HIV Lipodystrophy Case Definition using Artificial Neural Network Modelling

Objective

A case definition of HIV lipodystrophy has recently been developed from a combination of clinical, metabolic and imaging/body composition variables using logistic regression methods. We aimed to evaluate whether artificial neural networks could improve the diagnostic accuracy.

Methods

The database of the case-control Lipodystrophy Case Definition Study was split into 504 subjects (265 with and 239 without lipodystrophy) used for training and 284 independent subjects (152 with and 132 without lipodystrophy) used for validation. Back-propagation neural networks with one or two middle layers were trained and validated. Results were compared against logistic regression models using the same information.

Results

Neural networks using clinical variables only (41 items) achieved consistently superior performance than logistic regression in terms of specificity, overall accuracy and area under the ROC curve. Their average sensitivity and specificity were 72.4 and 71.2%, as compared with 73.0 and 62.9% for logistic regression, respectively (area under the ROC curve, 0.784 vs 0.748). The discriminating performance of the neural networks was largely unaffected when built excluding 13 parameters that patients may not have readily available. The average sensitivity and specificity of the neural networks remained the same when metabolic variables were also considered (total 60 items) without a clear advantage against logistic regression (overall accuracy 71.8%). The performance of networks considering also body composition variables was similar to that of logistic regression (overall accuracy 78.5% for both).

Conclusions

Neural networks may offer a means to improve the discriminating performance for HIV lipodystrophy, when only clinical data are available and a rapid approximate diagnostic decision is needed. In this context, information on metabolic parameters is apparently not helpful in improving the diagnosis of HIV lipodystrophy, unless imaging and body composition studies are also obtained.

Submergence induces expansin gene expression in flooding-tolerant Rumex palustris and not in flooding-intolerant R. acetosa

Ethylene-enhanced leaf elongation upon submergence is part of the survival mechanism of Rumex palustris Sm. plants that grow in frequently flooded areas. Other Rumex species, like R. acetosa L., do not possess this ability and can therefore only survive in habitats that are not frequently inundated. Expansins are proteins that induce extension of isolated cell walls, and therefore might play a role in the stimulation of petiole elongation, also in Rumex. We report here on the identification of several gene sequences encoding for alpha-expansins in R. palustris and R. acetosa plants. The pattern of transcript accumulation of one of these genes, Rp-EXP1, could be correlated with the pattern of leaf elongation in R. palustris after submergence or ethylene treatment. Induction of expansin gene activity was not found in R. acetosa upon these treatments, indicating that ethylene induces the expression of expansin genes in leaves of species that exhibit flooding-induced shoot elongation.

Ocular torsion before and after 1 hour centrifugation

To assess a possible otolith contribution to effects observed following prolonged exposure to hypergravity, we used video oculography to measure ocular torsion during static and dynamic conditions of lateral body tilt (roll) before and after 1 h of centrifugation with a Gx-load of 3 G. Static tilt (from 0 to 57 degrees to either side) showed a 10% decrease in otolith-induced ocular torsion after centrifugation. This implies a reduced gain of the otolith function. The dynamic condition consisted of sinusoidal body roll (frequency 0.25 Hz, amplitude 45 degrees) about an earth horizontal and about an earth vertical axis (respectively, "with" and "without" otolith stimulation). Before centrifugation the gain of the slow component velocity (SCV) was significantly lower "with" otolith stimulation than "without" otolith stimulation. Apparently, the contribution of the otoliths counteracts the ocular torsion response generated by the semicircular canals. Therefore, the observed increase in SCV gain in the condition "with" otolith stimulation after centrifugation, seems in correspondence with the decreased otolith gain in the static condition.

Saccular impact on ocular torsion

When someone is tilted laterally, the shear force on the maculae of the utriculus and the sacculus is described by the sine and the cosine of the angle of tilt, respectively. So both the sacculus and the utriculus are stimulated, but in the literature, ocular torsion is normally attributed to utricular function alone (and, thus, seen as a response to y-axis linear acceleration). However, on the base of a series of experiments on a tilt chair, a linear track, human centrifuges, and during parabolic flights, we conclude that the sacculus contributes to ocular torsion as well (there is a response to z-axis linear acceleration). The data suggest that the ratio of the utricular and saccular impact on ocular torsion is 3:1. The utriculus generates conjugate and the sacculus disjunctive torsional eye movements.