Table 5.
Studies Employing Clustering Methods to Stratify Patients in a Cross-Diagnostic Setting
| Study | Subjects (N) | Measures | Algorithm | No. of Clusters (Method) | Cluster Descriptions | External Validation |
|---|---|---|---|---|---|---|
| Olinio et al., 2010 (113) | Adolescents (1653), including MDD (603), ANX (253), SUD (453) | Diagnosis (longitudinal) | LCGA | 6 (BIC) | Persistent depression | Demographic and case history variables |
| Persistent anxiety | ||||||
| Late onset anxiety, increasing depression | ||||||
| Increasing depression | ||||||
| Initially high, decreasing anxiety | ||||||
| Absence of psychopathology | ||||||
| Lewdanowski et al., 2014 (111) | SCZ (41), SAD (53), BPDp (73) | Clinical and cognitive measures | K means | 4 (Ward’s method) | Neuropsychologically normal | Diagnosis, demographic variables, and community functioning |
| Globally and significantly impaired | ||||||
| Mixed cognitive profiles (×2) | ||||||
| Kleinman et al., 2015 (112) | ADHD (23), BPD (10), BPDa (33), and HCs (18) | Continuous performance test measures | K means | 2 [Silhouette index (46)] | Sustained attention (–) , inhibitory control (–), impulsiveness (+), and vigilance (–) | Diagnosis |
| The converse of above |
External validation is defined as a data measure used to validate the derived classes that is of a different type to the data use to derive the classes. Wherever possible, we follow the authors’ own nomenclature for describing clusters and a (+) or (–) indicates relative improvement or deficit in the specified variable.
ADHD, attention-deficit/hyperactivity disorder; ANX, anxiety disorders; BPD(p/a), bipolar disorder (with psychosis/ADHD); BIC, Bayesian information criterion; DEP, depressive disorders (major depression and dysthymia); HC, healthy control; LCGA, latent class growth analysis; MDD, major depressive disorder; SAD, schizoaffective disorder; SCZ, schizophrenia; SUD, substance use disorder.