搜索结果：NPP - digital psychiatry and neuroscience

Artificial intelligence (AI)-based computational tools for deriving digital behavioral markers are increasingly able to automatically detect clinically relevant patterns in mood and behavior through algorithmic analysis of continuously and passively collected data. The integration of these technologies into clinical care is imminent, most notably in clinical psychology and psychiatry but also other disciplines (e.g., cardiology, neurology, neurosurgery, pain management). Meanwhile, ethical guidelines for implementation are lacking, as are insights into what patients and caregivers want and need to know about these technologies to ensure acceptability and informed consent. In this work, we present qualitative findings from interviews with 40 adolescent patients and their caregivers examining ethical and practical considerations for translating these technologies into clinical care. We observed seven key domains (in order of salience) in stakeholders' informational needs: (1) clinical utility and value; (2) evidence, explainability, evaluation and contestation; (3) accuracy and trustworthiness; (4) data security, privacy, and misuse; (5) patient consent, control, and autonomy; (6) physician-patient relationship; and (7) patient safety, well-being, and dignity. Drawing from these themes, we provide a checklist of questions, as well as suggestions and key challenges, to help researchers and practitioners respond to what stakeholders want to know when integrating these technologies into clinical care and research. Our findings inform participatory approaches to co-designing treatment roadmaps for using these AI-based tools for enhanced patient engagement, acceptability and informed consent. This study examines what adolescent patients and their caregivers need to know when agreeing to AI-based digital tools that monitor behavior for mental health care. Interviews with 40 participants revealed key areas where patients and caregivers had questions, including data privacy, clinical benefits, and control over data. These insights help healthcare providers address patient concerns, improve understanding, and ensure informed consent as these technologies become more common in clinical settings.

Researchers and clinicians are increasingly looking to leverage artificial intelligence (AI) and digital tools to improve psychiatric care. Of particular promise is addressing the youth mental health crisis. Yet, the introduction of AI-enabled digital technologies for psychiatric treatment of young adults raises a host of ethical, legal, and societal issues (ELSI). To provide guidance in addressing these issues, we convened a two-day meeting at the Radcliffe Institute for Advanced Study at Harvard University: Advancing Neurotech Justice in Mental Health: Insights from an Interdisciplinary and Cross-Generational Workshop. The meeting brought together a diverse cohort of 17 experts and 5 students from various fields and different countries. In partnership with the MIT Critical Data team, the workshop engaged participants in an interactive Prompt-a-Thon to explore first-hand the potential benefits, biases, and harms related to the use of Large Language Model chatbots in mental health care. This Perspective reports on five principles of digital psychiatry deployment that the workshop participants determined to be the most essential: ensuring accuracy, remaining human-centric, promoting just access, protecting privacy, and providing transparency. We place these five principles within a "Neurotech Justice" framework and discuss how guardrails can be built to promote neurotech justice in digital psychiatry. This article presents findings from an interdisciplinary workshop focused on Neurotech Justice in youth digital mental health, addressing the ethical issues raised by the increasing use of AI-enabled tools to provide mental health services for young adults. Workshop participants, a mix of youth and experts, co-created a framework of five core principles to ensure equitable and ethical deployment: ensuring accuracy, remaining human-centric, promoting just access, protecting privacy, and providing transparency.

Mobile health (mHealth) tools can be used to deliver nonpharmacologic therapies to patients with migraine. However, mHealth studies often report poor treatment adherence. Neuroscience Education Therapy (NET), behavioral economics, and Digital Navigators have the potential to increase treatment adherence and thereby improve remote migraine self-management. We conducted a 6-month prospective pilot randomized controlled trial testing if a multi-component package of behavioral interventions increased treatment adherence among patients using one of two different mHealth migraine self-management programs (low-intensity program consisting only of a headache diary versus high-intensity program consisting of a headache diary and behavioral exercises). Our outcomes were the number of diary entries and behavioral exercises completed/week captured via back-end analytics of the mHealth application. We also compared our adherence data at 90-days (a secondary endpoint to assess the durability of the effect) with adherence data from similar published studies without the adherence-enhancing package. We enrolled 26 participants (n = 15 low intensity group, n = 11 high-intensity group). During the 6-week intervention period, we had a median of 7 headache diary entries/week in both groups and a median of 6 days/week of behavioral exercises in the high-intensity group. The rate of adherence with the adherence-enhancing package included was 2.9-8x higher compared to the median rates of the behavioral exercises to historical controls. With use of NET, behavioral economics, and digital navigators, participants achieved higher levels of adherence to both self-management programs compared to prior remote migraine self-management studies. Therefore, these tools may be beneficial to improving adherence to migraine self-management programs. Mobile health studies often face adherence and engagement issues. In this study, Neuroscience Education Therapy (NET), behavioral economics (BE), and Digital Navigators were used with the intention to increase adherence to a remote migraine self-management program.

The field of biological psychiatry faces a growing influx of digital biomarkers spanning self-report, social, behavioral, cognitive, and physiological indicators of various mental health conditions. However, the definition of "digital biomarker," particularly the "bio-" component, remains unclear. This article reviews the terminology of digital biomarkers in psychiatry and argues for the reservation of the term exclusively for measures of biological parameters with a plausible pathway connecting to the disease or condition of interest to enhance terminological clarity and consistency with conventional definitions of biomarker, short for biological marker. While the distinction between biological and non-biological parameters may blur at the edges, the Research Domain Criteria (RDoC) developed by the US National Institute of Mental Health offers a valuable heuristic. The RDoC distinguishes between biological (genes, molecules, cells, neural circuits, physiology) and non-biological (broadly understood behavior and self-report) units of analysis. Aligning digital biomarker definitions in psychiatry with the RDoC framework would mark a significant shift from the current broad usage, where almost any digitally measured characteristic, when used as an indicator, qualifies as a digital biomarker. This work explores the growing use of digital tools to track mental health, such as apps that measure behavior or physiology. It points out that the term "digital biomarker" is often used too broadly and argues it should only refer to biological data that can be directly linked to a mental health condition. By using a clearer definition, the field can better focus on meaningful indicators that align with biological psychiatry standards.

Psychophysiological variables-e.g., heart rate (HR), heart rate variability (HRV), and skin conductance response (SCR)-reflect autonomic nervous system functioning implicated in arousal, emotion (dys)regulation, and psychopathology. Psychophysiological variables can be leveraged to assess cognitive, social, and functional domains by overcoming subjective biases associated with self-, caregiver- and observer report. Psychophysiology can be measured across multiple contexts using various biosensing devices. Naturalistic biosensing can expand diverse participation in neurobiological research, by removing barriers of time and geographic distance required for lab-based assessments. Biosensing in clinical contexts also has the potential to provide peripheral physiological indicators of response to psychotherapeutic interventions. Measuring psychophysiology naturalistically and during psychotherapeutic sessions can elucidate mechanistic and causal processes. This Perspectives piece provides guideposts for scientists and practitioners to consider when selected biosensing devices/systems for clinical and research applications. Empirical evidence supporting the use of biosensors for valid and reliable psychophysiological signals-like electrodermal activity (EDA), photoplethysmography (PPG), and electrocardiography (ECG)-are reviewed in terms of the end-to-end user experience, accessibility of raw data, data quality, and data security. Finally, considerations of racial bias and variation related to biological sex in psychophysiological measures are discussed. The ultimate goal of this Perspectives piece is to inform expanded use of biosensing for the measurement of peripheral physiology to (1) improve understanding of naturalistic disease processes, (2) predict treatment response, (3) guide treatment progression, and (4) identify underlying treatment mechanisms for further refinement in clinical and research settings. This work explores the growing use of biosensing devices/systems to track changes in bodily states that may map onto mental health phenomena. It provides guidance for practical use of biosensors in research labs, treatment settings, and every day contexts. By providing fundamental guidance, the field can better focus on improving reliability and accuracy of biosensors while also considering user experience and diversity in design.

Ecological momentary assessment (EMA) is a tool facilitating the repeated collection of real-time data in naturalistic settings that can be applied to clinical research. Despite established methodological strengths, EMA protocols may be burdensome for participants, potentially leading to problems with adherence. Existing meta-analytic evidence is insufficient to inform the decision making of clinical researchers in using EMA in their work. In the current registered report, we address this need by conducting a systematic review with meta-analysis (1) examining adherence (enrollment, dropout, and compliance) in children and adolescents with psychological disorders and symptoms and (2) identifying aspects of study design that maximize adherence. In January 2023, we searched five databases for empirical EMA studies of youth (8-17 years) with psychological symptoms/diagnoses with data on adherence. We extracted data, assessed study quality, and conducted meta-analyses using random-effects models. We included 130 studies with 14,400 participants. On average, surveys contained 15 items, took over 3&#x2009;min to complete, and incorporated surveys with multiple response scale types delivered using smartphones/cell phones provided to participants. Meta-analyses revealed that study enrollment was moderate to high (82% in youth with psychopathology, 67% in community youth) and dropout prior to starting EMA protocols was low (<1-2%). Dropout during EMA protocols was 12% for youth with psychopathology and 8% for community youth, underscoring the importance of maintaining participant engagement throughout EMA studies. Compliance approximated the 80% field benchmark for healthy youth but was lower for youth from the community and with psychopathology. Participant characteristics (e.g., younger age) and design factors (e.g., incentive-based compensation) were associated with greater compliance in certain groups. Despite limitations (missing data, methodological constraints), findings have important implications for researchers developing and conducting pediatric EMA protocols. The stage 1 protocol for this Registered Report was accepted in principle on April 19, 2024. The protocol, as accepted by the journal, can be found at: https://doi.org/10.6084/m9.figshare.25732482.v1 . This research was supported by the Intramural Research Program (IRP) of the NIMH and the NIH Library's and Office of Research Service's support of the NIH IRP. Ecological momentary assessment (EMA) is a tool for collecting naturalistic, real-time data. We conducted a systematic review with meta-analysis examining adherence (enrollment, dropout, and compliance) in children and adolescents with psychological disorders and symptoms and aspects of study design that maximize adherence.

Social isolation and social impairment are hallmarks of progression as well as predictors of relapse in psychiatric disorders. We conducted a pilot study to assess the feasibility of sensing the social activity phenotype and loneliness using active and passive markers collected using a smartphone application. The study included 9 schizophrenia and bipolar disorder patients followed in the Bipolar Longitudinal study for at least 1 month and for whom mobile communication data was collected using the Beiwe smartphone application. Subjects completed daily surveys on digital and in-person social activity, and feelings of being outgoing or lonely. We described the level and variability of social activity features. We employed k-means clustering to identify "important contacts". Further, we investigated whether social network-derived features of mobile communication are independent predictors of weekly counts of outgoing calls and text, weekly average self-reported digital social activity, and loneliness using mixed effect models and clustering with dynamic time warping distance. Subjects were followed between 5 and 208 weeks (number of days of observation = 2538). The k-means cluster analysis approach identified the number of "important contacts" among close friends and family members as reported in clinical interviews. The cluster analysis and longitudinal regression analysis indicate that the number of individuals a person communicates with on their phone is an independent predictor of perceived loneliness, with stronger evidence when "important contacts" only are included. This study provides preliminary evidence that the number of "important contacts" a person communicates with on their phone is a promising marker to capture subjects' engagement in mobile communication activity and perceived loneliness. The work of Valeri et al. gives insights into the value of adopting of a social network perspective for digital phenotyping of social activity and loneliness using call and text data in SMI populations. Mobile communication network degree of &#x201c;important contacts&#x201c; inferred using a clustering approach is an independent predictor of self-reported loneliness and social activity.

We sought to evaluate the ability of automated speech and language features to longitudinally track fluctuations in the major psychosis domains: Thought Disorder, Negative Symptoms, and Positive Symptoms. Sixty-six participants with psychotic disorders were assessed soon after inpatient admission, at discharge, and at 3- and 6-months. Psychosis symptoms were measured with semi-structured interviews and standardized scales. Recordings were collected from paragraph reading, fluency, picture description, and open-ended tasks. Relationships between psychosis symptoms and 357 automated speech and language features were analyzed using a single component score and as individual features, using linear mixed models. We found that all three domains demonstrated significant longitudinal relationships with the single component score. Thought Disorder was particularly related to features describing more subordinated constructions, less efficient identification of picture elements, and decreased semantic distance between sentences. Negative Symptoms was related to features describing decreased speech complexity. Positive Symptoms domain score did not show relationships with individual features that survived p-value correction, but Suspiciousness was related to decreased use of nouns and Hallucinations was related to greater semantic distances. These relationships were largely robust to interactions with gender and race. Interactions with timepoint revealed variable relationships during different phases of illness (acute vs. stable). In summary, automated speech and language features show promise as scalable, objective markers of psychosis severity. Detailed attention to clinical setting and patient population is needed to optimize clinical translation. We used acoustic analysis and Natural Language Processing (NLP) to evaluate speech data from 66 individuals with psychosis, over time. The study identified specific language features that correlate with different psychosis symptoms as they changed over time. These insights could lead to innovative, non-invasive tools for monitoring schizophrenia and related disorders, enhancing personalized treatment approaches in psychiatry.

Individuals are increasingly utilizing large language model (LLM)-based tools for mental health guidance and crisis support in place of human experts. While AI technology has great potential to improve health outcomes, insufficient empirical evidence exists to suggest that AI technology can be deployed as a clinical replacement; thus, there is an urgent need to assess and regulate such tools. Regulatory efforts have been made and multiple evaluation frameworks have been proposed, however,field-wide assessment metrics have yet to be formally integrated. In this paper, we introduce a comprehensive online platform that aggregates evaluation approaches and serves as a dynamic online resource to simplify LLM and LLM-based tool assessment: MindBench.ai. At its core, MindBench.ai is designed to provide easily accessible/interpretable information for diverse stakeholders (patients, clinicians, developers, regulators, etc.). To create MindBench.ai, we built off our work developing MINDapps.org to support informed decision-making around smartphone app use for mental health, and expanded the technical MINDapps.org framework to encompass novel large language model (LLM) functionalities through benchmarking approaches. The MindBench.ai platform is designed as a partnership with the National Alliance on Mental Illness (NAMI) to provide assessment tools that systematically evaluate LLMs and LLM-based tools with objective and transparent criteria from a healthcare standpoint, assessing both profile (i.e. technical features, privacy protections, and conversational style) and performance characteristics (i.e. clinical reasoning skills). With infrastructure designed to scale through community and expert contributions, along with adapting to technological advances, this platform establishes a critical foundation for the dynamic, empirical evaluation of LLM-based mental health tools-transforming assessment into a living, continuously evolving resource rather than a static snapshot. AI chatbots powered by large language models are increasingly used for mental health support, yet they can give misleading or unsafe replies. To address this, our team created MindBench.ai, an open platform that helps patients, clinicians, researchers, and regulators evaluate AI systems transparently and consistently. Building on MINDapps.org, it profiles and benchmarks AI tools with metrics developed with NAMI, experts, and people with lived experience to ensure transparency, safety, and responsible use in mental health.

The integration of Large Language Models (LLMs) into mental healthcare and research heralds a potentially transformative shift, one offering enhanced access to care, efficient data collection, and innovative therapeutic tools. This paper reviews the development, function, and burgeoning use of LLMs in psychiatry, highlighting their potential to enhance mental healthcare through improved diagnostic accuracy, personalized care, and streamlined administrative processes. It is also acknowledged that LLMs introduce challenges related to computational demands, potential for misinterpretation, and ethical concerns, necessitating the development of pragmatic frameworks to ensure their safe deployment. We explore both the promise of LLMs in enriching psychiatric care and research through examples such as predictive analytics and therapy chatbots and risks including labor substitution, privacy concerns, and the necessity for responsible AI practices. We conclude by advocating for processes to develop responsible guardrails, including red teaming, multi-stakeholder oriented safety, and ethical guidelines/frameworks, to mitigate risks and harness the full potential of LLMs for advancing mental health.

Adolescent depression remains a major public health concern, and Behavioral Activation (BA),&#xa0;a brief therapeutic intervention designed to reduce depression-related avoidance and boost engagement in rewarding activities,&#xa0;has shown encouraging results. Still, few studies directly measure the hypothesized mechanism of "activation" in daily life, especially using low-burden, ecologically valid methods. This proof-of-concept study evaluates the validity of two technology-based approaches to measuring activation in adolescents receiving BA: smartphone-based mobility sensing and large language model (LLM) ratings of free-response text. Adolescents (n&#x2009;=&#x2009;38, ages 13-18) receiving 12-week BA therapy for anhedonia completed daily ecological momentary assessment (EMA) reporting on positive and negative affect. GPT-4o was used to rate behavioral activation from EMA free-text entries. A subsample (n&#x2009;=&#x2009;13) contributed passive smartphone sensing data (e.g., accelerometer activity, GPS-derived mobility). Activation and symptoms were assessed weekly via self-report. GPT-derived activation ratings correlated positively with passive sensing indicators (number of places visited, time away from home) and self-reported activation. Within-person increases in GPT-rated activation were associated with higher daily positive affect and lower negative affect. Passive sensing features also forecasted weekly improvements in anhedonia and depressive symptoms. Associations emerged primarily at the within-person level, suggesting that changes in activation relative to one's own baseline are clinically meaningful. This study demonstrates the feasibility and validity of passively measuring behavioral activation in adolescents' daily lives using smartphone data and LLMs. These tools hold promise for advancing data-informed psychotherapy by tracking therapeutic processes in real time, reducing reliance on self-report, and enabling personalized, adaptive interventions. Clinical Trial Registry: NCT02498925. Behavioral Activation therapy helps depressed teens by encouraging them to engage in more rewarding activities. We tested whether smartphones and LLM could automatically track this 'activation' in daily life. Using movement data from phones and LLM-based ratings from 38 teens in therapy, we found these digital tools accurately detected when teens were more active and higher activation predicted better mood and fewer depression symptoms. This technology could help therapists monitor progress in real-time and personalize treatment more effectively.

Linguistic hurdles in healthcare, such as complex language, significantly affect patient outcomes, including satisfaction with interaction, comprehension of healthcare materials, and engagement with the healthcare system. Reducing these hurdles has been a focus in healthcare delivery, as they significantly hinder patient engagement and adherence to treatments. The growing use of large language models (LLMs) in healthcare opens the possibility to reduce these linguistic hurdles. This study evaluates the ability of five prominent LLMs-GPT-3.5, GPT-4, GPT-4o, LLaMA-3, and Mistral-to simplify healthcare information to the standard recommended by the American Journal of Medicine. Our results indicate that while LLMs can approximate targeted reading levels, their outputs are inconsistent, with significant variability in reading level and deviation from the topic, making them unsuitable for deployment in healthcare settings. In this work we aim to see if public-facing healthcare materials can be simplified using Large Language Models (LLMs). Currently, the American Journal of Medicine recommends that healthcare materials be provided to people at a reading level of 6. In this work we take five state of the art LLMs viz. GPT-3.5, GPT-4, GPT-4o, LLaMA-3, and Mistral-7b and experiment with prompt engineering to see if these models can simplify healthcare materials from different sources such as academic venues, CDC and WHO releases or public releases from bodies like Mayo Clinic. We find significant variability, shown through large standard-deviations in the performance of LLMs. This work paves the pathway to develop and nurture better simplification and summarization pipelines in healthcare.

Psychiatric trials have some of the lowest success rates across therapeutic areas, resulting in decreased investment in psychopharmacological drug development even as the need for more effective treatments grows. Digital measures and digital biomarkers (DBMs) provide one potential avenue for ameliorating three of the largest problems impeding clinical trial success in psychiatry: diagnostic heterogeneity, endpoint subjectivity, and high placebo response rates. First, DBMs may address heterogeneity and comorbidity in psychiatric nosology by identifying predictive DBMs of treatment response via the targeting of drugs to psychiatric subtypes. Second, DBMs can provide objective measures of physiology and behavior that when grounded in meaningful aspects of health (MAH) could support use for regulatory decision-making. By objectively and continuously measuring aspects of a patient's disease that the patient wants to improve or prevent from getting worse, DBMs might provide clinical trial endpoints that are more sensitive to treatment effects as compared to traditional clinician-reported outcomes. Lastly, DBMs could help address challenges surrounding high placebo response rates. Development of predictive DBMs of placebo response may allow for improved enrichment study designs to reduce placebo response. Objective digital measures may also be more robust against the placebo effect and offer an improved study endpoint alternative. Successful deployment of DBMs to address the historical challenges facing psychiatric drug trials will require close collaboration between industry, academic, and regulatory partners. Psychiatric clinical trials fail at high rates, leading to less investment in new treatments despite the growing need for new innovations. Digital measures, such as data from wearable devices, offer a potential solution to core challenges in psychiatric trials. They could identify specific patient groups who may respond better to certain drugs, provide objective measurements of symptoms, and help resolve the impact of the placebo effect on trials.

Digital phenotyping uses data from smartphones and wearables to extract behavioural and biosocial markers of psychopathology in situ. Traditional entropy-based measures capture static system properties that neglect temporal dependencies critical to psychiatric phenomena. We propose a "dynamic" approach to the modelling of digital data capturing the time-varying aspects of processes of mental disorders. We defend that the resulting dynamic digital markers better capture variability in regulatory mechanisms of psychopathology. Digital phenotyping uses information from smartphones and wearable devices to track patterns in behavior and physiology related to mental health. Most current methods summarize this data in ways that miss how experiences change over time. We propose a new, dynamic approach that focuses on how patterns evolve moment by moment. By capturing these changes, our method aims to better reflect how mental disorders involve shifting and unstable processes of regulation in everyday life.

Researchers with lived experience (RWLE) of serious mental illness or substance use disorders (SMI/SUD) bring critical dual expertise to psychiatric neuroscience as both scientists and individuals directly affected by the conditions they study. Yet their participation and leadership remain profoundly limited by entrenched stigma, disclosure risks that can obstruct promising career trajectories, lack of mentorship from senior RWLE, and the absence of structural protections against discrimination and exclusion. These systemic barriers silence voices that can help transform the field's understanding of mental illness and its biological underpinnings. Drawing on the authors' lived and/or professional experiences, this Perspective challenges the assumption that lived experience introduces bias, reframing it as a source of empirical strength, innovation, and epistemic diversity. Here, the authors propose structural reforms to reshape admissions, mentorship, and leadership pathways. Centering RWLE is both a scientific necessity and an ethical imperative for advancing a more equitable and representative psychiatric neuroscience. Researchers who live with serious mental illness or substance use disorders bring unique insight to psychiatric neuroscience, yet they remain underrepresented in the field. This paper calls for recognizing and removing the barriers that limit their participation and leadership. Including these researchers strengthens the science, improves the relevance of the research to real-world needs, and helps to ensure that research about mental illness includes those who live it.

Operant behavior paradigms are essential in preclinical models of neuropsychiatric disorders, such as substance use disorders, enabling the study of complex behaviors including learning, salience, motivation, and preference. These tasks often involve repeated, time-resolved interactions over extended periods, producing large behavioral datasets with rich temporal structure. To support genome-wide association studies (GWAS), the Preclinical Addiction Research Consortium (PARC) has phenotyped over 3000 rats for oxycodone and cocaine addiction-like behaviors using extended access self-administration, producing over 100,000 data files. To manage, store, and process this data efficiently, we leveraged Dropbox, Microsoft Azure Cloud Services, and other widely available computational tools to develop a robust, automated data processing pipeline. Raw MedPC operant output files are automatically converted into structured Excel files using custom scripts, then integrated with standardized experimental, behavioral, and metadata spreadsheets, all uploaded from Dropbox into a relational SQL database on Azure. The pipeline enables automated quality control, data backups, daily summary reports, and interactive visualizations. This approach has dramatically improved PARC's high-throughput phenotyping capabilities by reducing human workload and error, while improving data quality, richness, and accessibility. We here share our approach, as these streamlined workflows can deliver benefits to operant studies of any scale, supporting more efficient, transparent, reproducible, and collaborative preclinical research. To uncover why some individuals are more vulnerable to addiction, the PARC rat GWAS and Biobank projects are testing thousands of rats, generating hundreds of thousands of behavioral data files. We created an automated system using Dropbox and Microsoft Azure to organize, store, and visualize these data. This pipeline reduces errors, saves time, and improves sharing, enabling large-scale, high-quality behavioral studies in preclinical models.

The transition from trainee to principal investigator represents a major inflection point in an academic research career. While doctoral and postdoctoral training programs provide extensive preparation in experimental design, data analysis, and scientific communication, far less attention is devoted to the practical responsibilities associated with launching and managing an independent research laboratory. Early career investigators must rapidly develop skills in leadership, personnel management, infrastructure planning, and strategic funding development while simultaneously establishing their scientific identity. These challenges have intensified in the modern digital era, as research programs increasingly rely on sophisticated data management systems, collaborative technologies, and interdisciplinary networks. In this Perspective, I discuss several practical considerations that shape the early development of independent research laboratories, including research program design, startup planning, team leadership, collaborative partnerships, and strategic funding trajectories. By highlighting common challenges and lessons learned during the transition to independence, this article aims to help demystify the process of launching a research laboratory and to support early career investigators as they build sustainable scientific programs. Starting a research lab is a major career transition, but scientists often receive little training in how to manage teams, resources, and collaborations. This article shares practical insights on building a successful lab, including planning research, leading teams, and navigating funding in a digital and collaborative environment. By making these often-hidden challenges more visible, the work aims to better prepare early career scientists for independence and long-term success.

Social isolation is a major public health concern linked to increased risk for both psychiatric and physical health conditions. Yet despite the potential consequences of social isolation, our understanding of its nature and how it emerges and evolves over time remains limited. We propose that social isolation should be understood and analyzed as a complex dynamical system. First, we introduce core principles of dynamical systems theory and describe how they can be applied to better understand social isolation. Second, we formalize a dynamical systems model using differential equations. Third, we present simulations based on the differential equations showing how changes in system dynamics may increase or decrease the likelihood of individuals entering a state of social isolation. Fourth, we provide a brief simulation-recovery analysis demonstrating model parameter identifiability from intensive longitudinal data designs. Finally, we offer a simulated example of how intensive longitudinal data could be used to identify signs of transitions between healthy and isolated states. Overall, this framework, both theoretical and computational, helps elucidate the dynamic nature of social isolation and may ultimately inform empirical research and personalized interventions capable of identifying those at risk for transitioning into a state of isolation. Social isolation, or having objectively few social relationships, is associated with psychiatric and physical health problems. However, it is unclear how social isolation develops in an individual. Here, we propose a theoretical and computational framework that aims to study how social isolation develops and changes over time. Ultimately, this framework may be able to help identify who is socially isolated and how, when, and why individuals transition into a chronic state of isolation.

Typing behaviour derived from smartphone keystroke metadata is an emerging digital phenotype that may assist in diagnosing and monitoring depressive symptoms. While psychomotor agitation and slowing have been hypothesised as depressive symptoms that may influence typing behaviour, no studies have directly tested this assumption. Here, we tested whether specific depressive symptoms were associated with various keystroke features of typing behaviour in adolescents. Adolescents from an Australian cohort study (n&#x2009;=&#x2009;895) completed a typing task on their smartphones. Common features of keystroke timing (i.e., median, dwell, interval, latency, down-down time, and up-up time) and frequency (i.e., total keystrokes, backspaces, spaces, backspace ratio, and spaces ratio) were extracted. Depressive symptoms were assessed using the Patient Health Questionnaire-Adolescent version (PHQ-A). Multiple linear regression models were used to test associations between symptom items and keystroke features. Non-linear effects and moderating effects of sex were also explored. Psychomotor symptoms (i.e., PHQ-A item 8) were not associated with keystroke timing or frequency. However, higher appetite symptoms (i.e., PHQ-A item 5) were associated with faster down-down time and a greater number of total key presses. Symptoms of anhedonia (i.e., PHA item 1) showed non-linear associations with keystroke features. The results do not support a relationship between psychomotor symptoms and typing behaviour in adolescents. However, appetite-related symptoms were associated with faster and more frequent typing. Further research into the relationship between typing behaviour and mental health in young people is warranted. Clinical Trial Registry: ACTRN12619000855123. We examined whether teenagers' smartphone typing behaviours could reflect specific depressive symptoms. Contrary to expectations, we found no link between typing patterns and psychomotor changes, like agitation or slowing. Interestingly, adolescents experiencing increased appetite typed faster and pressed more keys, while symptoms of anhedonia showed complex associations. These findings suggest smartphone typing patterns might offer a useful tool for understanding and monitoring particular depression symptoms in young people.