Detect & connect behavioral health cases during crisis response
CaseFinder uses published peer-reviewed AI to detect 93.75% and record behavioral health cases hidden in 911 calls and police reports, routing them to the right care automatically and tracking them for compliance.
First responders (EMS, Police, Fire)
- ✓Identifies behavioral health trends over time to guide resource allocation and deployment
- ✓Flags cases appropriate for diversion and reduces unnecessary incarceration
- ✓Generates records that support state compliance requirements for crisis intervention and diversion protocols
The Impact
Behavioral Health Detection Rate
Co-Responder Daily Case Capacity
93.75%
Detection Accuracy
15×
More Cases Identified
Top 30%
Usability Score (SUS)
How CaseFinder Works
Pull in data
Pulls 911 transcripts, police narratives, and clinical notes
Identify behavioral cases
Peer-reviewed natural language processing engine identifies behavioral health cases
Check for bias
Ensure consistent, fair outputs across all demographics and geographies
Classify & connect
Severity scoring engine automatically routes each case to the right responder
Legal reporting
Audit-ready, court-admissible reports generated instantly
Why It Matters
01
Unlock Funding & Resources
Quantify drug- and opioid-related incidents from 911 and police data to build the evidence base for opioid settlement funds, SAMHSA grants, and other federal behavioral health funding streams.
02
More Lives Reached
Systematically identify every behavioral health incident — not just the worst cases.
03
Better Referrals
AI-assisted detection with standardized warm handoffs and tracked follow-up that closes the loop.
04
Compliance Built In
Audit-ready reports automatically unlock Title JAG, JMHCP, and co-responder grant funding.
05
Multi-Source Integration
Connects to 911 CAD, police RMS, and clinical record systems with no custom integration work.
06
Built-in Debiasing
Equity filters prevent disparate outcomes by race, age, or geography.
Independently validated
In partnership with Kennesaw State University, detection models were evaluated in peer-reviewed research and assessed by active police officers in live deployment environments. Brown et al. (2024): Smart Health journal.
Brown et al. (2024)
Citation: Brown, M., Azmee, A. A., Khan, M. A. A. H., Thomas, D., et al. (2024). Adaptive Attention-Aware Fusion for Human-in-the-Loop Behavioral Health Detection. Smart Health, 32, 100475.
Read the paper — doi.org/10.1016/j.smhl.2024.100475Request a demo
Join forward-thinking agencies to detect behavioral health crises before they escalate and coordinate the care that follows.
Request a Demo →