Methods and systems for collecting, presenting, and evaluating personalized health data.

Abstract

This invention relates to a method and a system based on the method for presenting individual-specific, personalized health and health-related data for at least one person. Using a 2D and / or 3D representation of a single person's real body, the body is explored like a terrain feature to obtain conclusions about their health status and / or physical condition, and to provide recommendations for treating and / or improving these conditions. For this purpose, cluster-related analytical data from anonymized personal data within the system, derived from a large amount of comparative and standard data, is used. By applying scaling, the dataset is used to selectively explore, treat, and develop personalized behavioral recommendations and risk analyses for each individual's real body.

Description

Technical Field

[0001] The present invention relates to a method for presenting individual-specific, personalized health status and health-related data of at least one individual, and a system based on the method. Background Technology

[0002] Systems, methods, and modules for collecting health measurement data and processing this data to generate warnings and modify patient treatment plans are known. Here, a system can be configured to receive, for example, data defined by multiple health sensors, and generate application logic based on this data. This application logic is further configured to, in response to user input, facilitate coupling between a user device and the multiple health sensors, thereby establishing communication between the user device and the health sensors.

[0003] Various data collection and monitoring systems are also known, such as smartwatches, fitness watches, fitness trackers, and apps.

[0004] These systems can, for example, present information via a display, inform users through vibration alarms or similar auditory and / or visual functions, and collect current status data via sensor technology. Thus, users can be observed and / or self-observed and receive context-specific support, and execute commands through interaction to control other devices. Typically, smartwatches can wirelessly connect to smartphones with appropriate apps via Bluetooth, enabling data presentation and evaluation. While smartwatches are typically consumer-facing products, they can also be used in industrial environments. Their applications are diverse, but can generally be categorized into sports, health, and extended smartphone functionality.

[0005] Some smartwatches also create personalized training plans, tailored to the user based on a wealth of collected data. Outdoor activity routes and training plans can be pre-planned and use GPS for navigation, or recorded and evaluated during the activity.

[0006] Sensor technology can identify anomalies, which allows for applications such as fall detection, assistance, epilepsy detection, in hazardous workplaces, or for medical use. Smartwatches are also used to identify arrhythmias, such as atrial fibrillation. Some models can also measure blood pressure. Some of these so-called smartwatches or standalone devices also offer blood oxygen saturation measurement via pulse oximeter, which can also be collected and presented via an app. Today, anyone can automatically collect steps, heart rate, blood sugar, and much other information using home testing devices or smartphones and apps.

[0007] Unrelated to and detached from this type of data and the systematic collection and evaluation of such data, almost everyone possesses health data stored in a doctor's health record in analog and / or digital form. This personalized data regarding health, illness, monitoring results (such as electrocardiograms (EKG) or X-rays), medication use, vaccinations, etc., may exist independently and detached from the personalized data in the aforementioned smartwatches or similar systems. Other personalized data sources from different medical institutions are also often unconnected. This includes general, individual-specific behaviors such as dietary habits, individual emotional states, and the body's response to weather conditions, climate change, and / or location changes due to travel, relocation, etc., which cannot be collected or exist only in an individual context. Summary of the Invention

[0008] The present invention now aims to provide a method and system for collecting, presenting, and evaluating personalized data. It also aims to develop a system that can provide behavioral recommendations to individuals based on ubiquitous anonymized health data.

[0009] This task is accomplished by methods, systems, and computer program products having the features of the independent claims. Advantageous design options and improvements are described in the dependent claims.

[0010] By using digital 2D and / or 3D representations of an individual's real body, that body can be explored like a terrain feature, allowing for conclusions about the individual's health and / or physical condition, and providing recommendations for treatment and / or improvement. This is achieved using cluster-related analytical data from anonymized personal data derived from the system.

[0011] Cluster-related analyses of anonymized personal data from the system consist of a large amount of comparative and standard data. By applying methods to scale regions of interest, datasets can be selectively utilized to explore, treat, and develop behavioral recommendations and risk analyses of an individual's true physical condition. Attached Figure Description

[0012] Further advantages and features of the present invention will become apparent from the following description, wherein embodiments of the invention will be described in detail with reference to the accompanying drawings. (Figures:) Figure 1 A two-dimensional representation of health data is shown, presented in the form of health data elements for different individuals, which also illustrates the relationships between the health data elements. Figure 2 A two-dimensional representation of health data for different individuals is shown, presented as health data elements in different colors and grouped by clusters. Figure 3A three-dimensional representation of individual health data is shown, presented as clustered health data elements arranged on a three-dimensional terrain. Detailed Implementation

[0013] The objective of this invention is achieved through at least one personalized data acquisition unit, at least one personalized data processing unit, at least one personalized data presentation unit, and at least one data evaluation unit. These units are interconnected via algorithms and, where necessary, through cloud-based, individual-specific, personalized presentation of health status and health-related data, providing a 2D and / or 3D representation of a single person's true body. This / these representations, derived from existing databases or datasets of relevant systems and the algorithms or methodologies used to correlate them, enable individuals to explore and present their bodies and minds as if exploring a landscape. According to the invention, the method for scaling regions of interest in digital images generated from health-related data is applied by reducing or increasing the resolution of the digital image according to a scaling ratio to personalize the attributes and structures of the true body (organs, blood circulation, skeletal structure, etc.) and to compare, analyze, explore, and provide treatment recommendations with anonymized data from other individuals or users.

[0014] It should be noted that the terms used in this article, such as data acquisition unit, data processing unit, clustering unit, or analysis unit, do not necessarily refer to actual devices, but rather to logical units and their functions. Logical units can be distributed across multiple actual devices.

[0015] It should also be noted that the term "computer program product" includes not only computer programs stored on at least one data carrier, but also computer programs that can be downloaded individually or in a distributed manner to one or more data acquisition and data processing units, clustering units or analysis units via a network and implemented there.

[0016] Health-related data can be obtained based on actual physical examinations. Examples of health-related data that can be processed according to the present invention are listed below. This list is merely illustrative and not exhaustive; it is primarily intended to illustrate the pursuit of appropriate structuring of health-related data due to its complexity and sheer volume, in order to provide users of the present invention with suitable access to their health-related data.

[0017] In some implementations, real-world bodily properties are obtained based on blood tests, in which different cell types and cellular components are analyzed to infer the body's health status.

[0018] Analysis of different cell types may include analysis of red blood cells, in which one or more of the following data are obtained: number, hemoglobin concentration, hematocrit, mean corpuscular volume (MCV), mean corpuscular hemoglobin content (MCH), and mean corpuscular hemoglobin concentration (MCHC). These analyses are typically performed by automated cell counting using a blood analyzer, where cell size and density are determined using methods such as light scattering or impedance measurements. Such measurements can provide indications of anemia or other blood abnormalities.

[0019] Analysis of different cell types can include analysis of white blood cells, in which one or more of the following data are obtained: total white blood cell count, subtype classification such as neutrophils, lymphocytes, monocytes, eosinophils, and basophils. For example, white blood cell differential counts can be used to determine inflammation, immune responses, or blood disorders (such as leukemia).

[0020] Analysis of different cell types can include platelet analysis, in which one or more of the following data are obtained: number and mean platelet volume (MPV). These parameters can, for example, indicate coagulation disorders or bone marrow diseases.

[0021] Serum and plasma samples offer additional opportunities for analyzing biochemical parameters from which health-related data can be derived. For example, glucose concentration can be determined using enzymatic methods such as the glucose oxidase reaction to infer blood glucose levels and metabolic health. Electrolytes such as sodium, potassium, calcium, and magnesium can be quantified using ion-selective electrodes to assess fluid and electrolyte balance. Lipid profiles, including cholesterol, low-density lipoprotein (LDL), high-density lipoprotein (HDL), and triglycerides, can be analyzed using enzymatic colorimetry or mass spectrometry to assess cardiovascular risk.

[0022] In addition, total protein concentrations, including albumin and globulins, and liver enzyme activities such as ALT, AST, and γ-GT can be checked. These measurements are typically performed spectrophotometrically or by enzyme activity assays to obtain information about liver and kidney function. Kidney function parameters such as creatinine, urea, and uric acid can be measured using enzymatic methods or based on... The reaction is analyzed to evaluate the kidney's filtration capacity.

[0023] Intracellular marker testing offers additional options. To assess mitochondrial redox status, the NAD+ / NADH ratio can be analyzed, for example, using fluorescence or mass spectrometry. Analysis of mitochondrial DNA (mtDNA) provides opportunities to identify marker mutations, deletions, or copy number changes. These analyses are typically performed using quantitative PCR or next-generation sequencing to identify mitochondrial dysfunction or age-related changes. Evaluation of mitochondrial function can also be accomplished by measuring ATP production. This can be achieved, for example, using a luminescent assay to detect luminescence during ATP hydrolysis. Additionally, the enzymatic activity of the mitochondrial respiratory chain (complex IV) can be determined through enzymatic assays or by measuring oxygen consumption. Substances such as FAD, cytochrome C, and coenzyme Q10 can be analyzed using high-performance liquid chromatography (HPLC) or mass spectrometry to evaluate the efficiency of the electron transport chain. Examination of mitochondrial oxidative stress provides opportunities to analyze reactive oxygen species (ROS) using chemiluminescent or fluorescent probes. Additionally, antioxidant status can be assessed by measuring the glutathione ratio (GSH / GSSG). The calcium concentration in mitochondria can be analyzed using fluorescence methods, in which special dyes are used to identify dysregulation in signal transduction.

[0024] For more detailed examination, liquid biopsy is offered, which can be considered for detecting free mitochondrial DNA (cf-mtDNA) in plasma, using digital PCR or sequencing techniques. Additionally, antioxidant enzymes such as superoxide dismutase (SOD) and catalase can be analyzed via enzymatic assays to evaluate cellular protective mechanisms.

[0025] Blood smears offer the opportunity to analyze the morphology of red blood cells, white blood cells, and platelets. For example, abnormalities such as sickle cells or vesicles can be identified using an optical microscope. Intracellular inclusions such as iron deposits or glycogen inclusions can be visualized using specialized staining techniques.

[0026] Functional imaging techniques such as positron emission tomography (PET) enable the analysis of cellular metabolic activity, for example, by analyzing glucose uptake using radiotracers such as 18F-FDG. Magnetic resonance imaging (MRI) provides the opportunity to visualize cell volume and tissue damage. Molecular analyses such as PCR, sequencing, or microarrays can be used to identify DNA mutations, gene expression, or epigenetic modifications (such as methylation status).

[0027] Flow cytometry can be used to determine leukocyte immunophenotype, analyze the CD4 / CD8 ratio, and evaluate the cell cycle. To assess oxidative stress, measures can be used to quantify reactive oxygen species or glutathione status. Metabolomics analysis offers options for measuring amino acids, lipids, or carbohydrates using mass spectrometry or nuclear magnetic resonance (NMR) spectroscopy.

[0028] Additionally, urinalysis can be considered to measure creatinine, electrolytes, hemoglobin degradation products, or hormones (such as adrenaline and cortisol). Swabs or biopsies of the skin and mucous membranes can reveal cell morphology, inflammatory markers, or abnormal proliferation.

[0029] The above analysis represents an exemplary data foundation for evaluating the state of cells, mitochondria, and subcellular structures, which can be processed as health-related data according to the present invention.

[0030] If necessary, health data may also include other health-related data, such as age, sex, height, weight, appearance-related data (e.g., skin color, eye color, or hair color), geographic data (e.g., place of residence or workplace), or socioeconomic information (e.g., occupation, marital status, or a particular social group or class).

[0031] In some implementations, health-related data is processed in an anonymized manner. Anonymized data from a variety of different sources, as well as individual-specific input, also allows the provision of private, anonymized data authorized by the respective individuals to the system according to the invention, so as to, in turn, provide insight and advice to the individuals and the public.

[0032] Figure 1 This section illustrates, generally and exemplarily, various sources that may contain data about an individual or a group of people. For example, point 11 represents data from patient X's health record.

[0033] Point 12 provides data from patient X's fitness watch, such as heart rate and steps. Figure 1 In the diagram, point 12, for example, indicates the current heart rate along axis A and the current number of steps along axis B. Point 12 also represents other health data, such as blood glucose levels, whose values ​​cause point 12 to not lie within the projection plane corresponding to a specific blood glucose value, as shown by point 12, which deviates from that specific blood glucose value. Therefore, Figure 1 The projection plane shown represents only one subspace of the multidimensional taxometrie. The way it is presented in the projection plane may depend on other subspaces of the multidimensional taxometrie that are not included in the projection plane.

[0034] The connections and relationships (referred to as "links") between health data elements can be represented by assigning appropriate presentation methods to each of these links. Figure 1 In this context, connections between points, for example, are indicated by lines connecting them. These connections could represent kinship or commonalities among health data elements, where the type of relationship can be expressed by color, line width, or line style. Furthermore, the way these connections are presented may depend on dimensions of the multidimensional classification system not included in the projection plane.

[0035] Point 13 might contain data on patient X's father, while point 14 might contain data on a professional group from a specific geographic area. The so-called individualized standard data (based on gender, height, weight, residence, behavioral patterns, etc.) can be compared both with the personalized, anonymized data of a single patient X and with anonymized data from comparable groups, in order to develop analyses and behavioral recommendations for these individuals and / or their doctors, fitness coaches, etc. Points 1 to 1+n (where n is a natural number) represent a large number of data sources from which patient X's information can be obtained. The 3D point representation can be designed using line widths and color schemes to make it visually easy to identify identical or similar features. This facilitates the application of scaling functions, allowing for targeted overlaying of similar data from different levels to form cluster analyses.

[0036] If a multidimensional classification system includes time in one dimension, then health data and the clusters to which they belong can be linked simultaneously in a time-based presentation, such as in a three-dimensional presentation that includes a timeline projection.

[0037] In a multidimensional classification system, health data elements represented by points do not necessarily have to be associated with a specific patient. Instead, they can be associated with a group of patients, or conversely, with a single body part of an individual patient. Here, various health data elements can exist in a hierarchical relationship, where one or more attributes of a health data element can be represented by health data elements at lower levels of the hierarchy. For example, a patient's overall health status can be represented by health data elements associated with a single organ of that patient. In this case, the multidimensional classification system can be hierarchically divided to classify a large number of health data elements according to its hierarchical structure. Classifying a large number of health data elements can also include selecting health data elements based on one or more selected levels in the classification system, thereby ignoring health data elements outside of those selected levels in the presentation graph.

[0038] A multidimensional classification system can also include spatial coordinate axes in a schematic or current two-dimensional or three-dimensional representation of patient X's body, and / or include time as another coordinate axis in the multidimensional classification system. This enables the representation of patient X's body, and, if necessary, the representation of patient X's physical development or body components and their development over time.

[0039] Metaphorically speaking, the ability to "travel" beneath the skin, through pathways like the intestines, arteries, or veins, and into organs (stomach, heart, etc.) also enables the sharing of specific portions of a database, such as with physicians from different specialties, or the addition of new data over time by incorporating data from sources like PET / CT scans or colonoscopies, to develop medical histories, treatment recommendations, and personalized behavioral patterns. This capability allows a single individual (or another individual within the algorithm) to explore changes over time (due to aging, etc.), predict potential deterioration, and identify the necessity of preventative measures (e.g., training programs to strengthen specific muscles or structures).

[0040] Algorithms such as the "zoom" function can achieve a progressively detailed visual presentation of specific parts of the body. For example, the user first sees the heart, then the details of the myocardium, then the cells and intracellular matrix, and finally the internal compartments of a single cell, such as mitochondria.

[0041] CT and / or MRI images can serve as the basis for the overall dataset and presentation, where information such as video images from colonoscopies can be integrated in an appropriate manner. Ultrasound images can also be integrated, and scans and models of universally available organs can be used to fill gaps in the individual-specific dataset, thus archiving a presentation that is as close as possible to the individual's likely movements.

[0042] Algorithms such as "follow the path" or "follow the path" commands can be used to "travel" along tubular structures like veins or intestines, and to observe their inner walls from the inside or identify abnormalities along their length, such as aneurysms or diverticulitis. For example, a computer mouse can be used as a control tool.

[0043] When the algorithm (“Comparison with Standard” algorithm) identifies the specificities of each organ (e.g., high fat cell content in the liver) by comparing an individual’s presentation with a healthy, level-averaged presentation, the additional algorithm (“Recommended Remedies”) will show options such as lifestyle changes (i.e., “reducing carbohydrate intake, reducing alcohol consumption”) and possible medications, and add options for further analysis to observe changes (e.g., adding pulsed ultrasound to monitor and measure liver fibrosis).

[0044] Treatment centers and specialists can be recommended and identified. Estimated costs and schedules for treatment can be provided. An additional algorithm (“Overall Benefit / Risk”) highlights the sites of impact and shows the potential and likely effects of such interventions or lifestyle changes on an individual's physical and mental health. Based on an individual's medication history and dietary intake, the likely short- and long-term effects on body structure, organ function, and the likely impact on an individual's mental and emotional well-being can be shown, with risks or side effects highlighted.

[0045] Figure 2 The example illustrates health data elements presented in point cloud form, which may originate from the health data of a patient suffering from arrhythmia. Arrhythmia can be caused by addictions such as alcohol, nicotine, or caffeine. Mineral imbalances can also cause arrhythmia. For example, mineral deficiencies (especially potassium and magnesium deficiencies) may induce or exacerbate arrhythmia. Other possible causes of arrhythmia include hyperthyroidism. Finally, high blood pressure, overweight, and congenital or acquired heart defects can also lead to arrhythmia. An individual's health data elements can be categorized according to these causes and entered into a multidimensional classification system. Figure 2 In this process, two of these causes will be entered along axes A and B into a two-dimensional representation diagram of a subspace representing a multidimensional classification system. Figure 2 In the multidimensional classification system, other subspaces not expanded by axes A and B are presented by coloring health data elements in such a way that, for example, the values ​​of the unpresented dimensions are encoded by the color values ​​of points in the projection plane.

[0046] The arbitrary selection of cluster colors, positions, sizes, and overlaps allows for inferences about possible treatment outcomes. Based on this, individualized comparative studies can be developed for each patient. For example, point cloud 23 could map all male patients with arrhythmias. Point cloud 21, for example, records patients with a specific body mass index (BMI). Comparisons between treatment methods can be derived from the intersection 22 of the overlapping points 21 and 23. This can be zoomed in on region 22 to access further relevant comparative data, which may stem from medical history or geographical specificity, for example.

[0047] As a result of scaling in region 22, exemplarily as in Figure 3As shown, data set 34 can be obtained, which is formed by overlapping data sets 31, 32, and 33 as a result. Here, data set 31 may include patients with atrial arrhythmias. In addition, arrhythmias of bradycardia (below 60 beats per minute) and tachycardia (above 100 beats per minute) may be distinguished, for example, by data set 32.

[0048] The underlying cause of cardiac arrhythmias is often insufficient energy in cardiomyocytes. In this case, the function of the cell's powerhouse (the so-called mitochondria) is disrupted. This dysfunction of the cell's powerhouse may be primarily caused by insufficient blood supply to the myocardium and hypoxia, but many prescription cardiac medications (such as beta-blockers, cholesterol-lowering drugs, or antibiotics) can also damage mitochondria.

[0049] Figure 3 The diagram illustrates data group 33 as an example of antibiotic-induced damage. Based on this, data group 34, formed by the overlap of data groups 31, 32, and 33, can be re-evaluated in conjunction with active medical treatment and / or personalized behavioral approaches. For example, it is possible to treat the patient using a so-called neurostimulator via a defined area in the ear. Therefore, the therapeutic efficacy of such an ear neurostimulator over time period t can be inferred from the role of electrocardiogram values ​​and / or personalized data (duration; stimulation intensity) present during that time period t. This reflects lifestyle factors (dietary habits, alcohol consumption, occupational activities (stress symptoms), step count, sleep behavior, etc.).

[0050] Data sets 35 and 36 exemplarily represent what is known as terrain formation. Here, health data elements are represented by corresponding heights based on their frequency of occurrence across various patients. If, in the representation, these heights are not based on the frequency of occurrence of health data elements representing all patients, but rather on the frequency of occurrence of a single patient X, then "hills" grow in the context of terrain formation. These hills may be constructed from the cumulative number of the same health data elements, such as those related to organs, blood counts, and ECG data, over time. Through the growth and formation of these so-called mountains and valleys, personalized health profiles can be developed over time, which can be compared with other health profiles in terms of contour, shape, height, peak value, etc. For this purpose, the color contours of time segments facilitate selection during cluster analysis.

[0051] Extracting individual-specific personal data can also be accomplished via terminology and / or image capture from the full text of treatment and / or medical examination reports, so that it can then be standardized based on syntactic and semantic rules (natural language processing).

[0052] Each personalized concept is weighted based on its identification and frequency of occurrence, such as the organs or body parts involved (i.e., real-time status, overall health history, personalized medical history, etc.). The extracted concepts reflect the semantic content describing the patient.

[0053] The image representation through maps is formulated using relevant concepts and can be constructed through the following steps.

[0054] First, a vector model of a multidimensional classification system is established, mainly covering concept extraction and weighting. Then, clustering, or cluster analysis, is performed, in which methods are used to discover similar structures within the dataset. Groups of "similar" objects found in this way are called clusters, and the assignment of these groups is called clustering.

[0055] By reducing the dimensions of a multidimensional classification system, not only can personalized anonymized data be compared and presented, but the corresponding personalized anonymized disease images and / or behavioral patterns and / or fitness data can also be identified.

[0056] By projecting the generated health data elements using a so-called mapping algorithm, a graphical representation of the health data elements and their relationships is created. This is followed by image analysis and presentation. An example of this is a map, which can, for instance, show specific areas of the body and can be scaled appropriately to match the actual phenomena and data. This helps to present the health data of multiple patients in 2D space (map) or 3D representation, allowing distances to reflect the similarity distance of each individual's personalized health data as accurately as possible.

[0057] Each point or point cloud (dataset) can correspond to an individual with patient data or to a group of people with exactly or very similar characteristics, thus allowing the location of points to be based on the similarity of these patients.

[0058] The more health data elements there are, and the higher the common similarity among them, the closer they are to each other, thus providing a basis for diseases, possible treatment methods and their success probabilities, and recommendations. The entire system can use a healthy body as a standard parameter. The distance between an individual's represented point and the standard parameter can be regarded as a measure of patient X's health status.

[0059] Calculate the distance between points associated with each patient and present it in a multidimensional diagram as an image or as a concept (N patients correspond to N-1 dimensions).

[0060] In a monochromatic cluster, identify patients (represented as points) who share common concepts / characteristics and are related by spatial proximity and similarity. Simultaneously, present the distance from the standard parameters of a healthy body, or the point cloud of a healthy body, as a reference point.

[0061] During projection, the system calculates the location of each cluster, or each point cloud.

[0062] Here, 3D rendering can also be used to represent the relationship between a subspace that is not rendered.

[0063] If patients with similar appearances (size, shape, color, etc.) within the same predefined cluster or point cloud are located on multiple so-called peaks (3D representations of the height differences in patient data or patient point clouds) or on a single peak, it means that the system has determined that some patients are also related to dimensions of other classification systems. Therefore, the correlation with dimensions of the classification system can be as follows: Figure 2 The data shown can be presented through the colors of health data elements, or through height modeling. Color schemes can also collaborate with height modeling. For example, green in the peak area could indicate a strong correlation with another classification dimension that is not presented elsewhere.

[0064] One of its key advantages is that all information can be presented in a single format, making it easy for each user to understand and observe their body, organs, and functions. Through anonymized presentation and so-called authorized open access, the user can input their personalized data into the overall system and make it available anonymously.

[0065] By utilizing the system according to the invention, each user benefits from the personalized, anonymous data of other users, enabling them to gain a deeper understanding of their own situation.

[0066] Technical or medical terms used in medical reports (often expressed in Latin or medical abbreviations) can be translated into everyday language (referred to here as conceptual language) and synchronized. Semantic databases can further transform this conceptual language into physician-specific or medically specific expressions. "Great saphenous vein (Venasaphena magna)" suddenly becomes a concrete visual image, rather than an incomprehensible Latin term.

[0067] To address this, artificial intelligence (AI) algorithms are used to connect different user groups and user levels. This allows certain elements, body parts, and / or organs, or their functions, to be incorporated into the human body representation in a way that is understandable to the average user. This, in turn, helps users input personal data into the system as real-time data when necessary (e.g., body temperature, headache, sudden sweating, date / time, etc.).

[0068] Visual demonstrations of an intervention can be observed, such as observing the closure of the great saphenous vein in a specific individual and its impact on that individual's blood circulation distribution, which significantly reduces pre-treatment explanation time. Ultimately, potential patients can see the effects of this intervention on blood circulation and how it improves the healing of chronic wounds in their legs.

[0069] However, although the implementation of the method and system according to the present invention is a medium- to long-term project and goal, it can still be easily improved in the short term compared to the prior art, in which medical information is scattered in paper form or generally incompatible digital formats in different clinics, hospitals and patients’ own file systems.

[0070] Current attempts, such as attempts to create electronic medical record systems (i.e., current attempts to improve existing technologies), have been considered in this invention because it provides a comprehensive framework and data structure that patients can understand, and also offers positivity and possibilities, as well as helping patients understand and clearly grasp the effects of various measures on their body and health.

[0071] The possibility of selecting the function of specific subsystems (such as the circulatory system or specific neural feedback loops) can also be integrated.

[0072] Therefore, making certain layers and systems transparent while highlighting others is another characteristic of this representation (or structured database).

[0073] Basic data such as age, gender, weight, and blood pressure, as well as simple visualizations (a zoomable "body map"), along with continuously updated existing and new data (e.g., electrocardiograms, data automatically collected from Withings and smartwatches), can also be processed.

[0074] In one particular embodiment of the invention, the method and system according to the invention can be combined with a method and system that couples newly acquired data and data analysis in a matched geographic visualization form on a graphical user interface (GUI) (e.g., on a remote client computer device) to obtain a new data model thereunder.

[0075] Databases containing patient-specific data can be used as references and for comparison.

[0076] Solutions to this task may also include: using an app to provide users with a clear visualization of their health status and enabling them to compare their own health data with reference values.

[0077] If individuals continuously collect data such as blood pressure and electrocardiograms (via health apps), simple data analysis can provide faster and more accurate diagnoses (e.g., differentiating between regular hypertension and systolic hypertension). Smartwatches or similar fitness watches can provide diagnoses such as "sinus rhythm" or "unknown" very quickly (e.g., after 30 seconds) via an app to these devices.

[0078] A comprehensive system may include the following components: Input (manual and automatic): • Blood tests, magnetic resonance imaging (MRT), positron emission tomography (PET), ultrasound, DNA testing, and electrocardiogram (ECG). • Data, such as weight, muscle mass, and body fat percentage values ​​provided by Withings scales. • Blood pressure measurement • Age, gender • Physical activity • Dietary habits • Other (cigarettes, alcohol, sugar) • Drugs and details • Input on mental health

[0079] It enables state-based visualization and comparison with best-in-class comparative data / standard parameters.

[0080] Based on this, projections can be customized as suggestions: • Sports, fitness, exercise • Nutrition • Medicine • Intervention • Treatment response (positive and negative) • etc

[0081] It can integrate communication interfaces with doctors, hospitals, medical institutions, equipment, and / or cloud platforms.

[0082] Building on this, patients (or users) can have a personalized app to manage their private health data, including medical and fitness data. This app serves as a replacement for unreliable paper documents or various electronic systems that only contain fragments of their medical history. With this app, all the information that is important to them is stored in one place.

[0083] The present invention also includes systems and methods for collecting, presenting, evaluating, and personalizing guidance from datasets derived from sleep data, sleepwalking, personalized dream experiences and their individual interpretations (multiple) cluster analyses, and personal descriptions of sensations of heat, food intolerances, headaches, limb pain, restlessness, emotional states, etc., which are obtained in real-time by combining existing data from smartwatches or fitness watches.

[0084] This system and methodology can also be applied to the investigation of mental illnesses and their causes, as well as to provide treatment recommendations. This allows for targeted exploration and treatment of so-called "occupational burnout." Furthermore, it enables a better understanding of the consequences and conclusions of so-called remote workplaces.

[0085] This invention is also particularly useful for further research into autoimmune diseases, neurological diseases (such as multiple sclerosis), and rare diseases (such as Asperger's syndrome, Barrett's esophagus, vascular dementia, osteochondritis, etc.), for which the necessary research input is not always adequate due to the small number of patients.

[0086] In particular, the scaling capabilities of data analysis on genetic influences, combined with geographic data analysis, population lifestyles, the type and extent of drug treatment, and the resulting intersections, are of paramount importance for personalized treatment and personalized behavioral approaches.

[0087] This also allows for the early identification of potential diseases, changes in the user's body, investigations into the risk of infectious disease transmission, and predictive models of the occurrence and spread of epidemics, enabling better real-time prevention and control of their occurrence and spread.

[0088] This approach presupposes the anonymization of the user data collected. Users can share personalized data by authorizing specific user groups (such as their family doctors).

[0089] Further advantageous designs of the present invention are listed in the following numbered embodiments (NAB):

[0090] NAB 1. A system for collecting, presenting, and evaluating personalized health data, the system comprising: One or more servers, configured to respond to data analysis requests, via... At least one personalized data acquisition unit, At least one personalized data processing unit, At least one personalized data presentation unit, and At least one data evaluation unit Receive, correlate, and evaluate the health data of individual A; A personalized input unit that can associate newly collected health data for individual A with individual A’s existing personalized health data; At least one data unit, which is used to process personalized health data of any number of users B through cluster analysis; At least one data unit is configured to correlate, analyze, present, transform, and unify the health data of individual A with the health data of user B.

[0091] NAB 2: A system for collecting, presenting and evaluating personalized health data as described in NAB 1, wherein a personalized dataset of at least one individual A is compared with a plurality of individuals B from a dataset (n+1) by cluster analysis, the comparison being performed based on 2D and / or 3D renderings of the real bodies of the individual individuals in the dataset (n+1).

[0092] NAB 3. A system for collecting, presenting and evaluating personalized health data as described in NAB 1 or NAB 2, wherein geographically based clusters are compared with health data, evaluated and action recommendations are generated.

[0093] NAB 4. A method for operating a system for collecting, presenting, and evaluating personalized health data, wherein, for the purpose of data analysis, the following is utilized: - At least one personalized data acquisition unit, - At least one personalized data processing unit, - At least one personalized data presentation unit, and - At least one data evaluation unit, - To receive, process, correlate, and / or evaluate the health data of individual A, and - Using at least one personalized input unit, link newly collected health data of individual A in real time with individual A's existing personalized health data. - Using at least one data unit, process personalized data of any number of users B through cluster analysis, and - Using at least one data unit, the health data of individual A and the health data of user B are correlated, analyzed, presented, transformed and / or unified, particularly for medical treatment and / or for developing personalized fitness plans.

[0094] NAB 5. A method according to NAB 4 for operating a system for collecting, presenting, and evaluating personalized health data, wherein at least one data analysis on real-body aspects is performed by zooming in on a region of interest from a digital image to compare the body’s genetic and / or pathogenic effects and / or physiological and / or psychological specificities with geographical and / or environment-specific and / or climatic aspects and / or with population lifestyles and / or individual or population clinical presentations, so as to ultimately establish the type and extent of drug treatment and develop personalized treatment and / or behavioral recommendations for individual A based on the resulting data intersection.

[0095] NAB 6. A method for operating a system for collecting, presenting and evaluating personalized health data as described in NAB 4 or NAB 5, wherein individual-specific personal data of individual A is obtained via terms and / or image records in the full text of treatment and / or medical examination reports, and is standardized based on syntactic and semantic rules.

[0096] NAB 7. A method in which treatment is performed via a defined area in a patient's ear using an otostimulator, wherein the otostimulator is used to treat for a duration t, and conclusions are drawn regarding the effect (duration, stimulation intensity) on electrocardiogram values ​​and / or personalized data from a patient archive file present during that time period t.

[0097] NAB 8. A computer program having program code for performing the method according to claims 4 to 7 when the computer program is implemented on a computer unit.

[0098] NAB 9. A computer-aided method for browsing large amounts of health data elements, the method comprising: Select a multidimensional classification system for health data elements; Classify a large number of health data elements so that each health data element is associated with a point in the space expanded by at least the first part of the first dimension of the multidimensional classification system; For each health data element, an association relationship is established between the first presentation method and the point in space that is associated with the respective health data element, wherein the associated first presentation method depends on one or more attributes of the health data element that are classified by at least the second part of the multidimensional classification system. For each relationship between related health data elements, a second presentation method is assigned to the respective relationship, wherein the assigned second presentation method depends on one or more attributes of the related health data elements, which are classified by at least the third part dimension of a multidimensional classification system, wherein the first part dimension, the second part dimension, and the third part dimension can overlap. The first and second presentation methods of the projection of the output space and the corresponding segments of the subset of health data elements and their relationships found in the output are triggered. Provide a user interface to modify the fragment and trigger the output of the modified fragment.

[0099] NAB 10. According to the method described in NAB 9, Among these, at least some of the numerous health data elements are in a hierarchical relationship, wherein one or more attributes of a health data element are represented by a lower-level health data element in the hierarchy, and The multidimensional classification system is divided into levels so that a large number of health data elements can be classified according to their hierarchical structure.

[0100] NAB 11. According to the method described in NAB 10, The classification of a large number of health data elements includes selecting health data elements based on one or more selected hierarchical levels in the classification system, thereby ignoring health data elements located outside of the one or more selected hierarchical levels in the output.

[0101] NAB 12. According to the method described in NAB 10 or NAB 11, The user interface includes providing a zoom function, which allows selecting one or more hierarchical levels and matching the first and second presentation modes of the output accordingly.

[0102] NAB 13. The method according to any one of NAB 9 to NAB 12, The first part of the dimension includes three dimensions, which are output in the form of a two-dimensional projection of space.

[0103] NAB 14. According to the method described in NAB 13, The first presentation method relies on up to three attributes of the health data elements as color values, allowing users to identify commonalities or similarities based on clusters of similar color schemes.

Claims

1. A method for operating a system for collecting, presenting, and evaluating personalized health data, wherein, In order to analyze the health data of individual A: - Collect the health data of individual A using at least one personalized data collection unit. - Using at least one personalized data processing unit, process, correlate, and / or evaluate the health data of individual A. - Using at least one clustering unit, cluster analysis is used to process large amounts of personalized data from user B. - Using at least one analysis unit, the health data of individual A and the health data of user B are correlated, analyzed, transformed, and / or unified, and - Present the results of the analysis unit using at least one personalized data presentation unit. The method is particularly useful in the field of medical treatment and / or in developing personalized fitness plans.

2. The method according to claim 1, in, The personalized data processing unit, the analysis unit, and / or the clustering unit perform the following operations: - Select a multidimensional classification system for the health data; - Classify a large number of health data elements such that each health data element is associated with a point in a space expanded by at least the first part of the dimensions of the multidimensional classification system; - For each health data element, establish an association relationship between the first presentation method and the point in space that is associated with the respective health data element, wherein the associated first presentation method depends on one or more attributes of the health data element that are classified by at least the second part of the dimensions of the multidimensional classification system.

3. The method according to claim 2, in, The data presentation unit triggers the output of a segment corresponding to the first presentation mode of the projection of the space and the output of the subset of health data elements found.

4. The method according to claim 2, in, The personalized data processing unit, the analysis unit, and / or the clustering unit also perform the following operations: - For each relationship between related health data elements, a second presentation method is assigned to the respective relationship, wherein the assigned second presentation method depends on one or more attributes of the related health data elements, which are classified by at least the third dimension of the multidimensional classification system, wherein the first dimension, the second dimension, and the third dimension can overlap. Furthermore, the data presentation unit performs the following operations: - Triggers a segment corresponding to the first and second presentation modes of the projection of the output space and the subset of health data elements identified in the output and their relationships.

5. The method according to any one of claims 2 to 4, in, At least a portion of the large number of health data elements are in a hierarchical relationship, wherein one or more attributes of a health data element are represented by a lower-level health data element in the hierarchy, and The multidimensional classification system is divided into levels so that the large number of health data elements can be classified according to their hierarchical structure.

6. The method according to claim 5, in, Classifying a large number of health data elements involves selecting health data elements based on one or more selected hierarchical levels in the classification system, thereby ignoring health data elements located outside of the one or more selected hierarchical levels in the output.

7. The method according to any one of claims 3 to 6, in, The data presentation unit provides a user interface for modifying the fragment and triggering the output of the modified fragment.

8. The method according to claim 7, in, The user interface includes providing a zoom function, based on which one or more hierarchical levels are selected and the output is matched accordingly with the first presentation mode and, if necessary, the second presentation mode.

9. The method according to claim 8, in, By zooming in on a region of interest from a digital image, at least one data analysis is performed on a real physical aspect of the individual A, wherein the genetic and / or pathogenic effects and / or physiological and / or psychological specificities of the individual A's body are correlated with geographical and / or environment-specific and / or climate-specific data analysis and / or with the lifestyle of the user group B and / or the clinical presentation of the individual A or the user B, in order to ultimately determine the type and extent of drug treatment and to develop personalized treatment and / or behavioral recommendations for the individual A based on the resulting data intersection.

10. The method according to any one of claims 2 to 9, in, The first part of the dimension includes three dimensions, which are output in the form of a two-dimensional projection of the space.

11. The method according to claim 10, in, The first presentation method relies on up to three attributes of the health data element as color values, thereby enabling the user to perceive commonalities or similarities based on clusters of similar color schemes.

12. The method according to any one of claims 1 to 9, in, Cluster analysis is used to establish a relationship between the personalized health data of individual A and the health data of user B, and Among them, the health data of individual A related to the health data of user B is presented as a 2D and / or 3D rendering of the actual body of individual A.

13. The method according to any one of claims 1 to 12, in, The clustering unit generates a geographic-based cluster for user B, and the analysis unit establishes a relationship between the geographic-based cluster and the health data of individual A, evaluates the relationship, and generates action suggestions for individual A based on the evaluation of the relationship.

14. The method according to any one of claims 1 to 13, in, In order to provide individual-specific health data for the individual A, the data acquisition unit evaluates and standardizes the terminology and / or image records in the full text of treatment and / or medical examination reports based on syntactic and semantic rules.

15. The method according to any one of claims 1 to 15, in, Using at least one personalized input unit, the newly collected health data of individual A in real time is associated with the existing personalized health data of individual A.

16. A system for collecting, presenting, and evaluating personalized health data using the method according to any one of claims 1 to 14, the system comprising: One or more servers, the servers being configured to, in response to requests for data analysis, via: At least one personalized data acquisition unit, At least one personalized data processing unit, At least one personalized data presentation unit, and At least one data evaluation unit Receive, correlate, and / or evaluate the health data of individual A; At least one clustering unit is used to process personalized health data of any number of users B through cluster analysis. At least one analysis unit is configured to unify, correlate, and / or present the health data of individual A and the health data of user B.

17. The system of claim 15, for implementing the method of claim 16, wherein the system is provided with a personalized input unit capable of associating newly collected health data for individual A with existing personalized health data of individual A.

18. A computer program product having program code for performing the method according to any one of claims 1 to 15 when the program code is implemented on a computer unit.

Images