AUAdil Umer

Adil Umer

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Adil Umer has a total of 79 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Novel Sensors and Data-Driven Approach to Support Prevention, Diagnosis, and Treatment Planning of Cerebrovascular Accidents: Protocol for a Multimodal Data Collection Study With Novel Sensors

    by Milla Immonen, Hilkka Liedes, Aysen Degerli, Ilona Ruotsalainen, Juha Pajula, Mika Hilvo, Heidi Similä, Adil Umer, Mark van Gils, Miia Jansson, et al.

    Background: Stroke is the second leading cause of death worldwide. Cerebrovascular diseases (CVDs), including strokes and transient ischemic attacks (TIAs), cause long-term disabilities and economic burdens. Strokes can be ischemic, caused by blood clots; or hemorrhagic, caused by bleeding in the brain. Immediate diagnosis and treatment are crucial. Proper management of TIAs is essential due to the high risk of subsequent strokes. Currently, wearable sensors, AI-based prediction, and automatic video analysis are not used in CVD diagnosis and recovery estimation. Objective: This paper describes the design, cohort characteristics, and multimodal dataset of the Stroke-Data study conducted at 2 university hospitals in Finland. Although findings from individual components of the study have been reported elsewhere, this paper provides the first comprehensive description of the overall study design, cohort, and multimodal data collection protocol. The study collected a unique multimodal dataset comprising sensor data, video recordings, clinical assessments, questionnaires, and health record data from healthy controls and patients with stroke and TIA to support the development of AI, sensor-based, and video-based methods for CVD diagnosis and recovery estimation. Methods: Stroke-Data was a prospective national multicenter study conducted at Oulu University Hospital and Kuopio University Hospital from October 2021 to December 2022. A rich multimodal dataset from patients with stroke and TIA and healthy controls was collected by study nurses and a research assistant. Inclusion criteria for patients were age >18 years and a diagnosis of cerebrovascular accident or TIA within the previous 3 days. Healthy control participants were aged 18 years and older and had no major chronic diseases, although blood pressure and cholesterol medications were permitted. Data collection included electroencephalogram; electrocardiogram; near-infrared spectroscopy; accelerometers to analyze gait and balance; retinal fundus images; video recordings of neurological examinations to analyze the face, body movements, and speech; clinical assessments; questionnaires; and electronic health records. Results: In total, 263 participants were recruited, of whom 123 were controls (median age 59, IQR 45-72 years; female: 84/123, 68.3%), 31 were patients with TIA (median age 71, IQR 60-80 years; female: 8/31, 25.8%), and 103 were patients with stroke (median age 70, IQR 59-76 years; female: 42/102, 41.2%, sex data missing from 1 participant). A total of 6 participants were excluded (5 had diagnoses other than TIA or stroke and 1 control participant had a previous CVD). Conclusions: We successfully conducted a multicenter multimodal data collection study on healthy controls and patients with stroke and TIA. This protocol paper provides a comprehensive methodological description of the Stroke-data study, serving as a reference for previously published and future analyses based on the dataset. The protocol is unique in combining physiological sensor data, video recordings, clinical assessments, questionnaires, and health record data from patients with stroke and TIA and healthy controls in a multicenter setting. International Registered Report Identifier (IRRID): DERR1-10.2196/86930

  • Open Access

    The Usage Effects, Effect Modifiers, and Experiences of a Web-Based App for Healthy Habit Formation in Adults: Exploratory Analysis of a Quasi-Experimental Real-World Intervention

    by Eeva Rantala, Mikko Valtanen, Adil Umer, Suvi Parikka, Jussi Pihlajamäki, Ilona Ruotsalainen, Jaana Lindström

    Background: Digital interventions provide a scalable approach to promote healthy lifestyles, but at-scale evidence of their effects and effect modifiers is limited—even scarcer for habit-based digital interventions, although habits are promising lifestyle intervention targets. Objective: We conducted a 1-group pre-post effect and effect modification assessment of a web-based app designed to support the formation of health-promoting lifestyle habits by exploring the relationship between objective app use and subjective changes in behavioral outcomes. Methods: Three-month app access was offered to a subsample of the population-based Healthy Finland survey participants aged 20-74 years via SMS text messaging or mail. The app provided personalized behavioral suggestions that translated evidence-based lifestyle guidelines into simple, repeatable actions (“habits”). Users could browse and select these habits, and report and monitor their performances. The assessment used app log data, questionnaires collected through the app at baseline and at 45 and 90 days, and background information obtained from the national population register and the Healthy Finland Survey. Linear mixed effects models explored the (1) associations between app use and changes in self-reported diet quality (Healthy Diet Index), physical activity (metabolic equivalent of task hours per week), and BMI, and (2) modification of these associations by baseline characteristics related to sociodemographics, health, lifestyle, and e-service use. App use measures comprised the percentage of app use days (ie, days with logins/days of follow-up×100) and the number of reported habit performances (total, diet-related, physical activity–related, and BMI-related). Results: Of 6975 invitees, 1282 (18.4%) accepted the invitation and 382 (5.5%; mean age 51, SD 15 y; women: %) completed the data collection required for the assessment. Over 90 days, the median percentage of app use days was 5.9% (IQR 3.3%‐11%), and the total number of reported habit performances was 22 (IQR 3‐68.5). A higher percentage of use days (by 10 percentage points) was associated with a 3.09 (95% CI 0.79‐5.39) metabolic equivalent of task hours per week greater increase in physical activity and a 1-unit higher logarithmic number of reported performances with a 0.51 (95% CI 0.07‐0.95) Healthy Diet Index point greater improvement in diet quality. Other associations between app use and outcomes were nonsignificant. Greater physical activity and a more positive attitude to e-services at baseline appeared to enhance the effect of app use on physical activity ( P values <.05). The app received a median acceptability rating of 2.9 (IQR 2.4‐3.3, scale: 1‐4) and a median overall score of 7 (IQR 5‐8, scale: 0‐10). Conclusions: An inexpensive, low-intensity digital support for healthy habits could foster small beneficial lifestyle changes, but effects require user engagement and may depend on the individual. The findings warrant confirmation in more robust study designs and call for further research for identifying those most likely to benefit from such digital support.

  • Open Access

    Unraveling the Factors Associated With Digital Health Intervention Uptake: Cross-Sectional Study

    by Ilona Ruotsalainen, Mikko Valtanen, Riikka Kärsämä, Adil Umer, Hilkka Liedes, Suvi Parikka, Annamari Lundqvist, Kirsikka Aittola, Suvi Koivunen, Jussi Pihlajamäki, et al.

    Background: Chronic noncommunicable diseases (NCDs) remain a leading health challenge worldwide, and reducing modifiable lifestyle risk factors is a key prevention strategy. Digital health interventions (DHIs) offer scalable, cost-effective tools to support healthy behaviors, but concerns persist about their equitable reach and uptake across population groups. Objective: This study aimed to examine how socioeconomic factors, health status, lifestyle behaviors, and attitudes and experiences related to the use of electronic services (e-services) are associated with the uptake of a DHI. Methods: In this cross-sectional study, we invited (through mail or SMS) a subgroup of 6978 participants aged 20-74 years from the population-based Healthy Finland survey to take part in a DHI. The DHI, delivered via the web-based BitHabit app, aimed to support the adoption of healthy lifestyle habits. Uptake was defined as successful registration, agreeing to the terms of use, and accepting the invitation to participate. Predictor variables were drawn from national registry and self-reported survey data and included socioeconomic status, health indicators, lifestyle behaviors, and attitudes and experiences related to the use of e-services. Adjusted logistic regression models were used to identify significant predictors of DHI uptake. Results: Of the final sample of 6975 participants, 1287 (18.5%) started using the DHI. Uptake was significantly higher among women (adjusted odds ratio [aOR] 1.69, 95% CI 1.49-1.93), middle-aged individuals (aOR 1.47, 95% CI 1.21-1.79), and those with higher income (aORs 1.76-1.97, 95% CIs 1.37-2.59) and more years of education (aOR 1.10, 95% CI 1.08-1.12). Healthier lifestyle indicators, including better diet quality (aOR 1.07, 95% CI 1.04-1.10), less frequent smoking or nonsmoking (aORs 1.59-2.29, 95% CIs 1.08-3.12), sleep (aOR 0.58, 95% CI 0.37-0.86), higher functional capacity (aOR 1.06, 95% CI 1.02-1.11), and good overall current health (aOR 1.46, 95% CI 1.15-1.89), were associated with increased likelihood of DHI uptake. The strongest predictors were related to the use of e-services: Individuals who used e-services (aORs 2.48-6.08, 95% CIs 1.19-11.92) reported higher competence to use e-services (aORs 2.00-4.10, 95% CIs 1.44-5.92), had low concerns about data security (aORs 1.37-1.76, 95% CIs 1.03-2.33), believed in the benefits of digital services (aOR 1.04, 95% CI 1.02-1.05), and had better internet connections had higher odds of uptake. Conclusions: Our findings show that DHI uptake is associated with socioeconomic status, health and lifestyle factors, and, especially, individuals’ experience and attitudes toward e-services. Individuals with lower education levels, lower income, and poorer health and lifestyle habits are less likely to adopt DHIs, raising concerns about potential digital health inequities. These results underscore the need for targeted strategies to reduce barriers and ensure more equitable reach and engagement in future DHI implementations.


  • Open Access

    Novel Sensors and Data-Driven Approach to Support Prevention, Diagnosis, and Treatment Planning of Cerebrovascular Accidents: Protocol for a Multimodal Data Collection Study With Novel Sensors (Preprint)

    by Milla Immonen, Hilkka Liedes, Aysen Degerli, Ilona Ruotsalainen, Juha Pajula, Mika Hilvo, Heidi Similä, Adil Umer, Mark van Gils, Miia Jansson, et al.

    BACKGROUND Stroke is the second leading cause of death worldwide. Cerebrovascular diseases (CVDs), including strokes and transient ischemic attacks (TIAs), cause long-term disabilities and economic burdens. Strokes can be ischemic, caused by blood clots; or hemorrhagic, caused by bleeding in the brain. Immediate diagnosis and treatment are crucial. Proper management of TIAs is essential due to the high risk of subsequent strokes. Currently, wearable sensors, AI-based prediction, and automatic video analysis are not used in CVD diagnosis and recovery estimation. OBJECTIVE This paper describes the design, cohort characteristics, and multimodal dataset of the Stroke-Data study conducted at 2 university hospitals in Finland. Although findings from individual components of the study have been reported elsewhere, this paper provides the first comprehensive description of the overall study design, cohort, and multimodal data collection protocol. The study collected a unique multimodal dataset comprising sensor data, video recordings, clinical assessments, questionnaires, and health record data from healthy controls and patients with stroke and TIA to support the development of AI, sensor-based, and video-based methods for CVD diagnosis and recovery estimation. METHODS Stroke-Data was a prospective national multicenter study conducted at Oulu University Hospital and Kuopio University Hospital from October 2021 to December 2022. A rich multimodal dataset from patients with stroke and TIA and healthy controls was collected by study nurses and a research assistant. Inclusion criteria for patients were age >18 years and a diagnosis of cerebrovascular accident or TIA within the previous 3 days. Healthy control participants were aged 18 years and older and had no major chronic diseases, although blood pressure and cholesterol medications were permitted. Data collection included electroencephalogram; electrocardiogram; near-infrared spectroscopy; accelerometers to analyze gait and balance; retinal fundus images; video recordings of neurological examinations to analyze the face, body movements, and speech; clinical assessments; questionnaires; and electronic health records. RESULTS In total, 263 participants were recruited, of whom 123 were controls (median age 59, IQR 45-72 years; female: 84/123, 68.3%), 31 were patients with TIA (median age 71, IQR 60-80 years; female: 8/31, 25.8%), and 103 were patients with stroke (median age 70, IQR 59-76 years; female: 42/102, 41.2%, sex data missing from 1 participant). A total of 6 participants were excluded (5 had diagnoses other than TIA or stroke and 1 control participant had a previous CVD). CONCLUSIONS We successfully conducted a multicenter multimodal data collection study on healthy controls and patients with stroke and TIA. This protocol paper provides a comprehensive methodological description of the Stroke-data study, serving as a reference for previously published and future analyses based on the dataset. The protocol is unique in combining physiological sensor data, video recordings, clinical assessments, questionnaires, and health record data from patients with stroke and TIA and healthy controls in a multicenter setting. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/86930

  • Open Access

    Development and consumer perceptions of a snack machine producing customized or personalized on-demand bakery products

    by Jenni Lappi, Anne Arvola, Alex Calton, Adil Umer, Saara Vanhatalo, Pekka Kilpeläinen, Kyösti Pennanen, Nesli Sozer


  • Open Access

    A Simulation-Based Study on Securing Data Sharing for Situational Awareness in a Port Accident Case

    by Juhani Latvakoski, Adil Umer, Topias Nykänen, Jyrki Tihinen, Aleksi Talman

    The cyber–physical systems (CPSs) of various stakeholders from the mobility, logistics, and security sectors are needed to enable smart and secure situational awareness operations in a port environment. The motivation for this research arises from the challenges caused by some unexpected events, such as accidents, in such a multi-stakeholder critical environment. Due to the scale, complexity, and cost and safety challenges, a simulation-based approach was selected as the basis for the study. Prototype-level experimental solutions for dataspaces for secure data sharing and visualization of situational awareness were developed. The secure data-sharing solution relies on the application of verifiable credentials (VCs) to ensure that data consumers have the required access rights to the data/information shared by the data prosumer. A 3D virtual digital twin model is applied for visualizing situational awareness for people in the port. The solutions were evaluated in a simulation-based execution of an accident scenario where a forklift catches fire while loading a docked ship in a port environment. The simulation-based approach and the provided solutions proved to be practical and enabled the smooth study of disaster-type situations. The realized concept of dataspaces is successfully applied here for both daily routine operations and information sharing during accidents in the simulation-based environment. During the evaluation, needs for future research related to perception, comprehension, projection, trust, and security as well as performance and quality of experience were detected. Especially, distributed and secure viewpoints of objects and stakeholders toward real-time situational awareness seem to require further studies.


  • Open Access

    Unraveling the Factors Associated With Digital Health Intervention Uptake: Cross-Sectional Study (Preprint)

    by Ilona Ruotsalainen, Mikko Valtanen, Riikka Kärsämä, Adil Umer, Hilkka Liedes, Suvi Parikka, Annamari Lundqvist, Kirsikka Aittola, Suvi Koivunen, Jussi Pihlajamäki, et al.

    BACKGROUND Chronic noncommunicable diseases (NCDs) remain a leading health challenge worldwide, and reducing modifiable lifestyle risk factors is a key prevention strategy. Digital health interventions (DHIs) offer scalable, cost-effective tools to support healthy behaviors, but concerns persist about their equitable reach and uptake across population groups. OBJECTIVE This study aimed to examine how socioeconomic factors, health status, lifestyle behaviors, and attitudes and experiences related to the use of electronic services (e-services) are associated with the uptake of a DHI. METHODS In this cross-sectional study, we invited (through mail or SMS) a subgroup of 6978 participants aged 20-74 years from the population-based Healthy Finland survey to take part in a DHI. The DHI, delivered via the web-based BitHabit app, aimed to support the adoption of healthy lifestyle habits. Uptake was defined as successful registration, agreeing to the terms of use, and accepting the invitation to participate. Predictor variables were drawn from national registry and self-reported survey data and included socioeconomic status, health indicators, lifestyle behaviors, and attitudes and experiences related to the use of e-services. Adjusted logistic regression models were used to identify significant predictors of DHI uptake. RESULTS Of the final sample of 6975 participants, 1287 (18.5%) started using the DHI. Uptake was significantly higher among women (adjusted odds ratio [aOR] 1.69, 95% CI 1.49-1.93), middle-aged individuals (aOR 1.47, 95% CI 1.21-1.79), and those with higher income (aORs 1.76-1.97, 95% CIs 1.37-2.59) and more years of education (aOR 1.10, 95% CI 1.08-1.12). Healthier lifestyle indicators, including better diet quality (aOR 1.07, 95% CI 1.04-1.10), less frequent smoking or nonsmoking (aORs 1.59-2.29, 95% CIs 1.08-3.12), sleep (aOR 0.58, 95% CI 0.37-0.86), higher functional capacity (aOR 1.06, 95% CI 1.02-1.11), and good overall current health (aOR 1.46, 95% CI 1.15-1.89), were associated with increased likelihood of DHI uptake. The strongest predictors were related to the use of e-services: Individuals who used e-services (aORs 2.48-6.08, 95% CIs 1.19-11.92) reported higher competence to use e-services (aORs 2.00-4.10, 95% CIs 1.44-5.92), had low concerns about data security (aORs 1.37-1.76, 95% CIs 1.03-2.33), believed in the benefits of digital services (aOR 1.04, 95% CI 1.02-1.05), and had better internet connections had higher odds of uptake. CONCLUSIONS Our findings show that DHI uptake is associated with socioeconomic status, health and lifestyle factors, and, especially, individuals’ experience and attitudes toward e-services. Individuals with lower education levels, lower income, and poorer health and lifestyle habits are less likely to adopt DHIs, raising concerns about potential digital health inequities. These results underscore the need for targeted strategies to reduce barriers and ensure more equitable reach and engagement in future DHI implementations.

  • Open Access

    Influencing Factors in Digital Health Intervention Uptake: The Interplay of Education, Lifestyle, and Digital Literacy

    by Ilona Ruotsalainen, Mikko Valtanen, Riikka Kärsämä, Adil Umer, Suvi Parikka, Annamari Lundqvist, Jaana Lindström

    Chronic diseases strain global healthcare economically, and integrating digital solutions are proposed to help in meeting the rising demand. Digital health interventions (DHIs) offer promise for personalized, and cost-effective health services, however, factors influencing their uptake remain unclear. We examined whether the probability of lifestyle DHI uptake varies among individuals with different educational levels and lifestyles, based on their attitudes and usage of e-services. We also examined the effect of sex and age, and the association between DHI uptake and both educational attainment and overall lifestyle. A possibility to start using a web-based lifestyle DHI was offered to a subgroup (n = 6978) of Healthy Finland survey participants and adjusted logistic regression models were used to investigate the factors affecting uptake. We found that higher education and healthier lifestyle, as indicated by lifestyle score, were related to higher odds of DHI uptake. However, the effects of age, sex, independence of e-service use, and competence to use online services varied across lifestyle score groups. No significant interactions were observed related to educational attainment. These results imply that lifestyle DHIs are less likely to reach individuals with less-healthy lifestyle habits and lower educational attainment. In addition, some predictors affected the uptake differently across lifestyle score groups, suggesting that implementations of DHIs might attempt strategies to optimize the participation rates in especially targeted subgroups.


  • Open Access

    Unraveling the factors associated with digital health intervention uptake

    by Ilona Ruotsalainen, Mikko Valtanen, Riikka Kärsämä, Adil Umer, Hilkka Liedes, Suvi Parikka, Annamari Lundqvist, Kirsikka Aittola, Suvi Manninen, Jussi Pihlajamäki, et al.

    For preventing chronic diseases, reducing modifiable lifestyle risk factors is crucial. Digital health interventions (DHIs) hold promise for reaching large population groups, but raise health equity concerns. A subgroup (n=6978) of 20 to 74-year-old participants of the population-based Healthy Finland survey were offered an opportunity to start using a web-based DHI, aiming to support adoption of healthy lifestyle habits. We used adjusted logistic regression models to identify significant predictors of DHI uptake. Women (adjusted odds ratio [aOR] 1.69, 95% CI 1.49–1.93), middle-aged individuals (1.47, 1.21–1.79), and those with higher income (aORs between 1.76–1.97) and education (1.10, 1.08–1.12) had higher odds of DHI uptake. Moreover, healthier lifestyle indicated by better diet quality (1.07, 1.04– 1.10), less frequent or non-smoking (aORs between 1.59–2.29), sleep (0.58, 0.37–0.86), higher functional capacity (1.06, 1.02–1.11), and good overall current health (1.46, 1.15– 1.89) associated with increased likelihood of DHI uptake. Lastly, individuals with better internet connections, higher competence to use e-services (aORs between 2.00–4.10), low concerns about data security (aORs between 1.37–1.76), stronger belief in benefits of digital services (1.04, 1.02–1.05), and reporting to use e-services (aORs between 2.48–6.08) had higher odds of uptake. Our findings indicate that those with higher socioeconomic status, better health and healthier lifestyle are more likely to take up DHI. Our research also highlights the impact of digital literacy and positive attitudes towards online services in adopting DHIs. These insights will be valuable in shaping strategies for future DHI initiatives.


  • Open Access

    Tailored Food Recommendations in Facilitating Dietary Change: A Rule-Based Personalized Eating Solution

    by Jenni Lappi, Adil Umer, Jaakko Lähteenmäki, Nesli Sözer

    Background and objectives: A concept of personalized eating originates from personalized nutrition, where dietary advice is tailored to an individual. In personalized nutrition solutions, dietary advice is more and more based on clinical biomarkers, genetics, and the gut microbiome. However, there is evidence that tailored dietary advice based only on personal dietary data is effective in facilitating changes in dietary intakes. Thus, the aim is to create a personalized eating solution: a prototype of data platform recommends foods by linking individual’s dietary data with product information via specified rules. Methods: The data platform is integrated with an external global food product database and a user interface (UI), and the system structure is: (1) a personal profile, (2) a rules engine with functionality for setting tags and filtering rules, and (3) a knowledge database (food product database). The food product database is integrated via an open API (application programming interface) with the platform, and is utilized to retrieve product information for the filtering rules. When using the platform for the first time, a user must enter demographic data and information about specific dietary criteria and personal preferences. With the permission from the user, the data platform may also retrieve data for the personal profile from other integrated services, including wearable devices. Food recommendations are generated by filtering the product information based on the personal profile and food groups selected by the user. The user can access the food recommendations via a web-based UI. The platform also includes an API, which allows the recommendations to be integrated to existing wellness applications and devices. Results and Discussion: The personalized eating solution suitability for use by consumers and ecommerce services will be tested in 2023. A strength is that the solution considers personal preferences to motivate users, such as values related to the consumption of ethic and sustainable products. However, the food recommendation rules rely on formal information about products in the external food database. In the future, the solution could be used for research, commercial, and healthcare purposes in facilitating dietary changes to promote health and wellbeing.