scholarly journals Peer Review #1 of "Machine learning prediction of motor response after deep brain stimulation in Parkinson’s disease—proof of principle in a retrospective cohort (v0.1)"

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Alexandre Boutet ◽  
Radhika Madhavan ◽  
Gavin J. B. Elias ◽  
Suresh E. Joel ◽  
Robert Gramer ◽  
...  

AbstractCommonly used for Parkinson’s disease (PD), deep brain stimulation (DBS) produces marked clinical benefits when optimized. However, assessing the large number of possible stimulation settings (i.e., programming) requires numerous clinic visits. Here, we examine whether functional magnetic resonance imaging (fMRI) can be used to predict optimal stimulation settings for individual patients. We analyze 3 T fMRI data prospectively acquired as part of an observational trial in 67 PD patients using optimal and non-optimal stimulation settings. Clinically optimal stimulation produces a characteristic fMRI brain response pattern marked by preferential engagement of the motor circuit. Then, we build a machine learning model predicting optimal vs. non-optimal settings using the fMRI patterns of 39 PD patients with a priori clinically optimized DBS (88% accuracy). The model predicts optimal stimulation settings in unseen datasets: a priori clinically optimized and stimulation-naïve PD patients. We propose that fMRI brain responses to DBS stimulation in PD patients could represent an objective biomarker of clinical response. Upon further validation with additional studies, these findings may open the door to functional imaging-assisted DBS programming.


2021 ◽  
Vol 12 ◽  
Author(s):  
Emanuele Camerucci ◽  
Cole D. Stang ◽  
Pierpaolo Turcano ◽  
Philip W. Tipton ◽  
James H. Bower ◽  
...  

Background: No studies have reported the rate of motor complications (MC) and response to medical and surgical treatment in a population-based cohort of young-onset Parkinson's Disease (YOPD) patients and a cohort of sex-matched late-onset Parkinson's Disease (LOPD).Objective: To assess the outcomes of dopaminergic treatment in YOPD and LOPD, explore treatment-induced MC, medical adjustment, and rate of deep brain stimulation (DBS).Methods: We used the expanded Rochester Epidemiology Project (eREP) to investigate a population-based cohort of YOPD between 2010 and 2015 in 7 counties in Minnesota. Cases with onset ≤55 years of age were included as YOPD. An additional sex-matched cohort of LOPD (onset at ≥56 years of age) was included for comparison. All medical records were reviewed to confirm the diagnoses.Results: In the seven counties 2010–15, there were 28 YOPD patients, which were matched with a LOPD cohort. Sixteen (57%) YOPD had MC, as compared to 9 (32%) LOPD. In YOPD, 9 had motor fluctuations (MF) and Levodopa-induced dyskinesia (LID) together, whereas 3 had LID only and 4 MF only. In LOPD, 3 had MF and LID, 3 MF only, and 3 LID only. Following medical treatment for MC, 6/16 YOPD (38%) and 3/9 (33%) LOPD had symptoms resolution. In YOPD, 11/16 (69%) were considered for DBS implantation, in LOPD they were 2/9 (22%), but only 7 (6 YOPD and 1 LOPD) underwent the procedure. YOPD had significantly higher rates in both DBS candidacy and DBS surgery (respectively, p = 0.03 and p = 0.04). Among DBS-YOPD, 5/6 (83%) had positive motor response to the surgery; the LOPD case had a poor response. We report the population-based incidence of both YOPD with motor complications and YOPD undergoing DBS, which were 1.17 and 0.44 cases per 100,000 person-years, respectively.Conclusion: Fifty-seven percent of our YOPD patients and 32% of the LOPD had motor complications. Roughly half of both YOPD and LOPD were treatment resistant. YOPD had higher rates of DBS candidacy and surgery. Six YOPD and 1 LOPD underwent DBS implantation and most of them had a positive motor response after the surgery.


Sign in / Sign up

Export Citation Format

Share Document