Purulent Bacterial Pericarditis: Rare Yet Lethal.

Bacterial pericarditis is a rare phenomenon that progresses rapidly and carries high mortality. Patients presenting with new pericardial effusions are often evaluated for concomitant rheumatologic, oncologic, and infectious diseases. We present a complex case of purulent pericarditis with pneumopericardium.

Late onset cardiac cirrhosis and portal hypertensive ascites after atrial fibrillation ablation.

Pulmonary vein stenosis is a potential complication following catheter ablation of atrial fibrillation (AF). We report the case of a patient with refractory ascites late after multiple catheter ablation procedures for AF. This is the first case report of portal hypertensive ascites due to acquired multiple pulmonary vein stenoses resulting in pulmonary hypertension (PH) and cardiac cirrhosis late after AF ablation. Despite extensive surgical reconstruction of the affected pulmonary veins, the patient has PH and right heart failure with persistent ascites and lower extremity edema.

A Case of Myocarditis and Near-Lethal Arrhythmia Associated With Interleukin-2 Therapy.

We present a case of a 48-year-old female who developed myocarditis and near fatal arrhythmias during high dose Il-2 therapy for metastatic renal cancer. On day 5 of therapy, the patient developed sudden onset chest pain, elevated cardiac enzymes and ST segment changes on EKG. Coronary angiogram was normal, however echocardiogram showed reduced ejection fraction and hemodynamic measurements showed elevated bilateral elevated filling pressures. The patient then developed episodes of recurrent ventricular arrhythmia, precipitated by bradycardia and PVC, requiring defibrillation and temporary pacemaker placement. Endomycardial biopsy was nonspecific showing fibrosis with subsequent cardiac MRI showed evidence of myocardial edema, consistent with Il-2 induced myocarditis in the setting of no prior cardiac history. After the discontinuation of Il-2 therapy, the patient displayed clinical improvement as well as improved ejection fraction. This case brings attention to the cardiac toxicities associated with high dose Il-2 therapy including potentially lethal arrhythmias and highlights the importance of careful cardiac screening prior to initiation of treatment.

Embedding and retrieving private metadata in electrocardiograms.

Due to the recent explosion of 'identity theft' cases, the safeguarding of private data has been the focus of many scientific efforts. Medical data contain a number of sensitive attributes, whose access the rightful owner would ideally like to disclose only to authorized personnel. One way of providing limited access to sensitive data is through means of encryption. In this work we follow a different path, by proposing the fusion of the sensitive metadata within the medical data. Our work is focused on medical time-series signals and in particular on Electrocardiograms (ECG). We present techniques that allow the embedding and retrieval of sensitive numerical data, such as the patient's social security number or birth date, within the medical signal. The proposed technique not only allows the effective hiding of the sensitive metadata within the signal itself, but it additionally provides a way of authenticating the data ownership or providing assurances about the origin of the data. Our methodology builds upon watermarking notions, and presents the following desirable characteristics: (a) it does not distort important ECG characteristics, which are essential for proper medical diagnosis, (b) it allows not only the embedding but also the efficient retrieval of the embedded data, (c) it provides resilience and fault tolerance by employing multistage watermarks (both robust and fragile). Our experiments on real ECG data indicate the viability of the proposed scheme.

Finding unusual medical time-series subsequences: algorithms and applications.

In this work, we introduce the new problem of finding time series discords. Time series discords are subsequences of longer time series that are maximally different to all the rest of the time series subsequences. They thus capture the sense of the most unusual subsequence within a time series. While discords have many uses for data mining, they are particularly attractive as anomaly detectors because they only require one intuitive parameter (the length of the subsequence), unlike most anomaly detection algorithms that typically require many parameters. While the brute force algorithm to discover time series discords is quadratic in the length of the time series, we show a simple algorithm that is three to four orders of magnitude faster than brute force, while guaranteed to produce identical results. We evaluate our work with a comprehensive set of experiments on electrocardiograms and other medical datasets.