Stevo Lukic

Adaptive neuro fuzzy selection of heart rate variability parameters affected by autonomic nervous system

Heart rate variability (HRV) parameters can be used as specific indicator of autonomic nervous system (ANS) behavior. ANS, with its main two branches, sympathetic and parasympathetic, may be considered as a coordinated neuronal network which controls heart rate continually. Many parameters define heart rate variability in different domains such as time, frequency or nonlinear. An excessively high computational complexity can occur when developing models for medical applications when the best set of inputs to use is not known. To build a model that can predict a specific process output, it is desirable to select a subset of variables that are truly relevant or the most influential to this output. This procedure is typically called variable selection, and it corresponds to finding a subset of the full set of recorded variables that exhibits good predictive abilities. In this study an architecture for modeling complex systems in function approximation and regression was used, based on using adaptive neuro-fuzzy inference system (ANFIS). Variable searching using the ANFIS network was performed to determine how the ANS branches affect the most relevant HRV parameters. The method utilized may work as a basis for examination of ANS influence on HRV activity.

Are lamotrigine kinetics altered in menopause? Observations from a drug monitoring database

To assess possible alterations in the pharmacokinetics of lamotrigine (LTG) in menopause, we reviewed the database of the drug monitoring service at the Karolinska University Hospital. Dose/plasma concentration (D/C) ratios of LTG in different age groups of women under treatment with LTG were compared with ratios for men. For further comparison, D/C ratios were calculated for men and women treated with carbamazepine (CBZ). D/C ratios were available for 752 men and 1115 women on LTG, and for 3464 men and 3088 women on CBZ. The D/C ratios of CBZ were very similar among men and women in all age groups under study. In contrast, LTG D/C ratios seemed to decline in women 51-55 years of age, and were in this age group significantly lower among women than among men (P<0.05). Our data suggest that there may be a transient decline in clearance of LTG in conjunction with presumed menopause.

Artificial neural networks based prediction of cerebral palsy in infants with central coordination disturbance.

BACKGROUND In a previous study we demonstrated that heart variability parameters (HRV) could be helpful clinically as well as a prognostic tool in infants with central coordination disturbance (CCD). In recent years, outcome predictions using artificial neural networks (ANN) have been developed in many areas of health care research, but there are no published studies considered ANN models for prediction of cerebral palsy (CP) development. OBJECTIVE To compare the results of an ANN analysis with results of regression analysis, using the same data set and the same clinical and HRV parameters. METHODS The study included 35 infants with CCD and 37 healthy age and sex-matched controls. Time-domain HRV indices were analyzed from 24h electrocardiography recordings. Clinical parameters and selected time domain HRV parameters are used to predict CP by logistic regression, and then an ANN analysis was applied to the same data set. Input variables were age, gender, postural responses, heart rate parameters (minimum, maximum and average), and time domain parameters of HRV (SDNN, SDANN and RMSSD). For each of one the pairs of ANN and clinical predictors, the area under the receiver operating characteristic (ROC) curves with test accuracy parameters were calculated and compared. RESULTS In the observed dataset, ANN model overall correctly classified all infants, compared with 86.11% correct classification for the logistic regression model, and compared with 67.65% and 77.14% for SDANN and SDNN respectively. CONCLUSIONS ANN model, based on clinical and HRV data can predict development of CP in patients with CCD with accuracy greater than 90%. Our results strongly indicate that a well-validated ANN may have a role in the clinical prediction of CP in infants with CCD.

Heart rate variability in infants with central coordination disturbance.

Despite a remarkable medical progress in the field of Developmental Medicine and Child Neurology, early identification of infants at risk for permanent motor disabilities still presents challenge for both clinicians and researchers. As an indicator of cardiac autonomic control, it was shown that heart rate variability (HRV) might reflect not only sympathetic or parasympathetic activity but also functional integrity of the central nervous system (CNS). Furthermore a pattern of HRV was demonstrated to correlate with motor developmental outcome in high risk infants. The purpose of this study was to analyze the clinical usefulness as well as predictive value of time-domain HRV parameters in infants with central coordination disturbance. The study included 35 infants with central coordination disturbance and 37 healthy age and sex-matched controls. Time-domain HRV indices were analyzed from 24-h electrocardiography recordings. We found significantly lower values of SDNN, SDANN and RMSSD parameters in infants with central coordination disturbance compared to controls. Additionally, logistic regression analyses demonstrated independent predictive value of parameters SDNN and SDANN in infants who subsequently developed cerebral palsy (CP). By performing receiver operating characteristic (ROC) analyses, the optimal cut-off value of SDNN<=48ms predicted CP with a sensitivity of 68.7% (95% CI 41.4-88.9) and specificity of 84.2% (95 CI 60.4-96.4) while the optimal cut-off value of SDANN<=41ms predicted CP with a sensitivity of 87.5% (95% CI 61.6-98.1) and specificity of 57.9% (95 CI 33.5-79.7). We are in opinion that time domain HRV analysis could be helpful clinically as well as a prognostic tool in infants with central coordination disturbance.

Blood Pressure Variability and Left Ventricular Mass Index in Children

Clinical implications of blood pressure variability (BPV) on subclinical organ damage in children are unknown. The authors sought to explore the potential utility of two newly derived BPV indices: weighted standard deviation (wBPSD) and real average variability (ARV), as well as two standard ambulatory blood pressure indices: average 24‐hour systolic blood pressure (SBP) and 24‐hour SBP load, to identify children at high risk for left ventricular (LV) hypertrophy (LVH). The study group consisted of 67 consecutive children who were referred to our institution for evaluation of suspected hypertension. LV mass was estimated by M‐mode echocardiography using Devereuxs formula according to the Penn convention and indexed for height2.7. We found a statistically significant, positive correlation between 24‐hour wBPSD and LV mass index (LVMI) (ρ=0.389; P=.002) and no correlation between 24‐hour ARV and LVMI (P>.05). However, partial correlation analysis of 24‐hour wBPSD adjusted for body mass index (BMI) and LVMI showed only a weak correlation (ρ=0.3; P=.022). By using multiple linear regression analysis in a model with LVMI as a dependent variable and 24‐hour wBPSD, 24‐hour ARV, and BMI as independent variables, only BMI showed statistically significant independent positive associations with LVMI (P=.028). Results of our study showed that currently used BPV indices (24‐hour wBPSD and 24‐hour ARV) are not clinically reliable parameters to identify children at risk for LVH. Apparent contribution of the 24‐hour wBPSD parameter to LVMI is negligible and is secondary to its close correlation with BMI (ρ=0.335 P=.009).

The therapeutic efficacy of propranolol in children with recurrent primary epistaxis

We hypothesized that some characteristics of beta-blockers, including negative inotropic, peripheral vasoconstrictor, and antiangiogenic effects, might be potentially useful in treating children with epistaxis. From June 2010 to March 2012, a total of seven children with recurrent primary epistaxis resistant to conventional management were observed at our institution. An overall effectiveness of propranolol was noted in all seven children when given a dose of 1.5–2 mg/kg/day (divided into three doses) as a second line therapy for terminating epistaxis. Based on our first experience, we believe that propranolol could be a favorable treatment option for patients with primary epistaxis.

Hypertensive encephalopathy as a late complication of autonomic dysreflexia in a 12-year-old boy with a previous spinal cord injury

The scope of paediatric autonomic disorders is not well recognised, and paediatricians seem to be generally unaware of the complexity and diversity of their clinical manifestations. We report a 12-year-old boy presenting with hypertensive encephalopathy caused by autonomic dysreflexia. Conclusion: This observation emphasises the importance of the recognition of this rare autonomic disorder, which can have potentially life-threatening neurological complications.

Comparation of Artificial Neural Network and Logistic Regression Models for Predicting Clinically Relevant Outcome

Dumont et al. have reported performances of the artificial neural network (ANN) and two logistic regression models (LRMs) for prediction of the symptomatic cerebral vasospasm after aneurysmal subarachnoid hemorrhage (4). We agree with comments by A. Dumont and Yeoh (3) that research (4) is a valuable contribution to the introduction of the ANN concept in neurosurgery clinical decisions, which will be useful for future studies and we want to acknowledge authors for their efforts. However, several issues raise concerns regarding the suggestion of “significant” improvement by the ANN model (3, 4).

Causal or casual association between lamotrigine and sudden unexpected death in females with epilepsy

Goraya JS, Khurana DS, Valenceia I, Melvin JJ, Cruz M, Legido A, Kothare SV. (2008) Intravenous levetiracetam in children with epilepsy. Paediatr Neurol 38:177–180. Hçfler J, Unterberger I, Dobesberger J, Kuchukhidze G, Walser G, Trinka E. (2011) Intravenous lacosamide in status epilepticus and seizure clusters. Epilepsia 50:e148–e152. Mehta V, Singhi P, Singhi S. (2007) Intravenous sodium valproate versus diazepam infusion for the control of refractory status epilepticus in children: a randomized controlled trial. J Child Neurol 22:1191– 1197. Shiloh-Malawsky Y, Fan Z, Greenwood R, Tennison M. (2011) Successful treatment of childhood prolonged refractory status epilepticus with lacosamide. Seizure 20:586–588. Tassinari CAI, Dravet C, Rojer J, Cano JP, Gastaut H. (1972) Tonic status epilepticus precipitated by intravenous benzodiazepine in five patients with Lennox–Gastaut syndrome. Epilepsia 13:421–435.

Intriguing association of Parkinson's disease and epileptic seizures

We read with interest the article by Gruntz et al. These authors suggest that incident Parkinsons disease (PD) is associated with an increased risk of incident epileptic seizures. This observation is a very important contribution, which will be useful in future studies, and we want to acknowledge these authors for their efforts. However, some issues raise concerns and merit a more detailed examination. First, Gruntz et al’s case selection is based on a large data set from a primary care setting. The same group, using the same data set in previous articles, specified that only a small percentage (1%) of all cases were referred to a neurologist to confirm the diagnosis, and that seizure diagnosis is not formally validated in the data set. Other disorders with prominent signs and symptoms of transient loss of consciousness (TLOC), such as syncope, may be confused with seizures. The reliability of the diagnosis of the first TLOC is therefore surprisingly low, and this may particularly be the case in a primary care setting, such as the one used for this study. Second, for case selection, one of the engaged criteria was usage of antiepileptic drugs (AEDs) in combination with diagnostic codes indicating a suspected epileptic seizure as a surrogate for the diagnosis of epileptic seizure. However, AEDs can be indicated for many conditions other than epilepsy, which may lead to misclassification. In a sensitivity analysis, these authors applied a definition of incident epilepsy that they used in another study with the same data set. However, that study used criteria of AED prescriptions in conjunction with diagnostic codes for epilepsy and not with codes for suspected epileptic seizures. Finally, this study utilized a conditional logistic regression analyses to explore the “real association” between PD and the risk of epileptic seizures. Nevertheless, these authors essentially presented only the results of a univariate logistic regression. A univariate analysis should be only the first step in any model building process. Despite the fact that this study matched controls for many variables, there can still be effect modifiers, and a multivariate analysis could examine potential statistical interactions between each of the selected variables. Overall, the association of PD and epileptic seizures is intriguing, and we strongly support further investigation in this area. However, considerable caution is necessary in making causal inferences from case‐control studies.