Maternal undernutrition and micronutrient deficiencies remain pervasive, contributing to adverse pregnancy outcomes and long-term health risks for mothers and offspring. Multiple micronutrient supplementation (MMS) during pregnancy has demonstrated benefits, including reduced risks of low birth weight, small-for-gestational-age births, and neonatal mortality, when compared with standard iron-folic acid supplementation. Current MMS strategies, however, often follow a standard MMS, overlooking variations in nutritional status, health profiles, and context. Advances in artificial intelligence (AI), particularly deep learning and natural language processing, provide opportunities to strengthen maternal nutrition programs by integrating diverse data sources. Rather than promising fully individualized recommendations, AI could help stratify women by risk of insufficiencies or deficiencies, highlight groups most likely to benefit from additional support, and inform the design of more responsive supplementation strategies during preconception and pregnancy. We outline a conceptual model in which multimodal health data-including electronic health records (EHRs), wearable sensor outputs, nutrition and fertility app logs, genomic markers, and sociodemographic information-are aggregated and analyzed by AI systems to inform personalized MMS plans. The framework introduces the concept of a "nutritional digital twin," a virtual profile of the patient's nutritional and metabolic state. This digital twin can simulate micronutrient needs and predict maternal-fetal outcomes under different supplementation scenarios, enabling clinicians to test scenario-based options (e.g. standard MMS ± targeted add-ons) for individuals. We describe how deep learning models can identify complex patterns (e.g. diet-genome interactions or behavioral trends) while natural language processing (NLP) algorithms extract clinically relevant insights from unstructured data (such as medical notes or patient queries). In addition, we discuss the role of digital maternal health tools, such as mobile apps and wearable trackers, in supplying real-time data to the AI models and in engaging women to improve adherence to supplementation regimens. Harnessing AI for MMS could transform maternal nutrition care in both high- and low-resource settings. In high-income contexts, rich data (comprehensive EHRs, genetic tests, continuous monitoring devices) could feed advanced predictive models to support risk-stratified care with protocolized supplementation options, under clinical oversight. In low- and middle-income countries, where maternal undernutrition and micronutrient gaps are most prevalent, AI-driven approaches can help stratify risk groups and optimize limited resources. Ubiquitous mobile phone access and digital health tools in many such settings provide avenues for data collection and intervention delivery. We highlight examples where machine learning on population data revealed "hidden hunger" patterns and key predictors of low supplement uptake (e.g. low education, minimal antenatal visits)-insights that policymakers can use to target nutrition programs. A nutritional digital twin could further allow scenario-testing (e.g. predicting the impact of adding a vitamin D supplement for a specific patient) before clinical decisions are made. To realize this vision, the key concerns are ethics, credibility, and fairness. Ethical frameworks must guide development so that sensitive reproductive health data are protected and clinician oversight remains central. The credibility of AI-generated recommendations depends on transparency about the assumptions used to translate nutritional and health data into supplement type and dose, and on prospective validation against maternal and neonatal outcomes. This requires a continuous feedback loop in which recommendations are tested in real-world settings and recalibrated using outcomes data, ensuring that the system learns from observed benefits and harms, rather than relying solely on theoretical modeling. Fairness demands that training data sets represent diverse populations and that solutions are tailored to local contexts to reduce bias and avoid widening disparities. Critically, the approach must be fed by data streams that extend beyond initial demographics and clinical baselines to include biomarkers, adherence patterns, and pregnancy outcomes, so that the models can be refined and dosing rules adjusted over time. If these safeguards are embedded, AI-enhanced personalized MMS can move beyond proof of concept towards a credible, equitable, and empirically grounded contribution to global maternal health. AI-driven personalized nutrition support represents a frontier in obstetric care. By combining clinical knowledge with data-driven intelligence, we can move beyond generalized prenatal supplements towards precision maternal nutrition. The integration of deep learning models and digital health innovations into antenatal care pathways has the potential to better nourish pregnancies, save lives, and ensure healthier futures for mothers and children worldwide.

Digital choices as emotional Mirrors: Mapping psychosocial profiles through smartphone app usage patterns.

Advances in health technology have enabled body composition assessments using smartphone photos, offering an accessible, cost-efficient, and portable alternative that can also be used by non-experts. However, it is essential to provide clarity on their technical development and estimation process for clinicians, researchers, and users. Here, we aimed to provide a technical description and guidance on the use and interpretation of a selected artificial intelligence (AI)-based app for body composition estimation. We selected one app as a representative for in-depth technical analysis, based on a non-systematic review of scientific databases, developer websites, search engines, and digital marketplaces, to generate insights relevant to similar tools. MeThreeSixty® app was selected due to its availability and validation for several body composition measures (body fat, fat mass, fat-free mass, and appendicular lean mass). The app integrates advanced technologies, such as three-dimensional (3D) imaging and AI, which improves its accuracy with potential for refinement. It also features a self-assessment function to enhance user accessibility. Early findings indicate the app provides reliable group-level results for body circumference and composition estimations, with refinements needed for individual assessments. MeThreeSixty app used 3D imaging and AI with acceptable group-level accuracy for estimating body circumference and composition, but limited precision at the individual level requires cautious interpretation. Further prospective validation and model refinement are needed, especially in diverse populations, and using longitudinal datasets before supporting personalized nutrition and broader health platform integration.

Eating disorders (EDs), including anorexia nervosa and bulimia nervosa, are complex, distressing and debilitating disorders that affect a significant proportion of adolescents. Maladaptive beliefs about eating and body image are well-established cognitive risk factors for the development and maintenance of EDs; therefore, targeting these beliefs is an important component of prevention programs. This randomized trial evaluated the effects of a cognitive behavioral framework-based mobile application designed to reduce vulnerability to EDs by targeting associated maladaptive beliefs. A non-clinical sample of adolescents (n=93; Mage=13.9; 56 girls) was randomized to use a mobile application targeting maladaptive beliefs related to EDs for approximately 5min a day during a 2-week period. The non-active control group used the same app, for the same period of time but with neutral content. Maladaptive belief related to EDs, ED symptoms, body satisfaction and self-esteem were measured at baseline (T1), immediately after two weeks of mobile application use (T2), and at 1-month follow-up (T3). Data obtained indicated that relative to those in the control condition, adolescents that used the application demonstrated a decrease in some ED-related maladaptive beliefs and symptoms. These effects were small-to-medium size and were maintained at 1-month. No significant effects were found regarding depression, body satisfaction or self-esteem. These results underscore the potential usefulness of brief, low-intensity, mobile interventions in reducing vulnerability to EDs in the adolescent population.

Promoting adherence to weight-related behaviors in young adults: Design of the Nudge microrandomized trial.

Early detection of cognitive decline may be effective in reducing the adverse impacts of Alzheimer's disease and related dementias (ADRD). Given that functional declines precede ADRD evaluation and diagnosis, regular assessments of everyday function are an avenue for detecting cognitive performance changes. While app-based measures of everyday function and cognition are promising tools for early detection, perceptions of these tools' value remain unexamined. This study explored perceptions of an app-based measure of everyday function (i.e., comfort with sharing performance data and perceived utility in healthcare) with community-dwelling midlife and older adults in South Carolina, United States (N = 131, Mage = 67.08 years). Participants completed daily tasks through a mobile app objectively measuring everyday function then shared their feedback through a semi-structured interview. Our thematic analysis found that interest and confidence in utilizing this technology was connected to beliefs around the value of having real-time information about one's cognitive performance, experiences with healthcare providers, and trust in technology security and accuracy. Additionally, some adults have not thought critically about the role of these technologies in their healthcare. As health-tracking technology expands in cognitive healthcare, researchers and practitioners must be aware of midlife and older adults' perceptions and educate users on its potential function.

The purpose of this study is to test the feasibility and exploratory within-participant changes associated with implementing a multiple-behavior self-monitoring intervention in a diabetes care and support program. In this 3-month mixed-method implementation study, 45 adults with type 2 diabetes were planned for enrollment from certified diabetes care and support programs. Participants logged diet, activity, blood glucose, and weight using smartphone apps or paper diaries, based on preference. All received a brief lifestyle intervention adapted from Look AHEAD (Action for Health in Diabetes). Outcomes included weight and A1C at 3 months, and feasibility was assessed through retention and qualitative interviews. Thirty-one participants completed the study. Participants showed modest within-participant weight loss and maintained glycemic control, with A1C remaining stable during the study period. Exploratory descriptive comparisons did not suggest meaningful differences between participants using smartphone versus paper methods. Qualitative interviews supported feasibility, with participants reporting the intervention as both acceptable and useful. Implementing a digital-optimized multiple-behavior self-monitoring intervention is feasible in a diabetes self-monitoring diabetes care and support program. The findings suggest that implementation of the intervention is feasible and acceptable, with observed weight loss and maintenance of glycemic control over 3 months.

Premenstrual syndrome (PMS) is associated with significant psychological distress and productivity loss in women. This study aimed to evaluate whether a low-intensity digital intervention-comprising a symptom-tracking smartphone application and standardized informational emails-could reduce the psychological burden of PMS among women who self-identified as experiencing PMS. We conducted a fully internet-based, open-label, parallel-group, nonrandomized controlled trial using centrally administered alternating allocation among women aged 18years or older in Japan who self-identified as experiencing PMS. Participants were allocated alternately to either a 3-month intervention group (daily symptom tracking using a smartphone app and twice-weekly informational emails) or a waitlist control group. The primary outcome was the between-group difference in change scores on the psychological subscale of the Japanese version of the PMS-Impact Scale, measured from baseline to 3months. Analyses were conducted per protocol. A total of 419 women were enrolled and assigned to either the intervention group (n = 210) or the waitlist control group (n = 209). Of these, 355 participants were included in the per-protocol analysis. The intervention group showed greater improvement in self-reported psychological distress than the waitlist control group. The between-group difference in change score, defined as intervention minus control, was - 1.37 points (95% CI, - 2.47 to - 0.27; p = 0.015). A simple, scalable digital intervention was associated with greater improvement in self-reported psychological distress among women who self-identified as experiencing PMS. These findings suggest that accessible, non-clinician-led tools may have potential as a self-management strategy for PMS, although causal interpretation is limited by the nonrandomized design. This trial was registered with the University Hospital Medical Information Network Clinical Trials Registry (UMIN-CTR) on September 26, 2022. UMIN000048422.

Abstract Introduction Digital formats have the potential to enhance access and engagement of obesity treatment programs, yet little is known about how parents experience them. This qualitative study aimed to explore how parents of children aged 2–6 years perceived and experienced the digital delivery of a well-established and evidence-based parent support program (More and Less, ML) as treatment. The study was part of a larger randomized controlled trial (RCT) within the EU-funded STOP project, which compared the digital intervention with standard care. The treatment included a 10-week online version of the ML parent support program, followed by six months of continued support via a smartphone app. The ML program constituted the active treatment, while the follow-up app was introduced afterwards as a supportive tool to help families maintain changes. Methods Semi-structured interviews were conducted with 14 parents from 13 families (12 mothers and 2 fathers, mean age 38 years, range 30–47) in Sweden. Nine held a university degree. Their children (9 girls and 4 boys) were aged 2–6 years; 9 had obesity and 4 had overweight. Interviews were recorded, transcribed, and analyzed using thematic analysis guided by the COM-B model, which focuses on the capability, opportunity, and motivation required for behavior change. Results Two main themes were identified: Supporting each other (with subthemes Group support and Group learning ) and Support through digital programs (with subthemes Digital vs in-person engagement and Staying on track ). Parents highlighted the value of connecting with peers during group sessions, which fostered a sense of community and emotional safety. Although many preferred in-person meetings, the digital format was appreciated for its convenience. Motivation to use the app as follow-up varied; some found it helpful, while others expressed a desire for a more interactive and personalized format. Conclusion Parents managing childhood obesity benefit from supportive, nonjudgmental environments. Peer support—even when delivered digitally—enhances their confidence and engagement. Digital tools may also serve as a valuable complement to group-based treatment by extending support beyond the sessions. These findings suggest that future interventions should combine flexible digital components with peer support to enhance engagement and sustainability.

Wireless passive optical gas sensors reduce food waste by providing real-time freshness information through continuous biomarker analysis. However, their practical use remains limited by high cost, strict environmental requirements, poor stability, and device rigidity. Here, programmable carbon dots (CDs) were incorporated into a poly(vinylidene fluoride-co-hexafluoropropylene) (PVDF-HFP) electrospun film to monitor volatile fatty acid (VFA) levels in dairy products via fluorescence color changes. While the rational design of carboxylic and amino groups on the CD surface ensures wide-range pH sensitivity, the hydrophobic polymer matrix enables a self-cleaning mechanism for dynamic sensing. This colorimetric readout is further enhanced by a convolutional neural network model integrated into a mobile app, achieving over 98% accuracy in VFA assessment and providing a precise "best-before date." The simplicity and integrable design of this VFA sensor make it well suited for incorporation into dairy packaging, where it can reduce food waste and uphold safety standards. Broadly, this dynamic in situ pH sensor with a regenerable surface is effective in both liquid and vapor phases, offering diverse potential practical applications.

Informal carers provide essential support to individuals with mental health conditions, yet often experience poor well being and limited access to traditional supports due to stigma, time constraints, and geographic barriers. Self-accessible digital tools may offer a flexible and scalable solution. This scoping review explores the impact of self-accessible digital support tools on the well being and experience of informal carers of individuals with mental health conditions. Five databases were searched for peer-reviewed studies (2015-2025) evaluating digital tools for carers of individuals with mental health conditions, excluding neurocognitive disorders. Nine studies met the inclusion criteria and were assessed using the Mixed Methods Appraisal Tool. Seven unique digital tools were identified (three mobile apps, four web-based tools). Professionally developed tools appeared to be associated with greater improvements in caregiver burden, emotional regulation, and quality of life. Codesigned digital tools were positively received for their flexibility and relevance, but had mixed clinical outcomes and engagement challenges. Findings suggest that while digital tools can benefit carers, digital literacy, usability, and sustained engagement are critical factors. Codesign alone does not guarantee improved outcomes, particularly when user involvement is limited or underreported. Future research should further investigate codesigned interventions, with clear reporting of development processes and strategies that promote sustained use. Digital interventions can enhance the well being and experience of informal mental health carers, particularly those that are codesigned and multifactorial to address carer needs. Strengthening these tools has the potential to support carers and reduce systemic strain on mental health services.

Depression is common and mostly managed in primary care. In the Netherlands, general practitioners (GPs) and mental health nurses (GP-MHNs) generally start with education and lifestyle advice, yet the latter remains underused despite evidence of its effectiveness. Smartphone-based eHealth tools may help integrate lifestyle interventions into routine care by offering personalized support and monitoring. This study evaluates the (cost-)effectiveness of a Personalized eHealth Lifestyle Intervention (PLI) delivered via a smartphone app for patients with symptoms of depression in primary care. This multicenter, cluster-randomized controlled trial will be conducted in Dutch general practices. Practices will be randomized (1:1), stratified by region and area-level socioeconomic status, into two groups: (1) intervention group including care as usual plus the PLI, or (2) control group including care as usual plus a monitoring app. Within the PLI, patients will use an app for 6 months to set lifestyle goals, monitor progress in lifestyle behavior, and track symptoms of depression and anxiety. GPs and GP-MHNs will have access to patient progress through a web-based version. Control group patients will use a similar app for symptom tracking only. The primary outcome is the change in severity of symptoms of depression assessed with the Patient Health Questionnaire-9 (PHQ-9). Secondary outcomes include lifestyle behaviors, satisfaction with lifestyle, anxiety symptoms, patient satisfaction with treatment by GP and GP-MHNs, mental health-related quality of life, social support, use of antidepressants, use of anxiolytics, and utilization of medical and mental health services. Cost-effectiveness will also be evaluated. A total of 105 patients per arm (PHQ-9 ≥ 5) will be recruited. The results of this study will provide valuable insights into the clinical and economic impact of a digital lifestyle support tool. This trial aims to contribute to more accessible, personalized, sustainable, and cost-effective care for people with symptoms of depression in primary care. ClinicalTrials.gov NCT07022184. Registered on June 22, 2025.

Despite the notable proliferation of smoking cessation mobile apps, to date, no validated, Spanish-language, culturally tailored mobile intervention exists for Spanish speakers in the United States. The aim of this study was to conduct formative research to inform the adaptation of an evidence-based smoking cessation intervention developed for Spanish-speaking Hispanic and Latino individuals from a printed format into a mobile app. Guided by a user-centered approach and in collaboration with product design industry experts, wireframes were developed to present the app's layout and functionality. Focus groups were conducted over Zoom (Zoom Communications) with Spanish-speaking individuals who currently smoke to assess their previous mobile app experience, attitudes toward mobile apps, and feedback on app architecture and design. Two independent reviewers (RB in collaboration with another member from the qualitative core) trained in qualitative methods coded the focus group data using a thematic analysis approach and identified emerging themes. The app wireframes included 4 navigation buttons on the home screen to organize and deliver evidence-based intervention content-Home (Inicio), Learn (Aprende), My Coach (Mi Couch), and Profile (Perfil). Different wireframe designs were generated in distinct color palettes. Data saturation was reached after three focus groups. Participants were 54% (7/13) women, had a mean age of 56 (SD 14.9) years, 39% (5/13) had an education ≤high school, and 31% (4/13) were married or cohabitating. All participants smoked daily, a mean of 14 (SD 7.8) cigarettes per day, for 32 (SD 16.9) years, and 54% (7/13) smoked ≤30 minutes of waking. Participants reported using social media, news, shopping, and gaming apps, but few used mobile health apps. Salient barriers for app use included worries regarding privacy breaches and fears about misinformation. Desired features included community-building elements, personalization, reward badges, knowledge checks, and audiovisual presentation of content within the app. Participants disliked having a countdown to quit date, preferring an "I quit" button to initiate monitoring progress. They also viewed sharing progress with support networks as a source of unwanted pressure, although a few saw it as motivational. Overall, participants liked the app design and indicated willingness to use it. This formative research provides critical insights into preferences related to the development of culturally tailored mobile smoking cessation interventions for Spanish-speaking individuals. Key findings highlighted enthusiasm for a smoking cessation app and the importance of including features that foster social connection and allow for personalization.

Wearable sensors are transforming physical education by enabling real-time monitoring and feedback to improve athletes’ performance. These sensors, combined with advanced technologies, bridge the gap between traditional methods and data-driven training models. However, current practices are subjective, leading to discrepancies in measuring physical activity, performance, and progress, with slow feedback for corrective actions. This research proposes the IoT-empowered Proactive-Pulsed Energizing (IoT-PE) model, integrating wearable sensors with cloud computing and mobile apps. The IoT-PE system collects real-time data on heart rate, movement, and calories burned, providing instant feedback through mobile and web applications. It ensures consistent, accurate assessments and enhances engagement through interactive feedback tools. The model personalizes training, allowing educators to tailor sessions based on individual needs. It also provides teachers with actionable insights and data visualizations for informed decision-making. By improving the accuracy of physical activity evaluations, fostering positive athlete interactions, and supporting continuous improvement through real-time feedback, the IoT-PE model enhances the quality of physical education. Furthermore, it encourages long-term fitness practices among athletes, contributing to a data-driven strategy for promoting lifelong health and fitness.

Scalable, low-burden tools are needed to identify individuals at risk of depression before progressing to a clinically significant level of depressive disorder. We evaluated a smartphone framework for subclinical-depression risk using self-supervised speech representations and a field-ready data-collection protocol. Participants (N = 119) were stratified into high-risk (PHQ-9 ≥ 10; n = 64) and low-risk (n = 55) groups. A mobile app elicited two 1-minute narrative recordings using negative and positive mood-induction tasks, separated by a 10-minute neutral interval. We compared four models: extreme gradient boosting on handcrafted features; a convolutional neural network-recurrent neural network (CNN-RNN) on mel-spectrograms; head-only WavLM-MLP; and fully fine-tuned WavLM (WavLM-FT). Performance was estimated using 5-fold cross-validation (CV) and out-of-fold (OOF) aggregation. In a 5-fold CV, WavLM-FT achieved the highest area under the receiver operating characteristic curve (ROC-AUC) of 0.90, area under the precision-recall curve of 0.90, F1 of 0.73, accuracy of 0.68, recall of 0.89, and precision of 0.65. In OOF subject-level predictions, WavLM-FT led (ROC-AUC 0.86; accuracy 0.79) and outperformed CNN-RNN and WavLM-MLP. Results suggest full-model adaptation captures informative paralinguistic cues within standardized smartphone recordings. A brief, ecologically valid protocol with self-supervised learning may enable scalable, non-invasive depression-risk screening.

BackgroundOlder adults who have fallen are at an increased risk of future falls. Training cognitive and physical functions simultaneously, known as dual-task (DT) training, has been shown to improve mobility and reduce fall risks. With appropriate digital tools, such as smartphones and mobile apps, it is possible to deliver DT training in unsupervised, home-based settings, thereby increasing accessibility beyond the clinical environment.ObjectiveThis study aimed to evaluate the feasibility and acceptability of a technology-based DT training program delivered through a blended model of supervised and self-directed sessions for older adults with a history of falls. Perspectives of health care professionals working in fall-prevention services were also explored.MethodsA single-arm, nonrandomized feasibility study was conducted with 45 community-dwelling adults aged 65 years or older with a history of falls. Participants were recruited through primary care practices, secondary care fall-prevention services, and community outreach. The 24-week DT program, which integrated balance and strength exercises with cognitive training using a mobile app, was delivered in two phases: (1) for12 weeks, weekly 50-minute physiotherapist-led group classes in the community, and 2 additional 50-minute self-directed sessions at home, and (2) for 12 weeks, 3 weekly 50-minute self-directed sessions at home. Feasibility and acceptability were assessed through recruitment and retention rates, adherence, app usage, and self-reported satisfaction. Qualitative data were obtained from focus groups with 28 participants who completed the program and 16 health care professionals. Quantitative data were analyzed descriptively, and qualitative data were analyzed thematically.ResultsWe recruited 45 of the target 50 participants, with most participants (n=41) recruited through community pathways; 4 were recruited via National Health Service (NHS) pathways. Adherence was 64%, with higher adherence during phase 1 (81%) than phase 2 (50%). App usage was high (95%), and self-reported program satisfaction was moderate to high. Retention at 24 weeks was 76%, and no adverse events occurred. The qualitative findings supported the program’s feasibility and acceptability, emphasizing social connection and tailored exercises as key to adherence—especially in home-based sessions. Health care professionals identified community organizations and referral pathways as the most practical routes for implementation.ConclusionsA blended, technology-based DT training program is both feasible and acceptable for older adults at risk of falling and can be effectively delivered beyond clinical settings. Community-based recruitment outperformed NHS pathways, highlighting the value of community engagement. These findings support the feasibility and acceptability of a full-scale trial, with targeted refinements to recruitment, support structures, and delivery to maximize scalability and impact.

Physical Activity Self-Reflections: A Year-Long Analysis of Barriers and Facilitators in a Diabetes Prevention Program.

Documenting plant phenotypic data in the field is a common task necessary for the preservation of crop plant biodiversity in genebanks. Today, mobile applications are used to record data more efficiently and avoid errors. The Pheno-App is an open-source Android application developed to facilitate digital recording of plant phenotypic data at the Julius Kühn Institute (JKI) in Quedlinburg. Designed for tablets and smartphones, the application features customizable trials based on Excel formats, allowing both manual editing and machine processing. One major challenge in collecting phenotypic data during regeneration of plant genetic resources (PGR) in a genebank such as IPK is the diversity of crops and the many traits to record. To make the Pheno-App usable for specific genebank work, corresponding requirements were collected and implemented. The latest version, Pheno-App 2.0, is being developed at the IPK. Major advances over the original version include the ability to apply crop-specific trait sets within a single trial and efficiently input multiple observations per time point, such as percentage characterisations for population traits. These developments make Pheno-App 2.0 a versatile, evolving tool for genebank experts in conservation and characterisation of PGRs.

Objective Audiology-specific mobile apps enhance hearing healthcare by supporting self-management of ear and hearing conditions and their associated secondary impacts. However, app adoption by hearing care professionals (HCPs) and adults accessing hearing services remains inconsistent. Understanding the perceived barriers and facilitators influencing app use is critical for clinical integration. Design A cross-sectional survey exploring attitudes towards app use and factors influencing HCP recommendation of apps to adult clients. Survey development was informed by implementation science frameworks, including the Normalisation Process Theory (NPT) and determinants of digital engagement. Study sample Australian HCPs and adults accessing hearing services (aged 40–70 years). Results A total of 824 adults accessing hearing services and 191 HCPs participated. Almost all (97.5%) adults accessing hearing services owned a smartphone and 46.3% used mobile health (mHealth) apps. HCPs cited digital literacy, dexterity, and cognition as perceived barriers to app adoption, while adults accessing hearing services were more concerned about privacy, security, and cost. Conclusions Improving HCP’s awareness of available apps, confidence in assessing client digital literacy, and skills in addressing privacy, security, and cost concerns could support the integration of digital solutions in audiology, ensuring equitable access and benefit for all clients, regardless of age, ability, or socioeconomic status.

IntroductionTechnologies to help patients with type 2 diabetes mellitus (T2DM) have increased and have shown promising results in supporting self-management. However, not all applications consider healthcare providers’ knowledge in designing and developing these tools, which may impact adoption and effectiveness. This study examined healthcare providers’ perspectives on how mobile phone technologies can support patients with T2DM in self-managing their condition and inform user-centered design.MethodsWe conducted two online focus group sessions with nine healthcare providers involved in T2DM care. A semistructured guide was used to explore the participants’ perspectives on adopting mobile apps. Transcribed narratives were transcribed verbatim and analyzed using thematic analysis. The report followed COREQ guidelines for qualitative studies.ResultsFive main themes emerged: (1) diabetes—challenges and self-care; (2) the use of technologies in managing T2DM; (3) the market for diabetes management tools; (4) suggestions for ideal app features; and (5) the role of healthcare providers. Healthcare providers acknowledged the benefits of mobile apps in enhancing patient engagement to manage type 2 diabetes. Participants also pointed out the barriers to full implementation, such as usability challenges, patient digital literacy, and integration with clinical workflows. They also considered that patients with T2DM should provide feedback on digital health designs.ConclusionHealthcare providers’ involvement in developing an app ensures alignment with clinical practices and patients’ needs. The study's findings support the user-centered design of digital tools tailored to managing T2DM and may inform future digital health design and evaluation for T2DM or other chronic conditions.