Assessment of Clinical Metadata on the Accuracy of Retinal Fundus Image Labels in Diabetic Retinopathy in Uganda: Case-Crossover Study Using the Multimodal Database of Retinal Images in Africa.

BACKGROUND: Labeling color fundus photos (CFP) is an important step in the development of artificial intelligence screening algorithms for the detection of diabetic retinopathy (DR). Most studies use the International Classification of Diabetic Retinopathy (ICDR) to assign labels to CFP, plus the presence or absence of macular edema (ME). Images can be grouped as referrable or nonreferrable according to these classifications. There is little guidance in the literature about how to collect and use metadata as a part of the CFP labeling process. OBJECTIVE: This study aimed to improve the quality of the Multimodal Database of Retinal Images in Africa (MoDRIA) by determining whether the availability of metadata during the image labeling process influences the accuracy, sensitivity, and specificity of image labels. MoDRIA was developed as one of the inaugural research projects of the Mbarara University Data Science Research Hub, part of the Data Science for Health Discovery and Innovation in Africa (DS-I Africa) initiative. METHODS: This is a crossover assessment with 2 groups and 2 phases. Each group had 10 randomly assigned labelers who provided an ICDR score and the presence or absence of ME for each of the 50 CFP in a test image with and without metadata including blood pressure, visual acuity, glucose, and medical history. Specificity and sensitivity of referable retinopathy were based on ICDR scores, and ME was calculated using a 2-sided t test. Comparison of sensitivity and specificity for ICDR scores and ME with and without metadata for each participant was calculated using the Wilcoxon signed rank test. Statistical significance was set at P<.05. RESULTS: The sensitivity for identifying referrable DR with metadata was 92.8% (95% CI 87.6-98.0) compared with 93.3% (95% CI 87.6-98.9) without metadata, and the specificity was 84.9% (95% CI 75.1-94.6) with metadata compared with 88.2% (95% CI 79.5-96.8) without metadata. The sensitivity for identifying the presence of ME was 64.3% (95% CI 57.6-71.0) with metadata, compared with 63.1% (95% CI 53.4-73.0) without metadata, and the specificity was 86.5% (95% CI 81.4-91.5) with metadata compared with 87.7% (95% CI 83.9-91.5) without metadata. The sensitivity and specificity of the ICDR score and the presence or absence of ME were calculated for each labeler with and without metadata. No findings were statistically significant. CONCLUSIONS: The sensitivity and specificity scores for the detection of referrable DR were slightly better without metadata, but the difference was not statistically significant. We cannot make definitive conclusions about the impact of metadata on the sensitivity and specificity of image labels in our study. Given the importance of metadata in clinical situations, we believe that metadata may benefit labeling quality. A more rigorous study to determine the sensitivity and specificity of CFP labels with and without metadata is recommended.

Enhancing the Implementation and Integration of mHealth Interventions in Resource-Limited Settings: A Scoping Review.

Background: Although mobile health (mHealth) interventions have shown promise in improving health outcomes, most of them rarely translate to scale. Prevailing mHealth studies are largely small-sized, short-term and donor-funded pilot studies with limited evidence on their effectiveness. To facilitate scale-up, several frameworks have been proposed to enhance the generic implementation of health interventions. However, there is a lack of a specific focus on the implementation and integration of mHealth interventions in routine care in low-resource settings. Our scoping review aimed to synthesize and develop a framework that could guide the implementation and integration of mHealth interventions. Methods: We searched the PubMed, Google Scholar, and ScienceDirect databases for published theories, models, and frameworks related to the implementation and integration of clinical interventions from 1st January 2000 to 31st December 2023. The data processing was guided by a scoping review methodology proposed by Arksey and O'Malley. Studies were included if they were i) peer-reviewed and published between 2000 and 2023, ii) explicitly described a framework for clinical intervention implementation and integration, or iii) available in full text and published in English. We integrated different domains and constructs from the reviewed frameworks to develop a new framework for implementing and integrating mHealth interventions. Results: We identified eight eligible papers with eight frameworks composed of 102 implementation domains. None of the identified frameworks were specific to the integration of mHealth interventions in low-resource settings. Two constructs (skill impartation and intervention awareness) related to the training domain, four constructs (technical and logistical support, identifying committed staff, supervision, and redesigning) from the restructuring domain, two constructs (monetary incentives and nonmonetary incentives) from the incentivize domain, two constructs (organizational mandates and government mandates) from the mandate domain and two constructs (collaboration and routine workflows) from the integrate domain. Therefore, a new framework that outlines five main domains-train, restructure, incentivize, mandate, and integrate (TRIMI)-in relation to the integration and implementation of mHealth interventions in low-resource settings emerged. Conclusion: The TRIMI framework presents a realistic and realizable solution for the implementation and integration deficits of mHealth interventions in low-resource settings.

Acceptability and feasibility of a mobile health application for enhancing public private mix for TB care among healthcare Workers in Southwestern Uganda.

Background: Mobile health interventions can potentially enhance public-private linkage for tuberculosis care. However, evidence about their acceptability and feasibility is lacking. This study sought to assess the initial acceptability and feasibility of a mobile health application for following up on presumptive tuberculosis patients referred from private to public hospitals. Twenty-two healthcare workers from three private hospitals and a public hospital in southwestern Uganda received the Tuuka mobile application for 1 month for testing. Testing focused on referring patients by healthcare workers from private hospitals and receiving referred patients by public healthcare workers and sending SMS reminders to the referred patients by filling out the digital referral forms inbuilt within the app. Study participants participated in qualitative semi-structured in-depth interviews on the acceptability and feasibility of this app. An inductive, content analytic approach, framed by the unified theory of acceptance and use of technology model, was used to analyze qualitative data. Quantitative feasibility metrics and the quantitative assessment of acceptability were analyzed descriptively using STATA. Results: Healthcare workers found the Tuuka application acceptable and feasible, with a mean total system usability scale score of 98 (SD 1.97). The majority believed that the app would help them make quicker medical decisions (91%), communicate with other healthcare workers (96%), facilitate partnerships with other hospitals (100%), and enhance quick TB case notification (96%). The application was perceived to be useful in reminding referred patients to adhere to referral appointments, notifying public hospital healthcare workers about the incoming referred patients, facilitating communication across facilities, and enhancing patient-based care. Conclusion: The Tuuka mobile health application is acceptable and feasible for following up on referred presumptive tuberculosis patients referred from private to public hospitals in southwestern Uganda. Future efforts should focus on incorporating incentives to motivate and enable sustained use among healthcare workers. Supplementary Information: The online version contains supplementary material available at 10.1186/s44247-023-00009-0.

Digital Determinants of Health: Health data poverty amplifies existing health disparities-A scoping review.

Artificial intelligence (AI) and machine learning (ML) have an immense potential to transform healthcare as already demonstrated in various medical specialties. This scoping review focuses on the factors that influence health data poverty, by conducting a literature review, analysis, and appraisal of results. Health data poverty is often an unseen factor which leads to perpetuating or exacerbating health disparities. Improvements or failures in addressing health data poverty will directly impact the effectiveness of AI/ML systems. The potential causes are complex and may enter anywhere along the development process. The initial results highlighted studies with common themes of health disparities (72%), AL/ML bias (28%) and biases in input data (18%). To properly evaluate disparities that exist we recommend a strengthened effort to generate unbiased equitable data, improved understanding of the limitations of AI/ML tools, and rigorous regulation with continuous monitoring of the clinical outcomes of deployed tools.