A novel neural-network model for deriving standard 12-lead ECGs from serial three-lead ECGs: application to self-care.

Synthesis of the 12-lead ECG has been investigated in the past decade as a method to improve patient monitoring in situations where the acquisition of the 12-lead ECG is cumbersome and time consuming. This paper presents and assesses a novel approach for deriving 12-lead ECGs from a pseudoorthogonal three-lead subset via generic and patient-specific nonlinear reconstruction methods based on the use of artificial neural-networks (ANNs) committees. We train and test the ANN on a set of serial ECGs from 120 cardiac inpatients from the intensive care unit of the Cardiology Hospital of Lyon. We then assess the similarity between the synthesized ECGs and the original ECGs at the quantitative level in comparison with generic and patient-specific multiple-regression-based methods. The ANN achieved accurate reconstruction of the 12-lead ECGs of the study population using both generic and patient-specific ANN transforms, showing significant improvements over generic (p -value < or = 0.05) and patient-specific ( p-value < or = 0.01) multiple-linear-regression-based models. Consequently, our neural-network-based approach has proven to be sufficiently accurate to be deployed in home care as well as in ambulatory situations to synthesize a standard 12-lead ECG from a reduced lead-set ECG recording.

Toward personal eHealth in cardiology. Results from the EPI-MEDICS telemedicine project.

Despite many attempts to improve the management of acute myocardial infarction, only small trends to shorter time intervals before treatment have been reported. The self-care solution developed by the European EPI-MEDICS project (2001-2004) is a novel, very affordable, easy-to-use, portable, and intelligent Personal ECG Monitor (PEM) for the early detection of cardiac ischemia and arrhythmia that is able to record a professional-quality, 3-lead electrocardiogram (ECG) based on leads I, II, and V2; derive the missing leads of the standard 12-lead ECG (thanks to either a generic or a patient-specific transform), compare each ECG with a reference ECG by means of advanced neural network-based decision-making methods taking into account the serial ECG measurements and the patient risk factors and clinical data; and generate different levels of alarms and forward the alarm messages with the recorded ECGs and the patient's Personal electronic Health Record (PHR) to the relevant health care providers by means of a standard Bluetooth-enabled, GSM/GPRS-compatible mobile phone. The ECG records are SCP-ECG encoded and stored with the PHR on a secure personal SD Card embedded in the PEM device. The alarm messages and the PHR are XML encoded. Major alarm messages are automatically transmitted to the nearest emergency call center. Medium or minor alarms are sent on demand to a central PEM Alarm Web Server. Health professionals are informed by a Short Message Service. The PEM embeds itself a Web server to facilitate the reviewing and/or update of the PHR during a routine visit at the office of the general physician or cardiologist. Eighty PEM prototypes have been finalized and tested for several weeks on 697 citizens/patients in different clinical and self-care situations involving end users (188 patients), general physicians (10), and cardiologists (9). The clinical evaluation indicates that the EPI-MEDICS concept may save lives and is very valuable for prehospitalization triage.

New paradigms in telemedicine: ambient intelligence, wearable, pervasive and personalized.

After decades of development of information systems dedicated to health professionals, there is an increasing demand for personalized and non-hospital based care. An especially critical domain is cardiology: almost two third of cardiac deaths occur out of hospital, and victims do not survive long enough to benefit from in-hospital treatments. We need to reduce the time before treatment. But symptoms are often interpreted wrongly. The only immediate diagnostic tool to assess the possibility of a cardiac event is the electrocardiogram (ECG). Event and transtelephonic ECG recorders are used to improve decision making but require setting up new infrastructures. The European EPI-MEDICS project has developed an intelligent Personal ECG Monitor (PEM) for the early detection of cardiac events. The PEM embeds advanced decision making techniques, generates different alarm levels and forwards alarm messages to the relevant care providers by means of new generation wireless communication. It is cost saving, involving care provider only if necessary and requiring no specific infrastructure. This solution is a typical example of pervasive computing and ambient intelligence that demonstrates how personalized, wearable, ubiquitous devices could improve healthcare.