Deficits in social cognition (SC) are significantly related to community functioning in schizophrenia (SZ). Few studies investigated longitudinal changes in SC and its impact on recovery. In the present study, we aimed: (a) to estimate the magnitude and clinical significance of SC change in outpatients with stable SZ who were assessed at baseline and after 4 years, (b) to identify predictors of reliable and clinically significant change (RCSC), and (c) to determine whether changes in SC over 4 years predicted patient recovery at follow-up.

The reliable change index was used to estimate the proportion of true change in SC, not attributable to measurement error. Stepwise multiple logistic regression models were used to identify the predictors of RCSC in a SC domain (The Awareness of Social Inference Test [TASIT]) and the effect of change in TASIT on recovery at follow-up.

In 548 participants, statistically significant improvements were found for the simple and paradoxical sarcasm of TASIT scale, and for the total score of section 2. The reliable change index was 9.8. A cut-off of 45 identified patients showing clinically significant change. Reliable change was achieved by 12.6% and RCSC by 8% of participants. Lower baseline TASIT sect. 2 score predicted reliable improvement on TASIT sect. 2. Improvement in TASIT sect. 2 scores predicted functional recovery, with a 10-point change predicting 40% increase in the probability of recovery.

The RCSC index provides a conservative way to assess the improvement in the ability to grasp sarcasm in SZ, and is associated with recovery.

Resilience is defined as the ability to modify thoughts to cope with stressful events. Patients with schizophrenia (SCZ) having higher resilience (HR) levels show less severe symptoms and better real-life functioning. However, the clinical factors contributing to determine resilience levels in patients remain unclear. Thus, based on psychological, historical, clinical and environmental variables, we built a supervised machine learning algorithm to classify patients with HR or lower resilience (LR).

SCZ from the Italian Network for Research on Psychoses (N = 598 in the Discovery sample, N = 298 in the Validation sample) underwent historical, clinical, psychological, environmental and resilience assessments. A Support Vector Machine algorithm (based on 85 variables extracted from the above-mentioned assessments) was built in the Discovery sample, and replicated in the Validation sample, to classify between HR and LR patients, within a nested, Leave-Site-Out Cross-Validation framework. We then investigated whether algorithm decision scores were associated with the cognitive and clinical characteristics of patients.

The algorithm classified patients as HR or LR with a Balanced Accuracy of 74.5% (p < 0.0001) in the Discovery sample, and 80.2% in the Validation sample. Higher self-esteem, larger social network and use of adaptive coping strategies were the variables most frequently chosen by the algorithm to generate decisions. Correlations between algorithm decision scores, socio-cognitive abilities, and symptom severity were significant (pFDR < 0.05).

We identified an accurate, meaningful and generalizable clinical-psychological signature associated with resilience in SCZ. This study delivers relevant information regarding psychological and clinical factors that non-pharmacological interventions could target in schizophrenia.