Modeling Individual Cyclic Variation in Human Behavior

Abstract

Cycles are fundamental to human health and behavior. Examples include mood cycles, circadian rhythms, and the menstrual cycle. However, modeling cycles in time series data is challenging because in most cases the cycles are not labeled or directly observed and need to be inferred from multidimensional measurements taken over time. Here, we present Cyclic Hidden Markov Models (CyH-MMs) for detecting and modeling cycles in a collection of multidimensional heterogeneous time series data. In contrast to previous cycle modeling methods, CyHMMs deal with a number of challenges encountered in modeling real-world cycles: they can model multivariate data with both discrete and continuous dimensions; they explicitly model and are robust to missing data; and they can share information across individuals to accommodate variation both within and between individual time series. Experiments on synthetic and real-world health-tracking data demonstrate that CyHMMs infer cycle lengths more accurately than existing methods, with 58% lower error on simulated data and 63% lower error on real-world data compared to the best-performing baseline. CyHMMs can also perform functions which baselines cannot: they can model the progression of individual features/symptoms over the course of the cycle, identify the most variable features, and cluster individual time series into groups with distinct characteristics. Applying CyHMMs to two real-world health-tracking datasets—of human menstrual cycle symptoms and physical activity tracking data—yields important insights including which symptoms to expect at each point during the cycle. We also find that people fall into several groups with distinct cycle patterns, and that these groups differ along dimensions not provided to the model. For example, by modeling missing data in the menstrual cycles dataset, we are able to discover a medically relevant group of birth control users even though information on birth control is not given to the model.

Characterizing physiological and symptomatic variation in menstrual cycles using self-tracked mobile-health data

“…While there has been ample work on hormone-level characterizations of the menstrual cycle [68][69][70][71] , studies of the relationship between menstrual patterns and symptomatic variables are limited-recent work has explored this association using selftracked data, but over a limited set of symptoms 72 and without discriminating over age or birth control usage 60 . A method for estimating ovulation timing based on Fertility Awareness Method observations (i.e., basal body temperature (BBT), cervical mucus, cervix position, and vaginal sensation) has been presented 62 , but such data are inaccessible for this study due to the European Union's General Data Protection Regulation and other dataprivacy concerns (sensitive fields such as appointments, ovulation and pregnancy tests, and BBT were not available in Clue's dataset).…”

Leveraging Routine Behavior and Contextually-Filtered Features for Depression Detection among College Students

“…Banovic et al [9] employ the maximum causal entropy algorithm [97] to model routine behaviors and their variance. Pierson et al [66] propose Cyclic Hidden Markov Models to model cycles in human behavior. Among these options, ARM is a powerful method for mining contextual data to better understand human behavior.…”

Labeling self-tracked menstrual health records with hidden semi-Markov models

“…Hidden Markov models only performed well in labeling individual cycles whose start and ends were already identified and where users had reported enough data to constrain the duration of each phase. Others have proposed cyclic HMM (CyHMM) to recover cycle characteristics from menstrual cycle app data (Pierson et al, 2017). While this framework is successful in identifying cycles, it did not include prior biological knowledge beyond the average cycle length.…”