Methods and systems for evaluating and improving the state of mental well-being of a subject

Abstract

Computer systems and methods for providing mental well-being support to a subject are disclosed. The systems and methods involve receiving data associated with the subject, such as biological data, behavioural data, environmental data, and survey data, the survey data collected through at least one questionnaire. The systems and methods process the data associated with the subject to predict a state of mental well-being of the subject and optionally provide at least one recommendation to improve the predicted state of mental well-being of the subject. Data associated with the subject may be collected in real time, allowing real-time predictions of the state of mental well-being of the subject. The disclosed systems and methods may enable a subject to proactively make positive life changes to improve mental well-being. Moreover, health care professionals may use the data and insights collected by the methods and systems disclosed herein to provide personalized medical treatment plans.

Description

METHODS AND SYSTEMS FOR EVALUATING AND IMPROVING THE STATE OF MENTAL WELL-BEING OF A SUBJECTTECHNICAL FIELD

[0001] The present disclosure relates to mental well-being technology, and in particular, to systems and methods for predicting the state of mental well-being of a subject and offering recommendations to improve the predicted state of mental well-being of the subject.BACKGROUND

[0002] Traditional approaches to medical treatment involve diagnosing a condition and providing a standard treatment plan. More recently, there has been greater focus on personalized medicine, which aims to provide the most effective medical treatment to an individual based on the unique circumstances of the individual. For example, using a personalized medicine approach, a health care professional may prescribe a certain type of medication to treat a condition depending on an individual’s lifestyle habits and genetic makeup.

[0003] Personalized medicine may also provide a better approach to treating mental health conditions. However, due to the dynamic nature of symptoms relating to mental health issues it can be difficult to develop a personalized mental health treatment plan. For example, an individual suffering from mental health issues may experience a wide range of mental health symptoms (e.g., feelings and / or mood swings) throughout a week. However, that individual may only briefly meet with a mental health care professional once a week. During the meeting, the individual may have difficulty recollecting the symptoms they experienced throughout the week making it difficult for the mental health care professional to recommend a personalized approach to treating the mental health condition.

[0004] Mental health is often referred to as being on a continuum. Even those who do not suffer from a mental health condition may be interested in improving their mental wellbeing. However, with many different possible causes of mental distress, and further, withmany individuals leading a busy life, it is often difficult for an individual to identify their state of mental health at any given moment, the cause of that state, and what the individual can do to improve their mental health state.

[0005] There is therefore a need for a convenient means to monitor the mental health state of an individual to enable personalized strategies to improve mental well-being.SUMMARY

[0006] According to one aspect of the present invention, there is provided a computer- implemented method for predicting a state of mental well-being of a subject, the method comprising: receiving survey data associated with the subject, the survey data collected through at least one questionnaire; receiving biological data associated with the subject; receiving behavioural data associated with the subject; processing the survey data, the biological data, and the behavioural data to predict the state of mental well-being of the subject; providing an output of predicted state of mental well-being of the subject; and providing at least one recommendation to improve the predicted state of mental well-being of the subject.

[0007] According to one aspect of the present invention, there is provided a computer- implemented method predicting a state of mental well-being of a subject, the method comprising the step of receiving data associated with the subject, the data comprising a plurality of data values comprising: a plurality of biological data values, a plurality of behavioural data values, and a plurality of survey data values collected through at least one questionnaire. The method further comprises the step of processing the data associated with the subject to predict the state of mental well-being of the subject, the processing comprising: assigning a respective weight to each of the plurality of data values; adjusting the respective weight of at least one of the plurality of data values as a function of time; calculating a mental well-being score of the subject as a function of the respective weight of at least one of the plurality of data values; and predicting the state of mental well-being of the subject as a function of the mental well-being score of the subject. The method further comprises the step of providing an output of the predicted state of mental well-being of the subject.

[0008] According to another aspect of the present invention, there is provided a computer system comprising: one or more processors; and memory operatively coupled to the one or more processors and storing processor-executable instructions thereon that, when executed, cause the one or more processors to implement the computer-implement methods disclosed herein.

[0009] According to another aspect of the present invention, there is provided a computer system for providing mental well-being support to a subject, the system comprising: a database for storing data associated with the subject, the data comprising: biological data, behavioural data, and survey data, the survey data collected through at least one questionnaire; at least one processor; memory operatively coupled to the one or more processors and storing processor-executable instructions thereon that, when executed, cause the one or more processors to processes the data associated with the subject to predict a state of mental well-being of the subject; and an interface for receiving the data associated with the subject and for outputting the predicted state of mental well-being of the subject.

[0010] A potential advantage of the present invention is that it may enable a subject to proactively respond to their predicted state of mental well-being, which may improve the state of mental well-being of the subject.

[0011] Y et another potential advantage of the present invention is that it may provide a comprehensive collection of data, which can be probed to identify causes of symptoms of mental health conditions, which, in turn, can be used by a mental health professional to develop a personalized mental health treatment plan.BRIEF DESCRIPTION OF THE FIGURES

[0012] Further advantages, permutations, and combinations of the invention will become apparent from the following detailed description of the various illustrative embodiments of the invention taken together with the accompanying drawings, each of which are intended to be non-limiting, in which:

[0013] FIG. 1 is a flowchart illustrating an exemplary method for predicting a state of mental well-being of a subject.

[0014] FIG. 2 is a functional block diagram of an exemplary computer system according to some embodiments of the present disclosure.

[0015] FIG. 3 is a flowchart illustrating a process of providing mental well-being support according to some embodiments of the present disclosure.

[0016] FIG. 4 is a flowchart illustrating a method of processing data associated with a subject for predicting a state of mental well-being of the subject, according to some embodiments of the present disclosure.DETAILED DESCRIPTION

[0017] Reference will now be made in detail to exemplary embodiments of the disclosure, wherein numerals refer to like components, examples of which are illustrated in the accompanying drawings that further show exemplary embodiments, without limitation.

[0018] FIG 1 shows a flowchart illustrating an exemplary method for predicting a state of mental well-being of a subject. At a high level, the method shown in FIG 1 is a computer implemented method 100 comprising the steps of: receiving data associated with a subject 110, processing the data associated with a subject to predict the state of mental wellbeing of the subject 120, providing an output of the predicted state of mental well-being of the subject 130, and providing at least one recommendation to improve the predicted state of mental well-being of the subject 140.

[0019] In embodiments, the computer implemented method 100 of FIG 1 may be performed by the exemplary computer system of FIG 2. For convenience, both FIG 1 and FIG 2 will be described together.

[0020] FIG 2 shows a functional block diagram of an exemplary computer system according to some embodiments of the present disclosure. As shown in FIG 2, data 20 associated with a subject (i.e. a human individual) is received by a computer system 10.

[0021] In embodiments, the data 20 associated with the subject comprises one or more of: survey data 21, biological data 22, behavioural data 23, and environmental data 24. In embodiments, an interface 12 of the computer system 10 receives the data 20 associated withthe subject. For example, in embodiments, the interface 12 is a combination of hardware and software components that enable the subject to interact with the computer system 10. In embodiments, the interface 12 also enables communication between the computer system 10 and at least one device worn by the subject, the at least one device for collecting data 20 associated with the subject. In embodiments, the interface allows the subject, and optionally other individuals, such as, health care professionals, to access the computer system 10 via a mobile application, web application, or combination thereof.

[0022] As shown in FIG 2, the computer system 10 further comprises a database 14, memory 16, and one or more processors 18. In embodiments, database 14 stores data 20 associated with the subject. A skilled person will understand that the computer system 10 may be designed in a wide range of options. In embodiments, the hardware components of the computer system 10 may be stored in different locations. For example, in embodiments, database 14 may be a cloud database comprising hard drives in multiple different warehouses.

[0023] In embodiments, memory 16 is operatively coupled to the one or more processors 18 and stores instructions executable by one or more processors 18 that, when executed, cause the one or more processors 18 to processes the data 20 associated with the subject to produce an output 30. For example, in embodiments, output 30 may be a predicted state of mental well-being of the subject.

[0024] In embodiments, the output 30 may comprise electronic signals that may be interpreted by an electronic device (e.g., smart phone, laptop, computer, or the like) and displayed to the subject as images, words, sounds, etc. that communicate to the subject the predicted state of mental well-being of the subject and any other data processed by the computer system 10.

[0025] To further understand the methods and systems disclosed herein, the data 20 associated with the subject (in particular, the survey data 21, biological data 22, behavioural data 23, and environmental data 24) will now be described.

[0026] In embodiments of the systems and methods disclosed herein, survey data 21 is collected through at least one questionnaire. The at least one questionnaire may ask open-ended questions, requiring a brief explanation. In other words, the survey data 21 may comprise qualitative (non-numerical) data. Additionally, or in the alternative, the at least one questionnaire may ask the subject to rank the intensity of their feelings (e.g., feelings of anger) on a scale of one to ten. In other words, the survey data 21 may comprise quantitative data.

[0027] In embodiments, the at least one questionnaire comprises questions with an optional range of pre-determined responses, for example, ranging from “Not at all” to “Almost constantly”. In embodiments, the pre-determined responses may comprise a set of emoticons, each emoticon showing a pictorial representation of facial expressions ranging from sad, angry, happy, indifferent, etc. The severity and frequency of symptoms experienced by a subject may be gleaned depending on which pre-determined response is selected by the subject to answer a given question. In embodiments, the subject’s answer may be converted to a numerical value to enable the system and methods disclosed herein to perform downstream calculations.

[0028] In embodiments, the subject may fill out at least one questionnaire comprising questions for probing at least one of: depressive disorder, generalized anxiety disorder, panic disorder, obsessive-compulsive disorder, and specific phobias. In embodiments, the at least one questionnaire comprises questions to identify potential mental health red flags and / or to identify mental health conditions. For example, red flags may be raised for responses indicating a high level of risk (e.g., suicidal risk or risk of violence towards other) or significant impairment in daily functioning.

[0029] In embodiments, the at least one questionnaire comprises questions to investigate whether the subject has depressive disorder. For example, questions may probe whether the subject experiences symptom of depression, such as: frequent feelings of sadness, sleep disturbances, loss of interest or pleasure, appetite changes, and / or fatigue or difficulty initiating tasks. In embodiments, red flags may be triggered depending on the severity and frequency of one or more of the symptoms of depression experienced by the subject.

[0030] In embodiments, the at least one questionnaire comprises questions to investigate whether the subject has generalized anxiety disorder. For example, questions mayprobe whether the subject experiences: symptoms of anxiety, such as, excessive worrying, physical symptoms during anxious episodes, avoidance behaviour, sleep disturbances, and / or an inability to carry out daily activities. In embodiments, red flags may be triggered depending on the severity and frequency of one or more of the symptoms of anxiety experienced by the subject.

[0031] In embodiments, the at least one questionnaire comprises questions to investigate whether the subject has panic disorder. For example, questions may probe whether the subject experiences: panic attacks (including the frequency, duration, triggers of panic attacks), physical symptoms during panic attacks, fear of future attacks, and / or avoidance behaviour (e.g., anti-social behaviour). In embodiments, red flags may be triggered depending on the frequency and intensity of the experienced panic attacks and associated symptoms.

[0032] In embodiments, the at least one questionnaire comprises questions to investigate whether the subject has obsessive-compulsive disorder. For example, questions may probe whether the subject experiences: obsessive thoughts, compulsive behaviours, behaviours impacting the subject’s daily life, and / or difficulty resisting urges, and whether the subject is aware of their irrational thoughts and / or behaviour. In embodiments, red flags may be triggered depending on the persistence and intrusiveness of obsessive thoughts, frequency of engaging in compulsive behaviours, difficulty in resisting compulsive urges, lack of insight into irrational thoughts, and / or whether the subject’s thoughts and / or behaviour significantly interferes with daily activities.

[0033] In embodiments, the at least one questionnaire comprises questions to investigate whether the subject has specific phobias. For example, questions may identify potential phobia triggers and probe whether the subject experiences avoidance patterns and / or physical responses during exposure to phobia triggers (including the duration of the response and the functional impact of the phobia response on daily activities and social interactions). In embodiments, red flags may be triggered depending on the intensity, frequency, and duration of phobia responses.

[0034] In embodiments, the at least one questionnaire asks the subject to provide a rating of their level of stress on a scale of one to ten, for example: one (minimal stress), two tofour (low stress), five to seven (moderate stress), and eight to ten (high stress). The at least one questionnaire may ask about stress experienced by a subject in the day in which the questionnaire is administered, the previous week (on average), the previous month (on average), or any other period of time. Survey data 21 may therefore provide insights into the stress experienced by a subject and may be cross referenced for accuracy with biological stress markers.

[0035] In embodiments, the at least one questionnaire asks the subject to provide a rating of their physical activity level, ranging from, for example: sedentary (little to no exercise), lightly active (light exercise or engaging in sports one to three days per week), moderately active (moderate exercise or engaging in sports three to five days per week), or very active (hard exercise or engaging in sports six to seven days per week).

[0036] In embodiments, the at least one questionnaire asks the subject to provide information about their dietary habits (e.g., omnivorous, vegan, vegetarian, gluten-free, dairy- free, mostly home cooked meals, etc.). Dietary information gleaned from survey data 21 may be helpful in evaluating state of mental health of a subject. In embodiments, the methods and systems disclosed herein provide recommendations to the subject to change their dietary habits to improve their state of mental health.

[0037] In embodiments, the at least one questionnaire asks the subject to provide information about their social support structure, for example, raging from: a strong support network of friends and family, a limited support network, seeking support groups or communities, or mostly solitary. In embodiments, the methods and systems disclosed herein provide recommendations to the subject to change their social support structure to improve their state of mental health.

[0038] In embodiments, the at least one questionnaire asks the subject to provide information about their current emotional state, for example, ranging from: flourishing (overflowing with positivity and energy for the day), content (feeling at ease and satisfied with life), neutral (neither particularly good nor bad, just steady moving), disheartened (experiencing a sense of sadness or discouragement), or overwhelmed (feeling deeply stressed or emotionally burdened). In embodiments, each questionnaire answer may be associate witha weight. For example, in the just mentioned emotional state responses, ‘flourishing’ may be assigned two points, ‘content’ may be assigned one point, ‘neutral’ may be assigned zero points, ‘disheartened’ may be assigned negative one point, and ‘overwhelmed’ may be assigned negative two points. Scoring survey responses (assigning value to answers) may be conducted for any type of questionnaire, not just questionnaires inquiring about the subject’s emotional state.

[0039] In embodiments, the at least one questionnaire asks the subject to provide information about their current mood and each response may be associated with a weight, for example, responses and weights may be: calm and content (one point), tressed or anxious (minus two points), happy and optimistic (two points), sad or low (minus one point), irritable or frustrated (zero points).

[0040] In embodiments, the at least one questionnaire asks the subject to provide information about any stress triggers the subject may be experiencing, for example: workplace stressors (conflicts and disagreements with coworkers, tough deadlines, excessive working hours, and job insecurity), financial stress (debt, bills, financial instability, or unexpected expenses), relationship strain (arguments, conflicts, or dissatisfaction with family members, friends, or romantic partners), health concerns (physical illness, chronic pain, or mental health issues affecting the subject’s daily life), academic pressure (exams, assignments, academic performance, and pressure to excel in studies), environmental stressors (noise pollution, overcrowding, pollution, or uncomfortable living conditions), personal responsibilities (balancing multiple roles such as caregiving, household chores, and personal obligations), social stress (feeling left out, loneliness, social anxiety, or pressure to conform to societal norms). Each stressor selected may be associate with a negative one-point weight, for example.

[0041] In embodiments, the at least one questionnaire asks the subject to provide information about any coping mechanisms the subject may use to cope with stress, for example: avoidance or distraction (deliberately or unconsciously ignoring or avoiding stressors rather than confronting them directly), substance abuse (using drugs or alcohol in attempt to distract from stress or negative emotions that arise), overeating or undereating(using food to cope with stress and emotions, possibly leading to further unhealthy eating habits or unintended weight gain / loss), procrastination (delaying tasks or responsibilities instead of addressing them promptly) self- isolation (withdrawing from social interactions and support networks when feeling stressed or overwhelmed), excessive screen time (escaping stress by spending excessive amounts of time on electronic devices, such as smartphones or computers), self-harm (engaging in self-injurious behaviors as a maladaptive coping mechanism for dealing with emotional pain), and / or negative self-talk (engaging in critical or self-deprecating thoughts that worsen stress and diminish self-esteem over time). The coping mechanisms in this example are unhealthy ways of dealing with stress which may be associate with a negative one -point weight, for example. The subject may select one or more coping mechanisms. If the ‘self- harm’ coping mechanism is selected, the systems and methods disclosed herein may detect a red flag and contact a mental health professional or emergency health service.

[0042] The subject may also select one or more healthy coping mechanisms which may be associate with a positive weight. For example, each of the following stress coping responses may be associated with a one-point weight: physical exercise (engaging in activities such as walking, jogging, yoga, or sports to release tension and boost mood), deep breathing techniques (practicing deep breathing exercises to calm the mind and reduce stress levels), mindfulness and meditation (incorporating mindfulness practices or meditation to increase self-awareness and cultivate inner peace), social support (seeking support from friends, family, or support groups to share feelings and gain perspective), time management (organizing tasks, prioritizing responsibilities, and setting realistic goals to manage stress effectively), relaxation techniques (using relaxation techniques such as listening to music, taking a warm bath, or indulging in hobbies to unwind), positive affirmations (repeating positive affirmations to challenge negative thoughts and promote self-esteem), and seeking help (consulting with family, friends, counselors, or support groups for guidance and support).

[0043] In embodiments, the at least one questionnaire asks the subject to rate the quality of their social interactions, and each rating may be associated with a weight, for example, ratings and weights may be: extremely positive (two points), mostly positive (onepoint), neutral (zero points), somewhat negative (negative one point), and very negative (negative two points).

[0044] In embodiments, the at least one questionnaire asks the subject to rate the quality of social support received from family and friends, and each rating may be associated with a weight, for example, ratings and weights may be: strongly supported (three points), moderately supported (two points), somewhat supported (one point), not supported (zero points).

[0045] In embodiments, the at least one questionnaire asks the subject how comfortable they are expressing their emotions and needs to others. Each response may be associated with a weight, for example, ratings and weights may be: very comfortable (two points), comfortable (one point), neutral (zero points), uncomfortable (negative one point), and very uncomfortable (negative two points).

[0046] In embodiments, the at least one questionnaire asks the subject about their current surrounding environment. Each response may be associated with a weight, for example, responses and weights relating to ambient noise levels may be: very quiet (two points), quiet (one point), moderate noise (zero points), noisy (negative one point), and very noisy (negative two points). Survey data 21 relating to the ambient noise of the subject’s surrounding environment may be cross referenced with environmental data 24 collected by a wearable device that can monitor the subject’s surrounding environment.

[0047] In embodiments, the at least one questionnaire asks the subject about the air quality of their current surrounding environment. Each response may be associated with a weight, for example, responses and weights relating to air quality may be: good (one point), unsure (zero points), and bad (minus one point). Survey data 21 relating to the air quality of the subject’s surrounding environment may be cross referenced with environmental data 24 collected by a wearable device that can monitor the subject’s surrounding environment.

[0048] In embodiments, the at least one questionnaire asks the subject about their natural light exposure in the past twenty-four hours (or other period of time). Each response may be associated with a weight, for example, responses and weights relating to natural lightexposure in a twenty-four hour period may be: none (zero points), about thirty minutes (one point), about an hour (two points), or more than an hour and half (three points). Survey data 21 relating to the subject’s natural light exposure may be cross referenced with environmental data 24 collected by a wearable device that can monitor the subject’s surrounding environment.

[0049] In embodiments of the systems and methods disclosed herein, survey data 21 is input via a mobile application or web application. For example, with reference to FIG 2, a subject may input survey data 21 through a mobile application on their mobile phone. The survey data 21 is then received by the computer system 10 and stored in database 14. In embodiments, a health care professional may assist the subject to input survey data 21 into the computer system 10 or may input survey data 21 on their own based on observations of the subject.

[0050] In embodiments, multiple questionnaires are administered to the subject over a period of time, for example, throughout a day. For example, in embodiments, a subject answers questions for a questionnaire, and upon completion of the questionnaire, the survey data 21 (i.e. questionnaire responses) are transmitted to the computer system 10. In embodiments, the survey data 21 may be transmitted from a mobile application on the subject’s phone to the computer system 10. The computer system 10 may receive survey data 21 throughout the day as the subject completes questionnaires.

[0051] In embodiments, the first questionnaire completed by a subject is a comprehensive questionnaire, which investigates several aspects of the subject’s mental wellbeing. In embodiments, questionnaires following the first questionnaire are brief, for example, comprising only a few questions to investigate the subject’s mood at a specific point in time.

[0052] In embodiments, the computer system 10 and computer implemented method 100 involve receiving survey data 21 collected through two or more questionnaires at different points in time. In embodiments, each time survey data 21 is received, the computer system 10 and computer implemented method 100 process the data 20 associated with the subject to predict the state of mental well-being of the subject. In this regard, the systems andmethods disclosed herein are capable of providing a real-time, updated evaluations of the state of mental well-being of the subject at any moment in time.

[0053] In embodiments, the system and methods disclosed herein involve receiving biological data 22. In general, biological data 22 relates to information derived from the body of the subject. For example, biological data 22 may comprise: genetic information, metabolite concentration, microbial diversity, neurotransmitter levels, inflammatory marker concentration, and brain activity.

[0054] In embodiments, biological data 22 includes weight, height, blood pressure, and heart rate of a subject. In embodiments, biological data 22 may be grouped into a category, for example, blood pressure may be categorized as: normal (systolic pressure less than one-hundred-twenty and diastolic pressure less than eighty), elevated (systolic pressure one-hundred-twenty to one-hundred-twenty-nine and diastolic pressure less than eighty), stage one hypertension (systolic pressure one-hundred-thirty to one-hundred-thirty-nine or diastolic pressure eighty to eighty-nine), and stage two hypertension (systolic pressure one- hundred-forty or higher or diastolic pressure ninety or higher). In embodiments, biological data 22 may associated with a weight, for example, normal blood pressure may be two points, elevated blood pressure may be negative one point, stage one hypertension blood pressure may be negative two points, and stage two hypertension blood pressure may be negative three points.

[0055] Biological data 22 may be collected through lab testing. In an embodiment, biological data 22 includes genetic information associated with the subject. For example, in embodiments, genetic information may include a whole genome single nucleotide polymorphism analysis. Alternatively, the single nucleotide polymorphism analysis may be conducted on specific genes, e.g., genes relating to resilience traits, mood regulation, and / or stress response. For example, the single nucleotide polymorphism analysis may focus on genes influencing serotonin and dopamine pathways.

[0056] In embodiments, biological data 22 includes genetic information (e.g., mutations / variation) relating to genes associated with depressive disorder, generalized anxiety disorder, panic disorder, obsessive-compulsive disorder, and specific phobias. For instance,biological data 22 may include information about genetic variations within the SERT and BDNF genes (associated with depressive disorder).

[0057] In embodiments, genetic information may be used by the systems and methods disclosed herein to determine whether the subject is genetically predisposed to experiencing certain states of mental well-being, e.g., frequent sadness.

[0058] In embodiments, biological data 22 includes genetic information (e.g., mutations / variation) relating to genes integral to regulating stress resilience and emotional coping mechanisms. For instance, biological data 22 may include information about genetic variations within the FKBP5, BDNF, and COMT genes.

[0059] In embodiments, the genetic information comprises genetic variations within RNA. Genetic information may be obtained from a biological sample of the subject (e.g., blood or saliva). Portions of, or the entire genome, of the subject may be sequenced using known techniques. In embodiments, genetic information of the subject may be input into the computer system 10. In embodiments, the methods and systems disclosed herein use the genetic information of the subject (along with other data 20 associated with the subject) to predict the state of mental well-being of the subject.

[0060] In embodiments, biological data 22 includes information from a microbial diversity assessment. For example, DNA sequencing techniques can reveal the diversity and composition of the gut microbiome of the subject. Certain microbial taxa are associated with resilience and mental well-being. The presence or absence of such bacteria in the gut microbiome in the subject may be biological data 22 used by the systems and methods disclosed herein (along with other data 20 associated with the subject) to predict the state of mental well-being of the subject.

[0061] In embodiments, biological data 22 includes measures of short-chain fatty acid produced by gut bacteria, such as, butyrate and propionate, which are known to impact mood, stress resilience, and cognitive function.

[0062] In embodiments, biological data 22 includes measurements of neurotransmitters (e.g., through blood or urine samples). For example, neurotransmitter levelsincluding serotonin, dopamine, gamma-aminobutyric acid, and endorphins may offer insights into mood regulation and resilience.

[0063] In embodiments, biological data 22 includes measurements of cortisol levels, inflammatory markers, and histamine levels. In embodiments, biological data 22 includes measurements of pro-inflammatory and anti-inflammatory cytokines, cortisol, adrenal hormone levels (e.g., adrenaline and noradrenaline), and omega-3 fatty acids to gain insight into the subject’s physiological response to stress and provide indicators of resilience capacity.

[0064] In embodiments, biological data 22 includes measurements of various biomarkers commonly associated with mental health conditions. For example, measured biomarkers may provide valuable information about stress response dysregulation, neurotransmitter imbalances, and inflammatory processes associated with various mental health conditions.

[0065] In embodiments, biological data 22 includes measuring brain activity of the subject, for example, using functional magnetic resonance imaging (fMRI) and / or quantitative electroencephalography (qEEG). For example, fMRI provides the ability to examine brain activity patterns, particularly in regions associated with emotion regulation and cognitive control. Insights gleaned from fMRI may be correlated with stress resilience. Similarly, using qEEG, brain wave patterns may be assessed and linked to emotional resilience and stress resilience.

[0066] A skilled person will understand that the accuracy of the systems and methods disclosed herein in predicting the state of mental well-being of a subject depends on the quality and scope (comprehensiveness) of data 20 that is provided to the computer system 10. Accordingly, it will be understood that more comprehensive biological data 22 will yield more accurate predictions of the state of mental well-being of the subject. Therefore, in general, in embodiments, biological data 22 comprises genetic information, metabolite concentration, microbial diversity, neurotransmitter levels, inflammatory marker concentration, and brain activity. Using all of this information, the systems and methods disclosed herein may provide a better understanding of cognitive and emotional well-being ofthe subject and offer personalized insights into genetic predispositions, gut-brain axis function, neurotransmitter balance, neural activity patterns, and inflammatory status. Furthermore, with more comprehensive biological data 22 the systems and methods disclosed herein can offer tailored interventions that will more meaningfully enhance resilience and promote longevity.

[0067] In embodiments, certain biological data 22 is input and received by the computer system 10 once. For example, genetic information need only be uploaded to the computer system 10 once (unless better quality / more accurate generic information is obtained). Other biological data 10 may be updated periodically (e.g., updated brain scans) and therefore uploaded to the computer system every time updated biological data 22 is obtained. In embodiments, biological data (e.g., blood pressure) is monitored in real-time (e.g., using a wearable device) and transmitted to the computer system 10 in real time.

[0068] In embodiments, wearable devices may be used to detect certain vitals (i.e. a form of biological data 22). For example, sensors may be used to monitor skin tone, blood flow, and heart rate. These vitals may provide early signs of stress or fatigue. In embodiments, techniques used in remote photoplethysmography may be used to monitor and measure vitals.

[0069] In embodiments, observed vitals may be assigned a weight value depending on whether the biological data value falls within a healthy range on a spectrum. For example, a negative weight may be assigned to a skin tone data value if an individual appears very pale (compared to their normal state). Various other types of biological data values may be assigned weight values. For example, positive weights may be associated with a healthy state of mental well-being and negative weights may be associated with an unhealthy state of mental well-being.

[0070] In embodiments, the system and methods disclosed herein involve receiving behavioural data 23. In general, behavioural data 23 relates to information about how the subject interacts with the surrounding environment.

[0071] In embodiments, the behavioural data 23 comprises at least one of: social interactions data, cognitive engagement data, sleep pattern data, and facial expression data.For example, in embodiments, the subject’s behaviour may be tracked and data relating to the same may be recorded and transmitted to the computer system 10. In embodiments, behavioural data 23 is tracked by the subject, a mental health professional, tracking devices, or any combination thereof.

[0072] In embodiments, behaviours tracking is facilitated through behavioural tracking tools, for example, cognitive engagement data (including attention span and processing speed) may be obtained through at least one of: problem-solving games or tasks (e.g. puzzles, matching games, word recall, pattern recognition, spatial memory or other memory recall games, number sequencing games, N-back game, trail making test, Stroop test, etc.) which may be offered to the subject through a mobile application capable of communicating with the computer system 10. In embodiments, the systems and methods disclosed herein monitor cognitive engagement and employ machine learning algorithms to assess cognitive engagement levels and provide personalized recommendations for optimizing brain function and neuroplasticity.

[0073] To assess the subject’s social awareness, the systems and methods disclosed herein may involve a game designed to improve and assess the subject’s facial recognition abilities. For example, the subject is shown images of different facial expressions and asked to identify them emotion or feelings associated with the expression. The difficulty of this type of game may be increased by showing more faces, less-distinct facial expressions, or older pictures of people.

[0074] In embodiments, games used to assess cognitive function may evolve in difficulty and focus requirement based on the subject’s progress and performance, thereby helping the subject enhance their cognitive abilities over time. Artificial intelligence may be used to continuously monitor cognitive performance of a subject and make personalized recommendations based on ongoing assessment of data.

[0075] Games may also be used for purposes other than evaluating cognitive wellbeing. For example, games may integrate emotional regulation exercises. Games and cognitive tasks may be provided by third party application that may be integrated with thesystems and methods disclosed herein or may be built in as part of a single integrated solution.

[0076] In embodiments, the subject’s performance on a game or task may be assigned a weight based, at least in part, on the speed the subject completes the game / task and number of incorrect actions. For example, game performance may be a behavioural data value, and that value may be assigned five points if the user completes the game in a certain time without making a mistake. Each mistake may result in one point being subtracted from the weight. If the subject cannot complete the game in certain time, minus five points may be assigned to the game performance behavioural data value. A skilled person will understand various other methods of allocating weight to a behavioural data value, where the weight provides an indication of the relevance of the data value in assessing a healthy or unhealthy state of mental well being of the subject.

[0077] In embodiments, an Al may used to normalize the subject performance in cognitive games / tasks against age-matched norms, and weight may be assigned to the behavioural data values associated with game performance after normalization.

[0078] In embodiments, behavioural data 23 may include brain imaging data used to assess brain plasticity and neural activity correlated with behavioural change.

[0079] In embodiments, behavioural data 23 may include emotional experiences, stress triggers, and coping mechanisms of the subject. In embodiments, games, assignments, brain imaging, or a combination thereof may provide insights into the emotional well-being of the subject, including emotional states, stress levels, and mood fluctuations of the subject throughout the day. In embodiments, the methods and systems disclosed herein provide information about the subject’s emotional resilience and offer strategies for managing stressors and promoting emotional well-being.

[0080] In embodiments, behavioural data 23 may be monitored using wearable devices, such as, smart watches, smart bracelets, smart rings, glasses, and headsets. In embodiments, the behavioural data 23, comprises facial expression data obtained using an artificial intelligence (Al) facial recognition program that can detect changes in facialexpressions of the subject. For example, a wearable device, such as, a headset may be equipped with a camera that observes the subject and the data recorded by the camera may be processed by the computer system 10 (or another system) comprising an Al facial recognition module which detects facial expressions. For instance, by capturing subtle changes in facial features (such as, muscle tension, eye movements, and lip curvature, eyebrow tension / furrowing, skin tone, facial landmark detection) an Al facial recognition module can assess a subject’s facial expressions, which, in turn, can be used by the computer system 10 to predict a state of mental well-being of the subject, or an aspect thereof, e.g., mood, emotional state, stress levels, and happiness levels in real-time. In embodiments, a stress metric may be created correlated to the eyebrow furrow distance and lip tension of a subject. More complex correlations can be developed by incorporating other facial features.

[0081] A skilled person is familiar with third-party facial expression detection libraries (e.g. pre-trained Al models) that may be integrated with the systems and methods disclosed herein. Al models may be fine tuned to specifically be able to detect, with better accuracy, the facial expressions of the target subject.

[0082] Weight may be assigned to behavioural data values associated with facial expressions depending on the intensity of the facial expression and length of time the expression is maintained. For example, a camera may detect the subject expressing a visibly sad expression for 30 seconds. In embodiments, this expression may be assigned negative five points. Facial expressions associated with happiness may be assigned positive weight values.

[0083] In embodiments, dietary habits (a form of behavioural data 23) may be tracked. For example, by integrating the systems and methods herein with internet of things devices like smart food journals and wearable nutrition monitors, dietary habits, such as food and alcohol intake, may be monitored. The systems and methods disclosed herein may correlate food intake (including alcohol consumption) with cognitive and emotional states, and offer recommendations to improve the same by making changes to the subject’s diet.

[0084] In embodiments, behavioural data 23 may be displayed to the subject via intuitive interfaces and intelligent dashboards, for example, via mobile applications, webapplications, or a combination thereof. The subject and / or health care professional can review historical behavioural data 23 to gain insights into the brain health of the subject.

[0085] In embodiments, behavioural data 23 is updated throughout a period of time, e.g., a day. In embodiments, as new behavioural data 23 is collected, it may be transmitted to the computer system 10 for processing to provide up-to-date predictions of the state of mental well-being of the subject as well as up-to-date recommendations on how to improve the predicted state of mental well-being of the subject. In embodiments, behavioural data 23 is tracked in real-time and provided to the computer system 10 in real-time so that real-time predictions of the state of mental well-being of the subject may be provided.

[0086] In embodiments, behavioural data 23 includes a comprehensive scope of data including social interactions data, cognitive engagement data, sleep pattern data (e.g. length of sleep, time at which the subject goes to bed, and sleep cycles experiences by the subject during sleep), and facial expression data. In general, more comprehensive behavioural data 23 will provide greater insights into a subject’s cognitive habits, emotional responses, and surrounding influences on brain health. In embodiments, after processing the data 20 associated with the subject, the systems and methods disclosed herein may provide the subject with personalized feedback and guidance tailored to the subject’s unique brain wellness goals.

[0087] In embodiments, the behavioural data 23 may be gleaned from the survey data 21. For example, a questionnaire may ask questions to evaluate the subject’s social interactions, including frequency, duration, and quality of social engagements with friends, family, colleagues, and community members. In embodiments, behavioural data 23 gleaned from survey data 21, may be cross-referenced for accuracy based on behavioural data 23 monitored and tracked by one or more devices worn by the subject. Alternatively, social interactions data may be observed by a social worker or party other than the subject, and input into the computer system 10. Cameras may also observe the subject and recorded data may be processed by an Al module to predict social behaviour.

[0088] A skilled person is familiar with various third-party wearable sensors that may be integrated with the systems and methods disclosed herein.

[0089] Using a combination of facial expression recognition, game performance, and data collected by internet of things devices, the systems and methods disclosed herein can detect early signs of cognitive decline (e.g., Alzheimer’s disease of dementia), including memory issues, confusion, and emotional instability. For example, methods and systems may compare recently collected behavioural data 23 of a subject with historical (i.e. past) behavioural data 23 to evaluate whether the subject is aging normally or experiencing cognitive health decline. For instance, slower responses or increased hesitation in decisionmaking in cognitive games / tasks can be flagged by the methods and systems as potential signs of declining processing speed or cognitive function.

[0090] In embodiments, the system and methods disclosed herein involve receiving environmental data 24. In general, environmental data 24 relates to information about the subject’s surrounding environment. For example, in embodiments, environmental data 24 comprises at least one of: ambient noise levels, air quality, temperature, and natural light exposure. Environmental data 24 may influence cognitive function, mood regulation, and sleep quality, and therefore, may assist the systems and methods disclosed herein to predict the state of mental well-being of a subject.

[0091] In embodiments, the environmental data 24 is collected by at least one device wearable by the subject, the at least one device comprising at least one of: a smart watch, a smart bracelet, a smart ring, glasses, and a headset.

[0092] In embodiments, the systems and methods disclosed herein use sensors on a subject’s phone to collect environmental data 24 such as ambient noise levels, light, temperature, and air quality. The systems and methods disclosed herein may correlate environmental data 24 with the subject’s stress levels and cognitive performance and offer recommendations to improve the same by changing the subject’s exposure to environmental elements.

[0093] In embodiments, the systems and methods disclosed herein may offer personalized recommendations for optimizing environmental conditions to support positive brain health and well-being. For example, the computer system 10 may recommended that the subject obtain more sunlight exposure or go indoors to a quiet, calming environment.

[0094] Once data 20 associated with the subject is provided to the computer system 10, the at least one processor 18 of the computer system can process the data 20 associated with the subject to evaluate the state of mental well-being of the subject. Ultimately, this evaluation is a prediction, and confidence or certainty of the prediction is dependant on the quality and breadth of the data 20 associated with the subject, and, in some cases, how recently the data 20 has been collected.

[0095] In embodiments, the predicted state of mental well-being of the subject includes stress levels, stress resilience, happiness levels, anger levels, or a prediction of other feelings and the intensity of those feelings.

[0096] In embodiments, the data 20 associated with the subject is processed by the computer system 10 to provide a comprehensive overview of a subject’s behavioural profile, including behaviour habits and triggers of certain behaviours.

[0097] In embodiments, the survey data 21 comprises a plurality of survey data values. In embodiments, the biological data 22 comprises a plurality of biological data values. In embodiments, the behavioural data 23 comprises a plurality of behavioural data values. In embodiments, the environmental data 24 comprises a plurality of environmental data values. In embodiments, the data 20 associated with the subject comprises a plurality of data values. In embodiment, the plurality of data values comprises the plurality of survey data values, the plurality of biological data values, the plurality of behavioural data values, and the plurality of environmental data values.

[0098] In embodiments, some of the plurality of data values may be associated with a point in time when a given data value was collected. In embodiments, old data values are assigned less weight during the processing of the data 20 associated with the subject to predict the state of mental well-being of the subject. For example, data values relating to heart rate or blood pressure (i.e. a type of biological data 22) may only influence the predicted state of mental well-being of the subject if the data values are collected in real-time and received by the computer system 10 in real-time. This is because heart rate and blood pressure are prone to changing quickly and, therefore, old or stale heart rate or blood pressure information may not be relevant to predicting the current state of mental well-being of a subject. However,historical data, may nevertheless be valuable in conducting analyses to determine causes of past events (such as, a manic episode), which may be useful in providing recommendations to improve the subject’s mental well-being.

[0099] In predicting the state of mental well-being of a subject, the weight assigned to a given data value may depend on how recently the data value was collected. However, in embodiments, some types of value may become stale faster than others. For example, blood pressure data values collected fifteen minutes ago may be irrelevant or have very low relevance in predicting the current state of mental well being of a subject, whereas, cortisol levels collected fifteen minutes ago may be just as relevant as recently measured cortisol levels in predicting the current state of mental well being of a subject. A skilled person will appreciate the rate at which different types of values decline in relevance and assign appropriate weights to different data values accordingly. In embodiments, a machine learning algorithm is trained to assign weights to different data values depending on the freshness of the data value.

[0100] In embodiments, some of the plurality of data values may not be associated with a point in time when the data value was collected. For example, where time has no impact on the data value, time need not be associated with the data value. For instance, genetic information may not be impacted by the time at which the genetic information was collected. In other words, the relevance of genetic information in predicting the state of mental well-being of the subject may not depend on when the genetic information was collected.

[0101] In embodiments, the systems and methods disclosed herein provide an analysis of data 20 associated with a subject to predict emotional, behavioural, and cognitive profiles of the subject and provide at least one recommendation to improve the subject’s lifestyle. In embodiments, the recommendations may aim to optimize cognitive and emotional well-being of the subject.

[0102] In embodiments, the systems and methods disclosed herein provide at least one recommendation to improve the predicted state of mental well-being of the subject comprisesat least one of: a lifestyle modification, an exercise regimen, scheduling a meeting with a mental health professional.

[0103] In embodiments, the systems and methods disclosed herein seek to inspire the subject to take proactive steps in their life to optimize brain health and foster positive lifestyle modifications.

[0104] In embodiments, the systems and methods disclosed herein provide a stress assessment involving processing biological data 22, such as, stress hormone levels (e.g., cortisol, adrenaline, and noradrenaline) and optionally integrating functional neuroimaging to examine brain regions associated with stress response.

[0105] In embodiments, the systems and methods disclosed herein provide insights into mood regulation by analysing, at least, biological data 22 regarding neurotransmitter levels.

[0106] In embodiments, the systems and methods disclosed herein provide a happiness evaluation involving processing biological data 22, such as, neurotransmitter levels including serotonin, dopamine, and endorphins, and analysing genomic variants associated with happiness traits.

[0107] In embodiments, stress and happiness indexes based on quantitative measurements of facial features and expressions may be provided by the computer system 10. For example, the indexes may provide objective assessments of emotional well-being and serve as valuable indicators of stress resilience and happiness levels over time. Facial expressions may be detected using Al facial recognition technology.

[0108] In embodiments, the systems and methods disclosed herein analyze stress hormone concentrations, neuroimaging data, and behavioural data to identify physiological, neural, and behavioural correlations with stress and happiness.

[0109] In embodiments, the systems and methods disclosed herein provide a longevity assessment, e.g., providing insights on how the subject’s mental well-being may affect their life span. In embodiments, a longevity assessment may involve analysing historical data 20associated with the subject, for example, over a period of a week, a month, a year, ten years, or more than ten years.

[0110] A longevity assessment may involve assigning more weight to data values associated with aging, chronic disease risk, and mortality. In embodiments, the systems and methods disclosed herein provide personalized recommendations on how a subject may increase their lifespan.

[0111] In embodiments, the systems and methods disclosed herein employ machine learning algorithms to analyze data 20 associated with the subject over a period of time and identify predictive markers of longevity. These algorithms may be used to develop personalized longevity plans tailored to individual needs and goals, empowering the subject to make informed decisions and adopt lifestyle modifications that promote longevity and vitality.

[0112] A longevity assessment may involve processing data related to one or more of: stress hormone levels in blood or saliva (including cortisol, adrenaline, and noradrenaline) neurotransmitter levels (such as, serotonin, dopamine, and endorphins), genomic variants, gut microbiome composition, and inflammatory biomarker concentrations (e.g., pro-inflammatory and anti-inflammatory cytokines).

[0113] In embodiments, systems and methods disclosed herein employing machine learning algorithms may be trained on data values from multiple different subjects (different individuals). In embodiments, such algorithms may be fine tuned by training the algorithm using data from a single subject, namely, the subject for which the computer system 10 provides predictions of the state of mental well-being and recommendations to improve the state of mental well-being.

[0114] In embodiments, the systems and methods disclosed herein evaluate whether the subject is experiencing distress, ranging from social isolation to depression or panic attacks. For example, if the computer system 10 determines that the subject is experiencing distress, the computer system 10 may recommend that the subject seek professional medical guidance, perform certain exercises (e.g., calming exercises), attend a personalized coachingsession led by a mental health professional, and / or participate in group chats. Coaching sessions may be provided by the computer system 10 via a mobile application on the subject mobile device or a web application accessible via a laptop computer. Coaching sessions offer subjects tailored guidance, support, and accountability in implementing lifestyle changes and optimizing brain-related behaviours.

[0115] If the distress experienced by a subject is severe and requires urgent care, the computer system 10 may alert a care facility (such as, an emergency care service) in order to prevent harm.

[0116] Data collected by the computer system 10 may be used by a health care professional to develop a personalized medical treatment plan, including the prescription of drugs.

[0117] In embodiments, historical behavioural data 23 may be reported to the subject to promote positive behavioural changes. By analyzing a variety of data 20 associated with the subject (e.g., survey data 21, biological data 22, behavioural data 23, and environmental data 24), the systems and methods disclosed herein may offer deep insights into a subject’s cognitive habits, emotional responses, and environmental influences on brain health.

[0118] By reporting personalized data insights, predictions about the state of mental well-being of the subject, and actionable recommendations on how to improve the state of mental well-being, the systems and methods disclosed herein empower the subject to take proactive steps towards enhancing their cognitive function, emotional well-being, and overall brain health.

[0119] In light of all the foregoing, a specific (non-limiting) process 300 of providing mental well-being support using an embodiment of a computer system 10 and computer implemented method 100 will now be described with reference to FIG 3.

[0120] In step 310 of process 300, a subject accesses a computer system 10. The computer system 10 may be accessible through a mobile phone application, web application, or a combination thereof. In embodiments, the computer system 10 comprises client-side software (e.g., a mobile phone application) along with server-side software installed onhardware in a cloud environment. In embodiments, access to the computer system 10 may be enabled via biometric data including fingerprints, eye gaze, facial features, weight, blood pressure, and other relevant health data during sign-up and for subsequent login.

[0121] In step 320 of process 300, a computer system 10 provides the subject with an initial screening assessment via one or more questionnaires. In embodiments, these initial screening assessments inquire about the subject’s lifestyle, habits, emotional and behavioural issues, and goals to improve mental health. The purpose of the initial screening assessment is to obtain survey data 21 from the subject providing insights into the general mental wellbeing of the subject.

[0122] In step 330 of process 300, a computer system 10 provides the subject with a comprehensive assessment, which allows the subject to integrate a wide range of biological data 23 into the computer system 10, for example, information relating to genomic testing, metabolomics studies, and pharmacogenomics studies, microbial diversity studies, neurotransmitter level testing, and inflammatory markers testing. Using information learned from other subjects, the machine learning enabled computer system 10 may gain insights into the target subject by cross-referencing the results from the initial screening assessment with the results of the comprehensive screening assessment.

[0123] In step 340 of process 300, a computer system 10 obtains up-to-date data 20 associated with the subject. In embodiments, this data may be obtained in real-time. For example, the data in step 340 may be behavioural data 23 and / or environmental data 24 obtained through tracking technology, such as, wearable devices. For instance, smart glasses or a headset coupled to Al facial recognition programs may enable the detection of facial expressions and allow the subject to accurately track behavioural data 23. Data obtained in step 340 may also be survey data 21 obtained through the administration of additional questionnaires (e.g., via a mobile or web application) asking a few short questions to probe the current mood or emotions of the subject.

[0124] In step 350 of process 300, a computer system 10 processes data 20 associated with the subject (e.g., survey data 21, biological data 22, behavioural data 23, and environmental data 24) to provide insights into the subject’s mental well-being, such as,evaluating happiness, stress levels, mood, etc. Data processing occurs in a cloud environment or on a user device (e.g., laptop or phone), or a combination thereof. After evaluating (i.e., predicting) the mental well-being of the subject, the computer system 10 may recommend precision interventions to improve the state of mental well-being of the subject, e.g., recommending exercises or activities. Behavioural data collected in real-time as well as key biomarkers, such as, stress response genes, microbial diversity, neurotransmitter levels, and inflammatory markers may play a key part in processing and analysing data, and developing tailored interventions.

[0125] In step 360 of process 300, a computer system 10 offers personalized coaching sessions led by mental health professionals to provide guidance, support, and accountability, integrating data collected by the computer system 10. In embodiment, health care professionals are made available to the subject through videoconferencing software integrated into the client-side software of the computer system 10. A doctor may access the computer system 10 and review the data 20 associated with the subject, the analysis performed by the computer system 10 on the data 20 associated with the subject, and any insights offered by the computer system 10 to the subject to assist in developing personalized treatments including prescribing medications.

[0126] The purpose of process 300 is to improve the mental well-being of a subject. Accordingly, in embodiments, after receiving personalized medications and care plans from a health care professional, the subject continues using the computer system 10, which collects more data 20 associated with the subject. Using this data, health care professionals can determine whether treatments are effective. Through the process of iteratively using the computer system 10 and consulting with health care professionals, the subject may enhance cognitive function, emotional well-being, and overall brain health, ultimately promoting longevity and vitality.

[0127] Referring to FIG 4, an exemplary method 400 of processing data 20 associated with a subject for predicting a state of mental well-being of the subject, will now be described.

[0128] In step 410, the method 400 involves receiving data 20 associated with the subject. The data 20 associated with the subject may comprise a plurality of data values, including a plurality of biological data values, a plurality of behavioural data values, and a plurality of survey data values collected through at least one questionnaire. In embodiment, the plurality of data values further comprises a plurality of environmental data value.

[0129] The plurality of biological data values are what make up biological data 22 as described earlier herein. Likewise, the plurality of survey data values are what make up survey data 21, the plurality of behavioural data values are what make up behavioural data 23, and the plurality of environmental data values are what make up environmental data 24.

[0130] In embodiments, the plurality of environmental data values comprise information about at least one of: ambient noise levels, air quality, temperature, and natural light exposure.

[0131] In embodiments, the at least one questionnaire comprises two or more questionnaires and the plurality of survey data values collected through the two or more questionnaires are collected at different points in time.

[0132] In embodiments, the plurality of biological data values comprise information about at least one of: genetics, metabolite concentration, microbial diversity, neurotransmitter levels, inflammatory marker concentration, and brain activity.

[0133] In embodiments, the plurality of behavioural data values comprise information about at least one of: social interaction, cognitive engagement, sleep, and facial expression.

[0134] In step 420, the method 400 involves processing the data 20 associated with the subject to predict the state of mental well-being of the subject. In embodiments, step 420 involves: assigning 422 a respective weight to each of the plurality of data values, adjusting 424 the respective weight of at least one of the plurality of data values as a function of time, calculating 426 a mental well-being score of the subject as a function of the respective weight of at least one of the plurality of data values, and predicting 428 the state of mental well-being of the subject as a function of the mental well-being score of the subject.

[0135] Data processing may be performed on one or more edge devices, on a cloud environment, or a combination thereof. Where third-party libraries are used, e.g., for Al facial expression detection, third-party cloud environments may process some components of the data 20 associated with the subject.

[0136] In embodiment, processing the data 20 associated with the subject involves assigning 422 a respective weight to each of the plurality of data values. For example, as noted above, each data values may be associated with a weight. In embodiments described above, positive data value weights are associated with a healthy state of mental well-being and negative data value weights are associated with an unhealthy state of mental well-being (and data values assigned weight near zero have a neutral impact on metal health evaluation). However, a skilled person will understand that the assigning weight to data values can be conducted in any logical manner. The purpose of assigning weight (or scores) to data is to provide an indicator as to whether a given data value is relevant to a healthy or unhealthy state of mental well-being of the subject. Data value weight also indicates how relevant a given data value is in evaluating a healthy or unhealthy state of mental well-being of the subject. For instance, in the examples provided herein, a greater magnitude of weight, e.g., high positive value or low negative value, indicates a greater relevance of the data value in evaluating a healthy or unhealthy state of mental well-being of the subject, respectively. In other embodiments, only positive weights may be assigned to data values and a large positive weight may be associated with an unhealthy state of mental well-being.

[0137] Any of the biological data values, environmental data values, survey data values, and behavioural data values may be assigned a weight. Upon receiving data values, the computer system 10 may assign a weight to a given data value depending on where the data value falls in a range of possible values. In embodiments, a subject may select a predetermined response already associated with a data value weight. In this case, when the subject selects a response, the response is transmitted to the computer system 10 which receives data 20 associated with the subject and one or more data values and assigns the one or more data values weight depending on the associated weight of the selected data value. In other words, receiving data by computer system 10 may involve receiving data values alreadyassigned a weight. Accordingly, it will be understood that assigning weight to a data value need not be performed after computer system 10 received a data value.

[0138] In embodiments, some data values (e.g., certain qualitative data) may not be assigned a weight. In embodiments, some data values may be assigned zero weight. In embodiments, method 400 may process zero weight and / or unweighted data values for reasons other than calculating a mental well-being score of the subject.

[0139] In embodiment, processing the data 20 associated with the subject involves adjusting 424 the respective weight of at least one of the plurality of data values. For example, as discussed above, the weights of data values may be adjusted as a function of time. For instance, blood pressure data collected at noon on a given day may be irrelevant an hour later to the subject’s current stress levels. Accordingly, the weight of a data value may decrease as time passes. As noted above, the rate at which data value weights decrease (or become less relevant) depend on the type of data. Accordingly, the respective weight of a first data value may be adjusting based on time to a different extent than adjusting the respective weight of a second data value. For instance, cortisol levels collected at noon may still be relevant an hour later to the subject’s current stress levels and, therefore, the passage of time has less of an impact on the weight of data values associated with cortisol levels as compared to the weight of data values associated with blood pressure (as it relates to the subject’s current stress levels, for example).

[0140] In embodiments, not all data value weights are adjusted based on time (i.e. the passage of time from when data values are collected). For example, time may not have an impact on the relevance of genetic information.

[0141] In embodiment, processing the data 20 associated with the subject involves calculating 426 a mental well-being score of the subject as a function of the respective weight of at least one of the plurality of data values. For example, after adjusting the weights of the data values for which adjustment is warranted, the resulting data values may be summed (for example) to arrive at a mental well-being score. In some embodiments, the mental well-being score may relate to a certain aspect of the mental well-being of the subject, e.g., emotional well-being, stress levels, etc. Accordingly, a given mental well-being score may be calculatedbased on certain data values only. For instance, an emotional mental well-being score may be calculated using data values relating to the emotional state of the subject.

[0142] In embodiments, a comprehensive mental well-being score relating to the cognitive agility of the subject may be evaluated based on the weights of data values relating to memory game performance, observed social interactions, oxygen levels in the environment, etc. In some embodiments, the weights of certain data values may be multiplied by a multiplier factor (which may vary depending on the data value) in calculating a comprehensive mental well-being score relating to cognitive agility.

[0143] In embodiments, a comprehensive mental well-being score relating to the emotional resilience of the subject may be evaluated based on the weights of data values relating to stress levels, facial expressions, stress biomarkers, survey data relating to emotional state, etc. In some embodiments, the weights of certain data values may be multiplied by a multiplier factor (which may vary depending on the data value) in calculating a comprehensive mental well-being score relating to emotional resilience.

[0144] In embodiments, a comprehensive mental well-being score relating to the stress levels of the subject may be evaluated based on the weights of data values relating to facial expressions, frequency of facial expressions, intensity of facial expressions, stress biomarkers, survey data relating to emotional stress, etc. In some embodiments, the weights of certain data values may be multiplied by a multiplier factor (which may vary depending on the data value) in calculating a comprehensive mental well-being score relating to stress levels.

[0145] In embodiments, a comprehensive mental well-being score relating to the health and vitals of the subject may be evaluated based on the weights of data values relating to oxygen levels, heart rate, skin tone, blood pressure, etc. In some embodiments, the weights of certain data values may be multiplied by a multiplier factor (which may vary depending on the data value) in calculating a comprehensive mental well-being score relating to health and vitals.

[0146] In embodiments, a comprehensive mental well-being score relating to the sleep quality of the subject may be evaluated based on the weights of data values relating to total sleep time, amount of deep sleep, amount of light sleep, time the subject went to bed, number of times the subject woke up, etc. In some embodiments, the weights of certain data values may be multiplied by a multiplier factor (which may vary depending on the data value) in calculating a comprehensive mental well-being score relating to sleep quality.

[0147] In embodiments, a comprehensive mental well-being score relating to nutritional wellness of the subject may be evaluated based on the weights of data values relating to healthy food intake, alcohol consumption, unhealthy food intake, vitamin intake, etc. In some embodiments, the weights of certain data values may be multiplied by a multiplier factor (which may vary depending on the data value) in calculating a comprehensive mental well-being score relating to nutritional wellness.

[0148] In embodiments, an overall mental well-being score of the subject may be evaluated by adding the weights of data values. In some embodiments, the weights of certain data values may be multiplied by a multiplier factor (which may vary depending on the data value).

[0149] In embodiments, a mental well-being score of the subject may be calculated, at least in part, by comparing healthy data value weights with unhealthy data value weights (for example, in a ratio).

[0150] In embodiments, an overall mental well-being score of the subject may be evaluated by adding the weights associated with mental well-being scores of particular aspects of mental health (e.g., comprehensive mental well-being score relating to the cognitive agility of the subject, comprehensive mental well-being score relating to the emotional resilience of the subject, comprehensive mental well-being score relating to the health and vitals of the subject, comprehensive mental well-being score relating to the sleep quality of the subject, comprehensive mental well-being score relating to nutritional wellness of the subject, etc.). In some embodiments, the weights of certain mental well-being scores of particular aspects of mental health may be multiplied by a multiplier factor (which may vary depending on the particular aspects of mental health).

[0151] In embodiments, a given data value may be associated with multiple weights, each weight relevant to a different aspect of the subject’s state of mental well being. For example, data values associated with serotonin levels may have a first weight that is large in magnitude (i.e. high relevance) and that is used as part of the evaluation of the mood of a subject and a second weight that is low in magnitude (i.e. low relevance) that is used as part of the evaluation of cognitive abilities of the subject. In other embodiments, a given data value may be associated with single weight, and that single weight may be multiplied by different multiplier factors depending on the aspect of the subject’s state of mental well-being that the data value is being used to evaluate. For example, data values associated with serotonin levels may be associated with a single weight and that single weight may be multiplied by a factor of 5.3 in the evaluation of a subject’s mood, however, when that same data value weight may be multiplied by a factor of 1.6 in the evaluation of a subject’s cognitive ability. Different multiplier factors are used where data values have different relevance in evaluating different aspects of mental health. In some embodiments, a data value may have a positive (healthy) impact on a first state of a subject’s mental well-being and a negative (unhealthy) impact on a second state of a subject’s mental well-being. In this case, a given data value may be multiplied by a positive multiplier in evaluating the first state of a subject’s mental well-being and a negative multiplier in evaluating the second state of a subject’s mental well-being.

[0152] In embodiment, processing the data 20 associated with the subject involves predicting 428 the state of mental well-being of the subject as a function of the mental wellbeing score of the subject. For example, the method 400 may arrive at a calculated emotional mental well-being score of the subject of 70 / 100 or seventy percent, which may correspond to general satisfaction with life, some sense of purpose, and a good ability to manage stress. In embodiments, the mental well-being score may be calculated for specific aspects of the subject mental well-being, e.g., happiness levels, stress levels, anger levels, anxiety levels, etc.

[0153] In step 430, the method 400 involves providing an output of the predicted state of mental well-being of the subject. For example, an output may be a signal transmitted to a user device, such as a smart phone, which can display the signal as information the subjectcan understand. This step may involve providing a detailed report of the mental well-being of the subject and providing at least one recommendation to improve the predicted state of mental well-being of the subject.

[0154] Method 400 may further involve alerting a care facility when the predicted state of mental well-being of the subject requires urgent care, for example, when the subject is at risk of harming themselves or others. The systems and methods herein may also alert the subject when a determination is made that the subject is experiencing cognitive decline, emotional instability, or health data anomalies. For example, by analysing cognitive health data (e.g., game performance and data related to emotional state), the systems and methods herein may detect early signs of memory impairment. Emotional instability may be detected when an analysis of data reveals persistent stress or emotional shifts. Health data anomalies may be detected when an analysis of data reveals deviations in sleep patterns or vitals. A subject may be alerted by the systems and methods herein via a mobile app on their phone, web application, or combination thereof. Weights associated with data values may be used to by the systems and methods herein to determine whether a subject should be alerted. For example, a subject may be alerted of high stress levels if the systems and methods determine weights associate with data values associated with stress fall below a certain threshold.

[0155] In embodiments, the methods and systems herein may offer personalized recommendations to improve the subject’s state of mental well-being, respond to user queries, and provide real-time feedback based on sensor data, cognitive performance, and emotional state (e.g., through a virtual assistant). In embodiments, a subject may receive visual graphs and trends (on their phone or computer) showing their cognitive, emotional, and health data over time. Monthly or weekly reports provide actionable insights into a subject’s progress and areas needing attention.

[0156] Method 400 is a computer-implemented method that may be performed by computer system 10. For example, method 400 may be performed by a computer system comprising: one or more processors and memory operatively coupled to the one or more processors and storing processor-executable instructions thereon that, when executed, cause the one or more processors to implement method 400 or any variation thereof.

[0157] Other steps may be included in method 400 and some steps may be omitted. Furthermore, the illustrated steps in method 400 may be performed in any logical order.

[0158] As those skilled in the art will appreciate, the methods disclosed herein may be implemented as one or more software and / or firmware programs having necessary computerexecutable code or instructions and stored in one or more non-transitory computer-readable storage devices or media which may be any volatile and / or non-volatile, non-removable or removable storage devices such as RAM, ROM, EEPROM, solid-state memory devices, hard disks, CDs, DVDs, flash memory devices, and / or the like. One or more processors may read the computer-executable code from the storage devices and execute the computer-executable code to perform the methods.

[0159] Unless defined otherwise, all terms used herein (including in the claims) have the same meaning as commonly understood by one of ordinary skill in the art to which the disclosure pertains. If there is any conflict in the usages of a word or term in this specification and one or more patents, patent applications, or other documents that may be referenced herein, the definitions that are consistent with this specification should be adopted.

[0160] In the present disclosure, all terms referred to in singular form are meant to encompass plural forms of the same. Likewise, all terms referred to in plural form are meant to encompass singular forms of the same. Moreover, the indefinite articles “a” or “an” as used in herein (including in the claims) are defined herein to mean one or more than one of the element that it introduces.

[0161] The apparatuses and / or methods disclosed herein may be described in terms of “comprising,” “containing,” or “including” various components or steps - these terms are to be understood as “including, but not limited to”.

[0162] As used herein, the term “about” refers to an approximately + / -10 % variation from a given value. It is to be understood that such a variation is always included in any given value provided herein, whether or not it is specifically referred to.

[0163] For the sake of brevity, only certain ranges are explicitly disclosed herein. However, ranges from any lower limit may be combined with any upper limit to recite a rangenot explicitly recited, as well as, ranges from any lower limit may be combined with any other lower limit to recite a range not explicitly recited. In the same way, ranges from any upper limit may be combined with any other upper limit to recite a range not explicitly recited. Additionally, whenever a numerical range with a lower limit and an upper limit is disclosed, any number and any included range falling within the range are specifically disclosed. In particular, every range of values (of the form, “from about a to about b,” or, equivalently, “from approximately a to b,” or, equivalently, “from approximately a-b”, or the like) disclosed herein is to be understood to set forth every number and range encompassed within the broader range of values even if not explicitly recited. Thus, every point or individual value may serve as its own lower or upper limit combined with any other point or individual value or any other lower or upper limit, to recite a range not explicitly recited.

[0164] A skilled person will appreciate that the method steps claimed and disclosed herein may be performed in any logical order and in some embodiments, method steps are performed iteratively, concurrently, or a combination thereof.

[0165] The drawings included in this disclosure are merely illustrative of the invention disclosed herein. Items shown in any given figure may not be proportionate to one. Moreover, claims should not be limited because of details shown in the drawings.

[0166] The illustrative (i.e., exemplary) embodiments disclosed above may be altered or modified and all such variations are considered within the scope of the present disclosure. Many obvious variations of the embodiments set out herein will suggest themselves to those skilled in the art having the benefit of the present disclosure. Such obvious variations are within the full intended scope of the appended claims.

[0167] Although individual embodiments are discussed, where possible (as would be understood by a skilled person), the disclosure covers all combinations of all those embodiments.

Claims

CLAIMS1. A computer-implemented method for predicting a state of mental well-being of a subject, the method comprising: receiving survey data associated with the subject, the survey data collected through at least one questionnaire; receiving biological data associated with the subject; receiving behavioural data associated with the subject; processing the survey data, the biological data, and the behavioural data to predict the state of mental well-being of the subject; providing an output of the predicted state of mental well-being of the subject; and providing at least one recommendation to improve the predicted state of mental well-being of the subject.

2. The method of claim 1 wherein the at least one questionnaire comprises questions for probing at least one of: depressive disorder, generalized anxiety disorder, panic disorder, obsessive-compulsive disorder, and specific phobia.

3. The method of claim 1 or 2 wherein the survey data comprises qualitative data and quantitative data.

4. The method of any one of claims 1 to 3, wherein the at least one questionnaire comprises two or more questionnaires and the receiving survey data comprises receiving survey data collected through the two or more questionnaires at different points in time.

5. The method of any one of claims 1 to 4, wherein the biological data comprises at least one of: genetic information, metabolite concentration, microbial diversity, neurotransmitter levels, inflammatory marker concentration, and brain activity.

6. The method of claim 5 wherein the genetic information comprises single nucleotide polymorphisms associated with genes influencing serotonin and dopamine pathways.

7. The method of claim 5 or 6 wherein the genetic information comprises genetic variations within at least one of: SERT, FKBP5, BDNF, and COMT genes.

8. The method of any one of claims 5 to 7, wherein the genetic information comprises genetic variations within RNA.

9. The method of any one of claims 5 to 8, wherein the metabolite concentration comprises levels of short-chain fatty acids produced by gut bacteria in the subject.

10. The method of any one of claims 5 to 9, wherein the neurotransmitter levels comprise blood or urine concentrations of at least one of: serotonin, dopamine, gamma-aminobutyric acid, and endorphins.

11. The method of any one of claims 5 to 10, wherein inflammatory marker concentration comprises concentrations of at least one of: pro-inflammatory cytokines, anti-inflammatory cytokines, cortisol, adrenaline, and noradrenaline.

12. The method of any one of claims 5 to 11, wherein the brain activity is obtained using at least one of: functional magnetic resonance imaging and quantitative electroencephalography.

13. The method of any one of claims 1 to 12, wherein the behavioural data comprises at least one of: social interactions data, cognitive engagement data, sleep pattern data, and facial expression data.

14. The method of claim 13 wherein the cognitive engagement data is obtained through at least one of: problem-solving games, memory games, problem-solving assignments, or memory assignments.

15. The method of claim 13 wherein the facial expression data is obtained using anartificial intelligence facial recognition program that can detect changes in facial expressions of the subject.

16. The method of any one of claims 13 to 15, wherein: the behavioural data is received in real-time; the survey data, the biological data, and the behavioural data are processed in real-time as the behavioural data is received to provide a real-time predicted state of mental well-being of the subject; the output of the predicted state of mental well-being of the subject is provided in real-time; and the at least one recommendation to improve the predicted state of mental wellbeing of the subject is provided in real-time.

17. The method of any one of claims 1 to 16, further comprising: receiving environmental data associated with the subject and processing the environmental data, in addition to the survey data, the biological data, and the behavioural data, to predict the state of mental well-being of the subject.

18. The method of claim 17 wherein the environmental data comprises at least one of: ambient noise levels, air quality, temperature, and natural light exposure.

19. The method of claim 17 or 18 wherein the environmental data is collected by at least one device wearable by the subject, the at least one device comprising at least one of: a smart watch, a smart bracelet, a smart ring, glasses, and a headset.

20. The method of any one of claims 1 to 18, wherein the behavioural data is collected by at least one device wearable by the subject, the at least one device comprising at least one of: a smart watch, a smart bracelet, a smart ring, glasses, and a headset.

21. The method of any one of claims 1 to 20, wherein the state of mental well-being comprises at least one of: stress levels and happiness levels.

22. The method of any one of claims 1 to 21, wherein the at least one recommendation to improve the predicted state of mental well-being of the subject comprises at least one of: a lifestyle modification, an exercise regimen, scheduling a meeting with a mental health professional.

23. The method of any one of claims 1 to 22, wherein the predicted state of mental wellbeing of the subject requires urgent care, and wherein the method further comprises alerting a care facility of the predicted state of mental well-being of the subject.

24. A computer system comprising: one or more processors; memory operatively coupled to the one or more processors and storing processorexecutable instructions thereon that, when executed, cause the one or more processors to implement the method of any one of claims 1 to 23.

25. A computer system for providing mental well-being support to a subject, the system comprising: a database for storing data associated with the subject, the data comprising: biological data, behavioural data, and survey data, the survey data collected through at least one questionnaire; at least one processor; memory operatively coupled to the one or more processors and storing processor-executable instructions thereon that, when executed, cause the one or more processors to processes the data associated with the subject to predict a state of mental well-being of the subject; and an interface for receiving the data associated with the subject and for outputting the predicted state of mental well-being of the subject.

26. The system of claim 25 wherein: the processor-executable instructions, when executed, further cause the one ormore processors to provide at least one recommendation to improve the predicted state of mental well-being of the subject; and the interface is further for outputting at least one recommendation to improve the predicted state of mental well-being of the subject.

27. The system of claim 26, wherein the at least one recommendation to improve the predicted state of mental well-being of the subject comprises at least one of: a lifestyle modification, an exercise regimen, scheduling a meeting with a mental health professional.

28. The system of claim 26 or 27, wherein the system comprises a communication module for alerting a care facility when the predicted state of mental well-being of the subject requires urgent care.

29. The system of claims 25 or 28 wherein the system is accessible through a user interface comprising biometric login.

30. The system of any one of claims 25 to 29, wherein data associated with the subject comprises environmental data.

31. The system of claim 30 wherein the environmental data comprises at least one of: ambient noise levels, air quality, temperature, and natural light exposure.

32. The system of claim 30, wherein the interface receives the environmental data from at least one device worn by the subject.

33. The system of any one of claims 25 to 31, wherein the interface receives the behavioural data from at least one device worn by the subject.

34. The system of any one of claims 25 to 33, wherein the at least one questionnaire comprises questions for probing at least one of: depressive disorder, generalized anxiety disorder, panic disorder, obsessive-compulsive disorder, and specific phobia.

35. The system of any one of claims 25 to 34, wherein the survey data comprises qualitative data and quantitative data.

36. The system of any one of claims 25 to 35, wherein the at least one questionnaire comprises two or more questionnaires and the survey data collected through the two or more questionnaires is collected at different points in time.

37. The system of any one of claims 25 to 36, wherein the biological data comprises at least one of: genetic information, metabolite concentration, microbial diversity, neurotransmitter levels, inflammatory marker concentration, and brain activity.

38. The system of claim 37 wherein the genetic information comprises single nucleotide polymorphisms associated with genes influencing serotonin and dopamine pathways.

39. The system of claim 37 or 38 wherein the genetic information comprises genetic variations within at least one of: SERT, FKBP5, BDNF, and COMT genes.

40. The system of any one of claims 37 to 39, wherein the genetic information comprises genetic variations within RNA.

41. The system of any one of claims 37 to 40, wherein the metabolite concentration comprises levels of short-chain fatty acids produced by gut bacteria in the subject.

42. The system of any one of claims 37 to 41, wherein the neurotransmitter levels comprise blood or urine concentrations of at least one of: serotonin, dopamine, gamma- aminobutyric acid, and endorphins.

43. The system of any one of claims 37 to 42, wherein inflammatory marker concentration comprises concentrations of at least one of: pro-inflammatory cytokines, anti-inflammatory cytokines, cortisol, adrenaline, and noradrenaline.

44. The system of any one of claims 37 to 43, wherein the brain activity is obtained using at least one of: functional magnetic resonance imaging and quantitative electroencephalography.

45. The system of any one of claims 25 to 44, wherein the behavioural data comprises at least one of: social interactions data, cognitive engagement data, sleep pattern data, and facial expression data.

46. The system of claim 45 wherein the cognitive engagement data is obtained through at least one of: problem-solving games, memory games, problem-solving assignments, or memory assignments.

47. The system of claim 45 wherein the facial expression data is obtained using an artificial intelligence facial recognition program that can detect changes in facial expressions of the subject.

48. The system of any one of claims 25 to 47, wherein the interface receives portions of the data associated with the subject in real-time.

49. The system of any one of claims 25 to 48, wherein the predicted state of mental wellbeing comprises at least one of: stress levels and happiness levels.

50. The system of any one of claims 25 to 49, wherein: the data associated with the subject comprises a plurality of data values; and at least a portion of the data values are assigned varying levels of weight in the process of predicting the state of mental well-being of the subject.

51. A computer-implemented method for predicting a state of mental well-being of a subject, the method comprising: receiving data associated with the subject, the data comprising a plurality ofdata values comprising: a plurality of biological data values, a plurality of behavioural data values, and a plurality of survey data values collected through at least one questionnaire; processing the data associated with the subject to predict the state of mental well-being of the subject, the processing comprising: assigning a respective weight to each of the plurality of data values; adjusting the respective weight of at least one of the plurality of data values as a function of time; calculating a mental well-being score of the subject as a function of the respective weight of at least one of the plurality of data values; and predicting the state of mental well-being of the subject as a function of the mental well-being score of the subject; and providing an output of the predicted state of mental well-being of the subject.

52. The method of claim 51 wherein the plurality of data values comprises a plurality of environmental data value.

53. The method of claim 52 wherein the plurality of environmental data values comprise information about at least one of: ambient noise levels, air quality, temperature, and natural light exposure.

54. The method of any one of claims 51 to 53, wherein the at least one questionnaire comprises two or more questionnaires and the plurality of survey data values collected through the two or more questionnaires are collected at different points in time.

55. The method of any one of claims 51 to 54, wherein the plurality of biological data values comprise information about at least one of: genetics, metabolite concentration, microbial diversity, neurotransmitter levels, inflammatory marker concentration, and brain activity.

56. The method of any one of claims 51 to 55, wherein the plurality of behavioural data values comprise information about at least one of: social interaction, cognitive engagement, sleep, and facial expression.

57. The method of any one of claims 51 to 56, wherein further comprising the step of providing at least one recommendation to improve the predicted state of mental well-being of the subject.

58. The method of any one of claims 51 to 57, wherein the step of adjusting the respective weight of at least one of the plurality of data values as a function of time comprises adjusting the respective weight of a first data value to a different extent than adjusting the respective weight of a second data value.

59. The method of any one of claims 51 to 58, further comprising the step of alerting a care facility when the predicted state of mental well-being of the subject requires urgent care.

60. A computer system comprising: one or more processors; memory operatively coupled to the one or more processors and storing processor-executable instructions thereon that, when executed, cause the one or more processors to implement the method of any one of claims 51 to 59.

Images