Characteristic of Cognitive Decline in Parkinson's Disease: A 1-Year Follow-Up

Bias Investigation in Artificial Intelligence Systems for Early Detection of Parkinson's Disease: A Narrative Review

Background and Motivation: Diagnosis of Parkinson's disease (PD) is often based on medical attention and clinical signs. It is subjective and does not have a good prognosis. Artificial Intelligence (AI) has played a promising role in the diagnosis of PD. However, it introduces bias due to lack of sample size, poor validation, clinical evaluation, and lack of big data configuration. The purpose of this study is to compute the risk of bias (RoB) automatically.

METHOD

The PRISMA search strategy was adopted to select the best 39 AI studies out of 85 PD studies closely associated with early diagnosis PD. The studies were used to compute 30 AI attributes (based on 6 AI clusters), using AP(ai)Bias 1.0 (AtheroPointTM, Roseville, CA, USA), and the mean aggregate score was computed. The studies were ranked and two cutoffs (Moderate-Low (ML) and High-Moderate (MH)) were determined to segregate the studies into three bins: low-, moderate-, and high-bias.

RESULT

The ML and HM cutoffs were 3.50 and 2.33, respectively, which constituted 7, 13, and 6 for low-, moderate-, and high-bias studies. The best and worst architectures were "deep learning with sketches as outcomes" and "machine learning with Electroencephalography," respectively. We recommend (i) the usage of power analysis in big data framework, (ii) that it must undergo scientific validation using unseen AI models, and (iii) that it should be taken towards clinical evaluation for reliability and stability tests.

CONCLUSION

The AI is a vital component for the diagnosis of early PD and the recommendations must be followed to lower the RoB.

Computerized testing in Parkinson's disease: Performance deficits in relation to standard clinical measures

OBJECTIVE

This study assessed deficits associated with Parkinson's disease (PD) at two time points separated by 1 year using a computerized neuropsychological battery, and determined interrelationships with conventional clinical measures of cognitive functioning (Montreal Cognitive Assessment; MoCA) and motor impairment (Part III of the Unified PD Rating Scale; UPDRS), as well as other factors known to influence cognitive dysfunction in PD.

METHOD

Participants included 37 with PD and 47 controls. Linear mixed-effects models were developed for each computerized task.

RESULTS

Results showed that the PD group performed worse than controls on all of the computerized tasks at both time points. In contrast, MoCA scores differed between PD and controls only at follow-up. However, the MoCA detected decline over the year in the PD group, whereas only one of the computerized tasks did. In both groups, higher MoCA scores predicted better performance on some but not all of the computerized tasks. Surprisingly, UPDRS-rated motor impairment did not predict performance on any of the computerized tasks, and aside from older age, which predicted poorer performance on all but one task, the other factors-education, affective and impulsivecompulsive symptoms, sleep quality, dopaminergic medication-generally had no relationship with performance on the computerized tasks.

CONCLUSIONS

The presence of performance deficits for all of the computerized tasks in the PD group compared to controls, but not for the MoCA at initial testing, indicates that the computerized battery was better able to detect deficits. However, in contrast to the MoCA, the current results call into question the suitability of the computerized battery as measured here for tracking decline.

Effects of the adenosine A2A receptor antagonist on cognitive dysfunction in Parkinson's disease

Parkinson's disease (PD) is primarily characterized by motor abnormalities, but cognitive changes also occur in the early and late stages of the disease process. In PD patients, cognitive dysfunction is associated with reduced quality of life, as well as increased morbidity and mortality, resulting in increases in caregiver burden, and health-related costs. Therefore, safe and effective approaches are needed to treat cognitive dysfunction in PD patients. The underlying pathophysiology of cognitive dysfunction is complex and not fully understood, however. α-Synuclein, amyloid-related proteins, and cholinergic deficits have been reported to partially contribute to cognitive dysfunction. Changes in cortical dopamine (DA) content may also be responsible for early cognitive changes in patients with PD. Certainly, dopaminergic afferents to the frontal cortex degenerate in PD, and there is a reduction of DA content in the prefrontal cortex (PFC). It has also been reported that PFC dopaminergic input plays an important role in working memory performance. Moreover, PFC DA levels and working memory performance are significantly reduced by a 6-hydroxydopamine lesion in the PFC of a rat. Recent findings in the areas of pharmacological manipulation and genetic ablation suggest that the adenosine A2A receptor is also related to cognitive functions, especially working memory. In addition, the blockade of adenosine A2A receptors reverses cognitive dysfunction in PFC-lesioned rats, and this blocking effect may be due to an increase in PFC DA content. Therefore, adenosine A2A receptor antagonists not only improve motor performance, but they may also lead to improved cognitive function in those with PD.

Effects of the adenosine A2A antagonist istradefylline on cognitive performance in rats with a 6-OHDA lesion in prefrontal cortex

RATIONALE

Altered cognitive function is a common feature of both the early and later stages of Parkinson's disease (PD) that involves alterations in cortical dopamine content. Adenosine A2A antagonists, such as istradefylline, improve motor function in PD, but their effect on cognitive impairment has not been determined.

OBJECTIVE

The present study investigated whether impairment of working memory due to the loss of dopaminergic input into the prefrontal cortex (PFC) is reversed by administration of istradefylline. We also evaluated whether A2A antagonist administration modulates dopamine levels in the PFC.

METHODS

Bilateral lesions of the dopaminergic input to the PFC were produced in rats using 6-hydroxydopamine (6-OHDA). Cognitive performance was evaluated using an object recognition task and delayed alternation task. The effects of istradefylline, donepezil and methamphetamine on cognitive performance were examined. In addition, the effect of istradefylline on extracellular dopamine levels in the PFC was studied.

RESULTS

PFC dopamine levels and cognitive performance were significantly reduced by 6-OHDA lesioning. Istradefylline, donepezil and methamphetamine improved cognitive performance of PFC-lesioned rats. Istradefylline increased dopamine levels in the PFC in both normal and PFC-lesioned rats.

CONCLUSIONS

PFC dopaminergic input plays an important role in working memory performance. Blockade of A2A receptors using istradefylline reverses the changes in cognitive function, and this may be due to an increase in PFC dopamine content. Adenosine A2A receptor antagonists not only improve motor performance in PD but may also lead to improved cognition.