other examples, the processor may apply one or more algorithms to changes in heart rate, increased heart rate variability, changes in blood pressure, or other suitable data changes to detect a smoking event.

[0118] FIG. 17 illustrates an exemplary flow diagram 1700 for detecting a smoking event as described above. A processor (e.g., in the server 106 or 204) can determine diagnostic and / or detection tests for a smoking event according to the flow diagram 1700. In step 1702, the processor receives current patient data. In step 1704, the processor retrieves previously stored patient data from a database, e.g., a patient database stored in the server 106 or 204. In step 1706, the processor compares the current patient data with the previous patient data to detect a smoking event. For example, the processor can analyze a spike in the patient's CO level. Detecting a spike can include detecting a relative increase in the patient's CO level from a previously measured baseline. The processor can detect the spike as a change in the slope of the patient's CO trend over a period of time. For example, a CO trend moving from a negative slope to a positive slope may be indicative of a smoking behavior. In other examples, the processor can apply one or more algorithms to changes in heart rate, increases in heart rate variability, changes in blood pressure, or other suitable data changes to detect a smoking event. At step 1708, the processor determines whether a smoking event has occurred, for example, based on a spike in the patient's CO levels as described. If a smoking event is not detected, at step 1710, the processor returns a message indicating that a smoking event did not occur. If a smoking event is detected, at step 1712, the processor returns a message indicating that a smoking event has occurred. At step 1714, the processor updates the patient database with the results of either step 1710 or 1712.

[0119] It is contemplated that the steps or descriptions of FIG. 17 may be used with any other embodiment of the present disclosure. Also, the steps and descriptions described in connection with FIG. 17 may be performed in alternate orders or in parallel to further the objectives of the present disclosure. For example, each of these steps may be performed in any order, in parallel, or substantially simultaneously as necessary to reduce delays or increase the speed of the system or method. Furthermore, any of the devices or apparatuses described in connection with FIG. 1 (e.g., devices 102, 104, or 106) or devices or apparatuses described in connection with FIG. 2 (e.g., devices 202 or 204) may be used to perform one or more of the steps of FIG. 17.

[0120] In some embodiments, the processor first analyzes the received data to determine when a person smokes and ties the algorithm to the variable that triggers the algorithm to diagnose and / or detect a smoking event. As additional patient data is received, the processor continues to analyze other variables. The processor determines other variables that change when the patient smokes and uses those variables instead to trigger the algorithm. For example, the processor may choose to use other variables because they are less invasive or easier to measure than the initially selected variable.

[0121] In some embodiments, the algorithm for detecting smoking events has high sensitivity. Sensitivity is defined as the percentage of the number of actual smoking events detected by the sensor and algorithm. For example, if a patient smokes 20 times a day, the algorithm will have a sensitivity of 100% if it identifies all smoking events.

[0122] 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 of smoking events (i.e., a positive test when no smoking events are present). If the sensor and algorithm make no false positive calls in a day, the specificity will be 100%.

[0123] In another example, if a patient smokes 20 times and the algorithm identifies 18 of 20 actual smoking events and indicates the other 20 false smoking events, it has a sensitivity of 90% (i.e., 90% of the smoking events are detected) and a specificity of 50% (i.e., it overcalls the number of smoking events by 2-fold).

[0124] In some embodiments, after the processor determines and applies one or more algorithms to the SpCO measurement to detect smoking events with appropriate sensitivity and specificity, the processor determines whether there are other biometric or contextual variable associations with the SpCO result that can be used on their own (without SpCO) to detect smoking events. The processor determines which other variables change when the patient smokes and uses those variables instead to trigger the algorithm. For example, the processor may choose to use the other variables because they are less invasive, easier to measure, or more reliable than the initially selected variables.

[0125] In some embodiments, the processor analyzes the received patient data to predict the likelihood of a smoking event before it occurs. The processor may analyze the received patient data over a period of time, e.g., 5 minutes, 10 minutes, 15 minutes, 20 minutes, or other suitable time interval, prior to the smoking event to determine one or more triggers. For example, some smoking events may be preceded by a contextual trigger (e.g., before, during, or after a bar, a meal, before, during, or after sex, or other suitable contextual trigger). In other examples, some smoking events may be preceded by a change in a biometric variable, e.g., heart rate or other suitable biometric variable. The determined variables may overlap with the variables selected for diagnosis and detection, and therefore may also be used for prediction. Alternatively, the determined variables may not overlap with the variables selected for diagnosis.

[0126] The processor can notify the patient of a possible smoking event and trigger a prevention protocol (e.g., as discussed with respect to Figures 14 and 15) to prevent smoking change behavior. The processor can, for example, detect the patient's smoking events entered into a smoking cessation program and track and analyze trends in the received patient data. The processor can determine the patient's goals and reward them when he achieves the set-up goals (e.g., as discussed with respect to Figure 13). The processor can predict when the patient is about to smoke and just in time to intervene by suggesting a call to a peer group or a doctor, or by administering a bolus of nicotine (e.g., as discussed with respect to Figure 12).

[0127] In one example, the processor predicts a patient's smoking event preceded by an increase in heart rate (or other suitable change in a variable) based on 75% of the patient's smoking events during the diagnosis. During the smoking cessation program, the processor applies one or more algorithms to the received patient data to predict smoking events and initiate a prevention protocol. For example, the prevention protocol can engage the patient at the appropriate time by contacting the patient with a supporter, such as a doctor, counselor, peer, team member, nurse, spouse, friend, robot, or other suitable supporter. In some embodiments, the processor applies algorithms to adjust settings based on a 5-day run-in diagnostic period, such as each patient's baseline, threshold, sensitivity, and other suitable settings. The processor then uses these customized algorithms to execute a smoking cessation program for the particular patient. The combination of techniques described for changing a patient's smoking behavior may be referred to as a digital drug.

[0128] In some embodiments, the processor detects smoking in a binary manner with positive or negative indicators. The processor first detects smoking behavior using observational studies and SpCO measurements from the patient. For example, the processor receives data from the observational data of the patient's smoking behavior regarding a true positive for a smoking event. The processor determines whether the detection based on the SpCO measurement is consistent with a true positive for a smoking event. If there is a match, the processor applies an algorithm to other patient data received, such as the patient's SpCO, SpO2, heart rate, respiratory rate, blood pressure, body temperature, sweat, heart rate variability, electrical rhythm, pulse rate, galvanic skin response, pupil size, geographic location, environment, ambient temperature, stressors, life events, and other suitable parameters. The processor determines whether a pattern in the non-SpCO variable data is also indicative of a smoking event. Such variables can be used in algorithms in non-SpCO devices, such as wearable smart watches and heart rate monitor straps, to detect smoking events.

[0129] The processor may quantify smoking behavior when detected based on the received patient data. For example, the processor may analyze trends in SpCO data to indicate how hard the patient smoked each cigarette, the number of cigarettes smoked per day, the amount of each cigarette smoked, and / or the time it took to smoke each cigarette. The processor may also use other biometric or contextual variables for indicators. The processor may use the received patient data to predict the likelihood that a smoking event will occur in the near future, for example, in the next 10 minutes. The processor may analyze the received patient data over a preceding period prior to the smoking event, for example, 5 minutes, 10 minutes, 15 minutes, 20 minutes, or other suitable time interval, to determine one or more triggers.

[0130] In some embodiments, the systems and methods described herein provide an assessment of a patient's smoking behavior. During a five-day test period, the patient behaves as normal. The device 102, 104, and / or 106, or the device 202 and / or the server 204, receives patient data regarding the patient's smoking behavior. There is little or no patient involvement, as the purpose of the test period is to observe the patient's smoking patterns. The test period can be extended to a second five days as needed. Alternatively, the first and second periods may be shorter, e.g., two or three days, or longer, e.g., one week or more. Prior to the second test period, the processor determines a model of the patient's smoking method.

[0131] In a second test phase, the processor applies a series of perturbations to the model to see if the smoking behavior changes. There are several types of perturbations, each with several dimensions. For example, a perturbation can be whether sending a text message before or during a smoking event avoids or shortens the smoking event. The dimensions within the perturbation can be different senders, different timing, and / or different content of the text message. In other examples, a perturbation can be whether a phone call at a particular time of day or before or during a smoking event avoids or shortens the smoking event. The dimensions within the perturbation can be different callers, different timing, and / or different content of the call. In yet other examples, a perturbation can be whether to warn the patient to consider their smoking behavior at some points in the day and avoid smoking for a period of time thereafter. The dimensions can include determining if and when that aversion is extinguished. In other examples, a perturbation can be a reward, a team play, or other suitable trigger to avoid or shorten the patient's smoking event.

[0132] In some embodiments, the processor uses a machine learning process to provide perturbations to the patient's smoking model. The machine learning process provides the perturbations, tests the results, and adjusts the perturbations accordingly. The processor determines which is best for achieving the identified behavior change by trying options via the machine learning process. The machine learning process can be applied as small perturbations in the second testing phase. The machine learning process can also apply larger perturbations during the patient's smoking cessation phase to increase the patient's efforts to quit or continue to quit smoking.

[0133] FIG. 18 shows an example flow diagram 1800 for applying one or more perturbations to a patient's smoking model in a second testing phase. In step 1802, a processor in the wearable device 102 or 202, the mobile device 104, or the server 106 or 204 receives patient data regarding the patient's smoking behavior in the first testing phase. In step 1804, the processor analyzes the received patient data to determine a model of the patient's smoking behavior. In step 1806, the processor applies one or more perturbations to the model to see if the smoking behavior changes. The perturbations can be applied to the model using a machine learning process. There are several types of perturbations, each with several dimensions. For example, a perturbation can be whether sending a text message before or during a smoking event avoids or shortens the smoking event. The dimensions in the perturbation can be different senders, different timing, and / or different content of the text message.

[0134] In step 1808, the processor determines whether the perturbation changed the patient's smoking behavior. For example, the processor determines whether receiving a text message before or during a smoking event caused the patient to quit smoking or to cut short a smoking session. If the perturbation caused a change in the patient's smoking behavior, in step 1810, the processor updates the model of the patient's smoking behavior to reflect the positive outcome of the applied perturbation. The processor then moves to step 1812. If not, the processor moves directly from step 1808 to step 1812 to determine whether to apply another perturbation or a change in the dimension of the current perturbation. The processor can use a machine learning process to determine whether to apply additional perturbations to the model. If no perturbations need to be applied, in step 1814, the processor ends the process of applying perturbations.

[0135] If more perturbations need to be applied, in step 1816, the processor determines other perturbations to apply to the model. For example, the processor may adjust the current perturbation to send a text message to the patient at a different time or with different content. In other examples, the processor may apply a different perturbation by calling the patient before or during a smoking event. The processor returns to step 1806 of applying the perturbation to the model. The processor may provide the perturbation using a machine learning process, test the results, and adjust the perturbation or select other perturbations accordingly. In this way, the processor determines which is most effective for achieving the identified behavior change in the patient by trying different options via the machine learning process.

[0136] It is contemplated that the steps or descriptions of FIG. 18 may be used with any other embodiment of the present disclosure. Also, the steps and descriptions described in connection with FIG. 18 may be performed in alternative orders or in parallel to further the objectives of the present disclosure. For example, each of these steps may be performed in any order, in parallel, or substantially simultaneously as necessary to reduce delays or increase the speed of the system or method. Furthermore, any of the devices or apparatuses described in connection with FIG. 1 (e.g., devices 102, 104, or 106) or devices or apparatuses described in connection with FIG. 2 (e.g., devices 202 or 204) may be used to perform one or more of the steps of FIG. 18.

[0137] In an illustrative example, a 52-year-old male patient is encouraged by his employer to be screened for smoking behavior. The patient enrolls in an assessment program on June 1, 2015. The patient reports smoking 20 cigarettes per day. A program coordinator, such as a physician or counselor, loads an app onto the patient's smartphone, such as mobile device 104, and provides the patient with a connected sensor, such as wearable device 102 or 202. The coordinator informs the patient to smoke and behave normally during the five-day test period and respond to prompts from the app as they occur. After the five-day period ends, the coordinator places the patient in a supplemental test period, where the app will prompt a little more frequently (e.g., to apply a perturbation). The coordinator informs the patient that it is up to the patient to respond in whatever way he wishes at that point. The coordinator sets a target date of June 10, 2015 to include the ten days of testing.

[0138] After the 5-day testing period, the coordinator receives a report (e.g., the 5-day report card described in Figure 8). The report compares 150 smoking events detected using CO with 100 smoking events based on patient estimation. The report indicates that relevant contextual variables include alcohol, location, stress, and other pertinent data. The report indicates that relevant biometric variables include increased heart rate without movement, as it preceded 50% of the smoking events. The report indicates that the stress level prompt indicated increased stress in 20% of the smoking events.

[0139] During the supplemental 5-day test period, a processor in the mobile device (e.g., device 104), wearable device (e.g., device 102 or 202), or 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 that includes the number of cigarettes smoked, the smoking intensity, and the time of day. As the day progresses, the prompts cause the patient to smoke less for longer periods of time. The net effect is that the patient smokes fewer cigarettes in the second half of the day compared to the first half. In another example, the mobile device prompts the patient at 10 a.m. each day with a display that includes the number of cigarettes smoked the previous day. The net effect is examined as to how the prompts affect the patient's smoking behavior for the remainder of the day. The machine learning process can adjust the time and content of the display to change the dimensionality of the perturbation as needed.

[0140] In another embodiment, the processor applies the perturbation via a machine learning process in the form of a text message sent to the patient during the smoking event. The machine learning process varies the dimension of the perturbation by different senders, different timing, sending before or during smoking, different content of the message, different images in the message, and / or different rewards for abstaining. In another embodiment, the processor applies the perturbation via a machine learning process in the form of a phone call to the patient during the smoking event. The machine learning process varies the dimension of the perturbation by different callers, different timing, calling before or during smoking, different content of the call, different tone of the call, and / or different rewards for abstaining.

[0141] In another embodiment, the processor applies the perturbation via the machine learning process in the form of a prompt for a particular activity on the patient's mobile device. The prompt may indicate that the patient is smoking, but should consider smoking only half a cigarette before going outside. During long periods between cigarette events, or when an event is predicted, the machine learning process applies the perturbation to try to avoid the smoking event altogether. For example, the mobile device may display a prompt informing the patient that they are in a high-risk zone and should consider other activities or locations, or call a friend.

[0142] After the test period, the coordinator places the patient in the smoking cessation program. During the smoking cessation period, the processor receives the patient's data and applies the algorithm to the data as described above. The processor uses all data from the first and second test periods to customize the algorithm and the initiation regimen and smoking cessation program interventions for the particular patient. The diagnostic and detection algorithm detects smoking behavior using one or more biometric variables of the patient, such as SpCO. The smoking cessation program includes nicotine therapy beginning on day one as part of nicotine replacement therapy. Nicotine may be delivered via transdermal patch or transdermal delivery from a reservoir of nicotine stored in a wearable device given to the patient. The processor applies the algorithm to the received patient data to determine the most effective intervention. The processor applies the intervention and further adjusts it as needed. The processor sets a target number of events and determines the most effective method to change the patient's smoking behavior. The processor can invoke multiple individualized interventions from the stakeholders as perturbations via machine learning processes and tests that work best to change the patient's smoking behavior. Perturbations that have the most impact on the patient's smoking model may be retained, while perturbations that have less or no impact may not be used further.

[0143] 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 smoking via cigarettes, pipes, cigars, and water pipes, and smoking illicit products such as marijuana, cocaine, heroin, and alcohol-related behavior, it will be readily apparent to one of ordinary skill in the art that the teachings of the present invention are equally applicable to any other undesirable behavior. Other such examples include: oral placement of certain substances, specific examples being placement of chewing tobacco and snuff in the oral cavity, transdermal absorption of certain substances, specific examples including the application of certain creams, ointments, gels, patches or other products to the skin, including the abuse of drugs such as narcotics and LSD, and nasal inhalation of drugs or abused substances (including, but not limited to, snorting cocaine).

[0144] In general, the basic configuration of devices 102 and 104 or device 202, and the associated steps and methods disclosed herein, remain similar between the different operations being addressed. The devices may vary slightly in design to account for different testing methods necessitated by different target substances required for testing or different markers associated with particular undesirable operations.

[0145] It will also be appreciated by those skilled in the art that patients participating in a formal smoking cessation program may utilize the systems and methods disclosed herein as an adjunct to the smoking cessation program, and it will likewise be appreciated that patients may be independently and self-motivated and thus advantageously utilize the systems and methods to unilaterally cease undesirable behaviors outside of a formal smoking cessation program.

[0146] In further exemplary embodiments, the systems and methods disclosed herein may be readily adapted for data collection, particularly for the collection of reliable and verifiable data for studies related to undesirable behaviors that the present invention is well suited to test. Such studies may be accomplished with little modification to the basic devices or methods, except that there is no need to necessarily update test or treatment protocols based on user input if no treatment is involved.

[0147] FIG. 19 illustrates another variation of a system and / or method using some of the embodiments described herein to influence an individual's smoking behavior and further quantify the individual's exposure to tobacco smoke. In the illustrated example, multiple samples of biometric data are obtained from the individual and analyzed to quantify the individual's exposure to tobacco smoke, and the quantified information may be relayed to the individual, a medical caregiver, and / or other parties with a stake in the individual's health. The example discussed below employs a portable device 1900 that obtains multiple exhaled breath samples from the individual using a commonly available sensor that measures the amount of carbon monoxide in the exhaled breath sample (also called exhaled carbon monoxide or ECO). However, the quantification and communication is not limited to exhaled breath-based smoking exposure. As noted above, there are many sampling means for obtaining an individual's smoking exposure. The methods and devices described in this example can be combined or supplemented with such sampling means, where possible, while remaining within the scope of the invention. Also, while this example describes the use of a portable sampling unit, the methods and procedures described herein can be used with dedicated or portable sampling units.

[0148] It is known that measuring CO levels in exhaled breath can serve as an immediate, 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, S. Erhan Devecia, et al., Department of Public Health, Medical Faculty of Firat University, Elazig, Turkey 2003 and Comparison of Tests Used to Distinguish Smokers from Nonsmokers, MJ Jarvis et al. American Journal of Public Health, November 1987, V77, No. 11. These articles explain that exhaled CO ('eCO') levels in non-smokers may range from 3.61 ppm to 5.6 ppm. In one example, the cut-off level of eCO was above 8-10 ppm to identify smokers.

[0149] Returning to FIG. 19, as shown, the portable or personal sampling unit 1900 communicates with either a personal electronic device 110 or a computer 112. Here, the personal electronic device 110 includes, but is not limited to, a smart phone, a regular phone, a mobile phone, or other personal transmitting device designed solely 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. Data transmission 114 from the personal sampling unit 1900 can occur to both or either the personal electronic device 110 and / or the computer 112. Furthermore, synchronization 116 between the personal electronic device 110 and the computer 112 is optional. 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 as described herein. Alternatively, the data analysis can be performed, fully or partially, on a local device (such as a computer or personal electronic device). In either case, the personal electronic device 110 and / or computer 112 can provide information to the individual, a caregiver, or other individuals, as shown in FIG.

[0150] In the embodiment shown in FIG. 19, a personal sampling unit 1900 receives a sample of exhaled breath 108 from an individual via a collection tube 1902. Hardware in the personal sampling unit 1900 includes any commercially available electrochemical gas sensor that detects carbon monoxide (CO) gas in the exhaled breath sample, available transmission hardware that transmits data 114 (e.g., via Bluetooth, cellular, or other radio waves that provide for the transmission of data). The transmitted data and associated measurements and quantifications are displayed on either (or both) the computer display 112 or the personal electronic device 110. Alternatively, or in combination, any information can be selectively displayed on the portable sampling unit 1900.

[0151] The personal sampling unit (or personal respiratory unit) may also use standard ports that allow for direct wired communication with the respective devices 110 and 112. In certain variations, the personal sampling unit 1900 may also include removable or built-in memory storage, such memory allowing for recording of data and separate transmission of data. Alternatively, the personal sampling unit may store and transmit data simultaneously. Further variations of the device 1900 do not require a storage device. Additionally, the unit 1900 may use any number of GPS components, inertial sensors (to track movement), and / or other sensors that provide additional information about the patient's behavior.

[0152] 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 an individual to prepare the device 1900 for delivery of a breath sample 108 or to record other information about the cigarette, such as the amount of cigarette smoked, the strength, etc. Additionally, variations of the personal sampling unit 1900 also associate a timestamp of any input to the device 1900. For example, the personal sampling unit 1900 may associate the time the sample is provided and provide the measured or entered data with the time of the measurement when transmitting the data 114. Alternatively, the personal sampling device 1900 may use alternative means to identify the time the sample is obtained. For example, given a series of samples, rather than recording the timestamp of each sample, the period between each sample in the series may be recorded. Thus, by identifying the timestamp of any one sample, the timestamp of each sample in the series may be determined.

[0153] In certain variations, the personal sampling unit 1900 is designed so that it has a minimal profile and can be easily carried by an individual with minimal effort. Thus, 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 commonly known technologies. For example, as shown, the portable sampling unit 1900 can include a screen 1908 that shows selection information as discussed below. Alternatively or additionally, the feedback can be in the form of a vibration element, an audible element, and a visual element (e.g., one or more colored illumination sources). Any of the feedback components can be configured to provide an alarm to the individual and can act as a reminder to provide a sample or provide feedback related to the measurement of smoking behavior. The feedback component may also provide repeated alerts to remind the individual to provide periodic samples of exhaled breath to extend the period during which the system captures biometric (eCO, CO levels, etc.) and other behavioral data (location manually entered or entered via a GPS component connected to the unit, number of cigarettes smoked, or other triggers, etc.). In some cases, more frequent reminders may be triggered during the initial program or data capture. Once sufficient data is obtained, the reminder frequency may be scaled back.

[0154] FIG. 20A illustrates a visual representation of data that may be collected using a variation of the system shown in FIG. 19. As described above, an individual provides an exhaled breath sample using a portable sampling unit. The individual may recall at regular or random intervals depending on the nature of the treatment or intervention program. Each sample is evaluated by one or more sensors in the portable sampling unit to measure the amount of CO. The CO measurements typically correspond to inflection points 410 on the graph of FIG. 20A. Each CO measurement 410 corresponds to a timestamp as shown in the horizontal axis. The data accumulated via the portable sampling unit allows for the collection of a data set including at least the CO measurement and the time of the sample, which can be graphed to obtain an eCO curve showing the amount of CO attributable to the individual's smoking behavior over a period of time.

[0155] As discussed herein, the individual may further track additional information such as cigarette smoking. The smoking of a cigarette may be associated with its own timestamp, as indicated by bar 414. In one variation of methods and systems according to the present disclosure, the individual may use an input trigger on the portable sampling unit to input the number of cigarettes smoked or a fraction thereof. For example, each actuation of the input trigger may be associated with a fraction of a cigarette (e.g., 1 / 2, 1 / 3, 1 / 4, etc.).

[0156] FIG. 20B shows a portion of a graphical representation of the data collected as described above. However, in this variation, quantification of an individual's smoking behavior can use behavioral data to better approximate CO values ​​between eCO measurements. For example, in some variations, eCO measurements between any two points 410 can be approximated using a linear approximation between the two points. However, it is known that CO levels decay in the bloodstream without exposure to new CO. This decay can be approximated using a standard rate, a rate based on the patient's biometric information (weight, heart rate, activity, etc.). As shown in FIG. 20B, when the patient is between cigarettes 414, the calculated CO level can follow a decay rate 440. Once the individual logs a cigarette 414, the CO increase 442 can be estimated again, either at the standard rate or one calculated using the biometric data described above, or based on the strength, duration, and amount of the cigarette. Thus, the methods and systems described herein can optionally use an improved (or approximated) eCO curve 438 using the behavioral data discussed above. Such improved eCO rate may also be used to determine an improved eCO curve 438 while the individual is asleep. This improved eCO curve can then provide an improved eCO loading as described herein. The biometric information used to determine the decay rate may be measured by a portable sampling device or an external biometric measurement device in communication with the system.

[0157] This estimated or improved eCO curve 438 may be displayed to the individual (or to a third party) as a means of aiding behavior change such that the individual can see real-time estimated CO levels (i.e., percentage decrease when not smoking and percentage increase when smoking). Additional information may also be displayed, for example the system may calculate the CO increase for each cigarette based on the starting CO value.

[0158] FIG. 21 illustrates an example of a data set used to determine an eCO curve 412 over a period of time, where the eCO attributable to an individual's smoking behavior can be quantified over various time intervals to determine an eCO burden or eCO load for each interval. As shown, the time period extends along the horizontal axis and includes historical and ongoing data transmitted and captured by the portable sampling unit. To provide more effective feedback regarding an individual's smoking behavior, the eCO curve 412 during a particular time interval can be quantified. In the illustrated example, the time interval between times 416 and 418 comprises a 24-hour time interval. A subsequent 24-hour interval is defined between times 418 and 420. A time interval or time interval may include any time between two points within the period spanned by the data set. In most cases, a time interval is compared to other time intervals with the same duration (i.e., each interval is comprised of M minutes, H hours, D days, etc.).

[0159] One way to quantify the eCO burden / load over time intervals is to obtain the eCO curve 412 or a defined area under it for a given time interval (e.g., 416 to 418, 418 to 420, etc.) using a dataset such as that shown in the graph of FIG. 21 as follows. In the illustrated example, the eCO burden / load 422 for the first interval (416 to 418) includes 41 (measured in CO ppm*t) and the eCO burden 422 for the second interval (418 to 420) includes 37. As noted above, along with the eCO burden / load 422, the dataset can include the number of cigarettes smoked 414 along with a timestamp for each cigarette. This cigarette data may be summarized 426 for any time interval along with the eCO burden / load 422. In the illustrated example, the eCO burden / load is a daily load, which allows an individual to track their CO exposure. Determining the CO burden is a more accurate reflection of total smoke exposure than simply counting cigarettes because smokers smoke differently. One smoker may smoke an entire cigarette completely, deeply, and intensely, while the other smokes less deeply and intensely. Both may smoke a pack a day, but the former will have a much higher daily CO burden due to the intensity with which the smoke is inhaled. CO burden is also important when an individual becomes a patient in a smoking cessation program. In such cases, quantification allows a caregiver or counselor to follow the patient while they are reducing their smoking activity. For example, a patient may reduce from 20 cigarettes per day to 18 to 16. However, at 10 cigarettes per day, the patient may not yet have a reduced daily CO burden because they are compensating for when they smoked fewer cigarettes (i.e., the patient smoked harder, deeper, and more intensely). A reduction in the patient's smoking exposure will only occur if their CO burden is reduced.

[0160] The data shown in Figure 21 is for illustrative purposes only, and the length of time for a particular data set will depend on the length of time an individual uses a portable sampling unit to obtain biometric and behavioral data. Quantifying exhaled carbon monoxide exposure involves using the data set to correlate a function of exhaled carbon monoxide versus time over a period of time to obtain an area under the eCO curve 412. In variations of the methods and systems, the eCO curve can be calculated or approximated.

[0161] Figure 22 shows an example of displaying biometric data and various other information for the benefit of a user, caregiver, or other party interested in assessing an individual's smoking behavior. The data shown in Figure 22 is for illustrative purposes and may be displayed on a portable electronic device (e.g., see 110 in Figure 19) or one or more computers. Also, any of the biometric data or other data may be displayed on the portable sampling unit 1900.

[0162] 22 shows a "dashboard" view 118 of an individual's smoking behavior data, including a graphical output 120 of the eCO curve 412 over a period of time, as well as the number of cigarettes smoked for any given time interval within that period. The graphical output 120 may also provide a measured or calculated nicotine trend 424. This nicotine trend 424 may be determined from the number of cigarettes smoked 426, rather than a direct measurement of nicotine.

[0163] 22 also shows a second graphical output display 122 of the eCO curve 412 over an alternative time period. In this example, the first graphical display 120 shows the eCO curve 412 over a seven day period, and the second display 122 shows data over a three day period. The dashboard view 118 may also include additional information including the latest eCO burden / load 124 (or latest eCO reading from latest sample), number of cigarettes 126 over a defined period such as the current day, along with the amount of nicotine 128. The dashboard 118 may also include a count of the number of samples 130 provided by the individual over a defined period (such as daily to monthly counts).

[0164] The dashboard 118 can also display information that can assist an individual in reducing or quitting smoking. For example, FIG. 22 also shows the cost of cigarettes 132 using a count of the portions of cigarettes smoked by the individual 126 or 426. The dashboard can also display social connections 146, 142, 140 to assist with smoking cessation. For example, the dashboard can display health care providers or counselors 140 that can be directly messaged. Information can also be displayed to social acquaintances 142 who are also attempting to reduce their own smoking behavior.

[0165] The dashboard 118 may also display information regarding smoking triggers 134, as described above, as a reminder for 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 that the individual previously completed with his / her medical practitioner or counselor.

[0166] The dashboard 118 can also selectively display any of the information discussed herein based on an analysis of the individual. For example, it may be possible to characterize an individual's smoking behavior and associate such behavior with specific measures that are effective in helping the individual reduce or quit smoking. In these cases, the individual's behavior can be classified into one or more phenotypes (where the individual's observable characteristics can be classified within one or more groups). The dashboard can display information that has been found to be effective for that particular phenotype. Additionally, the information on the dashboard can be selectively adjusted by the user, allowing for customization that the individual perceives as effective as a motivator for quitting smoking.

[0167] FIG. 23 shows another variation of the dashboard 118 that displays similar information to that shown in FIG. 22. As mentioned above, the information displayed can be customized. For example, this variation shows eCO load 140 in a graphical display showing historical data (yesterday's load), current eCO burden or load, as well as goal levels for non-smokers. As shown in FIGS. 22 and 23, individual previous attempts 138 at quitting smoking can be displayed. Also, the graphical representation 120 of eCO trends 412 can be illustrated with individual eCO readings (for each sample), which can be displayed along with information about smoking time 426, along with a graphic showing smoking time or duration (as shown by circles of various diameters). As mentioned above, such information can be entered with a portable sampling unit and displayed in additional formats, as shown at 126 and 127, which show historical and current data on number of cigarettes smoked and total number of cigarettes smoked, respectively.

[0168] 24A-24C show other variations of data sets including carbon monoxide breath, collection time, and cigarette data quantified and displayed to benefit individuals seeking to understand smoking behavior. FIG. 24A shows an example where a patient collected breath samples over several days. The example data shown in FIGS. 24A-24C shows data displayed over a 21 day period, although any time range is within the scope of the systems and methods described herein.

[0169] As shown in Figure 24A, a time period 432 is shown along the horizontal axis, with the time intervals being for each day within the period. Although not shown, in the early stages of sample collection, the period itself may consist of one or more days, with the time intervals being a matter of hours or minutes. Obviously, the longer the period, the greater the ability of the program to select meaningful time intervals within that period.

[0170] FIG. 24A shows a variation of the dashboard 118 in which smoking data (including total number of cigarettes 428 and associated curve 430) is overlaid on a graph showing the eCO curve 412. As described above, an individual provides a breath sample periodically or randomly. In a particular variation, a portable sampling unit (not shown) prompts the individual to provide a sample for measuring CO. The portable sampling unit can be used to associate the sample with a timestamp and transmit other user-generated data as described above. The CO data is then quantified to provide a value for CO exposure (eCO for exhaled CO) over a time interval (e.g., per day as shown in FIG. 24A).

[0171] 24A also illustrates the ability to show historical data alongside current data. For example, CO load data 140 shows the CO load from the previous day, as well as the highest, lowest, and average CO readings. A similar history is shown for tobacco data and smoking cessation questionnaire results 136.

[0172] 24B and 24C show the dataset in graphical form as the individual reduces his / her smoking behavior. As the individual continues to provide samples for measurement of CO, as shown in FIG. 24C, the graphical representation of the dataset shows the individual's self-report of smoking fewer cigarettes, which is confirmed through a decrease in the value of CO load 124.

[0173] The systems and methods described herein, i.e., the quantification and display of smoking behavior and other behavioral data, provide a foundation that health care professionals can leverage for effective programs designed to reduce the effects of tobacco smoke. For example, the systems and methods described herein can be used to simply identify a population of smokers from among the general population. Once this population is identified, the construction of a data set on an individual's specific smoking behavior can be performed prior to attempting to enroll the individual in a smoking cessation program. As described above, the quantification of smoking burden (or CO burden) and time data of smoking activity can be combined with other behavioral data to identify smoking triggers specific to the individual. Thus, an individual's smoking behavior can be fully understood by a health care professional prior to selecting a smoking cessation program. Furthermore, the systems and methods described herein can be easily adapted to monitor an individual's behavior once they enter a smoking cessation program and monitor the individual once they have stopped smoking to ensure that the smoking cessation program remains effective and that the individual abstains from smoking.

[0174] Additionally, the above-described systems and methods for quantifying smoking behavior can be used to build, update, and improve models of the above-described smoking behavior and provide perturbations to ultimately reduce an individual's smoking behavior.

[0175] 25A-25H show other variations of the above systems and methods used to implement a treatment plan for identifying an individual's smoking behavior to ultimately help the individual quit smoking and maintain the individual's status as a non-smoker.

[0176] For example, FIG. 25A shows an overview of an exemplary overview incorporating teachings found herein to provide a multi-phase regime / program 440 intended to ultimately assist an individual in reducing and / or quitting smoking behavior. As shown, each phase 442, 444, 446, 448, 450, 452 of the 440 program may be associated with a display 438. The illustrated display 438 represents a portable device (e.g., smartphone, tablet, computer), but the display may include any display or dedicated electronic device capable of receiving and / or interacting with the user interface and themes provided by the program. The themes provided by the program may be smoking-related themes intended to inform the individual about the effects of smoking and / or may be themes based on smoking behavior. Additionally, the themes may change based on the tracked behavior of the individual, or the themes may change based on other factors not related to the tracked behavior of the individual.

[0177] Smoking-related subject matter may also include information and / or warnings regarding the proper use of devices and systems used to edit smoking behavior. For example, warnings may include warnings against using the device / system in these cases, including, but not limited to, measurements of possible carbon monoxide poisoning, measurements of non-tobacco smoke inhalation (e.g., from a fire or chemical release). In some cases, the system may instruct the individual to call emergency medical services (e.g., 911) if non-tobacco CO exposure occurs. The system may also provide system-specific warnings, such as warnings against sharing breath sensors between different individuals.

[0178] Additionally, the subject matter communicated to the individual may include a general note that the amount of smoking behavior is not safe. Such a warning is intended to prevent the individual from using the system to attempt to reduce or maintain their smoking behavior at a relative level that they may mistakenly perceive as a safe level of smoking. For example, such a warning may be triggered at a specific level of exhaled CO, e.g., 0-6 ppm. The warning may state that low levels of CO in exhaled breath are not an indication that it is safe to start or increase smoking, or that the current level is safe. The warning may further state that smoking is harmful to a person's health and that smoking any amount is dangerous.

[0179] In the illustrated example, phases 442, 444, 446, 448, 450, 452 of the program 440 can be divided into separate periods or time periods, with each phase providing a different goal that allows the individual to build and progress in an attempt to moderate their smoking behavior. For example, in the example method / system, the initial phase 442 allows the user to explore smoking behavior with little or no attempt to force an immediate change in smoking behavior. Such an exploration phase 442 provides the individual with information that allows the individual to identify their smoking behavior. In the illustrated example shown in FIG. 25A, the program phases are divided into example time periods as follows: exploration 442 (9 days), building 444 (1 day to 4 weeks), mobilization 446 (1 week), termination 448 (1 week), consolidation 450 (11 weeks), sustain 552 (40 weeks). Obviously, a variation in time period can be associated with each phase.

[0180] Exploration 442 can be used to prompt action regarding smoking behavior and stimulate the individual's interest in quitting. Construction 444 can be used to build skills that prompt the individual to decide to quit. Mobilization 446 can be used to prepare the individual to quit. Termination 448 can be used to assist the individual in quitting. For example, this phase can be used to provide support to the individual during smoking cessation, where support can include facilitating interactive communication with a counselor, facilitating interactive communication of peer support, displaying themes of information that support smoking cessation, or a combination of these. Retention 450 can be used to provide the individual with skills to continue quitting. Sustain 452 can be used to provide support to the individual to prevent relapse and solidify smoking cessation behavior.

[0181] For example, as described above, such a first phase 442 may include recording a plurality of behavioral data from the individual, such behavioral data may include the number of cigarettes smoked, the time the cigarettes were smoked, the individual's location, the individual's location while smoking, mood, and other data indicative of the individual's behavior. In conjunction with the behavioral data, the method may enable the individual to submit a plurality of biological data from the individual. For example, the biological data may include a breath sample submitted to the electronic device described above. Alternatively, or in combination, the submission of biological data may be passive through any number of sensors that actively measure the individual's biological information (e.g., via blood, breath, temperature, etc.).

[0182] The biological information is then quantified to allow the individual to understand the effects of their smoke exposure. As noted above, where the biological data includes exhaled carbon monoxide, quantification of smoke exposure may include exhaled carbon monoxide load.

[0183] The method then includes compiling a behavioral summary combining at least a portion of the behavioral data and the smoking exposure. FIG. 25B shows an example display of a behavioral summary showing the smoking exposure breath CO load 124, as well as several behavioral data including, but not limited to, number of cigarettes smoked, estimated smoking cost, and time since last cigarette. The visual display can also provide various menu options 462 to allow the individual to interact between various subject items related to smoking behavior and counselors. The display 438 can also allow the individual to view a behavioral summary based on daily values ​​or over a set period of time (e.g., 7 days, 30 days, complete history, etc.).

[0184] The system may also evaluate the submitted data (either biological and / or behavioral) to ensure accuracy of the data. For example, the system may evaluate the time period between submitted samples and issue a warning if samples are submitted at undesirable intervals. For example, the system may provide a warning to the individual if obtaining multiple biological data from an individual occurs within a predetermined time of the previous submission of biological data. In some cases, particularly for biological data, submitting samples without allowing sufficient time between samples may reduce the validity of the measurement. In additional variations, the warning to the individual may further include rejecting at least one of the multiple biological data from the individual in addition to providing a warning. Such warnings may be provided visually, audibly, sensorily, and / or through visual indications of the subject matter discussed herein.

[0185] 25C shows an additional example of an example behavioral summary that includes behavioral data 460 in conjunction with biological data 124. In this example, the user can select between displaying the biological data (e.g., breath carbon monoxide load) and the number of cigarettes smoked. The display 438 also allows the user to interact with the data by selecting specific information, such as a smoking map that shows the behavioral data in the form of smoking locations 464. This disclosure includes any number of variations of displaying all or at least a portion of the behavioral summary to an individual to inform the individual about their smoking behavior.

[0186] FIG. 25D illustrates another embodiment of the method disclosed herein that uses one or more interactive activities to engage the individual during the program. In this variation, the interactive activities can be spread over the first phase of the program. For example, the first phase of the program can include any time period, but in the illustrated variation, the first phase is divided into nine days, with each day having markers 468, 470, 474 representing the activities for that day. The markers can be interactive, i.e., the individual can access the activities, or the markers can be turned on to provide information to the user. Regardless, the activities can provide the individual with a theme regarding smoking behavior. For example, as shown in FIG. 25D, the first activity 468 can remind or induce the individual to begin submitting biological and / or behavioral data as described above, and the method can generate a theme incorporating any of the data that provides feedback to the user. In FIG. 25D, a first activity 468 may provide thematic feedback to the user regarding the need for a biological sample (e.g., a breath sample) and provide information related to the current count, minimum number of samples required, etc., related to the biological or behavioral sample or countdown until the minimum number of samples is reached.

[0187] FIG. 25D also shows additional markers 468, 474 representing additional activities and / or days of the first phase of the program. As shown in FIG. 25D, the subject 472 may be purely informational, such as providing information on how measured CO is a useful indicator of an individual's exposure to toxins in cigarettes. In other variations, the subject may include interactive activities, as shown in FIG. 25E. For example, as shown in FIG. 25E, the center screen image may prompt the individual for costs associated with cigarettes or smoking, and calculate the information as shown. The activity may then combine the prompted information to provide additional information indicative of the individual's smoking behavior 478, as shown in the right screen. For example, in this example, the information includes the estimated cost of smoking, reasons for smoking, and estimated savings upon quitting. The interactive activity may also provide rewards 480 to the individual for providing biological and / or behavioral data.

[0188] 25F shows additional markers 482, 486, 488, 490, and 496 representing subjects such as reasons for smoking 482, extras 486, home 488, time (smoking) 490, and credit 496. As shown, the subject matter displayed can be purely informational (e.g., displaying reasons for smoking 484) or can be combined with data entered during the program (e.g., displaying the amount of time spent smoking per week 492).

[0189] Figure 25G shows another activity (related to activity 6 488 in Figure 25F) in which interactive data prompted by the program relates to environmental factors related to the individual (e.g., household information), as shown in the center screen. Once the individual enters the environmental information, the program can combine the prompted environmental information and use the environmental data to provide additional information indicative of the individual's smoking behavior 478, as shown in the right screen.

[0190] FIG. 25H represents activity or day 7 by 9 490, 496, 498. As the first phase of the program draws to a close, the individual is asked for their confidence in their ability to quit smoking 494, which may be influenced if the program has provided the individual with the above metrics regarding their smoking behavior. Upon completion of the first program phase, as indicated by the completion marker 498, the individual will have a personalized smoking behavior profile compiled with metrics specific to that individual. Interactive activities may then prompt the individual to enter the next stage of the program (as outlined in FIG. 25A).

[0191] Several embodiments of the invention are described. However, it will be understood that various modifications can be made without departing from the spirit and scope of the invention. Combinations of aspects of the above-described variations, and combinations of the variations themselves, are contemplated to be within the scope of the disclosure.

[0192] Various modifications may be made to the invention as described, and equivalents (whether described herein or not included for purposes of brevity) may be substituted without departing from the true spirit and scope of the invention. Also, any feature of the variations of the invention may be presented and claimed either individually or in combination with any one or more of the features described herein. Thus, the invention contemplates combinations of various aspects of the embodiments or combinations of the embodiments themselves, where possible. Reference to a single item includes the possibility of there being multiple of the same item. More specifically, as used in this specification and the appended claims, the singular forms "a," "an," "said," and "the" include plural references unless the context clearly dictates otherwise.

Claims

1. 1. A method for identifying smoking behavior of an individual, comprising: recording a plurality of non-biological behavioral data provided by said individual; obtaining a plurality of biological data from the individual, the biological data being one or more of a carbon monoxide level of the individual, or an exhaled carbon monoxide level of the individual; evaluating the submitted biological and / or behavioral data to ensure accuracy of the data by evaluating the time period between submitted samples and providing a warning if the sample is submitted within a predetermined time from a previous submission; quantifying smoking exposure of the individual using the plurality of biological data; compiling a behavioral summary including data on the plurality of behaviors and at least one association with the smoking exposure; allowing the individual to view data in the behavioral summary and providing at least a portion of the behavioral summary to a user interface configured to inform the individual about how the individual's behavior affects their smoking behavior and to display at least one of the plurality of behavioral data related to the smoking exposure.

2. 2. The method of claim 1, wherein the step of providing an alert if the sample is submitted within a predetermined time from a previous submission includes rejecting at least one of the plurality of biological data from the individual in addition to providing the alert.

3. 2. The method of claim 1, wherein visually displaying at least the portion of the behavioral summary comprises displaying trends in the plurality of behavioral data or trends in the smoking exposure.

4. 2. The method of claim 1, wherein obtaining the plurality of behavioral data from the individual includes tracking a number of cigarettes smoked by the individual.

5. 10. The method of claim 1, wherein obtaining the plurality of behavioral data from the individual further comprises obtaining a geographic location of the individual during a smoking event.

6. 2. The method of claim 1, wherein compiling the behavioral summary includes timing the time between puffs of a cigarette.

7. 2. The method of claim 1, wherein compiling the behavior summary includes estimating the cost of cigarettes smoked.

8. 10. The method of claim 1, wherein visually displaying at least a portion of the behavioral summary comprises displaying intermediate results of a plurality of biological data.

9. 10. The method of claim 1 further comprising the step of graphically displaying the smoking-related subject of the information.

10. 10. The method of claim 9, wherein the step of displaying the smoking-related subject matter of the information occurs during a first program phase.

11. 11. The method of claim 10, wherein the step of displaying said information related to smoking is repeated daily during said first program phase.

12. 10. The method of claim 1, further comprising facilitating interactive communication between a counselor and the individual.

13. 13. The method of claim 12, wherein the counselor is provided with access to the behavior summary.

14. 10. The method of claim 1, further comprising providing an interactive activity to engage the individual.

15. 15. The method of claim 14, wherein providing the interactive activity comprises obtaining a plurality of responses to a plurality of solicitations related to the individual's smoking behavior.

16. 16. The method of claim 15, further comprising the steps of editing the personal story and displaying the personal story, the personal story including the plurality of responses associated with the plurality of behavioral data.

17. The step of acquiring a plurality of biological data includes: 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 the plurality of samples of exhaled breath; measuring an amount of exhaled carbon monoxide for each sample of the plurality of samples of exhaled breath; compiling a data set including the amount of exhaled carbon monoxide and the collection time of each sample of the plurality of samples of the exhaled breath; and quantifying the individual's smoking exposure comprises: quantitating exhaled carbon monoxide exposure over time intervals within said period and assigning exhaled carbon monoxide burdens to said time intervals using said data set; providing at least a portion of the activity summary comprises:

2. The method of claim 1, further comprising displaying the exhaled carbon monoxide load.

18. 20. The method of claim 17, wherein obtaining the multiple samples of breath from the individual over the period of time and recording the collection time of each sample of breath comprises obtaining the multiple samples of breath consecutively.

19. 20. The method of claim 17, wherein quantifying the exposure to exhaled carbon monoxide comprises correlating a function of exhaled carbon monoxide with time.

20. 20. The method of claim 19, further comprising obtaining the area of ​​exhaled carbon monoxide and the time under the curve partitioned by said function over said interval of time.

21. 20. The method of claim 17, further comprising the step of generating a signal to the individual and providing at least one sample of exhaled breath.

22. 20. The method of claim 17, further comprising the step of repeatedly alerting the individual to provide breath samples over the period of time.

23. 20. The method of claim 17, further comprising the steps of receiving input data from the individual and recording a time of the input data.

24. 24. The method of claim 23, wherein the input data includes behavioral information of the individual.

25. 20. The method of claim 17, wherein measuring the amount of exhaled carbon monoxide includes using a portable sensor.

26. 1. A method for identifying smoking behavior of an individual, comprising: recording a plurality of non-biological behavioral data provided by said individual; obtaining a plurality of biological data from the individual, the biological data being one or more of a carbon monoxide level of the individual, or a single breath carbon monoxide level of the individual; evaluating the submitted biological and / or behavioral data to ensure accuracy of the data by evaluating the time period between submitted samples and providing a warning if the sample is submitted within a predetermined time from a previous submission; quantifying smoking exposure of the individual using the plurality of biological data; generating a behavioral profile by correlating the non-biological behavioral data provided by the individual with the smoking exposure; providing at least a portion of the behavioral summary to a user interface configured to allow the individual to access data in the behavioral summary and to inform the individual of how the individual's behavior affects the smoking behavior, and to display at least one of the plurality of behavioral data related to the smoking exposure.

27. 27. The method of claim 26, wherein the step of providing an alert if the sample is submitted within a predetermined time from a previous submission includes rejecting at least one of the plurality of biological data from the individual in addition to providing the alert.

Images