Android Smartphone Research Articles

Android Based Visual Product Identification System for the Blind

The proposed system, "Android-Based Visual Product Identification for the Blind," aims to enhance the independence of visually impaired individuals by enabling them to identify everyday products using an Android smartphone. The system leverages computer vision techniques integrated with Android’s mobile platform to capture images of products, analyse them using a trained machine learning model, and provide audio feedback to the user. The application focuses on product packaging, barcodes, and distinct visual features, ensuring accurate identification in real-time. The solution is designed to be user-friendly with voice commands, accessible navigation, and low latency, making it practical for daily use. By offering a portable and reliable means of product identification, this tool addresses the challenges faced by the blind in interacting with their surroundings, improving their quality of life and fostering independence.

Detecting Deception and Ensuring Data Integrity in a Nationwide mHealth Randomized Controlled Trial: Factorial Design Survey Study.

Social behavioral research studies have increasingly shifted to remote recruitment and enrollment procedures. This shifting landscape necessitates evolving best practices to help mitigate the negative impacts of deceptive attempts (eg, fake profiles and bots) at enrolling in behavioral research. This study aimed to develop and implement robust deception detection procedures during the enrollment period of a remotely conducted randomized controlled trial. A 32-group (2×2×2×2×2) factorial design study was conducted from November 2021 to September 2022 to identify mobile health (mHealth) survey design features associated with the highest completion rates of smartphone-based ecological momentary assessments (n=485). Participants were required to be at least 18 years old, live in the United States, and own an Android smartphone that was compatible with the Insight app that was used in the study. Recruitment was conducted remotely through Facebook advertisements, a 5-minute REDCap (Research Electronic Data Capture) prescreener, and a screening and enrollment phone call. The research team created and implemented a 12-step checklist (eg, address verification and texting a copy of picture identification) to identify and prevent potentially deceptive attempts to enroll in the study. Descriptive statistics were calculated to understand the prevalence of various types of deceptive attempts at study enrollment. Facebook advertisements resulted in 5236 initiations of the REDCap prescreener. A digital deception detection procedure was implemented for those who were deemed pre-eligible (n=1928). This procedure resulted in 26% (501/1928) of prescreeners being flagged as potentially deceptive. Completing multiple prescreeners (301/501, 60.1%) and providing invalid addresses (156/501, 31.1%) were the most common reasons prescreeners were flagged. An additional 1% (18/1928) of prescreeners were flagged as potentially deceptive during the subsequent study screening and enrollment phone call. Reasons for exclusion at the screening and enrollment phone call level included having an invalid phone type (6/18, 33.3%), completing multiple prescreeners (6/18, 33.3%), and providing an invalid address (5/18, 27.7%). This resulted in 1409 individuals being eligible after all deception checks were completed. Postenrollment social security number checks revealed that 3 (0.6%) fully enrolled participants out of 485 provided erroneous social security numbers during the screening process. Implementation of a deception detection procedure in a remotely conducted randomized controlled trial resulted in a substantial proportion of cases being flagged as potentially engaging in deceptive attempts at study enrollment. The results of the deception detection procedures in this study confirmed the need for vigilance in conducting remote behavioral research in order to maintain data integrity. Implementing systematic deception detection procedures may support study administration, data quality, and participant safety in remotely conducted behavioral research. ClinicalTrials.gov NCT05194228; https://clinicaltrials.gov/study/NCT05194228.

Mobile Toolbox sequences task: development and validation of a remote, smartphone-based working memory test.

The ability to assess cognitive skills remotely is increasing with the widespread use and availability of smartphones. The Mobile Toolbox (MTB) is a measurement system that includes Sequences, a new measure of working memory designed specifically for smartphones. This study describes the development of Sequences and presents the studies conducted to evaluate its psychometric properties. We developed a new measure of working memory that can be self-administered remotely using an iOS or Android smartphone. In Sequences, a series of numbers and letters are shown on the screen one at a time, and the participant must first tap the letters they see in alphabetical order, followed by tapping the numbers in ascending numerical order. The Sequences measure was evaluated for usability and feasibility across two pilot studies and then assessed in this validation study (which included a total sample size of N = 1,246). Psychometric properties of the new measure were evaluated in three studies involving participants aged 18-90 years. In Study 1 (N = 92), participants completed MTB measures in a laboratory setting. They were also administered both an equivalent NIH Toolbox (NIHTB) measure along with external measures of similar constructs. In Study 2 (N = 1,007), participants were administered NIHTB measures in the laboratory and then completed MTB measures remotely on their own devices. In Study 3 (N = 147), participants completed MTB measures twice, remotely on their own devices, with a 2-week interval between sessions. Sequences exhibited moderately high correlations with a comparable NIHTB test and external measures of a similar construct, while exhibiting a lower correlation with an unrelated test, as hypothesized. Internal consistency was high, but test-retest reliability was moderate. When controlling for age, phone operating system (iOS vs. Android) and sex assigned at birth did not significantly impact performance; however, there was a significant difference between individuals who completed college and those with a high school education or lower. The results support the validity of Sequences as a measure of working memory for remote self-administered use. The internal consistency was strong, with moderate test-retest reliability that is likely a function of the test's unproctored self-administration method. The findings suggest that Sequences is appropriate for use with adults aged 18-90 years in remote self-administered designs that focus on group results.

Use of Google Platforms in Teaching-Learning and Evaluation: A Study with Special Reference to Teaching of English to the UG and PG Classes

The 21st century is essentially an era of information, communication and technology. The use of technology in teaching-learning and evaluation has enhanced the students’ perception and understanding at different levels. Technology has become part and parcel of modern life style. We cannot keep teaching of English in India alienated from the use of technology. The students of UG and PG are using different Google platforms. They are connected to the entire world through internet, Google and social media. Therefore, the teachers have to become tech-savvy in order to make teaching- learning and evaluation more effective, live and learner-friendly. In the present research, the primary focus is given on different Google platforms. Google platforms are user-friendly and easy to use. Google platforms like email, YouTube, Google Classroom, Google Meet, Google Drive, Google Scholar, Google Search, Translator, Calendar, Sheet, Docs, Slides, Blogger, Jam board, Google Earth, Podcasts, Art and Culture, etc. are very popular. These Google platforms are very innovative and smart. If the teachers use these platforms, the students can learn and study at their own pace. It is the best way to keep students engaged in the teaching-learning and evaluation process. All these Google platforms are available on Android Mobile and Smartphones. In the present research, an attempt is made to discuss the usefulness of Email, Google Classroom, Google Meet, YouTube, Google Docs, Google Scholar, Google Drive, and Google Translator in making the teaching-learning and evaluation student-centric, fast, continuous, smart, technology-enabled and eco-friendly also. Google platforms can be used for multiple purposes, like dissemination of information and knowledge, assigning activities, evaluating progress, conducting surveys, expanding traditional classroom teaching boundaries, etc. The present researcher has been using these Google platforms for the last ten years. The observations and findings in the present research are based on the researcher’s use of different Google platforms.

Pengaruh Pengembangan Karir dan Disiplin Kerja Terhadap Kinerja Karyawan

Career development is an effort to improve the ability of employees in the organization and develop careers through education and training. Employees who have high performance are talented, qualified, highly motivated and willing to work with the team. Motivation is very important for employees because motivation is what causes, channels, and supports human behavior so that they want to work hard and enthusiastically to achieve optimal results. In addition, the presence of education and high work discipline in employees in a company will make these employees effective at work. This research was conducted at PT Bangga Teknologi Indonesia with the intention of knowing how strong the influence of employee career development and work discipline on performance at PT Bangga Teknologi Indonesia which is engaged in the leading Android tablets and smartphones in Indonesia with the Advan Vandroid brand which currently controls more than 75% of the Android tablet and smartphone market in Indonesia which also produces mobile phones. In this study using qualitative methods. The data collection process was carried out using a questionnaire technique. In this study multiple linear regression analysis was used, because this research was conducted to determine the effect of Career Development (X1) and Work Discipline (X2) on Employee Performance (Y). Based on the results of the discussion, it shows that the variables of career development and work motivation have a positive effect on employee performance.

Effect of Smartphone use on Convergence among Undergraduate Students

Aim: This study aimed to determine the effect of smartphone usage on convergence among undergraduate students. Study Design: Cross-sectional study. Duration and Setting of the Study: This study was conducted from July 2019 to December 2019 at Pakistan Institute of Community Ophthalmology, Hayatabad Medical Complex, Peshawar. Methods: A non-probability sampling technique was used to include students. The subjects were taken as per the inclusion criteria. Visual acuity was recorded with log MAR at 4 meters, and retinoscopy was performed to rule out refractive error in the subjects. The researcher asked the questions given in the structured questionnaire and recorded the responses. The near point of convergence was determined with the help of the RAF ruler. The Convergence Insufficiency Symptom Survey (CISS) questionnaire was used to record the convergence insufficiency score. Results: A total of 100 students participated, in which 49% were male and 51% were female. The use of Android smartphones was more (82%) than iOS (16%) and others (2%). Most of the subjects used smartphones during the night (54%). It also showed that hours spent on smartphones were interrupted (70%). Smartphone users used their smartphones with dull screens (62%). The near point of convergence was 5cm in (63%). CISS score was noted (>21) was noted in (73%) of students. There was a strong correlation between near point of convergence and CISS scores (p=0.000), with significant associations between smartphone usage patterns and convergence issues (p=0.02). Conclusion: In this study it is concluded that those subjects whose usage of mobile was more than 4 hours had an excess of convergence along with worse symptoms. CISS scores indicated a high prevalence of symptoms, particularly among those with poor near point of convergence (NPC).

IMPLEMENTASI APLIKASI PENGENALAN SOP PENGOLAHAN LIMBAH INDUSTRI PT X BERBASIS ANDROID

B3 medical waste management raises specific considerations and can provide a major problem if not handled effectively. As a result, PT. Desa Air Cargo Batam is on hand to undertake the processing, and the company already holds a B3 industrial waste processing authorization. To meet the company's vision and objective, the correct Standard Operating Procedure (SOP) must be used to reduce negative affects on the environment and society. However, in these companies, awareness and comprehension of the Standard Operating Procedure (SOP) for the handling of B3 medical waste remains a concern that must be addressed. The Software Development Life Cycle (SDLC) research technique was utilized for software development, and application development in this study was done with Adobe Illustrator, Visual Studio Code, and Flutter. The resulting application is compatible with Android smartphones running at least version 8.0 (Oreo). The waterfall method is applied in this scenario. The findings of black-box testing and functional testing reveal that the application performed as predicted, and the results of this application questionnaire are in the very good category, with no problems when operating

3D Adventure Game Design for Early Childhood Alphabet Recognition

Since good practices in childhood will influence adult habits, dental health education should start early. Until recently, the only way to get information about dental health care and good and bad food choices for teeth was through lectures and pamphlets. The traditional approach is considered boring, unnecessarily visualized, and not difficult enough for children to understand. Dr. Rizza Dwi Prasetya from K24 Dental Care Lamongan says that one of the most important things to maintain good dental growth and health is to instill the value of dental care in children from an early age. One way to do this is by creating a 3D adventure game for Android smartphones that teaches about oral health. The Multimedia Development Life Cycle (MDLC) approach, which consists of six stages-ideation, design, material collection, assembly, testing, and distribution-was used in making this application. With an indicator of 81% "Very Good", this 3D adventure game about dental health has gone through user acceptability testing and black box testing. This means that this application is suitable for use as an educational tool for children to help them care for and maintain oral health.

Co-Designing the MOSAIC mHealth App With Breast Cancer Survivors: User-Centered Design Approach.

Breast cancer is the world's most prevalent cancer. Although the 5-year survival rate for breast cancer in the United States is 91%, the stress and uncertainty of survivorship can often lead to symptoms of depression and anxiety. With nearly half of breast cancer survivors living with stress and symptoms of depression and anxiety, there are a significant number of unmet supportive care needs. New and potentially scalable approaches to meeting these supportive care needs are warranted. This study aimed to engage breast cancer survivors and acceptance and commitment therapy (ACT) content experts in user-centered design (UCD) to develop a mobile health app (MOSAIC [Mobile Acceptance and Commitment Therapy Stress Intervention]) using stress intervention strategies. We held 5 UCD sessions with 5 breast cancer survivors, 3 ACT content experts, 2 user experience design experts, and 1 stress expert facilitator over the course of 10 weeks. The sessions were developed to lead the 10 co-designers through the 5-step UCD process (eg, problem identification, solution generation, convergence, prototyping, and debriefing and evaluation). Following the fifth session, a prototype was generated and evaluated by the 5 breast cancer survivors and 3 ACT experts using the System Usability Scale, Acceptability E-scale, and a brief set of semistructured interview questions. The 10 co-designers were present for each of the 5 co-design sessions. Co-designers identified 5 design characteristics: simple entry with use reminders (behavioral nudges), a manageable number of intervention choices, highly visual content, skill-building exercises, and social support. A total of 4 features were also identified as critical to the use of the tool: an ACT and breast cancer-specific onboarding process, clean navigation tools, clear organization of the interventions, and once-per-week behavioral nudges. These requirements created the foundation for the app prototype. The 5 breast cancer survivors and 3 ACT co-designers evaluated the app prototype for 1 week, using an Android smartphone. They rated the app as usable (mean 79.29, SD 19.83) on the System Usability Scale (a priori mean cutoff score=68) and acceptable (mean 24.28, SD 2.77) on the Acceptability E-scale (a priori mean cutoff score=24). Through the UCD process, we created an ACT app prototype with 5 breast cancer survivors, 3 ACT experts, and 2 UCD designers. The next step in our research is to continue the assessment and refining of the prototype with additional breast cancer survivors. Future work will pilot-test the app to examine the feasibility of a large-scale, randomized control trial. Studies will enroll increasingly diverse breast cancer survivors to broaden the generalizability of findings.

Learning Project Based with the Help of an Android Smartphone on Trigonometry Comparison Material

The aim of this research is to describe the use of project-based learning with the help of Android smartphones in trigonometric ratio material in grade X SMAN 1 Kota Besi. This research method is descriptive qualitative. The subjects of this study were tenth grade students SMAN 1 Kota Besi. Based on the results of reflections and interviews, it shows that the use of android aplication in project-based learning, namely (1) makes learning easier for students to understand and learning is more interactive because students experience it for themselves, (2) learning becomes more interesting because they use their gadgets for learning and practicum, and (3) students are more creative because they have to make reports and make presentations in front of the class. Thus the use of android aplication can support project-based learning on trigonometric ratio material at SMAN 1 Kota Besi both inside and outside the classroom and outside of school.

IOT Based Green House Monitoring and Controlling with Arduino

Greenhouses offer a controlled environment for growing plants. For a green house system to function effectively, it needs to consistently oversee and control various environmental elements such as hotness, dampness, soil moisture, light strength, and soil p H. The main objective of the project is to create a cost-efficient design to promote optimal plant growth and yield. Arduino system that allows for constant updating and adjustment of environmental parameter values. The DHT 11,s and acidity, LDR plus dryness are the important sensors in the project, measuring moisture, temperature, water purpose, light strength, and earth wetness. Android smart phones receive environmental data both offline and online. The present situation of the surrounding circumstances is displayed in an SMS sent via a GSM modem. The user gets a text when this sensor value goes above a specific threshold. Farmers can observe and control their green houses from anywhere. SMS commands can be used to change environmental factors like the fluid pump, motor breathe, refrigeration fan, emission fan, and manufactured illumination fluids pump, engine breathe, cooling fan, exhaust fan, and false lighting. To prevent SMS charges, data parameters are sent to mobile phones using Ethernet. Using Ethernet, all environmental data is sent to the machine ad kept on the data file in this way, the Android app allows the user to monitor and manage settings.

An Objective Assessment of Neuromotor Control Using a Smartphone App After Repeated Subconcussive Blast Exposure.

Subconcussive blast exposure has been shown to alter neurological functioning. However, the extent to which neurological dysfunction persists after blast exposure is unknown. This longitudinal study examined the potential short- and long-term effects of repeated subconcussive blast exposure on neuromotor performance from heavy weapons training in military personnel. A total of 214 participants were assessed; 137 were exposed to repeated subconcussive blasts and 77 were not exposed to blasts (controls). Participants completed a short stepping-in-place task while an Android smartphone app placed on their thigh recorded movement kinematics. We showed acute suppression of neuromotor variability 6 h after subconcussive blast exposure, followed by a rebound to levels not different from baseline at the 72 h, 2-week, and 3-month post-tests. It is postulated that this suppression of neuromotor variability results from a reduction in the functional degrees of freedom from the subconcussive neurological insult. It is important to note that this change in behavior is short-lived, with a return to pre-blast exposure movement kinematics within 72 h.

Education of the "SusCatinTing" application on changes in knowledge, attitudes, and behavior of brides-to-be.

The "SusCatinTing" application is a digital health intervention designed to enhance the knowledge, attitudes, and practices (KAP) of brides-to-be regarding stunting prevention during the critical first 1000 days of life. This study aimed to evaluate the effectiveness of this application in improving stunting prevention efforts among brides-to-be in Bengkulu Province, Indonesia. The application provides educational content on healthy pregnancy, maternal nutrition, and stunting prevention strategies, incorporating both text and audio explanations to ensure accessibility for illiterate and visually impaired users. A quantitative research design was employed, utilizing a single-group pretest-posttest approach involving 50 pairs of brides-to-be with internet-connected Android smartphones. Data collection was conducted through structured questionnaires administered by trained enumerators, focusing on KAP related to stunting prevention. The results indicated a significant improvement in KAP scores post-intervention (knowledge score increase: 42.59, p < 0.001). The application's unique features, including interactive quizzes and a certification process for marriage registration at the Office of Religious Affairs, contributed to its effectiveness. The study concludes that the "SusCatinTing" application is a promising tool for enhancing health education and promoting preventive behaviors among brides-to-be. Further research is recommended to explore the long-term impact of such digital interventions on stunting rates and maternal-child health outcomes.

Smart System Augmented Reality For Cultural and Tourism Mapping in North Padang Lawas

The era of digital technology continues to develop rapidly which opens up new opportunities, including in cultural mapping and tourism. The aim of this research is to develop and evaluate the effectiveness of the Augmented Reality AR system in improving tourism experiences and cultural understanding in North Padang Lawas with innovations in improving tourism experiences through AR. The cultural and tourism potential of North Padang Lawas includes Bahal I Temple, Bahal II Temple, Bahal III Temple, Aek Milas Pangirkiran, Sagayung Lake, Danao Tao, Paya Goti Lake and Siombob Waterfall. The use of AR in cultural and tourism mapping makes it easier for tourists to navigate with additional information presented interactively. The research method stages are: First, Literature Study: collecting information about AR technology, Second, Survey and Interview: interviews with tourists, local communities, tourism stakeholders and cultural experts. Third Prototype Development: Developing an AR application prototype. Fourth Testing and Evaluation: Testing the AR application can run on an Android smartphone and the AR application can scan tourist and cultural barcodes. Next, evaluate the effectiveness of the application in improving tourism experiences and understanding of cultural heritage in North Padang Lawas. Fifth Data Analysis: data obtained from surveys, interviews and application testing to evaluate the success of applying AR technology in cultural and tourism mapping in North Padang Lawas. AR technology in tourism and culture can enrich tourism and culture with different interactive experiences, education, digitalization, tourism and culture preservation and innovation in developing mapping of cultural and tourist objects

Static analysis framework for permission-based dataset generation and android malware detection using machine learning

Since Android is the popular mobile operating system worldwide, malicious attackers seek out Android smartphones as targets. The Android malware can be identified through a number of established detection techniques. However, the issues presented by modern malware cannot be met by traditional signature or heuristic-based malware detection methods. Previous research suggests that machine-learning classifiers can be utilised to analyse permissions, making it possible to differentiate between malicious and benign applications on the Android platform. There exist machine-learning methods that utilise permission-based attributes to build models for the detection of malware on Android devices. Nevertheless, the performance of these detection methods is dependent on the raw or feature datasets. Android malware research frequently faces a major obstacle due to the lack of adequate and up-to-date raw malware datasets. In this paper, we put forward a systematic approach to generate an Android permission-based dataset using static analysis. To create the dataset, we collect recent raw malware samples (APK files) and focus on the reverse engineering approach and permission-based features extraction. We also conduct a thorough feature analysis to determine the important Android permissions and present a machine-learning-based Android malware detection mechanism. The experimental result of our study demonstrates that with just 48 features, the random forest classifier-based Android malware detection model obtains the best accuracy of 97.5%.

A short-term evaluation of oral hygiene education methods in fixed orthodontics patients: a randomized clinical trial comparing assistant training, software, and social media

ObjectiveTo compare the effectiveness of different oral hygiene education strategies on periodontal health in fixed orthodontic patients in a one-month period: assistant-led instruction, social media-based education, and custom-made software.MethodsSixty orthodontic patients from Mashhad University of Medical Sciences’ Dentistry School were randomly assigned into three groups. Each group received oral health education differently: via assistant instruction, educational videos on social media, or a researcher-designed software for Android smartphones. After a month, participants’ oral health was evaluated using the plaque index (PI) and the gingival index (GI).ResultsAssistant-led education group demonstrated the highest PI (1.26 ± 0.70) and GI (0.92 ± 0.67), while the software group reported the lowest indices (PI = 0.68, GI = 0.46 ± 0.46). The social media group’s measurements fell between these extremes (PI = 0.89 ± 0.75, GI = 0.60 ± 0.52). Significant group differences were found for both PI and GI (P = 0.028 and P = 0.047, respectively). Pairwise comparison revealed significantly lower PI and GI in the software group compared to the assistant group. No significant differences were found between the social media and other groups.ConclusionOur results suggest that the use of specially designed software could be the most effective strategy for improving oral hygiene in orthodontic patients. Meanwhile, traditional assistant-led education showed the least effectiveness. The study supports the potential benefit of utilizing digital tools, such as bespoke software and social media, in oral health education for orthodontic patients.Trial registrationThe study was registered in the Iranian Registry of Clinical Trials (IRCT) database with the identification code IRCT20200609047705N2 in 13.07.2021.

Mozart: A Mobile ToF System for Sensing in the Dark Through Phase Manipulation

Sensing in low-light and dark environments has a wide range of applications. However, existing sensing technologies suffer several major challenges, such as excessive noise and low resolution. In this work, we propose Mozart - a new mobile sensing system that leverages off-the-shelf Time-of-Flight (ToF) depth cameras to generate high-resolution and rich-in-texture maps for applications in dark scenarios. The design of Mozart is based on our key observation that the phase components of ToF measurements can be manipulated to expose texture information. Through in-depth analysis of the physical reflection model, we show that the textures can be exposed and enhanced using highly compute-efficient phase manipulation functions. Moreover, by exploiting the physics texture models, we propose an autoencoderbased unsupervised learning approach that can automatically learn efficient representations from phase components to generate high-resolution maps. We implemented Mozart on several Android smartphone models and an edge testbed with standalone ToF camera platforms for various applications in the dark. The results show that Mozart can work in real time and delivers significant improvement over existing sensing technologies. The demo video at https:// www.youtube.com/watch?v=L_sxyTZxIdU shows that Mozart offers a low-cost, highperformance sensing technology for nextgeneration applications in the dark.

WISE-Energy: Wireless Integrated Smart Energy Systems

This paper introduces WISE-Engergy, Wireless Integrated Smart Energi Systems. This system is designed to optimize indoor electricity usage by fostering user awareness of energy-saving practices. Users are reminded to turn off electrical devices when leaving the room through notifications on an Android smartphone application. The research aims to increase public awareness of the importance of energy conservation and to apply technology to achieve higher energy efficiency. The contribution of this research lies in the development of an innovative energy-saving system that can be implemented in various indoor environments to support sustainable energy-saving efforts. The test results show that this system successfully achieves its intended goals. The notifications sent to the last user in the room effectively encouraged them to turn off the lights upon leaving. The WSN communication test between room 1 and room 2 also demonstrated that the system could transmit power data from room 2 to room 1 via the XBee module. System evaluation and testing indicated that SENIOR successfully notified users to turn off electrical devices. This research makes a significant contribution to addressing energy-saving challenges and promoting an energy-saving culture in the community.

Development of Student E-Attendance System using QR-Code and WhatsApp Gateway with The Iterative Model Based on Android

The rapid advancement of technology not only creates new industries but also reshapes global competition. In higher education, learning implementation must meet standards for content, process, and assessment. Student attendance plays a significant role within these standards. Using Android smartphones for attendance tracking resolves issues related to student presence, saves time, and enhances the efficiency and accuracy of the attendance recapitulation process for lecturers. This study explores an innovative system that integrates QR-Code and WhatsApp Gateway using an iterative model on a single platform. Blackbox testing confirmed that all features and functions of the Android application work as intended. Furthermore, a Likert scale evaluation scored 89%, indicating that the e-attendance system effectively facilitates student attendance and helps lecturers summarize attendance data more accurately and efficiently. The system then provides this data as administrative monitoring reports for the academic department regarding the conducted lectures.

Enhancing Fracture Detection in Remote Settings: Evaluating the Efficacy of FIXUS AI Deep Learning Algorithms in Identifying Fifth Metatarsal Fractures Using Mixed-Quality X-rays

Category: Midfoot/Forefoot; Trauma Introduction/Purpose: The diagnosis of fractures can be challenging in specific medical settings due to limited expertise or time. While deep learning has shown promising results, its use is confined to the quality of images and the hassle of importing images to the models. This study aims to develop a model to detect fifth metatarsal fractures based on cell phone photos of radiographs directly taken from a regular screen. Methods: retrospective case-control study was conducted including patients aged &gt; 18 years with fifth metatarsal fractures (n=1240) (Fx), and healthy controls (n=1224) (NoF). Three view radiographs (anterior, posterior, and lateral) were obtained from the Electronic Health Record (EHR) in PNG format. To generate a mixed-quality dataset, Android and iOS smartphones (SP) were used to create two separate datasets for each Fx and NoF group. Two separate deep learning models on each EHR, SP, and combined datasets were developed using Inception V3 architecture (Figure 1.). The models were also tested on a separate SP dataset (SP-test) that was not included in the development process. Area Under the Receiver Operating Characteristics Curve (AUC) along with other performance metrics were calculated and reported. Continuous data were presented as median (interquartile range), and a p-value of &lt; 0.05 was considered to be significant. Results: Baseline analysis revealed differences between the groups with a median age of 56 years (36-68) for the Fx group, and 62 years (51-72) for the NoF group (p &lt; 0.001). Similarly, the racial composition of the groups was also different (Fx: 84.8% white; NoF: 92.2% white; p &lt; 0.001). Initially, the SP model showed the best performance (Youden Index (YI): 0.92, AUC: 0.99) followed by the EHR (YI: 0.74, AUC: 0.96), and combined (YI: 0.52, AUC: 0.97) models. When tested on the SP-test dataset the EHR model’s performance dropped markedly showing a YI of 0.33, an AUC of 0.78, and a sensitivity of 0.49 (Table 1.). However, the SP and combined models continued to perform optimally (YI: 0.94, AUC: 0.99; YI: 0.78, AUC: 0.98, respectively). Conclusion: This study highlights the crucial role of image quality in developing deep learning models for detecting fifth metatarsal fractures. Our findings demonstrate a markedly reduced performance of the EHR model in identifying fractures within lower-quality images. This emphasizes the need for training algorithms on images of varying quality to create more generalizable models capable of operating effectively across diverse settings.