PO077 Mesalazine and Acute Myocarditis: Random Association or Real Risk? L. Filippucci* 1 , A. Russo 1 , L. Sanesi 2 , G. Vaudo 2 1 USL UMBRIA 1, REHABILITATIVE CARDIOLOGY AND SPORTS, PERUGIA, 2 DEPARTMENT OF MEDICINE, UNIT OF INTERNAL MEDICINE, POSTGRADUATE SCHOOL IN PHYSICAL EXERCISE AND SPORTS MEDICINE, SANTA MARIA HOSPITAL, TERNI, Italy Introduction: Mesalazine is the first-line treatment for ulcerative colitis. Main side effects include nausea, vomit and abdominal pain. Myocarditis is a rare 5-ASA-treatment complication. The mechanism underlying the myocardial toxicity is still unknown; it may be explained by a cell-mediated hypersensitivity. Objectives: A 20-year-old male, with ulcerative colitis treated for two weeks with 5-ASA, presented with fever and thoracic pain worsened by breathing. No viral syndromes in the last weeks. Negative physical examination. EKG (sinus tachycardia), chest X-ray (negative) and echocardiogram [Left ventricle with apical and anterior wall hypokinesia (EF 35%);no peri- cardial effusion] were performed. Laboratory studies revealed increased troponin (6.82 ng/ml) and NT-proBNP (1400 pg/ml) levels, whereas inflammatory markers, autoimmunity screening and viral serology were normal. In suspect of iatrogenic myocarditis, 5-ASA was discontinued, obtaining rapid improvement of clinical and laboratory features, and regional left ventricular function. Cardiac MRI showed areas of T2 hyperintensity involving posterior and middle-lateral myocardium, as inflammatory exudation, and non-ischaemic pattern of late gadolinium enhancement (LGE) in subepicardical areas after contrast administration. On the basis of clinical history and radiological signs, 5-ASA-related acute myocarditis was diagnosed. Methods: The patient moved to Sports and Rehabilitative Cardiology unit, where the Holter EKG excluded complex arrhythmias and echocardiography confirmed that left ventricle systolic function was fully recovered (EF 66%). Results: Cardiac disease may occur during inflammatory bowel disorders, due not only to inflammatory state itself but also to drug-induced toxicity. The latter is a rare but life-threatening condition: 8 cases only have been referenced in the literature. In our patient MRI was essential in diagnosing because subepicardic LGE excluded ischaemic myocardial infarction. Discontinu- ation of 5-ASA is the key strategy for treatment, which leads to rapid clinical recovery. Conclusion: In this patient, the absence of “flu-like” preceding symptoms and vasculitis or connective tissue signs, combined with negative labs allowed us to exclude viral and autoimmune aetiology of myocarditis, whereas time between taking the 5-ASA and onset of symptoms with rapid recovery after interrupting the medication led to our final diagnosis of 5-ASA-related acute myocarditis. Disclosure of Interest: None declared PO078 Rare Case Report of Classic Dengue Fever With Pericardic Effusion Manifestation L. L. B. Bandeira 1,1,1 , I. P. B. dos Anjos 1 , P. R. S. Dantas 1 , R. R. Soares 1 , C. T. dos Santos 1 , T. L. D. S. Macedo 1 , M. D. S. C. Júnior 2 , V. F. Marcolla 3 , E. Rabello 4 , A. R. B. Neto 1 , A. A. B. Aragão 1 , I. P. B. Aragão* 1 1 Medical school, severino sombra university, 2 Medical school, grande rio university, vassouras, 3 Cardiology, state university of rio de janeiro, rio de janeiro, 4 Severino sombra university, vassouras, Brazil Introduction: The cardiac involvement and extracavitary effusion occurred in dengue are related to the severe form of the disease although, most of the times, it is cited as transient and self-limiting. Objectives: Discuss a clinical case of dengue fever withunusual manifestation of pericardial effusion that did not regress after 1 year of follow-up, despite clinical and serological improvement. Methods: The patient’s chart in regular consultation with the cardiology office was analyzed and through serum exams and imaging the case data were evaluated. Results: MAT, female, 62 years old, initiated in February 2015 fatigue, nocturnal sweating, dry cough, pain in the orofaringe, fever with axilar tempearture of 38,4  C and chills. Patient went to the emergency from where she was sent home with a prescription of amoxicilin 500mg 3x/day for 7 days. Evolved with postural hypotension, vertigo and tiredness in responde to medium efforts intermitently during a month. Then evolved with the same symptoms in the course of the year of 2015 with an improvement in the end of the year. Laboratorial exams done in March: hematocrit 36%, eritrocit sedimentation index 68, ultra sensitive C reactive protein 4,65mg/dL, IgM sorology for Dengue 1,14 and IgG 5,07, nitrogenated compounds, hepatography and platelets without evidences. In April the Toracic Radiography was normal, however the exam showed estriated subpleural opacities, and ground-glass opacities on the superior right and left and little non calcified difused nodular opacities and PE. The Ecocardiogram done in May evidenciated light to moderate PE without diastolic restriction and thickening. Treatment was initiated: colchicina and ibuprofen until November. The Echocardiograms that were done in June, September and November of 2015, and June and November of 2016, however, showed that the effusion was mantained (light). Tuberculosis, pericardiditis, thyroid disease and collagenasis were contemplated as diferential diagnosis and discarded by the exams. Conclusion: The diagnosis should follow the protocols with great attention to classic symptoms. According to dynamic evolution, the use of imaging tests such as ultrasound and echocardiogram during clinical management becomes advisable in order to avoid outcomes that result in increased mortality in patients, even if they present mild dengue sintomatology. Disclosure of Interest: None declared PO082 Complementary Supportive Therapy For Symptomatic Patients With A Left Ventricular Dilatation and Reduced Ejection Fraction M. Jakovljevic* 1 1 Polyclinic for cardiovascular diseases and prevention, Korcula, Croatia Introduction: Some of the main goals of treatment in patients with heart failure (HF) is improving the quality of life and functional capability. Objectives: The aim of the study is to assess the effect of complementary supportive therapy (CST) on the quality of life and functional capability in patients with heart failure and reduced ejection fraction (HFrEF). Methods: We investigated 33 patients with left ventricular dilatation (LVIDd > 60 mm) and reduced ejection fraction (EF<40% )in 76 CST periods. Prior to each CST period, therapy was optimized (OMT) during one month. Complementary supportive therapy (CST) consists of a 10-day session. In addition to OMT, the patients were treated with carnitine, coenzym Q-10, L-arginine, vitamin B, vitamin E, vitamin C, selenium while lying for 30 minutes inside a pulsating electromagnetic field (up to 30 microTeslas with indi- vidual frequency settings) and inhaling 02-. Before and after each CST period they were asked to evaluate the quality of life using the Minnesota Living with Heart Failure. Questionnaire (MLHFQ)and the visual analogue scale and EF, LVIDd and NYHA class were determined. Statistical analysis of the CST was based on the t-test, Spearman’s rank correlation coefficient and Wilcoxon’s signed-ranks test. The median monitoring period was 60 months (ranging 11-122). Results: After administering the complementary supportive therapy, a statistically signif- icant improvement (p< 0.05) was noticed in the particular items of the MLHFQ, in emotional and physical dimensions. The values of VAS and EF increased whereas NYHA and LVIDd decreased significantly (p<0.001). Conclusion: CST significantly improved the quality of life and functional capacity of pa- tients with HFrEF. Disclosure of Interest: None declared PO086 Machine Learning Approaches Improve Noninvasive Prediction of Ischemic From Non-Ischemic Cardiomyopathies M. Baydoun 1 , L. Safatly 2 , J. Walsh 2 , O. Abou Hassan 2 , W. Jaroudi 3 , A. El Hajj 4 , H. Ghaziri* 1 , H. Isma’eel 5 1 Beirut Research and Innovation Center, 2 American University of Beirut, Lebanon, 3 Internal Medicine Department, Clemenceau Medical Center, 4 Faculty of Engineering and Architecture, 5 Internal Medicine Department, American University of Beirut, Lebanon, Beirut, Lebanon Introduction: The gold standard for the diagnosis of ischemic cardiomyopathy is coronary angiography. However, risk score models are used to stratify patients who are most likely to benefit from the procedure. These score models have assumed traditional regression ana- lyses to associate between risk factors and cardiovascular outcomes. Data mining and machine learning allows for improved accuracy in predicting the outcome. Objectives: Our aim is to implement machine learning algorithms to interpret clinical, ECG, and echocardiography data to determine need for coronary angiography. Methods: We identified a cohort of 204 consecutive patients with reduced ejection fraction (EF<50% on echocardiography) and who received a subsequent coronary angiogram and ECG within 90 days between July 1st 2013 and December 1st 2015. Several algorithms were tested to obtain the best subset of features along with the corresponding ranking of the importance of each clinical, ECG and echocardiography (including speckle tracking) variables. These included Decision Tree Classification, ensemble learning techniques (boosting and bagging), and Deep Learning Neural Networks. Results: The resulting algorithms contained between 9-17 variables. The post-systolic shortening (PSS) and PSS deceleration time, especially of the basal anterior and infero-septal segments respectively, and Right bundle branch block were highly ranked variables in many of the algorithms. The first ranked feature in all algorithms was regional wall motion (RWM) and had comparable AUC across all approaches. However, the accuracy results of the downstream variables diverged within each algorithm. AUC was lowest for the decision tree (0.72) and the Deep Learning NN (0.767) and highest for the Logitboost (0.839) when RWM was excluded. As such, the power of the algorithms to sway the final result from an ischemic to non-ischemic output or vice versa was shown to be the greatest with Deep learning ANN algorithm. Conclusion: Machine learning algorithms, particularly the AdaboostM1 and GentleBoost models, are easy algorithms to implement and interpret with high accuracy. They outperform the traditional regression analyses, in predicting ischemic cardiomyopathy from clinical, ECG and echocardiographic data. These algorithms may be integrated as tools to determine need for coronary angiography to diagnose this disease. Disclosure of Interest: None declared PO087 Importance of Left Ventricular Global Longitudinal Strain In Cocaine Abuse Patients With Heart Failure N. Sen* 1 , A. Jain 1 , S. Tanwar 2 , R. K. Gokhroo 3 1 Cardiology, Narayana Hrudayalaya, Jaipur, 2 Cardiology, HG SMS HOSPITAL, Jaipur, 3 Cardiology, JLN Medical College, Ajmer, India 404 GHEART Vol 13/4/2018 j December, 2018 j POSTER/2018 WCC PO003-PO653 POSTER ABSTRACTS