Dataset Information

Mobile Health (mHealth) Viral Diagnostics Enabled with Adaptive Adversarial Learning.

ABSTRACT: Deep-learning (DL)-based image processing has potential to revolutionize the use of smartphones in mobile health (mHealth) diagnostics of infectious diseases. However, the high variability in cellphone image data acquisition and the common need for large amounts of specialist-annotated images for traditional DL model training may preclude generalizability of smartphone-based diagnostics. Here, we employed adversarial neural networks with conditioning to develop an easily reconfigurable virus diagnostic platform that leverages a dataset of smartphone-taken microfluidic chip photos to rapidly generate image classifiers for different target pathogens on-demand. Adversarial learning was also used to augment this real image dataset by generating 16,000 realistic synthetic microchip images, through style generative adversarial networks (StyleGAN). We used this platform, termed smartphone-based pathogen detection resource multiplier using adversarial networks (SPyDERMAN), to accurately detect different intact viruses in clinical samples and to detect viral nucleic acids through integration with CRISPR diagnostics. We evaluated the performance of the system in detecting five different virus targets using 179 patient samples. The generalizability of the system was confirmed by rapid reconfiguration to detect SARS-CoV-2 antigens in nasal swab samples (n = 62) with 100% accuracy. Overall, the SPyDERMAN system may contribute to epidemic preparedness strategies by providing a platform for smartphone-based diagnostics that can be adapted to a given emerging viral agent within days of work.

SUBMITTER: Shokr A

PROVIDER: S-EPMC8299938 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Mobile Health (mHealth) Viral Diagnostics Enabled with Adaptive Adversarial Learning.

Shokr Ahmed A Pacheco Luis G C LGC Thirumalaraju Prudhvi P Kanakasabapathy Manoj Kumar MK Gandhi Jahnavi J Kartik Deeksha D Silva Filipe S R FSR Erdogmus Eda E Kandula Hemanth H Luo Shenglin S Yu Xu G XG Chung Raymond T RT Li Jonathan Z JZ Kuritzkes Daniel R DR Shafiee Hadi H

ACS nano 20201123 1

Deep-learning (DL)-based image processing has potential to revolutionize the use of smartphones in mobile health (mHealth) diagnostics of infectious diseases. However, the high variability in cellphone image data acquisition and the common need for large amounts of specialist-annotated images for traditional DL model training may preclude generalizability of smartphone-based diagnostics. Here, we employed adversarial neural networks with conditioning to develop an easily reconfigurable virus dia ...[more]

PMID: 33226787

Similar Datasets

Project description:Background: Healthy aging is critically important for several reasons, including economic impact and quality of life. As the population of older adults rapidly increases, identifying acceptable ways to promote healthy aging is a priority. Technologies that can facilitate health promotion and risk reduction behaviors may be a solution, but only if these mobile health (mHealth) tools can be used by the older adult population. Within the context of a physical activity intervention, this study gathered participant's opinions about the use of an mHealth device to learn about acceptance and to identify areas for improvement. Methods: The Independent Walking for Brain Health study (NCT03058146) was designed to evaluate the effectiveness of a wearable mHealth technology in facilitating adherence to a physical activity prescription among participants in free-living environments. An Exit Survey was conducted following intervention completion to gauge participant's perceptions and solicit feedback regarding the overall study design, including exercise promotion strategies and concerns specific to the technology (e.g., privacy), that could inform more acceptable mHealth interventions in the future. The Digital Health Checklist and Framework was used to guide the analysis focusing on the domains of Privacy, Access and Usability, and Data Management. Results: Participants (n = 41) were in their early 70's (mean = 71.6) and were predominantly female (75.6%) and White (92.7%). Most were college educated (16.9 years) and enjoyed using technology in their everyday life (85.4%). Key challenges included privacy concerns, device accuracy, usability, and data access. Specifically, participants want to know what is being learned about them and want control over how their identifiable data may be used. Overall, participants were able to use the device despite the design challenges. Conclusions: Understanding participant's perceptions of the challenges and concerns introduced by mHealth is important, as acceptance will influence adoption and adherence to the study protocol. While this study learned from participants at studycompletion, we recommend that researchers consider what might influence participant acceptance of the technology (access, data management, privacy, risks) and build these into the mHealth study design process. We provide recommendations for future mHealth studies with older adults.

Project description:IntroductionDiagnosis is a key step towards the provision of medical intervention and saving lives. However, in low- and middle-income countries, diagnostic services are mainly centralized in large cities and are costly. Point of care (POC) diagnostic technologies have been developed to fill the diagnostic gap for remote areas. The linkage of POC testing onto smartphones has leveraged the ever-expanding coverage of mobile phones to enhance health services in low- and middle-income countries. Tanzania, like most other middle-income countries, is poised to adopt and deploy the use of mobile phone-enabled diagnostic devices. However, there is limited information on the situation on the ground with regard to readiness and capabilities of the veterinary and medical professionals to make use of this technology.MethodsIn this study we survey awareness, digital literacy and prevalent health condition to focus on in Tanzania to guide development and future implementation of mobile phoned-enable diagnostic tools by veterinary and medical professionals. Data was collected using semi-structured questionnaire with closed and open-ended questions, guided in-depth interviews and focus group discussion administered to the participants after informed consent was obtained.ResultsA total of 305 participants from six regions of Tanzania were recruited in the study. The distribution of participants across the six regions was as follows: Kilimanjaro (37), Arusha (31), Tabora (68), Dodoma (61), Mwanza (58), and Iringa (50). Our analysis reveals that only 48.2% (126/255) of participants demonstrated significant awareness of mobile phone-enabled diagnostics. This awareness varies significantly across age groups, professions and geographical locations. Interestingly, while 97.4% of participants own and can operate a smartphone, 62% have never utilized their smartphones for health services, including disease diagnosis. Regarding prevalent health condition to focus on when developing mobile phone -enabled diagnostics tools for Tanzania; there was disparity between medical and veterinary professionals. For medical professionals the top 4 priority diseases were Malaria, Urinary Tract Infections, HIV and Diabetes, while for veterinary professionals they were Brucellosis, Anthrax, Newcastle disease and Rabies.DiscussionDespite the widespread ownership of smartphones among healthcare providers (both human and animal), only a small proportion have utilized these devices for healthcare practices, with none reported for diagnostic purposes. This limited utilization may be attributed to factors such as a lack of awareness, absence of policy guidelines, limited promotion, challenges related to mobile data connectivity, and adherence to cultural practices.ConclusionThe majority of medical and veterinary professionals in Tanzania possess the necessary digital literacy to utilize mobile phone-enabled diagnostics and demonstrate readiness to adopt digital technologies and innovations to enhance diagnosis. However, effective implementation will require targeted training and interventions to empower them to effectively apply such innovations for disease diagnosis and other healthcare applications.

Dataset Information

Mobile Health (mHealth) Viral Diagnostics Enabled with Adaptive Adversarial Learning.

Publications

Mobile Health (mHealth) Viral Diagnostics Enabled with Adaptive Adversarial Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets