An Unsupervised Neural Network to Predict the Level of Heat Stress

Heat stress is known to induce high mortality rate due to multi-system illness, which demands urgent attention to reduce the fatality rate in such patients. Further, for the diagnosis and supportive therapy, one needs to define the severity of heat stress that can be distinguished as mild, intermediate and severe. The objective of this work is to develop an automated unsupervised artificial system to analyze the clinical outcomes of different levels of heat related illnesses. The Kohonen neural network program written in C++, which has seven normalized values of different clinical symptoms between 0–1 fed to the input layer of the network with 50 Kohonen output neurons, has been presented. The optimized initializing parameters such as neighborhood size and learning rate was set to 50 and 0.7, respectively, to simulate the network for 10 million iterations. The network was found smartly distinguishing all 51 patterns to three different states of heat illnesses. With the advent of these findings, it can be concluded that the Kohonen neural network can be used for automated classification of the severity of heat stress and other related psycho-patho-physiological disorders. However, to replace the expert clinicians with such type of smart diagnostic tool, extensive work is required to optimize the system with variety of known and hidden clinical and pathological parameters.

[1]  Rakesh Kumar Sinha,et al.  Study of changes in some pathophysiological stress markers in different age groups of an animal model of acute and chronic heat stress. , 2007, Iranian biomedical journal.

[2]  R. K. Sinha.  Artificial neural network detects changes in electro-encephalogram power spectrum of different sleep-wake states in an animal model of heat stress , 2003, Medical and Biological Engineering and Computing.

[3]  Rakesh Kumar Sinha,et al.  Backpropagation ANN-Based Prediction of Exertional Heat Illness , 2007, Journal of Medical Systems.

[4]  Youfei Zheng,et al.  Heat wave impacts on mortality in Shanghai, 1998 and 2003 , 2006, International journal of biometeorology.

[5]  Peter R. Griffiths,et al.  Classification and recognition of compounds in low-resolution open-path FT-IR spectrometry by Kohonen self-organizing maps , 1998 .

[6]  Jean Gotman,et al.  Computer-assisted sleep staging , 2001, IEEE Trans. Biomed. Eng..

[7]  Stefan Wermter,et al.  Data mining using rule extraction from Kohonen self-organising maps , 2006, Neural Computing & Applications.

[8]  Amitabh Chak,et al.  Prediction of outcome in acute lower-gastrointestinal haemorrhage based on an artificial neural network: internal and external validation of a predictive model , 2003, The Lancet.

[9]  Rakesh Kumar Sinha,et al.  Prediction of Heat-Illness Symptoms with the Prediction of Human Vascular Response in Hot Environment Under Resting Condition , 2008, Journal of Medical Systems.

[10]  J. Knochel,et al.  Medical progress: Heat stroke , 2002 .

[11]  D. Mathai,et al.  Predictors of multi-organ dysfunction in heatstroke , 2005, Emergency Medicine Journal.

[12]  Valluru B. Rao,et al.  C++, neural networks and fuzzy logic (2nd ed.) , 1995 .

[13]  C. Kurth,et al.  EEG Spike Detection With a Kohonen Feature Map , 2000, Annals of Biomedical Engineering.

[14]  Valluru Rao,et al.  C++ neural networks and fuzzy logic , 1993 .

[15]  Rakesh Kumar Sinha,et al.  An approach to estimate EEG power spectrum as an index of heat stress using backpropagation artificial neural network. , 2007, Medical engineering & physics.

[16]  P. Gottschalk,et al.  Heat Stroke , 1912 .