Every day, across the country, mental health workers are filling out assessments. Every minute, the mountain of information on individuals of all ages is growing. Their stories, caught in multiple choice sized chunks, are being held in bits and pieces, on 8.5 x 11 papers and digital forms, in file cabinets and on secure network drives, in offices and in the cloud. Why? For what end?
In the age of big data, where machine learning is driving advances in retail, transportation, government services and more, don’t we owe it to the most vulnerable in our society to do something with the data they have entrusted us with? Use of machine learning is growing fast in the health care sector in general. But its benefits to the mental health field so far can be seen as limited. Identification of a handful of diagnoses has been made more efficient. EHRs have been improved to make them more able to support more advanced technology. But are mental health professionals feeling those advances yet?
What if every completed mental health assessment became part of a local knowledge base, where data points joined together to grow an understanding of what works for whom? When a client graduates a program having completed their goals, there is something to be learned from that success. When a client is discharged due to undesirable circumstances there is an opportunity to learn from that as well. A system can be designed to receive that information, connect it with other local data points, and loop it back to inform the program itself. A system like that adds value to the assessment process, and empowers data driven decision making at the local level.
Making meaningful use of the data that is collected at the local level, through carefully developed analytical models, puts powerful data informed tools in the hands of professionals in the field. Machine learning provides opportunities to tailor best practices for treatment based on links between evidenced based research, population patterns, and the individual client. And it can impact the field now, making changes in the work being done today.