In our lives, most of us have had the experience where we have sought guidance from a doctor, spiritual leader or administrator to address a concern in our life. It is likely that in some experiences we felt the person from whom we sought guidance understood our concern and provided helpful advice, but in other interactions we may have felt misunderstood or even dismissed. While we want to believe that all doctors will understand all of our medical problems, that is just not the case. Doctors, like us, are humans too.
The same is also the case in behavioral health. Not every behavioral health professional is the right match for every client. It is also true that not every behavioral health agency will be able to provide the right supports for every person it serves, and not every program can address the needs of those who seek to enroll. So, how can we determine what works for whom?
The first step to identify what works for whom is to know more about the individual who is seeking care. To do this, scientists are using machine learning to identify biomarkers of health disorders, but there are so many additional influences that affect our behavioral health in our environment and in our historical experiences, such as our ACES (adverse childhood experiences). Researchers have already identified that the number of ACES we experience can increase our risks for health and behavioral health disorders. Therefore, in addition to biomarkers, it is important to think about story markers when considering personalized care.
Story markers are the influential parts of our experiences that have helped shape us to be who we are. They are the pieces of our lives that we feel someone might need to know about us in order to really understand who we are. That might include where we grew up, traumatic events we experienced, people who influenced our belief system, people we have influenced, issues we struggled to overcome and goals we achieved. While they don’t define us, story markers do contribute to our current outlook and our approach to interacting with life.
Like scientific approaches for biomarkers, machine learning applied to story markers can help identify how to personalize care. By understanding the story markers of those who successfully complete a program as compared to the story markers of those who were not as successful in the same program, we can begin to identify what works for whom. Like biomarkers, story markers can better match the right individual to the right treatment and right skilled helpers.