Illness Detection via Menstrual Cycle Pattern Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wearable devices often misinterpret physiological data, leading to incorrect illness predictions, particularly during menstrual cycles, causing anxiety and stress due to false-positive fever readings.
Innovation Solution
The system analyzes menstrual cycle patterns to differentiate normal temperature fluctuations from illness indicators, using machine learning classifiers and baseline physiological data to predict transitions from a healthy to an unhealthy state, and vice versa, providing early warnings and personalized insights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If wearable devices use physiological data to detect illness, then illness detection capability is improved, but false-positive predictions during menstrual cycles increase
Solution Approach 1:
The system performs preliminary actions by collecting and analyzing menstrual cycle data beforehand to establish a personalized baseline pattern. This preliminary analysis enables the system to anticipate and differentiate between normal menstrual temperature fluctuations and actual illness indicators, thereby reducing false-positive predictions while maintaining reliable illness detection
Solution Approach 2:
The system applies parameter changes by dynamically adjusting temperature thresholds and detection criteria based on the user's menstrual cycle phase. During luteal phase when elevated temperature is normal, the system modifies the fever detection threshold to prevent false positives, while maintaining sensitive detection during other cycle phases when temperature should remain stable
2Loss of information
If the system provides detailed health monitoring, then user insight into physical health is improved, but user anxiety and stress increase due to false alarms
Solution Approach 1:
The system implements feedback by continuously monitoring both physiological data and user responses to alerts. When false positives occur, the system learns from user corrections and adjusts its detection algorithms accordingly. This feedback mechanism maintains comprehensive health information provision while reducing psychological stress by improving prediction accuracy over time
Solution Approach 2:
By providing preliminary context about menstrual cycle effects before illness alerts, the system prevents unnecessary user anxiety. The advance information about expected temperature variations during certain cycle phases helps users understand that not all temperature changes indicate illness, thereby maintaining complete health monitoring while reducing stress
Data Source
AI summary
Methods, systems, and devices for illness detection are described. A method may include identifying a menstrual cycle model associated with a menstrual cycle for a user, and receiving physiological data for the user collected throughout a first time interval and a second time interval by a wearable device. The method may include inputting the physiological data and the menstrual cycle model into a classifier, and identifying a satisfaction of deviation criteria between first and second subsets of the physiological data collected throughout the first and second time intervals, respectively, based on the menstrual cycle model. The method may include causing a graphical user interface (GUI) of a user device to display an illness risk metric associated with the user based on the satisfaction of the deviation criteria, the illness risk metric associated with a relative probability that the user will transition from a healthy state to an unhealthy state.