Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide
About This Grant
Project Summary/Abstract Ecological Momentary Assessment (EMA) studies capture unprecedented data about suicidal thoughts and be- haviors (STBs) via smartphones and wearable biosensors. While promising, EMA studies are expensive to run, require a large staff, and are limited in scientific value due to three data analysis challenges. These challenges create a bottleneck for suicide research. Challenge 1: small data size. Even the largest of EMA studies yield modest sample sizes with low compliance. This bars applications of (data-hungry) deep learning (DL) methods, successful in other areas of healthcare. Challenge 2: stochasticity. STBs are, in part, driven by stochastic (or random) external events that cannot be captured (e.g. reactions to triggering stimuli). Methods that do not model external stochasticity often learn spurious correlations, making incorrect and overconfident forecasts of future pa- tient outcomes. Challenge 3: empirically testing theories of suicide. Empirically evaluating theories with data is difficult given their verbal (non-quantitative) nature; mathematically formalized theories require an extreme level of specification detail, making it difficult for clinical and machine learning (ML) researchers alike to determine which details capture the high-level idea of the theory. As such, current methods struggle to accurately forecast STBs, identify those at imminent risk, and test psychological theories of suicide. Our central hypothesis is that encod- ing clinical knowledge in DL models addresses key data analysis challenges. We define qualitative clinical knowledge (QCK) as clinical knowledge that is difficult to mathematize, like intuition. Encoding QCK in DL meth- ods will provide the model additional supervision, reducing its over-reliance on limited data (Challenge 1). Guided by clinical knowledge, it will discover scientifically viable associations between EMA outcomes and unobserved external factors, avoiding spurious correlations due to stochasticity (Challenge 2). Lastly, our method will pro- vide clinicians with a mechanism for encoding their knowledge into the model without specifying uninterpretable mathematical details (Challenge 3). Our project has three aims. Aim 1: develop a new DL model, tailored for noisy, irregularly-sampled, partially-observed EMA data. Aim 2: identify types of QCK that clinicians can reliably provide, encode them into our DL model, and assess their predictive value. Exploratory Aim 3: prototype an interactive modeling paradigm that algorithmically solicits clinicians for QCK (from Aim 2) into the DL model (from Aim 1). Expected Outcomes: This project will yield (1) theoretically and empirically validated ML methods for use in future scientific and clinical work, (2) new insights/findings from existing EMA data, increasing the scientific yield from previous NIH-funded projects, (3) an interactive ML paradigm for embedding clinical knowledge in DL methods, useful in all mental health and healthcare contexts, and (4) highly optimized, modular open-source code, available for the broader community to apply and adapt to their needs.
Grant Summary
Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide is a NIMH - National Institute of Mental Health grant providing up to $708K for university, nonprofit, healthcare org. Applications are due 2031-05-31 (open). Check eligibility and apply with FindGrants.
Not quite the right fit?
Search 9,000+ open grants, or get matches ranked for your organization — free.
Focus Areas
Eligibility
How to Apply
Up to $708K
2031-05-31
- 1Confirm your organization is eligible for Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide from NIMH - National Institute of Mental Health, checking organization type, location, and any population or project requirements.
- 2Gather the required documents and information, including your organization details, project plan, and budget figures.
- 3Draft your application narrative and budget addressing the funder's priorities and review criteria. FindGrants can draft each section for you to review and edit.
- 4Review every section against the requirements checklist, then export a submission-ready application pack and submit it to NIMH - National Institute of Mental Health before the deadline.
Don't want to draft it yourself?
We'll draft the complete application against NIMH - National Institute of Mental Health's requirements, run a quality review, and email you a submission-ready PDF plus an editable Word doc within 5 business days. Most orders deliver in 24-48 hours. Flat $399, any grant size.
AI Requirement Analysis
Detailed requirements not yet analyzed
Have the NOFO? Paste it below for AI-powered requirement analysis.
Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide: Frequently Asked Questions
Who is eligible for the Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide?
Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide is offered by NIMH - National Institute of Mental Health and is generally open to university, nonprofit, healthcare org. It is open to organizations nationwide unless the funder specifies otherwise. Review the specific eligibility terms before applying, since funders set their own requirements around organization type, location, and the population or project being served.
How much funding does the Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide provide?
Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide provides up to $708K per award from NIMH - National Institute of Mental Health. Actual award sizes depend on the scope of your project, available program funds, and the number of applicants, so build a budget that reflects realistic, allowable costs rather than the maximum figure.
When is the Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide deadline?
Applications for Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide are due 2031-05-31 (open). Because deadlines can change, verify the date with the funder, NIMH - National Institute of Mental Health, and give yourself enough time to prepare a complete, competitive application before the close date.
How do you apply for the Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide?
To apply for Aligning Machine Learning Models with Clinician Knowledge for Understanding, Prediction, and Prevention of Suicide, confirm your eligibility, gather the required documents, and prepare a narrative and budget that address the funder's priorities. FindGrants guides you step by step and can draft each section, then exports a submission-ready application pack for this grant from NIMH - National Institute of Mental Health.