New technological innovations are providing healthcare organizations with rich context to identify suicidal risk, leveraging diverse and previously untapped data sources.
PHILADELPHIA, April 24, 2025 /PRNewswire-PRWeb/ -- As part of NeuroFlow's mission to uncover hidden behavioral health needs to empower more timely and effective care, the company has published new findings on symptom and severity identification that can further the industry's ability to assess risk, catch suicidal ideation sooner, and treat patients more efficiently. The research emphasizes how technology unlocks new data insights to surface suicide risk, often among populations that would have otherwise remained under- or undiagnosed.
On average, over 1.5 million people in the U.S. attempt suicide annually, claiming approximately 49,000 lives. The ripple effect of this statistic is massive, causing devastation personally and societally and contributing to billions of dollars in healthcare utilization. With rates steadily rising each year, suicide prevention must be a top priority. Technology is now making it possible to find those who have been "hiding in plain sight". Newly published research demonstrates how user-friendly tools, comprehensive measurement and artificial intelligence can help healthcare organizations spot emerging risk remotely, potentially enabling life-saving interventions.
Two new studies — one published in the Journal of Technology in Behavioral Science (JTIBS) and another currently under review at BMC Psychiatry — show how digital tools can transform suicide risk detection by leveraging self-reported data and AI-driven risk stratification.
Further Validation for Technology-Enabled Suicide Prevention
The first study, Predicting Risk of Suicidal Ideation with Digital Ecological Momentary Assessment (EMA), examined data from more than 30,000 individuals who used NeuroFlow's digital health platform to track their mood, stress, sleep, and pain in daily life. The study found that these self-reported measures, which can be completed in just a few seconds, accurately predicted suicidal ideation risk, with mood emerging as a particularly strong indicator. Clinical assessments, like the PHQ-9, are used in traditional care settings to identify suicidal ideation. However, based on patient behavior in the study, there's a preference to complete mood trackers instead of clinical assessments, with a completion ratio of 18:1. While validated clinical assessments still provide impartial data and remain the 'gold standard' for intake, they can be enhanced by digital tools like real-time mood tracking, bringing a new model to the field.
"We're encouraged about the potential of mood scoring and stress tracking – directly correlating with suicidal ideation – as a way to fuel our risk stratification model," said NeuroFlow Chief Medical Officer Tom Zaubler, MD. "This is a new and legitimate input for preventing suicide, and it reflects NeuroFlow's expertise in gathering disparate data to make sense of often hidden or complex behavioral health conditions. We've always known patients enjoy using trackers to monitor their own progress, and we're excited to connect this high-volume activity to identifying actual risk."
Key Findings Around Artificial Intelligence's Ability to Detect Suicidality Earlier
The second study, Evaluating Generative Pretrained Transformer (GPT) Models for Suicide Risk Assessment in Synthetic Patient Journal Entries, creates a blueprint for safe, effective AI design to support suicidal risk identification in patients. By using a dataset of clinically validated synthetic patient journaling exercises, the study compared risk ratings from large language models (LLMs) against those of five independent experts. The research team found that their ensemble AI model agreed with experts' intervention decisions 92% of the time, demonstrating a fast, accurate, and efficient solution to the challenge of scalable risk detection.
"Artificial intelligence is one of the most democratizing tools of our generation. It has the potential to add a layer of patient insight across the healthcare system – instead of siloing behavioral health data to one site of care," said NeuroFlow researcher Dan Holley, PhD. "What we've been able to prove is that AI is capable of augmenting care teams by triaging thousands of patient records to rapidly turn risk indicators into actionable health intelligence, potentially enabling lifesaving interventions."
Transforming Suicide Prevention Frameworks
Together, these studies highlight how self-reported data and AI-driven risk detection can complement human expertise and expedite care in critical moments. Without true innovation at scale, patients will be left undetected and untreated, a problem reflected in that over half of people who die by suicide receive some form of healthcare within 30 days before their death. With more ways to engage and identify high-risk individuals, limited healthcare resources can be utilized more effectively upstream, and these lives can be saved. Ultimately, the technology industry is paving the way for scalable, high-tech, evidence-based solutions that integrate seamlessly into clinical workflows, helping to ensure at-risk individuals receive timely care and support.
About NeuroFlow
NeuroFlow helps risk-bearing healthcare organizations improve outcomes and cost of care in medically complex populations by surfacing and supporting behavioral health needs that typically go undetected and under-addressed. Across payors, providers, and the federal government, NeuroFlow's scalable technology and analytics capabilities empower organizations with the behavioral health insights they're missing to manage these populations in a financially sustainable way. Powered by deep expertise in whole-person care, NeuroFlow offers a path to risk predictability and proactive care that helps overcome the systemic challenges in today's healthcare ecosystem.
Media Contact
Sara Cohen, NeuroFlow, 1 610-420-1724, [email protected], neuroflow.com
SOURCE NeuroFlow
Share this article