3 results
62 Prediction of Mild Cognitive Impairment Conversion Using Cox Model in Parkinson’s Disease
- Lyna Mariam El Haffaf, Lucas Ronat, Alexandru Hanganu
-
- Journal:
- Journal of the International Neuropsychological Society / Volume 29 / Issue s1 / November 2023
- Published online by Cambridge University Press:
- 21 December 2023, pp. 572-573
-
- Article
-
- You have access Access
- Export citation
-
Objective:
Mild cognitive impairment (MCI) in Parkinson’s disease (PD) is a critical state to consider. In fact, PD patients with MCI are more likely to develop dementia than the general population. Thus, identifying the risk factors for developing MCI in patients with PD could help with disease prevention. We aim to use the Cox regression model to identify the variables involved in the development of MCI in healthy controls (HC) and in a PD cohort.
Participants and Methods:The Parkinson’s Progressive Markers Initiative (PPMI) database was used to analyze data from 166 HC and 365 patients with PD. They were analyzed longitudinally, at baseline and at 3-year follow up. Both HC and PD were further divided in 2 groups based on the presence or absence of MCI. Conversion to MCI was defined as the first detection of MCI. For all participants, we extracted the (1) Neuropsychiatric symptoms (anxiety, impulsive-compulsive disorders and sleep impairment), (2) 3T MRI-based data (cortical and subcortical brain volumes based on the Desikan atlas, using FreeSurfer 7.1.1) and (3) genetic markers (MAPT and APOE £4 genes). We used Python 3.9 to perform three Cox proportional hazard models (PD-HC, HC only and PD only) and to model the risk of conversion to MCI, attributable to neuropsychiatric symptoms and cortical brain parameters. We included as covariates: age, sex, education, and disease duration (for the PD group). Hazard ratios (HRs) along with their 95% confidence intervals (CIs) are reported.
Results:When including both HC and PD in the model, Cox regression analyses showed that age of onset, diagnosis, the State-Trait Anxiety Inventory (STAI) and sleep impairment are variables that are associated with a greater risk of conversion to MCI (p<.005). For HC, only the STAI and the genetic marker MAPT were significantly associated with a risk of cognitive decline (p<.05). These results further indicated that a greater anxiety score at the STAI leads to a greater chance of developing a MCI whereas being a carrier of the MAPT gene reduces the risk of MCI. Regarding analysis on PD, results revealed that the STAI and the cortical volumes of the frontal dorsolateral and temporal regions are involved with a greater risk of developing a MCI (p<.05).
Conclusions:These analyses show that the neuropsychiatric symptom of anxiety seem to play an important role in the development of a MCI (significant in all three analyses). For patients with PD, cortical volumes of the frontal dorsolateral and temporal regions are significantly related to risk of MCI. This study highlights the importance of considering neuropsychiatric symptoms as well as cerebral volumes as key factors in the development of MCI in PD.
47 Evolution of Brain Morphology and Cognitive Performance in Parkinson’s Disease with Impulse Control Disorder
- Adina Lorena Patru, Lucas Ronat, Alexandru Hanganu
-
- Journal:
- Journal of the International Neuropsychological Society / Volume 29 / Issue s1 / November 2023
- Published online by Cambridge University Press:
- 21 December 2023, p. 560
-
- Article
-
- You have access Access
- Export citation
-
Objective:
Parkinson’s disease (PD) affects the person’s quality of life, but the comorbidity of PD and impulsive control disorder (ICD), which has an average prevalence of 23%, can enhance the disruption of quality of life for the patients and their caregivers. The effects of ICD in PD on brain morphology and cognition have been little studied. Thus, this study proposes to investigate the differences in the evolution of cognitive performance and brain structures between PD patients with ICD (PD-ICD) vs. without ICD (PD-no-ICD).
Participants and Methods:Parkinson’s Progression Markers Initiative (PPMI) data of 58 patients with idiopathic PD, including their MRI data at baseline and three years later, were analyzed. The MRIs were processed with FreeSurfer (7.1.1) to extract cortical volumes, areas, thicknesses, curvatures and folding index as well as volumes of subcortical segmentations. All participants underwent cognitive evaluations. The Questionnaire for Impulsive-Compulsive Disorders in Parkinson’s Disease was used to differentiate those with at least one ICD from those without any ICD. 12 of the 58 patients had an ICD at their first visit and 19 had an ICD at their visit three years later. There was no significant difference between PD-ICD and PD-no-ICD with respect to sex, use of overall medication, age, age of onset, age at diagnosis, years of education and the Montreal cognitive assessment score. Two-way mixed ANOVAs were performed for each neuropsychological test and brain structure extracted from MRIs with the time of the visit as the repeated independent variable (within participants) and the presence or absence of an ICD as the other independent variable (between participants).
Results:The mixed ANOVA revealed that PD-ICD had their performance decline after three years, for the Hopkins Verbal Learning Test delayed recall and the Symbol Digit Modalities Test while PD-no-ICD saw their performance increase. A whole brain analysis showed that PD-ICD had a significant decrease after three years of the right cortex area total brain volume in comparison to PD-no-ICD. Specific brain structures also underwent significant changes over three years. Cortical changes in PD-ICD were: (1) increased surface area in the left temporal parahippocampus and (2) decreased surface areas of the right insula, right middle and superior temporal regions, left occipital lingual as well as left cingulate isthmus. Furthermore, in the subcortical nuclei, PD-ICD showed (1) increased volumes of the paratenial thalamic nucleus and whole right amygdala and (2) decreased volumes of the right amygdalian basal nucleus and thalamic ventromedial nucleus.
Conclusions:This study suggests that PD patients who also have ICD might be prone to develop over three years: (1) significant changes in cognitive performance (memory, attention), (2) morphological changes in the amygdala and thalamic nuclei and (3) significant atrophy and area shrinkage in the temporal and insula regions.
85 Predicting Conversion to Mild Cognitive Impairment in Parkinson’s Disease: a Random Forest Machine Learning Model Based on Parkinson’s Progression Markers Initiative Dataset.
- Lucas A Ronat, Alexandru Hanganu
-
- Journal:
- Journal of the International Neuropsychological Society / Volume 29 / Issue s1 / November 2023
- Published online by Cambridge University Press:
- 21 December 2023, p. 388
-
- Article
-
- You have access Access
- Export citation
-
Objective:
Mild cognitive impairment (MCI) is common in Parkinson’s disease (PD). Recent scientific advances show that MCI in PD could also be impacted by neuropsychiatric symptoms (such as apathy, anxiety, depression), dopaminergic deficiency (more striatal denervation associated with MCI) and certain genotypes such as in APOE E4, MAPT H1 or SNCA C/C carriers. We used a python-based random forest machine-learning algorithm (scikit-learn) in order to evaluate the factors that are mostly involved in the MCI conversion over a 5-year follow-up period.
Participants and Methods:Baseline data of healthy individuals and participants with Parkinson’s disease were extracted from the PPMI dataset. All participants also had the evaluations of their cognitive status, neuropsychiatric symptoms (hallucinations, anxiety, apathy, depression, sleepiness, impulse control disorders and rapid eye movement behaviors), dopaminergic uptake (DaT-Scan) and genetic status (APOE, MAPT and SNCA) at baseline and after 5 years. Baseline demographic (age, sex, education years) and clinical values (duration of disease, age of onset) were also included in the model. The algorithm defined (1) the most important variables in predicting MCI, (2) the threshold values to distinguish “converting” vs. “non-converting” subgroups.
Results:The algorithm showed that (1) age onset of disease, (2) dopaminergic uptake, (3) age, (4) anxiety, and (5) years of education were the most important factors in predicting MCI over 5 years. Among the factors involved in predicting conversion to MCI, a lower number of years of education associated with lower dopaminergic uptake in the right putamen increased the risk of conversion. Individuals with more years of education are at higher risk of conversion if they have symptoms of depression, anxiety, and lower right striatal dopamine uptake. Other factors that were involved in increasing the risk, were the presence of sleepiness and the presence of rapid eye movement disorders. Interestingly, the genetic factors were of negligible importance and were not considered by the algorithm. Finally, the model showed an accuracy of classification of participants (converters vs. non-converters) of 92.53%.
Conclusions:Random forest algorithm shows that (1) depression and anxiety are probably important factors for MCI conversion; (2) years of education influences the conversion; (3) presence of sleepiness and rapid eye movement increases the risk of conversion to MCI. Since the algorithm considers the disease’s age onset, but not the diagnosis of individuals, it would be necessary to generate a model for each group (Healthy on the one hand, Parkinson’s on the other).