The apolipoprotein E gene (APOE), located on human chromosome 19, has three common alleles (ϵ2, ϵ3, ϵ4) which encode for the three main isoforms indicated as E2, E3 and E4 respectively. Several findings indicate ϵ4 allele as an important risk factor in both sporadic and familial late-onset Alzheimer's disease (AD). Pathological changes similar to AD are seen in almost all patients with Down's syndrome (DS) aged over 35 (senile plaques, neurofibrillary tangles and neuronal loss); a proportion of these may subsequently develop dementia. Aim of this study is to evaluate the possible pathological role of ϵ4 allele as risk factor for developing AD in a DS population. Apoe ϵ4 allele frequency is not significantly different in DS cases and controls. We found a statistically significant inverse correlation between full scale IQ values and age of patients in the subgroup of DS subjects selected for the presence of at least one ϵ4 allele, while no correlation was observed in DS subjects with other ApoE genotypes. A longitudinal analysis of cognitive performances (available in 38 patients) showed a faster rate of decline in intellectual ability in those subjects carrying at least one ϵ4 allele. Our data support the hypothesis that ApoE ϵ4 allele has a contributory role in accelerating the mental deterioration of AD-type in DS patients. © 1997 Elsevier Science B.V.

An approach to electrocardiogram (ECG) interpretation which exploits a uniform notation to define structures to be found and interpretation strategies is presented. The study of the ECG visual interpretation activity by cardiologists provided the guidelines for the development of the system for ECG interpretation (SIECG), an automatic assistant able to identify and evaluate structures which are tracks of meaningful events in an ECG. SIECG follows a data-driven strategy, i.e. a sequence of computational actions determined step by step. The strategy provides for the accumulation of findings at different levels of abstraction. A method for defining strategies based on conditional attributed rewriting systems has been defined which provides SIECG with reflective abilities. Some examples have shown situations in which the system has to exploit this feature

A system aimed at a better exploitation by a cardiologist of descriptions supplied by present ECG interpretation systems is presented. This goal is achieved by looking at the ECG as a visual sentence, whose elements are graphical representations of the phenomena of interest to cardiologists. They are thus allowed to exploit and enhance their culture of visual intepretation in the interaction with the report generator of the system.

The authors present an approach to the automatic analysis of electrocardiograms (ECGs) based on the criteria used by a practising cardiologist in the visual interpretation of ECGs. Practising cardiologists primarily exploit shape to focus their attention on the ECG features to be studied in detail. Shape is also an important feature in the description, recognition, and classification of patterns. In order to assist the cardiologist in this activity, a method of producing shape descriptions of the tracing is presented. This method is based on attributed conditional rewriting systems and allows the integration of structural methods and traditional signal processing techniques. The architecture of a system for the integration of these tools and the construction of descriptions is presented. The use of such a system to set up and manage archives of tracings is discussed.<>

A technique for the recognition of structures in an electrocardiogram (ECG) and its application to the case of P and T-wave detection are presented. The technique combines a structural approach to the detection and description of structures, based on their shape properties, with a method based on multiple-valued logic for plausible evaluation of their medical meaning. The possibility of visualizing both the shapes of the structures and the reasoning process allow a human user to understand and control the recognition process. The method is general enough to be applied to the recognition and classification of the different patterns in the ECG

An automatic system which sets up high-level descriptions of the ECG, based on its medical shape features, from the low-level descriptions of the numerical techniques is discussed. These descriptions are organized into a description scheme, thus making it possible for physicians to use visual interpretation to control the whole description process. At each moment during an interpretation activity, the content of the data structure can be shown to the user in a graphical manner. Using this method, the progress of the process and the reasons why an interpretation strategy is followed can be controlled by the user

The knowledge employed by a cardiologist in the interpretation of an electrocardiogram (ECG) can be represented by means of a system of conditional attributed rewriting rules (calL-systems), a generative device introduced in (1) which has been successfully applied in other experiments (2,3,4). Each rule codes a chunk of knowledge necessary to recognize a structure in the ECG and evaluate its characteristics. Attributed rewriting systems have been proposed in (5) to overcome the limitations of the statistical and syntactical approaches to pattern recognition which were both used separately for ECG interpretation (6,7). This coding of the physician’s knowledge allows one to derive a Pattern Directed Inference System (PDIS) (8) able to describe the ECG at hand. Once the ECG is described, the descriptions can be stored in an Information Retrieval System and retrieved even by combination of characteristics not foreseen by the developer of the system, but which can be of interest to a physician in the case at hand.