OBJECTIVE: Many countries risk failing the Sustainable Development Goal to reduce neonatal mortality to 12 in 1000 live births before 2030, necessitating intervention. This scoping review assesses available evidence from studies implementing smartphone application-based education and clinical decision support in neonatal emergency care in low- and middle-income countries and describes applied assessment tools to highlight gaps in the current literature.
METHODS: A systematic search on 28 March 2024 of PubMed, Web of Science, and EMBASE identified original research papers published in peer-reviewed journals after 2014 in English. The evaluation was based on Kirkpatrick\'s framework.
RESULTS: In total, 20 studies assessing eight different smartphone applications were included. Participants found applications acceptable and feasible in 11 of 14 studies. Knowledge and/or skills were improved in 11 of 12 studies. Behaviour was assessed in 10 studies by tracking app usage. Patient outcome was assessed in four studies, focusing on perinatal mortality, Basic Newborn Care outcomes and correct assessment of newborns.
CONCLUSIONS: Data from included studies further strengthens hope that smartphone applications can improve neonatal mortality rates in low- and middle-income countries. However, further research into the effectiveness of these applications is warranted. This review highlights gaps in the current literature and provides guidance for future trials.

UNASSIGNED: Counseling, nicotine replacement, and other cessation medications have been proven effective in smoking cessation. The wide-scale adoption of smartphones and other mobile devices has opened new possibilities for scalable and personalized smoking cessation approaches. The study investigated whether a smartphone application would be more effective than written material for smoking cessation and reduction in smoking in individuals undergoing low-dose computed tomography (LDCT) screening for lung cancer (NCT05630950).
UNASSIGNED: This randomized controlled trial enrolled 201 current smokers with marked smoking history (smoked ≥15 cigarettes/day for ≥25 years or smoked ≥10 cigarettes/day for ≥30 years). Participants were stratified by age and pack-years and randomized in 1:1 fashion to the developed smartphone application (experimental arm) or written material (standard of care). All the subjects underwent LDCT screening. Self-reported smoking cessation at three and six months were the primary endpoints of the study. The smoking-related secondary endpoints of the study were the percentage of individuals who had reduced the number of smoked cigarettes/d from the baseline.
UNASSIGNED: Between Nov 18, 2022, and Apr 14, 2023, 201 patients were screened at Oulu University Hospital, Finland, of whom all were randomly assigned to smartphone application (n = 101) or written cessation material (n = 100); 200 were included in the full analysis set. Study arms were well-balanced for all the studied demographic factors. Subjects randomized to the smartphone application arm had significantly higher rates for self-reported smoking cessation at three (19.8 versus 7.1%; OR 3.175 CI 95% 1.276-7.899) and six months (18.8 versus 7.1%; OR 2.847 CI 95% 1.137-7.128). In the experimental arm, individuals with a frequent use of the application had a higher chance for smoking cessation at three (p < 0.001) and six months (p = 0.003).
UNASSIGNED: The study showed that the developed smartphone application increases the likelihood for smoking cessation in individuals undergoing lung cancer LDCT screening.
UNASSIGNED: AstraZeneca, Roche, and Cancer Foundation Finland.

BACKGROUND: Magnetic resonance imaging (MRI) education is crucial in the undergraduate radiological technology curriculum. Traditional approaches, such as lectures and observation, are insufficient for enhancing student understanding. Educational tools dedicated to MRI learning are needed to improve students\' knowledge and comprehension.
OBJECTIVE: To develop an application for MRI learning via smartphones, and to assess students\' satisfaction with the application and its effectiveness as a self-learning tool for radiological technology students.
METHODS: The MRI learning application was developed using the Thunkable platform, covering MRI theory, equipment, pulse sequences, parameters, MRI safety, and artifacts. Seventy-three undergraduate radiological technology students were recruited and divided into app-users (n = 37) and non-users (n = 36). Pre- and post-tests, comprising 20 multiple-choice questions, were created and utilized to assess the effectiveness of the application. Pre- and post-test scores were then analyzed and compared between the two groups using a student\'s t-test. Finally, user satisfaction with the MRI learning application was assessed using a questionnaire with a five-point Likert scale.
RESULTS: The mean pre-test and post-test scores for the app-users group were 12.65 ± 3.24 and 13.95 ± 3.41, respectively, while those for the non-users group were 12.94 ± 2.99 and 13.94 ± 2.74, respectively. The mean post-test score was significantly increased after using the MRI learning application (P = 0.01). However, there was no significant difference in the mean scores of the pre- and post-tests between the two groups. All participants expressed a high level of satisfaction with the application (4.32 ± 0.11 points).
CONCLUSIONS: The developed smartphone application for MRI learning has the potential to enhance students\' knowledge. The survey results indicated a high level of satisfaction among users. Thus, the MRI learning application could serve as an alternative tool for radiological technology students seeking to deepen their understanding of MRI-related subjects.

UNASSIGNED: Despite remarkable progress in diabetes technology, most systems still require estimating meal carbohydrate (CHO) content for meal-time insulin delivery. Emerging smartphone applications may obviate this need, but performance data in relation to patient estimates remain scarce.
UNASSIGNED: The objective is to assess the accuracy of two commercial CHO estimation applications, SNAQ and Calorie Mama, and compare their performance with the estimation accuracy of people with type 1 diabetes (T1D).
UNASSIGNED: Carbohydrate estimates of 53 individuals with T1D (aged ≥16 years) were compared with those of SNAQ (food recognition + quantification) and Calorie Mama (food recognition + adjustable standard portion size). Twenty-six cooked meals were prepared at the hospital kitchen. Each participant estimated the CHO content of two meals in three different sizes without assistance. Participants then used SNAQ for CHO quantification in one meal and Calorie Mama for the other (all three sizes). Accuracy was the estimate\'s deviation from ground-truth CHO content (weight multiplied by nutritional facts from recipe database). Furthermore, the applications were rated using the Mars-G questionnaire.
UNASSIGNED: Participants\' mean ± standard deviation (SD) absolute error was 21 ± 21.5 g (71 ± 72.7%). Calorie Mama had a mean absolute error of 24 ± 36.5 g (81.2 ± 123.4%). With a mean absolute error of 13.1 ± 11.3 g (44.3 ± 38.2%), SNAQ outperformed the estimation accuracy of patients and Calorie Mama (both P > .05). Error consistency (quantified by the within-participant SD) did not significantly differ between the methods.
UNASSIGNED: SNAQ may provide effective CHO estimation support for people with T1D, particularly those with large or inconsistent CHO estimation errors. Its impact on glucose control remains to be evaluated.

Dietary and physical activity interventions through smartphone healthcare applications (apps) have recently surged in popularity as effective methods for weight loss. However, the specific factors contributing to successful weight loss remain uncertain. We conducted an analysis of baseline characteristics and app usage frequencies over three months among 68 Japanese adults with overweight and obesity who were assigned to the intervention group in a previous randomized controlled trial. Logistic regression analysis revealed a negative association (OR: 0.248; p = 0.018) between having a walking habit at baseline and successful weight loss, defined as a 3% reduction in initial weight. Additionally, slower walking speeds and family medical history were identified as potential predictors of successful weight loss. These findings offer insights into the profile of individuals who achieve success in weight loss through our smartphone app, providing valuable guidance for the development of future healthcare apps.

BACKGROUND: Methods available at home for capturing facial images to track changes in skin quality and evaluate skincare treatments are limited. In this study, we developed a smartphone camera application (app) for personalized facial aesthetic monitoring.
METHODS: A face alignment indicators (FAIN) system utilizing facial landmark detection, an artificial intelligence technique, to estimate key facial parts, was implemented into the app to maintain a consistent facial appearance during image capture. The FAIN system is composed of a fixed target indicator and an alignment indicator that dynamically changes its shape according to the user\'s face position, size, and orientation. Users align their faces to match the alignment indicator with the fixed target indicator, and the image is automatically captured when alignment is achieved.
RESULTS: We investigated the app\'s effectiveness in ensuring a consistent facial appearance by analyzing both geometric and colorimetric data. Geometric information from captured faces and colorimetric data from stickers applied to the faces were utilized. The coefficients of variation (CVs) for the L*, a*, and b* values of the stickers were higher compared to those measured by a colorimeter, with CVs of 14.9 times, 8.14 times, and 4.41 times for L*, a*, and b*, respectively. To assess the feasibility of the app for facial aesthetic monitoring, we tracked changes in pseudo-skin color on the cheek of a participant using skin-colored stickers. As a result, we observed the smallest color difference ∆Eab of 1.901, which can be considered as the experimentally validated detection limit using images acquired by the app.
CONCLUSIONS: While the current monitoring method is a relative quantification approach, it contributes to evidence-based evaluations of skincare treatments.

OBJECTIVE: The prototype \"Oldenburger Logopädie App\" (OLA) was designed to support voice therapy for patients with recurrent paresis, such as to accompany homework or as a short-term substitute for regular therapy due to dropouts, such as during the COVID-19 pandemic. The treating speech and language pathologists (SLPs) unlocks videos individually applicable to the respective patients, in which the SLPs instruct the individual exercises. The app can be used without information technology knowledge or detailed instructions.
METHODS: The prototype\'s usability was evaluated through a usability test battery (AttrakDiff questionnaire, System Usability Scale, Visual Aesthetics of Websites Inventory questionnaire) and informal interviews from the perspective of patients and SLPs.
RESULTS: The acceptance, usability, user experience, self-descriptiveness, and user behavior of OLA were consistently given and mostly rated as positive. Both user groups rated OLA as practical and easy to use (eg, System Usability Scale: \"practical\" (agree: ∅ 49.5%), \"cumbersome to use\" (total: strongly disagree: ∅ 60.0%). However, the monotonous layout of the app and the instructional and exercise videos should be modified in the next editing step. An overview of relevant criteria for a voice therapy app, regarding design and functions, was derived from the results.
CONCLUSIONS: This user-oriented feedback on the usability of the voice app provides the proof of concept and the basis for the further development of the Artificial intelligence-based innovative follow-up app LAOLA. In the future, it should be possible to support the treatment of all voice disorders with such an app. For the further development of the voice app, the therapeutic content and the effectiveness of the training should also be investigated.

BACKGROUND: Mild cognitive impairment (MCI) involves cognitive decline beyond typical age-related changes, but without significant daily activity disruption. It can encompass various cognitive domains as the causes of MCI are diverse. MCI as well as frequent comorbid neuropsychiatric conditions like depression and anxiety affect individuals\' quality of life. Early interventions are essential, and computerized cognitive training (cCT) is an established treatment method. This paper presents the protocol for the NeuroNation MED Effectiveness Study, evaluating the self-administered mobile cCT intervention (\"NeuroNation MED\") in individuals with MCI to assess training effects on cognitive domains, health competence, neuropsychiatric symptoms, psychological well-being, and the general application usability.
METHODS: This study protocol presents a single-blinded multicenter randomized controlled trial that will be carried out in six study centers in Germany and Luxembourg. We included adults with MCI (existing F06.7 ICD-10-GM diagnosis and TICS ≥ 21 and ≤ 32). The intervention group will use a mobile, multi-domain cCT (\"NeuroNation MED\") for 12 weeks. Meanwhile, the wait list control group will receive standard medical care or no care. The eligibility of volunteers will be determined through a telephone screening. After completion of the baseline examination, patients will be randomly assigned to one of the experimental conditions in a 2:1 ratio. In total, 286 participants will be included in this study. The primary outcome is the change of cognitive performance measured by the index score of the screening module of the Neuropsychological Assessment Battery. Secondary outcomes are changes in the Cognitive Failures Questionnaire, Hospital Anxiety and Depression Scale, Health-49, Health Literacy Questionnaire, among others. All of the primary and secondary outcomes will be assessed at baseline and after the 12-week post-allocation period. Furthermore, the intervention group will undergo an assessment of the System Usability Scale, and the training data of the NeuroNation MED application will be analyzed.
CONCLUSIONS: This study aims to assess the effectiveness of a mobile self-administered cCT in enhancing cognitive abilities among individuals diagnosed with MCI. Should the findings confirm the effectiveness of the NeuroNation MED app, it may confer possible benefits for the care management of patients with MCI, owing to the accessibility, cost-effectiveness, and home-based setting it provides. Specifically, the cCT program could provide patients with personalized cognitive training, educational resources, and relaxation techniques, enabling participants to independently engage in cognitive training sessions at home without further supervision.
BACKGROUND: German Clinical Trials Register DRKS00025133. Registered on November 5, 2021.

Cities are a major source of litter pollution. Determination of the abundance and composition of plastic litter in cities is imperative for effective pollution management, environmental protection, and sustainable urban development. Therefore, here, a multidisciplinary approach to quantify and classify the abundance of litter in urban environments is proposed. In the present study, litter data collection was integrated via the Pirika smartphone application and conducted image analysis based on deep learning. Pirika was launched in May 2018 and, to date, has collected approximately one million images. Visual classification revealed that the most common types of litter were cans, plastic bags, plastic bottles, cigarette butts, cigarette boxes, and sanitary masks, in that order. The top six categories accounted for approximately 80 % of the total, whereas the top three categories accounted for more than 60 % of the total imaged litter. A deep-learning image processing algorithm was developed to automatically identify the top six litter categories. Both precision and recall derived from the model were higher than 75 %, enabling proper litter categorization. The quantity of litter derived from automated image processing was also plotted on a map using location data acquired concurrently with the images by the smartphone application. Conclusively, this study demonstrates that citizen science supported by smartphone applications and deep learning-based image processing can enable the visualization, quantification, and characterization of street litter in cities.

An easy-to-use and reliable tool is essential for gait assessment of people with gait pathologies. This study aimed to assess the reliability and validity of the OneStep smartphone application compared to the C-Mill-VR+ treadmill (Motek, Nederlands), among patients undergoing rehabilitation for unilateral lower extremity disability. Spatiotemporal gait parameters were extracted from the treadmill and from two smartphones, one on each leg. Inter-device reliability was evaluated using Pearson correlation, intra-cluster correlation coefficient (ICC), and Cohen\'s d, comparing the application\'s readings from the two phones. Validity was assessed by comparing readings from each phone to the treadmill. Twenty-eight patients completed the study; the median age was 45.5 years, and 61% were males. The ICC between the phones showed a high correlation (r = 0.89-1) and good-to-excellent reliability (ICC range, 0.77-1) for all the gait parameters examined. The correlations between the phones and the treadmill were mostly above 0.8. The ICC between each phone and the treadmill demonstrated moderate-to-excellent validity for all the gait parameters (range, 0.58-1). Only \'step length of the impaired leg\' showed poor-to-good validity (range, 0.37-0.84). Cohen\'s d effect size was small (d < 0.5) for all the parameters. The studied application demonstrated good reliability and validity for spatiotemporal gait assessment in patients with unilateral lower limb disability.