%! Author = alex
%! Date = 3/6/25


\section{Related Work}\label{sec:related_work}

This section will introduce related work of both ovulation detection and ovulation prediction.
First, I will introduce early work on the detection of the ovulation based on biomarkers.
Then, I will show how others have used body temperature to predict ovulation and what their limitations are.
Lastly, I will take a closer look at related work that uses other biomarkers as base, or as an addition to the body
temperature for ovulation and fertility prediction.

A variety of approaches have historically been explored for ovulation detection and prediction,
ranging from hormonal assays to physiological signal tracking.

In~\citeyear{wallach_prediction_1980}, \citeauthor{wallach_prediction_1980} identified several physiological indicators for ovulation timing,
including salivary ferning and viscosity, serum levels of progesterone and estrogen,
and urinary luteinizing hormone (LH) concentrations~\cite{wallach_prediction_1980}.
These indicators showed strong correlation with ovulation timing as measured via transvaginal ultrasound.
\citeauthor{vermesh_monitoring_1987} later expanded on this work by focusing specifically on LH and estradiol,
confirming that LH surges reliably indicate an imminent ovulation event~\cite{vermesh_monitoring_1987}.

Despite their diagnostic value, many of these biomarkers are difficult to measure continuously and reliably in everyday settings,
limiting their practicality for real-time or large-scale applications.
Among the physiological indicators explored, body temperature has gained particular attention due to its accessibility
and suitability for passive, continuous monitoring.

\subsection{Temperature-Based Approaches}\label{subsec:temperature_based_approaches}
Body temperature has emerged as a more accessible physiological signal for ovulation tracking,
given the feasibility of continuous and non-invasive measurement.
As outlined in Section~\ref{subsubsec:physiological_signs}, basal body temperature (BBT) exhibits a biphasic pattern across
the menstrual cycle that correlates with ovulation.

However, several studies have raised concerns about its reliability as a predictive marker.
\citeauthor{bauman_basal_1981} concluded that BBT alone is insufficiently robust due to its retrospective nature and
high susceptibility to external confounders, recommending caution in its clinical or research use~\cite{bauman_basal_1981}.
Similarly, \citeauthor{moghissi_accuracy_1976} emphasized its limited accuracy, particularly in cycles with irregularities~\cite{moghissi_accuracy_1976}.

Such conclusions were largely based on the standard BBT method, which relies on a single-point measurement taken
immediately upon waking—typically reflecting the body's lowest resting temperature.
In contrast, this study, along with several recent works, leverages continuous or high-resolution temperature data collected during sleep or throughout the day.
This richer signal provides a more robust foundation for detecting ovulatory patterns and addresses many of the limitations historically associated with BBT-based methods.

This was further supported by a study from \citeauthor{zhu_accuracy_2021}, who compared the accuracy and sensitivity of traditional BBT measurements with continuous skin temperature recordings from a wrist-worn device~\cite{zhu_accuracy_2021}.
They found that continuous temperature measurements achieved higher sensitivity but at the cost of more false positives and reduced specificity.
Importantly, the continuous data showed a greater average temperature difference between the follicular and luteal phases.
The authors conclude that for women seeking to optimize their chances of conception, continuous temperature tracking offers measurable benefits—primarily due to improved phase delineation enabled by the richer signal.

The predictive value of continuous temperature data was further demonstrated in a study by \citeauthor{luo_detection_2020},
who used an in-ear wearable device that measured ear canal temperature every five minutes during sleep~\cite{luo_detection_2020}.
They trained a Hidden Markov Model (HMM) to classify each data point into either a high- or low-temperature state,
augmented with biorhythm information from the user.

After filtering, the final dataset consisted of 65 cycles, each with at least 40\% data availability and at least one self-reported ovulation day, as determined by a hormone test kit,
a notable contrast to the 40,000 cycles analyzed in this study.
However, no information was provided regarding the distribution of cycle lengths or ovulation timing.

Ovulation detection was considered successful if the predicted day fell within ±3 days of the self-reported value.
The method achieved a sensitivity of 92.31\%, with 54.69\% of ovulation days detected exactly on the reported date.

The model, however, relies on strong assumptions of phase regularity and fixed transition durations, such as a standard
luteal phase length of 14 days, which do not reflect real-world variability.
Moreover, HMM predictions are conditioned on either a previous cycle or population-level averages, limiting performance in irregular or anovulatory cycles.
As a result, the approach performs well on regular, well-behaved data but lacks robustness in more diverse, real-world scenarios.

Building on this idea, \citeauthor{yu_tracking_2022} combined temperature with additional physiological signals to improve predictive performance.
In~\citeyear{yu_tracking_2022}, they employed an in-ear thermometer along with a fitness tracker
for heart rate monitoring to predict the fertile window using machine learning~\cite{yu_tracking_2022}.
Their study population consisted of 153 women, divided into a regular cycle group ($n = 103$) and an irregular group ($n = 50$).
After filtering, 89 and 25 participants remained in the regular and irregular groups, respectively.

The prediction task was to determine whether a given day falls within the fertile window, based on data from the preceding days.
They developed a probability function based on a changepoint analysis of the smoothed waveforms of the BBT and heart rate.
A second function was developed in a similar way to predict whether menstruation occurs on a given day, again using preceding data as input.

For the fertile window prediction, the model achieved a sensitivity of 69.30\% in the regular group and 21.00\% in the irregular group.
For menstruation prediction, the model detected 70.70\% of menstruation days in the regular group and 36.30\% in the irregular group.

These results indicate that the model performed well in regular cycles but struggled with irregularity, particularly in detecting the fertile window.

In~\citeyear{kilungeja_machine_2025},~\citeauthor{kilungeja_machine_2025} trained a set of classification models
to predict the cycle phase a day based on skin temperature, electrodermal activity, interbeat interval and heart rate.
The measurements were automatic and did not require manual participant input~\cite{kilungeja_machine_2025}.
The classification was either into three or four targets: period, ovulation, luteal phase, and follicular phase for the four-class models.
Their dataset included 65 cycles across 18 subjects.
They trained a decision tree, random forest ensemble, logistic regression and support vector machine to enable
an architectural comparison.
Results show an edge for the random forest model with a reported 87\% accuracy and AUC-ROC (area under the receiver operating characteristic curve)
of 0.96 for the three class approach.
The four class approach significantly reduced accuracy to 68\% and AUC-ROC of 0.77.
There was no separation into cycle groups and all cycles were in a regular group, with a mean length of 28 days (SD: 1.65).

There are some additional studies based on commercial products, such as \emph{Oura Ring}\cite{thigpen_oura_2025}
or \emph{Natural Cycles}\cite{bull_real-world_2019} that work with temperature data as a base.
However, they all focus on retrospective ovulation-detection and often complement this with advice to remain
abstinent during the first cycle phase until the ovulation was reliably detected.
This way they can offer a contraceptive product option, without needing to create a predictive model or algorithm.

Complementing academic efforts, several other commercial products have also adopted temperature-based tracking,
such as \textit{Ava}~\cite{sl_ava_nodate}, \textit{Daysy}~\cite{electronics_zykluscomputer_nodate} or \textit{Trackle}~\cite{noauthor_trackle_nodate}.
However, these products rely on proprietary algorithms, and no peer-reviewed publications are available detailing their methodology or performance.
This lack of transparency limits their scientific evaluation and comparability.
In contrast, the present study provides an open and data-driven approach to ovulation prediction based on continuous temperature data, aiming to contribute reproducible evidence to the field.

\subsection{Other Physiological Signals}\label{subsec:other_physiolocical_signals}
In addition to temperature, other physiological signals have been explored for ovulation and cycle phase prediction.

As early as~\citeyear{moreno_temporal_1988}, researchers investigated ovulation prediction based on the electrical resistance of salivary and vaginal secretions~\cite{moreno_temporal_1988}.
Their study analyzed 29 cycles from 11 women, with daily recordings of BBT, urinary LH, pelvic ultrasound, and ovulation predictor kit results.
Participants were under the age of 35, had cycle lengths between 25 and 35 days, and had abstained from hormone therapies for at least two months prior to the study.

The results showed that, in all but one cycle, peaks in salivary resistance occurred 5–11 days prior to the estimated ovulation day.
The nadir in vaginal resistance coincided with or occurred on the day of ovulation.
These findings suggest that electrical resistance is a strong physiological marker for predicting ovulation.

A related modern implementation is the commercial product \textit{kegg}~\cite{noauthor_kegg_nodate}, which measures the electrical resistance of cervical mucus.
The device uses an undisclosed algorithm to estimate fertility status based on these readings, although no peer-reviewed validation studies are currently available.

In~\citeyear{masuda_machine_2025}, \citeauthor{masuda_machine_2025} developed a machine learning algorithm to classify phases of the menstrual cycle
(follicular vs. luteal) based on sleeping heart rate, as recorded by a fitness tracker~\cite{masuda_machine_2025}.
They used an XGBoost classifier for this binary task and additionally performed ovulation day prediction,
although the details of this task were not fully specified.
Ground truth labels were derived from self-reported data and daily ovulation predictor kits.

The dataset used in their study was restricted to healthy, non-pregnant women aged 18–34 with natural menstrual cycles.
Anovulatory cycles were excluded, along with users meeting the following criteria:
\begin{itemize}
    \item Use of medications, including hormonal contraceptives
    \item Travel across time zones
    \item Night-shift work
    \item Pregnancy within the past year
    \item Sleep disorders
    \item Tobacco use
\end{itemize}

They further subdivided participants into groups with low and high sleep variability, called HVST and LVST respectively.
As a result, the study population and cycle types were highly regular and homogeneous,
with 30 cycles (18 women) in the HVST and 26 cycles (16 women) in the LVST category.
No information about the distribution of both cycle lengths or ovulation dates was given.

Based on selected features—such as minimum sleeping heart rate and single-point basal body temperature (BBT) after
waking—they report classification accuracies between 0.843 and 0.864, depending on the feature subset,
with very similar numbers for precision, recall, specificity and F1 score.
Ovulation day prediction yielded an average absolute error between 3.6 and 4.1 days.

\subsection{Summary}\label{subsec:related_work_summary}
While various physiological signals and modeling strategies have been explored for ovulation prediction,
many existing studies are limited by small, highly selective datasets, assumptions of cycle regularity, or reliance on proprietary algorithms.
The present work extends prior approaches by leveraging a large, heterogeneous dataset of real-world cycles and applying transparent,
data-driven modeling to better capture individual variability.