Embodiments of the present disclosure relate to a medical support system for patient treatment, a medical support method for patient treatment, and a machine readable medium to execute the medical support method. Embodiments of the present disclosure relate particularly to medical decision making using artificial intelligence (AI).

In today’s healthcare delivery, for example in hospitals and through ambulance services, it is increasingly difficult to find the optimal treatment for a patient. In particular, there is an increasing challenge to identify the most effective treatment for a patient as well as to reduce costs and achieve greater efficiency. These difficulties are due, at least in part, to rising cost pressures, an increasing number of treatment options, and increased information availability. It is therefore desirable to identify optimal treatments, minimize a treatment time and reduce medical costs.

In light of the above, a medical support system for patient treatment, a medical support method for patient treatment, and a machine readable medium to execute the medical support method are provided. It is an object of the present disclosure to improve identification of a patient condition and to perform optimal treatment. It is another object of the present disclosure to minimize a treatment time and/or reduce medical costs.

The objects are solved by the features of the independent claims. Preferred embodiments are defined in the dependent claims. According to an independent aspect of the present disclosure, a medical support system for patient treatment is provided. The medical support system includes a reception module configured to receive sensor data indicative of one or more physiological parameters of a patient and external data indicative of external circumstances relating to the patient; and an artificial intelligence module configured to analyze the sensor data and the external data, wherein the artificial intelligence module is further configured to provide a medical support function at least based on the analysis of the sensor data and the external data.

According to some embodiments, which can be combined with other embodiments described herein, the artificial intelligence module may be configured to implement a machine learning algorithm. For example, the artificial intelligence module may implement a neural network to analyze the sensor data and the external data in order to provide the medical support function. According to some embodiments, which can be combined with other embodiments described herein, the medical support system may further include a communication module configured to receive the external data from one or more external devices. The communication module may further be configured to receive sensor data from at least one sensor, e.g. a sensor of at least one active implant. An active implant is a medical device manufactured to actively replace, enhance or support a missing or damaged biological structure. The active implant relies on a power source not provided by the body or gravity and is designed to be introduced into the body of a human or an animal.

Furthermore, the communication module can be configured to receive external data from the at least one sensor and/or to receive sensor data from the one or more external devices. In addition, it is possible to exchange data (sensor data, external data, etc.) between the active implant and the communication module, regardless of whether the at least one active implant includes a sensor. The at least one active implant can be designed, among other, as a cardiac pacemaker, a defibrillator or a neurostimulator, in particular as a neuro spinal cord stimulator (Neuro SCS). In addition, the one or more external data and/or sensor data can be influenced or generated by neurostimulation, in particular by the Neuro SCS.

According to some embodiments, which can be combined with other embodiments described herein, the one or more external devices may be selected from the group including (or consisting of) a mobile terminal, a server, a wearable, a smart device, a smart home, a vehicle, a mobility assistance device or mobility aid, and combinations thereof.

According to some embodiments, which can be combined with other embodiments described herein, the external data may include at least one of movement data of the patient; location data of the patient; environmental data at a location of the patient; seasonal data; calendar data of the patient; one or more user profiles of the patient; habit data of the patient; and nutrition data of the patient. According to some embodiments, which can be combined with other embodiments described herein, the reception module may be configured to receive the external data based on a current location and/or at least one previous location of the patient.

According to some embodiments, which can be combined with other embodiments described herein, the medical support function may be selected from the group including (or consisting of) medical decision-making and medical treatment of the patient.

According to some embodiments, which can be combined with other embodiments described herein, the medical support system may be configured for cardiology diagnostics, neurological diagnostics and/or process monitoring.

According to some embodiments, which can be combined with other embodiments described herein, the medical support system may further include at least one output device. The medical support system may be configured to control the at least one output device to output information indicative of the analysis of the sensor data and the external data. According to some embodiments, which can be combined with other embodiments described herein, the at least one output device may be selected from the group including (or consisting of) a display device and an acoustical device. According to some embodiments, which can be combined with other embodiments described herein, the medical support system may further include a control module configured to control one or more medical treatment devices based on the analysis of the sensor data and the external data. According to some embodiments, which can be combined with other embodiments described herein, the control module may be configured to initiate and/or change a treatment of the patient by the control of the one or more medical treatment devices coupled to or connected to the medical support system. According to some embodiments, which can be combined with other embodiments described herein, the medical support system for patient treatment, comprises a reception module configured to receive sensor data SD indicative of one or more physiological parameters of a patient and external data ED indicative of external circumstances relating to the patient; and an artificial intelligence module configured to analyze the sensor data SD and the external data ED, wherein the artificial intelligence module is further configured to provide a medical support function based on the analysis of the sensor data SD and the external data ED, wherein the medical support system further comprises a communication module configured to receive the external data ED and/or the sensor data SD from one or more external devices and/or from one or more sensors, wherein the one or more external devices are selected from the group consisting of a mobile terminal, a server, a wearable, a smart device, a smart home, a vehicle, and a mobility assistance device. Furthermore, the reception module is configured to receive the external data ED based on a current location and/or at least one previous location of the patient, and the medical support system further comprises a control module configured to control one or more medical treatment devices based on the analysis of the sensor data SD and the external data

ED, and the control module is configured to initiate and/or change a treatment of the patient by the control of the one or more medical treatment devices. Thus, the external devices allow the location to be determined in a simple manner, so that the location-dependent transmission/reception of the data is efficiently possible. Furthermore, due to the location-sensitive data processing, movement of the patient is encouraged and, at the same time, its effects on the patient's condition can be evaluated.

According to some embodiments, which can be combined with other embodiments described herein, the medical support system may further include, or be connected/connectable, to one or more sensors associated with the patient. The one or more sensors may be configured to detect the one or more physiological parameters and provide the sensor data to the reception module.

According to another independent aspect of the present disclosure, a medical support method for patient treatment is provided. The medical support method includes receiving sensor data indicative of one or more physiological parameters of a patient and external data indicative of external circumstances relating to the patient; analyzing, by an artificial intelligence module, the sensor data and the external data; and providing a medical support function at least based on the analysis of the sensor data and the external data. Embodiments are also directed at systems for carrying out the disclosed methods and include system aspects for performing each described method aspect. These method aspects may be performed by way of hardware components, a computer programmed by appropriate software, by any combination of the two or in any other manner. Furthermore, embodiments according to the invention are also directed at methods for operating the described system. It includes method aspects for carrying out every function of the system.

According to another independent aspect of the present disclosure, a machine-readable medium is provided. The machine-readable medium includes instructions executable by one or more processors to implement the medical support method for patient treatment of the embodiments of the present disclosure. The (e.g. non-transitory) machine readable medium may include, for example, optical media such as CD-ROMs and digital video disks (DVDs), and semiconductor memory devices such as Electrically Programmable Read-Only Memory (EPROM), and Electrically Erasable Programmable Read-Only Memory (EEPROM). The machine- readable medium may be used to tangibly retain computer program instructions or code organized into one or more modules and written in any desired computer programming language. When executed by, for example, one or more processors such computer program code may implement one or more of the methods described herein. According to another independent aspect of the present disclosure, a medical support system for patient treatment is provided. The medical support system includes one or more processors; and a memory (e.g. the above machine-readable medium) coupled to the one or more processors and comprising instructions executable by the one or more processors to implement the medical support method for patient treatment of the embodiments of the present disclosure.

So that the manner in which the above recited features of the present disclosure can be understood in detail, a more particular description of the disclosure, briefly summarized above, may be had by reference to embodiments. The accompanying drawings relate to embodiments of the disclosure and are described in the following:

Fig. 1 shows a schematic view of a medical support system for patient treatment according to embodiments described herein; Fig. 2 shows a schematic view of a medical support system receiving physiological data and external data according to embodiments described herein; and

Fig. 3 shows a flow chart of a medical support method for patient treatment according to embodiments described herein. Reference will now be made in detail to the various embodiments of the disclosure, one or more examples of which are illustrated in the figures. Within the following description of the drawings, the same reference numbers refer to same components. Generally, only the differences with respect to individual embodiments are described. Each example is provided by way of explanation of the disclosure and is not meant as a limitation of the disclosure. Further, features illustrated or described as part of one embodiment can be used on or in conjunction with other embodiments to yield yet a further embodiment. It is intended that the description includes such modifications and variations. Nowadays it is increasingly difficult to find the optimal treatment for a patient. These difficulties are due, at least in part, to rising cost pressures, an increasing number of treatment options, and increased information availability.

The embodiments of the present disclosure address the above challenges by analyzing a combination of physiological data and non-physiological in an artificial intelligence module to determine a condition of the patient. The analysis of physiological data and non- physiological data enables an improved medical support function. In particular, a sensitivity and/or specificity of the AI-based medical support system can be significantly increased, thereby expanding an applicability of the medical support system to medical issues.

Fig. 1 shows a schematic view of a medical support system 100 for patient treatment according to embodiments described herein. The medical support system 100 includes a reception module 110 configured to receive sensor data SD indicative of one or more physiological parameters of a patient 1 and external data ED indicative of external circumstances relating to the patient 1; and an artificial intelligence module 120 configured to analyze the sensor data SD and the external data ED, wherein the artificial intelligence module 120 is further configured to provide a medical support function for the patient 1 based on the analysis of the sensor data SD and the external data ED. In some embodiments, the medical support function is a medical decision-making function and/or a medical treatment function. As an example, the physical activity of a heart failure patient depends not only on the current status of the heart failure, but also on the current weather and season. In very hot or cold weather or in the dark season, the patient is less likely to spend time outdoors than in more favorable weather or lighter seasons. The medical support system 100 may use this information to provide an improved medical decision-making and/or medical treatment.

The term “module” as used throughout the present application may be understood in the sense of software components and/or software instances which are designed to implement different tasks of the medical support system 100 of the present disclosure.

The term “artificial intelligence” as used throughout the present application may be understood in the sense of software components or software instances which are designed to correctly interpret data (i.e., the sensor data SD and the external data ED), to learn from such data, and to use those learnings to provide a medical support function through flexible adaptation.

According to some embodiments, which can be combined with other embodiments described herein, the artificial intelligence module 120 is configured to implement a machine learning algorithm. For example, a neural network can be implemented to analyze the sensor data SD and the external data ED.

The term “machine learning algorithm” as used throughout the present application refers to a software algorithm that can build a model based on training data, in order to make predictions and/or decisions without being explicitly programmed to do so.

A neural network is based on a collection of connected nodes. A node that receives a signal processes it and can signal nodes connected to it. Typically, nodes are aggregated into layers. Different layers may perform different transformations on their inputs. Signals travel from an input layer to an output layer. Such a neural network may be trained by processing examples, each of which contains a known input and result, forming probability-weighted associations between the two, which are stored within the data structure of the neural network. Thus, the neural network learns to perform tasks by considering examples.

To train the neural network, the deep learning method is used. Preferably, the neural network is a feed forward network with several hidden layers or a recurrent neural network with several hidden layers. The neural network can include input signal conditioning and post processing of the results. Optionally, the neural network has a model governance layer to make the medical application traceable. The type of data to train the neural network essentially depend on the medical domain (Cardiac Rhythm Management, Neuro Spinal Cord Stimulation, etc.) and the desired medical support function. To achieve optimal sensitivity and specificity, at least three of the following data must be available for training of the neural network in the Cardiac Rhythm Management domain:

ECG (intracardiac or surface ECG) for detection of cardiac insufficiencies (e.g. atrial fibrillation), - general patient data (gender, age, weight, diagnosed disease), medication, motion profiles, location information, weather data, and/or - calendar data.

In order to achieve optimal sensitivity and specificity, at least three of the following data must be available for training in the area of spinal cord stimulation: general patient data (gender, age, weight, diagnosed disease), - content information about used programs for therapy control in the implant (electrode configuration, amplitude, pulse width, frequencies, duty cycle, electrode offset, etc.), information about how the programs for therapy control are used (which program is used how often, how the patient sets the amplitudes, etc.), motion profiles, - medication, location information, weather data, and/or calendar data.

In the context of the present disclosure, the neural network may be suitably trained to process the sensor data SD and the external data ED to provide the medical support function.

According to some embodiments, which can be combined with other embodiments described herein, the medical support system 100 includes or is (e.g., wired or wirelessly) connected to one or more sensors 10a, 10b ... 10h associated with the patient 1. The one or more sensors 10a, 10b ... 10h may be configured to detect the one or more physiological parameters and provide the sensor data SD to the reception module 110.

The one or more sensors 10a, 10b ... 10h can be configured for non-invasive and/or invasive monitoring. For example, the one or more sensors 10a, 10b ... 10h can be connected or attached to the patient’s body to determine or monitor the physiological parameters in an invasive or a non-invasive manner.

In some embodiments of the present disclosure, the one or more physiological parameters can be selected from the group including (or consisting of) heart rate, blood pressure, body temperature, and serum levels (e.g., of various stress hormones). However, the present disclosure is not limited thereto, and other physiological parameters, such as those related to the respiratory system, that are useful in determining a health condition of the patient 1 may be measured by the one or more sensors 10a, 10b ... lOn. The external data ED are indicative of external circumstances of the patient 1 and indicate non-physiological parameters. In particular, the external data ED relate to aspects influenced by the patient 1 and/or aspects influencing the health condition of the patient 1. For example, the external data ED may be non-medical data provided by one or more external devices 12a, 12b ... 12n.

It is to be understood that the non-physiological parameters may indirectly affect the physiological parameters. However, the non-physiological parameters do not directly affect the physiological parameters or a measurement thereof, such as air pressure applying an offset to a pressure sensor in the patient’s body.

According to some embodiments, which can be combined with other embodiments described herein, the external data ED include at least one of movement data of the patient (e.g., a movement profile); location data of the patient (e.g., previous locations and/or a current location); environmental data at a location of the patient (e.g., weather conditions at a current location of the patient); seasonal data (e.g., time of year; sunrise and/or sunset times at a current location of the patient); calendar data of the patient (e.g., personal calendar entries); one or more user profiles of the patient (e.g., user profiles of personal devices, smart home device, electronic means of payment, and the like); habit data of the patient (e.g., preferred places); and nutrition data of the patient (e.g., electronic grocery shopping lists, data from a smart refrigerator, data from smart kitchen appliances, and the like).

The present disclosure is not limited to the above examples and the external data ED can include other data that affect and/or are suitable to identify a patient’s medical condition.

According to some embodiments, which can be combined with other embodiments described herein, the medical support system 100 further includes a communication module (not shown) configured to receive the external data ED from the one or more external devices 12a, 12b ... 12n. This is also applicable for sensor data SD of the one or more sensors 10a, 10b ... lOn. For example, active implants can send sensor data directly or indirectly via external relay device (patient device, patients smartphone, WLAN router) to the reception module 110.

For example, the medical support system 100 and the one or more external devices 12a, 12b ... 12n may communicate via at least one transmission medium 20, such as a network. In a preferred embodiment, the at least one transmission medium 20 includes a mobile network and/or a local network. This is also applicable for sensor data SD of the one or more sensors 10a, 10b ... lOn. For example, active implants can send sensor data directly or indirectly via external relay device (patient device, patients smartphone, WLAN router) to the reception module 110. The mobile network may use any of various wireless communication technologies, or telecommunication standards, such as GSM, UMTS, LTE, LTE-Advanced (LTE-A), 5G, HSPA, and the like. For example, the communication module of the medical support system 100 may include a communication profile such as an embedded subscriber identification module, eSIM, profile. However, the present disclosure is not limited thereto, and a conventional SIM may be used or another non-SIM communication profile.

The local network may use any of various wired and/or wireless communication technologies, such as Local Area Networks (LANs), Wireless LAN (WiFi), Bluetooth, and the like.

In some implementations, the one or more external devices 12a, 12b ... 12n may all communicate via the same transmission medium 20 with the medical support system 100, e.g., using the mobile network or the local network. This is also applicable for sensor data SD of the one or more sensors 10a, 10b ... lOn. For example, active implants can send sensor data directly or indirectly via external relay device (patient device, patients smartphone, WLAN router) to the reception module 110. Alternatively, the one or more external devices 12a, 12b ... 12n may communicate with the medical support system 100 using two or more different transmission media 20. For example, at least one external device of the one or more external devices 12a, 12b ... 12n may communicate with the medical support system 100 using the mobile network, and at least one other external device of the one or more external devices 12a, 12b ... 12n may communicate with the medical support system 100 using the local network. This is also applicable for sensor data SD of the one or more sensors 10a, 10b ... lOn. For example, active implants can send sensor data directly or indirectly via external relay device (patient device, patients smartphone, WLAN router) to the reception module 110. The present disclosure is not limited to the above examples and any suitable combination of different communication technologies can be used for a communication between the one or more external devices 12a, 12b ... 12n and the medical support system 100. This is also applicable for sensor data of the one or more sensors SD 10a, 10b ... lOn. For example, active implants can send sensor data directly or indirectly via external relay device (patient device, patients smartphone, WLAN router) to the reception modulel 10. According to some embodiments, which can be combined with other embodiments described herein, the one or more external devices 12a, 12b ... 12n are selected from the group including (or consisting of) a mobile terminal, a server, a wearable, a smart device, a smart home, a vehicle (e.g., a car), a mobility assistance device, and combinations thereof. This is also applicable for sensor data SD of the one or more sensors 10a, 10b ... lOn. For example, active implants can send sensor data directly or indirectly via external relay device (patient device, patients smartphone, WLAN router) to the reception module 110.

In particular, the term “mobile terminal” includes computer devices which are mobile (e.g., vehicles or mobility assistance devices) and/or portable (e.g., smartphones or wearables), and that are equipped with communication technology. Examples of mobile terminals include mobile telephones or smartphones, portable gaming devices, laptops, wearable devices (e.g., smart watches, smart glasses), PDAs, portable Internet devices, music players, data storage devices, or other handheld devices. In some embodiments, the reception module 110 is configured to receive the external data ED based on a current location and/or at least one previous location of the patient 1. For instance, the medical support system 100 may send a location identifier indicating a current location of the patient 1 to at least one external device of the one or more external devices 12a, 12b ... 12n. The at least one external device may then return the external data ED to the medical support system 100 based on the received location identifier. For example, the at least one external device may be a server configured to provide weather data corresponding to the current location of the patient 1 to the medical support system 100.

According to some embodiments, the location identifier may indicate coordinates, such as GPS coordinates, corresponding to the current location of the patient 1. According to some embodiments, which can be combined with other embodiments described herein, the medical support system 100 is configured for medical decision making and/or medical treatment of the patient 1. For example, the medical support system 100 may be configured for cardiology diagnostics, heart failure diagnostics, neurological diagnostics, progress monitoring, therapy control, and combinations thereof.

According to some embodiments, which can be combined with other embodiments described herein, the medical support system 100 further includes at least one output device 130. The medical support system 100 may be configured to control the at least one output device 130 to output information indicative of the analysis of the sensor data SD and the external data ED. For example, the at least one output device 130 may include at least one display device and/or at least acoustical device (e.g., at least one loudspeaker) or an interface for providing information indicative of the analysis to other entities. In some embodiments, the output information provided by the at least one output device 130 may include, or be, a medical diagnosis and/or medical treatment instructions. The output information may be, for example, instructions for the administration of a drug by medical personnel. According to some embodiments, which can be combined with other embodiments described herein, the medical support system 100 further includes a control module (not shown) configured to control one or more medical treatment devices 140 based on the analysis of the sensor data SD and the external data ED. An example of a medical treatment device is a device for drug administration or automatic drug administration.

In some implementations, the control module of the medical support system 100 is configured to initiate and/or change a treatment of the patient 1 by the control of the one or more medical treatment devices 140. For example, the control module may change a drug dose administered to the patient 1 based on the analysis of the sensor data SD and the external data ED. Fig. 2 shows a schematic view of a medical support system 100 receiving physiological data and external data according to embodiments described herein.

The medical support system 100 shown in Fig. 2 is an AI-based medical decision system that is used to monitor the progress of a patient 1 with a heart failure. However, it could also be a patient 1 with a disease of the nervous system, a neurological damage or simply pain. In this example, physiological patient data 230 is collected for heart failure monitoring and sent to the medical decision system 100 for processing. The physiological patient data 230 correspond to the sensor data explained with respect to Fig. 1.

Further, a number of additional data are collected and used to interpret the physiological patient data 230 in the AI-based medical decision system 100. The additional data correspond to the external data explained with respect to Fig. 1. The additional data used by the AI-based medical decision system 100 may include, but are not limited to, at least one of the following:

1. Data from the patient’s smartphone 220, such as physical activity, a user profile of the smartphone, and the like.

2. A user profile of a smart TV 210. 3. A user profile of electric lighting 280 in the patient’s home. For example, sleep times and/or movement profiles within the patient’s home can be used.

4. Location(s) 270 of the patient outside her/his home.

5. Weather, climate, and/or seasonal data 260 at the patient’s current location. These data could be analyzed together with, for example, the movement profile of the patient. 6. Stress data 250 indicating physical stress.

7. Exercise data 240 on participation in a cardiac exercise group.

The AI-based medical decision-making system is thus enabled to match deflections of physiological parameters with the patient’s circumstances and thus substantially increase the sensitivity and specificity of diagnostics. Fig. 3 shows a flow chart of a medical support method 300 for patient treatment according to embodiments described herein.

The medical support method 300 includes in block 310 receiving sensor data indicative of one or more physiological parameters of a patient and external data indicative of external circumstances relating to the patient; in block 320 analyzing, by an artificial intelligence module, the sensor data and the external data; and in block 330 providing a medical support function based on the analysis of the sensor data and the external data. According to embodiments described herein, the medical support method for patient treatment can be conducted by means of computer programs, software, computer software products and the interrelated controllers, which can have a CPU, a memory, a user interface, and input and output means being in communication with the corresponding components of the medical support system for patient treatment.

The embodiments of the present disclosure analyze a combination of physiological data and non-physiological in an artificial intelligence module to determine a condition of the patient. In particular, the analysis of physiological data and non-physiological data enables an improved medical support function. Thus, identification of optimal treatments can be achieved. Furthermore, treatment time can be minimized and medical costs reduced.

While the foregoing is directed to embodiments of the disclosure, other and further embodiments of the disclosure may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.