Care Platform Derived Observations for Patient Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current care plans are rigid and not tailored to individual patients, lacking the ability to effectively monitor patient adherence and collect comprehensive data, which limits a doctor's ability to provide meaningful analysis.
Innovation Solution
A care platform that generates derived observations from patient biometric data, allowing for tailored care plans with specific metrics, thresholds, and remedial actions, and enables real-time monitoring and data collection through mobile devices and sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a standardized care plan is used for all patients with the same condition, then the ease of manufacture and implementation is improved, but the adaptability to individual patient needs deteriorates
Solution Approach 1:
The care plan is segmented into modular components including care plan definitions, event types, temporal slices, and metric definitions. Each component can be independently configured and combined to create personalized care plans. The system divides the overall care plan into discrete event types (e.g., exercise, medication, diet) that can be selectively applied to individual patients based on their specific needs.
Solution Approach 2:
The care plan system is designed to be dynamic rather than static. Care plans can be modified, updated, and adapted over time based on patient progress and changing conditions. The system allows for real-time adjustments to event types, temporal slices, and metric thresholds, enabling the care plan to evolve with the patient's needs while maintaining a structured framework.
2Measurement precision
If comprehensive biometric data collection is implemented, then the measurement precision and analysis capability are improved, but the device complexity and data processing requirements worsen
Solution Approach 1:
The system extracts only the relevant biometric data needed for specific care plan metrics rather than collecting all possible data. Event types are defined with specific data requirements (e.g., heart rate for exercise events, blood pressure for medication events), and the system collects only those specific measurements. This extraction approach reduces data complexity while maintaining measurement precision for the intended purposes.
Solution Approach 2:
The system performs preliminary configuration of event types, temporal slices, and metric definitions before actual data collection begins. Care plan definitions pre-specify which biometric data points are needed, the time periods for measurement, and the thresholds for analysis. This preliminary setup simplifies the actual data collection process by providing a clear framework for what data to collect and how to process it.
3Productivity
If real-time monitoring and derived metric generation are implemented, then the productivity of patient assessment is improved, but the use of energy and computational resources worsens
Solution Approach 1:
The system generates derived metrics selectively based on the specific care plan requirements rather than calculating all possible metrics continuously. Temporal slices are defined to cover only the necessary time periods for each metric, and event types are filtered to include only relevant data points. This partial action approach maintains high productivity for required assessments while reducing unnecessary computational energy consumption.
Solution Approach 2:
The system changes parameters such as temporal slice duration, event type frequency, and metric calculation intervals based on patient needs and care plan priorities. High-priority metrics are calculated more frequently with finer temporal resolution, while lower-priority metrics use coarser intervals. This dynamic parameter adjustment optimizes the balance between assessment productivity and energy consumption.
Data Source
AI summary
Techniques presented herein disclose a method for generating a derived observation for a care plan assigned to a patient. According to one embodiment, an application executing on a care platform server receives an event log having a plurality of events. Each event includes one or more types of biometric data for the patient. The care plan includes one or more definitions for metrics that are derived from the one or more types of biometric data. A temporal slice of the event log is selected based on one or more of the definitions. The derived metrics are generated by evaluating events within the selected temporal slice of the event log against one or more of the definitions. A condition of the patient is evaluated based on the derived metrics.