Reverse Engineering of Digital Measures: Inviting Patients to the Conversation.

Background: Digital measures offer an unparalleled opportunity to create a more holistic picture of how people who are patients behave in their real-world environments, thereby establishing a better connection between patients, caregivers, and the clinical evidence used to drive drug development and disease management. Reaching this vision will require achieving a new level of co-creation between the stakeholders who design, develop, use, and make decisions using evidence from digital measures. Summary: In September 2022, the second in a series of meetings hosted by the Swiss Federal Institute of Technology in Zürich, the Foundation for the National Institutes of Health Biomarkers Consortium, and sponsored by Wellcome Trust, entitled "Reverse Engineering of Digital Measures," was held in Zurich, Switzerland, with a broad range of stakeholders sharing their experience across four case studies to examine how patient centricity is essential in shaping development and validation of digital evidence generation tools. Key Messages: In this paper, we discuss progress and the remaining barriers to widespread use of digital measures for evidence generation in clinical development and care delivery. We also present key discussion points and takeaways in order to continue discourse and provide a basis for dissemination and outreach to the wider community and other stakeholders. The work presented here shows us a blueprint for how and why the patient voice can be thoughtfully integrated into digital measure development and that continued multistakeholder engagement is critical for further progress.

Behaviour recommendations with a deep learning model and genetic algorithm for health debt characterisation.

Human behaviour is a dense longitudinal multi-featured measure that directly impacts the health of individuals in the short and long terms. Therefore, issues usually emerge from the insistence on performing risky behaviours, such as smoking or eating fast foods, which continuously increase the gap between current and beneficial health states. This paper introduces the term "health debt" as an economic metaphor to represent the quantification of this gap in domains such as sleep, contributing to physical and mental health states. Then, we present a theoretical framework that relies on behaviour change recommendations to quantify this debt. The practical instantiation of this framework relies on passively assessed sleep related data via personal wearable devices, and uses of an attention-based predictive model as the fitness function of a genetic algorithm that acts as a recommender. We evaluate this proposal by means of a case example aimed at improving the sleep duration of individuals. Results show, for example, that the use of individual rather than generic datasets produces more accurate models. At the same time, the use of constraints on the variability of behaviours features generates more feasible recommendations. These foundations open new research opportunities to support the adoption of preventive medicine based on longitudinal wearable passive data analysis.

The social robot companion to support homecare nurses: The guardian study protocol.

Introduction: The reduction of the older people's self-sufficiency and the increase in the need for help in daily activities has a significant impact on the person and their caregivers. The primary objective of the GUARDIAN project is to enable the older people to live as long as possible at home, by means of the GUARDIAN socio-technical platform. Methods: and Analysis: The GUARDIAN platform consists of two connected apps: one dedicated to the caregiver (Caregiver App) and one dedicated to the older people (Senior App), plus a robot (Misty II), to provide coaching in an engaging modality. The study is designed as a technical feasibility pilot to test the GUARDIAN system on a group of older people. Discussions: The proposed solution reflects the real wants and needs of the older people person, increasing the acceptability of the system. In addition, the GUARDIAN project has the potential to have distinguished two phases of testing, so that changes can be made to the platform between the first and second phases, using data, both qualitative and quantitative, collected after the first phase. Ethics and dissemination: The study was approved by the Ethic Committee of the IRCCS INRCA. It was recorded in ClinicalTrials.gov on the number NCT05284292.

Burned-out with burnout? Insights from historical analysis.

Fierce debates surround the conceptualization and measurement of job-related distress in occupational health science. The use of burnout as an index of job-related distress, though commonplace, has increasingly been called into question. In this paper, we first highlight foundational problems that undermine the burnout construct and its legacy measure, the Maslach Burnout Inventory (MBI). Next, we report on advances in research on job-related distress that depart from the use of the burnout construct. Tracing the genesis of the burnout construct, we observe that (a) burnout's definition was preestablished rather than derived from a rigorous research process and (b) the MBI has little in the way of a theoretical or empirical foundation. Historical analysis suggests that the burnout construct was cobbled together from unchallenged personal impressions and anecdotal evidence before getting reified by the MBI. This state of affairs may account for many of the disconcerting problems encountered in burnout research. We close our paper by presenting the Occupational Depression Inventory (ODI), a recently developed instrument reflective of a renewed approach to job-related distress. The ODI has demonstrated robust psychometric and structural properties across countries, sexes, age groups, occupations, and languages. The instrument addresses job-related distress both dimensionally and categorically. A dimensional approach can be useful, for instance, in examining the dynamics of etiological processes and symptom development. A categorical approach can serve screening and diagnostic purposes and help clinicians and public health professionals in their decision-making. It is concluded that the ODI offers occupational health specialists a promising way forward.

Renal outcome and plasma methylmalonic acid levels after isolated or combined liver or kidney transplantation in patients with methylmalonic acidemia: A multicenter analysis.

BACKGROUND: Methylmalonic acidemia (MMAemia) is characterized by accumulation of methylmalonic acid (MMA) in all body tissues. To minimize disease-related complications, isolated kidney (KTx), liver (LTx) or combined liver-kidney transplantation (LKTx) have been suggested. However, the impact of these different transplant strategies on outcome are unclear. METHODS: In this multicenter retrospective observational study, we compared plasma MMA levels and estimated glomerular filtration rate (eGFR) data of 83 patients. Sixty-eight patients (82%) had a mut0-type MMAemia, one patient had a mut--type MMAemia, and seven (7.3%) had an inherited defect in cobalamin metabolism (cblA- or cblB-type MMAemia). Median observation period was 3.7 years (0-15.1 years). RESULTS: Twenty-six (31%) patients underwent KTx, 24 (29%) LTx and 33 (40%) LKTx. Posttransplant, mean plasma MMA concentration significantly decreased in all three cohorts; but at month 12, plasma MMA in KTx (1372 ± 1101 µmol/L) was 7.8-fold higher than in LTx (176 ± 103 µmol/L; P < 0.001) and 6.4-fold higher than in LKTx (215 ± 110 µmol/L; P < 0.001). Comparable data were observed at month 24. At time of transplantation, mean eGFR in KTx was 18.1 ± 24.3 mL/min/1.73 m2, in LTx 99.8 ± 29.9 mL/min/1.73 m2, and in LKTx 31.5 ± 21.2 mL/min/1.73 m2. At month 12 posttransplant, mean eGFR in KTx (62.3 ± 30.3 mL/min/1.73 m2) was 33.4% lower than in LTx (93.5 ± 18.3 mL/min/1.73 m2; P = 0.0053) and 25.4% lower than in LKTx (83.5 ± 26.9 mL/min/1.73 m2; P = 0.0403). CONCLUSIONS: In patients with isolated MMAemia, LTx and LKTx lead to markedly lower plasma MMA levels during the first 2 years posttransplant than KTx and are associated with a better preservation of kidney function. LTx should therefore be part of the transplant strategy in MMAemia.

What possibly affects nighttime heart rate? Conclusions from N-of-1 observational data.

Background: Heart rate (HR), especially at nighttime, is an important biomarker for cardiovascular health. It is known to be influenced by overall physical fitness, as well as daily life physical or psychological stressors like exercise, insufficient sleep, excess alcohol, certain foods, socialization, or air travel causing physiological arousal of the body. However, the exact mechanisms by which these stressors affect nighttime HR are unclear and may be highly idiographic (i.e. individual-specific). A single-case or "n-of-1" observational study (N1OS) is useful in exploring such suggested effects by examining each subject's exposure to both stressors and baseline conditions, thereby characterizing suggested effects specific to that individual. Objective: Our objective was to test and generate individual-specific N1OS hypotheses of the suggested effects of daily life stressors on nighttime HR. As an N1OS, this study provides conclusions for each participant, thus not requiring a representative population. Methods: We studied three healthy, nonathlete individuals, collecting the data for up to four years. Additionally, we evaluated model-twin randomization (MoTR), a novel Monte Carlo method facilitating the discovery of personalized interventions on stressors in daily life. Results: We found that physical activity can increase the nighttime heart rate amplitude, whereas there were no strong conclusions about its suggested effect on total sleep time. Self-reported states such as exercise, yoga, and stress were associated with increased (for the first two) and decreased (last one) average nighttime heart rate. Conclusions: This study implemented the MoTR method evaluating the suggested effects of daily stressors on nighttime heart rate, sleep time, and physical activity in an individualized way: via the N-of-1 approach. A Python implementation of MoTR is freely available.

Designing a Social Robot Companion to Support Homecare: Usability Results.

Earlier studies show frail seniors often experience loneliness and depression. Moreover, frailty can lead problems with medication and nutrition patterns. The availability of family care and/or nursing care at home is limited. Digital companions, such as social robots, could complement homecare nurses, thereby improving the quality of care to frail seniors. The Guardian project has co- designed with end-users, a social robot providing social company and health support. To assess the digital and co-created solution, usability evaluations have been conducted with 43 participants distributed as fairly as possible between frail seniors, family carers and professional nurses; in three different European areas: The Netherlands, Italy and Switzerland. The goal of this study is to evaluate if the GUARDIAN solution is accepted by the target users and also gather data on how to improve the system for ensuring added-value in home care. The iterative method based on user-centered approach put the end-users at the centre of the usability evaluation. Through thematic analysis of the qualitative datasets, we conclude that a high number of users accept the solution and describe it as useful. End-user needs have been mainly addressed but some new improvements have been pointed out by the participants and some other needs have been uncovered.

Using Consumer-Wearable Activity Trackers for Risk Prediction of Life-Threatening Heart Arrhythmia in Patients with an Implantable Cardioverter-Defibrillator: An Exploratory Observational Study.

Ventricular arrhythmia (VA) is a leading cause of sudden death and health deterioration. Recent advances in predictive analytics and wearable technology for behavior assessment show promise but require further investigation. Yet, previous studies have only assessed other health outcomes and monitored patients for short durations (7−14 days). This study explores how behaviors reported by a consumer wearable can assist VA risk prediction. An exploratory observational study was conducted with participants who had an implantable cardioverter-defibrillator (ICD) and wore a Fitbit Alta HR consumer wearable. Fitbit reported behavioral markers for physical activity (light, fair, vigorous), sleep, and heart rate. A case-crossover analysis using conditional logistic regression assessed the effects of time-adjusted behaviors over 1−8 weeks on VA incidence. Twenty-seven patients (25 males, median age 59 years) were included. Among the participants, ICDs recorded 262 VA events during 8093 days monitored by Fitbit (median follow-up period 960 days). Longer light to fair activity durations and a higher heart rate increased the odds of a VA event (p < 0.001). In contrast, lengthier fair to vigorous activity and sleep durations decreased the odds of a VA event (p < 0.001). Future studies using consumer wearables in a larger population should prioritize these outcomes to further assess VA risk.

The use of proxies and proxy-reported measures: a report of the international society for quality of life research (ISOQOL) proxy task force.

AIMS: Proxy reports are often used when patients are unable to self-report. It is unclear how proxy measures are currently in use in adult health care and research settings. We aimed to describe how proxy reports are used in these settings, including the use of measures developed specifically for proxy reporting in adult health populations. METHODS: We systematically searched Medline, PsycINFO, PsycTESTS, CINAHL and EMBASE from database inception to February 2018. Search terms included a combination of terms for quality of life and health outcomes, proxy-reporters, and health condition terms. The data extracted included clinical context, the name of the proxy measure(s) used and other descriptive data. We determined whether the measures were developed specifically for proxy use or were existing measures adapted for proxy use. RESULTS: The database search identified 17,677 possible articles, from which 14,098 abstracts were reviewed. Of these, 11,763 were excluded and 2335 articles were reviewed in full, with 880 included for data extraction. The most common clinical settings were dementia (30%), geriatrics (15%) and cancer (13%). A majority of articles (51%) were paired studies with proxy and patient responses for the same person on the same measure. Most paired studies (77%) were concordance studies comparing patient and proxy responses on these measures. DISCUSSION: Most published research using proxies has focused on proxy-patient concordance. Relatively few measures used in research with proxies were specifically developed for proxy use. Future work is needed to examine the performance of measures specifically developed for proxies. SYSTEMATIC REVIEW REGISTRATION: PROSPERO No. CRD42018103179.

Study protocol for the ETMED-L project: longitudinal study of mental health and interpersonal competence of medical students in a Swiss university using a comprehensive framework of empathy.

INTRODUCTION: Physician interpersonal competence is crucial for patient care. How interpersonal competence develops during undergraduate medical education is thus a key issue. Literature on the topic consists predominantly of studies on empathy showing a trend of decline over the course of medical school. However, most existing studies have focused on narrow measures of empathy. The first aim of this project is to study medical students' interpersonal competence with a comprehensive framework of empathy that includes self-reported cognitive and affective empathy, performance-based assessments of emotion recognition accuracy, and a behavioural dimension of empathy. The second aim of the present project is to investigate the evolution of mental health during medical school and its putative link to the studied components of interpersonal competence. Indeed, studies documented a high prevalence of mental health issues among medical students that could potentially impact their interpersonal competence. Finally, this project will enable to test the impact of mental health and interpersonal competence on clinical skills as evaluated by experts and simulated patients. METHODS AND ANALYSIS: This project consists of an observational longitudinal study with an open cohort design. Each year during the four consecutive years of the project, every medical student (curriculum years 1-6) of the University of Lausanne in Switzerland will be asked to complete an online questionnaire including several interpersonal competence and mental health measures. Clinical skills assessments from examinations and training courses with simulated patients will also be included. Linear mixed models will be used to explore the longitudinal evolutions of the studied components of interpersonal competence and mental health as well as their reciprocal relationship and their link to clinical skills. ETHICS AND DISSEMINATION: The project has received ethical approval from the competent authorities. Findings will be disseminated through internal, regional, national and international conferences, news and peer-reviewed journals.

Using an Individual-Centered Approach to Gain Insights From Wearable Data in the Quantified Flu Platform: Netnography Study.

BACKGROUND: Wearables have been used widely for monitoring health in general, and recent research results show that they can be used to predict infections based on physiological symptoms. To date, evidence has been generated in large, population-based settings. In contrast, the Quantified Self and Personal Science communities are composed of people who are interested in learning about themselves individually by using their own data, which are often gathered via wearable devices. OBJECTIVE: This study aims to explore how a cocreation process involving a heterogeneous community of personal science practitioners can develop a collective self-tracking system for monitoring symptoms of infection alongside wearable sensor data. METHODS: We engaged in a cocreation and design process with an existing community of personal science practitioners to jointly develop a working prototype of a web-based tool for symptom tracking. In addition to the iterative creation of the prototype (started on March 16, 2020), we performed a netnographic analysis to investigate the process of how this prototype was created in a decentralized and iterative fashion. RESULTS: The Quantified Flu prototype allowed users to perform daily symptom reporting and was capable of presenting symptom reports on a timeline together with resting heart rates, body temperature data, and respiratory rates measured by wearable devices. We observed a high level of engagement; over half of the users (52/92, 56%) who engaged in symptom tracking became regular users and reported over 3 months of data each. Furthermore, our netnographic analysis highlighted how the current Quantified Flu prototype was a result of an iterative and continuous cocreation process in which new prototype releases sparked further discussions of features and vice versa. CONCLUSIONS: As shown by the high level of user engagement and iterative development process, an open cocreation process can be successfully used to develop a tool that is tailored to individual needs, thereby decreasing dropout rates.

Integration of personalized drug delivery systems into digital health.

Personalized drug delivery systems (PDDS), implying the patient-tailored dose, dosage form, frequency of administration and drug release kinetics, and digital health platforms for diagnosis and treatment monitoring, patient adherence, and traceability of drug products, are emerging scientific areas. Both fields are advancing at a fast pace. However, despite the strong complementary nature of these disciplines, there are only a few successful examples of merging these areas. Therefore, it is important and timely to combine PDDS with an increasing number of high-end digital health solutions to create an interactive feedback loop between the actual needs of each patient and the drug products. This review provides an overview of advanced design solutions for new products such as interactive personalized treatment that would interconnect the pharmaceutical and digital worlds. Furthermore, we discuss the recent advancements in the pharmaceutical supply chain (PSC) management and related limitations of the current mass production model. We summarize the current state of the art and envision future directions and potential development areas.

Co-Calibrating Physical and Psychological Outcomes and Consumer Wearable Activity Outcomes in Older Adults: An Evaluation of the coQoL Method.

Inactivity, lack of sleep, and poor nutrition predispose individuals to health risks. Patient-Reported Outcomes (PROs) assess physical behaviours and psychological states but are subject of self-reporting biases. Conversely, wearables are an increasingly accurate source of behavioural Technology-Reported Outcomes (TechROs). However, the extent to which PROs and TechROs provide convergent information is unknown. We propose the coQoL PRO-TechRO co-calibration method and report its feasibility, reliability, and human factors influencing data quality. Thirty-nine seniors provided 7.4 ± 4.4 PROs for physical activity (IPAQ), social support (MSPSS), anxiety/depression (GADS), nutrition (PREDIMED, SelfMNA), memory (MFE), sleep (PSQI), Quality of Life (EQ-5D-3L), and 295 ± 238 days of TechROs (Fitbit Charge 2) along two years. We co-calibrated PROs and TechROs by Spearman rank and reported human factors guiding coQoL use. We report high PRO-TechRO correlations (rS≥ 0.8) for physical activity (moderate domestic activity-light+fair active duration), social support (family help-fair activity), anxiety/depression (numeric score-sleep duration), or sleep (duration to sleep-sleep duration) at various durations (7-120 days). coQoL feasibly co-calibrates constructs within physical behaviours and psychological states in seniors. Our results can inform designs of longitudinal observations and, whenever appropriate, personalized behavioural interventions.

Towards accurate models for predicting smartphone applications' QoE with data from a living lab study.

Progressively, smartphones have become the pocket Swiss army knife for everyone. They support their users needs to accomplish tasks in numerous contexts. However, the applications executing those tasks are regularly not performing as they should, and the user-perceived experience is altered. In this paper, we present our approach to model and predict the Quality of Experience (QoE) of mobile applications used over WiFi or cellular network. We aimed to create predictive QoE models and to derive recommendations for mobile application developers to create QoE aware applications. Previous works on smartphone applications' QoE prediction only focus on qualitative or quantitative data. We collected both qualitative and quantitative data "in the wild" through our living lab. We ran a 4-week-long study with 38 Android phone users. We focused on frequently used and highly interactive applications. The participants rated their mobile applications' expectation and QoE and in various contexts resulting in a total of 6086 ratings. Simultaneously, our smartphone logger (mQoL-Log) collected background information such as network information, user physical activity, battery statistics, and more. We apply various data aggregation approaches and features selection processes to train multiple predictive QoE models. We obtain better model performances using ratings acquired within 14.85 minutes after the application usage. Additionally, we boost our models' performance with the users expectation as a new feature. We create an on-device prediction model with on-smartphone only features. We compare its performance metrics against the previous model. The on-device model performs below the full features models. Surprisingly, among the following top three features: the intended task to accomplish with the app, application's name (e.g., WhatsApp, Spotify), and network Quality of Service (QoS), the user physical activity is the most important feature (e.g., if walking). Finally, we share our recommendations with the application developers, and we discuss the implications of QoE and expectations in mobile application design.

Complementing Human Behavior Assessment by Leveraging Personal Ubiquitous Devices and Social Links: An Evaluation of the Peer-Ceived Momentary Assessment Method.

BACKGROUND: Ecological momentary assessment (EMA) enables individuals to self-report their subjective momentary physical and emotional states. However, certain conditions, including routine observable behaviors (eg, moods, medication adherence) as well as behaviors that may suggest declines in physical or mental health (eg, memory losses, compulsive disorders) cannot be easily and reliably measured via self-reports. OBJECTIVE: This study aims to examine a method complementary to EMA, denoted as peer-ceived momentary assessment (PeerMA), which enables the involvement of peers (eg, family members, friends) to report their perception of the individual's subjective physical and emotional states. In this paper, we aim to report the feasibility results and identified human factors influencing the acceptance and reliability of the PeerMA. METHODS: We conducted two studies of 4 weeks each, collecting self-reports from 20 participants about their stress, fatigue, anxiety, and well-being, in addition to collecting peer-reported perceptions from 27 of their peers. RESULTS: Preliminary results showed that some of the peers reported daily assessments for stress, fatigue, anxiety, and well-being statistically equal to those reported by the participant. We also showed how pairing assessments of participants and peers in time enables a qualitative and quantitative exploration of unique research questions not possible with EMA-only based assessments. We reported on the usability and implementation aspects based on the participants' experience to guide the use of the PeerMA to complement the information obtained via self-reports for observable behaviors and physical and emotional states among healthy individuals. CONCLUSIONS: It is possible to leverage the PeerMA method as a complement to EMA to assess constructs that fall in the realm of observable behaviors and states in healthy individuals.

Effects of Sleep Deprivation on Blood Glucose, Food Cravings, and Affect in a Non-Diabetic: An N-of-1 Randomized Pilot Study.

Abstract: Sleep deprivation is a prevalent and rising health concern, one with known effects on blood glucose (BG) levels, mood, and calorie consumption. However, the mechanisms by which sleep deprivation affects calorie consumption (e.g., measured via self-reported types craved food) are unclear, and may be highly idiographic (i.e., individual specific). Single-case or "n-of-1" randomized trials (N1RT) are useful in exploring such effects by exposing each subject to both sleep deprivation and baseline conditions, thereby characterizing effects specific to that individual. We had two objectives: (1) To test and generate individual-specific N1RT hypotheses of the effects of sleep deprivation on next-day BG level, mood, and food cravings in two non-diabetic individuals; (2) To refine and guide a future n-of-1 study design for testing and generating such idiographic hypotheses for personalized management of sleep behavior in particular, and for chronic health conditions more broadly. We initially did not find evidence for an idiographic effect of sleep deprivation, but better-refined post hoc findings indicate that sleep deprivation may have increased BG fluctuations, cravings, and negative emotions. We also introduce an application of mixed-effects models and pancit plots to assess idiographic effects over time.

"I Must Try Harder": Design Implications for Mobile Apps and Wearables Contributing to Self-Efficacy of Patients With Chronic Conditions.

BACKGROUND: Diverse wellness-promoting mobile health technologies, including mobile apps and wearable trackers, became increasingly popular due to their ability to support patients' self-management of health conditions. However, the patient's acceptance and use depend on the perceived experience and the app appropriateness to the patient's context and needs. We have some understating of the experience and factors influencing the use of these technologies in the general public, but we have a limited understanding of these issues in patients. OBJECTIVE: By presenting results from an explorative study, this paper aims to identify implications for the design of mobile apps and wearables to effectively support patients' efforts in self-management of health with a special emphasis on support for self-efficacy of activities contributing to health. METHODS: An explorative mixed-method study involving 200 chronically ill patients of Stanford Medical Center (Stanford, CA, United States) was conducted between mid-2016 and end of 2018. Amongst these, 20 patients were involved in a 4-weeks study, in which we collected the underlying wearable device use logs (e.g., Fitbit) and subjective use experience [via an Ecological Momentary Assessment (EMA)], as well as patients' momentary perception of general self-efficacy in their natural environments and different daily contexts. RESULTS: The results indicate that mobile apps for health and wearables have the potential to enable better self-management and improve patients' wellbeing but must be further refined to address different human aspects of their use. Specifically, the apps/wearables should be easier to use, more personalized and context-aware for the patient's overall routine and lifestyle choices, as well as with respect to the momentary patient state (e.g., location, type of people around) and health(care) needs. Additionally, apps and devices should be more battery efficient and accurate; providing timely, non-judgmental feedback and personalized advice to the patients anywhere-anytime-anyhow. These results are mapped on major sources of the individuals' self-efficacy. CONCLUSION: Our results show how the apps/wearables that are aimed at supporting the patients' self-management should be designed to leverage and further improve the patients' general self-efficacy and self-efficacy of activities contributing to chronic disease management.

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

For most women of reproductive age, assessing menstrual health and fertility typically involves regular visits to a gynecologist or another clinician. While these evaluations provide critical information on an individual's reproductive health status, they typically rely on memory-based self-reports, and the results are rarely, if ever, assessed at the population level. In recent years, mobile apps for menstrual tracking have become very popular, allowing us to evaluate the reliability and tracking frequency of millions of self-observations, thereby providing an unparalleled view, both in detail and scale, on menstrual health and its evolution for large populations. In particular, the primary aim of this study was to describe the tracking behavior of the app users and their overall observation patterns in an effort to understand if they were consistent with previous small-scale medical studies. The secondary aim was to investigate whether their precision allowed the detection and estimation of ovulation timing, which is critical for reproductive and menstrual health. Retrospective self-observation data were acquired from two mobile apps dedicated to the application of the sympto-thermal fertility awareness method, resulting in a dataset of more than 30 million days of observations from over 2.7 million cycles for two hundred thousand users. The analysis of the data showed that up to 40% of the cycles in which users were seeking pregnancy had recordings every single day. With a modeling approach using Hidden Markov Models to describe the collected data and estimate ovulation timing, it was found that follicular phases average duration and range were larger than previously reported, with only 24% of ovulations occurring at cycle days 14 to 15, while the luteal phase duration and range were in line with previous reports, although short luteal phases (10 days or less) were more frequently observed (in up to 20% of cycles). 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.