Stepwise regression analysis of an intensive 1-year study of delirium tremens.

An intensive 1-year study was carried out on 41 male patients, mean age 49, mean hospitalization time 49 days, admitted to a special ward of the Beckomberga Hospital with the diagnosis of delirium tremens and 50 concomitant somatic and psychiatric diagnoses (1--9 per capita), and given a standardized treatment. The mean duration of delirium tremens after admission was 2 days; 76% recovered within 48 h. The duration after admission was positively correlated to age, number of previous delirium tremens, negatively correlated to B-haemoglobin and B-haematocrit for laboratory data obtained within the first 24 h and was positively correlated to blood sugar and S-creatinine on data taken within 40 h (Pearson correlation matrix). Stepwise multiple regression (SWR) based on 46 quantitative and dummy variables (the latter used to represent the presence of various concomitant diseases) was employed to identify the factors predicting the duration of delirium tremens. On final SWR analysis, which limited the number of observations to cases with complete observation vectors, the following regression equation was obtained: Duration after admission = 3.57--0.93 (S-magnesium)--0.29 (B-eosinophils) + 0.62 (liver disease), P greater than 0.05, n = 14. Although the regression coefficients were not statistically significant, S-magnesium, negatively associated with the duration after admission, offered 20% out of the total 38% of explanation given, whereas B-eosinophils, negatively associated, offered 12%, and liver disease, positively associated, 6%. The choice by the SWR program of S-magnesium as the most important factor in predicting the duration of delirium tremens is consistent with clinical evidence that alcohol ingestion causes magnesium diuresis and that magnesium deficiency is present in chronic alcoholism. In view of this knowledge, it is reasonable to assume that the lack of statistical significance is due to the small sample size rather than to the alternative that no explanation is offered by S-magnesium. Furthermore, B-haemoglobin, S-potassium, S-ASAT, and S-ALAT, known to be characteristically altered in delirium tremens, were found on forcing (a variant of SWR) to be of secondary importance to S-magnesium as explaining factors, whereas blood sugar and S-creatinine derived part of their explaining power from S-magnesium. In conclusion, extensive use of SWR analysis based on 46 potential explaining variables points to serum magnesium concentration as the most important factor in predicting the duration of delirium tremens.