RESUMEN
Introduction: Freezing of gait (FOG) is a paroxysmal motor phenomenon that increases in prevalence as Parkinson's disease (PD) progresses. It is associated with a reduced quality of life and an increased risk of falls in this population. Precision-based detection and classification of freezers are critical to developing tailored treatments rooted in kinematic assessments. Methods: This study analyzed instrumented stand-and-walk (SAW) trials from advanced PD patients with STN-DBS. Each patient performed two SAW trials in their OFF Medication-OFF DBS state. For each trial, gait summary statistics from wearable sensors were analyzed by machine learning classification algorithms. These algorithms include k-nearest neighbors, logistic regression, naïve Bayes, random forest, and support vector machines (SVM). Each of these models were selected for their high interpretability. Each algorithm was tasked with classifying patients whose SAW trials MDS-UPDRS FOG subscore was non-zero as assessed by a trained movement disorder specialist. These algorithms' performance was evaluated using stratified five-fold cross-validation. Results: A total of 21 PD subjects were evaluated (average age 64.24 years, 16 males, mean disease duration of 14 years). Fourteen subjects had freezing of gait in the OFF MED/OFF DBS. All machine learning models achieved statistically similar predictive performance (p < 0.05) with high accuracy. Analysis of random forests' feature estimation revealed the top-ten spatiotemporal predictive features utilized in the model: foot strike angle, coronal range of motion [trunk and lumbar], stride length, gait speed, lateral step variability, and toe-off angle. Conclusion: These results indicate that machine learning effectively classifies advanced PD patients as freezers or nonfreezers based on SAW trials in their non-medicated/non-stimulated condition. The machine learning models, specifically random forests, not only rely on but utilize salient spatial and temporal gait features for FOG classification.
RESUMEN
INTRODUCTION: The current approach to assessing bradykinesia in Parkinson's Disease relies on the Unified Parkinson's Disease Rating Scale (UPDRS), which is a numeric scale. Inertial sensors offer the ability to probe subcomponents of bradykinesia: motor speed, amplitude, and rhythm. Thus, we sought to investigate the differential effects of high-frequency compared to low-frequency subthalamic nucleus (STN) deep brain stimulation (DBS) on these quantified facets of bradykinesia. METHODS: We recruited advanced Parkinson's Disease subjects with a chronic bilateral subthalamic nucleus (STN) DBS implantation to a single-blind stimulation trial where each combination of medication state (OFF/ON), electrode contacts, and stimulation frequency (60 Hz/180 Hz) was assessed. The Kinesia One sensor system was used to measure upper limb bradykinesia. For each stimulation trial, subjects performed extremity motor tasks. Sensor data were recorded continuously. We identified STN DBS parameters that were associated with improved upper extremity bradykinesia symptoms using a mixed linear regression model. RESULTS: We recruited 22 subjects (6 females) for this study. The 180 Hz STN DBS (compared to the 60 Hz STN DBS) and dopaminergic medications improved all subcomponents of upper extremity bradykinesia (motor speed, amplitude, and rhythm). For the motor rhythm subcomponent of bradykinesia, ventral contacts yielded improved symptom improvement compared to dorsal contacts. CONCLUSION: The differential impact of high- and low-frequency STN DBS on the symptoms of bradykinesia may advise programming for these patients but warrants further investigation. Wearable sensors represent a valuable addition to the armamentarium that furthers our ability to conduct objective, quantitative clinical assessments.
Asunto(s)
Estimulación Encefálica Profunda , Hipocinesia , Enfermedad de Parkinson , Núcleo Subtalámico , Humanos , Enfermedad de Parkinson/terapia , Enfermedad de Parkinson/fisiopatología , Estimulación Encefálica Profunda/métodos , Estimulación Encefálica Profunda/instrumentación , Hipocinesia/terapia , Hipocinesia/fisiopatología , Núcleo Subtalámico/fisiopatología , Femenino , Masculino , Persona de Mediana Edad , AncianoRESUMEN
Subthalamic nucleus deep brain stimulation (STN-DBS) alleviates motor symptoms of Parkinson's disease (PD), thereby improving quality of life. However, quantitative brain markers to evaluate DBS responses and select suitable patients for surgery are lacking. Here, we used metabolic brain imaging to identify a reproducible STN-DBS network for which individual expression levels increased with stimulation in proportion to motor benefit. Of note, measurements of network expression from metabolic and BOLD imaging obtained preoperatively predicted motor outcomes determined after DBS surgery. Based on these findings, we computed network expression in 175 PD patients, with time from diagnosis ranging from 0 to 21 years, and used the resulting data to predict the outcome of a potential STN-DBS procedure. While minimal benefit was predicted for patients with early disease, the proportion of potential responders increased after 4 years. Clinically meaningful improvement with stimulation was predicted in 18.9 - 27.3% of patients depending on disease duration.
RESUMEN
Background: Although deep brain stimulation (DBS) has established uses for patients with movement disorders and epilepsy, it is under consideration for a wide range of neurologic and neuropsychiatric conditions. Objective: To review successful and unsuccessful DBS clinical trials and identify factors associated with early trial termination. Methods: The ClinicalTrials.gov database was screened for all studies related to DBS. Information regarding condition of interest, study aim, trial design, trial success, and, if applicable, reason for failure was collected. Trials were compared and logistic regression was utilized to identify independent factors associated with trial termination. Results: Of 325 identified trials, 79.7% were successful and 20.3% unsuccessful. Patient recruitment, sponsor decision, and device issues were the most cited reasons for termination. 242 trials (74.5%) were interventional with 78.1% successful. There was a statistically significant difference between successful and unsuccessful trials in number of funding sources (p = 0.0375). NIH funding was associated with successful trials while utilization of other funding sources (academic institutions and community organizations) was associated with unsuccessful trials. 83 trials (25.5%) were observational with 84.0% successful; there were no statistically significant differences between successful and unsuccessful observational trials. Conclusion: One in five clinical trials for DBS were found to be unsuccessful, most commonly due to patient recruitment difficulties. The source of funding was the only factor associated with trial success. As DBS research continues to grow, understanding the current state of clinical trials will help design successful future studies, thereby minimizing futile expenditures of time, cost, and patient engagement.
RESUMEN
INTRODUCTION: Directional deep brain stimulation (dDBS) has been suggested to have a similar therapeutic effect when compared with the traditional omnidirectional DBS, but with an improved therapeutic window that yields optimized clinical effect owing to the ability to better direct, or "steer," electric current. We present our single-center, retrospective analysis of our experience in the use of dDBS in patients with movement disorders and provide a review of the literature. MATERIALS AND METHODS: We identified all patients with Parkinson disease (PD) and essential tremor (ET) who received a dDBS system between 2018 and 2022 and retrospectively examined characteristics of their longitudinal treatment. A total of 70 leads were identified across 42 patients (28 PD, 14 ET). RESULTS: Three types of systems were implemented (single-segment activation, 45.2% of patients; multiple independent current control, 50.0%; and local field potential sensing-enabled, 4.7%). The subthalamic nucleus or globus pallidus internus was targeted in PD, and the ventral intermediate nucleus of the thalamus in ET. Across the entire cohort (n = 70 leads), at initial programming, 54.2% of leads (n = 38) were programmed using directional stimulation. At the most recent reprogramming, 58.6% of leads (n = 41) implemented directionality. In patients with PD, the average decrease in levodopa-equivalent daily dose at six months after implantation was 35.4% ± 39.2%. Despite the ability to steer current to relieve stimulation-induced side effects, ten leads in six patients required surgical revision owing to electrode malposition. CONCLUSIONS: We show wide adaptability and implementation of directional stimulation, adding to the growing compendium of real-world uses of dDBS therapy. We used directionality to improve clinical response in both patients with PD and patients with ET and found that its programming flexibility was used at high rates long after implantation and initial programming. In patients with PD, dDBS led to a significant reduction in dopaminergic medication, suggesting sustained clinical improvement. Nonetheless, accurate surgical placement remains necessary to ensure optimal clinical outcomes.
Asunto(s)
Estimulación Encefálica Profunda , Temblor Esencial , Enfermedad de Parkinson , Núcleo Subtalámico , Humanos , Estudios Retrospectivos , Estimulación Encefálica Profunda/efectos adversos , Resultado del Tratamiento , Enfermedad de Parkinson/terapia , Temblor Esencial/terapiaRESUMEN
Objective: The spatiotemporal gait changes in advanced Parkinson's disease (PD) remain a treatment challenge and have variable responses to L-dopa and subthalamic deep brain stimulation (STN-DBS). The purpose of this study was to determine whether low-frequency STN-DBS (LFS; 60 Hz) elicits a differential response to high-frequency STN-DBS (HFS; 180 Hz) in spatiotemporal gait kinematics. Methods: Advanced PD subjects with chronic STN-DBS were evaluated in both the OFF and ON medication states with LFS and HFS stimulation. Randomization of electrode contact pairs and frequency conditions was conducted. Instrumented Stand and Walk assessments were carried out for every stimulation/medication condition. LM-ANOVA was employed for analysis. Results: Twenty-two PD subjects participated in the study, with a mean age (SD) of 63.9 years. Significant interactions between frequency (both LFS and HFS) and electrode contact pairs (particularly ventrally located contacts) were observed for both spatial (foot elevation, toe-off angle, stride length) and temporal (foot speed, stance, single limb support (SLS) and foot swing) gait parameters. A synergistic effect was also demonstrated with L-dopa and both HFS and LFS for right SLS, left stance, left foot swing, right toe-off angle, and left arm range of motion. HFS produced significant improvement in trunk and lumbar range of motion compared to LFS. Conclusion: The study provides evidence of synergism of L-dopa and STN-DBS on lower limb spatial and temporal measures in advanced PD. HFS and LFS STN-DBS produced equivalent effects among all other tested lower limb gait features. HFS produced significant trunk and lumbar kinematic improvements.
RESUMEN
BACKGROUND: Neurological symptoms are common manifestation in acute COVID-19. This includes hyper- and hypokinetic movement disorders. Data on their outcome, however, is limited. METHODS: Cases with new-onset COVID-19-associated movement disorders were identified by searching the literature. Authors were contacted for outcome data which were reviewed and analyzed. RESULTS: Movement disorders began 12.6 days on average after the initial onset of COVID-19. 92% of patients required hospital admission (mean duration 23 days). In a fraction of patients (6 of 27; 22%; 4 males/2 females, mean age 66.8 years) the movement disorder (ataxia, myoclonus, tremor, parkinsonism) was still present after a follow-up period of 7.5 ± 3 weeks. Severe COVID-19 in general and development of encephalopathy were risk factors, albeit not strong predictors, for the persistence. CONCLUSIONS: The prognosis of new-onset COVID-19-associated movement disorder appears to be generally good. The majority recovered without residual symptoms within several weeks or months. Permanent cases may be due to unmasking of a previous subclinical movement disorder or due to vascular/demyelinating damage. Given the relatively low response rate of one third only and the heterogeneity of mechanisms firm conclusions on the (long-term) outome cannot, however, be drawn.
Asunto(s)
COVID-19 , Trastornos del Movimiento , Masculino , Femenino , Humanos , Anciano , COVID-19/complicaciones , Estudios de Seguimiento , Trastornos del Movimiento/etiología , Factores de Riesgo , Temblor/complicacionesRESUMEN
Parkinson's disease medication treatment planning is generally based on subjective data obtained through clinical, physician-patient interactions. The Personal KinetiGraph™ (PKG) and similar wearable sensors have shown promise in enabling objective, continuous remote health monitoring for Parkinson's patients. In this proof-of-concept study, we propose to use objective sensor data from the PKG and apply machine learning to cluster patients based on levodopa regimens and response. The resulting clusters are then used to enhance treatment planning by providing improved initial treatment estimates to supplement a physician's initial assessment. We apply k-means clustering to a dataset of within-subject Parkinson's medication changes-clinically assessed by the MDS-Unified Parkinson's Disease Rating Scale-III (MDS-UPDRS-III) and the PKG sensor for movement staging. A random forest classification model was then used to predict patients' cluster allocation based on their respective demographic information, MDS-UPDRS-III scores, and PKG time-series data. Clinically relevant clusters were partitioned by levodopa dose, medication administration frequency, and total levodopa equivalent daily dose-with the PKG providing similar symptomatic assessments to physician MDS-UPDRS-III scores. A random forest classifier trained on demographic information, MDS-UPDRS-III scores, and PKG time-series data was able to accurately classify subjects of the two most demographically similar clusters with an accuracy of 86.9%, an F1 score of 90.7%, and an AUC of 0.871. A model that relied solely on demographic information and PKG time-series data provided the next best performance with an accuracy of 83.8%, an F1 score of 88.5%, and an AUC of 0.831, hence further enabling fully remote assessments. These computational methods demonstrate the feasibility of using sensor-based data to cluster patients based on their medication responses with further potential to assist with medication recommendations.
Asunto(s)
Enfermedad de Parkinson , Humanos , Levodopa/uso terapéutico , Pruebas de Estado Mental y Demencia , Enfermedad de Parkinson/diagnóstico , Enfermedad de Parkinson/tratamiento farmacológico , TecnologíaRESUMEN
An increasing number of identified Parkinson's disease (PD) risk loci contain genes highly expressed in innate immune cells, yet their role in pathology is not understood. We hypothesize that PD susceptibility genes modulate disease risk by influencing gene expression within immune cells. To address this, we have generated transcriptomic profiles of monocytes from 230 individuals with sporadic PD and healthy subjects. We observed a dysregulation of mitochondrial and proteasomal pathways. We also generated transcriptomic profiles of primary microglia from brains of 55 subjects and observed discordant transcriptomic signatures of mitochondrial genes in PD monocytes and microglia. We further identified 17 PD susceptibility genes whose expression, relative to each risk allele, is altered in monocytes. These findings reveal widespread transcriptomic alterations in PD monocytes, with some being distinct from microglia, and facilitate efforts to understand the roles of myeloid cells in PD as well as the development of biomarkers.
Asunto(s)
Enfermedad de Parkinson , Humanos , Enfermedad de Parkinson/genética , Monocitos/metabolismo , Perfilación de la Expresión Génica , Transcriptoma , Encéfalo/metabolismoRESUMEN
Deep brain stimulation (DBS) is a surgical treatment for advanced Parkinson's disease (PD) that has undergone technological evolution that parallels an expansion in clinical phenotyping, neurophysiology, and neuroimaging of the disease state. Machine learning (ML) has been successfully used in a wide range of healthcare problems, including DBS. As computational power increases and more data become available, the application of ML in DBS is expected to grow. We review the literature of ML in DBS and discuss future opportunities for such applications. Specifically, we perform a comprehensive review of the literature from PubMed, the Institute for Scientific Information's Web of Science, Cochrane Database of Systematic Reviews, and Institute of Electrical and Electronics Engineers' (IEEE) Xplore Digital Library for ML applications in DBS. These studies are broadly placed in the following categories: (1) DBS candidate selection; (2) programming optimization; (3) surgical targeting; and (4) insights into DBS mechanisms. For each category, we provide and contextualize the current body of research and discuss potential future directions for the application of ML in DBS.
RESUMEN
More than one million people currently live with Parkinson's Disease (PD) in the U.S. alone. Medications, such as levodopa, can help manage PD symptoms. However, medication treatment planning is generally based on patient history and limited interaction between physicians and patients during office visits. This limits the extent of benefit that may be derived from the treatment as disease/patient characteristics are generally non-stationary. Wearable sensors that provide continuous monitoring of various symptoms, such as bradykinesia and dyskinesia, can enhance symptom management. However, using such data to overhaul the current static medication treatment planning approach and prescribe personalized medication timing and dosage that accounts for patient/care-giver/physician feedback/preferences remains an open question. We develop a model to prescribe timing and dosage of medications, given the motor fluctuation data collected using wearable sensors in real-time. We solve the resulting model using deep reinforcement learning (DRL). The prescribed policy determines the optimal treatment plan that minimizes patient's symptoms. Our results show that the model-prescribed policy outperforms the static a priori treatment plan in improving patients' symptoms, providing a proof-of-concept that DRL can augment medical decision making for treatment planning of chronic disease patients.
Asunto(s)
Discinesias , Enfermedad de Parkinson , Toma de Decisiones Clínicas , Humanos , Levodopa/uso terapéutico , Enfermedad de Parkinson/tratamiento farmacológicoRESUMEN
: Deep brain stimulation (DBS) of the subthalamic nucleus (STN) has become an effective and widely used tool in the treatment of Parkinson's disease (PD). STN-DBS has varied effects on speech. Clinical speech ratings suggest worsening following STN-DBS, but quantitative intelligibility, perceptual, and acoustic studies have produced mixed and inconsistent results. Improvements in phonation and declines in articulation have frequently been reported during different speech tasks under different stimulation conditions. Questions remain about preferred STN-DBS stimulation settings. Seven right-handed, native speakers of English with PD treated with bilateral STN-DBS were studied off medication at three stimulation conditions: stimulators off, 60 Hz (low frequency stimulation-LFS), and the typical clinical setting of 185 Hz (High frequency-HFS). Spontaneous speech was recorded in each condition and excerpts were prepared for transcription (intelligibility) and difficulty judgements. Separate excerpts were prepared for listeners to rate abnormalities in voice, articulation, fluency, and rate. Intelligibility for spontaneous speech was reduced at both HFS and LFS when compared to STN-DBS off. On the average, speech produced at HFS was more intelligible than that produced at LFS, but HFS made the intelligibility task (transcription) subjectively more difficult. Both voice quality and articulation were judged to be more abnormal with DBS on. STN-DBS reduced the intelligibility of spontaneous speech at both LFS and HFS but lowering the frequency did not improve intelligibility. Voice quality ratings with STN-DBS were correlated with the ratings made without stimulation. This was not true for articulation ratings. STN-DBS exacerbated existing voice problems and may have introduced new articulatory abnormalities. The results from individual DBS subjects showed both improved and reduced intelligibility varied as a function of DBS, with perceived changes in voice appearing to be more reflective of intelligibility than perceived changes in articulation.
RESUMEN
The emergence of motion sensors as a tool that provides objective motor performance data on individuals afflicted with Parkinson's disease offers an opportunity to expand the horizon of clinical care for this neurodegenerative condition. Subjective clinical scales and patient based motor diaries have limited clinometric properties and produce a glimpse rather than continuous real time perspective into motor disability. Furthermore, the expansion of machine learn algorithms is yielding novel classification and probabilistic clinical models that stand to change existing treatment paradigms, refine the application of advance therapeutics, and may facilitate the development and testing of disease modifying agents for this disease. We review the use of inertial sensors and machine learning algorithms in Parkinson's disease.
RESUMEN
BACKGROUND: Cerebrotendinous xanthomatosis (CTX) is a rare disorder due to defective sterol 27-hydroxylase causing a lack of chenodeoxycholic acid (CDCA) production and high plasma cholestanol levels. OBJECTIVES: Our objective was to review the diagnosis and treatment results in 43 CTX cases. METHODS: We conducted a careful review of the diagnosis, laboratory values, treatment, and clinical course in 43 CTX cases. RESULTS: The mean age at diagnosis was 32 years; the average follow-up was 8 years. Cases had the following conditions: 53% chronic diarrhea, 74% cognitive impairment, 70% premature cataracts, 77% tendon xanthomas, 81% neurologic disease, and 7% premature cardiovascular disease. The mean serum cholesterol concentration was 190 mg/dL; the mean plasma cholestanol level was 32 mg/L (normal <5.0 mg/L), which decreased to 6.0 mg/L (-81%) with CDCA therapy generally given as 250 mg orally 3 times daily. Of those tested on treatment, 63% achieved cholestanol levels of <5.0 mg/L; 91% had normal liver enzyme levels; none had significant liver problems after dose adjustment. Treatment improved symptoms in 57% at follow-up, but 20% with advanced disease continued to deteriorate. In the United States, CDCA has been approved for gallstone dissolution, but not for CTX despite long-term efficacy and safety data. CONCLUSIONS: Health care providers seeing young patients with tendon xanthomas and relatively normal cholesterol levels, especially those with cataracts and learning problems, should consider the diagnosis of CTX so they can receive treatment. CDCA should receive regulatory approval to facilitate therapy for the prevention of the complications of the disease.
Asunto(s)
Xantomatosis Cerebrotendinosa/diagnóstico , Xantomatosis Cerebrotendinosa/terapia , Adulto , Niño , Femenino , Humanos , Masculino , Persona de Mediana Edad , Resultado del Tratamiento , Adulto JovenRESUMEN
BACKGROUND: Deep brain stimulation of the subthalamic nucleus (STN) has demonstrated efficacy in improving motor disability in Parkinson's disease. The recently developed quantitative susceptibility mapping (QSM) technique, which can accurately map iron deposits in deep brain nuclei, promises precise targeting of the STN. OBJECTIVE: To demonstrate the use of QSM to target STN effectively by correlating with classical physiological-based targeting measures in a prospective study. METHODS: The precision and accuracy of direct targeting with QSM was examined in a total of 25 Parkinson's disease patients between 2013 and 2015 at our institution. QSM was utilized as the primary magnetic resonance imaging (MRI) method to perform direct STN targeting on a stereotactic planning station utilizing computed tomography/MR fusion. Intraoperative microelectrode recordings (MER) were obtained to confirm appropriate trajectory through the sensorimotor STN. RESULTS: Estimations of STN thickness between the MER and QSM methods appeared to be correlated. Mean STN thickness was 5.3 mm. Kinesthetic responsive cells were found in > 90% of electrode runs. The mean radial error (±SEM) was 0.54 ± 0.1 mm. Satisfactory clinical response as determined by Unified Parkinson's Disease Rating Scale (UPDRS III) was seen at 12 mo after surgery. CONCLUSION: Direct targeting of the sensorimotor STN using QSM demonstrates MER correlation and can be safely used for deep brain stimulation lead placement with satisfactory clinical response. These results imply that targeting based on QSM signaling alone is sufficient to obtain reliable and reproducible outcomes in the absence of physiological recordings.
Asunto(s)
Estimulación Encefálica Profunda/métodos , Enfermedad de Parkinson/terapia , Núcleo Subtalámico , Anciano , Antiparkinsonianos/uso terapéutico , Mapeo Encefálico/métodos , Electrodos Implantados , Femenino , Humanos , Levodopa/administración & dosificación , Imagen por Resonancia Magnética/métodos , Masculino , Microelectrodos , Persona de Mediana Edad , Examen Neurológico , Cuidados Posoperatorios/métodos , Trastornos Psicomotores/terapia , Resultado del TratamientoRESUMEN
BACKGROUND: Post-hypoxic myoclonus (PHM) is a syndrome that occurs when a patient has suffered hypoxic brain injury. The myoclonus is usually multifocal and generalized, often stemming from both cortical and subcortical origins. In severe cases, pharmacological treatments with antiepileptic medications may not satisfactorily control the myoclonus. METHODS: We present a case of a 23-year-old male with chronic medication refractory PHM following a cardiopulmonary arrest related to an asthmatic attack who improved with bilateral globus pallidus internus (GPi) deep brain stimulation (DBS). We review the clinical features of PHM, as well as the preoperative and postoperative Unified Myoclonus Rating Scale scores and DBS programming parameters in this patient and compare them with the three other published PHM-DBS cases in the literature. RESULTS: This patient experienced an alleviation of myoclonic jerks at rest and a 39% reduction in action myoclonus with improvement in both positive and negative myoclonus with bilateral GPi-DBS. High frequency stimulation (130 Hz) with amplitudes >2.5 V were needed for the therapeutic response. DISCUSSION: We demonstrate a robust improvement in a medication refractory PHM patient with bilateral GPi-DBS, and suggest that it is a viable therapeutic option for debilitating post-hypoxic myoclonus.
RESUMEN
OBJECTIVE: High frequency stimulation (HFS) of the subthalamic nucleus (STN) is a well-established therapy for Parkinson's disease (PD), particularly the cardinal motor symptoms and levodopa induced motor complications. Recent studies have suggested the possible role of 60 Hz stimulation in STN-deep brain stimulation (DBS) for patients with gait disorder. The objective of this study was to develop a computational model, which stratifies patients a priori based on symptomatology into different frequency settings (i.e., high frequency or 60 Hz). METHODS: We retrospectively analyzed preoperative MDS-Unified Parkinson's Disease Rating Scale III scores (32 indicators) collected from 20 PD patients implanted with STN-DBS at Mount Sinai Medical Center on either 60 Hz stimulation (ten patients) or HFS (130-185 Hz) (ten patients) for an average of 12 months. Predictive models using the Random Forest classification algorithm were built to associate patient/disease characteristics at surgery to the stimulation frequency. These models were evaluated objectively using leave-one-out cross-validation approach. RESULTS: The computational models produced, stratified patients into 60 Hz or HFS (130-185 Hz) with 95% accuracy. The best models relied on two or three predictors out of the 32 analyzed for classification. Across all predictors, gait and rest tremor of the right hand were consistently the most important. CONCLUSIONS: Computational models were developed using preoperative clinical indicators in PD patients treated with STN-DBS. These models were able to accurately stratify PD patients into 60 Hz stimulation or HFS (130-185 Hz) groups a priori, offering a unique potential to enhance the utilization of this therapy based on clinical subtypes.