Symptoms may be more useful prognostic markers for mental illness than diagnoses. We sought to investigate symptom domains in women with pre-existing severe mental illness (SMI; psychotic and bipolar disorder) as predictors of relapse risk during the perinatal period.

Data were obtained from electronic health records of 399 pregnant women with SMI diagnoses from a large south London mental healthcare provider. Symptoms within six domains characteristically associated with SMI (positive, negative, disorganization, mania, depression, and catatonia) recorded in clinical notes 2 years before pregnancy were identified with natural language processing algorithms to extract data from text, and associations investigated with hospitalization during pregnancy and 3 months postpartum.

Seventy-six women (19%) relapsed during pregnancy and 107 (27%) relapsed postpartum. After adjusting for covariates, disorganization symptoms showed a positive association at borderline significance with relapse during pregnancy (adjusted odds ratio [aOR] = 1.36; 95% confidence interval [CI] = 0.99–1.87 per unit increase in number of symptoms) and depressive symptoms negatively with relapse postpartum (0.78; 0.62–0.98). Restricting the sample to women with at least one recorded symptom in any given domain, higher disorganization (1.84; 1.22–2.76), positive (1.50; 1.07–2.11), and manic (1.48; 1.03–2.11) symptoms were associated with relapse during pregnancy, and disorganization (1.54; 1.08–2.20) symptom domains were associated with relapse postpartum.

Positive, disorganization, and manic symptoms recorded in the 2 years before pregnancy were associated with increased risk of relapse during pregnancy and postpartum. The characterization of routine health records from text fields is relatively transferrable and could help inform predictive risk modelling.

Research in schizophrenia and pregnancy has traditionally been conducted in small samples. More recently, secondary analysis of routine healthcare data has facilitated access to data on large numbers of women with schizophrenia.

To discuss four scientific advances using data from Canada, Denmark and the UK from population-level health registers and clinical data sources.

Narrative review of research from these three countries to illustrate key advances in the area of schizophrenia and pregnancy.

Health administrative and clinical data from electronic medical records have been used to identify population-level and clinical cohorts of women with schizophrenia, and follow them longitudinally along with their children. These data have demonstrated that fertility rates in women with schizophrenia have increased over time and have enabled documentation of the course of illness in relation with pregnancy, showing the early postpartum as the time of highest risk. As a result of large sample sizes, we have been able to understand the prevalence of and risk factors for rare outcomes that would be difficult to study in clinical research. Advanced pharmaco-epidemiological methods have been used to address confounding in studies of antipsychotic medications in pregnancy, to provide data about the benefits and risks of treatment for women and their care providers.

Use of these data has advanced the field of research in schizophrenia and pregnancy. Future developments in use of electronic health records include access to richer data sources and use of modern technical advances such as machine learning and supporting team science.