Risk assessment of alcohol withdrawal seizures with a Kohonen feature map

Recently, it has been suggested that alcohol-induced hyperhomocysteinaemia in patients suffering from chronic alcoholism might be a risk factor for al cohol withdrawal seizures. In the present follow-up study 12 patients with chronic alcoholism who suffered from withdrawal seizures had significantly higher revers of homocysteine (Hcy) on admission (71.43 +/- 25.84 mol/l) th an patients (n=37) who did not develop seizures (32.60+/-24.87 mol/l; U=37. 50, p=0.0003). Using a logistic regression analysis, withdrawal seizures we re best predicted by a high Hcy level on admission (p<0.01; odds ratio 2.07 ). Based on these findings we developed an artificial neural network system (Kohonen feature map, KFM) for an improved prediction of the risk of alcoh ol withdrawal seizures. Forty-nine patients with chronic alcoholism (12 wit h alcohol withdrawal seizures and 37 without seizures) were randomized into a training set and a test set. Best results for sensitivity of the KFM was 83.3% (five of six seizure patients were predicted correctly) with a speci ficity of 94.4% (one false positive prediction of 19 patients). We conclude that in patients with alcohol-induced hyperhomocysteinaemia the KFM is a u seful tool to predict alcohol withdrawal seizures. NeuroReport 12:1235-1238 (C) 2001 Lippincott Williams & Wilkins.