Estimation of the Biphasic Property in a Female’s Menstrual Cycle from Cutaneous Temperature Measured During Sleep
- 184 Downloads
This paper proposes a method to estimate a woman’s menstrual cycle based on the hidden Markov model (HMM). A tiny device was developed that attaches around the abdominal region to measure cutaneous temperature at 10-min intervals during sleep. The measured temperature data were encoded as a two-dimensional image (QR code, i.e., quick response code) and displayed in the LCD window of the device. A mobile phone captured the QR code image, decoded the information and transmitted the data to a database server. The collected data were analyzed by three steps to estimate the biphasic temperature property in a menstrual cycle. The key step was an HMM-based step between preprocessing and postprocessing. A discrete Markov model, with two hidden phases, was assumed to represent higher- and lower-temperature phases during a menstrual cycle. The proposed method was verified by the data collected from 30 female participants, aged from 14 to 46, over six consecutive months. By comparing the estimated results with individual records from the participants, 71.6% of 190 menstrual cycles were correctly estimated. The sensitivity and positive predictability were 91.8 and 96.6%, respectively. This objective evaluation provides a promising approach for managing premenstrual syndrome and birth control.
KeywordsHidden Markov model (HMM) Data mining Body temperature Long-term monitoring Mobile phone QR code
This study was supported in part by the Innovation Technology Development Research Program under JST (Japan Science and Technology Agency) grant H17-0318, Grants-In-Aid for Scientific Research under No. 20500601 and the competitive research funding from the University of Aizu. The authors would like to thank all the anonymous participants for their enduring efforts in long-term data collection.
- 3.Bauman, J. E. Basal body temperature: unreliable method of ovulation detection. Fertil. Steril. 36:792–833, 1981.Google Scholar
- 4.Bengio, Y. Markovian models for sequential data. Neural Comput. Surv. 2:129–162, 1999.Google Scholar
- 9.Coyne, M. D., C. M. Kesick, T. J. Doherty, M. A. Kolka, and L. A. Stephenson. Circadian rhythm changes in core temperature over the menstrual cycle: method for noninvasive monitoring. Am. J. Physiol. Regulatory Integrative Comp. Physiol. 279:1316–1320, 2000.Google Scholar
- 13.Elkum, N. B., and J. D. Myles. Modeling biological rhythms in failure time data. J. Circadian Rhythms. 7:4–14, 2006.Google Scholar
- 14.Gaunard, P., C. G. Mubikangiey, C. Couvreur, and V. Fontaine. Automatic classification of environmental noise events by hidden Markov models. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, Vol. 6, 1998, pp. 3609–3612.Google Scholar
- 23.Moghissi, K. S. Prediction and detection of ovulation. Fertil. Steril. 32:89–98, 1980.Google Scholar
- 36.Zuck, T. T. The relation of basal body temperature to fertility and sterility in women. Am. J. Obstet. Gynecol. 36:998–1005, 1938.Google Scholar