Patient monitoring system

Abstract

The invention relates to a system for monitoring patients (P1, P2 ... PN) after a procedure on a musculoskeletal system, comprising: • a plurality of patient-related sensors (SP1,1, SP1,2, ... SP1,M), • wherein a subset of the sensors determines movement parameters and a further subset of the sensors determines other medical parameters, • and a central unit (Z), • wherein the plurality of sensors and the central unit each contain devices for data exchange (I / O) with the aid of which sensor data can be transmitted to the central unit, • at least one selection unit (T) for displaying and selecting medically relevant parameters of the patient-related sensors, • wherein the central unit has Kl methods and algorithms that were previously trained using sensor parameters and with the aid of the selection unit,Based on a patient-specific preselection of the parameters to be considered, a score to be used in medicine is determined in relation to the course of rehabilitation of the measure, and a general assessment of the patient's condition is also carried out on the basis of other medical parameters, • Based on the score to be used in medicine and the general assessment of the condition, a recommendation for an adjustment and / or an intervention is given to a medical professional and / or the patient.

Description

The invention relates to a system for monitoring patients.BACKGROUND OF THE INVENTIONTo protect the social systems, stationary (over) capacities are currently being dissipated in the healthcare sector. At the same time, for demographic reasons, the number of degenerative joint diseases and injuries in older people increases.This leads to a work compaction of all occupation groups involved in the supply.Especially medical personnel are constantly receiving less time for anamnesis and examination. This problem is exacerbated by a lack of qualified professionals and high requirements for time-consuming documentation.This gives rise to the potential risk that less experienced medical practitioners make subjective decisions for therapy without sufficient information.In addition, optimized treatment concepts have led to a reduction in the stationary dwell time, which is also expedient from an economic point of view, which has at the same time led to a further work compaction of the stationary processes.The assessment of the health condition and the success of the operation requires a certain degree of experience and is often nevertheless not uniform on account of the subjective assessment of the attending physician.On the other hand, the early postoperative ambulatoryization of the patients requires objectiveable monitoring with the sectors being exceeded in the healthcare sector.So-called "fast track" concepts are intended to prepare the patient for the postoperative requirements already before the operation, but do not ensure sufficient rehabilitation.In order not to compromise the result of the treatment, a medically accompanied progress control is therefore required during acute rehabilitation and in the transition phase to return to the daily.In the period between acute rehabilitation action, sufficient rehabilitation and complete recovery without functional restrictions, there is a relative undersupply. If the patient leaves the clinic postoperatively, the hospital becomes "invisible" to the attending physician, so that even after stationary or domestic rehabilitation, a decision about the rehabilitation state and thus about the success (or failure) of the operation can be made only by a follow-up examination appointment in the clinic.Questions as a manual assessment method for detecting the pre- and post-operative patient condition and the joint functionality represent a subjective and no longer timely method.For example, in the field of disturbances of the locomotor apparatus, high-resolution measuring systems for objective analysis of the patient and its dynamic articulation functionality are known.Due to the complexity of the gait, all disturbances of the locomotor apparatus have an influence on the gait and manifest themselves by very small deviations in the gait pattern.In order to be able to analyze the gait image precisely, the use of sufficiently accurate "MoCap" systems (motion capture) is necessary. However, such high-resolution measurement systems for objective analysis of the patient and its dynamic articulation functionality are usually stationary (marker-based movement tracking), entail a high outlay for patients and examiners and are not charged by the cost providers.In addition to the enormous initial costs for such stationary systems (>100 000 ≅), the evaluation of the resulting data is also highly complex and requires a specific design.In contrast, video-based systems are provided which can detect the movement of a test subject by means of conventional handy cameras (OpenCap).However, these systems have considerable restrictions (not sufficient accuracy, increased rate of measurement errors, data safety), which is why use in clinical scenarios and for assisting attending physicians with focusing on the patient's intention is not currently implementable at all.On account of the high-resolution properties, a flood of measurement data is generated which cannot be used by the treating doctor without a specific formation. Even experienced gait analyzers do not have the ability to analyze and evaluate all data precisely, since minor changes in a patient's gait pattern are not always detectable by humans. An example of this is what are known as "normalized angular velocities", which are not directly recognizable to the human eye either in an observing gait analysis or in high-resolution measurement data, but play an extremely important role for the detection of functional limitations.In addition, the different orthopedic pathologies and characteristics of the functional limitations are extremely patient-specific and make it very difficult to diagnose according to requirements by inexperienced clinicians.Added to this are subjective statements from patients who do not represent the real state of health sufficiently well and can lead to misinterpretations on the part of the treating physician.That is, current systems and concepts have not yet been able to provide the attending orthopedics and accident surgeons with accurate and directly interpretable feedback about the functional status of the movement organ, including decision assistance, independently of location.Since these precise measurement systems have hitherto been unsuitable for clinical use, there are no systems known to us for the analysis and evaluation of high-resolution gait data.In order to maintain a high quality of supply, therefore, sector-wide, intelligent and at the same time resource-saving solutions are required.Proceeding from this situation, it is an object of the invention to provide a system for monitoring and monitoring orthopedic patients, which system makes it possible to offer solutions that are resource-saving and oriented at the patient's week and make it possible to monitor patients, in particular orthopedic patients, such that a course of action or the success thereof is improved.The invention is explained in more detail below with reference to the figures. In these, the following shows: FIG. 1 shows a schematic representation of an exemplary patient with sensors according to the invention, according to embodiments of the invention, FIG. 2 shows a schematic illustration of aspects of a central unit according to the invention in accordance with embodiments of the invention, in particular with regard to a data transmission to the central unit, FIG. 3 shows a schematic illustration of aspects of a central unit according to the invention, in accordance with embodiments of the invention, in particular with respect to a data transmission from the central unit, FIG. 4 is a schematic illustration of aspects of a central processing unit according to the invention in accordance with embodiments of the invention; and FIG. 5 is a schematic illustration of steps associated with the use of a system in accordance with embodiments of the invention.The invention will be illustrated in more detail below with reference to the figures. It should be noted that different aspects are described, which can be used individually or in combination. That is, any aspect may be used with various embodiments of the invention unless explicitly shown as a mere alternative.Furthermore, for the sake of simplicity, only one entity will normally be referred to below. If not explicitly stated, however, the invention can also have in each case a plurality of the entities concerned. In this respect, the use of the words "a", "an" and "an" is to be understood only as an indication that at least one entity is used in a simple embodiment.Insofar as methods are described below, the individual steps of a method can be arranged and / or combined in any order, unless the context explicitly reveals some variation. Furthermore, unless expressly stated otherwise, the methods can be combined with one another.Details with numerical values are generally not to be understood as exact values but also include a tolerance of + / - 1% up to + / - 10%.References to standards or specifications are to be understood as references to standards or specifications that apply / are considered at the time of application and / or-insofar as priority is claimed-at the time of priority application. However, this should not be understood as a general exclusion of applicability to subsequent or replacing standards or specifications.Due to the large intersection between orthopedic and traumatological or accident-surgical treatments on the supporting and movement organ, the terms (orthopedic, traumatological, accident-surgical) are subsummated below under the term "orthopedic" or "orthopedic".A basic idea of the invention is to support and relieve the medical personnel, and to improve personalized and patient-oriented orthopedic health care.As digitization progresses, timely routines no longer have to be broken up and used methods revised, so that new technical possibilities in the form of medical-safe tip technology are implemented in clinical processes and used for resource-saving health management.This invention can enable the medical personnel to be relieved by a patient-specific, directly interpretable decision feedback on the basis of the smart decision support system.This invention can also contribute to an improvement in personalized and patient-oriented health care by using precise and objective measurement systems for acquiring differentiated health data.The invention also allows the implementation of a direct translation telemedical feedback system in practice to cope with spatial distances and improve the exchange between medical personnel and patients.In FIG. 1, a patient P 1 is shown first by way of example. A plurality of patient-related sensors S P1,1, S P1,2,... are provided on the patient. S P1,M- here M=6-. The exact number of sensors can vary depending on the patient. It may likewise be that more than one parameter is detected by means of a sensor. Furthermore, the patient P 1 can also have at least one patient-related unit PE.The patient-related unit PE can be, for example, a (portable) device, such as a smartphone-see FIG. 2-, which is configured to receive data from one or more of the patient-related sensors S P1,1, S P1,2,... S P1,M.For this purpose, the patient-related unit PE can have corresponding communication interfaces which receive the data by means of a wireless (near-field) connection, e.g. Bluetooth, WLAN, ZigBEE, DECT. It should be noted that reception may also be active (periodic or controlled) polling.The patient-related unit PE can optionally pre-process, optionally buffer and optionally process collected data.The patient-related unit PE can forward ((pre-)processed and / or buffer-stored) data to a database DB (dashed lines) and / or directly to a central unit Z (solid lines). It can also be provided that individual sensors communicate with the database DB, while other sensors communicate with the central unit Z. It can also be provided in the case of the patient-related unit PE that the patient-related unit PE communicates individual data (e.g. specific sensors) to the database DB, while individual other data are communicated to the central unit Z by other sensors.It can also be provided that data are called up from individual sensors and / or the patient-related unit PE. The retrieval frequency can be predetermined or else the retrieval frequency can be changed, for example on the basis of a previously established profile. If, for example, the cause is to assume a deterioration, a more frequent data request may appear expedient, while conversely in the case of an improvement, a less frequent data request may be sufficient.Likewise, instead of a pull operation, a push operation can of course also be provided alternatively or additionally. The frequency with the data can be made available remotely (for example by the central unit Z and / or the medical professional M 1... M M) can be changed. If, for example, the patient detects a deterioration, he can also initiate the delivery of the data, for example by corresponding activation on the patient-related unit PE.Likewise, alternatively or additionally, upon explicit request by medical professionals M 1... M M- for example, in a practical search data.Likewise, a patient-related unit PE (in particular also the same patient-related unit PE that receives data from sensors) can also be configured to obtain recommendations for an adaptation and / or an intervention-see FIG. 3.In principle, it can also be provided that the patient-related unit PE communicates with a medical specialist user M 1... M M is possible.The database DB can be part of a central unit Z. However, a database DB can likewise also be provided externally to a central unit Z, for example in a cloud. The database DB can contain data from one or more patient-related sensors S P1,1, S P1,2,... S P1,M are obtained directly or indirectly ((pre-)processed) via one or more patient-related units PE. In a database DB, ((pre-)processed) data of the patient-related sensors S P1,1, S P1,2,... S P1,M can be stored patient-specifically (temporarily).To enable patient-specific processing, each patient P is 1... P N is uniquely identifiable. For this purpose, it can be provided, on the one hand, that one or more sensors have a unique identifier, and the identifier is stored, for example, in an allocation table, but likewise, in the case of indirect communication, for example, a unique identifier of the patient-related unit PE can also be used if one or more sensors communicate with this patient-related unit PE. In this case, it is sufficient if the patient-related unit PE has a unique identifier, and the identifier is stored, for example, in an assignment table. That is, it is possible for each patient P to be 1... P N identify data. As a rule, the data also have a time stamp, so that profiles can be detected. The time stamp can be transmitted with the data, on the one hand, but can also be derived on the basis of the reception date in the case of a timely data transmission.Obviously, not only can a patient be engaged in with the system, but it is possible to care a plurality of patients. The target of the monitoring can be different, as can be seen, for example, from FIG. 2. For example, while patient P has 1 sensors on the right leg that communicate with database DB and central unit Z, respectively, patient P has N sensors on the left leg and wrists. In this case, the sensor on the right wrist communicates directly with the central unit Z, while other sensors communicate with the patient-related unit PE of the patient P N. Thus, for example, data of the sensor on the leg can be communicated directly to the central unit Z, while data of other sensors are communicated via the database DB direction of the central unit Z. Regardless of the destination, (pre)processoring of the data can take place.It can also be provided that the destination of the communication of data is dependent on whether an indication of a problem arises from (pre)processor processing. For example, if sensors indicate that the patient is not actively actuating but his heart beat is too high, this could initiate direct communication with the central unit Z. This direct communication can comprise both the data from one or more sensors, but likewise only the indication can be given that data in the database DB require a timely assessment.In the System for Monitoring Patients P 1, P 2... P N after a measure on a supporting and moving organ, therefore, a plurality of patient-related sensors S P1,1, S P1,2,... S P1,M is used.A subset of the patient-related sensors S P1,1, S P1,2,... S P1,N, with N<M, determines movement parameters of a patient P 1 and a further subset of the patient-related sensors S P1,N+1,... S P1,M determines other medical parameters of the patient P1.For example, sensors for movement parameters of the patient P may be 1 sensors which acquire kinematic data and / or location data and / or load data. This allows (by means of the knowledge of the location of the sensors on the patient) e.g. an analysis of movement sequences, e.g. kinematic parameters, angle profiles, (normalized) angular speeds, pressure distribution, etc.) to be carried out.For example, sensors may sense other medical parameters or other associated factors of the patient P 1 such as temperature, heart rate, respiration rate, blood oxygen saturation, blood sugar, self-assessment of the patient such as pain, weight, age, sex, medical scores, wound condition, etc.The system according to the invention further comprises a central unit Z, wherein the plurality of patient-related sensors S P1,1, S P1,2,... S P1,M and the central unit Z each contain devices for data exchange I / O, with the aid of which sensor data can be transmitted to the central unit Z.Furthermore, the system has at least one selection unit T for displaying and selecting medically relevant parameters of the patient-related sensors S P1,1, S P1,2,... S P1,M. The selection unit T can be used, for example, to make the medical professional M 1,... M M make a selection of sensors that are appropriate for a particular patient P 1... P N is to be evaluated. That is, if not all data are required by a sensor, for example, then unsolicited data do not have to be transmitted and / or evaluated.As indicated in FIG. 5, the central unit Z has AI methods and algorithms, e.g. one or more neural networks, which have been trained beforehand by means of parameters of patient-related sensors and with the aid of the selection unit T. These are based on a patient-specific preselection of the parameters to be taken into account of the patient-related sensors of the patient P 1, which parameters are determined with the aid of a score to be used in medicine, based on the course of rehabilitation of the measure (1st prediction), and wherein furthermore a general determination of the state of the patient P 1(2. prediction) is determined on the basis of other medical parameters of the patient P 1.Based on the score to be used in medicine and from the general condition determination, a medical professional user M becomes 1,... M M and / or the patient P 1 are recommended for adaptation and / or intervention.For example, for the 1st prediction, machine learning, hierarchical regression models, hidden Markov model, neural networks, etc. may be used.For example, machine learning, classification, support vector machine, decision trees, neural networks, etc. can be used for the 2nd prediction.A recommendation for an adaptation and / or an intervention can relate, for example, to the rehabilitation course and indicate whether the course is good or poor, how much of the rehabilitation target has already been reached or that the rehabilitation target has been reached. However, it is also possible, in the case of stagnation or slight / slow improvement, to adapt the rehabilitation measures, for example the arrangement of one or more physiology application(s), special other therapies, an extension of the rehabilitation period, etc. In the event of a deterioration of the condition or an increase in pain, etc., an idea can be signaled to the patient at the physician and / or the setting / reduction of certain rehabilitation measures. However, it is also possible, on the one hand, to motivate even if the activity is reduced in the course of a rehabilitation measure, but on the other hand, to check specifically whether the patient is overrequested.In one embodiment of the invention, a patient-related unit PE acquires at least a part of the parameters of the plurality of patient-related sensors S P1,1, S P1,2,... S P1,M by means of - preferably wireless - communication.In a further embodiment of the invention, the devices for data exchange I / O for wireless communication are installed in the system.According to one embodiment of the invention, the system further comprises at least one database DB for storing parameters of the plurality of patient-related sensors S P1,1, S P1,2,... S P1,M. That is, such a database DB may store data associated with different patients. All data or only a selection of data can be stored.According to another embodiment of the invention, a medical professional user M 1... M M make the patient P 1 a recommendation for an adaptation and / or an intervention by means of the system.By using the system and in particular the sensors, e.g. the natural movement (e.g. gait of a patient) can be detected instrumentally and objectively as an orthopedic pathology.Sensors can be provided in many forms, for example also as wearables, in particular smart watches, cardio watch bracelets, textile sensor insoles, etc. These can generally not only provide acceleration and / or location data, but also gather vital parameters (so-called patient-associated data).On the basis of these comprehensive and differentiated measurement data, a multidimensional image of the patient can be generated, which enables not only a personalized, but also objective and optimized analysis of the state of health.The system allows the use of this multidimensional patient image in order to recognize functional restrictions by means of methods from the area of artificial intelligence (e.g. machine learning, neural networks, deep learning), to generate an orthopedic assessment and to provide the attending physician with relevant treatment recommendations a meaningful but directly interpretable state assessment (clinical software).In addition, the patient can be supported in his rehabilitation process by a direct patient feedback and can be reinforced for further rehabilitation measures (feedback app).The (compressed) condition feedback can provide the patient with a first feedback and can thus bridge the time until the treating physician has completely evaluated or follows the therapeutic arrangement.A final assessment by the physician is no longer based only on his expert and subjective assessment, but is supported by objective data.Since the acquisition of the high-resolution patient data can also be carried out independently in the domestic environment, the patient does not (first) have to be placed for a further on-site deadline.Via telesurging, a treating physician can access the data evaluation on a computer so that he obtains insight into the rehabilitation process and patient condition despite spatial distance.This enables a continuous and high-quality health care for the patient even in the case of future infections risks or other restrictions relating to mobility.The invention can be provided as a bundle with a portable measurement system and as individual software, so that already existing measurement systems of other manufacturers can also be used.For example, IMU-based (Inertial Measurement Unit), portable, compact measurement systems for movement detection can be used as patient-related sensors. These have a high accuracy, with daily movements, at the same time low costs and simple use.Wearables, in particular fitness trackers and / or so-called smart watches, can likewise be used in order to record, for example, heart rate, blood sugar, temperature, breathing rate, etc.As a "learning system", the system can also be adapted to new findings. Furthermore, it may be modular in terms of certain aspects.For example, one module may relate to rehabilitation of the shoulder joint, while another module relates to rehabilitation of the hip joint or knee joint, ankle joint, etc.Although the invention has been described above with the focus on rehabilitation, use in other fields is also possible.Also, the system can be used in the scientific field of medicine and sports sciences. This opens up new chances in the research fields sports orthopedics, return-to-sports, training sciences, pre-surgical planning and further surgical specialists.

Claims

System for monitoring patients (P1, P2... PN), according to a measure on a supporting and moving organ, having • a plurality of patient-related sensors (S P1,1, S P1,2,... S P1,M), • wherein a subset of the patient-related sensors (S P1,1, S P1,2,... S P1,N) determines movement parameters of a patient (P1) and a further subset of the patient-related sensors (S P1,N+1,... S P1,M) determines other medical parameters of the patient (P1), • and a central unit (Z), • wherein the plurality of patient-related sensors (S P1,1, S P1,2,... S P1,M) and the central unit (Z) each contain devices for data exchange (I / O), with the aid of which sensor data can be transmitted to the central unit (Z), • at least one selection unit (T) for displaying and selecting medically relevant parameters of the patient-related sensors (S P1,1, S P1,2,... S P1,M), • wherein the central unit (Z) has AI methods and algorithms which have been trained beforehand by means of parameters of patient-related sensors and with the aid of the selection unit (T), based on a patient-specific preselection of the parameters of the patient-related sensors of the patient (P1) to be taken into account, a score to be used in medicine is determined with respect to the course of rehabilitation of the measure, and wherein furthermore based on other medical parameters of the patient (P1) a general state determination of the patient (P1) is carried out, • wherein based on the score to be used in medicine and from the general state determination a medical specialist user and / or the patient (P1) is given a recommendation for adaptation and / or intervention.The system according to claim 1, characterized in that a patient-related unit (PE) comprises at least a part of the parameters of the plurality of patient-related sensors (S P1,1, S P1,2,... S P1,M) by wireless communication.System according to Claim 1 or 2, characterized in that the data interchange devices (I / O) are configured for wireless communication.The system according to any one of the preceding claims, characterized in that the system further comprises a database (DB) for storing parameters of the plurality of patient-related sensors (S P1,1, S P1,2,... S has P1,M).System according to one of the preceding claims, characterized in that the medical specialist user can make the patient (P1) a recommendation for adaptation and / or intervention by means of the system.

Images