An Exercise Health Simulation Method Based on Integrated Human Thermophysiological Model

Nan Jia, Xiaohong Chen, Liang Yu, Ruomei Wang, Kaixing Yang, Xiaonan LuoComputational 2017 · DOI

TL;DR

This paper introduces a novel simulation method for predicting exercise-related health risks by integrating a human thermophysiological model with a fuzzy finite state machine. This approach aims to proactively identify potential health issues like dehydration and heatstroke during exercise, offering a valuable tool for personalized health monitoring and accident prevention.

What Problem Does This Paper Address?

Regular exercise is crucial for health, but it also carries risks, including dehydration, heatstroke, and even sudden death. Current methods for monitoring exercise health often rely on wearable sensors that collect continuous data, which can be costly and inconvenient. While data mining techniques can analyze historical data, their accuracy is limited without sufficient personal information. This paper addresses the need for a proactive and integrated approach to predict exercise health risks by simulating the body's physiological responses during physical activity. The goal is to move beyond reactive monitoring to predictive health assessment, enabling timely interventions to prevent accidents.

Methods

The core of this work is an integrated human exercise thermophysiological model. This model combines two key components:

  1. Two-Node Thermal Regulation Model: This model simulates the human body's thermal behaviors, focusing on core and skin temperatures, heat storage, metabolic heat production, and heat loss mechanisms like sweating. It uses mathematical equations to represent these processes.
  2. Nonlinear Heart Rate Regulation Model: This model simulates how heart rate changes during exercise, taking into account both neural and peripheral effects, as well as exercise intensity.

These two models are coupled to simulate various physiological indicators, including core temperature, dehydration amount, and heart rate.

Once these physiological indicators are simulated, a fuzzy finite state machine (FSM) is employed for exercise health prediction.

  • Fuzzification: Simulated physiological indicators (core temperature, dehydration, heart rate) are converted into fuzzy symptoms using trapezoidal membership functions. These symptoms are categorized (e.g., low temperature, normal temperature, high temperature for core temperature).
  • Finite State Machine Definition: A specific FSM is defined to represent the possible health states and transitions. The FSM has states representing combinations of core temperature, dehydration, and heart rate symptoms. Transitions between states are triggered by changes in these fuzzy symptoms.
  • Health State Transition Metrics: Probabilities are calculated for transitions between states, allowing for the assessment of the likelihood of a particular health state over time.

Datasets

The paper does not explicitly mention training datasets. The model was validated using data collected from five adult male subjects performing two different exercise scenarios (walking and running) under controlled environmental conditions. The collected data included measured core temperature, dehydration percentage, and heart rate, which were then compared against the simulation results.

Key Insights and Ideas

  • Integrated Simulation is Key: The paper highlights that simulating thermal and physiological responses together provides a more holistic view of exercise health than looking at them in isolation.
  • Predictive Health is Achievable: By modeling the body's dynamic responses and using fuzzy logic to interpret them, it's possible to predict health transitions before critical events occur.
  • Fuzzy Logic for Nuance: Using fuzzy logic allows for a more nuanced representation of health states, moving beyond simple binary classifications to capture degrees of severity (e.g., mild, moderate, severe dehydration).
  • FSM for Dynamic Tracking: The FSM provides a structured way to track the progression of health states over time, offering insights into the trajectory of a person's well-being during exercise.
  • Personalized Risk Assessment: The model's parameters can be adjusted for individual subjects, suggesting the potential for highly personalized health risk assessments.

Key Results

The integrated thermophysiological model was validated against experimental data from five subjects.

  • Core Temperature Simulation: The simulated core temperature curves showed good agreement with measured values in both walking and running scenarios, with error bars within ±0.3°C.
  • Heart Rate Simulation: Simulated heart rate also closely matched measured values, with errors within ±10 bpm.
  • Dehydration Simulation: Simulated water loss values were slightly below experimental values, but the calculated dehydration percentages were very close, indicating the model's effectiveness in representing sweating mechanisms.
  • Health Prediction Cases: Two case studies demonstrated the FSM's ability to predict health state transitions.
  • Case 1 (Jogging): Predicted a transition from a normal state (NNN) to hyperthermia (FNN, FNT) and eventually a state indicating dehydration and potential heatstroke (FDT) over a 2-hour period.
  • Case 2 (Running): Predicted a rapid transition to a high-risk state (FNT) due to increased core temperature and heart rate, suggesting the exercise was too intense for the subject.

Limitations and Future Work

  • Subject Population: The current model and validation were performed on healthy adult males. Further research is needed to analyze and discuss similar simulations for specific populations, such as cardiac patients or other individuals with pre-existing health conditions.
  • Real-time Monitoring: While the paper mentions a real-time exercise monitoring framework and an implemented APP, challenges remain regarding simulation efficiency, load balancing, and the storage of increasing physiological data as user numbers grow.
  • Parameter Estimation: The accuracy of the model relies on accurate parameter estimation for individual subjects, which can be a complex task.
  • Further Refinement of FSM: While the FSM effectively tracks transitions, exploring more sophisticated methods for state transition probability calculation and health judgment could further enhance its predictive power.

Summary updated

Abstract

Research of healthy exercise has garnered a keen research for the past few years. It is known that participation in a regular exercise program can help improve various aspects of cardiovascular function and reduce the risk of suffering from illness. But some exercise accidents like dehydration, exertional heatstroke, and even sudden death need to be brought to attention. If these exercise accidents can be analyzed and predicted before they happened, it will be beneficial to alleviate or avoid disease or mortality. To achieve this objective, an exercise health simulation approach is proposed, in which an integrated human thermophysiological model consisting of human thermal regulation model and a nonlinear heart rate regulation model is reported. The human thermoregulatory mechanism as well as the heart rate response mechanism during exercise can be simulated. On the basis of the simulated physiological indicators, a fuzzy finite state machine is constructed to obtain the possible health transition sequence and predict the exercise health status. The experiment results show that our integrated exercise thermophysiological model can numerically simulate the thermal and physiological processes of the human body during exercise and the predicted exercise health transition sequence from finite state machine can be used in healthcare.
BibTeX
@inproceedings{jia2017exercise,
  author = {Nan Jia and Xiaohong Chen and Liang Yu and Ruomei Wang and Kaixing Yang and Xiaonan Luo},
  title = {{An Exercise Health Simulation Method Based on Integrated Human Thermophysiological Model}},
  booktitle = {Computational},
  year = {2017},
  doi = {10.1155/2017/9073706},
}
Figure