Patent Application
20200237244
The present invention relates to a method and a system for adjusting parameters of a medical device.
Algorithms configured to detect certain clinical events often have multiple user-selectable parameter settings to allow for individual variance in patient signals. Default settings are often used, however, since real-time evaluation of each combination of settings is both time consuming and difficult to evaluate. For example, QRS detection algorithms may have selectable filtering and threshold parameters for optimal detection of the QRS complex while rejecting T-waves and muscle artifact. Arrhythmia detection algorithm parameters are selected along a spectrum of higher sensitivity versus higher specificity.
According to the prior art, clinicians often manually select from the available parameter set, then evaluate their selection either immediately through real-time data (e.g., for QRS detection), or over time via statistics and stored data (e.g., arrhythmia detection) transmitted from or retrieved from the device.
U.S. Pat. No. 9,629,548 B2 describes a system, data collection method and workflow for predicting HF decompensation, wherein patient data is collected by an implantable device. The data is sent to an external device/data server and analyzed. The physician inputs feedback to the analyzed data. The data analysis is modified according to the physician's feedback.
Typically, algorithms known in the art have multiple parameters available for adjustment, resulting in a large number of parameter combinations. For example, three separate parameters, each with three possible values, result in 27 possible settings. Due to the time required to test each possibility, and the difficulty in evaluating the result, default settings are often used unless there are significant performance issues. There is often a long time period required to optimize settings in the current practice. Settings are adjusted and days or weeks elapse before the impact of those settings is realized. In the absence of remote programming, a subsequent follow up is required in order to correct poorly performing settings and bad adjustments. That also implies a long time lag in order to improve settings during the initial implant and tuning of the device.
It is accordingly an object of the invention to provide a method and a system for adjusting parameters of a medical device, which overcome the hereinafore-mentioned disadvantages of the heretofore-known methods and systems of this general type and which allows for an efficient optimization of parameter settings for the medical device.
With the foregoing and other objects in view there is provided, in accordance with the invention, a method for adjusting parameters of a medical device, comprising the steps of:
collecting patient data by using the medical device, wherein the medical device includes programmable parameters for adjusting a function carried out by the medical device, transmitting or communicating the patient data to an external device, conducting an analysis of the transmitted patient data on the external device, and providing an automatically computed proposal to a physician for adjusting at least one of the programmable parameters, or several of the programmable parameters, or all of the programmable parameters using the analysis.
According to an embodiment of the present method, the at least one adjusted programmable parameter is automatically programmed to the medical device. According to an embodiment, at least one adjusted programmable parameter is remotely programmed to the medical device.
According to embodiments of the present invention, the medical device is an implantable medical device such as for example a cardiac pacemaker, a spinal cord stimulator, a vagus nerve stimulator, a deep brain stimulator, or the like. The medical device is, according to an embodiment of the invention, a non-implantable medical device, such as for instance a medical device such as for instance a Holter monitor.
Particularly, the proposal can be displayed to the physician via a graphical user interface (GUI), particularly a GUI of the external device.
Thus, the present invention provides an opportunity to replay stored patient data (either on the external device, e.g. a programmer, or in an external data center) through a detection algorithm using all available settings of the parameters. The resulting performance can be presented as a function of settings, thereby allowing the clinician to choose the optimal parameter settings for this patient based on the collected patient data. In the context of the present invention, ‘patient data’ is understood as information on at least a physiological parameter of a patient, which is measured via an external device or an implantable medical device and converted into a signal. As an example, cardiac monitoring devices typically measure electrocardiogram (ECG) signals, wherein brain diagnostics devices measure electroencephalogram (EEG) signals, devices for volumetric measurements of an organ measure plethysmogram (PG) signals, etc. The present invention is applicable to all kinds of signals/patient data where an analysis of the patient data is desired. In the following the term “signal” is used as synonym for all kinds of possible signals representing a physiological parameter of a patient and measured by a the medical device. The term “patient data” is used as synonym for any kind of physiological patient parameter which is measured via the medical device via a signal.
Particularly, according to an embodiment, the external device can be a programming device (also denoted as a programmer), a single computer, or a network including several computers. The proposal can be displayed to the physician via a graphical user interface (GUI), particularly a GUI of the external device.
Particularly, in the context of the present invention, the notion “external device” means that the external device is disposed remote from the medical device, or outside the body of the patient when the medical device is an implantable medical device in an implanted state. Furthermore, implanting the implantable medical device into the patient does not form a step of the method according to the present invention, i.e. the method uses an implantable medical device that has been implanted into the patient before carrying out the method according to the present invention.
Particularly, according to an embodiment of the method, the event-detection function is carried out by the medical device by executing an algorithm implemented in the medical device, wherein the algorithm utilizes the programmable parameters to achieve a classification of clinical events such as but not limited to QRS detections or detections of atrial fibrillation, contained in the acquired patient data.
According to the present invention, a clinical event would be any event that would have relevance to the medical condition of the patient. This could be events detectable in the signal/patient data. E.g., for ECGs, clinical events could be those relating to the rhythm like arrhythmias. Clinical events can occur in another biological signal that gives information about the body (e.g. PG, impedance signal, evoked compound action potentials (ECAPS), EEGs, Electromyogram (EMG) signals, etc., etc.).
According to an exemplary QRS detection metric, the ECG signal is analyzed via high pass 0.5 Hz, high pass 10 Hz, high pass 18 Hz, or high pass 24 Hz filters. According to another example, typical thresholds for signal amplitude detection are set to 0.1 mV, 0.2 mV, 0.3 mV.
The algorithm can be implemented in the medical device in various fashions, and particularly when any of one or several parameters can be selected to alter the algorithm performance, it is relevant to this invention. According to an embodiment of the present invention, the algorithm or updates of the algorithm may be uploaded to the medical device via an external device or a service center.
Furthermore, according to an embodiment of the method, the step of collecting patient data by using the medical device corresponds to measuring an electrocardiogram (ECG), e.g. a particular ECG strip or group of ECG strips, i.e. the patient data is an ECG measured by using the medical device.
Furthermore, according to an embodiment of the method, the collected patient data is stored in the external device, particularly for later review. The measured signal can be evaluated by a physician and/or via algorithms for the occurrence of signals indicating a pathophysiology. In case of an ECG, pathophysiologies may be e.g. bradycardia, tachycardia, atrial fibrillation, ectopies, changes in the heart rate, asystolies or the like.
Further, according to an embodiment of the method, conducting the analysis includes carrying out the same algorithm on the external device and thereby applying the algorithm to the collected patient data for a plurality of different settings of each programmable parameter, wherein for each setting of the parameters the classification of clinical events obtained by the algorithm executed on the external device are stored (e.g. on the external device).
Further, according to an embodiment of the method, a human expert (e.g. physician) or an expert system independently processes the classifications of the clinical events made by the algorithm executed on the external device to adjudicate them as true or false.
Further, according to an embodiment, the method according to the invention includes the steps:
The adjudication is most effective on the implant data and could be made on a programmer or other external device. According to embodiments of the inventive method, the patient data is analyzed and evaluated through multiple iterations. Input from a human expert is not required in the data analysis/evaluation process. However, it is not to be categorically excluded that human expert knowledge can be used for adjusting certain steps of the inventive method, as e.g. for optimization of the algorithms behind the analysis of transmitted patient data in step 3 above.
Further, according to an embodiment of the method, the automatically computed proposal for adjusting at least one of the parameters, or several of the parameters, or all of the parameters is adapted such that false classifications of clinical events made by the algorithm are reduced when the respective parameter is adjusted according to the proposal.
In this way, the expert (physician) or expert system, with knowledge of the algorithm and its programmable parameters, determines or influences the optimum settings of the programmable parameters of the algorithm. Particularly, the optimum parameter settings that are now patient specific, are presented to the user (e.g. physician) for review and acceptance.
According to a further embodiment of the method, the user (e.g. physician) provides a preference or guidance regarding the type of performance. For instance, a higher sensitivity of the algorithm and a lower specificity, or vice versa. Based on these preferences, the optimization algorithm chooses parameter settings which provide performance matching that preference.
Furthermore, according to an embodiment, an evaluation and adjudication of the patient data/clinical events are performed in real-time by the clinician's programmer forming the external device and the proposal for adjusting one, or several, or all of the parameters is particularly made in real-time during a follow-up. Alternatively, the historical data stored on the programmer or on an external device could be leveraged to improve the optimization further and to adjust to the patient's longer-term health trajectory.
Further, according to an embodiment of the method according to the present invention, the function of the medical device corresponds to one of:
Detecting Q, R, and S waves in the ECG, wherein particularly the respective clinical event is the occurrence of a Q, R or S wave,
Detecting P waves in the ECG, wherein particularly the respective clinical event is the occurrence of a P wave,
Detecting T waves in the ECG, wherein particularly the respective clinical event is the occurrence of a T wave,
Detecting ectopic events from the atrium or ventricle, wherein particularly the respective clinical event is the occurrence of a ectopy,
Detecting atrial fibrillation in the ECG, wherein particularly the respective clinical event is the occurrence of an atrial fibrillation,
Detecting bradycardia in the ECG, wherein particularly the respective clinical event is the occurrence of bradycardia,
Detecting an asystole in the ECG, wherein particularly the respective clinical event is the occurrence of an asystole,
Detecting a sudden rate drop in the ECG, wherein particularly the respective clinical event is the occurrence of a sudden rate drop,
Detecting a high ventricular rate in the ECG, wherein particularly the respective clinical event is the occurrence of a high ventricular rate (e.g. above a pre-defined threshold).
Moreover, according to an embodiment of the inventive method, the parameters of the medical device are adjusted via the external device, another external device or an external data center via wireless programming.
With the objects of the invention in view there is also provided a system for adjusting parameters of a medical device, wherein the system includes:
a medical device configured to collect patient data, wherein the medical device is configured to perform a function and includes programmable parameters for adjusting the function, an external device, wherein the medical device is configured to transmit the collected patient data to the external device, wherein the external device is further configured to conduct an analysis of the transmitted patient data, and wherein the external device is configured to provide a proposal to a physician for adjusting at least one of the parameters, or several of the parameters, or all of the parameters (e.g. via a graphical user interface of the external device) using the analysis.
Particularly, the implantable medical device can be an implantable monitoring device or an implantable cardiac pacemaker or an implantable cardioverter defibrillator.
Further, according to an embodiment of the system according to the present invention, the medical device is configured to carry out the function by executing an algorithm implemented in the medical device, wherein the algorithm utilizes the programmable parameters to achieve a classification of clinical events contained in the patient data.
Particularly, according to an embodiment of the system, the collected patient data is an ECG of the patient, particularly a real-time ECG.
Furthermore, particularly, the system is configured to store the collected patient data (e.g. ECG) in the external device, particularly for later review.
Further, according to an embodiment of the system, the external device is configured to conduct the analysis by executing the same algorithm on the external device and apply the algorithm to the collected patient data for a plurality of different settings of each parameter, wherein the external device is further configured to store for each setting of the parameters the classifications of clinical events obtained by the algorithm executed on the external device.
Further, according to an embodiment of the system, the system is configured to process, as an input, adjudications by a human expert (e.g. physician) or an expert system whether the respective classification made by the algorithm executed on the external device is true or false.
Further, according to an embodiment of the system, the system is configured to adapt the automatically computed proposal for adjusting at least one of the parameters, or several of the parameters, or all of the parameters, such that false classifications of clinical events made by the algorithm are reduced when the respective parameter is adjusted according to the proposal.
Particularly, according to an embodiment of the system, the function corresponds to one of (see also above):
Detecting P, Q, R, S, and T waves in the signal,
Other features which are considered as characteristic for the invention are set forth in the appended claims.
Although the invention is illustrated and described herein as embodied in a method and a system for adjusting parameters of a medical device, it is nevertheless not intended to be limited to the details shown, since various modifications and structural changes may be made therein without departing from the spirit of the invention and within the scope and range of equivalents of the claims.
The construction and method of operation of the invention, however, together with additional objects and advantages thereof will be best understood from the following description of specific embodiments when read in connection with the accompanying drawings.
Referring now to the figures of the drawings in detail and first, particularly, to
Particularly, the external device 3 can be a programmer that is operable to program the programmable parameters of the medical device 2. The medical device 2 can be a monitoring device that is e.g. configured to monitor a signal 4 of the patient P. Alternatively the medical device 2 can be a cardiac pacemaker or a cardioverter defibrillator.
Particularly, according to an embodiment, for QRS detection, a real-time electrocardiogram (ECG) is captured by the external device 3 as the patient data 4. The external device 3 can be formed by a physician's programmer. The data 4 can be either directly received from the implant 2 or can be stored in the implant before. Particularly, a QRS detection algorithm that would normally be applied by the device 2 is applied to the captured ECG 4 by the external device 3, using e.g. all variations of the available parameter set. Particularly, a performance metric such as a Receiver Operating Curve (sensitivity versus 1-specificity) allows the clinician P′ to see which parameter set(s) would be most appropriate for this patient P. The clinician P′ can select a candidate from this ROC plot directly, or may examine the ECG 4 with detection annotations before selecting a candidate.
Since the algorithm for conducting data analysis is now running on the external device 3 (e.g. programmer), which does not have the processor and battery limitations of the implant 2, a much wider parameter space can be explored.
Particularly, a human expert (e.g. clinician/physician) P′ or an expert system independently processes the classifications of the events made by the algorithm executed on the external device 3 to adjudicate them as true or false. The automatically computed proposal is then adapted such that false classifications of clinical events made by the algorithm are reduced or true classifications are increased when the respective parameter is adjusted according to the proposal.
Apart from QRS detection described above, the function/algorithm may also be configured to detect one of: atrial fibrillation, bradycardia, asystole, sudden rate drop, or a high ventricular rate.
Particularly, according to an embodiment of the invention, when the function of the implantable device 2 relates to detecting bradycardia, a false snapshot can be re-evaluated with different bradycardia settings. These settings can be applied to other non-bradycardia snapshots of the measured ECG 4, to ensure that they are not falsely detected. A more sophisticated approach would be to evaluate both bradycardia and QRS detection for optimal settings of QRS detection in the context of bradycardia. For instance, various QRS detection settings can be applied to find the settings where a “false” bradycardia snapshot is no longer detected as false. The user P′ can adjudicate the snapshot or adjudicate specific events in order to provide a gold standard for grading the parameters.
Particularly, the present invention allows for improving performance by leveraging the parameter space of existing algorithms. The human or machine experts P′ are presented with performance data, so that they can use their domain experience to choose the best parameters for their patient P without going through the drudgery and time of manually selecting each parameter. This minimizes the need for customer support of patients P. By providing a graphical matrix of parameter settings (cf. e.g.
It will be apparent to those skilled in the art that numerous modifications and variations of the described examples and embodiments are possible in light of the above teaching. The disclosed examples and embodiments are presented for purposes of illustration only. Other alternate embodiments may include some or all of the features disclosed herein. Therefore, it is the intent to cover all such modifications and alternate embodiments as may come within the true scope of this invention.
This application claims the priority, under 35 U.S.C. § 119(e), of U.S. Provisional Patent Application No. 62/797,383 filed Jan. 28, 2019; the prior application is herewith incorporated by reference in its entirety.
| Number | Date | Country | |
|---|---|---|---|
| 62797383 | Jan 2019 | US |
