EP-4511108-B1 - BIOCHEMICAL SENSING FOR HEART FAILURE MANAGEMENT

Inventors

• STIGEN, TYLER
• NELSON, STEVEN G.
• O'BRIEN, RICHARD J.
• TAYLOR, Amanda D.
• PATEL, Nirav A.
• YOON, HYUN J.
• EISELE III, Val D
• WYSZYNSKI, Ryan D.
• KRAUSE, PAUL G.
• SARKAR, SHANTANU

Dates

Publication Date

20260513

Application Date

20230406

Claims (15)

1. A medical device system (2) comprising: an implantable medical device (10) configured to sense one or more physiological signals and determine first sensor data based on the one or more physiological signals; and processing circuitry (14) communicatively coupled to the memory, the processing circuitry being configured to: receive the first sensor data; determine, based on the first sensor data, a likelihood that a heart failure decompensation event of a patient is impending; compare the likelihood to a first threshold; and based on the likelihood satisfying the first threshold, at least one of a) generate a first instruction for output to a user to deploy at least one of one or more biochemical sensors or one or more bacterial sensors (44), or b) control the implantable medical device or another implantable medical device to automatically deploy at least one of one or more biochemical sensors or one or more bacterial sensors (44).
2. The medical device system of claim 1, wherein the processing circuitry is further configured to output the first instruction to the user.
3. The medical device system of claim 1 or 2, wherein the processing circuitry is further configured to: receive at least one of biochemical sensor data from the one or more biochemical sensors or bacterial sensor data from the one or more bacterial sensors; and update the likelihood that a heart failure decompensation event is impending based on at least one of the biochemical sensor data or the bacterial sensor data.
4. The medical device system of claim 3, wherein the processing circuitry is further configured to: compare the updated likelihood to a second threshold; and based on the updated likelihood meeting the second threshold, generate a first indication for output to a user.
5. The medical device system of claim 4, wherein the first indication comprises at least one of: an indication to seek medical attention; an indication of the updated likelihood that the heart failure decompensation event is impending; or a proposed treatment of the patient.
6. The medical device system of claim 4 or 5, wherein the processing circuitry is further configured to output the first indication to the user.
7. The medical device system of any of claims 1-6, wherein the implantable medical device comprises an insertable cardiac monitor.
8. The medical device system of claim 7, wherein the insertable cardiac monitor comprises: a housing (15) configured for subcutaneous implantation in a patient, the housing having a length between 40 millimeters (mm) and 60 mm between a first end and a second end, a width less than the length, and a depth less than the width; a first electrode (16A) at or proximate to the first end; and a second electrode (16B) at or proximate to the second end, wherein the insertable cardiac monitor is configured to sense at least one of the one or more physiological signals via the first electrode and the second electrode.
9. The medical device system of any one or more of claims 1-8, further comprising one or more boluses of anti-biotic medication disposed on the implantable medical device, wherein the one or more bacterial sensors are configured to generate bacterial sensor data, and wherein the processing circuitry is further configured to: determine that the bacterial sensor data indicates a bacterial infection; and control the implantable medical device to release at least one of the one or more boluses of anti-biotic medication based on the determination that the bacterial sensor data indicates the bacterial infection.
10. The medical device system of any of claims 1-9, wherein at least one of the one or more biochemical sensors or at least one of the one or more bacterial sensors are insertable into the patient by the patient or a caregiver.
11. The medical device system of any of claims 1-10, wherein the processing circuitry is further configured to at least one of: generate a second instruction for output to a user to deploy one or more biochemical or bacterial sensors according to a schedule, or control the implantable medical device to deploy one or more biochemical or bacterial sensors according to the schedule.
12. The medical device system of claim 11, wherein the schedule is at least one of: predetermined; programmed by a clinician; based on a change in pattern of at least one of sensed biochemical parameters, bacterial parameters, or physiological parameters over time; or determined by the processing circuitry executing a machine learning model.
13. The medical device system of claim 11 or claim 12, wherein the processing circuitry is further configured to: receive at least one of biochemical sensor data from the one or more biochemical sensors or bacterial sensor data from the one or more bacterial sensors; and generate a second indication for output to a clinician, the second indication comprising at least one of the biochemical sensor data or the bacterial sensor data.
14. The medical device system of any of claims 1-13, wherein the processing circuitry is further configured to: generate a score based on at least one of the first sensor data, the biochemical sensor data, or the bacterial sensor data; and output the score to a clinician, optionally, wherein the processing circuitry is further configured to: compare the score to a previous score; determine that the score is different than the previous score; and output a third indication for review by the clinician, the third indication comprising at least one of information relating to the change in the score from the previous score, a source of the change in the score from the previous score, or suggested treatment options.
15. The medical device of any of claims 1-14, wherein the first sensor data comprises a plurality of sensed physiological parameters and wherein as part of determining the likelihood that a heart failure decompensation event of a patient is impending, the processing circuitry is configured to: compare each of the plurality of sensed physiological parameters to parameter specific thresholds; and apply a Bayesian probabilistic model to results of the comparisons, optionally, wherein the plurality of sensed physiological parameters comprise at least two of a fluid index, patient activity, atrial tachycardia (AT)/atrial fibrillation (AF) burden, ventricular rate during AT/AF, percentage of ventricular pacing, shocks, treated ventricular tachycardia/ventricular fibrillation, night ventricular rate, heart rate variability, heart sounds, or lung sounds.

Description

TECHNICAL FIELD The disclosure relates generally to medical devices and, more particularly, medical devices configured to monitor patient parameters. BACKGROUND Some types of medical devices may be used to monitor one or more physiological parameters of a patient. Such medical devices may include, or may be part of a system that includes, sensors that detect signals associated with such physiological parameters. Values determined based on such signals may be used to assist in detecting changes in patient conditions, in evaluating the efficacy of a therapy, or in generally evaluating patient health. US 2021/0093254 A1 relates to determining likelihood of an adverse health event based on various physiological diagnostic states. SUMMARY The claimed subject matter is defined in claim 1. Acute decompensated heart failure is a manifestation of worsening of heart failure (or broadly chronic illness) symptoms that may require heart failure hospital admission to relieve such patients of congestion and/or shortness of breath symptoms. A system configured for continuous (e.g., on a periodic or triggered basis without human intervention) ambulatory heart failure monitoring may be used to potentially predict worsening heart failure prior to development of severe symptoms requiring heart failure hospitalizations and provide clinicians with an opportunity to proactively treat the patient to avoid the heart failure hospital admission. Remote monitoring of some physiological parameters, such as thoracic impedance, e.g., via OptiVol™ available from Medtronic, Inc. of Minneapolis, Minnesota, or pulmonary artery pressure, is available. However, clinicians are often reluctant to make treatment decisions in the absence of information provided by all or a portion of a Basic Metabolic Panel (BMP) (e.g., sodium, chloride, potassium, bicarbonate, BUN, creatinine, glucose, etc.) or an International Normalized Ration (INR), a measure of clotting time, or in the absence of information regarding an infection status of the patient. Such measures provide a more complete picture of a patient's health status. Biochemical parameters, such as those of the BMP, are usually measured by a blood draw and a laboratory analysis, a finger stick point of care test, or by short-term (measured in days) percutaneous sensors. In general, this disclosure is directed to techniques for using a medical device system to monitor physiological parameters of a patient, such as a heart failure patient. Sensors may be located on one or more implantable medical devices (IMDs), wearable devices, point of care finger stick devices, and/or other external devices, for sensing physiological parameters of a patient. Processing circuitry of the medical device system may execute an algorithm (e.g., TriageHF™ available from Medtronic, Inc. or a similar algorithm) to determine a likelihood of an impending heart failure decompensation event based on these sensed physiological parameters. As used herein "impending" may mean within less than 30 days, and in some examples within 7-10 days. Many sensors for sensing physiological parameters relevant to heart failure have much longer lifespans than biochemical sensors which may be used to determine biochemical parameters, such as those of a BMP, or bacterial sensors which may be used to determine bacterial parameters. Because such biochemical and bacterial sensors may have a much shorter lifespan than other sensors and because clinicians are reluctant to hospitalize a heart failure patient without a recent BMP or a known bacterial infection, it may be desirable to deploy such sensors when an impending heart failure decompensation event is detected. Data sensed by such sensors may be further input into the algorithm to increase the accuracy of the initial assessment of the likelihood that there may be an impending heart failure decompensation event. According to the techniques of this disclosure, a machine learning model or other algorithm configured to determine a likelihood of an impending heart failure decompensation event may be implemented in an implantable medical device (IMD), in a wearable device, such as a smart watch, in a smart phone that the patient may carry with them, on one or more servers, in a cloud computing environment, or the like. The device may execute the algorithm and may generate an instruction for output to a patient, caregiver or healthcare monitoring system, when the device determines that the likelihood of an impending heart failure decompensation event, based on sensed physiological parameters, meets a threshold. This instruction may automatically prescribe for the patient or caregiver to conduct a fingerstick measure, insert a percutaneous sensor, or insert an implantable sensor. Alternatively, or additionally, if the IMD includes one or more biochemical sensors or one or more bacterial sensors on or near the surface of the IMD, the device executing the algorithm could activate one or more biochemical