Search Articles

View query in Help articles search

Search Results (1 to 9 of 9 Results)

Download search results: CSV END BibTex RIS


Using Neural Networks with Routine Health Records to Identify Suicide Risk: Feasibility Study

Using Neural Networks with Routine Health Records to Identify Suicide Risk: Feasibility Study

Miotto and colleagues [20] created a deep ANN that received hospital diagnosis codes and created a “patient representation” vector of 500 features. This vector was fed to a random forest to predict 78 different diseases, including mental disorders such as schizophrenia. This model generated an accuracy of more than 90% for (more than) 76,000 patients, but suicide risk was not part of the study.

Marcos DelPozo-Banos, Ann John, Nicolai Petkov, Damon Mark Berridge, Kate Southern, Keith LLoyd, Caroline Jones, Sarah Spencer, Carlos Manuel Travieso

JMIR Ment Health 2018;5(2):e10144

Cookie Consent

We use our own cookies and third-party cookies so that we can show you this website and better understand how you use it, with a view to improving the services we offer. If you continue browsing, we consider that you have accepted the cookies.