Background. In bipolar disorder treatment, accurate prediction of manic and depressive episodes is paramount but remains difficult. A novel idiographic approach to prediction is to monitor generic early warning signals (EWS), which may manifest in symptom dynamics. EWS could thus form personalized alerts in clinical care. The present study investigated whether EWS can anticipate mood shifts in individual patients with bipolar disorder. Methods. Twenty bipolar type I/II patients participated in ecological momentary assessment (EMA), completing five questionnaires a day for four months (Mean=491 observations per person). Weekly completed symptom questionnaires on depressive (Quick Inventory for Depressive Symptomatology Self-Report) and manic (Altman Self-Rating Mania Scale) symptoms were used to determine transitions. EWS (rises in autocorrelation at lag-1 and standard deviation) were calculated in moving windows over 17 affective and symptomatic EMA items. Positive and negative predictive values were calculated to determine clinical utility. Results. Eleven (of the twenty) patients reported 1-2 manic or depressive transitions. The presence of EWS increased the probability of impending transitions towards depression and mania from 32-36% to 46-48% (autocorrelation) and 29-41% (standard deviation). However, the absence of EWS could not be taken as a sign that no transition would occur in the near future. The momentary states that indicated nearby transitions most accurately (predictive values: 65-100%) were cheerfulness, focusing ability, full of ideas, worry, racing thoughts, agitation, energy, and tiredness. Large individual differences in the utility of EWS were found.Conclusions. EWS may improve anticipating manic and depressive transitions in bipolar disorder, but await further empirical testing.