Clinical characterization and differentiation of B-SNIP psychosis Biotypes: Algorithmic Diagnostics for Efficient Prescription of Treatments (ADEPT)-1

Abstract

Clinically defined psychosis diagnoses are neurobiologically heterogeneous. The B-SNIP consortium identified and validated more neurobiologically homogeneous psychosis Biotypes using an extensive battery of neurocognitive and psychophysiological laboratory measures. However, typically the first step in any diagnostic evaluation is the clinical interview. In this project, we evaluated if psychosis Biotypes have clinical characteristics that can support their differentiation in addition to obtaining laboratory testing. Clinical interview data from 1907 individuals with a psychosis Biotype were used to create a diagnostic algorithm. The features were 58 ratings from standard clinical scales. Extremely randomized tree algorithms were used to evaluate sensitivity, specificity, and overall classification success. Biotype classification accuracy peaked at 91 % with the use of 57 items on average. A reduced feature set of 28 items, though, also showed 81 % classification accuracy. Using this reduced item set, we found that only 10-11 items achieved a one-vs-all (Biotype-1 or not, Biotype-2 or not, Biotype-3 or not) area under the sensitivity-specificity curve of .78 to .81. The top clinical characteristics for differentiating psychosis Biotypes, in order of importance, were (i) difficulty in abstract thinking, (ii) multiple indicators of social functioning, (iii) conceptual disorganization, (iv) severity of hallucinations, (v) stereotyped thinking, (vi) suspiciousness, (vii) unusual thought content, (viii) lack of spontaneous speech, and (ix) severity of delusions. These features were remarkably different from those that differentiated DSM psychosis diagnoses. This low-burden adaptive algorithm achieved reasonable classification accuracy and will support Biotype-specific etiological and treatment investigations even in under-resourced clinical and research environments.

Figure 1.

Glass effect sizes (y-axis) of the bio-factor domains (x-axis) used to create psychosis Biotypes. The healthy sample is represented by the zero line.The left plot shows effect sizes as a function of Biotype membership and the right plot shows effect sizes as a function of DSM diagnosis. The same subjects are used for both plots. The Cognition Measures are an average of BACS, antisaccade, and stop signal variables, Motor Reaction Time is speed of responding to saccade targets, ERP Amplitudes are an average of four measures of strength of neural response to auditory stimuli, and Intrinsic Brain Activity is an average of three measures indexing nonspecific brain activity (not locked to processing of any stimulus). BT1=Biotype-1, BT2=Biotype-2, BT3=Biotype-3, SZ=schizophrenia, SAD=schizoaffective disorder, and BDP=bipolar disorder with psychosis.

Figure 2.

The percent of cases conditioning on an initial group-type classification. The left plot shows the percent of cases with a particular DSM diagnosis across Biotypes, and the right plot shows the percent of cases with a particular Biotype across DSM diagnoses (e.g., the values within the black SZ line sum to 100; the values within the blue BT1 line sum to 100). BT1=Biotype-1, BT2=Biotype-2, BT3=Biotype-3, SZ=schizophrenia, SAD=schizoaffective disorder, and BDP=bipolar disorder with psychosis.

Figure 3.

Accuracy of Biotype classification in out-of-sample runs (y-axis) as a function of mean number of clinical features used in the decision out of 58 total (x-axis). The shaded area is the 99% confidence interval.

Figure 4.

The sensitivity, specificity, and AUC (area under the curve) of out of-sample tests for differentiating BT1 (left figure), BT2 (middle figure), or BT3 (right figure) from the other groups using an efficient set of clinical features.

Figure 5.

The top 10 most important clinical characteristics, in order of importance, for differentiating Biotypes. The bar chart at the top shows the normalized weights in the adaptive ADEPT algorithm for classifying a case into one group versus all others (BT1 or not, BT2 or not, BT3 or not). The feature names correspond to the items in the specific interview schedule (panss=Positive and Negative Symptom Scale; sfs=Birchwood Social Functioning Scale). The table at the bottom shows the means (SDs) of those items with the names associated with their item numbers (e.g., panss_n5=Difficulty in abstract thinking).