Please read Dr. Deo’s article in medRxiv titled, “Validation of an ICD-Code-Based Case Definition for Psychotic Illness Across Three Health Systems.“
Psychotic disorders typically have their onset during late adolescence or early adulthood, and are associated with high levels of lifelong disability and premature mortality. Studies have demonstrated that decreasing the duration of untreated psychosis can improve functional outcomes. Substantial effort has been dedicated over the past several decades to developing approaches for early detection of those who are at risk for or in the early stages of psychosis, in order to facilitate early intervention.
Electronic health records (EHRs) offer a large-scale resource of real-world health data and have been increasingly used in psychiatric research aimed at characterizing, detecting, or predicting important mental health outcomes. For example, a growing number of statistical and machine learning approaches have been applied to EHRs to identify or predict psychotic illness. Algorithms trained on EHR data typically rely on outcome labels in the form of International Classification of Diseases (ICD) diagnostic codes. To read the full article.
Validation of an ICD-Code-Based Case Definition for Psychotic Illness Across Three Health Systems. Deo AJ, Castro VM, Baker A, Carroll D, Gonzalez-Heydrich J, Henderson DC, Holt DJ, Hook K, Karmacharya R, Roffman JL, Madsen EM, Song E, Adams WG, Camacho L, Gasman S, Gibbs JS, Fortgang RG, Kennedy CJ, Lozinski G, Perez DC, Wilson M, Reis BY, Smoller JW. Schizophr Bull. 2024 May 10:sbae064. PMID: 38464074 PMCID: PMC10925367 DOI: 1101/2024.02.28.24303443