Can Behavioral Health Be Objective and Data-Driven?

Before microscopes, doctors diagnosed as best they could using external symptoms. Now we test for the presence of specific bacteria, viruses, or lesions. Dr. Thomas Young, chief medical officer and founder of Proem Behavioral Health, is convinced that psychiatry and behavioral health are also entering an age where objective data collected from the body will drive diagnoses and treatment.

Figure 1 shows some statistics about disorders tracked by Proem.

Proem Behavioral Health uses several measures to track mental disorders.
Figure 1: Measures used by Proem Behavioral Health and their uses

Two advances have come together over the past few years to enable better diagnoses and treatments: one in data collection and the other in data interpretation.

In data collection, consumer devices such as the Apple Watch, Fitbit, etc. can collect reasonably accurate data on important physical functions such as heart rate variability and sleep cycles.

In data interpretation, rigorous research has connected the data with diagnostic suggestions, which have to be combined with the clinicians’ subjective assessments to come up with diagnoses. Data can also suggest personalized treatments that are likely to work on the individual. Facial expressions recorded by a camera and voice patterns detected on a phone also yield increasingly precise information about chronic conditions as well as changes in the patient’s condition.

Young explains that patient device data is commonly used to determine how fast a disabled patient can be rehabilitated, when an injured athlete can return to the sport, and similar decisions.

Young explains that common physical problems such as heart failure can be treated through well-defined steps known as “process models.” Up until recently, no such models existed for behavioral health; clinicians and patients were making guesses based on their most expert understanding of symptoms. But the combination of modern data collection and research on interpretation is offering a new era of objective diagnosis and treatment.

Figure 2 shows a sample clinical follow-up generated by Proem.

A clinical follow-up can identify possible disorders along with steps to take.
Figure 2: Report generated by Proem.

Proem Behavioral Health collects and organizes data for its clients, which include both clinical and research organizations. These organizations apply existing research do help them make diagnoses and adopt treatment plans. The organizations also use machine learning to discover new information about their patients. Some of Proem’s clients have thousands of patients and gather enough data to contribute to new research about how to apply data to behavioral change.

It’s important to collect demographic data as well as clinical data to reflect differences in gender, age, race, etc. Proem can collect the data requested by clients to make these distinctions.

The successes reported by Young suggest an exciting affirmation of the power of data in health care. If Proem’s clients can move psychiatric and behavioral health from best guesses to data-driven decisions, vetted by clinicians’ expertise, some of the most intractable problems in health may be open to impressive improvements.

About the author

Andy Oram

Andy is a writer and editor in the computer field. His editorial projects have ranged from a legal guide covering intellectual property to a graphic novel about teenage hackers. A correspondent for Healthcare IT Today, Andy also writes often on policy issues related to the Internet and on trends affecting technical innovation and its effects on society. Print publications where his work has appeared include The Economist, Communications of the ACM, Copyright World, the Journal of Information Technology & Politics, Vanguardia Dossier, and Internet Law and Business. Conferences where he has presented talks include O'Reilly's Open Source Convention, FISL (Brazil), FOSDEM (Brussels), DebConf, and LibrePlanet. Andy participates in the Association for Computing Machinery's policy organization, named USTPC, and is on the editorial board of the Linux Professional Institute.

   

Categories