Introduction and Purpose Diabetes mellitus is a chronic disease that lasts a lifetime, cannot be cured, and whose incidence is progressively increasing, with social and societal dimensions (ADA, 2013). Diabetes can be managed through proper diet, regular physical activity, and self-care activities such as blood sugar control (Karakurt et al., 2013). The main goal in the treatment of diabetes is to change the lifestyles of diabetic individuals and to instill positive health behaviors. This research examines the effect of a mobile information intervention applied from the perspective of the health belief model on health belief, self-efficacy perception, and locus of control, and it is thought that this intervention will have a positive effect. Method This study will be conducted among 250 diabetic patients who voluntarily agree to participate in the research among participants of the Diabetes program on the Albert Health mobile application. Participants will be randomly assigned to a control or information group based on their user IDs. Participants will be divided into a control group and an information group. After sending the consent form to both groups, a pre-test will be conducted. In this context, participants will be sent the Demographic Information Form, the Multidimensional Health Locus of Control Scale, the Health Locus of Control Scale for Diabetics, and the Self-Efficacy Scale for Diabetes Management. While the control group will be sent generic content for two months, the information group will receive diabetes-specific content for two months. Afterwards, final assessments will be conducted. In this context, participants will be sent the Demographic Information Form, the Multidimensional Health Locus of Control Scale, the Health Locus of Control Scale for Diabetics, and the Self-Efficacy Scale for Diabetes Management again. Findings As a result of this research; i) it is expected that the post-test scores of self-efficacy, locus of control, and health belief in the diabetic patient group will be significantly higher than the pre-test scores, ii) the post-test scores of self-efficacy, locus of control, and health belief in the informed diabetic patient group will be significantly higher than those of the control group. Additionally, it is aimed to provide an environment where the patient is informed and can practice the informed areas. Discussion and Conclusion In diabetes treatment, the patient needs to know what precautions and treatments to apply as much as believing that they can implement these skills in their life, and thinking that the control of their health is in their own hands. Our research aims to examine the potential effects of mobile education on the health beliefs and control perceptions of diabetic patients. The results will guide the steps to be considered when developing applications in the field of diabetes and their evaluation.

This research examines the effect of a mobile information intervention applied from the perspective of the health belief model on health belief, self-efficacy perception, and locus of control, and it is thought that this intervention will have a positive effect.

Health Behavior Change in Diabetic Patients Using Mobile Health Application: An Information Study on Factors Determining Health Behaviors

Background &amp; Aims Mobile apps and conversational agents are becoming popular in healthcare by improving usability and accessibility. To reveal their clinical benefits, we analyzed conversational agent usage characteristics of asthma patients within a mobile app. Methodology Asthma survey results and conversational agent usage data from the users of an asthma-specific mobile app (Albert Health Assistant) were analyzed using descriptive statistics. The relationships between the groups were evaluated using the chi-square test. The distribution of continuous variables was checked using the Shapiro-Wilk test. Results Among the 254 users who completed the survey; 42.9% self-reported getting an asthma diagnosis within the last year. Most (57.1%) expected the app to be helpful for better asthma management. 42.1% were not using any inhaler for asthma treatment. Voice-based interaction was preferred by asthma patients. Fifty-three users (20.9%) interacted with the conversational agent 360 times, with a mean success rate of 88%. Voice-based interaction was higher than text-based interactions (6.78 and 2.48 times per user). Patients used both interfaces similarly (51.7% vs. 48.3%) for getting information about asthma; Patients primarily interacted by speaking to use functions of the application, such as setting a medication reminder or keeping an asthma diary, 72.2% vs. 27.8%, respectively (p&lt;0.001). They also used voice interface more in other contexts out of asthma(92.1% vs. 7.9%, p&lt;0.001). Conclusion The results highlight the potential of mobile apps and conversational agents to assist patients in managing their asthma. The higher frequency of voice-based interactions over text-based interactions indicates that patients may find it more convenient and efficient to interact with the application using voice.

In this study, the clinical benefits were revealed by analyzing the usage characteristics of asthma patients within a mobile app through conversational agent usage.

Descriptive Analysis of Conversational Agent Usage Characteristics in an Asthma App

Introduction The number and usability of mobile applications designed specifically for diabetes management have been increasing recently. The Albert Diabetes Program aims to empower patients in managing their diabetes by encouraging them to measure and record their blood glucose levels, providing valuable insights. This retrospective study analyzes the changes in fasting blood glucose levels (FBG) in patients who use the Albert mobile application to measure their blood sugar levels. About the Albert Health Assistant App Trusted by over 150,000 patients globally, the Albert Health Assistant Mobile Application offers advanced voice recognition for effortless communication between patients and caregivers. Albert’s core technology is its medical voice recognition and language processing technologies. This umbrella technology offers self-care tools like medication reminders, health parameters tracking, symptom diary, a complementary telehealth service, and remote patient monitoring from the doctors' side to increase treatment adherence and the quality of life of patients. Methodology A total of 92 engaged users were included. This retrospective study analyzed FBG recording data extracted from patients using the Albert App. Users who had monitored their FBG levels for more than 30 days and had recorded a minimum of 4 measurements were identified as engaged patients in glucose measurement. 30 times or more measurements were accepted as the indicator of regular blood glucose measurement. Users were divided into two groups: those recording levels 30 times or more (n=39), and those recording levels less than 30 times (n=53). Changes in fasting blood glucose were analyzed. Improvement in FBG levels between the groups was assessed for statistical significance using the chi-square test and p&lt;0,05 was considered significant. Results A significant improvement rate of 66.67% (n=26) was identified amongst participants who engaged with the app 30 times or more, compared to a 41.51% improvement rate (n=22) in the less frequent recording group. The comparison of improvements in FBG levels between the two groups showed statistical significance, with individuals who recorded 30 times or more having better glucose outcomes than those who recorded less than 30 times (OR: 2.82 [CI: 1.19, 6.67], p=0.017). This significant difference demonstrates the positive role of consistent app usage in aiding diabetes management and improving FBG levels. Conclusion This retrospective analysis suggests that regular blood glucose monitoring induced through digital apps designed for diabetes management may lead to improved blood glucose control. Engaging with these applications allows for active health monitoring, significantly aiding in improving FBG levels among users. This active engagement, facilitated by the app, enables patients to embrace lifestyle changes, and dietary plans and target glucose levels, essential for efficient diabetes management. However, larger prospective studies involving a broader population are needed for more precise conclusions.

This poster, presented at the 21st International Congress of Endocrinology, examines the effectiveness of the mHealth application Albert, and the Diabetes program. This retrospective study analyzes the changes in fasting blood glucose levels (FBG) in patients who use the Albert Diabetes program to measure their blood sugar levels.

Empowering Diabetes Self-management Through Consistent Mobile App Usage:  A Retrospective Data Analysis on Fasting Glucose Level Improvement

Introduction and Purpose Insulin dose titration is the process of adjusting the basal insulin dose for patients with diabetes who use insulin, based on the blood sugar range, either by increasing or decreasing it to make it suitable for the individual. Mobile applications can help make this complex process in clinical practice easier to manage for patients. In our study, we describe the development process, features, and preliminary results of a program named Albert Rx, aimed at enabling patients to self-adjust their basal insulin dose; achieving longer durations in glycemic targets, reducing complications such as hypoglycemia, hyperglycemia, overbasalization, and hospital visits. Methods The development process of the program involved a needs analysis, development of the algorithm, interface design of the mobile application, and integration of the algorithm, and validation steps; carried out by a multidisciplinary team of physicians and developers. During the design process, the needs of both patients and physicians were analyzed. The basal insulin titration algorithm was created according to international diabetes treatment guidelines, with parameters determined by the physician. Findings The Albert Rx Basal Insulin Titration Program is an innovative program developed to improve basal insulin titration in patients with type 2 diabetes aged 18 and over. In the program, doctors set patient-specific parameters via a web panel, while patients record their fasting blood sugar data through a mobile application. The program's algorithm combines the patient's real-time data with international diabetes treatment guidelines and the parameters set by the doctor to calculate the basal insulin dose required for that evening and inform the patient. The program allows the physician to set individual blood sugar targets considering the patient's age, comorbidities, and hypoglycemia risk. For patients exceeding the threshold values set by the physician, the algorithm suggests an insulin dose increase based on 3-day average values. Similarly, the system recommends a dose reduction for results below the target glucose value according to individual patient needs, based on data entered by the doctor, and limits the maximum dose increase. To prevent severe complications of hyperglycemia and hypoglycemia, the system indicates the need for intervention for values over 300 mg/dL and under 70 mg/dL. The algorithm ensures the recommended dose stays within clinically safe limits and prevents overbasalization by considering the maximum daily dose set by the physician. Discussion and Conclusion Albert Rx automates the process of basal insulin titration, offering more practical and personalized treatment management. This could provide a titration method where patients can manage themselves, with reduced risk of hypoglycemia and longer durations spent in target glycemic values. Further studies are required to assess the long-term effectiveness of the program and its impact on HbA1c.

This study, presented in the 59th National Diabetes Congress, discusses the development process, features, and preliminary results of the Albert Rx program, developed to help type 2 diabetic patients manage their basal insulin doses more effectively. Albert RX aims to reduce hypoglycemia and hyperglycemia risks and improve glycemic control by enabling patients to adjust their basal insulin dose based on their health data. 

Revolution in Basal Insulin Titration: Individualized Diabetes Treatment Management via Mobile App

Introduction: It highlights the challenge of managing diabetes through optimal insulin dosing and the potential role of mobile technology in enhancing this process. The study focuses on evaluating the effectiveness and reliability of a mobile algorithm designed for the specific diabetic population in Turkey. Methodology: Utilizing simulation-based patient profiles that adhere to the Turkish Endocrinology and Metabolism Association (TEMD) guidelines, the study created 105 different scenarios reflecting the realistic conditions of Turkey's diabetic population. These profiles included varying glucose levels and target ranges, with insulin doses determined by an internal medicine specialist and compared against the algorithm's recommendations and the American Diabetes Association (ADA) guidelines. How the Mechanism Works: This section outlines the process from the physician's initial examination and decision on basal insulin treatment to the algorithm's operation, including registering the patient, determining target glucose ranges, and adjusting doses based on the algorithm's rules for managing hypoglycemia and hyperglycemia. Results: The study found that the insulin doses recommended by the mobile algorithm completely aligned with those determined by the internal medicine specialist for all 105 simulated patient scenarios. Furthermore, the algorithm's recommendations were similar to those of the ADA guidelines, offering appropriate clinical warnings for extreme glucose levels. Conclusion: The mobile basal insulin titration algorithm is consistent with the recommendations of internal medicine specialists and international diabetes guidelines, demonstrating its reliability and effectiveness across different blood sugar target ranges. However, the study suggests that clinical trials are necessary to further evaluate its usability, effectiveness, and safety with actual patients.

The poster presented at The 21st International Congress of Endocrinology presents findings from a study evaluating the clinical accuracy of a mobile insulin titration algorithm for Turkey's diabetic population. The primary aim is to assess how well this algorithm aligns with clinical practice guidelines and the recommendations of clinicians for managing diabetes in Turkey. 

Evaluation of Clinical Accuracy of Mobile Insulin Titration Algorithm for Turkey's Diabetic Population

Background and Aims Detecting the risk of diabetes is of vital importance for both diagnosing the disease and preventing it. Despite the numerous calculation methods and scientific studies, many of these studies rely on laboratory tests yet demonstrate low sensitivity or specificity. We aimed to develop a machine learning model for diabetes risk prediction, considering demographic, clinical, and lifestyle variables that are gathered solely by patients. Methods An open-source dataset is employed with features of age, gender, hypertension, heart disease, BMI, smoking history, glucose level, and A1C. The preprocessing phase involved filtering for age (&gt;18), and BMI (14-50), excluding entries with unknown gender, dropping null values, and excluding the A1c column. Traditional models (KNN, Decision Tree, Random Forest, Gradient Boosting, XGBoost, and Logistic Regression) were employed. SMOTE, a widely utilized oversampling technique, was employed to address the imbalance in the representation of the diabetic class by generating synthetic data. Evaluation utilized cross-validation, assessing accuracy, F1-score, precision, and recall. Results Correlation analysis revealed notable associations: glucose level (44%), age (28%), BMI (22%), hypertension (19%), heart disease (17%), smoking history (9%), and gender (4%). The XGBoost model outperformed, achieving a Cross Validation score of 0.94. The model achieved strong performance across both diabetic (class 1) and non-diabetic (class 0) categories, with F1 scores of 0.90 and 0.95, precision of 0.95 and 0.93, and recall of 0.85 and 0.98, respectively. Excluding the glucose level feature maintained robust performance with a Cross-Validation score of 0.86. The F1 score, precision, and recall values for class 1 dropped to 0.77, while they slightly decreased for class 0. Conclusions This study demonstrates the efficacy of machine learning in diabetes risk prediction. By developing a model capable of accurate assessments even without direct glucose-level measurements, we offer a valuable tool for early intervention and improved healthcare outcomes. This approach holds promise for enhancing diabetes prevention strategies and ultimately improving the quality of patient care. To confirm the model's real-world applicability and effectiveness, further evaluation with real-life patient data and outcomes is necessary.

Discover our latest poster presented at The 21st International Congress of Endocrinology about the development of a patient-centric machine learning model for diabetes risk prediction. The study aimed to create a model that considers demographic, clinical, and lifestyle variables collected directly from patients to predict the risk of diabetes. 

Development of A Patient-Centric Machine Learning Model for Diabetes Risk Prediction

We will be attending Gitex, one of the world's most influential tech events, taking place in Dubai from October 16-20, 2023! We are excited to join this prestigious exhibition alongside the world's most innovative enterprises and best minds. If you're attending Gitex 2023, be sure to visit our booth at Dubai World Trade Center, Hall 11-14, Booth H13 - B17, and chat with us. Join us to meet Albert, dive into its capabilities, and explore our vision for Albert Health in the digital health landscape. Stay tuned for updates!

We will be attending Gitex, one of the world's most influential tech events, taking place in Dubai from October 16-20, 2023!

Save the Date! Albert Health at Gitex 2023, Dubai

Mobile health (mHealth) apps have become essential for individuals seeking to manage their health and long-term conditions. Whether they are safe or beneficial is becoming a matter of interest due to their possible impacts on human health. This article analyzes the features, user reviews, and potential of a mobile health application, Albert Health Assistant. The app, which over 200,000 users downloaded, is designed to aid patients in managing their chronic diseases through features such as medication tracking, voice assistant, and personalized notifications. The study involves meeting with the app developers and evaluating the app through Google Play and Apple App stores. The average user rating for Apple App Store and Google Play Store were 4.7 out of 5 and 4.8 out of 5. Overall, the results suggest that the app is highly utilized and well-received by users. It positively impacts their ability to manage their health conditions. The article suggests that mHealth apps like Albert Health Assistant have the potential to reach and engage large populations and may be an effective tool for delivering digital therapeutic interventions. Further research is needed to evaluate its impact on clinical outcomes and health economic outcomes. You can access the entire study on page 80 of the article via the link. <a target="_blank" rel="noopener noreferrer" href="https://turkmia.net/TurkMIA2023-Proceedings.pdf">https://turkmia.net/TurkMIA2023-Proceedings.pdf</a>&nbsp;

This study discusses the role of mHealth apps in health management, focusing on Albert Health Assistant. 

An Analysis of the Features, User Reviews, and Potential of a Mobile Health Application: Albert Health Assistant

Albert Health successfully returned home from CES 2023, the biggest consumer electronics fair in the world. Thanks to the support of the Istanbul Development Agency and The Republic Of Turkey Ministry of Industry and Technology, Albert Health was able to take place in a global arena alongside industry leaders in consumer electronics, technology, and digital health. Through the investor relations we’ve formed, the potential business partners we connected with, and the all the new technology we witnessed yielded to a fruitful experience and brought us closer to realizing our Digital Therapeutics vision.

We took part in CES, the world's largest consumer electronics fair, which brought together the latest and greatest technological innovations, held in Las Vegas between 5 - 8 January 2023! 

Albert Health Meets World Leaders at CES 2023!

We attended HIMSS, the world's largest health technologies fair, held in Chicago between 17-21 April 2023! We had an incredible time during HIMSS, meeting with pioneers in the international healthcare industry and exploring the latest advances in healthcare technologies. Thank you to everyone who visited us at our stand!

Albert Health attended the HIMSS Global Health Conference, the world's largest health-tech conference, held in Chicago from April 17-21, 2023!

Albert Health Attended HIMSS 2023 Chicago!

Our Medical Manager Dr. Selahattin Çolokoğlu took part as a speaker at the "Artificial Intelligence in Health" panel within the scope of the 30th Expomed Eurasia, organized with the mission of carrying the healthcare sector to the future. He shared valuable insights into how artificial intelligence technologies can contribute to this goal and he also highlighted our ongoing AI studies at Albert Health If you're interested in learning more about AI technologies in the healthcare sector, we welcome you to explore the world of Albert Health!

Our Medical Director Dr. Selahattin Çolokoğlu took part as a speaker at the "Artificial Intelligence in Health" panel within the scope of the 30th Expomed Eurasia. He shared insights about the future of artificial intelligence technologies and he highlighted our ongoing AI studies at Albert Health.


Our Medical Director, Dr. Selahattin Çolakoğlu Talked About the Future of AI Technologies in Healthcare at Expomed Eurasia!

We're thrilled to announce that Albert Health has been selected to join the TASMU Accelerator 2023 Cohort! TASMU Accelerator is a ground-breaking acceleration program aimed at nurturing the innovation ecosystem in Qatar. It is an initiative launched by the Ministry of Communications and Information Technology and operated and&nbsp;facilitated by Ooredoo Qatar. In the 6 months acceleration program, Albert Health will tackle the Qatar market needs in the digital health sector and contribute to achieving the Smart Qatar Vision of 2030. We are grateful for this opportunity and excited to collaborate with the other startups!

Albert Health has been selected to join the TASMU Accelerator 2023 Cohort! 

BLOG

Join Our Newsletter