Probing the Pre-diagnostic Phase of Parkinson's Disease in Population-Based Studies

How Lifetime Evolution of Parkinson's Disease Could Shape Clinical Trial Design: A Shared Patient-Clinician Viewpoint

Parkinson's disease (PD) has a long, heterogeneous, pre-diagnostic phase, during which pathology insidiously accumulates. Increasing evidence suggests that environmental and lifestyle factors in early life contribute to disease risk and progression. Thanks to the extensive study of this pre-diagnostic phase, the first prevention trials of PD are being designed. However, the highly heterogenous evolution of the disease across the life course is not yet sufficiently taken into account. This could hamper clinical trial success in the advent of biological disease definitions. In an interdisciplinary patient-clinician study group, we discussed how an approach that incorporates the lifetime evolution of PD may benefit the design of disease-modifying trials by impacting population, target and outcome selection. We argue that the timepoint of exposure to risk and protective factors plays a critical role in PD subtypes, influencing population selection. In addition, recent developments in differential disease mechanisms, aided by biological disease definitions, could impact optimal treatment targets. Finally, multimodal biomarker panels using this lifetime approach will likely be most sensitive as progression markers for more personalized trials. We believe that the lifetime evolution of PD should be considered in the design of clinical trials, and that such initiatives could benefit from more patient-clinician partnerships.

The Rotterdam Study. Design update and major findings between 2020 and 2024

The Rotterdam Study is a population-based cohort study, started in 1990 in the district of Ommoord in the city of Rotterdam, the Netherlands, with the aim to describe the prevalence and incidence, unravel the etiology, and identify targets for prediction, prevention or intervention of multifactorial diseases in mid-life and elderly. The study currently includes 17,931 participants (overall response rate 65%), aged 40 years and over, who are examined in-person every 3 to 5 years in a dedicated research facility, and who are followed-up continuously through automated linkage with health care providers, both regionally and nationally. Research within the Rotterdam Study is carried out along two axes. First, research lines are oriented around diseases and clinical conditions, which are reflective of medical specializations. Second, cross-cutting research lines transverse these clinical demarcations allowing for inter- and multidisciplinary research. These research lines generally reflect subdomains within epidemiology. This paper describes recent methodological updates and main findings from each of these research lines. Also, future perspective for coming years highlighted.

Orthostatic hypotension: Review and expert position statement

Orthostatic hypotension is defined as a drop in systolic blood pressure of at least 20mmHg or a drop in diastolic blood pressure of at least 10mmHg within 3minutes of standing. It is a common disorder, especially in high-risk populations such as elderly subjects and patients with neurological diseases, and is associated with markedly increased morbidity and mortality. Its management can be challenging, particularly in cases where supine hypertension is associated with severe orthostatic hypotension. Education of the patient, non-pharmacological measures, and drug adaptation are the cornerstones of treatment. Pharmacological treatment should be individualized according to the severity, underlying cause, 24-hour blood pressure profile, and associated coexisting conditions. First-line therapies are midodrine and fludrocortisone, which may need to be combined for optimal care of severe cases.

Machine learning for predicting neurodegenerative diseases in the general older population: a cohort study

BACKGROUND

In the older general population, neurodegenerative diseases (NDs) are associated with increased disability, decreased physical and cognitive function. Detecting risk factors can help implement prevention measures. Using deep neural networks (DNNs), a machine-learning algorithm could be an alternative to Cox regression in tabular datasets with many predictive features. We aimed to compare the performance of different types of DNNs with regularized Cox proportional hazards models to predict NDs in the older general population.

METHODS

We performed a longitudinal analysis with participants of the English Longitudinal Study of Ageing. We included men and women with no NDs at baseline, aged 60 years and older, assessed every 2 years from 2004 to 2005 (wave2) to 2016-2017 (wave 8). The features were a set of 91 epidemiological and clinical baseline variables. The outcome was new events of Parkinson's, Alzheimer or dementia. After applying multiple imputations, we trained three DNN algorithms: Feedforward, TabTransformer, and Dense Convolutional (Densenet). In addition, we trained two algorithms based on Cox models: Elastic Net regularization (CoxEn) and selected features (CoxSf).

RESULTS

5433 participants were included in wave 2. During follow-up, 12.7% participants developed NDs. Although the five models predicted NDs events, the discriminative ability was superior using TabTransformer (Uno's C-statistic (coefficient (95% confidence intervals)) 0.757 (0.702, 0.805). TabTransformer showed superior time-dependent balanced accuracy (0.834 (0.779, 0.889)) and specificity (0.855 (0.0.773, 0.909)) than the other models. With the CoxSf (hazard ratio (95% confidence intervals)), age (10.0 (6.9, 14.7)), poor hearing (1.3 (1.1, 1.5)) and weight loss 1.3 (1.1, 1.6)) were associated with a higher DNN risk. In contrast, executive function (0.3 (0.2, 0.6)), memory (0, 0, 0.1)), increased gait speed (0.2, (0.1, 0.4)), vigorous physical activity (0.7, 0.6, 0.9)) and higher BMI (0.4 (0.2, 0.8)) were associated with a lower DNN risk.

CONCLUSION

TabTransformer is promising for prediction of NDs with heterogeneous tabular datasets with numerous features. Moreover, it can handle censored data. However, Cox models perform well and are easier to interpret than DNNs. Therefore, they are still a good choice for NDs.