Smartphone as a monitoring tool for bipolar disorder: a systematic review including data analysis, machine learning algorithms and predictive modelling

AI Detection of Glottic Neoplasm Using Voice Signals, Demographics, and Structured Medical Records

OBJECTIVE

This study investigated whether artificial intelligence (AI) models combining voice signals, demographics, and structured medical records can detect glottic neoplasm from benign voice disorders.

METHODS

We used a primary dataset containing 2-3 s of vowel "ah", demographics, and 26 items of structured medical records (e.g., symptoms, comorbidity, smoking and alcohol consumption, vocal demand) from 60 patients with pathology-proved glottic neoplasm (i.e., squamous cell carcinoma, carcinoma in situ, and dysplasia) and 1940 patients with benign voice disorders. The validation dataset comprised data from 23 patients with glottic neoplasm and 1331 patients with benign disorders. The AI model combined convolutional neural networks, gated recurrent units, and attention layers. We used 10-fold cross-validation (training-validation-testing: 8-1-1) and preserved the percentage between neoplasm and benign disorders in each fold.

RESULTS

Results from the AI model using voice signals reached an area under the ROC curve (AUC) value of 0.631, and additional demographics increased this to 0.807. The highest AUC of 0.878 was achieved when combining voice, demographics, and medical records (sensitivity: 0.783, specificity: 0.816, accuracy: 0.815). External validation yielded an AUC value of 0.785 (voice plus demographics; sensitivity: 0.739, specificity: 0.745, accuracy: 0.745). Subanalysis showed that AI had higher sensitivity but lower specificity than human assessment (p < 0.01). The accuracy of AI detection with additional medical records was comparable with human assessment (82% vs. 83%, p = 0.78).

CONCLUSIONS

Voice signal alone was insufficient for AI differentiation between glottic neoplasm and benign voice disorders, but additional demographics and medical records notably improved AI performance and approximated the prediction accuracy of humans.

LEVEL OF EVIDENCE

NA Laryngoscope, 134:4585-4592, 2024.

Acoustic features from speech as markers of depressive and manic symptoms in bipolar disorder: A prospective study

INTRODUCTION

Voice features could be a sensitive marker of affective state in bipolar disorder (BD). Smartphone apps offer an excellent opportunity to collect voice data in the natural setting and become a useful tool in phase prediction in BD.

AIMS OF THE STUDY

We investigate the relations between the symptoms of BD, evaluated by psychiatrists, and patients' voice characteristics. A smartphone app extracted acoustic parameters from the daily phone calls of n = 51 patients. We show how the prosodic, spectral, and voice quality features correlate with clinically assessed affective states and explore their usefulness in predicting the BD phase.

METHODS

A smartphone app (BDmon) was developed to collect the voice signal and extract its physical features. BD patients used the application on average for 208 days. Psychiatrists assessed the severity of BD symptoms using the Hamilton depression rating scale -17 and the Young Mania rating scale. We analyze the relations between acoustic features of speech and patients' mental states using linear generalized mixed-effect models.

RESULTS

The prosodic, spectral, and voice quality parameters, are valid markers in assessing the severity of manic and depressive symptoms. The accuracy of the predictive generalized mixed-effect model is 70.9%-71.4%. Significant differences in the effect sizes and directions are observed between female and male subgroups. The greater the severity of mania in males, the louder (β = 1.6) and higher the tone of voice (β = 0.71), more clearly (β = 1.35), and more sharply they speak (β = 0.95), and their conversations are longer (β = 1.64). For females, the observations are either exactly the opposite-the greater the severity of mania, the quieter (β = -0.27) and lower the tone of voice (β = -0.21) and less clearly (β = -0.25) they speak - or no correlations are found (length of speech). On the other hand, the greater the severity of bipolar depression in males, the quieter (β = -1.07) and less clearly they speak (β = -1.00). In females, no distinct correlations between the severity of depressive symptoms and the change in voice parameters are found.

CONCLUSIONS

Speech analysis provides physiological markers of affective symptoms in BD and acoustic features extracted from speech are effective in predicting BD phases. This could personalize monitoring and care for BD patients, helping to decide whether a specialist should be consulted.

Mobile health for mental health support: a survey of attitudes and concerns among mental health professionals in Poland over the period 2020-2023

Introduction

Mobile health (mHealth) has emerged as a dynamic sector supported by technological advances and the COVID-19 pandemic and have become increasingly applied in the field of mental health.

Aim

The aim of this study was to assess the attitudes, expectations, and concerns of mental health professionals, including psychiatrists, psychologists, and psychotherapists, towards mHealth, in particular mobile health self-management tools and telepsychiatry in Poland.

Material and methods

This was a survey conducted between 2020 and 2023. A questionnaire was administered to 148 mental health professionals, covering aspects such as telepsychiatry, mobile mental health tools, and digital devices.

Results

The majority of professionals expressed readiness to use telepsychiatry, with a peak in interest during the COVID-19 pandemic, followed by a gradual decline from 2022. Concerns about telepsychiatry were reported by a quarter of respondents, mainly related to difficulties in correctly assessing the patient's condition, and technical issues. Mobile health tools were positively viewed by professionals, with 86% believing they could support patients in managing mental health and 74% declaring they would recommend patients to use them. Nevertheless, 29% expressed concerns about the effectiveness and data security of such tools. Notably, the study highlighted a growing readiness among mental health professionals to use new digital technologies, reaching 84% in 2023.

Conclusion

These findings emphasize the importance of addressing concerns and designing evidence-based mHealth solutions to ensure long-term acceptance and effectiveness in mental healthcare. Additionally, the study highlights the need for ongoing regulatory efforts to safeguard patient data and privacy in the evolving digital health landscape.

Transforming fatigue assessment: Smartphone-based system with digitized motor skill tests

BACKGROUND

The condition of fatigue is a complex and multifaceted disorder that encompasses physical, mental, and psychological dimensions, all of which contribute to a decreased quality of life. Smartphone-based systems are gaining significant research interest due to their potential to provide noninvasive monitoring and diagnosis of diseases.

OBJECTIVE

This paper studies the feasibility of using smartphones to collect motor skill related data for machine learning based fatigue detection. The authors' main goal is to provide valuable insights into the nature of fatigue and support the development of more effective interventions to manage it.

METHODS

An application for smartphones running on Android OS is developed. Two aim-based reaction tests, an Archimedean spiral test, and a tremor test, were assembled. 41 subjects participated in the study. The resulting dataset consists of 131 trials of fatigue assessment alongside digital signals extracted from the motor skill tests. Six machine learning classifiers were trained on computed features extracted from the collected digital signals.

RESULTS

The collected dataset SmartPhoneFatigue is presented for further research. The real-world utility of this database was shown by creating a methodology to construct a fatigue predictive model. Our approach incorporated 60 distinct features, such as kinematic, angular, aim-based, and tremor-related measures. The machine learning models exhibited a high degree of prediction rate for fatigue state, with an accuracy exceeding 70%, sensitivity surpassing 90%, and an f1-score greater than 80%.

CONCLUSION

The results demonstrate that the proposed smartphone-based system is suitable for motion data acquisition in non-controlled environments and shows promise as a more objective and convenient method for measuring fatigue.

The convergence of traditional and digital biomarkers through AI-assisted biosensing: A new era in translational diagnostics?

Advances in consumer electronics, alongside the fields of microfluidics and nanotechnology have brought to the fore low-cost wearable/portable smart devices. Although numerous smart devices that track digital biomarkers have been successfully translated from bench-to-bedside, only a few follow the same fate when it comes to track traditional biomarkers. Current practices still involve laboratory-based tests, followed by blood collection, conducted in a clinical setting as they require trained personnel and specialized equipment. In fact, real-time, passive/active and robust sensing of physiological and behavioural data from patients that can feed artificial intelligence (AI)-based models can significantly improve decision-making, diagnosis and treatment at the point-of-procedure, by circumventing conventional methods of sampling, and in person investigation by expert pathologists, who are scarce in developing countries. This review brings together conventional and digital biomarker sensing through portable and autonomous miniaturized devices. We first summarise the technological advances in each field vs the current clinical practices and we conclude by merging the two worlds of traditional and digital biomarkers through AI/ML technologies to improve patient diagnosis and treatment. The fundamental role, limitations and prospects of AI in realizing this potential and enhancing the existing technologies to facilitate the development and clinical translation of "point-of-care" (POC) diagnostics is finally showcased.

Capturing the Dynamics of the Social Environment Through Experience Sampling Methods, Passive Sensing, and Egocentric Networks: Scoping Review

BACKGROUND

Social interactions are important for well-being, and therefore, researchers are increasingly attempting to capture people's social environment. Many different disciplines have developed tools to measure the social environment, which can be highly variable over time. The experience sampling method (ESM) is often used in psychology to study the dynamics within a person and the social environment. In addition, passive sensing is often used to capture social behavior via sensors from smartphones or other wearable devices. Furthermore, sociologists use egocentric networks to track how social relationships are changing. Each of these methods is likely to tap into different but important parts of people's social environment. Thus far, the development and implementation of these methods have occurred mostly separately from each other.

OBJECTIVE

Our aim was to synthesize the literature on how these methods are currently used to capture the changing social environment in relation to well-being and assess how to best combine these methods to study well-being.

METHODS

We conducted a scoping review according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines.

RESULTS

We included 275 studies. In total, 3 important points follow from our review. First, each method captures a different but important part of the social environment at a different temporal resolution. Second, measures are rarely validated (>70% of ESM studies and 50% of passive sensing studies were not validated), which undermines the robustness of the conclusions drawn. Third, a combination of methods is currently lacking (only 15/275, 5.5% of the studies combined ESM and passive sensing, and no studies combined all 3 methods) but is essential in understanding well-being.

CONCLUSIONS

We highlight that the practice of using poorly validated measures hampers progress in understanding the relationship between the changing social environment and well-being. We conclude that different methods should be combined more often to reduce the participants' burden and form a holistic perspective on the social environment.

Improving the Accuracy of Diabetes Diagnosis Applications through a Hybrid Feature Selection Algorithm

Artificial intelligence is a future and valuable tool for early disease recognition and support in patient condition monitoring. It can increase the reliability of the cure and decision making by developing useful systems and algorithms. Healthcare workers, especially nurses and physicians, are overworked due to a massive and unexpected increase in the number of patients during the coronavirus pandemic. In such situations, artificial intelligence techniques could be used to diagnose a patient with life-threatening illnesses. In particular, diseases that increase the risk of hospitalization and death in coronavirus patients, such as high blood pressure, heart disease and diabetes, should be diagnosed at an early stage. This article focuses on diagnosing a diabetic patient through data mining techniques. If we are able to diagnose diabetes in the early stages of the disease, we can force patients to stay home and care for their health, so the risk of being infected with the coronavirus would be reduced. The proposed method has three steps: preprocessing, feature selection and classification. Several combinations of Harmony search algorithm, genetic algorithm, and particle swarm optimization algorithm are examined with K-means for feature selection. The combinations have not examined before for diabetes diagnosis applications. K-nearest neighbor is used for classification of the diabetes dataset. Sensitivity, specificity, and accuracy have been measured to evaluate the results. The results achieved indicate that the proposed method with an accuracy of 91.65% outperformed the results of the earlier methods examined in this article.

The PBC Model: Supporting Positive Behaviours in Smart Environments

Several behavioural problems exist in office environments, including resource use, sedentary behaviour, cognitive/multitasking, and social media. These behavioural problems have been solved through subjective or objective techniques. Within objective techniques, behavioural modelling in smart environments (SEs) can allow the adequate provision of services to users of SEs with inputs from user modelling. The effectiveness of current behavioural models relative to user-specific preferences is unclear. This study introduces a new approach to behavioural modelling in smart environments by illustrating how human behaviours can be effectively modelled from user models in SEs. To achieve this aim, a new behavioural model, the Positive Behaviour Change (PBC) Model, was developed and evaluated based on the guidelines from the Design Science Research Methodology. The PBC Model emphasises the importance of using user-specific information within the user model for behavioural modelling. The PBC model comprised the SE, the user model, the behaviour model, classification, and intervention components. The model was evaluated using a naturalistic-summative evaluation through experimentation using office workers. The study contributed to the knowledge base of behavioural modelling by providing a new dimension to behavioural modelling by incorporating the user model. The results from the experiment revealed that behavioural patterns could be extracted from user models, behaviours can be classified and quantified, and changes can be detected in behaviours, which will aid the proper identification of the intervention to provide for users with or without behavioural problems in smart environments.

A physically active lifestyle is associated with lower long-term incidence of bipolar disorder in a population-based, large-scale study

Background

Physical activity has been proposed to be beneficial for the symptomatic control of bipolar disorder, but the duration of the effects, sex-specific mechanisms, and impact of exercise intensity are not known.

Method

With an observational study design, we followed skiers and age and sex-matched non-skiers from the general population to investigate if participation in a long-distance cross-country ski race (Vasaloppet) was associated with a lower risk of getting diagnosed with bipolar disorder. Using the Swedish population and patient registries, skiers in Vasaloppet and age and sex-matched non-skiers from the general population were analyzed for any diagnosis of bipolar disorder after participation in the race. Additionally, we used finishing time of the ski race as a proxy for intensity levels to investigate if exercise intensity impacts the risk of bipolar disorder among the physically active skiers.

Results

Previous participation in a long distance ski race (n = 197,685, median age 36 years, 38% women) was associated with a lower incidence of newly diagnosed bipolar compared to an age and sex-matched general population (n = 197,684) during the up to 21 years follow-up (adjusted hazard ratio, HR = 0.48). The finishing time of the race did not significantly impact the risk of bipolar disorder in men. Among women, high performance (measured as the finishing time to complete the race, a proxy for higher exercise dose) was associated with an increased risk of bipolar disorder compared to slower skiing women (HR = 2.07).

Conclusions

Our results confirm that a physically active lifestyle is associated with a lower risk of developing bipolar disorder. Yet, to elucidate the direction of causality in this relationship requires complementary study designs. And the influence of physical performance level on the risk of bipolar disorder warrants further examinations among women.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

BACKGROUND

Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people's health. It is necessary to assess the current status on the application of AI towards the improvement of people's health in the domains defined by WHO's Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people's health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality.

METHODS

A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO's PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist.

RESULTS

The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews.

CONCLUSION

Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

Optimizing the Acceptability, Adherence, and Inclusiveness of the COVID Radar Surveillance App: Qualitative Study Using Focus Groups, Thematic Content Analysis, and Usability Testing

Background

The COVID Radar app was developed as a population-based surveillance instrument to identify at-risk populations and regions in response to the COVID-19 pandemic. The app boasts of >8.5 million completed questionnaires, with >280,000 unique users. Although the COVID Radar app is a valid tool for population-level surveillance, high user engagement is critical to the success of the COVID Radar app in maintaining validity.

Objective

This study aimed to identify optimization targets of the COVID Radar app to improve its acceptability, adherence, and inclusiveness.

Methods

The main component of the COVID Radar app is a self-report questionnaire that assesses COVID-19 symptoms and social distancing behaviors. A total of 3 qualitative substudies were conducted. First, 3 semistructured focus group interviews with end users (N=14) of the app were conducted to gather information on user experiences. The output was transcribed and thematically coded using the framework method. Second, a similar qualitative thematic analysis was conducted on 1080 end-user emails. Third, usability testing was conducted in one-on-one sessions with 4 individuals with low literacy levels.

Results

All 3 substudies identified optimization targets in terms of design and content. The results of substudy 1 showed that the participants generally evaluated the app positively. They reported the app to be user-friendly and were satisfied with its design and functionalities. Participants’ main motivation to use the app was to contribute to science. Participants suggested adding motivational tools to stimulate user engagement. A larger national publicity campaign for the app was considered potentially helpful for increasing the user population. In-app updates informing users about the project and its outputs motivated users to continue using the app. Feedback on the self-report questionnaire, stemming from substudies 1 and 2, mostly concerned the content and phrasing of the questions. Furthermore, the section of the app allowing users to compare their symptoms and behaviors to those of their peers was found to be suboptimal because of difficulties in interpreting the figures presented in the app. Finally, the output of substudy 3 resulted in recommendations primarily related to simplification of the text to render it more accessible and comprehensible for individuals with low literacy levels.

Conclusions

The convenience of app use, enabling personal adjustments of the app experience, and considering motivational factors for continued app use (ie, altruism and collectivism) were found to be crucial to procuring and maintaining a population of active users of the COVID Radar app. Further, there seems to be a need to increase the accessibility of public health tools for individuals with low literacy levels. These results can be used to improve the this and future public health apps and improve the representativeness of their user populations and user engagement, ultimately increasing the validity of the tools.

Smartphone-based interventions in bipolar disorder: Systematic review and meta-analyses of efficacy. A position paper from the International Society for Bipolar Disorders (ISBD) Big Data Task Force

BACKGROUND

The clinical effects of smartphone-based interventions for bipolar disorder (BD) have yet to be established.

OBJECTIVES

To examine the efficacy of smartphone-based interventions in BD and how the included studies reported user-engagement indicators.

METHODS

We conducted a systematic search on January 24, 2022, in PubMed, Scopus, Embase, APA PsycINFO, and Web of Science. We used random-effects meta-analysis to calculate the standardized difference (Hedges' g) in pre-post change scores between smartphone intervention and control conditions. The study was pre-registered with PROSPERO (CRD42021226668).

RESULTS

The literature search identified 6034 studies. Thirteen articles fulfilled the selection criteria. We included seven RCTs and performed meta-analyses comparing the pre-post change in depressive and (hypo)manic symptom severity, functioning, quality of life, and perceived stress between smartphone interventions and control conditions. There was significant heterogeneity among studies and no meta-analysis reached statistical significance. Results were also inconclusive regarding affective relapses and psychiatric readmissions. All studies reported positive user-engagement indicators.

CONCLUSION

We did not find evidence to support that smartphone interventions may reduce the severity of depressive or manic symptoms in BD. The high heterogeneity of studies supports the need for expert consensus to establish ideally how studies should be designed and the use of more sensitive outcomes, such as affective relapses and psychiatric hospitalizations, as well as the quantification of mood instability. The ISBD Big Data Task Force provides preliminary recommendations to reduce the heterogeneity and achieve more valid evidence in the field.

Digital phenotyping in psychiatry: A scoping review

BACKGROUND

Digital phenotyping has been defined as the moment-by-moment assessment of an illness state through digital means, promising objective, quantifiable data on psychiatric patients' conditions, and could potentially improve diagnosis and management of mental illness. As it is a rapidly growing field, it is to be expected that new literature is being published frequently.

OBJECTIVE

We conducted this scoping review to assess the current state of literature on digital phenotyping and offer some discussion on the current trends and future direction of this area of research.

METHODS

We searched four databases, PubMed, Ovid MEDLINE, PsycINFO and Web of Science, from inception to August 25th, 2021. We included studies written in English that 1) investigated or applied their findings to diagnose psychiatric disorders and 2) utilized passive sensing for management or diagnosis. Protocols were excluded. A narrative synthesis approach was used, due to the heterogeneity and variability in outcomes and outcome types reported.

RESULTS

Of 10506 unique records identified, we included a total of 107 articles. The number of published studies has increased over tenfold from 2 in 2014 to 28 in 2020, illustrating the field's rapid growth. However, a significant proportion of these (49% of all studies and 87% of primary studies) were proof of concept, pilot or correlational studies examining digital phenotyping's potential. Most (62%) of the primary studies published evaluated individuals with depression (21%), BD (18%) and SZ (23%) (Appendix 1).

CONCLUSION

There is promise shown in certain domains of data and their clinical relevance, which have yet to be fully elucidated. A consensus has yet to be reached on the best methods of data collection and processing, and more multidisciplinary collaboration between physicians and other fields is needed to unlock the full potential of digital phenotyping and allow for statistically powerful clinical trials to prove clinical utility.

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.

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

Background

Mental disorders are normally diagnosed exclusively on the basis of symptoms, which are identified from patients’ interviews and self-reported experiences. To make mental health diagnoses and monitoring more objective, different solutions have been proposed such as digital phenotyping of mental health (DPMH), which can expand the ability to identify and monitor health conditions based on the interactions of people with digital technologies.

Objective

This article aims to identify and characterize the sensing applications and public data sets for DPMH from a technical perspective.

Methods

We performed a systematic review of scientific literature and data sets. We searched 8 digital libraries and 20 data set repositories to find results that met the selection criteria. We conducted a data extraction process from the selected articles and data sets. For this purpose, a form was designed to extract relevant information, thus enabling us to answer the research questions and identify open issues and research trends.

Results

A total of 31 sensing apps and 8 data sets were identified and reviewed. Sensing apps explore different context data sources (eg, positioning, inertial, ambient) to support DPMH studies. These apps are designed to analyze and process collected data to classify (n=11) and predict (n=6) mental states/disorders, and also to investigate existing correlations between context data and mental states/disorders (n=6). Moreover, general-purpose sensing apps are developed to focus only on contextual data collection (n=9). The reviewed data sets contain context data that model different aspects of human behavior, such as sociability, mood, physical activity, sleep, with some also being multimodal.

Conclusions

This systematic review provides in-depth analysis regarding solutions for DPMH. Results show growth in proposals for DPMH sensing apps in recent years, as opposed to a scarcity of public data sets. The review shows that there are features that can be measured on smart devices that can act as proxies for mental status and well-being; however, it should be noted that the combined evidence for high-quality features for mental states remains limited. DPMH presents a great perspective for future research, mainly to reach the needed maturity for applications in clinical settings.

Apps and gaps in bipolar disorder: A systematic review on electronic monitoring for episode prediction

BACKGROUND

Long-term clinical monitoring in bipolar disorder (BD) is an important therapeutic tool. The availability of smartphones and wearables has sparked the development of automated applications to remotely monitor patients. This systematic review focus on the current state of electronic (e-) monitoring for episode prediction in BD.

METHODS

We systematically reviewed the literature on e-monitoring for episode prediction in adult BD patients. The systematic review was done according to the guidelines for reporting of systematic reviews and meta-analyses (PRISMA) and was registered in PROSPERO on April 29, 2020 (CRD42020155795). We conducted a search of Web of Science, MEDLINE, EMBASE, and PsycINFO (all 2000-2020) databases. We identified and extracted data from 17 published reports on 15 relevant studies.

RESULTS

Studies were heterogeneous and most had substantial methodological and technical limitations. Models varied widely in their performance. Published metrics were too heterogeneous to lend themselves to a meta-analysis. Four studies reported sensitivity (range: 0.21 - 0.95); and two reported specificity for prediction of mood episodes (range: 0.36 - 0.99). Two studies reported accuracy (range: 0.64 - 0.88) and four reported area under the curve (AUC; range: 0.52-0.95). Overall, models were better in predicting manic or hypomanic episodes, but their performance depended on feature type.

LIMITATIONS

Our conclusions are tempered by the lack of appropriate information impeding our ability to synthesize the available evidence.

CONCLUSIONS

Given the clinical variability in BD, predicting mood episodes remains a challenging task. Emerging e-monitoring technology for episode prediction in BD requires more development before it can be adopted clinically.

Portable technologies for digital phenotyping of bipolar disorder: A systematic review

BACKGROUND

Bias-prone psychiatric interviews remain the mainstay of bipolar disorder (BD) assessment. The development of digital phenotyping promises to improve BD management. We present a systematic review of the evidence about the use of portable digital devices for the identification of BD, BD types and BD mood states and for symptom assessment.

METHODS

We searched Web of Knowledge^SM, Scopus ®, IEEE Xplore, and ACM Digital Library databases (until 5/1/2021) for articles evaluating the use of portable/wearable digital devices, such as smartphone apps, wearable sensors, audio and/or visual recordings, and multimodal tools. The protocol is registered in PROSPERO (CRD42020200086).

RESULTS

We included 62 studies (2325 BD; 724 healthy controls, HC): 27 using smartphone apps, either for recording self-assessments (n = 10) or for passively gathering metadata (n = 7) or both (n = 10); 15 using wearable sensors for physiological parameters; 17 analysing audio and/or video recordings; 3 using multiple technologies. Two thirds of the included studies applied artificial intelligence (AI)-based approaches. They achieved fair to excellent classification performances.

LIMITATIONS

The included studies had small sample sizes and marked heterogeneity. Evidence of overfitting emerged, limiting generalizability. The absence of clear guidelines about reporting classification performances, with no shared standard metrics, makes results hardly interpretable and comparable.

CONCLUSIONS

New technologies offer a noteworthy opportunity to BD digital phenotyping with objectivity and high granularity. AI-based models could deliver important support in clinical decision-making. Further research and cooperation between different stakeholders are needed for addressing methodological, ethical and socio-economic considerations.

Behavioural and Self-Reported Data Collected from Smartphones in the Assessment of Depressive and Manic Symptoms for Bipolar Disorder Patients: Prospective Observational Study

BACKGROUND

Smartphones allow for real-time monitoring of patients' behavioural activities in a naturalistic setting. These data are suggested as markers of mental state in bipolar disorder (BD).

OBJECTIVE

We assess the relations between data collected from smartphones and the clinically rated depressive and manic symptoms together with the corresponding affective states in BD.

METHODS

BDmon - a dedicated mobile app was developed and installed on the patients' smartphones to automatically collect statistics about phone calls and text messages, as well as self-assessment of sleep and patient's mood. The final sample for the numerical analyses consisted of 51 eligible patients who participated in at least two psychiatric assessments and used the BDmon app (mean participation time: 208 days ± SD of 132 days). In total, 196 psychiatric assessments were performed using the Hamilton Depression Rating Scale (HDRS) and Young Mania Rating Scale (YMRS). Generalized linear mixed-effects models were applied to quantify the strength of the relation between the daily statistics about behavioural data collected automatically from smartphones and the affective symptoms and mood states in BD.

RESULTS

Objective behavioural data collected from smartphones and their relation to BD states were as follows: (1) depressed patients tended to make phone calls less frequently than in euthymia (β=-0.064, P=.01); (2) the number of incoming answered calls was lower in depression as compared to euthymia (β=-0.15, P=.01) and, at the same time, missed incoming calls were more frequent and increased as depressive symptoms intensified (β=4.431, P<.001; β=4.861, P<.001, respectively); (3) the fraction of outgoing calls was higher in manic states (β=2.73, P=.03); (4) the fraction of missed calls was higher in manic/mixed states as compared to euthymia (β=3.53, P=.01) and positively correlated to the severity of symptoms (β=2.991, P=.02); (5) variability of duration of outgoing calls was higher in manic/mixed states (β=1.22·10-3, P=.045) and positively correlated to the severity of symptoms (β=1.72·10-3, P=.02); (6) the number and length of sent text messages was higher in manic/mixed states as compared to euthymia (β=0.031, P=.01; β=0.015, P=.01, respectively) and positively correlated to the severity of manic symptoms (β=0.116, P<.001; β=0.022, P<.001). We also observed that self-assessment of mood was lower in depressive (β=-1.452, P<.001). and higher in manic states (β=0.509, P<.001).

CONCLUSIONS

Smartphone-based behavioural parameters are valid markers in assessing the severity of affective symptoms and discriminating between mood states. This opens a way toward early detection of worsening of the mental state and thereby increases the patient's chance of improving the course of the illness.

The growing field of digital psychiatry: current evidence and the future of apps, social media, chatbots, and virtual reality

As the COVID-19 pandemic has largely increased the utilization of telehealth, mobile mental health technologies - such as smartphone apps, vir-tual reality, chatbots, and social media - have also gained attention. These digital health technologies offer the potential of accessible and scalable interventions that can augment traditional care. In this paper, we provide a comprehensive update on the overall field of digital psychiatry, covering three areas. First, we outline the relevance of recent technological advances to mental health research and care, by detailing how smartphones, social media, artificial intelligence and virtual reality present new opportunities for "digital phenotyping" and remote intervention. Second, we review the current evidence for the use of these new technological approaches across different mental health contexts, covering their emerging efficacy in self-management of psychological well-being and early intervention, along with more nascent research supporting their use in clinical management of long-term psychiatric conditions - including major depression; anxiety, bipolar and psychotic disorders; and eating and substance use disorders - as well as in child and adolescent mental health care. Third, we discuss the most pressing challenges and opportunities towards real-world implementation, using the Integrated Promoting Action on Research Implementation in Health Services (i-PARIHS) framework to explain how the innovations themselves, the recipients of these innovations, and the context surrounding innovations all must be considered to facilitate their adoption and use in mental health care systems. We conclude that the new technological capabilities of smartphones, artificial intelligence, social media and virtual reality are already changing mental health care in unforeseen and exciting ways, each accompanied by an early but promising evidence base. We point out that further efforts towards strengthening implementation are needed, and detail the key issues at the patient, provider and policy levels which must now be addressed for digital health technologies to truly improve mental health research and treatment in the future.

AN EXECUTABLE METHOD FOR AN INTELLIGENT SPEECH AND CALL RECOGNITION SYSTEM USING A MACHINE LEARNING-BASED APPROACH

This paper describes a novel call recognizer system based on the machine learning approach. Current trends, intelligence, emotional recognition and other factors are important challenges in the real world. The proposed system provides robustness with high accuracy and adequate response time for the human–computer interaction. Intelligence and emotion recognition from the speech of human–computer interfaces are simulated via multiple classifier systems (MCSs). At a higher-level stage, the acoustic stream phase extracts certain acoustic features based on the pitch and energy of the signal. Here, the feature space is labeled with various emotional types in the training phase. Emotional categories are trained in the acoustic feature space. The semantic stream process converts speech into text in the input speech signal. Text classification algorithms are applied subsequently. The clustering and classification process is performed via a [Formula: see text]-means algorithm. The detection of the Tone of Voice of call recognition system is achieved with the XGBoost model for feature extraction and detection of a particular phrase in the client call phase. Speech expressions are used for understanding the human emotion. The algorithms are tested and demonstrate good performance in the simulation environment.

A Convenient and Low-Cost Model of Depression Screening and Early Warning Based on Voice Data Using for Public Mental Health

Depression is a common mental health disease, which has great harm to public health. At present, the diagnosis of depression mainly depends on the interviews between doctors and patients, which is subjective, slow and expensive. Voice data are a kind of data that are easy to obtain and have the advantage of low cost. It has been proved that it can be used in the diagnosis of depression. The voice data used for modeling in this study adopted the authoritative public data set, which had passed the ethical review. The features of voice data were extracted by Python programming, and the voice features were stored in the format of CSV files. Through data processing, a big database, containing 1479 voice feature samples, was generated for modeling. Then, the decision tree screening model of depression was established by 10-fold cross validation and algorithm selection. The experiment achieved 83.4% prediction accuracy on voice data set. According to the prediction results of the model, the patients can be given early warning and intervention in time, so as to realize the health management of personal depression.

The role of cognitive functions in the diagnosis of bipolar disorder: A machine learning model

BACKGROUND

Considering the clinical heterogeneity of the bipolar disorder, difficulties are encountered in making the correct diagnosis. Although a number of common findings have been found in studies on the neurocognitive profile of bipolar disorder, the search for a neurocognitive endophenotype has failed. The aim of this study is to separate bipolar disorder patients from healthy controls with higher accuracy by using a broader neurocognitive evaluation and a novel machine-learning algorithm.

METHODS

Individuals who presented to the Bipolar Outpatient Clinic of the Medical Faculty of Eskişehir Osmangazi University and met the inclusion criteria of the research are included in the study. Six neurocognitive tests from the CANTAB test battery were used for neurocognitive evaluation, Polyhedral Conic Functions algorithm was used to classify the participants.

RESULTS

Bipolar disorder patients differentiated from healthy controls with an accuracy of 78 %.

DISCUSSION

Our study presents a prediction algorithm that separates bipolar disorder from healthy controls with high accuracy by using CANTAB neurocognitive battery.