[ad_1]
MANHASSET, NY – (BUSINESS WIRE) – Researchers at the Feinstein Institutes for Medical Research have developed novel machine learning (ML) algorithms from a user’s Facebook activity that can accurately predict those who develop schizophrenia spectrum disorders (SSD) and mood disorders (MD) for more than one year prior to the patient’s first admission and official diagnosis. This milestone achieved – realized in collaboration with computer scientists at IBM Research and published today in Nature Partner Journals (npj) Schizophrenia – further supports the integration of digital activity and social media in early intervention and psychiatric care.
In an effort to improve psychiatric screening procedures and care trajectories, research led by Michael Birnbaum, MD, assistant professor at the Feinstein Institutes Behavioral Sciences Institute, analyzed Facebook data 18 months before the first psychiatric hospitalization. The study team extracted 3,404,959 Facebook messages and 142,390 images in 223 consented participants to identify characteristics that distinguished participants with SSD and MD from healthy volunteers (HV).
Some of the key findings include:
-
SSD and MD participants were more likely to use swear words than HV;
-
SSD used more perception words – such as “hear”, “see” and “hear”, than MD or HV;
-
MD used multiple words relating to blood, pain and other biological processes;
-
Closer to admission, punctuation increased in SSD compared to HV;
-
The use of negative emotion words increased in MD compared with HV;
-
Regarding the use of images, the height and width posted by participants with SSD and MD were less than HV, and the MD photos contained more blue and less yellow.
The time between the onset of the disease and receiving adequate care can be long, and mental health professionals are looking for new methods to objectively identify early warning signs of emerging psychiatric symptoms that could improve early intervention strategies. To date, most previous studies exploring associations between social media activity and psychiatric diagnoses have been based on assumptions about clinical and diagnostic status. This study is one of the first to use real data from patients with clinically confirmed and validated psychiatric diagnoses to develop machine learning algorithms and to explore social media activity more than a year in advance of receiving psychiatric care.
“There is great promise in current research regarding the relationship between social media activity and behavioral health, and our results published with IBM Research today show that machine learning algorithms are capable of identifying signals. associated with mental illness, well over a year before the first psychiatric hospitalization, ”said Dr. Birnbaum, program director for Northwell Health’s Early Treatment Program (ETP). “We have the potential to thoughtfully bring psychiatry into the modern digital age by integrating this data into the field.”
This research is one of many recent publications by Dr. Birnbaum and the team that point to the promise of social media and online activity for psychiatry. More recently, in collaboration with Cornell Tech and Georgia Tech, a paper published in Public library of science (PLOS) One analyzed more than 400,000 search queries, using data from a year before the first psychiatric hospitalization. Differences in timing, frequency, and content of searches were observed in those with SSD and MD versus HV, similar to the Facebook research published today.
“Early detection of severe mental illness significantly improves long-term outcomes and responses to treatment,” said Kevin J. Tracey, MD, president and CEO of the Feinstein Institutes. “Dr. Birnbaum is experimenting with social media and digital clinical strategies to detect disease in the early critical stages, when treatments are most likely to be effective.”
About the Feinstein Institutes
Feinstein Institutes for Medical Research is the research arm of Northwell Health, the largest healthcare provider and private employer in New York State. Home to 50 research laboratories, 3,000 clinical research studios, and 5,000 researchers and staff, the Feinstein Institutes raises the standard of medical innovation through its five institutes of behavioral science, bioelectronic medicine, cancer, health innovations and achievements, and molecular medicine. We make breakthroughs in genetics, oncology, brain research, mental health, autoimmunity, and are the global scientific leader in bioelectronic medicine, a new field of science that has the potential to revolutionize medicine. For more information on how we produce knowledge to cure disease, visit http://feinstein.northwell.edu and follow us on LinkedIn.
Source link
