NCNicholas Cummins

Nicholas Cummins

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Nicholas Cummins has a total of 364 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Remote Measurement of Sleep and Physical Activity for Depression Severity Prediction: A Machine Learning Study (Preprint)

    by Carolin Oetzmann, Nicholas Cummins, Ewan Carr, Yuezhou Zhang, Faith Matcham, Sara Siddi, Femke Lamers, Daniel Leightley, Katie M White, Amos A Folarin, et al.

    BACKGROUND Remote measurement technologies (RMTs) offer a potential solution for monitoring depression symptoms in situ while reducing reliance on self-report assessments. Sleep and physical activity measures derived from wearable devices may capture behavioural patterns relevant to depressions severity, but their incremental value for predicting current depression severity remains unclear. OBJECTIVE To evaluate the predictive value of wearable-derived sleep and physical activity measures for current depression severity, and to determine whether RMT-derived behavioural subtypes improve prediction compared with individual RMT features and baseline sociodemographic and clinical characteristics. METHODS Longitudinal data from the Remote Assessment of Disease and Relapse in Major Depressive Disorder (RADAR-MDD) cohort were used to predict three-monthly depression severity, at three to 36-months of follow-up, measured using the Inventory of Depressive Symptomatology- Self Report. Elastic net and random forest models were compared across different combinations of baseline individual characteristics, individual sleep and physical activity RMT features, and RMT-derived behavioural subtypes. RMT features were derived from data collected during the seven days preceding each IDS-SR assessment. Behavioural subtypes were previously derived from these longitudinal RMT data using a Hidden Markov model, which estimated participants’ subtype membership probabilities at each timepoint. Prediction models were evaluated using nested group five-fold cross-validation and assessed using root mean square error, R2 and mean absolute error. RESULTS Models including baseline depression severity achieved R2 values of approximately 0.6, with RMSE of approximately 10 and MAE of 8. Adding individual RMT features of RMT-derived subtypes provided little improvement in predictive performance. Excluding baseline depression severity reduced R2 to approximately 0.1, while RMSE increased to approximately 15 and MAE to 12, demonstrating the substantial contribution of baseline depression severity to predictive performance. CONCLUSIONS Wearable-derived sleep and physical activity measures and their behavioural subtypes provided limited additional predictive value for current depression severity beyond baseline individual characteristics, particularly baseline depression severity. Although these measures did not substantially improve prediction in the present models, they may still capture complementary behavioural information relevant to understanding depression.

  • Open Access

    Sleep and Activity Patterns in Depression From Wearable Data: Unsupervised Clustering Study

    by Carolin Oetzmann, Yuezhou Zhang, Nicholas Cummins, Ewan Carr, Faith Matcham, Sara Siddi, Femke Lamers, Daniel Leightley, Katie M White, Amos A Folarin, et al.

    Background: Efforts to advance our understanding of depression have long been constrained by the disorder’s vast symptom heterogeneity and by the reliance on self-report, which offers only a partial view of phenotypic expression. Digital phenotyping provides an opportunity to address these core challenges by generating real-time, objective data on behavior and physiology, offering new perspectives on understanding depression phenotypes. Yet, prior efforts to identify such objectively derived subtypes have relied on predefined diagnostic labels or supervised models, limiting discovery to existing clinical categories. Objective: This study aimed to identify subtypes of depression based on objective sleep and activity data using an unsupervised learning method and to explore how participants transition between these subtypes over time. Methods: We analyzed longitudinal Fitbit data from 623 participants with recurrent depression enrolled in the Remote Assessment of Disease and Relapse in Major Depressive Disorder study. To identify our subtypes, we applied Gaussian mixture models and hidden Markov models, incorporating a thorough model selection approach that combined grouped cross-validation and seed selection to ensure robustness. Results: Three activity subtypes (high, light, and low activity) and 4 sleep subtypes (efficient early sleepers, efficient late sleepers, disrupted sleepers, and variable late sleepers) were consistently identified. These subtypes align with known associations between depression and behavioral patterns. Transition modeling revealed stability within individuals over follow-up, further suggesting the presence of behavioral phenotypes rather than momentary fluctuations. Conclusions: The results demonstrate that wearable-derived features can identify reproducible and clinically relevant behavioral subtypes of sleep and activity in individuals with major depressive disorder. These subtypes reflect known behavioral correlates of depression and may offer a data-driven framework for reducing phenotypic heterogeneity, improving research stratification, and supporting personalized patient monitoring. Further work is needed to validate these findings in independent cohorts and evaluate their potential use in reducing noise when using sleep or activity data to predict depression outcomes.

  • Open Access

    Digital biomarkers from “video selfies” improve prediction of mental health: Results from a multimodal ecological momentary assessment study

    by Hadley Rahrig, Matthew Kaharudin, Nicole Hendry, Yogesh Prabhu, Naihao Xu, Simon Goldberg, Vikas Singh, Nathan J. Vack, Stuti Shrivastava, Robin Goldman, et al.

    Personal digital devices are transforming mental health assessment. Leveraging the ubiquity of smartphones and public familiarity with smartphone-recorded “selfies,” we developed a novel “video selfie” ecological momentary assessment, and tested the utility of digital biomarkers to improve prediction of mental health and well-being in a sample of non-clinical participants. Our video selfie paradigm yielding 71,902 videos (N = 1,634 participants) demonstrated high feasibility, indicated by high adherence (77% mean response rate) and high video quality with 92% of recordings meeting quality criteria. We show that video selfies demonstrate incremental validity beyond conventional self-report ecological momentary assessment, with video-based multimodal features collectively improving model performance for predicting concurrent NIH PROMIS scores for anxiety and depression and flourishing (Flourishing Index) (5.2%-7.0%). This research lays the groundwork for methodological innovation that advances mental health and well-being “in-the-wild” and at scale. Future applications include the integration of video-based data streams to improve time-sensitive delivery of digitally-mediated mental health interventions.

  • Open Access

    A pilot study on AI-based voice analysis for monitoring patients hospitalized with acute decompensated heart failure

    by Leonhard Riehle, Mariam Fouad, Marcus Hott, Emanuel Heil, Chong Bin Lee, Felix Schoenrath, Soumya Vungarala, Bruce Johnson, Lyle Olson, Aurele Goetz, et al.

    Aims: Monitoring pulmonary congestion in chronic heart failure (HF) reduces decompensation and hospitalization, but conventional methods such as weight and symptom tracking are often unreliable. As fluid accumulation affects the lungs and vocal tract, subtle voice alterations may serve as a non-invasive signal for early detection of worsening HF. Methods and results: The Voice Analysis for Monitoring Patients with HF trial (VAMP-HF, NCT06566911) prospectively enrolled 104 patients hospitalized with acute decompensated HF (ADHF) across two academic centres in the USA and Germany. Daily voice recordings were collected from admission to discharge, with breathing features extracted from speech and acoustic features from sustained vowels. A machine-learning model was trained to classify recordings as admission-phase vs. discharge-phase using leave-one-patient-out. Patients with clinical deterioration, insufficient audio quality, or short length of stay were excluded. Seventy-nine patients were included in the final dataset. The model classified admission and discharge with an F1-score of 0.83 (95% CI: 0.77–0.90; AUC = 0.90). In patients with higher audio volume (N = 54), performance reached 0.89 (95% CI: 0.82–0.94; AUC = 0.91). When applied to intermediate hospitalization days, model-predicted scores showed progressive increases from admission towards discharge. Performance remained robust irrespective of significant weight loss during hospitalization. Conclusion: In this pilot study, structured voice and breathing analysis discriminated hospitalization phase from admission through discharge in patients with ADHF. This non-invasive approach captured progressive changes during the hospital course and warrants further investigation with concurrent objective congestion markers to establish physiological specificity.


  • Open Access

    Technology matters: AI ‐driven tools in children's mental healthcare: perspectives from young people and parents

    by Zoë Firth, Christine Aicardi, Stephen Oram, Nicholas Cummins, Alice Wickersham, Helen L. Fisher, Johnny Downs

    Artificial intelligence may be able to improve the efficiency, accuracy and predictiveness of mental health assessments, and public perspectives are crucial to ensuring these tools are implemented with fairness and accountability. We developed an artificial intelligence‐driven tool to automatically analyse parents' speech data, which if successful could be implemented in children and young people's mental health assessments. To engage stakeholders with this project, we worked with a science fiction writer to produce two stories about possible futures of our tool, which we discussed in workshops with young people and parents. Here, we summarise key themes arising from this novel method of engaging the public in mental health research, and highlight considerations for clinicians and researchers creating novel technologies for children and young people's mental healthcare.


  • Open Access

    Consensus-Based Definitions for Vocal Biomarkers: The International VOCAL Initiative

    by Megane Pizzimenti, Ayush Kalia, Jamie A Toghranegar, Mohamed Ebraheem, Nicholas Cummings, Satrajit S. Ghosh, James T. Anibal, Rhoda Au, Arian Azarang, Ruth H. Bahr, et al.

    Importance: Voice-based health technologies are growing rapidly, but they lack standardized terminology, which hinders interdisciplinary collaboration, research quality, and clinical translation. Objective: The objective of this work is to develop universally accepted definitions in the rapidly evolving field of vocal biomarkers, as part of the VOCAL ( V ocal Biomarker Guidelines for O ntology, C lassification, A pplication, and L ogistics) initiative, a structured, international consensus-based framework that aims to provide standards, and guidelines. Design: VOCAL is a rigorous, international, multi-stage consensus-building study conducted in 2024-2025. Setting: Multi-institutional collaboration between representatives from the Bridge2AI-Voice Consortium (North America) and the eVoiceNet Network (European Union), culminating in an in-person workshop at the 2025 Bridge2AI Voice Symposium. Participants: A group of 24 international experts in medicine, clinical research, speech and language, audio signal processing, statistics, methodology, regulation, ethics. Methods: VOCAL’s iterative process involved five rounds of review, feedback, and an in-person workshop at the international 2025 Bridge2AI Voice Symposium, ensuring the incorporation of diverse perspectives and achieving a robust agreement on the proposed definitions. Main outcomes and measures: Consensus-based definitions for vocal biomarkers, spanning from broad concepts (biomarker, digital biomarker, vocal biomarker) to domain-specific measures (cardio-respiratory acoustic, voice, speech/articulatory, cognitive/language). Results: A hierarchical continuum model of vocal biomarkers was established. We first distinguished between the concepts of vocal measures and vocal biomarkers. We then defined terms from broad, overarching concepts (Level 0: Biomarker, Digital Biomarker, Vocal Biomarker) to more specific physiological and cognitive domains (Level 1: Cardio-Respiratory Acoustic; Level 2: Voice; Level 3: Speech/Articulatory; Level 4: Cognitive/Language, including linguistic and paralinguistic subtypes). Conclusions and Relevance: This work provides a shared vocabulary that is essential for fostering communication through interdisciplinary collaboration, improving the quality and efficiency of research and development, and ensuring the ethical, reliable, and scalable deployment of future voice-based health technologies. It lays foundational groundwork for upcoming guidelines and standards, which are crucial for advancing the field of vocal biomarkers into widespread clinical utility. Key points: Question: Can we establish an international consensus on the definitions related to vocal biomarkers? Findings: Through a multi-stage international consensus process involving expert representatives from the Bridge2AI-Voice Consortium and eVoiceNet Network, a hierarchical model of vocal biomarkers was developed, defining terms from broad concepts (biomarker, digital biomarker, vocal biomarker) to specific physiological and cognitive domains (cardio-respiratory acoustic, voice, speech/articulatory, cognitive/language). Meaning: Standardized definitions for vocal biomarkers provide an essential shared vocabulary for interdisciplinary collaboration and lay the foundational groundwork for future guidelines needed to advance the implementation of voice-based health technologies into clinical practice and clinical research.


  • Open Access

    Exploring biases related to the use of large language models in a multilingual depression corpus

    by Paula Andrea Perez-Toro, Judith Dineley, Raquel Iniesta, Yuezhou Zhang, Faith Matcham, Sara Siddi, Femke Lamers, Josep Maria Haro, Brenda W. J. H. Penninx, Amos A. Folarin, et al.

    Recent advancements in Large Language Models (LLMs) present promising opportunities for applying these technologies to aid the detection and monitoring of Major Depressive Disorder. However, demographic biases in LLMs may present challenges in the extraction of key information, where concerns persist about whether these models perform equally well across diverse populations. This study investigates how demographic factors, specifically age and gender affect the performance of LLMs in classifying depression symptom severity across multilingual datasets. By systematically balancing and evaluating datasets in English, Spanish, and Dutch, we aim to uncover performance disparities linked to demographic representation and linguistic diversity. The findings from this work can directly inform the design and deployment of more equitable LLM-based screening systems. Gender had varying effects across models, whereas age consistently produced more pronounced differences in performance. Additionally, model accuracy varied noticeably across languages. This study emphasizes the need to incorporate demographic-aware models in health-related analyses. It raises awareness of the biases that may affect their application in mental health and suggests further research on methods to mitigate these biases and enhance model generalization.


  • Open Access

    A Dual In-Person and Remote Assessment Approach to Developing Digital End Points Relevant to Autism and Co-Occurring Conditions: Protocol for a Multisite Observational Study

    by Isabel Yorke, Charlotte A Boatman, Akash Roy Choudhury, Bethany Oakley, Pauline Conde, Heet Sankesara, Yatharth Ranjan, Zulqarnain Rashid, Judith Dineley, Johnny Downs, et al.

    Background: Research priorities for autistic people include developing effective interventions for the numerous challenges affecting their daily living, for example, mental health problems, sleep difficulties, and social well-being. However, clinical research progress is limited by a lack of validated objective measures that represent target outcomes for improvement. Digital technologies, including wearable devices and smartphone apps, provide opportunities to develop novel measures that may reflect everyday experience and complement key clinical assessments. However, little is known about the acceptability and feasibility of implementing digital data collection in this population. Objective: The primary objective of this study is to evaluate the usability, acceptability, adherence, and feasibility of a dual in-person and remote (ie, at-home) protocol. Secondarily, we aim to explore the properties of certain resulting data with a view to developing novel digital end points for key target outcomes, including social communication, sleep, and mental health. Methods: Eligible autistic and nonautistic in the AIMS Longitudinal European Autism Project were invited to participate in a digitally augmented in-person Autism Diagnostic Observation Schedule-2 (ADOS-2) and a 28-day remote measurement (RM) protocol involving wearing a Fitbit device, downloading a passive smartphone data collection app, and using 2 active reporting apps. Results: The first AIMS Longitudinal European Autism Project study participants were enrolled in September 2021 (in-person component) and March 2022 (RM component). To date, 190 participants have taken part in the digitally augmented ADOS-2 component, and 86 participants have been enrolled for the RM protocol. Recruitment is now complete with some RM data collection ongoing until August 2025. Data analysis has commenced, including qualitative framework analysis of feedback interview data coproduced with autism community members, exploration of acceptability and feasibility metrics, pipeline development for ADOS-2 speech analysis, and RM sleep measures. Conclusions: This study lays important groundwork in understanding the acceptability and feasibility of in-person and remotely implemented digital measurement procedures to capture meaningful outcomes in domains important to improving everyday life for autistic people. International Registered Report Identifier (IRRID): DERR1-10.2196/71145


  • Open Access

    Collection and Analysis of Repeated Speech Samples: Methodological Framework and Example Protocol

    by Nicholas Cummins, Lauren Louise White, Zahia Rahman, Catriona Lucas, Tian Pan, Ewan Carr, Faith Matcham, Johnny Downs, Richard Dobson, Thomas F Quatieri, et al.

    Background: Speech and language biomarkers have the potential to provide regular, objective assessments of symptom severity in several neurological and mental health conditions, both in the clinic and remotely. However, speech and language characteristics within an individual are influenced by multiple variables that can make findings highly dependent on the chosen methodology and study cohort. These characteristics are often not reported adequately in studies investigating speech-based health assessment, which (1) hinders the progress of methodological speech research, (2) prevents replication, and (3) makes the definitive identification of robust biomarkers problematic. Objective: This study aims (1) to facilitate replicable speech research by presenting a transparent speech collection and feature extraction protocol and design checklist for other researchers to adapt and design for their own experiments and (2) to demonstrate in a pilot study the feasibility of implementing our example in-laboratory protocol that reduces multiple potential confounding factors in repeated recordings of healthy speech. Methods: We developed a collection and feature extraction protocol based on a thematic literature review to enable a controlled investigation of within-individual speech variability in healthy individuals. Our protocol comprises the elicitation of read speech, held vowels, and a picture description and extraction of 14 example features relevant to health. We collected speech using a freestanding condenser microphone, 3 smartphones, and a headset to enable a sensitivity analysis across different recording devices. Results: We collected healthy speech data from 28 individuals 3 times in 1 day (the “day” cohort), with the same schedule repeated 8 to 11 weeks later, and from 25 individuals on 3 days within 1 week at fixed times (the “week” cohort). Participant characteristics collected included sex, age, native language, and voice use habits. Before each recording, we collected information on recent voice use, food and drink intake, and emotional state. Recording times were also documented. Analysis relating to exploring within-individual variability within the day and week cohorts, as well as the device-type sensitivity analysis, is ongoing, with findings expected later in 2025. Conclusions: The wide variability in speech data collection, processing, analysis, and reporting in research on speech’s use in clinical trials and practice is the motivation for this paper and the development of the speech curation protocol design checklist. Increased, more consistent reporting and justification of study protocols is urgently required to facilitate speech research replication and translation into clinical practice. International Registered Report Identifier (IRRID): DERR1-10.2196/69431


  • Open Access

    A Dual In-Person and Remote Assessment Approach to Developing Digital End Points Relevant to Autism and Co-Occurring Conditions: Protocol for a Multisite Observational Study (Preprint)

    by Isabel Yorke, Charlotte A Boatman, Akash Roy Choudhury, Bethany Oakley, Pauline Conde, Heet Sankesara, Yatharth Ranjan, Zulqarnain Rashid, Judith Dineley, Johnny Downs, et al.

    BACKGROUND Research priorities for autistic people include developing effective interventions for the numerous challenges affecting their daily living, for example, mental health problems, sleep difficulties, and social well-being. However, clinical research progress is limited by a lack of validated objective measures that represent target outcomes for improvement. Digital technologies, including wearable devices and smartphone apps, provide opportunities to develop novel measures that may reflect everyday experience and complement key clinical assessments. However, little is known about the acceptability and feasibility of implementing digital data collection in this population. OBJECTIVE The primary objective of this study is to evaluate the usability, acceptability, adherence, and feasibility of a dual in-person and remote (ie, at-home) protocol. Secondarily, we aim to explore the properties of certain resulting data with a view to developing novel digital end points for key target outcomes, including social communication, sleep, and mental health. METHODS Eligible autistic and nonautistic in the AIMS Longitudinal European Autism Project were invited to participate in a digitally augmented in-person Autism Diagnostic Observation Schedule-2 (ADOS-2) and a 28-day remote measurement (RM) protocol involving wearing a Fitbit device, downloading a passive smartphone data collection app, and using 2 active reporting apps. RESULTS The first AIMS Longitudinal European Autism Project study participants were enrolled in September 2021 (in-person component) and March 2022 (RM component). To date, 190 participants have taken part in the digitally augmented ADOS-2 component, and 86 participants have been enrolled for the RM protocol. Recruitment is now complete with some RM data collection ongoing until August 2025. Data analysis has commenced, including qualitative framework analysis of feedback interview data coproduced with autism community members, exploration of acceptability and feasibility metrics, pipeline development for ADOS-2 speech analysis, and RM sleep measures. CONCLUSIONS This study lays important groundwork in understanding the acceptability and feasibility of in-person and remotely implemented digital measurement procedures to capture meaningful outcomes in domains important to improving everyday life for autistic people. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/71145