Natural Language Processing Methods and Bipolar Disorder: Scoping Review

Artificial intelligence in cardiovascular practice

ABSTRACT

Artificial intelligence (AI) is everywhere, but how is this expansive technology being used in cardiovascular care? This article explores common AI models, how they are transforming healthcare delivery, and important roles for clinicians, including advanced practice providers, in the development, adoption, evaluation, and ethical use of AI in cardiovascular care.

Artificial intelligence in cardiovascular practice

ABSTRACT

Artificial intelligence (AI) is everywhere, but how is this expansive technology being used in cardiovascular care? This article explores common AI models, how they are transforming healthcare delivery, and important roles for clinicians, including advanced practice providers, in the development, adoption, evaluation, and ethical use of AI in cardiovascular care.

Acoustic and Natural Language Markers for Bipolar Disorder: A Pilot, mHealth Cross-Sectional Study

Background

Monitoring symptoms of bipolar disorder (BD) is a challenge faced by mental health services. Speech patterns are crucial in assessing the current experiences, emotions, and thought patterns of people with BD. Natural language processing (NLP) and acoustic signal processing may support ongoing BD assessment within a mobile health (mHealth) framework.

Objective

Using both acoustic and NLP-based features from the speech of people with BD, we built an app-based tool and tested its feasibility and performance to remotely assess the individual clinical status.

Methods

We carried out a pilot, observational study, sampling adults diagnosed with BD from the caseload of the Nord Milano Mental Health Trust (Italy) to explore the relationship between selected speech features and symptom severity and to test their potential to remotely assess mental health status. Symptom severity assessment was based on clinician ratings, using the Young Mania Rating Scale (YMRS) and Montgomery-Åsberg Depression Rating Scale (MADRS) for manic and depressive symptoms, respectively. Leveraging a digital health tool embedded in a mobile app, which records and processes speech, participants self-administered verbal performance tasks. Both NLP-based and acoustic features were extracted, testing associations with mood states and exploiting machine learning approaches based on random forest models.

Results

We included 32 subjects (mean [SD] age 49.6 [14.3] years; 50% [16/32] females) with a MADRS median (IQR) score of 13 (21) and a YMRS median (IQR) score of 5 (16). Participants freely managed the digital environment of the app, without perceiving it as intrusive and reporting an acceptable system usability level (average score 73.5, SD 19.7). Small-to-moderate correlations between speech features and symptom severity were uncovered, with sex-based differences in predictive capability. Higher latency time (ρ=0.152), increased silences (ρ=0.416), and vocal perturbations correlated with depressive symptomatology. Pressure of speech based on the mean intraword time (ρ=-0.343) and lower voice instability based on jitter-related parameters (ρ ranging from -0.19 to -0.27) were detected for manic symptoms. However, a higher contribution of NLP-based and conversational features, rather than acoustic features, was uncovered, especially for predictive models for depressive symptom severity (NLP-based: R2=0.25, mean squared error [MSE]=110.07, mean absolute error [MAE]=8.17; acoustics: R2=0.11, MSE=133.75, MAE=8.86; combined: R2=0.16; MSE=118.53, MAE=8.68).

Conclusions

Remotely collected speech patterns, including both linguistic and acoustic features, are associated with symptom severity levels and may help differentiate clinical conditions in individuals with BD during their mood state assessments. In the future, multimodal, smartphone-integrated digital ecological momentary assessments could serve as a powerful tool for clinical purposes, remotely complementing standard, in-person mental health evaluations.

Applications of Large Language Models in the Field of Suicide Prevention: Scoping Review

BACKGROUND

Prevention of suicide is a global health priority. Approximately 800,000 individuals die by suicide yearly, and for every suicide death, there are another 20 estimated suicide attempts. Large language models (LLMs) hold the potential to enhance scalable, accessible, and affordable digital services for suicide prevention and self-harm interventions. However, their use also raises clinical and ethical questions that require careful consideration.

OBJECTIVE

This scoping review aims to identify emergent trends in LLM applications in the field of suicide prevention and self-harm research. In addition, it summarizes key clinical and ethical considerations relevant to this nascent area of research.

METHODS

Searches were conducted in 4 databases (PsycINFO, Embase, PubMed, and IEEE Xplore) in February 2024. Eligible studies described the application of LLMs for suicide or self-harm prevention, detection, or management. English-language peer-reviewed articles and conference proceedings were included, without date restrictions. Narrative synthesis was used to synthesize study characteristics, objectives, models, data sources, proposed clinical applications, and ethical considerations. This review adhered to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) standards.

RESULTS

Of the 533 studies identified, 36 (6.8%) met the inclusion criteria. An additional 7 studies were identified through citation chaining, resulting in 43 studies for review. The studies showed a bifurcation of publication fields, with varying publication norms between computer science and mental health. While most of the studies (33/43, 77%) focused on identifying suicide risk, newer applications leveraging generative functions (eg, support, education, and training) are emerging. Social media was the most common source of LLM training data. Bidirectional Encoder Representations from Transformers (BERT) was the predominant model used, although generative pretrained transformers (GPTs) featured prominently in generative applications. Clinical LLM applications were reported in 60% (26/43) of the studies, often for suicide risk detection or as clinical assistance tools. Ethical considerations were reported in 33% (14/43) of the studies, with privacy, confidentiality, and consent strongly represented.

CONCLUSIONS

This evolving research area, bridging computer science and mental health, demands a multidisciplinary approach. While open access models and datasets will likely shape the field of suicide prevention, documenting their limitations and potential biases is crucial. High-quality training data are essential for refining these models and mitigating unwanted biases. Policies that address ethical concerns-particularly those related to privacy and security when using social media data-are imperative. Limitations include high variability across disciplines in how LLMs and study methodology are reported. The emergence of generative artificial intelligence signals a shift in approach, particularly in applications related to care, support, and education, such as improved crisis care and gatekeeper training methods, clinician copilot models, and improved educational practices. Ongoing human oversight-through human-in-the-loop testing or expert external validation-is essential for responsible development and use.

TRIAL REGISTRATION

OSF Registries osf.io/nckq7; https://osf.io/nckq7.

College students' mental health evaluation model based on tensor fusion network with multimodal data during the COVID-19 pandemic

The COVID-19 pandemic has caused a series of effects on the mental health of college students, especially long-term home isolation or online learning, which has caused college students to have both academic pressure and employment pressure. How to accurately and effectively assess the mental health status of college students has become a research hotspot. Traditional methods based on questionnaires such as Self-Rating Depression Scale (SDS) and Self-Rating Anxiety Scale (SAS) are difficult to collect data and have poor evaluation accuracy. This paper analyzes the psychological state through text-images of multi-modal data with tensor fusion networks and constructs a mental health assessment model for college students. First, the validity of the model is verified through the MVSA (Multi-View Sentiment Analysis) dataset. Second, the psychological state of college students under the epidemic is analyzed using the collected text-images dataset. The results show that the TFN-MDA (Tensor Fusion Network-Multimodal Data Analysis) based mental health assessment model constructed in this paper can effectively assess the mental health status of college students, with an average accuracy of more than 70%.

Self-Administered Interventions Based on Natural Language Processing Models for Reducing Depressive and Anxiety Symptoms: Systematic Review and Meta-Analysis

BACKGROUND

The introduction of natural language processing (NLP) technologies has significantly enhanced the potential of self-administered interventions for treating anxiety and depression by improving human-computer interactions. Although these advances, particularly in complex models such as generative artificial intelligence (AI), are highly promising, robust evidence validating the effectiveness of the interventions remains sparse.

OBJECTIVE

The aim of this study was to determine whether self-administered interventions based on NLP models can reduce depressive and anxiety symptoms.

METHODS

We conducted a systematic review and meta-analysis. We searched Web of Science, Scopus, MEDLINE, PsycINFO, IEEE Xplore, Embase, and Cochrane Library from inception to November 3, 2023. We included studies with participants of any age diagnosed with depression or anxiety through professional consultation or validated psychometric instruments. Interventions had to be self-administered and based on NLP models, with passive or active comparators. Outcomes measured included depressive and anxiety symptom scores. We included randomized controlled trials and quasi-experimental studies but excluded narrative, systematic, and scoping reviews. Data extraction was performed independently by pairs of authors using a predefined form. Meta-analysis was conducted using standardized mean differences (SMDs) and random effects models to account for heterogeneity.

RESULTS

In all, 21 articles were selected for review, of which 76% (16/21) were included in the meta-analysis for each outcome. Most of the studies (16/21, 76%) were recent (2020-2023), with interventions being mostly AI-based NLP models (11/21, 52%); most (19/21, 90%) delivered some form of therapy (primarily cognitive behavioral therapy: 16/19, 84%). The overall meta-analysis showed that self-administered interventions based on NLP models were significantly more effective in reducing both depressive (SMD 0.819, 95% CI 0.389-1.250; P<.001) and anxiety (SMD 0.272, 95% CI 0.116-0.428; P=.001) symptoms compared to various control conditions. Subgroup analysis indicated that AI-based NLP models were effective in reducing depressive symptoms (SMD 0.821, 95% CI 0.207-1.436; P<.001) compared to pooled control conditions. Rule-based NLP models showed effectiveness in reducing both depressive (SMD 0.854, 95% CI 0.172-1.537; P=.01) and anxiety (SMD 0.347, 95% CI 0.116-0.578; P=.003) symptoms. The meta-regression showed no significant association between participants' mean age and treatment outcomes (all P>.05). Although the findings were positive, the overall certainty of evidence was very low, mainly due to a high risk of bias, heterogeneity, and potential publication bias.

CONCLUSIONS

Our findings support the effectiveness of self-administered NLP-based interventions in alleviating depressive and anxiety symptoms, highlighting their potential to increase accessibility to, and reduce costs in, mental health care. Although the results were encouraging, the certainty of evidence was low, underscoring the need for further high-quality randomized controlled trials and studies examining implementation and usability. These interventions could become valuable components of public health strategies to address mental health issues.

TRIAL REGISTRATION

PROSPERO International Prospective Register of Systematic Reviews CRD42023472120; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023472120.

Use of Machine Learning Tools in Evidence Synthesis of Tobacco Use Among Sexual and Gender Diverse Populations: Algorithm Development and Validation

BACKGROUND

From 2016 to 2021, the volume of peer-reviewed publications related to tobacco has experienced a significant increase. This presents a considerable challenge in efficiently summarizing, synthesizing, and disseminating research findings, especially when it comes to addressing specific target populations, such as the LGBTQ+ (lesbian, gay, bisexual, transgender, queer, intersex, asexual, Two Spirit, and other persons who identify as part of this community) populations.

OBJECTIVE

In order to expedite evidence synthesis and research gap discoveries, this pilot study has the following three aims: (1) to compile a specialized semantic database for tobacco policy research to extract information from journal article abstracts, (2) to develop natural language processing (NLP) algorithms that comprehend the literature on nicotine and tobacco product use among sexual and gender diverse populations, and (3) to compare the discoveries of the NLP algorithms with an ongoing systematic review of tobacco policy research among LGBTQ+ populations.

METHODS

We built a tobacco research domain-specific semantic database using data from 2993 paper abstracts from 4 leading tobacco-specific journals, with enrichment from other publicly available sources. We then trained an NLP model to extract named entities after learning patterns and relationships between words and their context in text, which further enriched the semantic database. Using this iterative process, we extracted and assessed studies relevant to LGBTQ+ tobacco control issues, further comparing our findings with an ongoing systematic review that also focuses on evidence synthesis for this demographic group.

RESULTS

In total, 33 studies were identified as relevant to sexual and gender diverse individuals' nicotine and tobacco product use. Consistent with the ongoing systematic review, the NLP results showed that there is a scarcity of studies assessing policy impact on this demographic using causal inference methods. In addition, the literature is dominated by US data. We found that the product drawing the most attention in the body of existing research is cigarettes or cigarette smoking and that the number of studies of various age groups is almost evenly distributed between youth or young adults and adults, consistent with the research needs identified by the US health agencies.

CONCLUSIONS

Our pilot study serves as a compelling demonstration of the capabilities of NLP tools in expediting the processes of evidence synthesis and the identification of research gaps. While future research is needed to statistically test the NLP tool's performance, there is potential for NLP tools to fundamentally transform the approach to evidence synthesis.

Natural Language Processing for Smart Healthcare

Smart healthcare has achieved significant progress in recent years. Emerging artificial intelligence (AI) technologies enable various smart applications across various healthcare scenarios. As an essential technology powered by AI, natural language processing (NLP) plays a key role in smart healthcare due to its capability of analysing and understanding human language. In this work, we review existing studies that concern NLP for smart healthcare from the perspectives of technique and application. We first elaborate on different NLP approaches and the NLP pipeline for smart healthcare from the technical point of view. Then, in the context of smart healthcare applications employing NLP techniques, we introduce representative smart healthcare scenarios, including clinical practice, hospital management, personal care, public health, and drug development. We further discuss two specific medical issues, i.e., the coronavirus disease 2019 (COVID-19) pandemic and mental health, in which NLP-driven smart healthcare plays an important role. Finally, we discuss the limitations of current works and identify the directions for future works.

Application and Potential of Artificial Intelligence in Heart Failure: Past, Present, and Future

The prevalence of heart failure (HF) is increasing, necessitating accurate diagnosis and tailored treatment. The accumulation of clinical information from patients with HF generates big data, which poses challenges for traditional analytical methods. To address this, big data approaches and artificial intelligence (AI) have been developed that can effectively predict future observations and outcomes, enabling precise diagnoses and personalized treatments of patients with HF. Machine learning (ML) is a subfield of AI that allows computers to analyze data, find patterns, and make predictions without explicit instructions. ML can be supervised, unsupervised, or semi-supervised. Deep learning is a branch of ML that uses artificial neural networks with multiple layers to find complex patterns. These AI technologies have shown significant potential in various aspects of HF research, including diagnosis, outcome prediction, classification of HF phenotypes, and optimization of treatment strategies. In addition, integrating multiple data sources, such as electrocardiography, electronic health records, and imaging data, can enhance the diagnostic accuracy of AI algorithms. Currently, wearable devices and remote monitoring aided by AI enable the earlier detection of HF and improved patient care. This review focuses on the rationale behind utilizing AI in HF and explores its various applications.

Ethical Implications of the Use of Language Analysis Technologies for the Diagnosis and Prediction of Psychiatric Disorders

Recent developments in artificial intelligence technologies have come to a point where machine learning algorithms can infer mental status based on someone's photos and texts posted on social media. More than that, these algorithms are able to predict, with a reasonable degree of accuracy, future mental illness. They potentially represent an important advance in mental health care for preventive and early diagnosis initiatives, and for aiding professionals in the follow-up and prognosis of their patients. However, important issues call for major caution in the use of such technologies, namely, privacy and the stigma related to mental disorders. In this paper, we discuss the bioethical implications of using such technologies to diagnose and predict future mental illness, given the current scenario of swiftly growing technologies that analyze human language and the online availability of personal information given by social media. We also suggest future directions to be taken to minimize the misuse of such important technologies.

Social Media Use and Well-being With Bipolar Disorder During the COVID-19 Pandemic: Path Analysis

Background

Reliable and consistent social support is associated with the mental health and well-being of persons with severe mental illness, including bipolar disorder (BD). Yet the COVID-19 pandemic and associated social distancing measures (eg, shelter in place) reduced access to regular social contacts, while social media use (SMU) increased concomitantly. Little is currently known about associations between the well-being of adults with BD and different types of SMU (eg, passive and active).

Objective

For this study, we had two goals. First, we report descriptive information regarding SMU by persons with BD during COVID-19 (all platforms). Specific to Facebook, we next developed and tested a hypothesized model to identify direct and indirect associations between BD symptoms, social support, loneliness, life satisfaction, and SMU. Responses were collected during the global spread of the Delta variant and prior/concurrent with the Omicron variant, 20 months after the World Health Organization declared COVID-19 a global pandemic.

Methods

Over 8 weeks, we obtained responses from an international sample of 102 adults with BD using the Qualtrics online platform. Most had previously participated in the BADAS (Bipolar Affective Disorders and older Adults) Study (n=89, 87.3%); the remainder were recruited specifically for this research (n=13, 2.7%). The subsamples did not differ in age (t₁₀₀=1.64; P=.10), gender (χ²₂=0.2; P=.90), socioeconomic status (χ²₆=9.9; P=.13), or time since BD diagnosis (t₉₇=1.27; P=.21). Both were recruited using social media advertising micro-targeted to adults with BD. On average, participants were 53.96 (SD 13.22, range 20-77) years of age, they had completed 15.4 (SD 4.28) years of education, and were diagnosed with BD 19.6 (SD 10.31) years ago. Path analyses were performed to develop and test our hypothesized model.

Results

Almost all participants (n=95, 93.1%) reported having both Facebook and LinkedIn accounts; 91.2% (n=93) reported regular use of either or both. During the pandemic, most (n=62, 60.8%) reported accessing social media several times a day; 36.3% (n=37) reported using social media more often since the emergence of COVID-19. Specific to Facebook, the model we hypothesized differed somewhat from what emerged. The resulting model suggests that symptoms of depression predict loneliness and, inversely, social support and life satisfaction. Social support predicts social Facebook use, whereas passive Facebook use predicts life satisfaction. Symptoms of depression emerged as indirect predictors of SMU via social support.

Conclusions

Our findings suggest that the operational definition of passive-active SMU requires further analysis and refinement. In contrast to theory, passive Facebook use appears positively associated with well-being among certain populations. Longitudinal data collection over multiple points is required to identify associations between BD symptoms, SMU, and well-being over time.