International Conference on Pervasive Computing Technologies for Healthcare : [proceedings]

Cannabis use among emerging adults is increasing globally, posing significant health risks and creating a need for effective interventions. We present an exploratory analysis of the MiWaves pilot study, a digital intervention aimed at supporting cannabis use reduction among emerging adults (ages 18-25). Our findings indicate the potential of self-monitoring check-ins and trend visualizations in fostering self-awareness and promoting behavioral reflection in participants. MiWaves intervention message timing and frequency were also generally well-received by the participants. The participants' perception of effort were queried on intervention messages with different tasks, and our findings suggest that messages with tasks like exploring links and typing in responses are perceived as requiring more effort as compared to messages with tasks involving reading and acknowledging. Finally, we discuss the findings and limitations from this study and analysis, and their impact on informing future iterations on MiWaves.

Adolescents are recommended to sleep at least 8-10 h per day. Inadequate sleep in adolescents is detrimental to their overall wellbeing and is linked to poor academic performance. Identifying causes of poor sleep in the sleep environment can help researchers and adolescents determine what changes need to be made to improve sleep quality. However, in-situ sleep monitoring is challenging because measurements cannot interfere with sleep, and people are poor at remembering what happens during the night. We report on the feasibility testing of an in-situ sleep monitoring application that uses passive sensing to drive context-sensitive ecological momentary assessments (EMAs) to help participants recall sleep disruptions when they wake up in the morning. Participants answered over 80% of EMAs delivered during the feasibility study and could recall meaningful reasons for over 40% of noise and motion events when they answered context-sensitive questions presented in the morning EMA. We discuss some challenges and future opportunities in sleep disruption detection.

In recent years, new treatments have become available which have improved survival rates in lung cancer patients. One promising treatment option is the rapidly growing field of oral targeted therapies, which employs drugs that interfere with specific molecules involved in the growth, progression, and spread of cancer. However, these therapies can cause a variety of symptoms and adverse events that can impair quality of life. mHealth technologies may help individuals with lung cancer better track their side effects and manage medications on a day-to-day basis. However, understanding patients’ attitudes toward smart devices such as smartphones, smartwatches, and smart pill bottles, as well as their specific needs when using these devices, is critical before design and deployment studies of medication adherence can be carried out. In this study, we conducted interviews with 9 individuals with stage III-IV lung cancer at a National Cancer Institute-designated comprehensive cancer center in the Mid-Atlantic region of the United States to assess the feasibility of using such devices for managing medication and medication related side-effects. We evaluated patients’ attitudes towards the design and function of smart devices and how these devices fit into their daily life. Our results may help clinicians and researchers to co-develop effective mHealth system deployments for side effect and medication management in oncology populations.

Self-esteem encompasses how individuals evaluate themselves and is an important contributor to their success. Self-esteem has been traditionally measured using survey-based methodologies. However, surveys suffer from limitations such as retrospective recall and reporting biases, leading to a need for proactive measurement approaches. Our work uses smartphone sensors to predict self-esteem and is situated in a multimodal sensing study on college students for five weeks. We use theory-driven features, such as phone communications and physical activity to predict three dimensions, performance, social, and appearance self-esteem. We conduct statistical modeling including linear, ensemble, and neural network regression to measure self-esteem. Our best model predicts self-esteem with a high correlation (r) of 0.60 and low SMAPE of 7.26% indicating high predictive accuracy. We inspect the top features finding theoretical alignment; for example, social interaction significantly contributes to performance and appearance-based self-esteem, whereas, and physical activity is the most significant contributor towards social self-esteem. Our work reveals the efficacy of passive sensors for predicting self-esteem, and we situate our observations with literature and discuss the implications of our work for tailored interventions and improving wellbeing.

Hearing aids help overcome the challenges associated with hearing loss, and thus greatly benefit and improve the lives of those living with hearing-impairment. Unfortunately, there is a lack of adoption of hearing aids among those that can benefit from hearing aids. Hearing researchers and audiologists are trying to address this problem through their research. However, the current proprietary hearing aid market makes it difficult for academic researchers to translate their findings into commercial use. In order to abridge this gap and accelerate research in hearing health care, we present the design and implementation of the Open Speech Platform (OSP), which consists of a co-design of open-source hardware and software. The hardware meets the industry standards and enables researchers to conduct experiments in the field. The software is designed with a systematic and modular approach to standardize algorithm implementation and simplify user interface development. We evaluate the performance of OSP regarding both its hardware and software, as well as demonstrate its usefulness via a self-fitting study involving human participants.

Digital psychiatry is a rapidly growing area of research. Mobile assessment, including passive sensing, could improve research into human behavior and may afford opportunities for rapid treatment delivery. However, retention is poor in remote studies of depressed populations in which frequent assessment and passive monitoring are required. To improve engagement and understanding participant needs overall, we conducted semi-structured interviews with 20 people representative of a depressed population in a major metropolitan area. These interviews elicited feedback on strategies for long-term remote research engagement and attitudes towards passive data collection. Our results found participants were uncomfortable sharing vocal samples, need researchers to take a more active role in supporting their understanding of passive data collection, and wanted more transparency on how data were to be used in research. Despite these findings, participants trusted researchers with the collection of passive data. They further indicated that long term study retention could be improved with feedback and return of information based on the collected data. We suggest that researchers consider a more educational consent process, giving participants a choice about the types of data they share in the design of digital health apps, and consider supporting feedback in the design to improve engagement.

Mobile mental health interventions have the potential to reduce barriers and increase engagement in psychotherapy. However, most current tools fail to meet evidence-based principles. In this paper, we describe data-driven design implications for translating evidence-based interventions into mobile apps. To develop these design implications, we analyzed data from a month-long field study of an app designed to support dialectical behavioral therapy, a psychotherapy that aims to teach concrete coping skills to help people better manage their mental health. We investigated whether particular skills are more or less effective in reducing distress or emotional intensity. We also characterized how an individual's disorders, characteristics, and preferences may correlate with skill effectiveness, as well as how skill-level improvements correlate with study-wide changes in depressive symptoms. We then developed a model to predict skill effectiveness. Based on our findings, we present design implications that emphasize the importance of considering different environmental, emotional, and personal contexts. Finally, we discuss promising future opportunities for mobile apps to better support evidence-based psychotherapies, including using machine learning algorithms to develop personalized and context-aware skill recommendations.

This paper introduces a system with persuasive communication to improve the diet compliance and adherence of participants of the PROMISS-project. For this persuasive communication different strategies and ways of personalisation are used, in accordance with existing literature. Furthermore, as the target group is elderly users, the design is tailored to their specific needs. A first prototype was created, based on seven functional requirements. During a pilot study, the prototype is evaluated with seven participants. Based on lessons learned during this pilot, as well as new requirements from the PROMISS dietitians, a refined design of the system was implemented. This refined design is briefly evaluated with four participants of the pilot during individual interviews. The changes made to the prototype were evaluated positively.

It is crucial for patients facing complex medical treatment to understand possible treatment outcomes, but this is difficult to achieve in practice due to the nature of stressful situations. This study explores how Bone Marrow Transplant (BMT) patients and providers perceive graphical representations of outcome-related information as a first step toward developing a secure patient portal to support the information needs of patients facing BMT. To inform system design, we conducted interviews with 10 veteran BMT patients and a focus group with 7 providers about our prototypes. We found that patients perceived the proposed tool as sense-making support to better comprehend and prepare for the complexities and emotional challenges relating to treatment rather than decision support, whereas providers attended to the tool's functionality in supporting decision-making. Findings revealed insights for personalized sense-making support regarding representations of numeric data and the navigation of experience-videos of veteran patients describing outcomes. Drawing on these, we discuss implications and suggest directions for future work.

Mobile sensing technology allows us to investigate human behaviour on a daily basis. In the study, we examined temporal orientation, which refers to the capacity of thinking or talking about personal events in the past and future. We utilise the mk-sense platform that allows us to use the experience-sampling method. Individual's thoughts and their relationship with smartphone's Bluetooth data is analysed to understand in which contexts people are influenced by social environments, such as the people they spend the most time with. As an exploratory study, we analyse social condition influence through a collection of Bluetooth data and survey information from participant's smartphones. Preliminary results show that people are likely to focus on past events when interacting with close-related people, and focus on future planning when interacting with strangers. Similarly, people experience present temporal orientation when accompanied by known people. We believe that these findings are linked to emotions since, in its most basic state, emotion is a state of physiological arousal combined with an appropriated cognition. In this contribution, we envision a smartphone application for automatically inferring human emotions based on user's temporal orientation by using Bluetooth sensors, we briefly elaborate on the influential factor of temporal orientation episodes and conclude with a discussion and lessons learned.

Recall assistance methods are among the key aspects that improve the accuracy of online dietary assessment surveys. These methods still mainly rely on experience of trained interviewers with nutritional background, but data driven approaches could improve cost-efficiency and scalability of automated dietary assessment. We evaluated the effectiveness of a recommender algorithm developed for an online dietary assessment system called Intake24, that automates the multiple-pass 24-hour recall method. The recommender builds a model of eating behavior from recalls collected in past surveys. Based on foods they have already selected, the model is used to remind respondents of associated foods that they may have omitted to report. The performance of prompts generated by the model was compared to that of prompts hand-coded by nutritionists in two dietary studies. The results of our studies demonstrate that the recommender system is able to capture a higher number of foods omitted by respondents of online dietary surveys than prompts hand-coded by nutritionists. However, the considerably lower precision of generated prompts indicates an opportunity for further improvement of the system.

Digital phenotyping is a novel approach to refer to moment-by-moment quantification of the individual-level social, physical, cognitive, emotional and behavioral phenotype in situ, using data from personal digital devices. This concept, understood as a tool to retrieve data on the users' state, including information about their own perception on their health, is unveiling as a powerful instrument to better understand patients with mental disorders for scientific and clinical goals, but also to provide personalized coaching and support that may facilitate disease detection, monitoring and treatment. In this paper, we review previous works on digital phenotyping for mental health care, through a framework that facilitates the description of relevant studies. We propose a general architecture for digital phenotyping platforms from the main key functionalities that have been identified and analyze the main barriers and needs to be overcome to exploit data in a patient-centric way. In particular, there is a requirement for extensive user validation, as existing studies are still very preliminary and, as a consequence, it is also key to explore the integration of digital phenotyping mhealth solutions as cornerstone tools for integrated care delivery.

Chronic respiratory conditions (CRCs) are life-long diseases affecting millions of people worldwide. They have a huge impact on individuals' everyday lives, resulting in a number of physical and emotional challenges. Self-management interventions for CRCs are thought to provide empowerment and improve quality of life. However, despite the number of people living with CRCs, most self-management tools in previous HCI work have been designed without the insight of those affected by the conditions.In this paper, we contribute to the literature by investigating the experiences and everyday challenges faced by those with CRCs, through the involvement of 156 participants via interviews and an anonymous survey. Our findings reveal the self-care challenges of CRCs and the reactive management approaches taken by participants. We conclude by providing a set of design implications that support the design of future self-management tools for CRCs.

Continuous measurement of physiological functions, like heart rate (HR) and heart rate variability (HRV), using commercially available wearable sensors provides the prospects of improving the healthcare of individuals with a positive impact on society, bringing pervasiveness, lower cost, and broader access. However, common wearable devices use photoplethysmography (PPG) to derive data on HR and HRV, and it is yet unclear to which extent PPG signals can be used as a proxy for data collected using medical-grade devices. To address this challenge, we consider five consumer devices to assess the signal quality of HR and two devices measuring HRV and compare them with a standard electrocardiography (ECG) Holter monitor. We collect data from fourteen participants who followed a 55 minutes protocol for at least two sessions. Using this data set, which we make publicly available to the research community, we show that PPG is a valid proxy for both HR and standard time-and frequency-domain measurements of HRV. Further, we demonstrate that wearable devices are suitable for monitoring both HR and HRV in daily life but might be limited during strenuous exercise. The study indicates that armband-based devices are more reliable than wrist-based wearables for HRV assessment.

The understanding of alcohol consumption patterns, especially those indicating negative drinking behavior, is an important issue to researchers and health policymakers. On social media, people share daily activities, including alcohol consumption, representing these moments through images and text. This work, using a five-year dataset from Instagram, analyzes what machine-extracted textual and visual cues reveal about trends of casual drinking (concepts gathered around #drink) and possible negative drinking (concepts gathered around #drunk). Our analysis reveals that #drunk posts occur more frequently in party occasions and nightlife locations, with a higher presence of people, while #drink posts occur at food locations, with a higher presence of drink containers. Manual coding further shows that #drunk posts have a higher chance of being perceived as potentially objectionable. A random forest classifier shows that #drink and #drunk posts can be discriminated with accuracy up to 82.3%. These results have important implications for alcohol research among youth.

Recent attention has been given to the role of emotion regulation in promoting well-being. Although various approaches have been established to design for emotion in design research and HCI, there is only little knowledge on how to support the process of regulating user emotions through design. The paper introduces a framework that delineates 17 emotion regulation strategies based on the theories of emotion regulation. The framework supports an understanding of emotion regulation strategies by enabling designers to compare differences and overlaps of the strategies. The paper describes the framework and its development process along with design examples. Implications and future research steps are discussed.

Modern machine learning techniques enable new possibilities for the analysis of psychological data. In the field of health psychology, it is of interest to explore the biological processes triggered by acute stress. This work introduces a method to automatically classify individuals into distinct stress responder groups based on these biological processes. Two important stress-sensitive markers were used: Salivary cortisol and Interleukin-6 (IL-6) in blood plasma. Controlled stress was induced using the Trier Social Stress Test on two consecutive days. Results show that Support Vector Machines performed best on the given dataset. We distinguished four different cortisol and three different IL-6 responder types with high mean accuracies (92.2 % ± 9.7 % and 91.2 % ± 6.3 %, respectively). Classification results were mainly limited by class imbalances and high intra-class standard deviations. Whereas promising as a first application of machine learning on such datasets, generalizability and real-world applicability of our results need to be proven by further research.

In this paper we address the problem of multimodal car driver stress recognition. To this aim, four different signals are considered: heart rate (HR), breathing rate (BR), palm EDA (P-EDA), and perinasal perspitation (PER-EDA). The raw signals are windowed and for each window 21 different features, including both time-domain and frequency-domain descriptors, are extracted. The recognition problem is formulated as a stress vs no-stress binary problem, and is addressed in two different experimental setups: five-fold cross validation and leave one subject out. In both setups the extracted features are classified, both individually and concatenated, with three different classifiers (k-NN, SVM, and ANN) using them both alone and stacking their predictions. Experiments run on a publicly available database of multimodal signals acquired in a controlled experiment on a driving simulator show that the best recognition results are obtained feeding the classifiers with the concatenation of the features of all the signals considered, reaching a micro average accuracy of 77.25% and 65.09% in the two experimental setups respectively.

Mental disorders are a major public health issue and have a strong impact on the people affected by these disabilities. A considerable number of eHealth applications are readily available on a wide range of health topics, and they are becoming increasingly important components of general medical care models, as well as in the treatment of mental illness. However, there is a lack of appropriate design recommendations regarding applications for people with mental disorders. For them, usability can be greatly improved by developing designs that meet their needs, such as low cognitive effort. The aim of this study is to develop an understanding of the usability aspects that influence the ability of people with mental disorders. For this purpose, this article includes a systematic literature review with regard to usability errors and design recommendations of eHealth applications in the field of mental illness. Based on this review, the results are grouped according the PACMAD model and then analyzed and discussed.

The ubiquity of wearable fitness trackers offers extensive opportunities for research on personal health. However, barriers specific to these trackers such as device abandonment and non-adherence often lead to substantial losses in data. As such, further research into adherence behaviors may derive the insights necessary to address these challenges and lead to more effective long-term studies. This paper serves to explore this approach: investigating the adherence behaviors of 617 college students belonging to a three-year observational study in which participants were monitored via Fitbit Charge HRs. Using this data, our objective was to assess the association between early adherence behaviors and device abandonment/long-term adherence. Adherence behavior from as early as participants' first 10 days in the study correlated with device abandonment and adherence over the next three years. Participants with unsatisfactory adherence in their first 30 days were twice as likely to abandon their devices and were, on average, 11% less adherent each month. The findings in this paper identify the stability of adherence behaviors, feasibility of their early detection and motivate the need to address non-adherent study participants early. Throughout these results, we discuss how the insights gathered from this work may shape the design of future long-term studies to minimize user attrition and promote prolonged engagement.