Investigating Rhythmicity in App Usage to Predict Depressive Symptoms: Protocol for Personalized Framework Development and Validation Through a Countrywide Study.

BACKGROUND: Understanding a student's depressive symptoms could facilitate significantly more precise diagnosis and treatment. However, few studies have focused on depressive symptom prediction through unobtrusive systems, and these studies are limited by small sample sizes, low performance, and the requirement for higher resources. In addition, research has not explored whether statistically significant rhythms based on different app usage behavioral markers (eg, app usage sessions) exist that could be useful in finding subtle differences to predict with higher accuracy like the models based on rhythms of physiological data. OBJECTIVE: The main objective of this study is to explore whether there exist statistically significant rhythms in resource-insensitive app usage behavioral markers and predict depressive symptoms through these marker-based rhythmic features. Another objective of this study is to understand whether there is a potential link between rhythmic features and depressive symptoms. METHODS: Through a countrywide study, we collected 2952 students' raw app usage behavioral data and responses to the 9 depressive symptoms in the 9-item Patient Health Questionnaire (PHQ-9). The behavioral data were retrieved through our developed app, which was previously used in our pilot studies in Bangladesh on different research problems. To explore whether there is a rhythm based on app usage data, we will conduct a zero-amplitude test. In addition, we will develop a cosinor model for each participant to extract rhythmic parameters (eg, acrophase). In addition, to obtain a comprehensive picture of the rhythms, we will explore nonparametric rhythmic features (eg, interdaily stability). Furthermore, we will conduct regression analysis to understand the association of rhythmic features with depressive symptoms. Finally, we will develop a personalized multitask learning (MTL) framework to predict symptoms through rhythmic features. RESULTS: After applying inclusion criteria (eg, having app usage data of at least 2 days to explore rhythmicity), we kept the data of 2902 (98.31%) students for analysis, with 24.48 million app usage events, and 7 days' app usage of 2849 (98.17%) students. The students are from all 8 divisions of Bangladesh, both public and private universities (19 different universities and 52 different departments). We are analyzing the data and will publish the findings in a peer-reviewed publication. CONCLUSIONS: Having an in-depth understanding of app usage rhythms and their connection with depressive symptoms through a countrywide study can significantly help health care professionals and researchers better understand depressed students and may create possibilities for using app usage-based rhythms for intervention. In addition, the MTL framework based on app usage rhythmic features may more accurately predict depressive symptoms due to the rhythms' capability to find subtle differences. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/51540.

Understanding the Sociocultural Challenges and Opportunities for Affordable Wearables to Support Poststroke Upper-Limb Rehabilitation: Qualitative Study.

Background: People who survive a stroke in many cases require upper-limb rehabilitation (ULR), which plays a vital role in stroke recovery practices. However, rehabilitation services in the Global South are often not affordable or easily accessible. For example, in Bangladesh, the access to and use of rehabilitation services is limited and influenced by cultural factors and patients' everyday lives. In addition, while wearable devices have been used to enhance ULR exercises to support self-directed home-based rehabilitation, this has primarily been applied in developed regions and is not common in many Global South countries due to potential costs and limited access to technology. Objective: Our goal was to better understand physiotherapists', patients', and caregivers' experiences of rehabilitation in Bangladesh, existing rehabilitation practices, and how they differ from the rehabilitation approach in the United Kingdom. Understanding these differences and experiences would help to identify opportunities and requirements for developing affordable wearable devices that could support ULR in home settings. Methods: We conducted an exploratory study with 14 participants representing key stakeholder groups. We interviewed physiotherapists and patients in Bangladesh to understand their approaches, rehabilitation experiences and challenges, and technology use in this context. We also interviewed UK physiotherapists to explore the similarities and differences between the 2 countries and identify specific contextual and design requirements for low-cost wearables for ULR. Overall, we remotely interviewed 8 physiotherapists (4 in the United Kingdom, 4 in Bangladesh), 3 ULR patients in Bangladesh, and 3 caregivers in Bangladesh. Participants were recruited through formal communications and personal contacts. Each interview was conducted via videoconference, except for 2 interviews, and audio was recorded with consent. A total of 10 hours of discussions were transcribed. The results were analyzed using thematic analysis. Results: We identified several sociocultural factors that affect ULR and should be taken into account when developing technologies for the home: the important role of family, who may influence the treatment based on social and cultural perceptions; the impact of gender norms and their influence on attitudes toward rehabilitation and physiotherapists; and differences in approach to rehabilitation between the United Kingdom and Bangladesh, with Bangladeshi physiotherapists focusing on individual movements that are necessary to build strength in the affected parts and their British counterparts favoring a more holistic approach. We propose practical considerations and design recommendations for developing ULR devices for low-resource settings. Conclusions: Our work shows that while it is possible to build a low-cost wearable device, the difficulty lies in addressing sociotechnical challenges. When developing new health technologies, it is imperative to not only understand how well they could fit into patients', caregivers', and physiotherapists' everyday lives, but also how they may influence any potential tensions concerning culture, religion, and the characteristics of the local health care system.

A Fast and Minimal System to Identify Depression Using Smartphones: Explainable Machine Learning-Based Approach.

BACKGROUND: Existing robust, pervasive device-based systems developed in recent years to detect depression require data collected over a long period and may not be effective in cases where early detection is crucial. Additionally, due to the requirement of running systems in the background for prolonged periods, existing systems can be resource inefficient. As a result, these systems can be infeasible in low-resource settings. OBJECTIVE: Our main objective was to develop a minimalistic system to identify depression using data retrieved in the fastest possible time. Another objective was to explain the machine learning (ML) models that were best for identifying depression. METHODS: We developed a fast tool that retrieves the past 7 days' app usage data in 1 second (mean 0.31, SD 1.10 seconds). A total of 100 students from Bangladesh participated in our study, and our tool collected their app usage data and responses to the Patient Health Questionnaire-9. To identify depressed and nondepressed students, we developed a diverse set of ML models: linear, tree-based, and neural network-based models. We selected important features using the stable approach, along with 3 main types of feature selection (FS) approaches: filter, wrapper, and embedded methods. We developed and validated the models using the nested cross-validation method. Additionally, we explained the best ML models through the Shapley additive explanations (SHAP) method. RESULTS: Leveraging only the app usage data retrieved in 1 second, our light gradient boosting machine model used the important features selected by the stable FS approach and correctly identified 82.4% (n=42) of depressed students (precision=75%, F1-score=78.5%). Moreover, after comprehensive exploration, we presented a parsimonious stacking model where around 5 features selected by the all-relevant FS approach Boruta were used in each iteration of validation and showed a maximum precision of 77.4% (balanced accuracy=77.9%). Feature importance analysis suggested app usage behavioral markers containing diurnal usage patterns as being more important than aggregated data-based markers. In addition, a SHAP analysis of our best models presented behavioral markers that were related to depression. For instance, students who were not depressed spent more time on education apps on weekdays, whereas those who were depressed used a higher number of photo and video apps and also had a higher deviation in using photo and video apps over the morning, afternoon, evening, and night time periods of the weekend. CONCLUSIONS: Due to our system's fast and minimalistic nature, it may make a worthwhile contribution to identifying depression in underdeveloped and developing regions. In addition, our detailed discussion about the implication of our findings can facilitate the development of less resource-intensive systems to better understand students who are depressed and take steps for intervention.

Risk communication and community engagement during COVID-19.

In today's information age, both excess and lack of information can cause a disaster. COVID-19 pandemic not only highlighted the significance of risk communication but also pointed out several unintended and distressing consequences due to information gaps and miscommunications. Despite facing a common threat, the local communities suffered differential impacts during the pandemic. This paper classifies the nature of risk communications experienced across different countries into three categories, namely: inadequate, ideal, and infodemic risk communication that influenced the local perceptions and responses. It further argues that inadequately planned risk communications tend to create new risks and compromise the efforts towards managing a disaster. As global risks are responded locally, there is a need for more inclusive and engaging risk communication that involves communities as responsible stakeholders who understand, plan, and respond to risks to increase their propensity for resilience during disasters and crisis situations.

The nature, cause and consequence of COVID-19 panic among social media users in India.

The recent pandemic of COVID-19 has not only shaken the healthcare but also economic structure around the world. In addition to these direct effects, it has also brought in some indirect difficulties owing to the information epidemic (hereafter termed as infodemic) on social media. We aimed to understand the nature of panic social media users in India are experiencing due to the flow of (mis)information. We further extend this investigation to other countries. We performed a cross-sectional study on 1075 social media users from India and 29 other countries. This revealed a significant increase in social media usage and the rise of panic (symbolizing a sense of alarm and/or fear) over time in India. Several of these behaviors are unique to social media users in India possibly because of later outbreak of COVID-19 and a prolonged uninterrupted lockdown. The amount of social media usage might not be causal but has a significant role in generating panic among the people in India. As multiple countries are entering into the second phase of lockdown, this study focused on India might provide a unique perspective of how various factors, including infodemic, affect the mental state of individuals around the globe. SUPPLEMENTARY INFORMATION: The online version supplementary material available at 10.1007/s13278-021-00750-2.

Chikungunya outbreak (2017) in Bangladesh: Clinical profile, economic impact and quality of life during the acute phase of the disease.

BACKGROUND: Chikungunya virus causes mosquito-transmitted infection that leads to extensive morbidity affecting substantial quality of life. Disease associated morbidity, quality of life, and financial loss are seldom reported in resources limited countries, such as Bangladesh. We reported the acute clinical profile, quality of life and consequent economic burden of the affected individuals in the recent chikungunya outbreak (May to September 2017) in Dhaka city, Bangladesh. METHODS: We conducted a cross-sectional study during the peak of chikungunya outbreak (July 24 to August 5, 2017) to document the clinical profiles of confirmed cases (laboratory test positive) and probable cases diagnosed by medical practitioners. Data related to clinical symptoms, treatment cost, loss of productivity due to missing work days, and quality of life during their first two-weeks of symptom onset were collected via face to face interview using a structured questionnaire. World Health Organization endorsed questionnaire was used to assess the quality of life. RESULTS: A total of 1,326 chikungunya cases were investigated. Multivariate analysis of major clinical variables showed no statistically significant differences between confirmed and probable cases. All the patients reported joint pain and fever. Other more frequently reported symptoms include headache, loss of appetite, rash, myalgia, and itching. Arthralgia was polyarticular in 56.3% of the patients. Notably, more than 70% patients reported joint pain as the first presenting symptom. About 83% of the patients reported low to very low overall quality of life. Nearly 30% of the patients lost more than 10 days of productivity due to severe arthropathy. CONCLUSIONS: This study represents one of the largest samples studied so far around the world describing the clinical profile of chikungunya infection. Our findings would contribute to establish an effective syndromic surveillance system for early detection and timely public health intervention of future chikungunya outbreaks in resource-limited settings like Bangladesh.