Circadian Blood Pressure Screening for Denervation Response
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing renal denervation therapies are ineffective for some patients, leading to wasted healthcare resources and patient discomfort due to the lack of accurate predictors for responsiveness.
Innovation Solution
A non-invasive method using a computing device to analyze circadian patterns of blood pressure and pulse waveforms to determine patient responsiveness to denervation therapy, employing machine learning models to generate a score indicative of therapy efficacy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If percutaneous renal denervation procedure is performed on all patients with uncontrolled hypertension, then some patients experience blood pressure lowering, but some patients are non-responders leading to wasted healthcare resources and patient discomfort
Solution Approach 1:
The patent replaces complex invasive physiological measurements with simple optical detection of pulse waveforms and blood pressure monitoring. The machine learning model processes these simple optical and pressure signals to predict denervation responsiveness, substituting sophisticated mechanical assessment systems with an information-processing approach that uses readily available vital signs data.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between simple vital sign measurements and the prediction of denervation responsiveness. This intermediary processes circadian patterns of blood pressure and pulse waveform data to generate a responsiveness score, bridging the gap between easily measurable parameters and clinically relevant outcomes without requiring complex direct measurements of nerve activity.
2Productivity
If invasive RDN procedure is performed to deliver denervation therapy, then sympathetic nerve activity is reduced, but patient discomfort and healthcare resource waste occur for non-responders
Solution Approach 1:
The patent performs preliminary assessment of denervation responsiveness using circadian blood pressure and pulse waveform analysis before the invasive RDN procedure. The machine learning model generates a prediction score in advance, allowing clinicians to identify likely non-responders and avoid performing the invasive procedure on them, thereby eliminating patient discomfort and resource waste before they occur.
Solution Approach 2:
The patent uses feedback from circadian blood pressure monitoring and pulse waveform analysis to predict treatment outcomes. By continuously monitoring these vital signs and analyzing their patterns, the system provides feedback about likely treatment responsiveness, enabling informed decisions about whether to proceed with the invasive denervation procedure.
Data Source
AI summary
An example computing device includes a memory; and one or more processors coupled to the memory, the one or more processors being configured to: determine a baseline circadian pattern of blood pressure for a patient over a first period of time; determine a subsequent circadian pattern of blood pressure for the patient over a second period of time, the second period of time being after the first period of time; determine one or more differences between the subsequent circadian pattern and the baseline circadian pattern; determine, based on the one or more differences between the subsequent circadian pattern and the baseline circadian pattern, whether the patient is a candidate for denervation therapy; and output, responsive to determining whether the patient is a candidate for the denervation therapy, an indication of whether the patient is or is not a candidate for the denervation therapy.