Digital mental health company Cerebral uses machine learning algorithms to identify patients at risk. According to the company, the recently announced initiative is “just the beginning” of Cerebral’s use of machine learning-enabled solutions.
“Machine learning (ML) and artificial intelligence (AI) are important tools in advancing mental health care, but these benefits are only possible at scale,” a team of Cerebral researchers said in a company post. is explained. “Both technologies require many data points to test and validate hypotheses to prove that the system is working effectively.”
Called “Crisis Message Detector 1 (CMD-1),” the newly touted tool identifies messages from patients experiencing a mental health crisis and refers them to crisis specialists. is designed to
The tool was specifically trained to spot signs of suicidal, homicidal, non-suicidal self-harm, or domestic violence, according to the company’s post. If the patient’s message to the cerebrum is flagged, a specialist will contact them directly to assess the patient’s risk level.
This mental health professional can call your emergency contact or local responder if needed.
The brain sells this instead of relying on patients to call 911 in the event of an emergency. The company claims the tool is accurate in properly identifying individuals at risk.
“During a one-week pilot period, CMD-1 screened over 60,000 EMR messages and flagged over 500 potential crises,” wrote the Cerebral researchers. “The model was successful in detecting her over 99% of all crisis messages, resulting in crisis management professionals being able to respond to patients within nine minutes on average.”
Cerebral receives thousands of patient messages each day via an online chat system or mobile app. Someone on the patient care team will review and act on those messages, according to the company, but that human-driven process isn’t always as fast as it should be.
The company plans to expand its machine learning initiative in the coming months to focus on issues such as response times for medication concerns, scheduling issues, and general support requests.
“With experience serving 250,000 people (and countless more), Cerebral develops and implements state-of-the-art ML/AI tools to complement clinician expertise and improve clinical outcomes. We can help you improve,” the company’s post added.
CMD-1 is deployed nationwide and available 24/7.
In addition to demonstrating the company’s interest in ML and AI, the patient identification tool reflects the previously described commitment to quality control.
Earlier this year, Cerebral came under fire for its practice of prescribing controlled substances. In June, news surfaced that the Department of Justice (DOJ) had launched an investigation into the company based on possible violations of the Controlled Substances Act.
Next, the digital health company changed management. Founder Kyle Robertson stepped down as CEO, and Chief Medical Officer Dr. David Mu took over the role.
“I would say we made a mistake,” Mou said at the American Telemedicine Association conference in May. “And we also admit that we make mistakes and keep learning.”
Cerebral also announced a July 1 layoff. In June, Mou told his BHB that the layoffs reflected the company’s priority to keep behavioral health front and center while transitioning to value-based care.
Looking to the future, the company aims to treat serious mental illnesses (SMIs) and is developing value-based care propositions, Mou previously told BHB.