Classification of Trustee ‘type’ from Investors’ behavior in two-party exchange. (A B) Depiction of model-free clustering approach using multi-round trust game data. The data used in this approach was collected in previous studies [34, 46–49] A. The multi round trust game is played between a healthy investor (black player) and a ‘target’ trustee (red player). The ‘target’ trustee was one of the following ‘types’: major depressive disorder (MDD), personal , borderline personality disorder - non-medicated (BPD-N) , borderline personality disorder - medicated (BPD-M) , impersonal , autism spectrum disorder (ASD) , and attention deficit hyperactivity disorder (ADHD) . The approach described in detail in Koshelev et al. (2010) examines the investor behavior as a polynomial of past rounds of investments and returns (see panel B). i1, i2, … , it are the investments made by the investor during round t. Likewise, r1, r2, … , rt are the repayments made by the trustee during round t. Classification of the investor-trustee dyad: is performed by predicting the investors’ decision at round t using a polynomial where the order of the polynomial, the number of past rounds, and the number of clusters discovered are left as free parameters to be discovered. The diagnostic categories for the trustee ‘type’ listed in panel A are blinded in this classification procedure. Only the behavior (investments and repayments over rounds) in the multi-round trust game is used. The result of this classification determined that a first-order polynomial, two rounds back, and four clusters were optimal. (B) Resulting four clusters and classification of diagnostic categories for model-free biosensor approach. The resulting classification identified four clusters where individuals from each diagnostic category were over- (blue bars) or under-represented (black bars). Vertical axes: investor-trustee dyad types (from top to bottom): MDD, personal , BPD-N , BPD-M , impersonal , ASD , and ADHD . Only the statistically significant categories (that is, greater than 1.5 standard deviations from the mean) are labeled in each plot. Horizontal axes: standard deviations from the mean. Figure adapted from .