Targeting ethical considerations tied to image-based mobile health diagnostic support specific to clinicians in low-resource settings: the Brocher proposition

Advancing mHealth Research in Low-Resource Settings: Young Women's Insights and Implementation Challenges with Wearable Smartwatch Devices in Uganda

In many regions globally, including low-resource settings, there is a growing trend towards using mHealth technology, such as wearable sensors, to enhance health behaviors and outcomes. However, adoption of such devices in research conducted in low-resource settings lags behind use in high-resource areas. Moreover, there is a scarcity of research that specifically examines the user experience, readiness for and challenges of integrating wearable sensors into health research and community interventions in low-resource settings specifically. This study summarizes the reactions and experiences of young women (N = 57), ages 18 to 24 years, living in poverty in Kampala, Uganda, who wore Garmin vívoactive 3 smartwatches for five days for a research project. Data collected from the Garmins included participant location, sleep, and heart rate. Through six focus group discussions, we gathered insights about the participants' experiences and perceptions of the wearable devices. Overall, the wearable devices were met with great interest and enthusiasm by participants. The findings were organized across 10 domains to highlight reactions and experiences pertaining to device settings, challenges encountered with the device, reports of discomfort/comfort, satisfaction, changes in daily activities, changes to sleep, speculative device usage, community reactions, community dynamics and curiosity, and general device comfort. The study sheds light on the introduction of new technology in a low-resource setting and also on the complex interplay between technology and culture in Kampala's slums. We also learned some insights into how wearable devices and perceptions may influence behaviors and social dynamics. These practical insights are shared to benefit future research and applications by health practitioners and clinicians to advance and enhance the implementation and effectiveness of wearable devices in similar contexts and populations. These insights and user experiences, if incorporated, may enhance device acceptance and data quality for those conducting research in similar settings or seeking to address population-specific needs and health issues.

Development and evaluation of deep learning algorithms for assessment of acute burns and the need for surgery

Assessment of burn extent and depth are critical and require very specialized diagnosis. Automated image-based algorithms could assist in performing wound detection and classification. We aimed to develop two deep-learning algorithms that respectively identify burns, and classify whether they require surgery. An additional aim assessed the performances in different Fitzpatrick skin types. Annotated burn (n = 1105) and background (n = 536) images were collected. Using a commercially available platform for deep learning algorithms, two models were trained and validated on 70% of the images and tested on the remaining 30%. Accuracy was measured for each image using the percentage of wound area correctly identified and F1 scores for the wound identifier; and area under the receiver operating characteristic (AUC) curve, sensitivity, and specificity for the wound classifier. The wound identifier algorithm detected an average of 87.2% of the wound areas accurately in the test set. For the wound classifier algorithm, the AUC was 0.885. The wound identifier algorithm was more accurate in patients with darker skin types; the wound classifier was more accurate in patients with lighter skin types. To conclude, image-based algorithms can support the assessment of acute burns with relatively good accuracy although larger and different datasets are needed.

Emotion detection for supporting depression screening

Depression is the most prevalent mental disorder in the world. One of the most adopted tools for depression screening is the Beck Depression Inventory-II (BDI-II) questionnaire. Patients may minimize or exaggerate their answers. Thus, to further examine the patient's mood while filling in the questionnaire, we propose a mobile application that captures the BDI-II patient's responses together with their images and speech. Deep learning techniques such as Convolutional Neural Networks analyze the patient's audio and image data. The application displays the correlation between the patient's emotional scores and DBI-II scores to the clinician at the end of the questionnaire, indicating the relationship between the patient's emotional state and the depression screening score. We conducted a preliminary evaluation involving clinicians and patients to assess (i) the acceptability of proposed application for use in clinics and (ii) the patient user experience. The participants were eight clinicians who tried the tool with 21 of their patients. The results seem to confirm the acceptability of the app in clinical practice.