A signature-based machine learning model for distinguishing bipolar disorder and borderline personality disorder

Application of the Random Forest Algorithm for Accurate Bipolar Disorder Classification

Bipolar disorder (BD) is a complex psychiatric condition characterized by alternating episodes of mania and depression, posing significant challenges for accurate and timely diagnosis. This study explores the use of the Random Forest (RF) algorithm as a machine learning approach to classify patients with BD and healthy controls based on electroencephalogram (EEG) data. A total of 330 participants, including euthymic BD patients and healthy controls, were analyzed. EEG recordings were processed to extract key features, including power in frequency bands and complexity metrics such as the Hurst Exponent, which measures the persistence or randomness of a time series, and the Higuchi's Fractal Dimension, which is used to quantify the irregularity of brain signals. The RF model demonstrated robust performance, achieving an average accuracy of 93.41%, with recall and specificity exceeding 93%. These results highlight the algorithm's capacity to handle complex, noisy datasets while identifying key features relevant for classification. Importantly, the model provided interpretable insights into the physiological markers associated with BD, reinforcing the clinical value of EEG as a diagnostic tool. The findings suggest that RF is a reliable and accessible method for supporting the diagnosis of BD, complementing traditional clinical practices. Its ability to reduce diagnostic delays, improve classification accuracy, and optimize resource allocation make it a promising tool for integrating artificial intelligence into psychiatric care. This study represents a significant step toward precision psychiatry, leveraging technology to improve the understanding and management of complex mental health disorders.

A machine learning approach for differentiating bipolar disorder type II and borderline personality disorder using electroencephalography and cognitive abnormalities

This study addresses the challenge of differentiating between bipolar disorder II (BD II) and borderline personality disorder (BPD), which is complicated by overlapping symptoms. To overcome this, a multimodal machine learning approach was employed, incorporating both electroencephalography (EEG) patterns and cognitive abnormalities for enhanced classification. Data were collected from 45 participants, including 20 with BD II and 25 with BPD. Analysis involved utilizing EEG signals and cognitive tests, specifically the Wisconsin Card Sorting Test and Integrated Cognitive Assessment. The k-nearest neighbors (KNN) algorithm achieved a balanced accuracy of 93%, with EEG features proving to be crucial, while cognitive features had a lesser impact. Despite the strengths, such as diverse model usage, it's important to note limitations, including a small sample size and reliance on DSM diagnoses. The study suggests that future research should explore multimodal data integration and employ advanced techniques to improve classification accuracy and gain a better understanding of the neurobiological distinctions between BD II and BPD.

Signature methods for brain-computer interfaces

Brain-computer interfaces (BCIs) allow direct communication between one's central nervous system and a computer without any muscle movement hence by-passing the peripheral nervous system. They can restore disabled people's ability to interact with their environment, e.g. communication and wheelchair control. However, to this day their performance is still hindered by the non-stationarity of electroencephalography (EEG) signals, as well as their susceptibility to noise from the users' environment and from their own physiological activity. Moreover, a non-negligible amount of users struggle to use BCI systems based on motor imagery. In this paper, a new method based on the path signature is introduced to tackle this problem by using features which are different from the usual power-based ones. The path signature is a series of iterated integrals computed from a multidimensional path. It is invariant under translation and time reparametrization, which makes it a robust feature for multichannel EEG time series. The performance can be further boosted by combining the path signature with the gold standard Riemannian classifier in the BCI field exploiting the geometric structure of symmetric positive definite (SPD) matrices. The results obtained on publicly available datasets show that the signature method is more robust to inter-user variability than classical ones, especially on noisy and low-quality data. Hence, this study paves the way towards the use of mathematical tools that until now have been neglected, in order to tackle the EEG-based BCI variability issue. It also sheds light on the lead-lag relationship captured by path signature which seems relevant to assess the underlying neural mechanisms.

Methodological and Quality Flaws in the Use of Artificial Intelligence in Mental Health Research: Systematic Review

BACKGROUND

Artificial intelligence (AI) is giving rise to a revolution in medicine and health care. Mental health conditions are highly prevalent in many countries, and the COVID-19 pandemic has increased the risk of further erosion of the mental well-being in the population. Therefore, it is relevant to assess the current status of the application of AI toward mental health research to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

This study aims to perform a systematic overview of AI applications in mental health in terms of methodologies, data, outcomes, performance, and quality.

METHODS

A systematic search in PubMed, Scopus, IEEE Xplore, and Cochrane databases was conducted to collect records of use cases of AI for mental health disorder studies from January 2016 to November 2021. Records were screened for eligibility if they were a practical implementation of AI in clinical trials involving mental health conditions. Records of AI study cases were evaluated and categorized by the International Classification of Diseases 11th Revision (ICD-11). Data related to trial settings, collection methodology, features, outcomes, and model development and evaluation were extracted following the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) guideline. Further, evaluation of risk of bias is provided.

RESULTS

A total of 429 nonduplicated records were retrieved from the databases and 129 were included for a full assessment-18 of which were manually added. The distribution of AI applications in mental health was found unbalanced between ICD-11 mental health categories. Predominant categories were Depressive disorders (n=70) and Schizophrenia or other primary psychotic disorders (n=26). Most interventions were based on randomized controlled trials (n=62), followed by prospective cohorts (n=24) among observational studies. AI was typically applied to evaluate quality of treatments (n=44) or stratify patients into subgroups and clusters (n=31). Models usually applied a combination of questionnaires and scales to assess symptom severity using electronic health records (n=49) as well as medical images (n=33). Quality assessment revealed important flaws in the process of AI application and data preprocessing pipelines. One-third of the studies (n=56) did not report any preprocessing or data preparation. One-fifth of the models were developed by comparing several methods (n=35) without assessing their suitability in advance and a small proportion reported external validation (n=21). Only 1 paper reported a second assessment of a previous AI model. Risk of bias and transparent reporting yielded low scores due to a poor reporting of the strategy for adjusting hyperparameters, coefficients, and the explainability of the models. International collaboration was anecdotal (n=17) and data and developed models mostly remained private (n=126).

CONCLUSIONS

These significant shortcomings, alongside the lack of information to ensure reproducibility and transparency, are indicative of the challenges that AI in mental health needs to face before contributing to a solid base for knowledge generation and for being a support tool in mental health management.

Novel digital methods for gathering intensive time series data in mental health research: scoping review of a rapidly evolving field

Recent technological advances enable the collection of intensive longitudinal data. This scoping review aimed to provide an overview of methods for collecting intensive time series data in mental health research as well as basic principles, current applications, target constructs, and statistical methods for this type of data.In January 2021, the database MEDLINE was searched. Original articles were identified that (1) used active or passive data collection methods to gather intensive longitudinal data in daily life, (2) had a minimum sample size of N ⩾ 100 participants, and (3) included individuals with subclinical or clinical mental health problems.In total, 3799 original articles were identified, of which 174 met inclusion criteria. The most widely used methods were diary techniques (e.g. Experience Sampling Methodology), various types of sensors (e.g. accelerometer), and app usage data. Target constructs included affect, various symptom domains, cognitive processes, sleep, dysfunctional behaviour, physical activity, and social media use. There was strong evidence on feasibility of, and high compliance with, active and passive data collection methods in diverse clinical settings and groups. Study designs, sampling schedules, and measures varied considerably across studies, limiting the generalisability of findings.Gathering intensive longitudinal data has significant potential to advance mental health research. However, more methodological research is required to establish and meet critical quality standards in this rapidly evolving field. Advanced approaches such as digital phenotyping, ecological momentary interventions, and machine-learning methods will be required to efficiently use intensive longitudinal data and deliver personalised digital interventions and services for improving public mental health.

Neural-signature methods for structured EHR prediction

Models that can effectively represent structured Electronic Healthcare Records (EHR) are central to an increasing range of applications in healthcare. Due to the sequential nature of health data, Recurrent Neural Networks have emerged as the dominant component within state-of-the-art architectures. The signature transform represents an alternative modelling paradigm for sequential data. This transform provides a non-learnt approach to creating a fixed vector representation of temporal features and has shown strong performances across an increasing number of domains, including medical data. However, the signature method has not yet been applied to structured EHR data. To this end, we follow recent work that enables the signature to be used as a differentiable layer within a neural architecture enabling application in high dimensional domains where calculation would have previously been intractable. Using a heart failure prediction task as an exemplar, we provide an empirical evaluation of different variations of the signature method and compare against state-of-the-art baselines. This first application of neural-signature methods in real-world healthcare data shows a competitive performance when compared to strong baselines and thus warrants further investigation within the health domain.

Identifying psychiatric diagnosis from missing mood data through the use of log-signature features

The availability of mobile technologies has enabled the efficient collection of prospective longitudinal, ecologically valid self-reported clinical questionnaires from people with psychiatric diagnoses. These data streams have potential for improving the efficiency and accuracy of psychiatric diagnosis as well predicting future mood states enabling earlier intervention. However, missing responses are common in such datasets and there is little consensus as to how these should be dealt with in practice. In this study, the missing-response-incorporated log-signature method achieves roughly 74.8% correct diagnosis, with f1 scores for three diagnostic groups 66% (bipolar disorder), 83% (healthy control) and 75% (borderline personality disorder) respectively. This was superior to the naive model which excluded missing data and advanced models which implemented different imputation approaches, namely, k-nearest neighbours (KNN), probabilistic principal components analysis (PPCA) and random forest-based multiple imputation by chained equations (rfMICE). The log-signature method provided an effective approach to the analysis of prospectively collected mood data where missing data was common and should be considered as an approach in other similar datasets. Because of treating missing responses as a signal, its superiority also highlights that missing data conveys valuable clinical information.

A Web-Based Application for Personalized Ecological Momentary Assessment in Psychiatric Care: User-Centered Development of the PETRA Application

BACKGROUND

Smartphone self-monitoring of mood, symptoms, and contextual factors through ecological momentary assessment (EMA) provides insights into the daily lives of people undergoing psychiatric treatment. Therefore, EMA has the potential to improve their care. To integrate EMA into treatment, a clinical tool that helps clients and clinicians create personalized EMA diaries and interpret the gathered data is needed.

OBJECTIVE

This study aimed to develop a web-based application for personalized EMA in specialized psychiatric care in close collaboration with all stakeholders (ie, clients, clinicians, researchers, and software developers).

METHODS

The participants were 52 clients with mood, anxiety, and psychotic disorders and 45 clinicians (psychiatrists, psychologists, and psychiatric nurses). We engaged them in interviews, focus groups, and usability sessions to determine the requirements for an EMA web application and repeatedly obtained feedback on iteratively improved high-fidelity EMA web application prototypes. We used human-centered design principles to determine important requirements for the web application and designed high-fidelity prototypes that were continuously re-evaluated and adapted.

RESULTS

The iterative development process resulted in Personalized Treatment by Real-time Assessment (PETRA), which is a scientifically grounded web application for the integration of personalized EMA in Dutch clinical care. PETRA includes a decision aid to support clients and clinicians with constructing personalized EMA diaries, an EMA diary item repository, an SMS text message-based diary delivery system, and a feedback module for visualizing the gathered EMA data. PETRA is integrated into electronic health record systems to ensure ease of use and sustainable integration in clinical care and adheres to privacy regulations.

CONCLUSIONS

PETRA was built to fulfill the needs of clients and clinicians for a user-friendly and personalized EMA tool embedded in routine psychiatric care. PETRA is unique in this codevelopment process, its extensive but user-friendly personalization options, its integration into electronic health record systems, its transdiagnostic focus, and its strong scientific foundation in the design of EMA diaries and feedback. The clinical effectiveness of integrating personalized diaries via PETRA into care requires further research. As such, PETRA paves the way for a systematic investigation of the utility of personalized EMA for routine mental health care.

Comorbid bipolar disorder and borderline personality disorder: Diagnosis using machine learning

Comorbid bipolar disorder (BP) and borderline personality disorder (BPD) presents a diagnostic challenge in its differentiation from each condition individually. We aimed to use a machine learning (ML) approach to differentiate comorbid BP/BPD from both BP and BPD. Participants were assigned DSM diagnoses and compared on self-report measures examining personality, emotion regulation strategies and perceived parental experiences during childhood. 82 participants were assigned as BP, 52 as BPD and 53 as comorbid BP/BPD. ML-derived diagnoses had an accuracy of 79.6% in classifying BP/BPD vs. BP, and 61.7% in classifying BP/BPD vs. BPD. Stress-related paranoid ideation and other core borderline personality items were important in distinguishing BP/BPD vs. BP, whereas deficits in emotion regulation strategies were important in distinguishing BP/BPD vs. BPD. Impulsivity and anger were important across both analyses. We identified clinical variables more distinctive in comorbid BP/BPD, with superior accuracy in distinguishing from BP, and with lower accuracy compared to BPD alone. Such an additive model should assist in sharpening clinical decision making, with future machine learning examination of larger datasets likely to further improve diagnostic accuracy.

Designing Tangibles to Support Emotion Logging for Older Adults: Development and Usability Study

BACKGROUND

The global population is aging, leading to shifts in health care needs. In addition to developing technology to support physical health, there is an increasing recognition of the need to consider how technology can support emotional health. This raises the question of how to design devices that older adults can interact with to log their emotions.

OBJECTIVE

We designed and developed 2 novel tangible devices, inspired by existing paper-based scales of emotions. The findings from a field trial of these devices with older adults are reported.

METHODS

Using interviews, field deployment, and fixed logging tasks, we assessed the developed devices.

RESULTS

Our results demonstrate that the tangible devices provided data comparable with standardized psychological scales of emotion. The participants developed their own patterns of use around the devices, and their experience of using the devices uncovered a variety of design considerations. We discuss the difficulty of customizing devices for specific user needs while logging data comparable to psychological scales of emotion. We also highlight the value of reflecting on sparse emotional data.

CONCLUSIONS

Our work demonstrates the potential for tangible emotional logging devices. It also supports further research on whether such devices can support the emotional health of older adults by encouraging reflection of their emotional state.

The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review

BACKGROUND

Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.

OBJECTIVE

This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.

METHODS

The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.

RESULTS

We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning-based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.

CONCLUSIONS

This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

Ethics and Law in Research on Algorithmic and Data-Driven Technology in Mental Health Care: Scoping Review

BACKGROUND

Uncertainty surrounds the ethical and legal implications of algorithmic and data-driven technologies in the mental health context, including technologies characterized as artificial intelligence, machine learning, deep learning, and other forms of automation.

OBJECTIVE

This study aims to survey empirical scholarly literature on the application of algorithmic and data-driven technologies in mental health initiatives to identify the legal and ethical issues that have been raised.

METHODS

We searched for peer-reviewed empirical studies on the application of algorithmic technologies in mental health care in the Scopus, Embase, and Association for Computing Machinery databases. A total of 1078 relevant peer-reviewed applied studies were identified, which were narrowed to 132 empirical research papers for review based on selection criteria. Conventional content analysis was undertaken to address our aims, and this was supplemented by a keyword-in-context analysis.

RESULTS

We grouped the findings into the following five categories of technology: social media (53/132, 40.1%), smartphones (37/132, 28%), sensing technology (20/132, 15.1%), chatbots (5/132, 3.8%), and miscellaneous (17/132, 12.9%). Most initiatives were directed toward detection and diagnosis. Most papers discussed privacy, mainly in terms of respecting the privacy of research participants. There was relatively little discussion of privacy in this context. A small number of studies discussed ethics directly (10/132, 7.6%) and indirectly (10/132, 7.6%). Legal issues were not substantively discussed in any studies, although some legal issues were discussed in passing (7/132, 5.3%), such as the rights of user subjects and privacy law compliance.

CONCLUSIONS

Ethical and legal issues tend to not be explicitly addressed in empirical studies on algorithmic and data-driven technologies in mental health initiatives. Scholars may have considered ethical or legal matters at the ethics committee or institutional review board stage. If so, this consideration seldom appears in published materials in applied research in any detail. The form itself of peer-reviewed papers that detail applied research in this field may well preclude a substantial focus on ethics and law. Regardless, we identified several concerns, including the near-complete lack of involvement of mental health service users, the scant consideration of algorithmic accountability, and the potential for overmedicalization and techno-solutionism. Most papers were published in the computer science field at the pilot or exploratory stages. Thus, these technologies could be appropriated into practice in rarely acknowledged ways, with serious legal and ethical implications.

Differentiation of bipolar disorder versus borderline personality disorder: A machine learning approach

BACKGROUND

Differentiation of bipolar disorder (BP) from borderline personality disorder (BPD) is a common diagnostic dilemma. We undertook a machine learning (ML) approach to distinguish the conditions.

METHODS

Participants meeting DSM criteria for BP or BPD were compared on measures examining cognitive and behavioral BPD constructs, emotion regulation strategies, and parental behaviors during childhood. Two analyses used continuous and dichotomised data, with ML-allocated diagnoses compared to DSM.

RESULTS

82 participants met DSM criteria for BP and 52 for BPD. Accuracy of ML classification was 84.1% - 87.8% for BP, 50% - 57.7% for BPD, with overall accuracy of 73.1% - 73.9%. Importance of items differed between the analyses with the overall most important items including identity difficulties, relationship problems, female gender, feeling suicidal after a relationship breakdown and age.

LIMITATIONS

Participants were volunteers, preponderance of bipolar II (BP II) participants, comorbidity of BP and BPD not examined, and small BPD sample contributed to the relatively low classification accuracies for this group CONCLUSIONS: Study findings may assist distinguishing BP and BPD based on differences in cognitive and behavioral domains, emotion regulation strategies and parental behaviors. Future studies using larger datasets could further improve predictive accuracy and assist in differential diagnosis.

Utilization of the Signature Method to Identify the Early Onset of Sepsis From Multivariate Physiological Time Series in Critical Care Monitoring

OBJECTIVES

Patients in an ICU are particularly vulnerable to sepsis. It is therefore important to detect its onset as early as possible. This study focuses on the development and validation of a new signature-based regression model, augmented with a particular choice of the handcrafted features, to identify a patient's risk of sepsis based on physiologic data streams. The model makes a positive or negative prediction of sepsis for every time interval since admission to the ICU.

DESIGN

The data were sourced from the PhysioNet/Computing in Cardiology Challenge 2019 on the "Early Prediction of Sepsis from Clinical Data." It consisted of ICU patient data from three separate hospital systems. Algorithms were scored against a specially designed utility function that rewards early predictions in the most clinically relevant region around sepsis onset and penalizes late predictions and false positives.

SETTING

The work was completed as part of the PhysioNet 2019 Challenge alongside 104 other teams.

PATIENTS

PhysioNet sourced over 60,000 ICU patients with up to 40 clinical variables for each hour of a patient's ICU stay. The Sepsis-3 criteria was used to define the onset of sepsis.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

The algorithm yielded a utility function score which was the first placed entry in the official phase of the challenge.

The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review (Preprint).. [DOI: 10.2196/preprints.29749] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.

OBJECTIVE

This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.

METHODS

The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.

RESULTS

We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning–based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.

CONCLUSIONS

This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

The Continuum Between Temperament and Mental Illness as Dynamical Phases and Transitions

The full range of biopsychosocial complexity is mind-boggling, spanning a vast range of spatiotemporal scales with complicated vertical, horizontal, and diagonal feedback interactions between contributing systems. It is unlikely that such complexity can be dealt with by a single model. One approach is to focus on a narrower range of phenomena which involve fewer systems but still cover the range of spatiotemporal scales. The suggestion is to focus on the relationship between temperament in healthy individuals and mental illness, which have been conjectured to lie along a continuum of neurobehavioral regulation involving neurochemical regulatory systems (e.g., monoamine and acetylcholine, opiate receptors, neuropeptides, oxytocin), and cortical regulatory systems (e.g., prefrontal, limbic). Temperament and mental illness are quintessentially dynamical phenomena, and need to be addressed in dynamical terms. A meteorological metaphor suggests similarities between temperament and chronic mental illness and climate, between individual behaviors and weather, and acute mental illness and frontal weather events. The transition from normative temperament to chronic mental illness is analogous to climate change. This leads to the conjecture that temperament and chronic mental illness describe distinct, high level, dynamical phases. This suggests approaching biopsychosocial complexity through the study of dynamical phases, their order and control parameters, and their phase transitions. Unlike transitions in physical systems, these biopsychosocial phase transitions involve information and semiotics. The application of complex adaptive dynamical systems theory has led to a host of markers including geometrical markers (periodicity, intermittency, recurrence, chaos) and analytical markers such as fluctuation spectroscopy, scaling, entropy, recurrence time. Clinically accessible biomarkers, in particular heart rate variability and activity markers have been suggested to distinguish these dynamical phases and to signal the presence of transitional states. A particular formal model of these dynamical phases will be presented based upon the process algebra, which has been used to model information flow in complex systems. In particular it describes the dual influences of energy and information on the dynamics of complex systems. The process algebra model is well-suited for dealing with the particular dynamical features of the continuum, which include transience, contextuality, and emergence. These dynamical phases will be described using the process algebra model and implications for clinical practice will be discussed.

Application of Artificial Intelligence in Pharmaceutical and Biomedical Studies

BACKGROUND

Artificial intelligence (AI) is the way to model human intelligence to accomplish certain tasks without much intervention of human beings. The term AI was first used in 1956 with The Logic Theorist program, which was designed to simulate problem-solving ability of human beings. There have been a significant amount of research works using AI in order to determine the advantages and disadvantages of its applicabication and, future perspectives that impact different areas of society. Even the remarkable impact of AI can be transferred to the field of healthcare with its use in pharmaceutical and biomedical studies crucial for the socioeconomic development of the population in general within different studies, we can highlight those that have been conducted with the objective of treating diseases, such as cancer, neurodegenerative diseases, among others. In parallel, the long process of drug development also requires the application of AI to accelerate research in medical care.

METHODS

This review is based on research material obtained from PubMed up to Jan 2020. The search terms include "artificial intelligence", "machine learning" in the context of research on pharmaceutical and biomedical applications.

RESULTS

This study aimed to highlight the importance of AI in the biomedical research and also recent studies that support the use of AI to generate tools using patient data to improve outcomes. Other studies have demonstrated the use of AI to create prediction models to determine response to cancer treatment.

CONCLUSION

The application of AI in the field of pharmaceutical and biomedical studies has been extensive, including cancer research, for diagnosis as well as prognosis of the disease state. It has become a tool for researchers in the management of complex data, ranging from obtaining complementary results to conventional statistical analyses. AI increases the precision in the estimation of treatment effect in cancer patients and determines prediction outcomes.

Gait Analysis with Wearables Can Accurately Classify Fallers from Non-Fallers: A Step toward Better Management of Neurological Disorders

Falls are the leading cause of mortality, morbidity and poor quality of life in older adults with or without neurological conditions. Applying machine learning (ML) models to gait analysis outcomes offers the opportunity to identify individuals at risk of future falls. The aim of this study was to determine the effect of different data pre-processing methods on the performance of ML models to classify neurological patients who have fallen from those who have not for future fall risk assessment. Gait was assessed using wearables in clinic while walking 20 m at a self-selected comfortable pace in 349 (159 fallers, 190 non-fallers) neurological patients. Six different ML models were trained on data pre-processed with three techniques such as standardisation, principal component analysis (PCA) and path signature method. Fallers walked more slowly, with shorter strides and longer stride duration compared to non-fallers. Overall, model accuracy ranged between 48% and 98% with 43-99% sensitivity and 48-98% specificity. A random forest (RF) classifier trained on data pre-processed with the path signature method gave optimal classification accuracy of 98% with 99% sensitivity and 98% specificity. Data pre-processing directly influences the accuracy of ML models for the accurate classification of fallers. Using gait analysis with trained ML models can act as a tool for the proactive assessment of fall risk and support clinical decision-making.

Recommendations for the use of long-term experience sampling in bipolar disorder care: a qualitative study of patient and clinician experiences

Background

Self-monitoring has been shown to improve the self-management and treatment of patients with bipolar disorder. However, current self-monitoring methods are limited to once-daily retrospectively assessed mood, which may not suit the rapid mood fluctuations in bipolar disorder. The experience sampling method (ESM), which assesses mood in real-time several times a day, may overcome these limitations. This study set out to assess the experiences of patients and clinicians with the addition of ESM monitoring, real-time alerts, and personalized feedback to clinical care. Participants were twenty patients with bipolar disorder type I/II and their clinicians. For four months, patients completed five ESM assessments per day on mood, symptoms, and activities. Weekly symptom questionnaires alerted patients and clinicians to potential episodes. After the monitoring, a personalized feedback report based on the patient’s data was discussed between patient and clinician. Three months later, patient and clinician were both interviewed.

Results

Thematic analysis of the transcripts resulted in four themes: perceived effects of the monitoring, alerts, and feedback, and recommendations for implementation of ESM. ESM was perceived as helping patients to cope better with their disorder by increasing awareness, offering new insights, and encouraging life style adjustments. ESM was further believed to facilitate communication between patient and clinician and to lead to new treatment directions. However, high assessment burden and pre-occupation with negative mood and having a disorder were also described. Patients and clinicians advocated for increased personalization and embedding of ESM in care.

Conclusions

This study demonstrates that long-term ESM monitoring, alerts, and personalized feedback are perceived as beneficial to the treatment and self-management of patients with bipolar disorder. Future research should further test the clinical utility of ESM. Clinically relevant feedback and technology need to be developed to enable personalized integration of ESM in clinical care.

Developments in diagnosis and treatment of people with borderline personality disorder

PURPOSE OF REVIEW

Borderline personality disorder (BPD) attracts significant attention from clinicians and researchers alike. Despite increased recognition and willingness to diagnose BPD, most effective treatment approaches remain inaccessible to most. We consider recent developments in the diagnosis and treatment of BPD.

RECENT FINDINGS

A literature search of EMBASE and PsychINFO, using the search terms 'borderline personality disorder,' 'diagnosis' and 'treatment' for publications since October 2018, yielded over 300 articles and reviews. The literature highlights the increasing awareness of the diagnostic complexity of BPD as well as the emerging significance of 'common factors' and stepped care approaches for managing and treating the disorder.

SUMMARY

Clinical practice is evolving to embrace more holistic diagnostic approaches, generalist treatment frameworks and stepped-care models that can be tailored to fit individual needs and service resources. The new frontiers in this field include expansion of timely treatment options, improved knowledge regarding the expression and management of BPD in men, adolescents and the elderly, and bridging cultural divides to create a worldwide population approach.

Digital solutions for shaping mood and behavior among individuals with mood disorders

Mood disorders present on-going challenges to the medical field, with difficulties ranging from establishing effective treatments to understanding complexities of one's mood. One solution is the use of mobile apps and wearables for measuring physiological symptoms and real-time mood in order to shape mood and behavior. Current digital research is focused on increasing engagement in monitoring mood, uncovering mood dynamics, predicting mood, and providing digital microinterventions. This review discusses the importance and risks of user engagement, as well as barriers to improving it. Research on mood dynamics highlights the possibility to reveal data-driven computational phenotypes that could guide treatment. Mobile apps are being used to track voice patterns, GPS, and phone usage for predicting mood and treatment response. Future directions include utilizing mobile apps to deliver and evaluate microinterventions. To continue these advances, standardized reporting and study designs should be considered to improve digital solutions for mood disorders.

mHealth in affective disorders: hype or hope? A focused narrative review

The constant growth and widespread availability of mobile technologies (i.e. smartphones and wearables) over the last decades have been a subject of intense interest and research in the affective disorders (AD) field. The potential of mHealth for collecting a new kind of passive and active information while providing cost-effective and tailored interventions have raised many hopes. However, until now, despite some encouraging results, research in the field has not been translated to reach real-world clinical settings or to develop additional evidence-based mHealth tools for people suffering from AD. Meanwhile, commercial untested apps and wearables are already being increasingly used and adopted by patients for the self-management of their illnesses. Hence, there is a latent need and demand from service users to integrate mHealth in their care, which the field cannot yet fulfil. In this article, through a focused narrative review, we discuss the evidence available for the use, validity and efficacy of mHealth tools in AD. Challenges in the academic field hampering the advancement of these technologies and its implementation into clinical practice are discussed. Lastly, we propose a framework to overcome these issues, which may facilitate mHealth solutions reaching service users.

The True Colours Remote Symptom Monitoring System: A Decade of Evolution

The True Colours remote mood monitoring system was developed over a decade ago by researchers, psychiatrists, and software engineers at the University of Oxford to allow patients to report on a range of symptoms via text messages, Web interfaces, or mobile phone apps. The system has evolved to encompass a wide range of measures, including psychiatric symptoms, quality of life, and medication. Patients are prompted to provide data according to an agreed personal schedule: weekly, daily, or at specific times during the day. The system has been applied across a number of different populations, for the reporting of mood, anxiety, substance use, eating and personality disorders, psychosis, self-harm, and inflammatory bowel disease, and it has shown good compliance. Over the past decade, there have been over 36,000 registered True Colours patients and participants in the United Kingdom, with more than 20 deployments of the system supporting clinical service and research delivery. The system has been adopted for routine clinical care in mental health services, supporting more than 3000 adult patients in secondary care, and 27,263 adolescent patients are currently registered within Oxfordshire and Buckinghamshire. The system has also proven to be an invaluable scientific resource as a platform for research into mood instability and as an electronic outcome measure in randomized controlled trials. This paper aimed to report on the existing applications of the system, setting out lessons learned, and to discuss the implications for tailored symptom monitoring, as well as the barriers to implementation at a larger scale.

Differential Diagnosis of Bipolar II Disorder and Borderline Personality Disorder

PURPOSE OF REVIEW

Differentiating bipolar (BP) disorders (in particular BP II) from borderline personality disorder (BPD) is a common diagnostic dilemma. We sought to critically examine recent studies that considered clinical differences between BP II and BPD, which might advance their delineation.

RECENT FINDINGS

Recent studies focused on differentiating biological parameters-genetics, epigenetics, diurnal rhythms, structural and functional neuroimaging-with indicative differences not yet sufficient to guide diagnosis. Key differentiating factors include family history, developmental antecedents, illness course, phenomenological differences in mood states, personality style and relationship factors. Less differentiating factors include impulsivity, neuropsychological profiles, gender distribution, comorbidity and treatment response. This review details parameters offering differentiation of BP II from BPD and should assist in resolving a frequent diagnostic dilemma. Future studies should specifically examine the BP II subtype directly with BPD, which would aid in sharpening the distinction between the disorders.

Machine learning and big data analytics in bipolar disorder: A position paper from the International Society for Bipolar Disorders Big Data Task Force

OBJECTIVES

The International Society for Bipolar Disorders Big Data Task Force assembled leading researchers in the field of bipolar disorder (BD), machine learning, and big data with extensive experience to evaluate the rationale of machine learning and big data analytics strategies for BD.

METHOD

A task force was convened to examine and integrate findings from the scientific literature related to machine learning and big data based studies to clarify terminology and to describe challenges and potential applications in the field of BD. We also systematically searched PubMed, Embase, and Web of Science for articles published up to January 2019 that used machine learning in BD.

RESULTS

The results suggested that big data analytics has the potential to provide risk calculators to aid in treatment decisions and predict clinical prognosis, including suicidality, for individual patients. This approach can advance diagnosis by enabling discovery of more relevant data-driven phenotypes, as well as by predicting transition to the disorder in high-risk unaffected subjects. We also discuss the most frequent challenges that big data analytics applications can face, such as heterogeneity, lack of external validation and replication of some studies, cost and non-stationary distribution of the data, and lack of appropriate funding.

CONCLUSION

Machine learning-based studies, including atheoretical data-driven big data approaches, provide an opportunity to more accurately detect those who are at risk, parse-relevant phenotypes as well as inform treatment selection and prognosis. However, several methodological challenges need to be addressed in order to translate research findings to clinical settings.

Using path signatures to predict a diagnosis of Alzheimer's disease

The path signature is a means of feature generation that can encode nonlinear interactions in data in addition to the usual linear terms. It provides interpretable features and its output is a fixed length vector irrespective of the number of input points or their sample times. In this paper we use the path signature to provide features for identifying people whose diagnosis subsequently converts to Alzheimer's disease. In two separate classification tasks we distinguish converters from 1) healthy individuals, and 2) individuals with mild cognitive impairment. The data used are time-ordered measurements of the whole brain, ventricles and hippocampus from the Alzheimer's Disease Neuroimaging Initiative (ADNI). We find two nonlinear interactions which are predictive in both cases. The first interaction is change of hippocampal volume with time, and the second is a change of hippocampal volume relative to the volume of the whole brain. While hippocampal and brain volume changes are well known in Alzheimer's disease, we demonstrate the power of the path signature in their identification and analysis without manual feature selection. Sequential data is becoming increasingly available as monitoring technology is applied, and the path signature method is shown to be a useful tool in the processing of this data.