Anna Prats

Nadir CD4 cell count predicts neurocognitive impairment in HIV-infected patients.

Though antiretroviral therapy attenuates neurocognitive disruption, impairment is still observed. We studied the nadir CD4 cell count as a predictor of neurocognitive changes. This cross-sectional study assessed 64 HIV-infected patients in two groups: G1 (n = 26, nadir CD4 < or =200 cells/ml) and G2 (n = 38, nadir CD4 >200 cells/ml). Percentages of patients showing neurocognitive impairment were compared according to different nadir CD4 cutoffs (200, 250, 300, and 350 cells/ml). From G2, we also took the subgroup of patients receiving treatment (G3) and compared this group with G1, in which all patients were being treated. Demographic and clinical variables were evaluated, as were differences in neurocognitive function. Neurocognitive impairment tended to be more prevalent in G1 [19 patients (73.1%)] than in G2 [20 (52.6%), p = 0.123]. When nadir CD4 cutoffs were compared, there was a trend toward more impaired subjects as the CD4 nadir decreased. Significantly different functioning was found in attention/working memory (digit span backward, p = 0.032) and executive functions (trail making test, part B, p = 0.020), with better performance in G2. Comparison between G1 and G3 confirmed those findings. We found differences in neurocognitive functioning in relation to nadir CD4 count in HIV-infected patients. Attention should be given to this value in the management of neurocognitive protection in HIV infection.

Home detection of freezing of gait using support vector machines through a single waist-worn triaxial accelerometer

Among Parkinson’s disease (PD) symptoms, freezing of gait (FoG) is one of the most debilitating. To assess FoG, current clinical practice mostly employs repeated evaluations over weeks and months based on questionnaires, which may not accurately map the severity of this symptom. The use of a non-invasive system to monitor the activities of daily living (ADL) and the PD symptoms experienced by patients throughout the day could provide a more accurate and objective evaluation of FoG in order to better understand the evolution of the disease and allow for a more informed decision-making process in making adjustments to the patient’s treatment plan. This paper presents a new algorithm to detect FoG with a machine learning approach based on Support Vector Machines (SVM) and a single tri-axial accelerometer worn at the waist. The method is evaluated through the acceleration signals in an outpatient setting gathered from 21 PD patients at their home and evaluated under two different conditions: first, a generic model is tested by using a leave-one-out approach and, second, a personalised model that also uses part of the dataset from each patient. Results show a significant improvement in the accuracy of the personalised model compared to the generic model, showing enhancement in the specificity and sensitivity geometric mean (GM) of 7.2%. Furthermore, the SVM approach adopted has been compared to the most comprehensive FoG detection method currently in use (referred to as MBFA in this paper). Results of our novel generic method provide an enhancement of 11.2% in the GM compared to the MBFA generic model and, in the case of the personalised model, a 10% of improvement with respect to the MBFA personalised model. Thus, our results show that a machine learning approach can be used to monitor FoG during the daily life of PD patients and, furthermore, personalised models for FoG detection can be used to improve monitoring accuracy.

Virological Efficacy in Cerebrospinal Fluid and Neurocognitive Status in Patients with Long-Term Monotherapy Based on Lopinavir/Ritonavir: An Exploratory Study

Background Data on suppression of HIV replication in the CNS and on the subsequent risk of neurocognitive impairment using monotherapy with boosted protease inhibitors are limited. Methods Ours was an exploratory cross-sectional study in patients on lopinavir/ritonavir-based monotherapy (LPV/r-MT) or standard triple therapy (LPV/r-ART) for at least 96 weeks who maintained a plasma viral load <50 copies/mL. HIV-1 RNA in CSF was determined by HIV-1 SuperLow assay (lower limit of detection, 1 copy/mL). Neurocognitive functioning was assessed using a recommended battery of neuropsychological tests covering 7 areas. Neurocognitive impairment (NCI) was determined and also a global deficit score (GDS) for study comparisons. Results Seventeen patients on LPV/r-MT and 17 on LPV/r-ART were included. Fourteen (82.4%) patients on LPV/r-MT and 16 (94.1%) on LPV/r-ART had HIV-1 RNA <1 copy/mL in CSF (p = 0.601). NCI was observed in 7 patients on LPV/r-MT and in 10 on LPV/r-ART (41% vs 59%; p = 0.494). Mean (SD) GDS was 0.22 (0.20) in patients on LPV/r-MT and 0.47 (0.34) in those on LPV/r-ART (p = 0.012). Conclusions Suppression of HIV in CSF is similar in individuals with durable plasma HIV-1 RNA suppression who are receiving LPV/r-MT or LPV/r-ART for at least 96 weeks. Findings for HIV-1 replication in CSF and neurocognitive status indicate that this strategy seems to be safe for CNS functioning.

Interruptions of antiretroviral therapy in human immunodeficiency virus infection: are they detrimental to neurocognitive functioning?

Because interruptions of antiretroviral treatment may entail clinical risks for human immunodeficiency virus (HIV)-infected individuals, we investigated their impact on neurocognitive functioning. Cross-sectional study was carried out, comparing HIV-infected persons who had interrupted antiretroviral therapy in the past (interruption group, IG) with persons who had never discontinued therapy (noninterruption group, NIG). Interruption was defined as the discontinuation of highly active antiretroviral therapy (HAART) for more than 15 days after previous treatment of at least 15 days. All the participants were on therapy. Demographic, clinical, and neurocognitive variables were assessed. The primary end point was the percentage of people with neurocognitive impairment. The score in different neurocognitive domains was a secondary end point. A total of 83 subjects participated in the study (IG: n = 27; NIG: n = 56). Demographic and clinical characteristics were balanced between the groups, except for years since HIV diagnosis (IG, 13.8; NIG, 10.2 [P = .003]). The percentage of people with neurocognitive impairment was significantly higher in the IG group (IG, 59.25%; NIG, 33.92% [P = 0.02]). As for scores in neurocognitive domains, individuals in the IG showed worse neurocognitive functioning, and significant differences in attention/working memory and information processing speed were found. The adjusted analysis supported the unadjusted analysis. In this study, a higher prevalence of neurocognitive impairment was detected in HIV-infected persons who had interrupted antiretroviral therapy in the past. Additionally, neurocognitive functioning was observed to be more impaired in the same individuals. Further studies should examine the potential negative effects of antiretroviral therapy interruptions on neurocognitive functioning.

A Waist-Worn Inertial Measurement Unit for Long-Term Monitoring of Parkinson’s Disease Patients

Inertial measurement units (IMUs) are devices used, among other fields, in health applications, since they are light, small and effective. More concretely, IMUs have been demonstrated to be useful in the monitoring of motor symptoms of Parkinson’s disease (PD). In this sense, most of previous works have attempted to assess PD symptoms in controlled environments or short tests. This paper presents the design of an IMU, called 9 × 3, that aims to assess PD symptoms, enabling the possibility to perform a map of patients’ symptoms at their homes during long periods. The device is able to acquire and store raw inertial data for artificial intelligence algorithmic training purposes. Furthermore, the presented IMU enables the real-time execution of the developed and embedded learning models. Results show the great flexibility of the 9 × 3, storing inertial information and algorithm outputs, sending messages to external devices and being able to detect freezing of gait and bradykinetic gait. Results obtained in 12 patients exhibit a sensitivity and specificity over 80%. Additionally, the system enables working 23 days (at waking hours) with a 1200 mAh battery and a sampling rate of 50 Hz, opening up the possibility to be used for other applications like wellbeing and sports.

Deep learning for freezing of gait detection in Parkinson’s disease patients in their homes using a waist-worn inertial measurement unit

Among Parkinsons disease (PD) motor symptoms, freezing of gait (FOG) may be the most incapacitating. FOG episodes may result in falls and reduce patients quality of life. Accurate assessment of FOG would provide objective information to neurologists about the patients condition and the symptoms characteristics, while it could enable non-pharmacologic support based on rhythmic cues.This paper is, to the best of our knowledge, the first study to propose a deep learning method for detecting FOG episodes in PD patients. This model is trained using a novel spectral data representation strategy which considers information from both the previous and current signal windows. Our approach was evaluated using data collected by a waist-placed inertial measurement unit from 21 PD patients who manifested FOG episodes. These data were also employed to reproduce the state-of-the-art methodologies, which served to perform a comparative study to our FOG monitoring system.The results of this study demonstrate that our approach successfully outperforms the state-of-the-art methods for automatic FOG detection. Precisely, the deep learning model achieved 90% for the geometric mean between sensitivity and specificity, whereas the state-of-the-art methods were unable to surpass the 83% for the same metric.

Determining the optimal features in freezing of gait detection through a single waist accelerometer in home environments

Freezing of gait (FoG) is one of the most disturbing and incapacitating symptoms in Parkinsons disease. It is defined as a sudden block in effective stepping, provoking anxiety, stress and falls. FoG is usually evaluated by means of different questionnaires; however, this method has shown to be not reliable, since it is subjective due to its dependence on patients’ and caregivers’ judgment. Several authors have analyzed the usage of MEMS inertial systems to detect FoG with the aim of objectively evaluating it. So far, specific methods based on accelerometers frequency response has been employed in many works; nonetheless, since they have been developed and tested in laboratory conditions, their performance is commonly poor when being used at patients’ home. Therefore, this work proposes a new set of features that aims to detect FoG in real environments by using accelerometers. This set of features is compared with three previously reported approaches to detect FoG. The different feature sets are trained by means of several machine learning classifiers; furthermore, different window sizes are also evaluated. In addition, a greedy subset selection process is performed to reduce the computational load of the method and to enable a real-time implementation. Results show that the proposed method detects FoG at patients’ home with 91.7% and 87.4% of sensitivity and specificity, respectively, enhancing the results of former methods between a 5% and 11% and providing a more balanced rate of true positives and true negatives.

Classification Models for Neurocognitive Impairment in HIV Infection Based on Demographic and Clinical Variables

Objective We used demographic and clinical data to design practical classification models for prediction of neurocognitive impairment (NCI) in people with HIV infection. Methods The study population comprised 331 HIV-infected patients with available demographic, clinical, and neurocognitive data collected using a comprehensive battery of neuropsychological tests. Classification and regression trees (CART) were developed to obtain detailed and reliable models to predict NCI. Following a practical clinical approach, NCI was considered the main variable for study outcomes, and analyses were performed separately in treatment-naïve and treatment-experienced patients. Results The study sample comprised 52 treatment-naïve and 279 experienced patients. In the first group, the variables identified as better predictors of NCI were CD4 cell count and age (correct classification [CC]: 79.6%, 3 final nodes). In treatment-experienced patients, the variables most closely related to NCI were years of education, nadir CD4 cell count, central nervous system penetration-effectiveness score, age, employment status, and confounding comorbidities (CC: 82.1%, 7 final nodes). In patients with an undetectable viral load and no comorbidities, we obtained a fairly accurate model in which the main variables were nadir CD4 cell count, current CD4 cell count, time on current treatment, and past highest viral load (CC: 88%, 6 final nodes). Conclusion Practical classification models to predict NCI in HIV infection can be obtained using demographic and clinical variables. An approach based on CART analyses may facilitate screening for HIV-associated neurocognitive disorders and complement clinical information about risk and protective factors for NCI in HIV-infected patients.

Deep learning for detecting freezing of gait episodes in Parkinson’s disease based on accelerometers

Freezing of gait (FOG) is one of the most incapacitating symptoms among the motor alterations of Parkinson’s disease (PD). Manifesting FOG episodes reduce patients’ quality of life and their autonomy to perform daily living activities, while it may provoke falls. Accurate ambulatory FOG assessment would enable non-pharmacologic support based on cues and would provide relevant information to neurologists on the disease evolution.

Transdermal rivastigmine for HIV-associated cognitive impairment: A randomized pilot study

Objective To assess the efficacy and safety of transdermal rivastigmine for the treatment of HIV-associated cognitive impairment. Methods We recruited HIV-infected patients with cognitive impairment on stable antiretroviral therapy in a randomized controlled pilot trial with a 48-week follow-up. An additional assessment was held at 12 weeks. Participants received transdermal rivastigmine (9.5 mg daily), lithium (400 mg twice daily, titrated progressively), or remained in a control group (no new medication). The primary efficacy endpoint was change in a global cognitive score (NPZ-7). Secondary endpoints included change in specific cognitive measures, domains, and functional parameters. Safety covered the frequency of adverse events and changes in laboratory results. Results Seventy-six subjects were screened, and 29 were finally enrolled. Better cognitive outcomes were observed in all groups, although there were no significant differences between the arms (mean NPZ-7 change [SD]): rivastigmine, 0.35 (0.14); lithium, 0.25 (0.40); control, 0.20 (0.44) (p = 0.78). The rivastigmine group showed the highest positive trend (mean NPZ-7 [SD], baseline vs week 48): rivastigmine, –0.47 (0.22) vs –0.11 (0.29), p = 0.06; lithium, –0.50 (0.40) vs –0.26 (0.21), p = 0.22; control, –0.52 (0.34) vs –0.32 (0.52), p = 0.44. The cognitive domains with the highest positive trends were information processing speed at week 12 and executive function at week 48 (rivastigmine vs control): information processing speed, 0.35 (0.64) vs –0.13 (0.25), p = 0.17, d = 0.96; and executive functioning, 0.73 (0.33) vs 0.03 (0.74), p = 0.09, d = 1.18. No relevant changes were observed regarding functional outcomes. A total of 12 (41%) individuals dropped out of the study: 2 (20%) were due to medication-related effects in the rivastigmine group and 4 (36%) in the lithium group. No severe adverse events were reported. Conclusions The results from this small randomized trial indicate that transdermal rivastigmine did not provide significant cognitive benefits in people with HAND on stable antiretroviral therapy, even though positive trends were found in specific cognitive domains. Relevant tolerability issues were not observed.