RESUMO
Background and Objectives: To recruit and characterize a national cohort of individuals who have a genetic variant (LRRK2 G2019S) that increases risk of Parkinson disease (PD), assess participant satisfaction with a decentralized, remote research model, and evaluate interest in future clinical trials. Methods: In partnership with 23andMe, Inc., a personal genetics company, LRRK2 G2019S carriers with and without PD were recruited to participate in an ongoing 36-month decentralized, remote natural history study. We examined concordance between self-reported and clinician-determined PD diagnosis. We applied the Movement Disorder Society Prodromal Parkinson's Disease Criteria and asked investigators to identify concern for parkinsonism to distinguish participants with probable prodromal PD. We compared baseline characteristics of LRRK2 G2019S carriers with PD, with prodromal PD, and without PD. Results: Over 15 months, we enrolled 277 LRRK2 G2019S carriers from 34 states. At baseline, 60 had self-reported PD (mean [SD] age 67.8 years [8.4], 98% White, 52% female, 80% Ashkenazi Jewish, and 67% with a family history of PD), and 217 did not (mean [SD] age 53.7 years [15.1], 95% White, 59% female, 73% Ashkenazi Jewish, and 57% with a family history of PD). Agreement between self-reported and clinician-determined PD status was excellent (κ = 0.94, 95% confidence interval 0.89-0.99). Twenty-four participants had prodromal PD; 9 met criteria for probable prodromal PD and investigators identified concern for parkinsonism in 20 cases. Compared with those without prodromal PD, participants with prodromal PD were older (63.9 years [9.0] vs 51.9 years [15.1], p < 0.001), had higher modified Movement Disorders Society-Unified Parkinson's Disease Rating Scale motor scores (5.7 [4.3] vs 0.8 [2.1], p < 0.001), and had higher Scale for Outcomes in PD for Autonomic Symptoms scores (11.5 [6.2] vs 6.9 [5.7], p = 0.002). Two-thirds of participants enrolled were new to research, 97% were satisfied with the overall study, and 94% of those without PD would participate in future preventive clinical trials. Discussion: An entirely remote national cohort of LRRK2 G2019S carriers was recruited from a single site. This study will prospectively characterize a large LRRK2 G2019S cohort, refine a new model of clinical research, and engage new research participants willing to participate in future therapeutic trials.
RESUMO
BACKGROUND: Access to neurological care for Parkinson disease (PD) is a rare privilege for millions of people worldwide, especially in resource-limited countries. In 2013, there were just 1200 neurologists in India for a population of 1.3 billion people; in Africa, the average population per neurologist exceeds 3.3 million people. In contrast, 60,000 people receive a diagnosis of PD every year in the United States alone, and similar patterns of rising PD cases-fueled mostly by environmental pollution and an aging population-can be seen worldwide. The current projection of more than 12 million patients with PD worldwide by 2040 is only part of the picture given that more than 20% of patients with PD remain undiagnosed. Timely diagnosis and frequent assessment are key to ensure timely and appropriate medical intervention, thus improving the quality of life of patients with PD. OBJECTIVE: In this paper, we propose a web-based framework that can help anyone anywhere around the world record a short speech task and analyze the recorded data to screen for PD. METHODS: We collected data from 726 unique participants (PD: 262/726, 36.1% were women; non-PD: 464/726, 63.9% were women; average age 61 years) from all over the United States and beyond. A small portion of the data (approximately 54/726, 7.4%) was collected in a laboratory setting to compare the performance of the models trained with noisy home environment data against high-quality laboratory-environment data. The participants were instructed to utter a popular pangram containing all the letters in the English alphabet, "the quick brown fox jumps over the lazy dog." We extracted both standard acoustic features (mel-frequency cepstral coefficients and jitter and shimmer variants) and deep learning-based embedding features from the speech data. Using these features, we trained several machine learning algorithms. We also applied model interpretation techniques such as Shapley additive explanations to ascertain the importance of each feature in determining the model's output. RESULTS: We achieved an area under the curve of 0.753 for determining the presence of self-reported PD by modeling the standard acoustic features through the XGBoost-a gradient-boosted decision tree model. Further analysis revealed that the widely used mel-frequency cepstral coefficient features and a subset of previously validated dysphonia features designed for detecting PD from a verbal phonation task (pronouncing "ahh") influence the model's decision the most. CONCLUSIONS: Our model performed equally well on data collected in a controlled laboratory environment and in the wild across different gender and age groups. Using this tool, we can collect data from almost anyone anywhere with an audio-enabled device and help the participants screen for PD remotely, contributing to equity and access in neurological care.
