Method for determining a patient's risk score

Abstract

The present disclosure generally relates to a computer-implemented method for updating a patient's treatment model. The present disclosure also relates to a corresponding computer system and computer program product.

Description

Technical Field

[0001] The present disclosure generally relates to a method implemented by a computer for determining a patient's risk score. The present disclosure also relates to a corresponding computer system and a computer program product.

Background Art

[0002] Over the past few decades, medical costs have increased rapidly, and various plans have been proposed to at least slow down the increase in such medical costs. Such plans may focus, for example, on implementing a higher threshold than the threshold when an individual receives appropriate treatment, and yet maintaining the quality of medical care within the medical system at a desirable level.

[0003] Alternatively, a physician, nurse, or any other form of skilled therapist or medical consultant may attempt to provide a recommendation to an individual for the purpose of causing a change in circumstances that may have a beneficial health impact on the individual, thereby reducing the risk that the individual must seek treatment within the medical system.

[0004] Some form of prior assessment of the individual is necessary to be able to determine when to treat a patient and when not to.

[0005] When evaluating an individual, such as a physician, nurse, or anyone assisting a patient, use the individual's experience, guidelines, and best practices to objectively define, as much as possible, the individual's current state and, in some cases, the recommended changes in circumstances of the treatment proposed for the individual. For example, a physician or therapist may maintain an advanced knowledge base but be human and may not be aware of the latest developments in the area and may not understand the individual's overall situation, such as all medical information relevant to the individual. Furthermore, the best practices currently available may, in some cases, refrain from providing an individual with an individual treatment.

[0006] Recently, digitized solutions have been introduced to assist physicians or therapists, significantly reducing the subjectivity in their decision-making while improving the "solution" of the best available practice, enabling physicians or therapists to make decisions based on more data. In addition, such digitized solutions can include any medical information related to an individual when defining the individual's current state.

[0007] An example of a digitized solution available for recommending situation changes is presented in Patent Document 1 (U.S. Patent Application Publication No. 2018 / 0165418). Patent Document 1 specifically discloses a system that collects situation data related to factors that cannot be denied as having the potential to affect an individual's health, in addition to data directly characterizing the individual's health. The collected factor data indicates the individual's health state over time and is used by the system to construct a vector of characteristics (a "health vector") that reflects it. The system may also evaluate the difference in the individual's health vector when the individual's health vector exists at different times and generates a change in the health vector. The system uses the individual's health vector and the change in the health vector to determine the individual's current health score. This characterizes the overall health of the individual at that time (e.g., a spectrum from a very healthy state to a very unhealthy state). The system further constructs a trend of the individual's health change ("health score trend") when the individual's health score changes over time by periodically generating a health score based on more recent health vector information. The system compares the individual's health score trend data with data reflecting the health score trends of people in approximately the same location (i.e., one or more population cohorts) and generates recommendations for actions or changes that an individual can perform, which not only have a high likelihood of improving the individual's health but also a high likelihood of being adopted by the individual, based on that comparison and the behavioral patterns of the compared cohorts.

[0008] However, the solution presented in Patent Document 1 has several general drawbacks. First, the solution presented in Patent Document 1 is of low accuracy in terms of individual evaluation, and ultimately, the physician / therapist may bypass the possible recommendations by the digitized solution and decide to "play it safe" and ensure the individual's satisfaction is in a secure state.

[0009] Second, the solution presented in Patent Document 1 is only applicable to general recommendations for individuals and does not focus at all on the actions that need to be taken when an individual is hospitalized or in need of actual treatment within the medical system. For this reason, the solution presented in Patent Document 1 will not solve the problem of increased medical costs, especially when an individual has to receive actual treatment within the medical system.

[0010] With the above in mind, there seems to be room for further improvement in the digitized solution for physicians, aiming to balance the reliability of evaluation and the quality of medical care with the overall intention of providing the individual with the most suitable type of treatment for their current health / situation.

Prior Art Documents

Patent Documents

[0011]

Patent Document 1

Summary of the Invention

[0012] According to one aspect of the present disclosure, the above is alleviated by a computer-implemented method implemented by a control unit to determine a patient's risk score. Here, the method includes, at the control unit, receiving a first set of personal parameters indicating the current or previous state of the patient; forming a personal patient model based on the first set of personal parameters using the control unit; determining, using the control unit, a degree of match between the personal patient model and each of a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score; selecting, using the control unit, at least one general patient model having a degree of match exceeding a predetermined threshold; and determining, using the control unit, the patient's risk score based on the at least one selected general patient model.

[0013] The overall concept of the present disclosure is to determine a patient's risk score, and the pre-assessment of the patient is used as the main input. Next, the risk score may be used within the medical system to provide the most appropriate treatment for the patient. Along with the present disclosure, the determination of the patient's risk score includes, compared with the prior art, not simply being based on the pre-assessment of the patient, but a process in which the data regarding the patient is collated with a plurality of different general patient models. The different general patient models are formed in advance, sometimes in close cooperation with experts in different fields. Here, the different general patient models may generally be considered to be related to the behavior and outcomes of different patients, for example, when not treated appropriately. Further, the different general patient models are typically not based on the knowledge of one patient, but on the general (typically anonymized) knowledge of a number of patients and the (combined) outcomes expected for such patients.

[0014] Accordingly, in accordance with the present disclosure, a patient's individual model (which depends on data collected for the patient) is collated with a plurality of different general patient models, and at least one general patient model having a degree of match exceeding a predetermined threshold is selected. Thus, instead of simply determining a patient's risk score based on a direct assessment of the patient, this scheme ensures that the patient's evaluation is put into the "big picture" by collating the patient's specific behavior with a "population" of patients who have presented / acted in a substantially similar manner.

[0015] Accordingly, according to the present disclosure, in order to determine a patient's risk score, it is possible to depend not only on an individual patient but also on the behavior of general patients. Thus, the advantages of this scheme include the possibility of reliably predicting a patient's expected future behavior and a way to optimally handle this possible behavior in order to minimize the patient's complications. The collation with different pre-specified general patient models may also be considered as a way to exclude possible variations in an individual's parameters for the patient. This is because such variations may have been previously determined to have little impact on the patient's future.

[0016] Accordingly, the present disclosure may aim to ensure that the quality of treatment provided to patients is improved while at the same time ensuring that "over-treatment" is reduced, thereby reducing the overall burden on the healthcare system. Furthermore, the present disclosure may be implemented in a very flexible manner and may, in some cases, ensure that "new" or "updated" general patient models can be introduced midway, taking into account newly identified "best practices".

[0017] Within the context of the present disclosure, the expression "set of parameters of an individual indicative of the current or previous state of a patient" needs to be interpreted broadly and should include any type of relevant information that has been collected or is being collected regarding the patient. Such information may include, for example, but is not limited to, the patient's vital signs, number of hospitalizations, test results, prescribed medications (e.g., data collected over a given period of time, from seconds / hours during different doctor consultations and / or hospitalizations to the patient's lifetime). Clinical data of the patient collected over a predetermined period may also be included. Additional information that may be relevant for use includes, for example, heart rate data, electrocardiogram (EKG / ECG) data, respiratory rate data, patient body temperature data, pulse oximetry data, and blood pressure data.

[0018] Of course, other parameters related to the patient are possible. For example, BMI, defecation inhibition ability, incontinence, visual risk areas of skin type, gender and age, malnutrition screening (MTS), mobility, other physical conditions, mental state, activities, perception, moisture of the patient's body parts, nutritional intake, friction and shear of the patient's body parts, body temperature, information regarding previous bedsores, perfusion (blood flow), diabetes, tissue perfusion and oxygenation, hygiene, hemodynamics, etc.

[0019] Preferably, the set of parameters of an individual may, in some embodiments, include at least one of an image and a video sequence of the patient. However, it is appropriate to enable a caregiver to input other information related to the patient, such as information related to the parameters listed above. The image and / or video may preferably be collected using, for example, a camera arranged to communicate with a control unit. Here, the control unit may apply, for example, an image processing scheme for extracting the parameters listed above. The image processing scheme may, in some embodiments, be configured to perform normalization using previously collected patient data.

[0020] Furthermore, in one embodiment, the expression "personal patient model", which includes the determination of a set of personal parameters for a patient, also needs to be interpreted broadly. However, in another embodiment, the personal patient model may be defined as a "receptacle" for the patient's personal parameters, for example, defined as a string of personal parameters, and in some cases, compiled according to a pre-defined standard to improve the matching with the general patient model.

[0021] Furthermore, the expression "control unit" needs to be interpreted broadly and may include any means for providing the computing power to execute the scheme according to the present disclosure. Therefore, as will be further considered in the detailed description of the present disclosure, the control unit (corresponding to any means for providing the processing power) may, in some cases, be implemented within the server, within the client device (e.g., a computer or a portable device), or shared between the server and the client device.

[0022] Preferably, in one embodiment of the present disclosure, the step of selecting includes the step of selecting the general patient model with the highest degree of match. For this reason, in some embodiments, one specific general patient model may be identified as the most relevant model, and the risk scoring is, in itself, based on this match. Such an implementation may be preferred in some embodiments, for example, when it is desirable to quickly determine the patient's risk score.

[0023] However, alternatively, it may be possible to determine a risk score based on the selection of a plurality of single general patient models, for example, based on a combination of at least two selected general patient models. In such embodiments, it may be desirable to assign a weight to each of the selected general patient models. Here, the weight may depend, for example, on the degree of match. As is clear, such an implementation may further improve with respect to the reliability of the determined risk score, but on the other hand, it may be slightly slower because it requires slightly more processing compared to the case where only a single general patient model is selected.

[0024] A predetermined threshold may be used in some embodiments to ensure that the match maintains at least a certain basic level. That is, if the match is insufficiently low, i.e., no actual match is produced when comparing an individual patient model with a plurality of different pre-defined general patient models, this information may be used to indicate that it is necessary to manually evaluate the patient's risk score through a physical examination without relying on this scheme. That being said, a low degree of match may also be considered as an indicator that the individual parameters indicating the patient's current or previous state are incorrect or otherwise unreliable, and that it may be appropriate to collect additional / new information about the patient before proceeding with the determination of the risk score.

[0025] In one embodiment of the present disclosure, the method further includes using a control unit to define low-risk, medium-risk, and high-risk categories, and using the control unit to assign a risk category to a patient by comparing the patient's determined risk score with pre-defined risk score ranges for the various categories. Of course, additional categories can be included, and the additional categories are within the scope of the present disclosure. Such additional categories may include, for example, an intermediate "elevated risk category" between the medium-risk category and the high-risk category. The use of risk categories may be useful, for example, to enable caregivers to obtain quick information regarding how to act in relation to a patient. Here, for example, the various categories may have been assigned to various actions that do not require interpretation of a "risk score number" previously (e.g., during training), (e.g., between 0 and 100, or defined in some other way). Thus, if a patient is determined to be in the high-risk category, the caregiver can act quickly to address the patient.

[0026] Therefore, in one embodiment of the present disclosure, the scheme further includes using a control unit to form a treatment proposed for a patient based on the selected patient risk category, where the proposed treatment may vary for each risk category. That is, in this scheme, instead of proposing a treatment for all risk categories, an exclusion is implemented to provide the proposed treatment only when it is "truly" necessary, and in some cases, providing treatment only to patients who truly need it can significantly reduce the overall cost of treatment, thus potentially reducing the overall burden on the healthcare system. It should be understood that the ranges of risk scores for the various categories may be dynamic, i.e., the ranges of risk scores may change over time or for the purpose of averaging the overall cost of providing optimal treatment to patients.

[0027] Preferably, the proposed treatment may include at least one of a "pre-treatment" for the patient or a treatment product / scheme for the patient. Within the context of the present disclosure, the expression "pre-treatment" may be any form of treatment provided to the patient, for example, before the onset of a difficult situation. Such pre-treatment may include everything from nutritional recommendations to hygiene instructions. Similarly, the expression "treatment product / scheme" needs to be interpreted broadly and may include any form or means suitable for use in connection with the active treatment of the patient, such as treating the patient's wound. With respect to wound products, by way of example, wound products may include, for example, wound dressings, bandages, topical applications, treatment methods in combination with certain types of wound dressings, and the like. Further, current or future treatment products / schemes are possible and within the scope of the present disclosure.

[0028] In some embodiments, the method further includes receiving, at a control unit, a second set of personal parameters indicative of the patient's condition after receiving the proposed treatment; using the control unit to determine an improvement in the patient's health based on the first and second sets of personal parameters; and using the control unit to compare the determined improvement in the patient's health with a predefined improvement in health defined for at least one selected general patient model.

[0029] According to the present disclosure, it may be possible to allow a time difference, for example, between 1 hour and 90 days, between the collection of the first set of personal parameters and the collection of the second set of personal parameters. However, the aforementioned time difference is merely an example, and the time difference may of course be shorter or longer than this. In one embodiment, it may be possible to allow the time difference to depend on the proposed treatment. Further, more sets of personal parameters than the first and second sets of personal parameters, such as a third set of personal parameters, may be used by the system, and in some cases, it should be further understood that the time difference between the times when the data is collected can be fixed or variable.

[0030] Furthermore, at least some of the general patient models may include associated health improvements. That is, in general patient models where there are (or are not) associated treatment recommendations / suggestions, expectations for the patient may be defined. Along this embodiment, it may be possible to compare how the patient actually responded to the proposed treatment as compared to the expected response (depending on the selected general patient model). Next, the comparison may be used to further develop the scheme according to the present disclosure. That is, in some embodiments, it may be possible to "validate" the selected general patient model, for example, when the patient's health improvement substantially corresponds to the pre-defined health improvement of the selected general patient model. Validation may in some cases include the step of updating the selected general patient model with additional data or fine-tuning.

[0031] However, even in situations where the patient's health improvement deviates (substantially) from the pre-defined health improvement of the selected general patient model, it may be equally useful to collect and store the patient's improvement situation. In such situations, for example, it may be possible to form a starting point (or a new general patient model). Here, the deviated health improvement may be considered a new situation as compared to what was previously expected.

[0032] The information collected regarding the patient may not only be used for updating / modifying / validating the general patient model. Rather, the overall scheme according to the present disclosure may be used to enable different institutions and / or organizations to evaluate each other. Therefore, in some embodiments, it may be desirable to ensure that the information collected regarding the patient is kept strictly anonymous.

[0033] In one embodiment, the step of updating / adjusting the general patient model may include applying a machine learning process. That is, instead of having a physician (or technician) form a new general patient model, the system itself may form such a model or a model iteration of a generally available patient model. For example, in some situations, if additional data is provided suggesting that different evaluations may be made in different situations, one general patient model may be subdivided into two (or more) sub-models. The machine learning process may, in some cases, be an unsupervised machine learning process, a supervised machine learning process, and / or based on a convolutional neural network (CNN) or a recurrent neural network (RNN). Additional implementations are possible and within the scope of the present disclosure.

[0034] According to another aspect of the present disclosure, there is further provided a computer-implemented method performed by a control unit to determine a patient risk score. Here, the method includes receiving, at the control unit, a first set of personal parameters indicative of the current or previous state of a patient; using the control unit to compare the first set of personal parameters with a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score; using the control unit to select at least the general patient model that is most optimal for the personal parameters; and determining the patient risk score based at least on the selected general patient model. This aspect of the present disclosure provides substantially the same advantages as those discussed above in connection with previous aspects of the present disclosure. That said, according to an aspect of the present disclosure, a slightly different approach is presented where personal parameters are directly compared with a plurality of different pre-defined general patient models without including a personal patient model. Such an implementation may be preferred in some situations, for example, when it is expected that the types of personal parameters are the same / nearly the same in all cases of collection.

[0035] According to yet another aspect of the present disclosure, there is provided a computer-implemented method performed by a control unit to reduce medical costs associated with a patient. Here, the method includes, at the control unit, receiving a first set of personal parameters indicative of the current or previous state of the patient; forming, using the control unit, a personal patient model based on the first set of personal parameters; determining, using the control unit, a degree of match between the personal patient model and each of a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score; selecting, using the control unit, at least one general patient model having a degree of match exceeding a predetermined threshold; determining, using the control unit, a risk score of the patient based on the at least one selected general patient model; defining, using the control unit, low-risk, medium-risk, and high-risk categories; assigning, using the control unit, a risk category to the patient by comparing the determined risk score of the patient with pre-defined risk score ranges of the various categories; and proposing, using the control unit, a treatment for the patient only if the patient is assigned to the high-risk category. Additionally, this aspect of the present disclosure provides substantially the same advantages as those discussed above in connection with the previous aspects of the present disclosure.

[0036] Furthermore, according to another aspect of the present disclosure, there is provided a computer system configured to determine a patient's risk score, the computer system comprising a control unit, the control unit being configured to receive a first set of personal parameters indicative of the patient's current or previous state, form a personal patient model based on the first set of personal parameters, determine a degree of match between the personal patient model and each of a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score, select at least one general patient model having a degree of match exceeding a predetermined threshold, and determine the patient's risk score based on the at least one selected general patient model. This aspect of the present disclosure offers substantially the same advantages as those discussed above in relation to the previous aspects of the present disclosure.

[0037] In a possible embodiment of the present disclosure, the computer system is a portable electronic device such as, for example, at least one of a "dedicated electronic device", a mobile phone, a tablet, etc. Alternatively, the computer system may be a computer (e.g., a laptop) equipped with the camera discussed above for acquiring an image or video sequence of the patient's wound. The computer system may be arranged to be operated, for example, by a caregiver.

[0038] In a preferred embodiment of the present disclosure, the computer system comprises a graphical user interface (GUI) configured to provide instructions to a caregiver for acquiring a first set of the patient's parameters. The GUI may then be configured to present information indicating the risk score and / or risk category in accordance with the processing steps discussed above.

[0039] According to yet another aspect of the present disclosure, there is provided a computer program product comprising a non-transitory computer-readable medium storing computer program means for operating a computer system configured to determine a patient's risk score. The computer system comprises a control unit. Here, the computer program product comprises code for receiving, at the control unit, a first set of personal parameters indicative of the current or previous state of a patient, code for forming, using the control unit, a personal patient model based on the first set of personal parameters, code for determining, using the control unit, a degree of match between the personal patient model and each of a plurality of different pre-defined general patient models, wherein each of the general patient models has a pre-defined patient risk score, code for selecting, using the control unit, at least one general patient model having a degree of match exceeding a predetermined threshold, and code for determining, using the control unit, the patient's risk score based on the at least one selected general patient model. Additionally, this aspect of the present disclosure provides substantially the same advantages as those discussed above in connection with the previous aspects of the present disclosure.

[0040] The control unit is preferably a microprocessor. Similarly, the computer-readable medium may be any type of memory device including a removable non-volatile random access memory, a hard disk drive, a floppy (registered trademark) disk, a CD-ROM, a DVD-ROM, a USB memory, an SD memory card, or a similar computer-readable medium known in the art.

[0041] Additional features and advantages of the present disclosure will become apparent when considering the appended claims and the following description. Those skilled in the art will understand that, without departing from the scope of the present disclosure, different features of the present disclosure can be combined to create embodiments other than those described below.

[0042] Various aspects of the present disclosure, including its particular features and advantages, will be readily apparent from the following detailed description and the accompanying drawings.

Brief Description of the Drawings

[0043]

Figure 1

Figure 2

Figure 3

Best Mode for Carrying Out the Invention

[0044] Here, the present disclosure will be further described in its entirety below with reference to the accompanying drawings showing the presently preferred embodiments of the present disclosure. However, the present disclosure may be embodied in many different forms and should not be construed as limited to the embodiments described herein. Rather, such embodiments are provided for the sake of completeness and totality and to fully convey the scope of the present disclosure to those skilled in the art. Similar reference characters refer to similar elements throughout.

[0045] Here, turning to the drawings, particularly FIG. 1, a computer system 100 configured to determine a patient's risk score is conceptually shown.

[0046] The computer system 100 includes a server 106 having some form of control unit 108 that provides computing power and is arranged to communicate with a database 110, and a client device 112 arranged for network communication with the server 106, such as using the Internet. In FIG. 1, the client device 112 is operated by a caregiver (not shown). However, for example, any user, such as any form of caregiver, may be permitted to operate the client device 112.

[0047] Network communication may be wired communication or wireless communication, including, for example, wired connections such as building LANs, WANs, Ethernet (registered trademark) networks, IP networks, etc., and wireless connections such as WLAN, CDMA, GSM (registered trademark), GPRS, 3G mobile communication, 4G mobile communication, 5G mobile communication, Bluetooth (registered trademark), infrared, etc.

[0048] As described in more detail in FIG. 2, the client device 112 shown as a mobile phone includes a graphical user interface (GUI) and a camera 204. The client device 112 also includes some form of control unit 206 that provides computing power. The GUI is preferably configured to present instructions and information to the caregiver, for example, to obtain an image of the patient 106 using the camera 204, to receive additional patient data entered by the caregiver, and to display information regarding the patient's risk score and / or the patient's risk category.

[0049] In addition to the control unit 108, the control unit 206 may include a general-purpose processor, an application-specific processor, a circuit including processing components, a group of distributed processing components, a group of distributed computers configured for processing, and the like. The processor may be any number of hardware components for performing data processing or signal processing, or for executing computer code stored in the memory, and may include such hardware components. The memory may be one or more devices for storing data and / or computer code for completing or facilitating the various methods described in this description. The memory may include volatile memory or non-volatile memory. The memory may include a database component, an object code component, a script component, or any other type of information structure for assisting with the various activities of this description. According to an exemplary embodiment, any distributed memory device or local memory device may be utilized with the systems and methods described in this description. According to an exemplary embodiment, the memory is communicatively connected to the processor (e.g., via a circuit or any other wired connection, wireless connection, or network connection) and includes computer code for executing one or more of the processes described herein.

[0050] Furthermore, in one embodiment, it is preferable to implement the computer system 100 as a cloud-based computing system. Here, the server 106 is a cloud server. Therefore, the computing power may be divided among a plurality of different servers (not shown), and the location of the servers should not be explicitly defined. As described above, the computing power may also be distributed between the server and the client device.

[0051] Other advantages of using cloud-based solutions include the achievement of inherent redundancy. That is, by applying a distributed approach not only to servers but also to users / operators, security can be improved. This is because it will usually not be possible to attack (either physically or by computer) a particular operating site that would hold both the server and the user / operator by prior art solutions.

[0052] During operation of computer system 100, referring further to FIG. 3, the process is initiated, for example, by a caregiver who provides, using the GUI of client device 112, a first set of personal parameters indicative of the current or previous state of a patient, which is received (S1) in turn by, for example, control unit 108 of the server and / or control unit 206 of client device 112.

[0053] Control unit 108 / 206 may then form a personal patient model based on the first set of personal parameters (S2). As described above, the personal patient model may, in some embodiments, be a pre-assessment of the patient, or in another embodiment, simply a data string or vector that holds the first set of personal parameters.

[0054] Next, the personal patient model is to be collated with a plurality of different pre-defined general patient models (S3). Here, each of the general patient models has a pre-defined patient risk score. The plurality of different pre-defined general patient models may, in some embodiments, be stored using database 110 and / or using a memory module including client device 112.

[0055] By matching between an individual patient model and a plurality of different pre - defined general patient models, the degree of match will be determined. The matching may be multi - dimensional matching in some embodiments. Here, a first set of an individual's parameters is matched with a number of different parameters associated with a plurality of different pre - defined general patient models. In some cases, the first set of an individual's parameters may not necessarily correspond to the parameters of a plurality of different pre - defined general patient models, and the plurality of different pre - defined general patient models may not necessarily hold the same type of parameters. For this reason, it may be necessary to match parameters in multiple dimensions to find a match. The degree of match should preferably take this into account and may include determining the Euclidean distance of different parameters in some embodiments.

[0056] When the degree of match is determined, at least one general patient model is selected (S4). However, there is a pre - condition for selecting only one or more general patient models having a degree of match exceeding a predetermined threshold. As described above, such a threshold is dynamic and may depend on the current implementation. Therefore, the range of the threshold is 0 - 100 (when the degrees of match are in a substantially the same range).

[0057] After selecting at least one general patient model, the risk score of the patient can be determined (S5). The determination of the risk score will be carried out based on at least one selected general patient model, but combinations of a plurality of selected general patient models may also be possible in some cases. In such an implementation, different general patient models may have different weights based on their individual degrees of match.

[0058] The risk score may, in some cases, be normalized between 0 and 100. Of course, other ranges are possible and are within the scope of the present disclosure. Further, the risk score may, in some cases, be used to determine a patient's risk category by allowing different ranges within the overall range of the risk score to correspond to different risk categories. In some embodiments, a risk score between 0 and 50 may correspond to a low risk category, a risk score between 51 and 75 may correspond to a medium risk category, and a risk score between 76 and 100 may correspond to a high risk category. The ranges provided are for illustrative purposes only. It may be desirable to provide some form of treatment to at least patients in the high risk category.

[0059] The present disclosure will enable a quick and effective determination of a patient's risk score in an efficient manner, which not only relies on data relevant to the patient but also includes a matching scheme with a plurality of predefined general patient models. Advantages of following this scheme include the possibility of reliably predicting a patient's expected future behavior and a way to optimally address this possible behavior to minimize the patient's complications. Matching with different predefined general patient models may also be considered a way to exclude possible variations in an individual's parameters for the patient. Such variations may, in some cases, have previously been determined to have little impact on the patient's future.

[0060] The control functions of the present disclosure may be implemented using an existing computer processor, or by a special-purpose computer processor for a suitable system, which is a computer processor incorporated for this or another purpose, or by a hardwired system. Embodiments within the scope of the present disclosure include program products that include a machine-readable medium that carries or has machine-executable instructions or data structures stored thereon. Such a machine-readable medium may be any available medium that can be accessed by a general-purpose or special-purpose computer or other machine equipped with a processor. By way of example, such machine-readable media include RAM, ROM, EPROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of machine-executable instructions or data structures and that can be accessed by a general-purpose or special-purpose computer or other machine equipped with a processor.

[0061] The figures may show an order, but the order of the steps may be different from that shown. Additionally, two or more steps may be performed simultaneously or partially simultaneously. Such variations will depend on the selected software system and hardware system and the designer's choices. All such variations are within the scope of the present disclosure. Similarly, the software implementation may be achieved using standard programming techniques using rule-based logic and other logic to perform various connection steps, processing steps, comparison steps, and decision steps. Further, even though the present disclosure has been described with reference to its particular exemplary embodiments, many different changes, modifications, etc. will become apparent to those skilled in the art.

[0062] Furthermore, variations of the disclosed embodiments can be understood and achieved by those skilled in the art when implementing the present disclosure from consideration of the drawings, the disclosure, and the appended claims. Further, in the claims, the term "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. The invention disclosed in this specification includes the following. [Aspect 1] A computer-implemented method performed by a control unit to determine a patient's risk score, the method comprising: - receiving, by the control unit, a first set of personal parameters indicative of the current or previous state of the patient; - forming, using the control unit, a personal patient model based on the first set of personal parameters; - determining, using the control unit, a degree of match between the personal patient model and each of a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score; - selecting, using the control unit, at least one general patient model having a degree of match exceeding a predetermined threshold; - determining, using the control unit, the risk score of the patient based on the at least one selected general patient model. [Aspect 2] The method according to aspect 1, wherein the selecting step includes selecting the general patient model having the highest degree of match. [Aspect 3] The method according to aspect 1, wherein the risk score is determined based on a combination of at least two selected general patient models. [Aspect 4] The method according to aspect 3, wherein each of the at least two selected general patient models has a weight applied when determining the risk score. [Aspect 5] The method according to any one of aspects 1 to 4, wherein the personal parameters include clinical data of the plurality of patients collected over a predetermined period. [Aspect 6] The method according to aspect 5, wherein the clinical data includes at least the patient's vital signs, number of hospitalizations, test results, and prescribed medications. [Aspect 7] The method according to aspect 6, wherein the patient's vital signs include at least one of heart rate data, electrocardiogram (EKG / ECG) data, respiratory rate data, patient body temperature data, pulse oximetry data, and blood pressure data. [Aspect 8] - defining, using the control unit, low-risk, medium-risk, and high-risk categories; - using the control unit to assign a risk category to the patient by comparing the determined risk score of the patient with pre-defined risk score ranges of the various categories; the method according to any one of Aspects 1 to 7, further comprising the step of [Aspect 9] - using the control unit to form a treatment proposed for the patient based on a selected patient risk category, the proposed treatment being different for each risk category; the method according to Aspect 8, further comprising the step of [Aspect 10] The method according to Aspect 9, wherein the treatment for the patient is formed only when the patient is assigned to the high-risk category. [Aspect 11] - receiving, at the control unit, a second set of personal parameters indicative of the state of the patient after receiving the proposed treatment; - using the control unit to determine the health status of the patient based on the first and second sets of personal parameters; - using the control unit to compare the determined improvement in the health of the patient with a pre-defined improvement in health defined for the at least one selected general patient model; the method according to any one of Aspects 9 and 10, further comprising the step of [Aspect 12] - further comprising the step of updating at least one of the general patient models based on a combination of the determined individual patient model and the result of the comparison of the improvement in health; the method according to Aspect 11. [Aspect 13] The method according to Aspect 12, wherein the step of updating at least one of the general patient models includes applying a machine learning process. [Aspect 14] The method according to Aspect 13, wherein the machine learning process is an unsupervised machine learning process. [Aspect 15] The method according to Aspect 13, wherein the machine learning process is a supervised machine learning process. [Aspect 16] The method according to Aspect 13, wherein the machine learning process is based on a convolutional neural network (CNN) or a recurrent neural network (RNN). [Aspect 17] A computer-implemented method performed by a control unit for determining a risk score of a patient, the method comprising - a step of receiving, by the control unit, a first set of personal parameters indicating the current or previous state of the patient; - a step of using the control unit to compare the first set of personal parameters with a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score; - a step of using the control unit to select the general patient model that is optimal for at least the personal parameters; - a method comprising a step of determining the risk score of the patient based on at least the selected general patient model. [Aspect 18] A computer-implemented method performed by a control unit to reduce medical costs associated with a patient, the method comprising: - a step of receiving, by the control unit, a first set of personal parameters indicating the current or previous state of the patient; - a step of using the control unit to form a personal patient model based on the first set of personal parameters; - a step of using the control unit to determine the degree of match between the personal patient model and each of a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score; - a step of using the control unit to select at least one general patient model having a degree of match exceeding a predetermined threshold; - a step of using the control unit to determine the risk score of the patient based on the at least one selected general patient model; - a step of using the control unit to define low-risk, medium-risk, and high-risk categories; - a step of using the control unit to assign a risk category to the patient by comparing the determined risk score of the patient with pre-defined risk score ranges of the various categories; - a method comprising a step of proposing treatment for the patient only if the patient is assigned to the high-risk category, using the control unit. [Aspect 19] A computer system configured to determine a risk score of a patient, the computer system comprising a control unit, the control unit being: - receiving a first set of personal parameters indicative of the current or previous state of the patient; - forming a personal patient model based on the first set of personal parameters; - determining a degree of match between the personal patient model and each of a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score; - selecting at least one general patient model having a degree of match exceeding a predetermined threshold; - determining the risk score of the patient based on the at least one selected general patient model, a computer system configured to perform. [Aspect 20] A computer program product comprising a non-transitory computer-readable medium storing computer program means for operating a computer system configured to determine a patient's risk score, the computer system comprising a control unit, in the computer program product, the computer program product comprising - code for receiving, at the control unit, a first set of personal parameters indicative of the current or previous state of the patient; - code for forming, using the control unit, a personal patient model based on the first set of personal parameters; - code for determining, using the control unit, a degree of match between the personal patient model and each of a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score; - code for selecting, using the control unit, at least one general patient model having a degree of match exceeding a predetermined threshold; - code for determining, using the control unit, the risk score of the patient based on the at least one selected general patient model, a computer program product.

Claims

1. A computer-implemented method, implemented by a control unit, for determining a risk score of a patient, the method comprising: - receiving, by the control unit, a first set of personal parameters indicative of the current or previous state of the patient; - forming, using the control unit, a personal patient model that is a data string or vector holding the first set of personal parameters; - determining, using the control unit, a degree of match between the personal patient model and a number of different parameters associated with each of a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score; - selecting, using the control unit, at least one general patient model having a degree of match exceeding a predetermined threshold; - determining, using the control unit, the risk score of the patient by collating the first set of personal parameters with the selected at least one general patient model, each of the general patient models being pre-formed and corresponding to a population of similar patients.

2. The method according to claim 1, wherein the selecting step comprises selecting the general patient model having the highest degree of match.

3. The method according to claim 1, wherein the risk score is determined based on a combination of at least two selected general patient models.

4. The method according to claim 3, wherein each of the at least two selected general patient models has a weight applied when determining the risk score.

5. The method according to any one of claims 1 to 4, wherein the personal parameters include clinical data of a plurality of the patients collected over a predetermined period.

6. The method according to claim 5, wherein the clinical data includes at least patient vitals, number of hospitalizations, test results and prescribed medications.

7. The method according to claim 6, wherein the patient vitals include at least one of heart rate data, electrocardiogram (EKG / ECG) data, respiratory rate data, patient body temperature data, pulse oximetry data and blood pressure data.

8. - Using the control unit, defining categories of low risk, medium risk, and high risk; - Using the control unit, assigning a risk category to the patient by comparing the determined risk score of the patient with pre-defined risk score ranges of the various categories, the method according to any one of claims 1 to 7, further comprising.

9. - Receiving, at the control unit, a second set of personal parameters indicative of the state of the patient after the patient has received a treatment proposed for the patient based on a selected patient risk category; - Using the control unit, determining the health state of the patient based on the first and second sets of personal parameters; - Using the control unit, comparing the determined improvement in the health of the patient with a pre-defined improvement in health defined for the selected at least one general patient model, the method according to claim 1, further comprising.

10. - Further comprising updating at least one of the general patient models based on a combination of the result of the comparison of the determined individual patient model with the improvement in health, the method according to claim 9.

11. The step of updating at least one of the general patient models comprises applying a machine learning process, the method according to claim 10.

12. The machine learning process is an unsupervised machine learning process, the method according to claim 11.

13. The machine learning process is a supervised machine learning process, the method according to claim 11.

14. The machine learning process is based on a convolutional neural network (CNN) or a recurrent neural network (RNN), the method according to claim 11.

15. A computer system configured to determine a risk score of a patient, the computer system comprising a control unit, the control unit comprising: - Receiving a first set of personal parameters indicative of the current or previous state of the patient; - Forming an individual patient model that is a data string or vector holding the first set of personal parameters; - A step of determining a degree of match between an individual patient model and a number of different parameters associated with each of a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score. - A step of selecting at least one general patient model having a degree of match exceeding a predetermined threshold. - A step of determining the risk score of the patient by collating the first set of the individual's parameters with the at least one selected general patient model, each of the general patient models being pre-formed and corresponding to a population of similar patients. A computer system configured to perform the steps. [

16. ] A computer program comprising a non-transitory computer-readable medium storing computer program means for operating a computer system configured to determine a patient's risk score, the computer system comprising a control unit. In the computer program, the computer program - Code for receiving, at the control unit, a first set of individual parameters indicative of the current or previous state of the patient. - Code for forming, using the control unit, an individual patient model that is a data string or vector holding the first set of individual parameters. - Code for determining, using the control unit, a degree of match between the individual patient model and a number of different parameters associated with each of a plurality of different pre-defined general patient models, each of the general patient models having a pre-defined patient risk score. - Code for selecting, using the control unit, at least one general patient model having a degree of match exceeding a predetermined threshold. - Code for determining, using the control unit, the risk score of the patient by collating the first set of the individual's parameters with the at least one selected general patient model, each of the general patient models being pre-formed and corresponding to a population of similar patients. The computer program includes the code.

Images