A data-driven feature extraction framework for predicting the severity of condition of congestive heart failure patients.

In this paper, we propose a novel methodology for utilizing disease diagnostic information to predict severity of condition for Congestive Heart Failure (CHF) patients. Our methodology relies on a novel, clustering-based, feature extraction framework using disease diagnostic information. To reduce the dimensionality we identify disease clusters using cooccurence frequencies.

Can death unrelated to secondary causes be predicted in intubated comatose tricyclic antidepressant-poisoned patients?

Context: It has been stated that the level of consciousness at presentation is the most sensitive clinical predictor of dysrhythmia and seizure in patients with tricyclic antidepressant (TCA) overdose.

Objective: To assess the prognostic value of the clinical characteristics and electrocardiographic (ECG) parameters in intubated comatose TCA-poisoned patients for predicting death.

Materials And Methods: In this retrospective, unmatched case-control study--conducted in Loghman-Hakim Poison Hospital in Tehran, Iran, between March 2005 and September 2010--the medical charts of 25 non-survived (cases) and 72 survived (controls) TCA-poisoned patients, initially presenting with deep coma (GCS ≤ 8) and being intubated before or after hospital presentation, were evaluated.