Detecting biomarkers associated with antipsychotic-induced extrapyramidal syndromes by using machine learning techniques.

BACKGROUND: Antipsychotic-associated extrapyramidal syndromes (EPS) are a common side effect that may result in discontinuation of treatment. Although some clinical features of individuals who develop specific EPSs are well defined, no specific laboratory parameter has been identified to predict the risk of developing EPS. METHODS: Three hundred and ninety hospitalizations of patients under antipsychotic medication were evaluated. Machine learning techniques were applied to laboratory parameters routinely collected at admission. RESULTS: Random forests classifier gave the most promising results to show the importance of parameters in developing EPS. Albumin has the maximum importance in the model with 4.28% followed by folate with 4.09%. The mean albumin levels of EPS and non-EPS group was 4,06 ± 0,40 and 4,24 ± 0,37 (p = 0,027) and folate level was 6,42 ± 3,44 and 7,95 ± 4,16 (p = 0,05) respectively. Both parameters showed lower levels in EPS group. CONCLUSIONS: Our results suggest that relatively low albumin and folate levels may be associated with developing EPS. Further research is needed to determine cut-off levels for these candidate markers to predict EPS.

Concordance rates of Doppler ultrasound and CT angiography in the grading of carotid artery stenosis: a systematic literature review.

Physicians have been increasingly relying on noninvasive imaging methods to grade carotid stenosis. The accuracy of Doppler ultrasound (DUS) and CT angiography (CTA) versus intra-arterial angiography (IA) has been assessed in many studies and at least two meta-analyses. Here, we performed a systematic review of studies that compared DUS to CTA. In a PubMed review of the literature from 2000 to 2009, we found 12 studies that compared DUS and CTA-based grading of carotid stenosis. Only 4 of them included at least 20 patients and provided data to classify the diseased arteries into the following categories: mild, moderate or severe NASCET stenosis or occlusion. We extracted 431 arteries from 244 patients (range per study: 48-164). It was not possible to distinguish symptomatic from asymptomatic stenoses. Nearly half arteries had severe stenosis (46% based on DUS and 43% based on CTA). The weighted kappa was 0.85 (95% CI 0.76-0.94), and the accuracy was 0.78. When the arteries were classified into medical and potentially surgical groups, the kappa was 0.76 (95% CI 0.70-0.83), and the accuracy was 0.89. Overall, 17% of the stenoses classified as medical based on DUS were reclassified as surgical based on CTA and 14% of the stenoses classified as medical based on CTA were reclassified as surgical based on DUS. The sparse available data comparing DUS and CTA suggest that the grading of a carotid stenosis as medical or potentially surgical remains uncertain in a relatively high proportion of patients.