Page Views Research Articles

961. Pandemic Hits: Evaluation of an Antimicrobial Stewardship Program Website for Hospital Communication During the COVID-19 Pandemic

Abstract Background Antibiotic Stewardship Programs (ASPs) assist front-line clinicians in synthesizing emerging data and establishing best practices. Our ASP team directly maintained and edited an internal web application, Duke CustomID®, to disseminate updated guideline, policy, and drug information during COVID-19. We aimed to describe website engagement and maintenance during the dynamic pandemic period. Methods We performed a descriptive, time-series analysis using Google Analytics software to measure engagement with Duke CustomID® during a 1-year pre-pandemic period through the Omicron surge: January 2019 to March 2022. We measured total page views (or “hits”), COVID-specific page hits, and days requiring COVID-specific page edits by week. Given fluctuations in hospitalization rates, we defined the primary outcome as the rate of hits divided by total hospitalizations. Weekly data were assessed graphically with positive COVID tests and COVID hospitalizations. We used negative binomial regression to quantify the association between COVID hospitalizations and hit rates and to trend engagement over time, adjusted for seasonality. We stratified data by COVID page and calculated a hit/edit ratio. Results Engagement with CustomID® increased during the pandemic period, especially during surges (Figure). Hits in the pre-pandemic period were median 1707 (range 1165-2354) per week, and hit rates median 1.95 per hospitalization (range 1.40-2.86). Peaks were observed in March 2020 (hit rate 4.59) and January 2022 (hit rate 3.87). On average, for every 100 COVID hospitalizations, the hit rate increased by 0.08 (0.004-0.16, p=0.04). Engagement slowly increased over the study period (relative rate week 1 versus 170: 1.15, 95% confidence interval 1.02-1.28, p=0.02). COVID page edits per week had a median of 2 (range 0-12). Adult Inpatient Guidelines and COVID Monoclonal Antibody pages had highest use (Table). Duke CustomID Hits and Maintenance Efforts over the Pandemic Top: COVID-specific CustomID hits per week (Green), Positive COVID tests per week (Blue) over time Middle: Total custom ID page hits relative to total hospitalizations per week (teal), COVID hospitalizations (Red) Bottom: Number of edits to COVID-specific CustomID pages per week, stratified by management pages and drug pages Several dates of significance are highlighted including the Emergency Use Authorizations (EUA) for remdesivir, the COVID Vaccines, and Paxlovid Duke CustomID COVID-19 Page Hits and Edits COVID specific pages on Duke CustomID with total hits, edits, and ratio over the pandemic Conclusion Our ASP’s website was a highly utilized, practical tool for disseminating practice-changing information during the pandemic. Use increased over time and especially during surges. An electronic reference customized for local practice and rapidly updated by ASPs offers critical support for front-line clinicians. Disclosures Martha B. Adams, M.D., Custom Clinical Decision Support, Inc: Board Member|Custom Clinical Decision Support, Inc: Ownership Interest Richard H. Drew, PharmD MS, American College of Clinical Pharmacists: Publication royalties|Takeda: Advisor/Consultant|UpToDate: publication royalties Rebekah W. Moehring, MD, MPH, FIDSA, FSHEA, UpToDate, Inc.: Author Royalties Michael J. Smith, M.D., M.S.C.E, Merck: Grant/Research Support|Pfizer: Grant/Research Support.

A two-phase model of collective memory decay with a dynamical switching point

Public memories of significant events shared within societies and groups have been conceptualized and studied as collective memory since the 1920s. Thanks to the recent advancement in digitization of public-domain knowledge and online user behaviors, collective memory has now become a subject of rigorous quantitative investigation using large-scale empirical data. Earlier studies, however, typically considered only one dynamical process applied to data obtained in just one specific event category. Here we propose a two-phase mathematical model of collective memory decay that combines exponential and power-law phases, which represent fast (linear) and slow (nonlinear) decay dynamics, respectively. We applied the proposed model to the Wikipedia page view data for articles on significant events in five categories: earthquakes, deaths of notable persons, aviation accidents, mass murder incidents, and terrorist attacks. Results showed that the proposed two-phase model compared favorably with other existing models of collective memory decay in most of the event categories. The estimated model parameters were found to be similar across all the event categories. The proposed model also allowed for detection of a dynamical switching point when the dominant decay dynamics exhibit a phase shift from exponential to power-law. Such decay phase shifts typically occurred about 10 to 11 days after the peak in all of the five event categories.

Cognitive and affective effects of teachers’ annotations and talking heads on asynchronous video lectures in a web development course

When it comes to asynchronous online learning, the literature recommends multimedia content like videos of lectures and demonstrations. However, the lack of emotional connection and the absence of teacher support in these video materials can be detrimental to student success. We proposed incorporating talking heads and annotations to alleviate these weaknesses. In this study, we investigated the cognitive and affective effects of integrating these solutions in asynchronous video lectures. Guided by the theoretical lens of Cognitive Theory of Multimedia Learning and Cognitive-Affective Theory of Learning with Media, we produced a total of 72 videos (average = four videos per subtopic) with a mean duration of 258 seconds (range = 193 to 318 seconds). To comparatively assess our video treatments (i.e., regular videos, videos with face, videos with annotation, or videos with face and annotation), we conducted an educational-based cluster randomized controlled trial within a 14-week academic period with four cohorts of students enrolled in an introductory web design and development course. We recorded a total of 42,425 total page views (212.13 page views per student) for all web browsing activities within the online learning platform. Moreover, 39.92% (16,935 views) of these page views were attributed to the video pages accumulating a total of 47,665 minutes of watch time. Our findings suggest that combining talking heads and annotations in asynchronous video lectures yielded the highest learning performance, longest watch time, and highest satisfaction, engagement, and attitude scores. These discoveries have significant implications for designing video lectures for online education to support students’ activities and engagement. Therefore, we concluded that academic institutions, curriculum developers, instructional designers, and educators should consider these findings before relocating face-to-face courses to online learning systems to maximize the benefits of video-based learning.

Changing Times

Changing Times

Education Theory Made Practical: Creating open educational resources via an apprenticeship model.

Clinical faculty may have limited knowledge of education theories and best practices in health professions education. Many faculty development programs focus on passive learning with limited application to practice. There is a need for more active engagement for early career educators. We created an apprenticeship-based electronic book series focused on translating education theories into practical applications for clinician educators. Chapters were authored by teams of two to four geographically separated early career educators, who were tasked with explaining an education theory and relating it to their educational practice. The chapters underwent internal peer review, followed by open peer review as a blog post and eventual publication. Usage data were collected, and surveys were sent to authors and end-users. Six volumes (60 total chapters) have been created to date by 180 unique authors and 17 editors over a 6-year period. There have been 65,571 total blog page views and 17,180 total book downloads across the five published volumes. Authors reported an increase in their perceived knowledge (pre 2.6 ± 1.7 vs. post 7.2 ± 1.1, mean difference 4.5/9.0, 95% confidence interval [CI] 4.0-5.0, p < 0.001) after writing their chapter. Authors also reported career benefits including authorship for academic advancement/promotion and developing an area of education theory expertise. End-users also reported a mean increase in their perceived knowledge (pre 4.4 ± 2.5 vs. post 7.3 ± 1.4, mean difference 2.9/9.0, 95% CI 2.1-3.8, p < 0.001) after reading a chapter. The Education Theory Made Practical electronic book series represents a proof of concept for an apprenticeship-based model to teach education theory, while also creating scholarship and open access resources for the broader community.

Global utilization of online information for substance use disorder: An infodemiological study of Google and Wikipedia from 2004 to 2022.

The increasing number of people who use drugs (PWUDs) can be attributed to the rising online sales of drugs and other related substances. Information on drugs and drug markets has also become easily accessible in web-search engines and social media. Aside from providing direct care, nurses have essential roles in preventing substance use disorder. These roles include health education, liaison, and researcher. Thus, nurses must examine and utilize the Internet, where information and transactions related to these substances are increasing. This study utilized an infodemiological design in exploring the worldwide information utilization for substance use disorder. Data were gathered from Google Trends and Wikimedia Pageview. The data included relative search volumes (RSV), top and rising related queries and topics, and Wikipedia page views between 2004 and 2022. After describing the data, autoregressive integrated mean averaging (ARIMA) models were used to predict future utilization of online information from Google and Wikipedia. Google trends ranked 37 countries based on the search volumes for substance use disorder. Ethiopia, Finland, the United States, Kenya, and Canada have the highest RSVs, while the lowest-ranked country is Turkey, followed by Mexico, Spain, Japan, and Indonesia. Google searches for substance use disorder-related information increased by more than 900% between 2004 and 2022. In addition, Wikipedia page views for substance use disorder-related information increased by almost 200% between 2015 and 2022. Based on the ARIMA models, RSVs and page views are predicted to increase by about 150% and 120% by December 2025. Top and rising search-related topics and queries revealed that the public increasingly utilized online information to understand specific substances and the possible mental health comorbidities related to substance use disorders. Their recent concerns revolved around diagnostics, specific substances, and specific disorders. The Internet can be of paradoxical use in substance use disorder. It has been previously reported to be increasingly used in drug trades, contributing to the increasing prevalence of substance use disorder. Likewise, the present study's findings revealed that it is increasingly utilized for substance use disorder-related information. Thus, nurses and other healthcare professionals should ensure that online information regarding substance use disorders is accurate and up-to-date. Nurse informaticists can form and lead Internet- and social-media-based health teams that perform national infodemiological investigations to assess online information. In doing so, they can inform, expand, and contextualize ehealth substance use education and strengthen the accessibility and delivery of substance use healthcare. In addition, public health nurses can collaborate to engage patients and communities in identifying harmful substance use disorder information online and creating culturally-appropriate messages that will correct misinformation and improve ehealth literacy, specifically in substance use disorder.

User Engagement Within an Online Peer Support Community (Depression Connect) and Recovery-Related Changes in Empowerment: Longitudinal User Survey.

The chronic nature of depression and limited availability of evidence-based treatments emphasize the need for complementary recovery-oriented services, such as peer support interventions (PSIs). Peer support is associated with positive effects on clinical and personal recovery from mental illness, but little is known about the processes of engagement that foster change, and studies targeting individuals with depression specifically are limited. This study aimed to evaluate whether the level of user engagement, assessed on several dimensions, in an online peer support community for individuals with depression promotes empowerment and the use of self-management strategies and reduces symptom severity and disability. In a longitudinal survey conducted from June 2019 to September 2020, we analyzed the data of the users of Depression Connect (DC), an online peer support community hosted by the Dutch Patient Association for Depression and the Pro Persona Mental Health Care institute, on measures of empowerment, self-management, depression, and disability. Of the 301 respondents, 49 (16.3%) respondents completed the survey again after 3 months and 74 (24.6%) respondents, after 6 months. Analysis of 3 parameters (ie, total time spent on the platform, number of page views, and number of posts) derived from their data logs yielded 4 engagement profiles. Linear mixed models were fitted to determine whether the outcomes had significantly changed over time and differed for the various profiles. Baseline engagement with the online peer support community was "very low" (177/301, 58.8%) or "low" (87/301, 28.9%) for most of the participants, with few showing "medium" (30/301, 9.9%) or "high" engagement patterns (7/301, 2.3%), while user profiles did not differ in demographic and clinical characteristics. Empowerment, self-management, depressive symptoms, and disability improved over time, but none were associated with the intensity or nature of user engagement. With most DC members showing very low to low engagement and only a few being identified as high-engaged users, it is likely that this flexibility in use frequency is what provides value to online PSI users. In other more formal supportive environments for depression, a certain level of engagement is predetermined either by their organizational or by their societal context; at DC, users can adapt the intensity and nature of their engagement to their current needs on their personal road to recovery. This study added to the current knowledge base on user engagement for PSIs because previous studies targeting depression with an online format focused on active users, precluding passive and flexible engagement. Future studies should explore the content and quality of the interactions in online PSIs to identify optimal user engagement as a function of current, self-reported clinical parameters and reasons to engage in the PSI.

Strategies to promote guideline adoption: lessons learned from the implementation of a national COVID-19 hospital guideline across NHS Wales

There is little understanding about what proportion of the target audience have read guidelines published through the traditional approach. The COVID-19 pandemic created a particularly difficult scenario for healthcare professionals (HCP) since the evidence base rapidly changed. In response, we established a freely accessible, video-based online resource, which was formally implemented requiring user registration. The guideline rapidly gained more than 4,500 registrants in the first wave alone, including nearly 100% of respiratory, intensive care or emergency unit consultants in Wales. During the first wave, there were nearly 170,000 page views with over 31,000 video plays and an average of 5.8 visits to the site per registrant. Acceptability using an online survey showed widespread support and that the unsubscribe rates were remarkably low. We suggest that this novel approach to guideline implementation achieved its aim of widespread engagement and acceptability and serves as a potential model for future medical guidelines and education beyond COVID-19.

Using Machine Learning to Model Advised-Investor Behavior

During periods of extreme market volatility, such as that experienced during the COVID-19 pandemic, advised investors may consider impulsive and inappropriate investment decisions like moving all assets to cash. Financial advisors, through proactive behavioral coaching, can help their clients avoid such decisions. But which clients need the most help? A predictive model that better identifies the clients most likely to react to market volatility can be an invaluable tool for financial advisors. Such a model requires insight into the investors’ mindset. In previous work, the authors focused on the perspective of the financial advisor and used natural language processing to explore advisors’ summary notes to extract such investor insights. They then used this novel data source as input for a machine-learning model to predict the investors most in need of intervention during volatile market periods. In this article, the authors further expand the model to include a unique dataset of investors’ digital activity, including investor-initiated contacts (via web, email, and phone) and web activity (page view and browsing history), to better reveal investor intention. Using machine-learning techniques, the authors build a model using this novel dataset as well as advisor notes, transaction activity, and a market volatility index to identify advised investors most in need of proactive intervention. The authors further describe the implication such work has for both traditional and robo-advisory service models.

173 Leveraging Syndromic Surveillance Data to Create Emergency Department COVID19 Data Visualization Tool

173 Leveraging Syndromic Surveillance Data to Create Emergency Department COVID19 Data Visualization Tool

Digital indicators of interest in natural world heritage sites

Due to their remoteness or boundless nature, activities at Natural Heritage Sites are difficult to monitor. In this study, two digital measures of the interest in Natural Word Heritage Sites are compared: one ex ante based on the number of Wikipedia page views of the site and another ex post derived from actual visitation as measured by the number of Instagram posts. The entire UNESCO database, which includes 248 Natural World Heritage Sites is linked to the 2.8 million Wikipedia page views, the 58 million Instagram posts and the Köppen extreme climate zone categories. Quantile regressions reveal that the main association in common for the two indicators is the risk of the site losing its inscription. Presence in the UNESCO Danger list is associated with reduced interest in a site, particularly in the number of Instagram posts and in the top quartile of Wikipedia views. Years since inscription is also an important explanatory variable, especially for the Instagram posts and the Wikipedia views in the top quartile. The UNESCO selection criterion of outstanding beauty only relates to the Instagram posts. Climate zone is mainly linked to the ex post variable and its upper quartile, where the sites with the most attention are found. Wikipedia views are also negatively associated with sites in Africa, the Arab countries and Latin America. Elevation, size of the area as well as kind of site are all variables not significant. There is a significant correlation between the two outcome variables with a coefficient of 0.5. While the Instagram posts relate clearly to actual visits, the Wikipedia page views is considered a possible leading indicator of future interest in a site.

Influencing factors of livestream selling of fresh food based on a push-pull model: A two-stage approach combining structural equation modeling (SEM) and artificial neural network (ANN)

Under the COVID-19, fresh food e-commerce has acquired new sales channels through live shopping, and the use of live broadcasts has become a hot spot in management and practice. However, there is little empirical evidence of the influence of live streaming on sales. This study combines the perspective of People-Goods-Scene and the push-pull theory, and proposes a two-stage method for forecasting sales volumes using structural equation models and artificial neural networks. It was found that the number of page views was the strongest predictor of live broadcast sales, while the numbers of interactive comments, live broadcasts with goods, and videos with goods, together with clean labels were weakly predictive. A comprehensive neural network model showed an accuracy of 83.76% in the prediction of live broadcast sales. These research results provide a theoretical basis for the prediction of fresh food shopping behavior in live-broadcast e-commerce from the perspectives of the consumers and the goods yard and provide ideas for the design of live broadcast content and optimization of user experience.

Cost of free open-access medical education (FOAM): An economic analysis of the top 20 FOAM sites.

Free open-access medical education (FOAM) is a growing resource within the field of medicine, in particular, emergency medicine. Yet despite FOAM's contribution to advancing medical education, the precise value of FOAM has never been calculated. As a result, content creators have not been acknowledged, either financially or academically, for their deliverables. The aim of this paper was to meet this challenge by determining a value for the top 20 FOAM sites as determined by web traffic in emergency medicine through two approaches. The first approach was to value the websites through a market-based method, where the value of the website was extrapolated from the number of blog posts published. The second approach was through a traffic analysis for each website. The top 20 FOAM websites in emergency medicine were identified and the monetary value of each resource was calculated through two methods, the first by extrapolating the number of blog posts published by each resource and the second through traffic analysis conducted by a third-party industry specialist based on the number of unique visitors and page visits. The median page views per month was 194,850 and the median number of unique visitors was 138,350. Based on the content valuation method, the median value of content produced in a year was $2337.06 per website. Through the traffic valuation method, the median overall value of a website was $22,815. Although two different approaches were used to value FOAM, both came to the same conclusion that there is substantial economic value being produced. This value should not go unrewarded and content creators should be acknowledged either academically or financially for their contributions.

Latent adversarial regularized autoencoder for high-dimensional probabilistic time series prediction

Many practical applications require probabilistic prediction of time series to model the distribution on future horizons. With ever-increasing dimensions, much effort has been invested into developing methods that often make an assumption about the independence between time series. Consequently, the probabilistic prediction in high-dimensional environments has become an essential topic with significant challenges. In this paper, we propose a novel probabilistic model called latent adversarial regularized autoencoder, abbreviated as TimeLAR, specifically for high-dimensional multivariate Time Series Prediction (TSP). It integrates the flexibility of Generative Adversarial Networks (GANs) and the capability of autoencoders in extracting higher-level non-linear features. Through flexible autoencoder mapping, TimeLAR learns cross-series relationships and encodes this global information into several latent variables. We design a modified Transformer for these latent variables to capture global temporal patterns and infer latent space prediction distributions, where only one step is required to output multi-step predictions. Furthermore, we employ the GAN to further refine the performance of latent space predictions, by using a discriminator to guide the training of the autoencoder and the Transformer in an adversarial process. Finally, complex distributions of multivariate time series data can be modeled by the non-linear decoder of the autoencoder. The effectiveness of TimeLAR is empirically underpinned by extensive experiments conducted on five real-world high-dimensional time series datasets in the fields of transportation, electricity, and web page views.

Welcome from the Editors

Welcome from the Editors

TV Snapshots

Discussion| September 01 2022 TV Snapshots: A Conversation with Lynn Spigel Bruno Guaraná Bruno Guaraná Bruno Guaraná is Master Lecturer of Film Studies in the Department of Film & Television at Boston University. Originally from Recife, Brazil, he received his PhD in Cinema Studies from New York University and his MA in Film from Columbia University. His current research explores negotiations of cultural citizenship in contemporary Brazilian media. He currently serves as the Page Views Editor for Film Quarterly. Search for other works by this author on: This Site PubMed Google Scholar BOOK DATA Lynn Spigel, TV Snapshots: An Archive of Everyday Life. Durham, NC: Duke University Press, 2022. $104.95 cloth, $27.95 paper. 328 pages. A Companion website and interactive archive of TV snapshots can be found at https://tvalbum.com. Film Quarterly (2022) 76 (1): 93–100. https://doi.org/10.1525/fq.2022.76.1.93 Views Icon Views Article contents Figures & tables Video Audio Supplementary Data Peer Review Share Icon Share Twitter LinkedIn Tools Icon Tools Get Permissions Cite Icon Cite Search Site Citation Bruno Guaraná; TV Snapshots: A Conversation with Lynn Spigel. Film Quarterly 1 September 2022; 76 (1): 93–100. doi: https://doi.org/10.1525/fq.2022.76.1.93 Download citation file: Ris (Zotero) Reference Manager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search Dropdown Menu toolbar search search input Search input auto suggest filter your search All ContentFilm Quarterly Search BOOK DATA Lynn Spigel, TV Snapshots: An Archive of Everyday Life. Durham, NC: Duke University Press, 2022. $104.95 cloth, $27.95 paper. 328 pages. A Companion website and interactive archive of TV snapshots can be found at https://tvalbum.com. Early in Todd Haynes’s melodrama Far from Heaven (2002), Cathy Whitaker (Julianne Moore) welcomes a reporter and a photographer to her home for a profile in the local Weekly Gazette. Cathy guides the reporter to her living room, where she sits down on the sofa next to a television set, as though posing for a candid shot. Haynes’s balanced composition, framed at eye level, lends equal attention to the protagonist and to the material objects surrounding her: colorful curtains, a vase, the TV set doubling as a stand for a bird sculpture, and, hanging on a wall, a framed advertisement partially cut off from the shot. As is later revealed,... You do not currently have access to this content.

32891 A cross-sectional study of dermatology articles in preprint servers

Background: Preprint servers allow researchers to post manuscripts before publication in peer-reviewed journals. An analysis of dermatology manuscripts in preprint servers has not been performed. Objectives: To analyze characteristics of dermatology preprints and assess preprint publication policies in top dermatology journals. Methods: Biology/health sciences preprint servers were searched (3/3/21-3/24/21) with keywords “dermatology,” “skin,” and “cutaneous.” Preprint server, preprint post date, location, metrics, journal, impact factor (IF), and journal publication date were recorded. Preprint policies of the top 20 dermatology journals were reviewed (https://www.scimagojr.com/). Results: A total of 1420 articles were posted to 11 preprint servers 6/20/07-2/15/21, and 377 (27%) were published in peer-reviewed journals, with 350 (93%) published within one year of preprint post. Preprints were published in 203 journals with mean IF 6.2. Growth in preprint posts by year (2007-2020) was exponential (R2 = 0.78). On average, preprints were viewed 496 times, with published vs. unpublished preprints viewed more often (596 vs. 362 views) (P < .001). Only 23/777 (3%) preprints with comments enabled had feedback. Among the top 20 dermatology journals, 18 (90%) allowed, 1 (5%) evaluated case-by-case, and 1 (5%) prohibited preprints. Conclusions: Our study showed exponential growth in dermatology preprints, a significant proportion published in peer-reviewed journals with high IF, and substantial number of page views for both published and unpublished preprints. Dermatologists should be aware of this trend both for disseminating their own scholarly work and for potentially obtaining the most current information relevant to their practice, while being aware that the data have not been peer-reviewed.

Betting on a buzz: Mispricing and inefficiency in online sportsbooks

Bookmakers sell claims to bettors that depend on the outcomes of professional sports events. Like other financial assets, the wisdom of crowds could help sellers to price these claims more efficiently. We use the Wikipedia profile page views of professional tennis players involved in over 10,000 singles matches to construct a buzz factor. This measures the difference between players in their pre-match page views relative to the usual number of views they received over the previous year. The buzz factor significantly predicts mispricing by bookmakers. Using this fact to forecast match outcomes, we demonstrate that a strategy of betting on players who received more pre-match buzz than their opponents can generate substantial profits. These results imply that sportsbooks could price outcomes more efficiently by listening to the buzz.

Usefulness of a Drug Information Resources Website (SAGASU-DI) Created Based on Inquiries to Clinical Pharmacists.

The use of drug information is increasing as the role of pharmacists expands. However, pharmacists spend a huge amount of time collecting drug information, and there has not been any drug information resource website that aims to improve the efficiency of community pharmacists with regard to drug information operations. The purpose of this study was to evaluate the usefulness of a drug information resources website (SAGASU-DI). SAGASU-DI articles were created based on inquiries to clinical pharmacists. The usage statistics of the SAGASU-DI were monitored using Google Analytics between May and July 2021. In addition, a pop-up questionnaire was used to evaluate the usefulness of the SAGASU-DI in answering the questions of viewers. Statistics showed that our website had 25,447 users and 33,000 page views, with a browsing time of 29 s on average. Visitors accessed the website through desktop (51.9%) and mobile (44.3%) systems. Community pharmacists accounted for 40.2% of the visitors. The pop-up questionnaire showed that 23.2% of the viewers were satisfied with our website, and 1.5% of the viewers were not. Although 65.1% of the viewers refused to answer the questionnaire, the average percentage of the viewers who were satisfied with the site was 94.1%. The SAGASU-DI was found to be a valuable resource website for drug information services, mainly for community pharmacists.

User engagement in relation to effectiveness of a digital lifestyle intervention (the HealthyMoms app) in pregnancy

Although user engagement is generally considered important for the effectiveness of digital behavior change interventions, there is a lack of such data in pregnancy. The aim of this study was therefore to examine the associations of user engagement with the HealthyMoms app with gestational weight gain, diet quality and physical activity in pregnancy. The study involved secondary analyses of participant data from the intervention group (n = 134) in a randomized controlled trial to determine the effectiveness of a 6-month mHealth intervention (the HealthyMoms app) on gestational weight gain, diet quality and physical activity. In adjusted regression models, the total number of registrations from three self-monitoring features (i.e., for weight-, diet- and physical activity) was associated with lower gestational weight gain (β = − 0.18, P = 0.043) and improved diet quality (β = 0.17, P = 0.019). These findings were mainly attributable to the associations of physical activity registrations with lower gestational weight gain (β = − 0.20, P = 0.026) and improved diet quality (β = 0.20, P = 0.006). However, the number of app sessions and page views were not associated with any of the outcomes. Our results may motivate efforts to increase user engagement in digital lifestyle interventions in pregnancy. However, additional studies are needed to further elucidate the influence of different types of user engagement in digital pregnancy interventions on their effectiveness.Trial registration: ClinicalTrials.gov (NCT03298555); https://clinicaltrials.gov/ct2/show/NCT03298555 (date of registration: October 2, 2017; date of first enrolled participant: October 24, 2017).