Using Data to Best Match Patients and Clinicians

Despite Medical Progress, Suicide Remains Difficult to Treat Even as medical care has progressed, one leading cause of death remains tragically high suicide. Despite persistent research over the past decades, suicide rates have only increased , and self-harm remains stigmatized for families and among caregivers.  In some ways, suicide is among the last of the medical taboos, and that makes sense: doctors don’t like to talk about ailments they can do little about. Even at the best hospitals in the world, psychiatrists fail to predict whether a depressed patient will take their own life after leaving the hospital. Studies show that they have just over a 50 percent probability of making an accurate assessment. Ineffective prognosis and treatments make medical professionals reluctant to take on these difficult cases, leaving patients and families even more isolated. A 2019 study found that willingness to treat was significantly lower and the likelihood of referring out was significantly higher among therapists for suicidal patients.”  To make matters worse, medications intended to alleviate depression and other mental health conditions can take weeks to take effect, leaving some patients especially vulnerable as they await the onset of effect. Overcoming Stigma and Developing Proactive Treatment We can and must do better. Suicide is a national emergency. Every 11 minutes in the United States, someone takes their own life, according to the Centers for Disease Control, and suicide rates increased 30 percent between 2010 and 2018. In 2020, suicide was the second leading cause of death for Americans aged 10 to 14 and 25 to 34. Rates of suicidal thinking are even higher. The CDC estimates that in 2020, 12.2 million adults seriously considered suicide and 1.2 million actually tried to take their own life.    Given the pervasiveness of suicidal ideation in the United States, mental health providers must adjust how we treat and think about suicide. In order to help these patients, we have to dismantle the stigma around talking about suicide. This starts with consistent screening for depression during routine physical exams. Removing stigmas starts with the clinician. If clinicians initiate the conversation, patients may feel more comfortable discussing topics they may have otherwise been too nervous to bring up.        In addition to clinicians, our medical system must broadly establish consistent screening for depression just as it’s done for blood pressure, high cholesterol, as well as much more intensive diagnostics like endoscopies and colonoscopies. Depression should be among the first things physicians and nurses ask about during physical exams - and yet often, it's the last. In fact, a panel of medical experts recently recommended anxiety screening for all adults under 65.        Fifty years ago, the diagnosis of cancer was similarly stigmatized, for the same reason that clinicians were not well-equipped to manage these conditions. The advent of new treatments, better outcomes, and advocacy efforts by medical professionals and patients alike changed perceptions about cancer completely. We can similarly change how we as a society think about suicide through a concerted effort to develop better treatments, improve outcomes, and increase awareness and acceptance.         In particular, telehealth offers a much-needed resource to address the current situation by providing access for patients who haven’t been able to seek mental health care in the past, were excluded in underserved communities, or didn’t feel comfortable seeking care. New Approaches Offer Promise As a first step in improving clinical care and outcomes, we need better measures of treatment for suicidal patients, something that is sorely lacking today. Better data, consistent measurement, and more widespread benchmarks would be a helpful first step. Then, we need to develop interventions that can decrease suicidal thinking.      Some developments are promising. New research indicates that even brief regular contacts with patients experiencing severe depression through post-cards, text messages, emails, phone calls or other communication can decrease suicidal ideation.        This approach helped inspire a new paper that I co-authored with colleagues at Harvard on Bibliotherapy. After suicidal patients read brief, first-person narratives about coping with suicidal ideation written by other people who overcame suicidal thinking, the readers themselves experienced lower rates of suicidal thinking. Bibliotherapy is cost-efficient, easy to scale, and a method of treatment Cerebral intends to launch in the next few months. How Cerebral is Making A Difference At Cerebral, we understand just how prevalent suicide is and how difficult it is to treat. And we are committed to taking on the toughest cases and making a real difference for suicidal patients and their families and utilize a comprehensive treatment plan.       Our organizational structure includes a comprehensive Clinical Safety department that includes crisis specialists, psychiatrists, and data scientists. With this crisis response capability in place, our goal is to make sure no one is neglected by the mental health care system and everyone receives consistent, measurable and high-touch interaction.      Cerebral’s data-driven approach is instrumental in improving clinical safety. Each day, Cerebral receives 5,000 to 10,000 patient messages via a chat system available on our website or mobile app. We are using machine-learning to analyze these messages, and we can correctly detect messages with suicidal content with 97% accuracy, and reach out to these patients within minutes.  This system can also serve as a way to connect with patients regularly and keep them close touch with their care team, as each patient message is reviewed and addressed by our patient support team.         Conclusion As the new research indicates, there are reasons to believe we can make progress in combating the scourge of suicide. As a psychiatrist and CEO of Cerebral, I have seen the devastating impact suicide has on individuals and their families firsthand. During medical training, medical students typically wore short white coats while more senior doctors were clad in longer ones, symbolizing that they had already completed the process of learning. At Massachusetts General Hospital, where I trained, all doctors wore short coats to emphasize that real learning never ends. We always practice medicine; we do not perfect medicine. That is the mentality which I bring to Cerebral. In order to improve care for our most vulnerable patients, we need to remain humble, data-driven, and committed to becoming life-long students of medicine. Too much is at stake for us not to try.  Resources: Suicide and Suicidal Behavior Prediction of Suicide Attempts Using Clinician Assessment, Patient Self-report, and Electronic Health Records | Electronic Health Records | JAMA Network Open | JAMA Network  To Treat or Not to Treat: The Effect of Hypothetical Patients’ Suicidal Severity on Therapists’ Willingness to Treat  Facts About Suicide | Suicide | CDC Advancing the Understanding of Suicide: The Need for Formal Theory and Rigorous Descriptive Research Taking care of suicidal patients with new technologies and reaching-out means in the post-discharge period

Millions of Americans who suffer from mental illnesses go untreated. This number has only risen since the onset of the COVID-19 pandemic, with fresh headlines detailing how serious the crisis has become. Just this month, for example, new data released in the American Journal of Preventive Medicine showed that almost 1 in 10 Americans suffer from depression. However, many victims of depression, anxiety, and other mental health conditions are simply unable to access the care they need for their conditions. At Cerebral, the majority of the patients who come to our platform haven’t been able to access high quality care through other avenues. In an effort to bring more attention to this issue, we have published our inaugural State of Mental Health Care report today. Its aim is to take a holistic look at the mental health field and provide Cerebral’s perspective on the potential solutions to our field’s main challenges. The full report can be found here. Barriers to access: why are so few people getting treatment? To compile our report, we evaluated numerous peer reviewed studies and sources of publicly available information. The results paint a stark picture: in 2020, 1 in 5 US adults experienced a mental illness, and 1 in 20 faced a serious mental illness (SMI), but only 46.2% of individuals received treatment. Our analysis has pinpointed five key reasons for why that is: cost of care, lack of providers who take insurance or are in-network, long wait times for an appointment, clinician fit (e.g. cultural, stylistic factors, etc.), and clinician availability, each with varying impact, depending on the individual. Cost of care was the most cited factor among these five. In the US, 10.3% of adults with a mental illness were uninsured in 2020, and for those without insurance, a standard hour-long therapy session can cost up to/more than $250. What’s more, only 56% of psychiatrists accept commercial insurance, compared to 90% of non-mental health physicians. Taken together, these unfortunate circumstances force many Americans seeking mental health care to pay out of pocket. What’s more, the cost is often prohibitive, even for those earning a comfortable living. An estimated 39% of US adults cited cost as a reason for not receiving mental health treatment. Even if an individual can overcome the sheer cost of care, they face additional barriers such as finding an available clinician who is (1) in their area, (2) accepting new patients, and (3) a cultural and stylistic fit. The average wait time for an appointment for new psychiatric patients can range from 25 to 90 days. As of March 2021, an estimated 122 million Americans were living in areas with a shortage of mental health care professionals. About two thirds of these shortages were in rural or partially rural parts of the country. Finally, as of 2020, the American Psychological Association reported that of all American psychologists, only 6.18% identified as LatinX, and only 4.24% identified as Black.To make matters worse, many people also battle with the stigma of admitting to mental health issues and seeking treatment for them at all. Our beleaguered mental health system is not setting our patients up for success. Cerebral’s Mission: Meeting Patients Where They Are  The reality for our patients prior to finding Cerebral is that it has been very hard for them to get help. Of the patients who turn to Cerebral for depression treatment, 76% report symptoms consistent with moderately severe or severe depression. Similarly, of the patients who came to Cerebral for anxiety treatment, 89% report symptoms consistent with moderately severe or severe anxiety. Cerebral’s telehealth model has proven its ability to fill this void. Our fully virtual model allows our clinicians to meet people where they are, vastly expanding the field of mental health care professionals. Patients have an easier time both getting that first appointment and making that personal connection through a tailored matching algorithm where we take into account our patients’ preferences. All the while, they can avoid perceived stigmas by taking appointments from their phone or computer or wherever they’re most comfortable. Above all, we are committed to ensuring that our clinical care is high-quality and equal to or above widely accepted standards of care. We do this by incorporating outcomes measurement into everything we do, something that is sorely lacking in the mental health care field. As an example, we use data science to improve care via a System for Measurement-based Access to Relationship-focused Treatment (SMART) approach. Our platform matches patients in a timely manner with an appropriate care team and care plan based on patient preference and clinical need. In turn, Cerebral is enabled to deliver high-quality care by using actionable data to improve access and therapeutic relationships. Cerebral tracks meaningful and actionable clinical quality indicators in order to monitor effectiveness, efficiency, safety, and timeliness of care. This approach stands in stark contrast to traditional mental health care providers, who have been hesitant to undertake measurement in a rigorous manner. A recent study even reported that 25% of psychiatrists do not use electronic medical records, and opt for paper notes instead. For underserved communities and others, Cerebral’s data-driven approach will also help us set broader benchmarks for care that can improve results in the future. What’s next? Cerebral is making strides every day in closing both the access and quality gap outlined in our State of Mental Health Care report. This is just the beginning, and much remains to be done.. At Cerebral, we are committed to facing this challenge head on, and we will continue to commit to democratizing access to high quality mental health care for all.

Blog Authors: Ivan Lopez, Akshay Swaminathan, Rafael Antonio Garcia Mar, Tom McClintock Upon calling any medical provider, the first thing you typically hear is: “If this is an emergency, please hang up and call 911.” Though these words are extremely common, little is known about the “standard” care journey for patients experiencing a mental health emergency.  Sadly, most mental health providers do not track the number of patients who call experiencing a crisis. For patients who end up calling 911, there is little data shared about the average wait times they experience before their emergencies are addressed.  To help address these gaps, Cerebral has developed a data-driven approach to improve clinical safety, especially as it relates to mental health emergencies. On a typical day, Cerebral receives 5,000-10,000 patient messages via a chat system available on our website or mobile application. This allows patients to connect with their care team on a variety of topics such as appointment rescheduling, questions about their treatment plans, medications, and more. It also serves as a form of contact for patients who are experiencing a crisis. Each patient message is reviewed and addressed by our patient support team. While this approach is best suited for non-emergencies, more serious mental health crises, such as suicidal ideation (when someone is having suicidal thoughts or ideas), need to be addressed and responded to as soon as possible. With this as our guide, we’ve developed ways to improve our response time in emergency cases. Using machine learning-enabled tools to improve mental healthcare delivery Machine learning (ML) and artificial intelligence (AI) are critical tools in the advancement of mental health care, but these benefits are only possible at scale. Both technologies require many data points to test and validate hypotheses in order to prove that the systems are working effectively. Because of Cerebral’s experience serving a quarter-million people (and counting), we are uniquely suited to develop and implement cutting edge ML/AI tools to supplement the expertise of our clinicians and help improve clinical outcomes. This means we can make sure our patients are safe around the clock and get them the help they need as quickly as possible. While all messages are and will continue to be viewed by Cerebral's professional staff, our innovative ML/AI tool allows our teams the ability to respond to patients in crisis in near real-time. With the help of a team of clinicians, crisis specialists and data scientists, we analyzed millions of patient messages to build a tool that would detect any indication of crisis. We call this tool the Crisis Message Detector 1 (CMD-1). Figure 1. Overview of Crisis Message Detector-1 (CMD-1) System  CMD-1 is a tool that identifies messages from patients experiencing a mental health crisis and shares them with our crisis response specialists. It’s designed to alert the crisis response team to messages that may indicate suicidal ideation, homicidal ideation, non-suicidal self-injury, or domestic violence, among other emergency situations. Once alerted, the crisis response team reaches out to patients directly to assess the level of immediate risk, then mobilizes emergency contacts and/or local responders, if appropriate. CMD-1 allows our care teams to significantly reduce the amount of time a patient experiencing a mental health crisis must wait before receiving support. During a week-long pilot, CMD-1 screened over 60,000 EMR messages and flagged more than 500 potential crises. The model successfully detected over 99% of all crisis messages and, as a result, crisis specialists were able to respond to patients in less than 9 minutes on average.  We are proud to have officially launched CMD-1 for all Cerebral patients, allowing our crisis specialists to support individuals when they are at their most vulnerable. This is just the beginning for machine learning-enabled solutions. In the coming months, we plan to apply this technology to improve response times for medication concerns, scheduling issues, and support requests across the board. ​Special thanks to the Cerebral employees and advisors who participated in the design, build and testing of our CMD-1 System: Tyler Heist, Madeline Holmes, Matthew Rubashkin, Sid Salvi, Shaked Azzam, Dr. David Mou, Dr. Matthew Nock and the entire Cerebral Clinical Quality and Safety teams!