Digital system for prioritizing admission and / or treatment of patient

Abstract

A digital prioritized admission / treatment system and corresponding apparatus and methods are disclosed. Priority admission / treatment systems, devices, and methods are based on an urgency rating of a patient's treatment. An artificial intelligence model may be used to determine an urgency rating. The invention further discloses a corresponding training method of artificial intelligence.

Description

Technical Field

[0001] The present invention relates to a digital system for optimizing the process of prioritizing admissions / treatments at a hospital based on the urgency rating of a patient's treatment. In addition, the present invention relates to a machine learning based method for predicting such an urgency rating and a method for training a corresponding model. Background Art

[0002] Rapidly and correctly assessing the urgency of a medical condition remains a huge challenge for all participating units in the health care system (e.g., for first responders, emergency units in hospitals, etc.), especially during global pandemic situations or in the aftermath of catastrophic events. In such situations, resources are often insufficient to treat all patients at once. Therefore, patients are ranked according to the urgency of their treatment. However, also in normal times, an effective system for prioritizing the admission of patients (e.g., in a hospital) is desired.

[0003] In situations where the patient is not physically present in the emergency room of a hospital, optimal health care may not be provided. This is because the respective medical staff is not aware of the patient’s potentially critical condition at home. The reason for this situation could be the pandemic and the corresponding lockdown, but it could also be the poor infrastructure that makes it difficult for patients to travel to hospitals.

[0004] Typically, a patient's readmission is highly unsatisfactory. The reason for this is that not only does the patient consume a portion of the already limited resources, but the fact that the patient is being readmitted indicates that these resources could have been avoided if the patient had been properly treated during his or her earlier hospitalization. Therefore, hospital medical staff are anxious to keep the patient's readmission rate and reduce it as low as possible. In some countries, a hospital's readmission rate is even considered a quality measure, which can result in the hospital being penalized if it is too high.

[0005] Efforts have been made to optimize the process of prioritizing admissions / treatments, such as providing web-based systems that are designed to automatically register and prioritize patients upon arrival at the emergency department. In addition, in order to avoid situations where admissions / treatments are required due to patient readmission, discharge toolkits have been developed to educate patients. These toolkits attempt to explain to patients possible future pain or events after surgery. For example, if a patient knows that a mild fever is most likely to occur within 1 week after surgery, the patient can be prepared and may not re-enter the emergency department due to a fever.

[0006] However, known systems for optimizing the priority of admission / treatment have major disadvantages. These systems only start with the admission / treatment of the patient when the patient arrives at the emergency department. This makes the process very inefficient for several reasons. First, emergency patients entering the emergency room lose valuable time on arrival because the registration and prioritization process must be completed first. Second, even if the process on arrival is optimized, the patient still loses very valuable early treatment time because he / she arrives only when the emergency has already occurred. In other cases, the patient enters the emergency room even though he / she may have been treated by a local doctor because the symptoms are not critical. On the other hand, usually, there may be patients with a high threshold for actually contacting an ambulance or a doctor. This is why they usually wait until their health condition becomes critical, resulting in a real emergency. In addition, prioritization of admission / treatment is usually performed at the emergency department level, which not only increases the workload of the corresponding medical staff, but also hinders the effective active treatment of symptoms.

[0007] In light of several shortcomings, improvements in admission / treatment prioritization are needed. Summary of the invention

[0008] This need is at least partially met by the system, apparatus and corresponding method of the independent claims of the present invention.

[0009] A first embodiment of the present invention is a computer-implemented method for training an artificial intelligence model for predicting an urgency rating of treatment, the method comprising: inputting training data into the artificial intelligence model to train the model, the training data comprising multiple data samples, wherein each data sample comprises: data describing a patient's health status; and an urgency rating of treatment associated with the data describing the patient's health status.

[0010] In some embodiments, the urgency rating may be defined as low, medium, or high. Additionally or alternatively, the urgency rating may be a value within a predefined interval / scale (e.g., on a scale from 1 to 10, with 1 being the lowest urgency rating and 10 being the highest urgency rating).

[0011] In the context of the present specification, the term "urgency rating of treatment" particularly indicates the need for treatment and the priority of treatment, especially compared to other patients. For example, a predicted urgency rating of treatment with a value of "low" or "zero" may indicate a non-urgent need for treatment or no need at all.

[0012] An artificial intelligence model trained according to this method can allow for accurate prediction of the urgency of a patient's treatment based on the patient's current health status.

[0013] In particular, this could enable a triage system based on data describing a patient's health status, without requiring the patient to enter a hospital.

[0014] According to the second embodiment, the training data may additionally or alternatively include: time series data of the patient, which is composed of a plurality of data describing the health status of the patient at different time points, each data being associated with an urgency rating of treatment.

[0015] Training an artificial intelligence model based on a patient's time series data may allow the model to predict the patient's future health status and / or future urgency rating. This may allow for increased accuracy of urgency predictions, since the model trained accordingly may analyze and predict trends in the patient's health status. Thus, negative / positive trends may be identified in advance, thereby improving the quality of treatment for the patient (e.g., valuable early treatment time may be gained in this way).

[0016] A third embodiment of the present invention is a computer-implemented method for predicting an urgency rating of a patient's treatment, the method comprising: using an artificial intelligence model to predict an urgency rating of the patient's treatment based on data describing the patient's health condition, wherein the artificial intelligence model is trained according to the method of the first embodiment.

[0017] Providing the method may allow the urgency of a patient's treatment to be accurately predicted based on the patient's current health status. For example, a patient with nonspecific chest pain after PCI may receive a higher urgency rating (ratio) than a patient with cold symptoms. Therefore, if the patient's current health status results in a prediction of a low urgency rating, for example, the patient may not be required to visit the emergency room, thereby avoiding inefficient use of resources. Therefore, triage is already performed from outside the hospital because it can be identified whether the patient requires faster or later treatment. This allows for improved and facilitated information flow, treatment arrangements, and patient transfers to hospitals. Therefore, the new triage system using the provided method reduces the fluctuating workload of the hospital, resulting in a better balanced workload and avoiding unnecessary triage situations in the emergency room.

[0018] In some examples, the data describing the patient's health condition includes or consists of sensor data.

[0019] According to a fourth embodiment, the method may additionally or alternatively include: predicting data describing the patient's future health status, and optionally using an artificial intelligence model to predict an urgency rating of the patient's treatment based on the data describing the patient's future health status, wherein the artificial intelligence model is trained according to the method of the second embodiment.

[0020] In some embodiments, when the artificial intelligence model has been additionally or alternatively trained on time series data of a patient consisting of multiple urgency ratings of the patient's treatment over time, the method can predict a future urgency rating of the patient's treatment without the step of predicting the future health condition.

[0021] Providing this method may allow accurate prediction of trends in a patient's health status to be considered. Thus, negative / positive trends may be identified in advance, thereby improving the quality of treatment for the patient (e.g., valuable early treatment time may be gained in this way).

[0022] In some embodiments, each value of the data describing the patient's health status can be associated with a set of adjustable weights. Before predicting the urgency rating of the patient's treatment, these weights are adjusted according to a selected prediction metric from a set of prediction metrics. Examples of such metrics can be, among others, a quality of life metric, a pain-related metric, a lethality metric, or a treatment effort metric.

[0023] Adjusting the data describing the health status before predicting the urgency rating can allow for improved efficiency in certain situations. For example, a rehabilitation hospital department may decide to select a quality of life metric to determine whether a certain patient has a high need for corresponding treatment after surgery to improve the recovery process and ultimately have a high quality of life.

[0024] A fifth embodiment of the present invention is a method for remote and / or wireless communication at a patient's portable user equipment, the method comprising: collecting data describing the patient's health status from at least one data source; sending the collected data describing the patient's health status to a server; and receiving from the server an urgency rating of treatment based on the patient's health status.

[0025] In some embodiments, the method may be performed only when executed by the patient, or it may be performed automatically. Where the method is performed automatically, the method may be performed periodically (e.g., once a day, once an hour, once a week). The frequency may be configurable by the patient, or may depend on the patient's current and / or past health status and / or urgency rating. The method may also be performed each time a change in the data describing the patient's health status is detected.

[0026] In some embodiments, the method also includes: receiving a treatment plan associated with the urgency rating from a server or a user device of a health care provider. For example, if the patient's urgency rating is low (e.g., 1 to 3), the associated treatment plan may include health advice (e.g., a diet with less fat). If the urgency rating is medium (e.g., 3 to 6), the associated treatment plan may include, for example, a medical prescription (a recommendation for a medical prescription) or an appointment scheduled at a corresponding doctor. A doctor or medical prescription (recommendation) may be selected based on the patient's health status (e.g., if the patient reports a headache, he may get a medical prescription (recommendation) for headache medication, and if the patient shows mild signs of heart problems, the selected doctor may be a cardiologist). However, if the urgency rating is high (e.g., 7 to 10), an ambulance call may be initiated to transfer the patient to a hospital, and the treatment plan may include information for the patient about the emergency situation and that the ambulance is on its way.

[0027] In the context of this specification, the term "health care provider" refers in particular to a person, group, agency or organization involved in and contributing to health care in general or emergency management in particular. Non-limiting examples of health care providers include medical personnel, hospital facilities, ambulances, rescue helicopters, personal physicians, etc.

[0028] Providing this method reduces the risk of patients entering critical health conditions because they can be frequently monitored. In addition, the threshold for patients to report their symptoms and contact doctors is reduced. Therefore, the overall process of prioritizing admission / treatment is improved because fewer emergencies occur, and patients will most likely not enter the emergency room unnecessarily. However, if an unforeseen accident occurs, which makes it necessary to transfer to the emergency room, less time is lost because the health care provider (e.g., the medical staff of the hospital) has been notified of the patient's arrival (e.g., because the server can warn the corresponding hospital accordingly). In addition, the health care provider may have been informed of the patient's health status and its expected arrival time, thereby improving the quality of treatment (e.g., because the server can warn the corresponding hospital accordingly).

[0029] A sixth embodiment of the present invention is a method for remote and / or wireless communication at a server, the method comprising: receiving data describing the patient's health status from the patient's portable user equipment; determining an urgency rating for treatment of the patient based on the data describing the patient's health status; the method also includes at least one of the following steps: sending the urgency rating of the treatment to the portable user equipment; sending the urgency rating of the treatment and the data describing the patient's health status to a user equipment of a health care provider for evaluating the urgency rating.

[0030] Providing this method may improve the overall admission / treatment prioritization process because the urgency rating of a patient's treatment can be determined without the patient being physically present in the emergency room.

[0031] According to the seventh embodiment, determining the urgency rating of treatment includes: predicting the urgency rating of treatment based on data describing the patient's health status according to the method of the third embodiment; additionally or alternatively, it may include: predicting the urgency rating of treatment according to the method of the fourth embodiment; adding the data describing the patient's health status and the predicted urgency rating to the patient's time series data indicating the patient's health status over time and the associated urgency rating; and retraining the artificial intelligence model according to the method of the second embodiment.

[0032] Using a specially trained AI model to determine urgency ratings improves the accuracy of urgency ratings, thereby improving the assessment of a patient's health status.

[0033] In some embodiments, when the server has sent the urgency rating to the user equipment of the healthcare provider for evaluating the urgency rating, the method may further include: receiving, from the user equipment of the healthcare provider; the evaluated urgency rating.

[0034] In some embodiments, when the server has received the assessed urgency rating, the method may further include: retraining the artificial intelligence model according to the training method of the first, second or subsequent embodiment using data describing the patient's health condition and / or the assessed urgency rating as an additional data sample.

[0035] In some embodiments, the server may assess the urgency rating in addition to or in lieu of the health care provider's assessment by determining data describing a health condition from a plurality of data describing a health condition of a previous treatment (from the same or other patients) that is similar to the data describing the patient's health condition (each associated with an urgency rating). The server may then compare the urgency rating associated with the similar data with the urgency rating predicted for the data describing the patient's health condition. If the difference between the two urgency ratings is acceptable (i.e., the difference is, for example, below a predefined threshold), the predicted urgency rating is accepted.

[0036] Providing these additional steps may increase the overall accuracy of urgency rating predictions, leading to an improved assessment of the patient's health status.

[0037] According to an eighth embodiment, the method may also include: before sending the urgency rating of the treatment and the data describing the patient's health condition to the user equipment of the health care provider, selecting a user equipment of the health care provider from a plurality of user equipments of the health care provider; wherein the user equipment of the health care provider is selected based on at least one of the following: the distance between the portable user equipment of the patient and the user equipment of the health care provider, the workload of the health care provider, the treatment specialization of the health care provider, and / or the treatment success rate of the health care provider for the health condition described by the data. The aforementioned treatment specialization and treatment success of the health care provider may also include or may be supplemented by the previous treatment history of the health care provider. For example, if the patient was previously treated at a specific health care provider (e.g., a hospital), the patient is most likely to be sent to the same health care provider by the system.

[0038] The user equipment of selecting a health care provider based on at least one of the mentioned criteria improves the treatment and assessment / evaluation of the patient's urgency level and health status. For example, in the case of predicting a high urgency level (i.e., needing to be transferred to the emergency department), selecting the health care provider (e.g., the corresponding hospital) closest to the patient can increase the patient's survival change. Several criteria can also be combined. For example, if two different user equipments of two different health care providers have the same distance from the patient, the treatment specialization of each health care provider can be regarded as an additional criterion for deciding which health care provider to select. If the patient's health status, for example, indicates a heart problem and one of the two health care providers is a cardiologist, the corresponding user equipment of the cardiologist is selected. The distance can be determined based on location data (e.g., GPS data) received from various user equipment.

[0039] A ninth embodiment of the present invention is a method for wireless communication at a user equipment of a health care provider, the method comprising: receiving an urgency rating of treatment and data describing a health status of a patient from a server; determining an assessed urgency rating of the treatment based at least on the data describing the health status of the patient; and sending the assessed urgency rating of the treatment to the server.

[0040] In some embodiments, the health care provider may also transmit a treatment plan based on the assessed urgency rating to a server and / or directly to the patient. Additionally or alternatively, the assessed urgency rating may also be sent directly to the patient.

[0041] Providing information about the urgency rating of a patient's treatment and corresponding data describing the health status to a user device of a health care provider improves the overall quality of treatment. Due to the improved information flow (i.e., convenient access to the patient's health records by medical personnel), health care providers can more effectively assess the health status of patients. As a result, fewer critically ill patients will be transported to the emergency room because these patients can be effectively preventively treated by sending the corresponding treatment plan to the patient (directly or via a server). In addition, due to the improved quality of treatment, the number of patients admitted to the emergency department whose health status does not require admission to the emergency department can be reduced.

[0042] According to a tenth embodiment, the data describing the health status of the patient comprises at least one of: a first set of health parameters and a second set of health parameters depending on the first set of health parameters, and / or a captured vital signal of the patient.

[0043] In some embodiments, the first set of health parameters may include or may be derived from at least one of the following: fever (e.g., temperature in C / F, duration of fever), pain (e.g., intensity, duration, frequency, location on a scale of 1-10), cough (dry / wet, painful, dyspnea), nausea / vomiting, dizziness, blindness, numbness, deafness, rash, injury, coloration, blood pressure, pulse, flatulence, diarrhea, and / or photographs. The first set of health parameters or a portion of these parameters may be collected based on, for example, general questioning by a general practitioner (e.g., it may be shown to the patient via a user interface of the portable user equipment, after which the patient enters data via the user interface (e.g., a touch screen)). The first set of health parameters may be collected directly from the patient's portable user equipment with the aid of sensors and / or may be requested from a database (e.g., a database from a general practitioner who has examined the patient). The first set of health parameters may also be collected with the aid of other suitable sensors (e.g., a fever monitor connected to the patient's portable user equipment).

[0044] In some embodiments, the second set of health parameters that depends on the first set of parameters may include or may come from at least one of the following: blood diagnosis (inflammation), tissue diagnosis (e.g., from an external laboratory), stool diagnosis, ultrasound examination, endoscopic images, X-ray images, magnetic resonance imaging, long-term blood pressure monitoring, pulse, fever (e.g., temperature in C / F, duration), pain (e.g., intensity, duration, frequency, location on a scale from 1 to 10), cough (dry / wet, painful, dyspnea), nausea / vomiting, dizziness, blindness, numbness, death, rash, injury and / or staining. The second set of health parameters can be collected based on specific questions, for example, conducted by a professional practitioner. The set of health parameters can depend on the first set of health parameters in a manner that selects related parameters of the second health parameters based on the value / result of the first health parameter. The second set of health parameters can be defined by a professional practitioner after the first set of health parameters have been received (e.g., via a communication device). The second set of health parameters may be collected directly from the patient's portable user equipment, for example, by means of a user interface, one or more sensors and / or may be requested from a database (e.g., from an external laboratory or professional practitioner that has previously collected X-ray images of the patient). The second set of health parameters may also be collected by means of other suitable sensors (e.g., a fever monitor connected to the patient's portable user equipment).

[0045] In some embodiments, captured vital signs (e.g., sensor data) may be collected via sensors. These sensors may be incorporated into a portable user equipment of the patient, or may be connected to or connectable to a portable user equipment. Examples of such sensors may be wearable devices such as smart watches, medical devices, medical implants (such as pacemakers), and / or pedometers. For example, the captured vital signs may correspond to ECG information measured by a smart watch, the number of steps walked measured by a step counter, or the number of heart beats per minute measured by a pacemaker.

[0046] Specifying data describing the patient's health status allows for a highly accurate representation of the patient's actual health status. Thus, the urgency rating can be predicted / assessed more accurately.

[0047] In some embodiments, the data describing the patient's health condition may also include GPS information regarding the patient's current location collected via a GPS sensor of the patient's portable user equipment.

[0048] Providing GPS information about the patient's location can increase the patient's chances of survival because not only can the nearest health care provider (e.g., paramedic or hospital) be identified, but the corresponding ambulance has accurate location information, thereby reducing transfer time. In addition, the health care provider is informed of the patient's emergency in advance and can make appropriate preparations.

[0049] In addition, the patient's GPS location can be used to extract information about physical activity. The speed derived from GPS characterizes the time the patient is not moving, walking, riding a bicycle, or using a vehicle. Changes in patient behavior monitored over longer periods of time allow detection of whether the patient's health has improved or deteriorated.

[0050] In this case of simple access to an activity tracker, AI could be trained to stabilize and improve physical activity and / or detect suspected deterioration in a patient in time to act before the heart is permanently damaged.

[0051] Any successful AI training relies on selecting easily obtainable and measurable output parameters that are sufficiently correlated with therapeutic success.

[0052] The eleventh embodiment of the present invention is a server, comprising a device for executing the method according to any one of embodiments 6 to 8 or embodiment 10, and embodiment 10 returns to any one of embodiments 6 to 8.

[0053] A twelfth embodiment of the invention is a portable user equipment for a patient comprising means for performing the method according to the fifth embodiment or the tenth embodiment referring back to the fifth embodiment.

[0054] A thirteenth embodiment of the present invention is a user equipment for a health care provider comprising means for performing the method according to the ninth embodiment or the tenth embodiment referring back to the ninth embodiment.

[0055] The user equipment of the healthcare provider may be designed as an app, a web-based application, a dedicated device, a computer program, etc.

[0056] The fourteenth embodiment of the present invention is a digital triage system for remote and / or wireless communication, wherein the system comprises: a server according to the eleventh embodiment; and at least one of: a portable user equipment for a patient according to the twelfth embodiment; and / or a user equipment for a health care provider according to the thirteenth embodiment.

[0057] A fifteenth embodiment of the present invention is a computer program including instructions which, when executed by a computer, cause the computer to execute the method according to any one of embodiments 1 to 10. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The following drawings are provided to support the understanding of the present invention:

[0059] Figure 1 is a diagram of a digital triage system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The following detailed description outlines possible exemplary embodiments of the invention.

[0061] Figure 1 A system 100 for prioritizing admission / treatment triage according to an embodiment of the present invention (i.e., a digital prioritization admission / treatment system) is shown. According to an embodiment of the present invention, the digital prioritization admission / treatment system 100 includes a server 120 and at least one portable user equipment 110 for a patient and / or at least one user equipment 130 for a health care provider. The digital prioritization admission / treatment system 100 and its components (server 120, portable user equipment 110 for a patient, user equipment 130 for a health care provider) can perform the methods described herein with respect to corresponding embodiments. A corresponding computer program can also be installed on the component, the computer program including instructions that, when executed by a computer (e.g., a processor of a component), cause the component to perform a corresponding method according to an embodiment of the present invention.

[0062] In a first step, a patient or a care provider of the patient may register with the digital prioritization admission / treatment system 100 via his portable user equipment (e.g., a smart phone, tablet, or smart watch capable of wireless communication) 110. Registration may be accomplished via an app installed on the user's portable user equipment 110 or a webapp (e.g., hosted on a server 120). When registering with the digital prioritization admission / treatment system 100, the patient may provide data describing his health status to the digital triage system 100. The data may be sent to the server and stored in a corresponding database. The data and / or the patient's identity may be anonymous. The patient's portable user equipment 110 may also be connected to one or more data sources (e.g., external databases, sensors (e.g., sensors incorporated into wearable devices such as smart watches, pedometers, pacemakers, or any other implants and / or medical devices)), from which data describing the patient's health status may be collected and / or updated according to a configured mode (i.e., only data for urgency rating prediction is collected when explicitly or periodically (e.g., daily) performed by the patient or whenever new data is available from one of the sources). In order to collect data describing the patient's health status, they can be asked to provide a first set of health parameters based on more general questioning. Based on the first set of health parameters, the patient can be asked to provide a second set of health parameters. These can be more specific, such as requested by a professional doctor. In addition, the patient can provide information about his current medication situation.

[0063] Once registered, data describing the patient's health status can be sent to the server 120 for determining the urgency rating of treatment based on the patient's health status. According to an embodiment of the present invention, the server 120 can use an artificial intelligence model trained to predict the urgency rating based on such data. The artificial intelligence model can be deployed on the server 120 or at another location where the server 120 can access the artificial intelligence model. The determined urgency rating can then be transmitted to the patient's portable user equipment 110. In this way, the patient obtains an accurate assessment of his current health status without actually being in the hospital or without having to overcome the threshold for the patient to contact the health care provider. It is also possible that the server is able to determine the patient's treatment plan based on data of previous patients with similar health status (possibly assessed by the health care provider) and treated according to a certain treatment plan (possibly created by the health care provider). In addition or alternatively, the server 120 can send the urgency rating and the corresponding data describing the patient's health status to the user equipment 130 of the health care provider. The server can determine the user equipment 130 of the health care provider to which the data is sent from a plurality of available user equipments 130 of the health care provider according to several criteria such as distance, treatment specialization of the health care provider, etc. Thus, the server 120 may categorize a plurality of available user equipment 130 of healthcare providers based on several criteria, and may therefore determine an ideal healthcare provider (eg, a medical practitioner or hospital) for the patient.

[0064] Where multiple portable user devices 110 of different patients are connected to the server, the server may determine urgency ratings from all patients and transmit a list sorted in descending order based on urgency rating to one or more connected user devices of the healthcare provider.

[0065] When the user equipment 130 of the health care provider (e.g., a laptop, tablet, smart phone, PC) receives the urgency rating and the data describing the health condition of the patient, the health care provider can evaluate the (correctness of) the urgency rating. The health care provider will analyze the data describing the health condition and check whether the health condition is as urgent as the rating indicates. The evaluated urgency rating can then be sent back to the server 120, which can allow the server 120 to retrain the artificial intelligence model (the urgency rating can generally refer to the same treatment, but additional urgency levels associated with different treatments can also be sent back to the server 120). In some examples, this reverse transmission can be omitted. When the artificial intelligence model is retrained on the evaluated urgency rating, this can allow the model to identify the correlation between certain health parameters and emergency treatments. This can lead to a more accurate determination of the patient's health condition and the corresponding urgency rating. The evaluated urgency rating can also be transmitted to the patient's portable user equipment 110 via the server 120 or directly from the user equipment 130 of the health care provider. In addition to the rating, a treatment plan can also be sent to the patient. In the case of a high urgency rating, the treatment plan may include transporting the patient to a corresponding hospital by ambulance or directly contacting the patient's doctor. In the case of a medium urgency rating, the treatment plan may include scheduling an appointment for the patient at a doctor. In the case of a low urgency rating, the treatment plan may only contain suggestions, such as a healthier diet.

[0066] An additional benefit of the present invention is that by monitoring and evaluating the patient's health status, conclusions can be drawn about the success of certain treatment plans. Assume that the patient's portable user equipment 110 sends data describing the patient's health status to the server 120, the server 120 predicts a high urgency rating, and the patient is transferred to the emergency department because the patient, for example, needs heart surgery. The system allows monitoring the development of the patient's health status even after leaving the hospital or recovering after surgery. If the health status described by the corresponding data transmitted to the server 120 and evaluated from the server 120 indicates that the patient feels better (for example, indicated by low pain indications or other vital signs such as a large number of counted steps), it can be assumed that the surgery has been effective. However, if the data indicates that the health status has not improved (as it should), the corresponding health care provider will note this and can call the patient or arrange an additional appointment.

[0067] Another benefit would be generated if the management of an insurance company or health care provider would participate in the system 100 for prioritizing admissions / treatments according to the invention, for example by accessing aggregated information that can be obtained from the system. For example, in low-load situations, the system 100 according to the invention could detect patients with predisposing symptoms earlier and would help detect critically ill patients who did not consult a doctor early enough to avoid serious consequences. This would avoid many emergency situations by preventive treatment. Management in a hospital could have an overview of costs, admission or readmission rates, and staff could plan treatments.

Claims

1. A computer-implemented method for training an artificial intelligence model for predicting an urgency rating of treatment, the method comprising: Input training data into the artificial intelligence model to train the model, the training data comprising a plurality of data samples, wherein each data sample comprises: Data describing the patient's health status; and An urgency rating for treatment associated with the data describing the patient's health condition.

2. The method according to the preceding claim, wherein: The training data also includes: The patient's time series data consists of a plurality of data describing the patient's health status at different time points, each data being associated with an urgency rating for the treatment.

3. A computer-implemented method for predicting an urgency rating for treatment of a patient, comprising: Using an artificial intelligence model to predict the urgency rating of the treatment for the patient based on data describing the patient's health condition, wherein the artificial intelligence model is trained according to the method of claim 1 or 2.

4. The method according to the preceding claim, further comprising: Using an artificial intelligence model to predict data describing the patient's future health status and predicting the urgency rating of the treatment for the patient based on the data describing the patient's future health status, wherein the artificial intelligence model is trained according to the method of claim 2.

5. A method for remote and / or wireless communication at a portable user equipment (110) of a patient, the method comprising: collecting data describing the patient's health status from at least one data source; sending the collected data describing the health condition of the patient to a server (120); and An urgency rating for treatment based on the health condition of the patient is received from the server (120).

6. A method for remote and / or wireless communication at a server (120), the method comprising: receiving data describing a health condition of the patient from a portable user equipment (110) of the patient; determining an urgency rating for treatment of the patient based on the data describing the health condition of the patient; The method further comprises at least one of the following steps: sending the urgency rating of the treatment to the portable user equipment of the patient (110); The urgency rating of the treatment and the data describing the health condition of the patient are sent to a user equipment (130) of a health care provider for evaluation of the urgency rating.

7. The method according to the preceding claim, wherein: Determining the urgency rating of the treatment includes: The method of claim 3 predicts the urgency rating of the treatment based on the data describing the health condition of the patient; and / or Predicting the urgency level of the treatment according to the method of claim 4; adding the data describing the health condition of the patient and the predicted urgency rating to time series data for the patient, the time series data indicating the health condition and associated urgency rating of the patient over time; and Retrain the artificial intelligence model according to the method of claim 2.

8. The method according to any one of the preceding claims 6 to 7, wherein: The method comprises: selecting a user equipment of a health care provider (130) from a plurality of user equipments (130) of health care providers before transmitting the urgency rating of the treatment and the data describing the health condition of the patient to the user equipment (130) of the health care provider; Wherein, the user equipment of selecting the health care provider (130) is based on at least one of the following: The distance between the patient's portable user equipment (110) and the health care provider's user equipment (130), the health care provider's workload, the health care provider's treatment specialization, and / or the health care provider's treatment success rate for the health condition described by the data.

9. A method for wireless communication at a user equipment (130) of a health care provider, the method comprising: receiving from a server (120) a rating of the urgency of treatment and data describing the patient's health condition; determining an urgency rating for the assessment of the treatment based at least on the data describing the health condition of the patient; and The assessed urgency rating of the treatment is sent to the server (120).

10. A method according to any one of the preceding claims, wherein: The data describing the patient's health condition includes at least one of the following: A first set of health parameters of the patient, a second set of health parameters depending on the first set of health parameters, and a captured vital signal.

11. A server (120) comprising means for performing the method according to any one of claims 6 to 8 or claim 10 when referring back to any one of claims 6 to 8.

12. A portable user equipment (110) for a patient comprising means for performing the method according to claim 5 or claim 10 when referring back to claim 5.

13. A user equipment (130) of a health care provider comprising means for performing the method according to claim 9 or claim 10 when referring back to claim 9.

14. A digital prioritization admission / treatment system (100) for remote and / or wireless communication, wherein: The system (100) comprises: The server (120) of claim 11; and at least one of: A portable user equipment (110) for a patient according to claim 12; A user device (130) for a healthcare provider according to claim 13.

15. A computer program comprising instructions which, when executed by a computer, cause the computer to perform the method according to any one of claims 1 to 10.

Images