Sensing Apps and Public Data Sets for Digital Phenotyping of Mental Health: Systematic Review

Old strategies, new environments: Reinforcement Learning on social media

The rise of social media has profoundly altered the social world - introducing new behaviours which can satisfy our social needs. However, it is yet unknown whether human social strategies, which are well-adapted to the offline world we developed in, operate as effectively within this new social environment. Here, we describe how the computational framework of Reinforcement Learning can help us to precisely frame this problem and diagnose where behaviour-environment mismatches emerge. The Reinforcement Learning framework describes a process by which an agent can learn to maximise their long-term reward. Reinforcement Learning, which has proven successful in characterising human social behaviour, consists of three stages: updating expected reward, valuating expected reward by integrating subjective costs such as effort, and selecting an action. Specific social media affordances, such as the quantifiability of social feedback, might interact with the Reinforcement Learning process at each of these stages. In some cases, affordances can exploit Reinforcement Learning biases which are beneficial offline, by violating the environmental conditions under which such biases are optimal - such as when algorithmic personalisation of content interacts with confirmation bias. Characterising the impact of specific aspects of social media through this lens can improve our understanding of how digital environments shape human behaviour. Ultimately, this formal framework could help address pressing open questions about social media use, including its changing role across human development, and its impact on outcomes such as mental health.

Advances in biosensors for major depressive disorder diagnostic biomarkers

Depression is one of the most common mental disorders and is mainly characterized by low mood or lack of interest and pleasure. It can be accompanied by varying degrees of cognitive and behavioral changes and may lead to suicide risk in severe cases. Due to the subjectivity of diagnostic methods and the complexity of patients' conditions, the diagnosis of major depressive disorder (MDD) has always been a difficult problem in psychiatry. With the discovery of more diagnostic biomarkers associated with MDD in recent years, especially emerging non-coding RNAs (ncRNAs), it is possible to quantify the condition of patients with mental illness based on biomarker levels. Point-of-care biosensors have emerged due to their advantages of convenient sampling, rapid detection, miniaturization, and portability. After summarizing the pathogenesis of MDD, representative biomarkers, including proteins, hormones, and RNAs, are discussed. Furthermore, we analyzed recent advances in biosensors for detecting various types of biomarkers of MDD, highlighting representative electrochemical sensors. Future trends in terms of new biomarkers, new sample processing methods, and new detection modalities are expected to provide a complete reference for psychiatrists and biomedical engineers.

Depressive symptom screening in elderly by passive sensing data of smartphones or smartwatches: A systematic review

BACKGROUND

The elderly is commonly susceptible to depression, the symptoms for which may overlap with natural aging or other illnesses, and therefore miss being captured by routine screening questionnaires. Passive sensing data have been promoted as a tool for depressive symptoms detection though there is still limited evidence on its usage in the elderly. Therefore, this study aims to review current knowledge on the use of passive sensing data via smartphones and smartwatches in depressive symptom screening for the elderly.

METHOD

The search of literature was performed in PubMed, IEEE Xplore digital library, and PsycINFO. Literature investigating the use of passive sensing data to screen, monitor, and/or predict depressive symptoms in the elderly (aged 60 and above) via smartphones and/or wrist-worn wearables was included for initial screening. Studies in English from international journals published between January 2012 to September 2022 were included. The reviewed studies were further analyzed by a narrative analysis.

RESULTS

The majority of 21 included studies were conducted in Western countries with a few in Asia and Australia. Most studies adopted a cohort study design (n = 12), followed by cross-sectional design (n = 7) and a case-control design (n = 2). The most popular passive sensing data was related to sleep and physical activity using an actigraphy. Sleep characteristics, such as prolonged wakefulness after sleep onset, along with lower levels of physical activity, exhibited a significant association with depression. However, cohort studies expressed concerns regarding data quality stemming from incomplete follow-up and potential confounding effects.

CONCLUSION

Passive sensing data, such as sleep, and physical activity parameters should be promoted for depressive symptoms detection. However, the validity, reliability, feasibility, and privacy concerns still need further exploration.

Predicting daily cognition and lifestyle behaviors for older adults using smart home data and ecological momentary assessment

OBJECTIVE

Extraction of digital markers from passive sensors placed in homes is a promising method for understanding real-world behaviors. In this study, machine learning (ML) and multilevel modeling (MLM) are used to examine types of digital markers and whether smart home sensors can predict cognitive functioning, lifestyle behaviors, and contextual factors measured through ecological momentary assessment (EMA).

METHOD

Smart home sensors were installed in the homes of 44 community-dwelling midlife and older adults for 3-4 months. Sensor data were categorized into eight digital markers. Participants responded to iPad-delivered EMA prompts 4×/day for 2 wk. Prompts included an n-back task and survey on recent (past 2 h) lifestyle and contextual factors.

RESULTS

ML marker rankings revealed that sensor counts (indicating increased activity) and time outside the home were among the most influential markers for all survey questions. Additionally, MLM revealed for every 1000 sensor counts, mental sharpness, social, physical, and cognitive EMA responses increased by 0.134-0.155 points on a 5-point scale. For every additional 30-minutes spent outside home, social, physical, and cognitive EMA responses increased by 0.596, 0.472, and 0.157 points. Advanced ML joint classification/regression significantly predicted EMA responses from smart home digital markers with error of 0.370 on a 5-point scale, and n-back performance with a normalized error of 0.040.

CONCLUSION

Results from ML and MLM were complimentary and comparable, suggesting that machine learning may be used to develop generalized models to predict everyday cognition and track lifestyle behaviors and contextual factors that impact health outcomes using smart home sensor data.

[Digital technologies to improve mental health]

The burden of mental diseases is enormous and constantly growing worldwide. The resulting increase in demand for psychosocial help is also having a negative impact on waiting times for psychotherapy in Germany. Digital interventions for mental health, such as interventions delivered through or with the help of a website (e.g. "telehealth"), smartphone, or tablet app-based interventions and interventions that use text messages or virtual reality, can help. This article begins with an overview of the functions and range of applications of digital technologies for mental health. The evidence for individual digital forms of interventions is addressed. Overall, it is shown that digital interventions for mental health are likely to be cost-effective compared to no therapy or a non-therapeutic control group. Newer approaches such as "digital phenotyping" are explained in the article. Finally, individual papers from the "Leibniz ScienceCampus Digital Public Health" are presented, and limitations and challenges of technologies for mental health are discussed.

What digital health technology types are used in mental health prevention and intervention? Review of systematic reviews for systematization of technologies

Digital health technology has been widely applied to mental health interventions worldwide. Using digital phenotyping to identify an individual's mental health status has become particularly important. However, many technologies other than digital phenotyping are expected to become more prevalent in the future. The systematization of these technologies is necessary to accurately identify trends in mental health interventions. However, no consensus on the technical classification of digital health technologies for mental health interventions has emerged. Thus, we conducted a review of systematic review articles on the application of digital health technologies in mental health while attempting to systematize the technology using the Delphi method. To identify technologies used in digital phenotyping and other digital technologies, we included 4 systematic review articles that met the inclusion criteria, and an additional 8 review articles, using a snowballing approach, were incorporated into the comprehensive review. Based on the review results, experts from various disciplines participated in the Delphi process and agreed on the following 11 technical categories for mental health interventions: heart rate estimation, exercise or physical activity, sleep estimation, contactless heart rate/pulse wave estimation, voice and emotion analysis, self-care/cognitive behavioral therapy/mindfulness, dietary management, psychological safety, communication robots, avatar/metaverse devices, and brain wave devices. The categories we defined intentionally included technologies that are expected to become widely used in the future. Therefore, we believe these 11 categories are socially implementable and useful for mental health interventions.

Remote sensing mental health: A systematic review of factors essential to clinical translation from validation research

Background

Mental illness remains a major global health challenge largely due to the absence of definitive biomarkers applicable to diagnostics and care processes. Although remote sensing technologies, embedded in devices such as smartphones and wearables, offer a promising avenue for improved mental health assessments, their clinical integration has been slow.

Objective

This scoping review, following preferred reporting items for systematic reviews and meta-analyses guidelines, explores validation studies of remote sensing in clinical mental health populations, aiming to identify critical factors for clinical translation.

Methods

Comprehensive searches were conducted in six databases. The analysis, using narrative synthesis, examined clinical and socio-demographic characteristics of the populations studied, sensing purposes, temporal considerations and reference mental health assessments used for validation.

Results

The narrative synthesis of 50 included studies indicates that ten different sensor types have been studied for tracking and diagnosing mental illnesses, primarily focusing on physical activity and sleep patterns. There were many variations in the sensor methodologies used that may affect data quality and participant burden. Observation durations, and thus data resolution, varied by patient diagnosis. Currently, reference assessments predominantly rely on deficit focussed self-reports, and socio-demographic information is underreported, therefore representativeness of the general population is uncertain.

Conclusion

To fully harness the potential of remote sensing in mental health, issues such as reliance on self-reported assessments, and lack of socio-demographic context pertaining to generalizability need to be addressed. Striking a balance between resolution, data quality, and participant burden whilst clearly reporting limitations, will ensure effective technology use. The scant reporting on participants' socio-demographic data suggests a knowledge gap in understanding the effectiveness of passive sensing techniques in disadvantaged populations.

Digital Phenotyping: Data-Driven Psychiatry to Redefine Mental Health

The term "digital phenotype" refers to the digital footprint left by patient-environment interactions. It has potential for both research and clinical applications but challenges our conception of health care by opposing 2 distinct approaches to medicine: one centered on illness with the aim of classifying and curing disease, and the other centered on patients, their personal distress, and their lived experiences. In the context of mental health and psychiatry, the potential benefits of digital phenotyping include creating new avenues for treatment and enabling patients to take control of their own well-being. However, this comes at the cost of sacrificing the fundamental human element of psychotherapy, which is crucial to addressing patients' distress. In this viewpoint paper, we discuss the advances rendered possible by digital phenotyping and highlight the risk that this technology may pose by partially excluding health care professionals from the diagnosis and therapeutic process, thereby foregoing an essential dimension of care. We conclude by setting out concrete recommendations on how to improve current digital phenotyping technology so that it can be harnessed to redefine mental health by empowering patients without alienating them.

The Use of Mobile Assessments for Monitoring Mental Health in Youth: Umbrella Review

BACKGROUND

Improving mental health in youth is a major concern. Future approaches to monitor and intervene in youth mental health problems should rely on mobile tools that allow for the daily monitoring of mental health both actively (eg, using ecological momentary assessments [EMAs]) and passively (eg, digital phenotyping) by capturing individuals' data.

OBJECTIVE

This umbrella review aims to (1) report the main characteristics of existing reviews on mental health and young people, including mobile approaches to mental health; (2) describe EMAs and trace data and the mental health conditions investigated; (3) report the main results; and (4) outline promises, limitations, and directions for future research.

METHODS

A systematic literature search was carried out in 9 scientific databases (Communication & Mass Media Complete, Psychology and Behavioral Sciences Collection, PsycINFO, CINAHL, ERIC, MEDLINE, the ProQuest Sociology Database, Web of Science, and PubMed) on January 30, 2022, coupled with a hand search and updated in July 2022. We included (systematic) reviews of EMAs and trace data in the context of mental health, with a specific focus on young populations, including children, adolescents, and young adults. The quality of the included reviews was evaluated using the AMSTAR (Assessment of Multiple Systematic Reviews) checklist.

RESULTS

After the screening process, 30 reviews (published between 2016 and 2022) were included in this umbrella review, of which 21 (70%) were systematic reviews and 9 (30%) were narrative reviews. The included systematic reviews focused on symptoms of depression (5/21, 24%); bipolar disorders, schizophrenia, or psychosis (6/21, 29%); general ill-being (5/21, 24%); cognitive abilities (2/21, 9.5%); well-being (1/21, 5%); personality (1/21, 5%); and suicidal thoughts (1/21, 5%). Of the 21 systematic reviews, 15 (71%) summarized studies that used mobile apps for tracing, 2 (10%) summarized studies that used them for intervention, and 4 (19%) summarized studies that used them for both intervention and tracing. Mobile tools used in the systematic reviews were smartphones only (8/21, 38%), smartphones and wearable devices (6/21, 29%), and smartphones with other tools (7/21, 33%). In total, 29% (6/21) of the systematic reviews focused on EMAs, including ecological momentary interventions; 33% (7/21) focused on trace data; and 38% (8/21) focused on both. Narrative reviews mainly focused on the discussion of issues related to digital phenotyping, existing theoretical frameworks used, new opportunities, and practical examples.

CONCLUSIONS

EMAs and trace data in the context of mental health assessments and interventions are promising tools. Opportunities (eg, using mobile approaches in low- and middle-income countries, integration of multimodal data, and improving self-efficacy and self-awareness on mental health) and limitations (eg, absence of theoretical frameworks, difficulty in assessing the reliability and effectiveness of such approaches, and need to appropriately assess the quality of the studies) were further discussed.

TRIAL REGISTRATION

PROSPERO CRD42022347717; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=347717.

Machine Learning and the Digital Measurement of Psychological Health

Since its inception, the discipline of psychology has utilized empirical epistemology and mathematical methodologies to infer psychological functioning from direct observation. As new challenges and technological opportunities emerge, scientists are once again challenged to define measurement paradigms for psychological health and illness that solve novel problems and capitalize on new technological opportunities. In this review, we discuss the theoretical foundations of and scientific advances in remote sensor technology and machine learning models as they are applied to quantify psychological functioning, draw clinical inferences, and chart new directions in treatment.

Clinician perspectives on how digital phenotyping can inform client treatment

This qualitative study explores mental health clinician perspectives on how information extracted from client interactions with digital devices such as smartphones and the Internet (their digital footprint data) can inform client treatment. The process of learning about an individual's behaviours and psychology from their digital footprint, what has been termed 'digital phenotyping', has emerged in recent years as a field of research with potential to offer insights of clinical value that could be used to predict/detect mental ill-health and inform treatment. This research agenda has largely consisted of quantitative studies exploring statistical associations between smartphone data and psychometric outcomes among relatively small participant cohorts. We on the other hand focus on how the data gathered from smartphones and other digital sources could be converted to pieces of meaningful information that clinicians could directly access and interpret to augment their practice and inform their treatment of clients. Through a reflexive thematic analysis of interviews involving clinical psychologists, this study presents ideas and a framework for understanding how digital phenotyping can inform, augment, and innovate client treatment. In total, five themes concerning the ethics, praxis, and value of digital phenotyping for client treatment are generated.

Modeling social interaction dynamics measured with smartphone sensors: An ambulatory assessment study on social interactions and loneliness

More and more data are being collected using combined active (e.g., surveys) and passive (e.g., smartphone sensors) ambulatory assessment methods. Fine-grained temporal data, such as smartphone sensor data, allow gaining new insights into the dynamics of social interactions in day-to-day life and how these are associated with psychosocial phenomena - such as loneliness. So far, however, smartphone sensor data have often been aggregated over time, thus, not doing justice to the fine-grained temporality of these data. In this article, we demonstrate how time-stamped sensor data of social interactions can be modeled with multistate survival models. We examine how loneliness is associated with (a) the time between social interaction (i.e., interaction rate) and (b) the duration of social interactions in a student population (N_participants = 45, N_observations = 74,645). Before a 10-week ambulatory assessment phase, participants completed the UCLA loneliness scale, covering subscales on intimate, relational, and collective loneliness. Results from the multistate survival models indicated that loneliness subscales were not significantly associated with differences in social interaction rate and duration - only relational loneliness predicted shorter social interaction encounters. These findings illustrate how the combination of new measurement and modeling methods can advance knowledge on social interaction dynamics in daily life settings and how they relate to psychosocial phenomena such as loneliness.

Digital Phenotyping of Mental Health using multimodal sensing of multiple situations of interest: A Systematic Literature Review

Many studies have used Digital Phenotyping of Mental Health (DPMH) to complement classic methods of mental health assessment and monitoring. This research area proposes innovative methods that perform multimodal sensing of multiple situations of interest (e.g., sleep, physical activity, mobility) to health professionals. In this paper, we present a Systematic Literature Review (SLR) to recognize, characterize and analyze the state of the art on DPMH using multimodal sensing of multiple situations of interest to professionals. We searched for studies in six digital libraries, which resulted in 1865 retrieved published papers. Next, we performed a systematic process of selecting studies based on inclusion and exclusion criteria, which selected 59 studies for the data extraction phase. First, based on the analysis of the extracted data, we describe an overview of this field, then presenting characteristics of the selected studies, the main mental health topics targeted, the physical and virtual sensors used, and the identified situations of interest. Next, we outline answers to research questions, describing the context data sources used to detect situations, the DPMH workflow used for multimodal sensing of situations, and the application of DPMH solutions in the mental health assessment and monitoring process. In addition, we recognize trends presented by DPMH studies, such as the design of solutions for high-level information recognition, association of features with mental states/disorders, classification of mental states/disorders, and prediction of mental states/disorders. We also recognize the main open issues in this research area. Based on the results of this SLR, we conclude that despite the potential and continuous evolution for using these solutions as medical decision support tools, this research area needs more work to overcome technology and methodological rigor issues to adopt proposed solutions in real clinical settings.

Taking modern psychiatry into the metaverse: Integrating augmented, virtual, and mixed reality technologies into psychiatric care

The landscape of psychiatry is ever evolving and has recently begun to be influenced more heavily by new technologies. One novel technology which may have particular application to psychiatry is the metaverse, a three-dimensional digital social platform accessed via augmented, virtual, and mixed reality (AR/VR/MR). The metaverse allows the interaction of users in a virtual world which can be measured and manipulated, posing at once exciting new possibilities and significant potential challenges and risks. While the final form of the nascent metaverse is not yet clear, the immersive simulation and holographic mixed reality-based worlds made possible by the metaverse have the potential to redefine neuropsychiatric care for both patients and their providers. While a number of applications for this technology can be envisioned, this article will focus on leveraging the metaverse in three specific domains: medical education, brain stimulation, and biofeedback. Within medical education, the metaverse could allow for more precise feedback to students performing patient interviews as well as the ability to more easily disseminate highly specialized technical skills, such as those used in advanced neurostimulation paradigms. Examples of potential applications in brain stimulation and biofeedback range from using AR to improve precision targeting of non-invasive neuromodulation modalities to more innovative practices, such as using physiological and behavioral measures derived from interactions in VR environments to directly inform and personalize treatment parameters for patients. Along with promising future applications, we also discuss ethical implications and data security concerns that arise when considering the introduction of the metaverse and related AR/VR technologies to psychiatric research and care.

Ubiquitous computing in light of human phenotypes: foundations, challenges, and opportunities

The interest in human phenotypes has leveraged interdisciplinary efforts encouraging a better understanding of the broad spectrum of psychological and behavioral disorders. Moreover, the usage of mobile and wearable devices along with unobtrusive computational capabilities provides an extensive amount of information that allows the characterization of phenotypes. This article describes the human phenotype through the lens of computational range and reviews state-of-the-art computational phenotyping. Furthermore, the article discusses computational phenotyping's extension concerning the combination of intelligent environments and personal mobile devices, addressing technical, managerial, and ethical challenges. This combination reinforces ubiquitous computational capabilities for phenotyping as a facilitator of interdisciplinary information convergence in favor of clinical and biomedical research.

Modern views of machine learning for precision psychiatry

In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

A Machine Learning Approach for Continuous Mining of Nonidentifiable Smartphone Data to Create a Novel Digital Biomarker Detecting Generalized Anxiety Disorder: Prospective Cohort Study

BACKGROUND

Anxiety is one of the leading causes of mental health disability around the world. Currently, a majority of the population who experience anxiety go undiagnosed or untreated. New and innovative ways of diagnosing and monitoring anxiety have emerged using smartphone sensor-based monitoring as a metric for the management of anxiety. This is a novel study as it adds to the field of research through the use of nonidentifiable smartphone usage to help detect and monitor anxiety remotely and in a continuous and passive manner.

OBJECTIVE

This study aims to evaluate the accuracy of a novel mental behavioral profiling metric derived from smartphone usage for the identification and tracking of generalized anxiety disorder (GAD).

METHODS

Smartphone data and self-reported 7-item GAD anxiety assessments were collected from 229 participants using an Android operating system smartphone in an observational study over an average of 14 days (SD 29.8). A total of 34 features were mined to be constructed as a potential digital phenotyping marker from continuous smartphone usage data. We further analyzed the correlation of these digital behavioral markers against each item of the 7-item Generalized Anxiety Disorder Scale (GAD-7) and its influence on the predictions of machine learning algorithms.

RESULTS

A total of 229 participants were recruited in this study who had completed the GAD-7 assessment and had at least one set of passive digital data collected within a 24-hour period. The mean GAD-7 score was 11.8 (SD 5.7). Regression modeling was tested against classification modeling and the highest prediction accuracy was achieved from a binary XGBoost classification model (precision of 73%-81%; recall of 68%-87%; F₁-score of 71%-79%; accuracy of 76%; area under the curve of 80%). Nonparametric permutation testing with Pearson correlation results indicated that the proposed metric (Mental Health Similarity Score [MHSS]) had a colinear relationship between GAD-7 Items 1, 3 and 7.

CONCLUSIONS

The proposed MHSS metric demonstrates the feasibility of using passively collected nonintrusive smartphone data and machine learning-based data mining techniques to track an individuals' daily anxiety levels with a 76% accuracy that directly relates to the GAD-7 scale.

Digital Phenotyping in Health Using Machine Learning Approaches: Scoping Review

BACKGROUND

Digital phenotyping is the real-time collection of individual-level active and passive data from users in naturalistic and free-living settings via personal digital devices, such as mobile phones and wearable devices. Given the novelty of research in this field, there is heterogeneity in the clinical use cases, types of data collected, modes of data collection, data analysis methods, and outcomes measured.

OBJECTIVE

The primary aim of this scoping review was to map the published research on digital phenotyping and to outline study characteristics, data collection and analysis methods, machine learning approaches, and future implications.

METHODS

We utilized an a priori approach for the literature search and data extraction and charting process, guided by the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-analyses Extension for Scoping Reviews). We identified relevant studies published in 2020, 2021, and 2022 on PubMed and Google Scholar using search terms related to digital phenotyping. The titles, abstracts, and keywords were screened during the first stage of the screening process, and the second stage involved screening the full texts of the shortlisted articles. We extracted and charted the descriptive characteristics of the final studies, which were countries of origin, study design, clinical areas, active and/or passive data collected, modes of data collection, data analysis approaches, and limitations.

RESULTS

A total of 454 articles on PubMed and Google Scholar were identified through search terms associated with digital phenotyping, and 46 articles were deemed eligible for inclusion in this scoping review. Most studies evaluated wearable data and originated from North America. The most dominant study design was observational, followed by randomized trials, and most studies focused on psychiatric disorders, mental health disorders, and neurological diseases. A total of 7 studies used machine learning approaches for data analysis, with random forest, logistic regression, and support vector machines being the most common.

CONCLUSIONS

Our review provides foundational as well as application-oriented approaches toward digital phenotyping in health. Future work should focus on more prospective, longitudinal studies that include larger data sets from diverse populations, address privacy and ethical concerns around data collection from consumer technologies, and build "digital phenotypes" to personalize digital health interventions and treatment plans.

Opportunities for Smartphone Sensing in E-Health Research: A Narrative Review

Recent years have seen significant advances in the sensing capabilities of smartphones, enabling them to collect rich contextual information such as location, device usage, and human activity at a given point in time. Combined with widespread user adoption and the ability to gather user data remotely, smartphone-based sensing has become an appealing choice for health research. Numerous studies over the years have demonstrated the promise of using smartphone-based sensing to monitor a range of health conditions, particularly mental health conditions. However, as research is progressing to develop the predictive capabilities of smartphones, it becomes even more crucial to fully understand the capabilities and limitations of using this technology, given its potential impact on human health. To this end, this paper presents a narrative review of smartphone-sensing literature from the past 5 years, to highlight the opportunities and challenges of this approach in healthcare. It provides an overview of the type of health conditions studied, the types of data collected, tools used, and the challenges encountered in using smartphones for healthcare studies, which aims to serve as a guide for researchers wishing to embark on similar research in the future. Our findings highlight the predominance of mental health studies, discuss the opportunities of using standardized sensing approaches and machine-learning advancements, and present the trends of smartphone sensing in healthcare over the years.

Boamente: A Natural Language Processing-Based Digital Phenotyping Tool for Smart Monitoring of Suicidal Ideation

People at risk of suicide tend to be isolated and cannot share their thoughts. For this reason, suicidal ideation monitoring becomes a hard task. Therefore, people at risk of suicide need to be monitored in a manner capable of identifying if and when they have a suicidal ideation, enabling professionals to perform timely interventions. This study aimed to develop the Boamente tool, a solution that collects textual data from users’ smartphones and identifies the existence of suicidal ideation. The solution has a virtual keyboard mobile application that passively collects user texts and sends them to a web platform to be processed. The platform classifies texts using natural language processing and a deep learning model to recognize suicidal ideation, and the results are presented to mental health professionals in dashboards. Text classification for sentiment analysis was implemented with different machine/deep learning algorithms. A validation study was conducted to identify the model with the best performance results. The BERTimbau Large model performed better, reaching a recall of 0.953 (accuracy: 0.955; precision: 0.961; F-score: 0.954; AUC: 0.954). The proposed tool demonstrated an ability to identify suicidal ideation from user texts, which enabled it to be experimented with in studies with professionals and their patients.