Predicting pregnancy using large-scale data from a women's health tracking mobile application

@article{Liu2019PredictingPU,
  title={Predicting pregnancy using large-scale data from a women's health tracking mobile application},
  author={Bo Liu and Shuyang Shi and Yongshang Wu and Daniel Thomas and Laura Symul and Emma Pierson and Jure Leskovec},
  journal={The World Wide Web Conference},
  year={2019}
}
Predicting pregnancy has been a fundamental problem in women's health for more than 50 years. Previous datasets have been collected via carefully curated medical studies, but the recent growth of women's health tracking mobile apps offers potential for reaching a much broader population. However, the feasibility of predicting pregnancy from mobile health tracking data is unclear. Here we develop four models - a logistic regression model, and 3 LSTM models - to predict a woman's probability of… 

Figures and Tables from this paper

Labeling Self-Tracked Menstrual Health Records With Hidden Semi-Markov Models

TLDR
A hierarchical approach relying on hidden semi-Markov models that adapts to changes in tracking behavior, explicitly captures variable– and state– dependent missingness, allows for variables of different type, and quantifies uncertainty is presented.

Assessment of menstrual health status and evolution through mobile apps for fertility awareness

TLDR
The digital epidemiology approach presented here can help to lead to a better understanding of menstrual health and its connection to women’s health overall, which has historically been severely understudied.

Labeling self-trackedmenstrual health records with hidden 1 semi-Markov models

TLDR
Two coupled hidden semi-Markov models are presented that adapt to changes in tracking behavior, explicitly capture variable– and state– dependentmissingness, allow for variables of di erent type, and quantify uncertainty.

Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis

Background Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm

The Quantified Woman: Exploring Perceptions on Health App Use among Austrian Females of Reproductive Age

TLDR
This study assessed aspects of health app use in an understudied segment of the general population of Austrian females, and suggested assuring data security and privacy for sensitive female health data collected by health apps.

Menstrual Cycle Tracking Applications and the Potential for Epidemiological Research: a Comprehensive Review of the Literature

Purpose of Review We reviewed published studies on menstrual cycle tracking applications (MCTAs) in order to describe the potential of MCTAs for epidemiologic research. Recent Findings A search of

Real-world menstrual cycle characteristics of more than 600,000 menstrual cycles

TLDR
Variations in menstrual cycle characteristics observed from a large database of cycles collected through an app are described and associations with cycle length, age and body mass index (BMI) are investigated.

Feasibility of Continuous Distal Body Temperature for Passive, Early Pregnancy Detection

TLDR
The development of pregnancy detection using DBT may reduce the delay from conception to awareness and increase the agency of pregnant individuals, and is proposed for testing and refinement in clinical settings, and for exploration in large, diverse cohorts.

Designers in White Coats: Deploying Ovum, a Fertility Tracking Device

TLDR
This paper unpacks the findings from a three-month long deployment of Ovum with seven couples trying to conceive and reports on the consequences of executing a design deployment that resembles a clinical trial.

Individuals’ number of children is associated with benevolent sexism

TLDR
This study illustrated ways to tentatively test predictions of theoretical accounts on sexism and identified new, though small, evidence for the role justification perspective.

References

SHOWING 1-10 OF 56 REFERENCES

Examining Menstrual Tracking to Inform the Design of Personal Informatics Tools

TLDR
It is found that women track their menstrual cycle for varied reasons that include remembering and predicting their period as well as informing conversations with healthcare providers and expanding the field's conceptions of personal informatics.

Healthier women, healthier reproductive outcomes: recommendations for the routine care of all women of reproductive age.

Evaluation of Smartphone Menstrual Cycle Tracking Applications Using an Adapted APPLICATIONS Scoring System

TLDR
Most free smartphone menstrual cycle tracking apps for patient use are inaccurate, and these are list accurate apps to aid health care providers in understanding the key components they can use to evaluate and recommend apps for patients.

A Bayesian joint model of menstrual cycle length and fecundity

TLDR
A Bayesian joint model is employed for MCL and pregnancy and finds a statistically significant quadratic relation between fecundity and menstrual cycle length, after adjustment for intercourse pattern and other attributes, including male semen quality, both partner's age, and active smoking status.

Accuracy of the peak day of cervical mucus as a biological marker of fertility.

DeepCare: A Deep Dynamic Memory Model for Predictive Medicine

TLDR
The efficacy of DeepCare for disease progression modeling and readmission prediction in diabetes, a chronic disease with large economic burden, is demonstrated and the results show improved modeling and risk prediction accuracy.

Bayesian Inferences on Predictors of Conception Probabilities

TLDR
A Bayesian approach based on a generalization of the Barrett and Marshall model to incorporate a woman-specific frailty and day-specific covariates is proposed and can be used for efficient variable selection and model averaging in general applications with categorical or discrete event time data.

Increased Infertility With Age in Men and Women

TLDR
Increased infertility in older couples is attributable primarily to declines in fertility rates rather than to absolute sterility, and many infertile couples will conceive if they try for an additional year.

The timing of the “fertile window” in the menstrual cycle: day specific estimates from a prospective study

TLDR
Only about 30% of women is the fertile window entirely within the days of the menstrual cycle identified by clinical guidelines—that is, between days 10 and 17; most women reach their fertile window earlier and others much later.

Bayesian methods for searching for optimal rules for timing intercourse to achieve pregnancy

TLDR
A Bayesian decision theoretic approach for searching for optimal rules for timing intercourse based on cycle day, secretions and other information is proposed and a stochastic search procedure is developed to search for rules with high expected utility.
...