Wearable devices present transformative opportunities for personalized healthcare through continuous monitoring of digital biomarkers; however, individual variations in device wear time could mask or otherwise impact signal identification. Despite the widespread adoption of wearable devices in research, no comprehensive framework exists for understanding how wear time varies across populations or for addressing wear time-related biases in analysis. Using Fitbit data from 11,901 participants in the All of Us Research Program, we conducted the first large-scale systematic assessment of wearable device wear time across demographics, social determinants of health, lifestyle factors, mental health symptoms, and disease. Our findings revealed that wear time was higher among males and increased with age, income, and education, but decreased with depressive, anxiety, and anhedonia symptoms, with reductions more pronounced following clinical diagnoses compared to symptom-based classifications. Individuals with chronic conditions displayed differential levels of wear time compared to healthy controls. Critically, we demonstrate that the widely used ≥10-hour daily compliance threshold, while appropriate for some research contexts, can disproportionately exclude days of data from disease populations: among individuals with major depressive disorder, 74.4% of data days were excluded compared to 20.9% for controls. We propose a flexible methodological framework including standard compliance thresholds, wear time covariate adjustment, metric normalization, propensity score matching, and adaptive thresholds that can be applied individually or in combination to optimize wearable data retention across diverse research contexts. These findings establish wear time as a critical methodological consideration for wearable device research and provide guidance for advancing equitable and rigorous digital health analytics.

Fanconi anemia (FA) is a rare genetic disorder of impaired DNA repair characterized by progressive bone marrow failure, congenital malformations, and cancer predisposition. Early identification of individuals with FA is critical for timely clinical management, yet phenotype-driven approaches to FA identification are hindered by inconsistencies in existing phenotypic profiles. We compared the Human Phenotype Ontology (HPO) annotations for FA in OMIM (215 terms across 22 complementation group entries) and Orphanet (106 terms in a single entry, ORPHA:84), quantifying overlap and anatomical system coverage. To address identified gaps, we developed a comprehensive custom HPO profile by extracting phenotypic terms from the entire Fanconi Cancer Foundation (FCF) Clinical Care Guidelines using OntoGPT, an LLM-based ontology extraction tool, followed by manual curation to ensure accuracy and clinical relevance. OMIM and Orphanet shared only 36 HPO terms (12.6% of their combined 285 unique terms), demonstrating substantial discordance. Our custom profile comprises 264 unique HPO terms, of which 161 (61.0%) are novel and not present in either existing source. The novel terms expand coverage particularly in musculoskeletal (39 terms, 23.8%), genitourinary (26 terms, 15.9%), limb (26 terms, 15.9%), head or neck (20 terms 12.2%), and digestive system (17 terms, 10.4%) phenotypes. Community-curated phenotypic profiles derived from clinical practice guidelines can substantially augment existing disease annotations. Our FA profile, the most comprehensive HPO-based phenotypic characterization of FA to date, is publicly available and provides a foundation for improved clinical decision support and EHR-based computable phenotyping that can accelerate diagnosis for individuals with FA. Furthermore, the LLM-assisted approach offers generalizable methods to improve the diagnostic odyssey for all rare diseases.

Precision medicine aims to enhance diagnosis, treatment, and prognosis by integrating multimodal data at the point of care. However, challenges arise due to the vast number of diseases, differing methods of classification, and conflicting terminological coding systems and practices used to represent molecular definitions of disease. This lack of interoperability artificially constrains the potential for diagnosis, clinical decision support, care outcome analysis, as well as data linkage across research domains to support the development or repurposing of therapeutics. There is a clear and pressing need for a unified system for managing disease entities⁠-including identifiers, synonyms, and definitions. To address these issues, we created the Mondo disease ontology-a community-driven, open-source, unified disease classification system that harmonizes diverse terminologies into a consistent, computable framework. Mondo integrates key medical and biomedical terminologies, including Online Mendelian Inheritance in Man (OMIM), Orphanet, Medical Subject Headings (MeSH), National Cancer Institute Thesaurus (NCIt), and more, to provide a comprehensive and accurate representation of disease concepts with fully provenanced and attributed links back to the sources. Mondo can be used as the handle for curation of gene-disease associations utilized in diagnostic applications, research applications such as computational phenotyping, and in clinical coding systems in clinical decision support by pointing the clinician to the numerous knowledge resources linked to the Mondo identifier. Mondo's community-centric approach, stewarded by the Monarch Initiative's expertise in ontologies, ensures that the ontology remains adaptable to the evolving needs of biomedical research and clinical communities, as well as the knowledge providers.

BackgroundElectronic health records (EHRs) provide valuable insights to address clinical and epidemiological research concerning HIV, including the disproportionate impact of the COVID-19 pandemic on people living with HIV. To identify this population, most studies using EHR or claims databases start with diagnostic codes, which can result in misclassification without further refinement using drug or laboratory data. Furthermore, given that antiretrovirals now have indications for both HIV and COVID-19 (ie, ritonavir in nirmatrelvir/ritonavir), new phenotyping methods are needed to better capture people living with HIV. Therefore, we created a generalizable and innovative method to robustly identify people living with HIV, preexposure prophylaxis (PrEP) users, postexposure prophylaxis (PEP) users, and people not living with HIV using granular clinical data after the emergence of COVID-19. ObjectiveThe primary aim of this study was to use computational phenotyping in EHR data to identify people living with HIV (cohort 1), PrEP users (cohort 2), PEP users (cohort 3), or “none of the above” (people not living with HIV; cohort 4) and describe COVID-19–related characteristics among these cohorts. MethodsWe used diagnostic and laboratory measurements and drug concepts in the National Clinical Cohort Collaborative to create a computational phenotype for the 4 cohorts with confidence levels. For robustness, we conducted a randomly sampled, blinded clinician annotation to assess precision. We calculated the distribution of demographics, comorbidities, and COVID-19 variables among the 4 cohorts. ResultsWe identified 132,664 people living with HIV with a high level of confidence, 36,088 PrEP users, 4120 PEP users, and 20,639,675 people not living with HIV. Most people living with HIV were identified by a combination of medical conditions, laboratory measurements, and drug exposures (74,809/132,664, 56.4%), followed by laboratory measurements and drug exposures (15,241/132,664, 11.5%) and then by medical conditions and drug exposures (14,595/132,664, 11%). A higher proportion of people living with HIV experienced COVID-19–related hospitalization (4650,132,664, 3.5%) or mortality (828/132,664, 0.6%) and all-cause mortality (2083/132,664, 1.6%) compared to other cohorts. ConclusionsUsing an extensive phenotyping algorithm leveraging granular data in an EHR repository, we have identified people living with HIV, people not living with HIV, PrEP users, and PEP users. Our findings offer transferable lessons to optimize future EHR phenotyping for these cohorts.

Ontologies are structured frameworks for representing knowledge by systematically defining concepts, categories, and their relationships. While widely adopted in biomedicine, ontologies remain largely absent in mental health research and clinical care, where the field continues to rely heavily on existing classification systems (e.g., the DSM). Although useful for clinical communication and administrative purposes, they lack the semantic structure, computational properties, and reasoning properties needed to integrate diverse data sources or support artificial intelligence-enabled analysis. This reliance on classification systems limits efforts to analyze and interpret complex, heterogeneous psychiatric data. In mood disorders, particularly bipolar disorder, the lack of formalized semantic models contributes to diagnostic inconsistencies, fragmented data structures, and barriers to precision medicine. By contrast, ontologies provide a standardized, machine-readable foundation for linking multimodal data sources, such as electronic health records, genetic and neuroimaging data, and social determinants of health, while enabling secure, deidentified computation. In this review, we survey the current landscape of mental health ontologies and highlight the Human Phenotype Ontology (HPO) as a promising framework for bridging psychiatric and medical phenotypes. We describe ongoing efforts to enhance the HPO through curated psychiatric terms, refined definitions, and structured mappings of observed phenomena. The Global Bipolar Cohort (GBC), an international collaboration, exemplifies this approach through the development of a consensus-driven ontology tailored to bipolar disorder. By supporting semantic interoperability, reproducible research, and individualized care, ontology-based approaches provide essential infrastructure for overcoming the limitations of classification systems and advancing data-driven precision psychiatry.

Objectives:Long COVID is a debilitating condition that impacts millions of Americans, but patients and clinicians have little information on how to prevent this disorder. Vaccination is a vital tool in preventing acute COVID-19 and may confer additional protection against Long COVID. There is limited evidence regarding the optimal timing of COVID-19 vaccination (i.e., vaccination schedule) to minimize the risk of Long COVID. Methods:We applied Longitudinal Targeted Maximum Likelihood Estimation to electronic health record (EHR) data from a retrospective cohort of patients vaccinated against COVID-19 between December 2021 and September 2022. We evaluated the association between binary COVID-19 vaccination status (two or more doses vs. zero doses) and 12-month Long COVID risk among patients diagnosed with acute COVID-19 between December 2021 and September 2022. In addition, we compared the 12-month cumulative risk of Long COVID (ICD-10 code U09.9) among patients diagnosed with acute COVID-19 one to three months after vaccination, three to five months after vaccination, or five to seven months after vaccination while adjusting for relevant high-dimensional baseline and time-dependent covariates. Results:We analyzed EHR data from a retrospective cohort of 1,558,018 patients. In our binary cohort (n = 519,980), we found that vaccinated patients had a lower risk of Long COVID than unvaccinated patients (adjusted marginal risk ratio 0.84 (0.81, 0.88)). In our longitudinal cohort (n = 1,085,291), we did not find a significant difference in Long COVID risk comparing patients who were diagnosed with acute COVID-19 one to three months after vaccination versus patients who were diagnosed with COVID-19 three to five months (adjusted marginal risk ratio 0.93 (95% CI 0.62, 1.41) or 5 to 7 months (adjusted marginal risk ratio 1.06 (95% CI 0.72, 1.56)) after vaccination. Conclusions:We found that COVID-19 vaccination before SARS-CoV-2 infection was protective against Long COVID, and we did not find that this protection significantly waned within 7 months after vaccination. These findings suggest that COVID-19 vaccination protects against Long COVID.

BackgroundPostpartum depression (PPD) is a mood disorder affecting 1 in 7 women after childbirth that is often underscreened and underdetected. If not diagnosed and treated, PPD is associated with long-term developmental challenges in the child and maternal morbidity. Wearable technologies, such as smartwatches and fitness trackers (eg, Fitbit), offer continuous and longitudinal digital phenotyping for mood disorder diagnosis and monitoring, with device wear time being an important yet understudied aspect. ObjectiveWe aimed to suggest that wear time of a wearable device may provide additional information about perinatal mental health to facilitate screening and early detection of PPD. We proposed that wear time of a wearable device may also be valuable for managing other mental health disorders. MethodsUsing the All of Us Research Program dataset, we identified females who experienced childbirth with and without PPD using computational phenotyping. We compared the percentage of days and number of hours per day females with and without PPD wore Fitbit devices during prepregnancy, pregnancy, postpartum, and PPD periods, determined by electronic health records. Comparisons between females with and without PPD were conducted using linear regression models. We also assessed the correlation between Fitbit wear time consistency (measured as the maximum number of consecutive days the Fitbit was worn) during prepregnancy and PPD periods in females with and without PPD using the Pearson correlation. All analyses were run with Bonferroni correction. ResultsOur findings showed a strong trend, although nonsignificant after multiple testing correction, that females in the PPD cohort wore their Fitbits more than those in non-PPD cohort during the postpartum (PPD cohort: mean 69.9%, 95% CI 42.7%-97%; non-PPD cohort: mean 50%, 95% CI 25.5%-74.4%; P=.02) and PPD periods (PPD cohort: mean 66.6%, 95% CI 37.9%-95.3%; non-PPD cohort: mean 46.4%, 95% CI 20.5%-72.2%; P=.02). We found no difference in the number of hours per day females in the PPD and non-PPD cohorts wore their Fitbit during any period of pregnancy. Finally, there was no relationship between the consistency of Fitbit wear time during prepregnancy and PPD periods (r=–0.05, 95% CI –0.46 to 0.38; P=.84); however, there was a trend, though nonsignificant, in Fitbit wear time consistency among females without PPD (r=0.25, 95% CI –0.02 to 0.49; P=.07). ConclusionsWe hypothesize that increased Fitbit wear time among females with PPD may be attributed to hypervigilance, given the common co-occurrence of anxiety symptoms. Future studies should assess the link between PPD, hypervigilance, and wear time patterns. We envision that wear time patterns of a wearable device combined with digital biomarkers such as sleep and physical activity could enhance early PPD detection using machine learning by alerting clinicians to potential concerns and facilitating timely screenings, which may have implications for other mental health disorders.

Introduction:Perinatal depression affects up to 30% of pregnant and postpartum women, which has increased since the COVID-19 pandemic, making rapidly identifying affected women a high clinical priority. While screening tools like the Edinburgh Postnatal Depression Scale (EPDS) are widely used, brevity is important for busy clinical practice to reduce administration time and patient burden. Current methods to shorten assessments rely on traditional psychometric approaches, rather than machine learning (ML) methods that could optimize predictive accuracy. Methods:We developed a ML framework using National Clinical Cohort Collaborative (N3C) data to predict full 10-item EPDS scores from shortened question subsets (n=22,924). We evaluated all 2-5 item combinations using linear regression, validating performance across multiple cohorts including postpartum women (n=7,750) and an external non-N3C pregnancy population (n=1,217). For additional validation, we applied our approach to the PHQ-9 (n=398,606) to test generalizability. Binary classification models using clinical thresholds (≥13) determined EPDS screening accuracy. Decision curve analysis was performed to assess the clinical utility of our ML method. Results:The optimal 2-question EPDS combinations Q4+Q8 (anxiety/sadness) and Q5+Q8 (scared/sadness) both achieved R2=0.70. Binary classification demonstrated strong performance (sensitivity=0.68-0.72, specificity=0.98-0.99). The framework generalized across postpartum subsets, external pregnancy cohorts, and PHQ-9 validation (R2=0.64-0.73). Adding covariates did not improve performance. Decision curve analysis showed our ML approach had superior clinical benefit (0.01-0.03) versus traditional additive scoring. Conclusion/Implications:Our ML framework suggests a reduced assessment burden with two EPDS questions maintains predictive accuracy as the full-item EPDS. With ~3.6 million annual U.S. births, this approach could identify additional positive perinatal depression screens, enhancing screening implementation across clinical settings.

We investigate risk factors for severe COVID-19 in persons living with HIV (PWH), including among racialized PWH, using the U.S. population-sampled National COVID Cohort Collaborative (N3C) data released from January 1, 2020 to October 10, 2022. We defined severe COVID-19 as hospitalized with invasive mechanical ventilation, extracorporeal membrane oxygenation, discharge to hospice or death. We used machine learning methods to identify highly ranked, uncorrelated factors predicting severe COVID-19, and used multivariable logistic regression models to assess the associations of these variables with severe COVID-19 in several models, including race-stratified models. There were 3 241 627 individuals with incident COVID-19 cases and 81 549 (2.5%) with severe COVID-19, of which 17 445 incident COVID-19 and 1 020 (5.8%) severe cases were among PWH. The top highly ranked factors of severe COVID-19 were age, congestive heart failure (CHF), dementia, renal disease, sodium concentration, smoking status, and sex. Among PWH, age and sodium concentration were important predictors of COVID-19 severity, and the effect of sodium concentration was more pronounced in Hispanics (aOR 4.11 compared to aOR range: 1.47-1.88 for Black, White, and Other non-Hispanics). Dementia, CHF, and renal disease was associated with higher odds of severe COVID-19 among Black, Hispanic, and Other non-Hispanics PWH, respectively. Our findings suggest that the impact of factors, especially clinical comorbidities, predictive of severe COVID-19 among PWH varies by racialized groups, highlighting a need to account for race and comorbidity burden when assessing the risk of PWH developing severe COVID-19.

BackgroundPostpartum depression (PPD) poses a significant maternal health challenge. The current approach to detecting PPD relies on in-person postpartum visits, which contributes to underdiagnosis. Furthermore, recognizing PPD symptoms can be challenging. Therefore, we explored the potential of using digital biomarkers from consumer wearables for PPD recognition. ObjectiveThe main goal of this study was to showcase the viability of using machine learning (ML) and digital biomarkers related to heart rate, physical activity, and energy expenditure derived from consumer-grade wearables for the recognition of PPD. MethodsUsing the All of Us Research Program Registered Tier v6 data set, we performed computational phenotyping of women with and without PPD following childbirth. Intraindividual ML models were developed using digital biomarkers from Fitbit to discern between prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods. Models were built using generalized linear models, random forest, support vector machine, and k-nearest neighbor algorithms and evaluated using the κ statistic and multiclass area under the receiver operating characteristic curve (mAUC) to determine the algorithm with the best performance. The specificity of our individualized ML approach was confirmed in a cohort of women who gave birth and did not experience PPD. Moreover, we assessed the impact of a previous history of depression on model performance. We determined the variable importance for predicting the PPD period using Shapley additive explanations and confirmed the results using a permutation approach. Finally, we compared our individualized ML methodology against a traditional cohort-based ML model for PPD recognition and compared model performance using sensitivity, specificity, precision, recall, and F1-score. ResultsPatient cohorts of women with valid Fitbit data who gave birth included <20 with PPD and 39 without PPD. Our results demonstrated that intraindividual models using digital biomarkers discerned among prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods, with random forest (mAUC=0.85; κ=0.80) models outperforming generalized linear models (mAUC=0.82; κ=0.74), support vector machine (mAUC=0.75; κ=0.72), and k-nearest neighbor (mAUC=0.74; κ=0.62). Model performance decreased in women without PPD, illustrating the method’s specificity. Previous depression history did not impact the efficacy of the model for PPD recognition. Moreover, we found that the most predictive biomarker of PPD was calories burned during the basal metabolic rate. Finally, individualized models surpassed the performance of a conventional cohort-based model for PPD detection. ConclusionsThis research establishes consumer wearables as a promising tool for PPD identification and highlights personalized ML approaches, which could transform early disease detection strategies.

The Human Phenotype Ontology (HPO) is a widely used resource that comprehensively organizes and defines the phenotypic features of human disease, enabling computational inference and supporting genomic and phenotypic analyses through semantic similarity and machine learning algorithms. The HPO has widespread applications in clinical diagnostics and translational research, including genomic diagnostics, gene-disease discovery, and cohort analytics. In recent years, groups around the world have developed translations of the HPO from English to other languages, and the HPO browser has been internationalized, allowing users to view HPO term labels and in many cases synonyms and definitions in ten languages in addition to English. Since our last report, a total of 2239 new HPO terms and 49235 new HPO annotations were developed, many in collaboration with external groups in the fields of psychiatry, arthrogryposis, immunology and cardiology. The Medical Action Ontology (MAxO) is a new effort to model treatments and other measures taken for clinical management. Finally, the HPO consortium is contributing to efforts to integrate the HPO and the GA4GH Phenopacket Schema into electronic health records (EHRs) with the goal of more standardized and computable integration of rare disease data in EHRs.

Bridging the gap between genetic variations, environmental determinants, and phenotypic outcomes is critical for supporting clinical diagnosis and understanding mechanisms of diseases. It requires integrating open data at a global scale. The Monarch Initiative advances these goals by developing open ontologies, semantic data models, and knowledge graphs for translational research. The Monarch App is an integrated platform combining data about genes, phenotypes, and diseases across species. Monarch's APIs enable access to carefully curated datasets and advanced analysis tools that support the understanding and diagnosis of disease for diverse applications such as variant prioritization, deep phenotyping, and patient profile-matching. We have migrated our system into a scalable, cloud-based infrastructure; simplified Monarch's data ingestion and knowledge graph integration systems; enhanced data mapping and integration standards; and developed a new user interface with novel search and graph navigation features. Furthermore, we advanced Monarch's analytic tools by developing a customized plugin for OpenAI’s ChatGPT to increase the reliability of its responses about phenotypic data, allowing us to interrogate the knowledge in the Monarch graph using state-of-the-art Large Language Models. The resources of the Monarch Initiative can be found at monarchinitiative.org and its corresponding code repository at github.com/monarch-initiative/monarch-app.

Background: Leveraging the National COVID-19 Cohort Collaborative (N3C), a nationally sampled electronic health records repository, we explored associations between individual-level social determinants of health (SDoH) and COVID-19-related hospitalizations among racialized minority people with human immunodeficiency virus (HIV) (PWH), who have been historically adversely affected by SDoH.Methods: We retrospectively studied PWH and people without HIV (PWoH) using N3C data from January 2020 to November 2023. We evaluated SDoH variables across three domains in the Healthy People 2030 framework: (1) healthcare access, (2) economic stability, and (3) social cohesion with our primary outcome, COVID-19-related hospitalization. We conducted hierarchically nested additive and adjusted mixed-effects logistic regression models, stratifying by HIV status and race/ethnicity groups, accounting for age, sex, comorbidities, and data partners.Results: Our analytic sample included 280,441 individuals from 24 data partner sites, where 3,291 (1.17%) were PWH, with racialized minority PWH having higher proportions of adverse SDoH exposures than racialized minority PWoH. COVID-19-related hospitalizations occurred in 11.23% of all individuals (9.17% among PWH, 11.26% among PWoH). In our initial additive modeling, we observed that all three SDoH domains were significantly associated with hospitalizations, even with progressive adjustments (adjusted odds ratios [aOR] range 1.36-1.97). Subsequently, our HIV-stratified analyses indicated economic instability was associated with hospitalization in both PWH and PWoH (aOR range 1.35-1.48). Lastly, our fully adjusted, race/ethnicity-stratified analysis, indicated access to healthcare issues was associated with hospitalization across various racialized groups (aOR range 1.36-2.00).Conclusion: Our study underscores the importance of assessing individual-level SDoH variables to unravel the complex interplay of these factors for racialized minority groups.

Abstract Background Long COVID, also known as post-acute sequelae of COVID-19 (PASC), is a poorly understood condition with symptoms across a range of biological domains that often have debilitating consequences. Some have recently suggested that lingering SARS-CoV-2 virus particles in the gut may impede serotonin production and that low serotonin may drive many Long COVID symptoms across a range of biological systems. Therefore, selective serotonin reuptake inhibitors (SSRIs), which increase synaptic serotonin availability, may be used to prevent or treat Long COVID. SSRIs are commonly prescribed for depression, therefore restricting a study sample to only include patients with depression can reduce the concern of confounding by indication. Methods In an observational sample of electronic health records from patients in the National COVID Cohort Collaborative (N3C) with a COVID-19 diagnosis between September 1, 2021, and December 1, 2022, and a comorbid depressive disorder, the leading indication for SSRI use, we evaluated the relationship between SSRI use during acute COVID-19 and subsequent 12-month risk of Long COVID (defined by ICD-10 code U09.9). We defined SSRI use as a prescription for SSRI medication beginning at least 30 days before acute COVID-19 and not ending before SARS-CoV-2 infection. To minimize bias, we estimated relationships using nonparametric targeted maximum likelihood estimation to aggressively adjust for high-dimensional covariates. Results We analyzed a sample (n = 302,626) of patients with a diagnosis of a depressive condition before COVID-19 diagnosis, where 100,803 (33%) were using an SSRI. We found that SSRI users had a significantly lower risk of Long COVID compared to nonusers (adjusted causal relative risk 0.92, 95% CI (0.86, 0.99)) and we found a similar relationship comparing new SSRI users (first SSRI prescription 1 to 4 months before acute COVID-19 with no prior history of SSRI use) to nonusers (adjusted causal relative risk 0.89, 95% CI (0.80, 0.98)). Conclusions These findings suggest that SSRI use during acute COVID-19 may be protective against Long COVID, supporting the hypothesis that serotonin may be a key mechanistic biomarker of Long COVID.

Individually, the COVID-19 and HIV pandemics have differentially impacted minoritized groups due to the role of social determinants of health (SDoH) in the U.S. Little is known how the collision of these two pandemics may have exacerbated adverse health outcomes. We evaluated county-level SDoH and associations with hospitalization after a COVID-19 diagnosis among people with (PWH) and without HIV (PWOH) by racial/ethnic groups. We used the U.S. National COVID Cohort Collaborative (January 2020-November 2023), a nationally-sampled electronic health record repository, to identify adults who were diagnosed with COVID-19 with HIV (n = 22,491) and without HIV (n = 2,220,660). We aggregated SDoH measures at the county-level and categorized racial/ethnic groups as Non-Hispanic (NH) White, NH-Black, Hispanic/Latinx, NH-Asian and Pacific Islander (AAPI), and NH-American Indian or Alaskan Native (AIAN). To estimate associations of county-level SDoH with hospitalization after a COVID-19 diagnosis, we used multilevel, multivariable logistic regressions, calculating adjusted relative risks (aRR) with 95

Postpartum depression (PPD), afflicting one in seven women, poses a major challenge in maternal health. Existing approaches to detect PPD heavily depend on in-person postpartum visits, leading to cases of the condition being overlooked and untreated. We explored the potential of consumer wearable-derived digital biomarkers for PPD recognition to address this gap. Our study demonstrated that intra-individual machine learning (ML) models developed using these digital biomarkers can discern between pre-pregnancy, pregnancy, postpartum without depression, and postpartum with depression time periods (i.e., PPD diagnosis). When evaluating variable importance, calories burned from the basal metabolic rate (calories BMR) emerged as the digital biomarker most predictive of PPD. To confirm the specificity of our method, we demonstrated that models developed in women without PPD could not accurately classify the PPD-equivalent phase. Prior depression history did not alter model efficacy for PPD recognition. Furthermore, the individualized models demonstrated superior performance compared to a conventional cohort-based model for the detection of PPD, underscoring the effectiveness of our individualized ML approach. This work establishes consumer wearables as a promising avenue for PPD identification. More importantly, it also emphasizes the utility of individualized ML model methodology, potentially transforming early disease detection strategies.