Auditory oddball responses in the human subthalamic nucleus and substantia nigra pars reticulata.

The auditory oddball is a mainstay in research on attention, novelty, and sensory prediction. How this task engages subcortical structures like the subthalamic nucleus and substantia nigra pars reticulata is unclear. We administered an auditory OB task while recording single unit activity (35 units) and local field potentials (57 recordings) from the subthalamic nucleus and substantia nigra pars reticulata of 30 patients with Parkinson's disease undergoing deep brain stimulation surgery. We found tone modulated and oddball modulated units in both regions. Population activity differentiated oddball from standard trials from 200 ms to 1000 ms after the tone in both regions. In the substantia nigra, beta band activity in the local field potential was decreased following oddball tones. The oddball related activity we observe may underlie attention, sensory prediction, or surprise-induced motor suppression.

Continental-scale migration patterns and origin of Helicoverpa zea (Lepidoptera: Noctuidae) based on a biogeochemical marker.

Insect migrations have ecological and economic impacts, particularly in agriculture. However, there is limited knowledge about the migratory movements of pests at the continental scale, which is an important factor influencing the spread of resistance genes. Understanding the migratory patterns of economic pests, like Helicoverpa zea (Boddie), is essential for improving Integrated Pest Management (IPM) and Insect Resistance Management (IRM) strategies. In this study, we used stable hydrogen isotopic ratios in wing tissue as a biogeochemical marker to examine migratory patterns and estimate the native origins of H. zea individuals collected across a wide latitudinal gradient in North America. Samples collected at higher latitudes (Ontario, Canada and Minnesota, USA) exhibited a greater proportion (60%-96%) of nonlocal individuals, with an increased probability of origin from the southeastern United States. Populations from mid-latitudes (Florida, North Carolina, and South Carolina) showed a blend of local and nonlocal (40%-60%) individuals. Finally, 15% of the southernmost population individuals (Puerto Rico) were classified as migratory, with some having a probability of origin at higher latitudes (>30°). Overall, our results provide evidence of a northward spring/summer migration of H. zea in North America and underscore the significance of the southeastern United States as a hub for genetic flow. In addition, based on stable hydrogen isotopic ratios, there is strong evidence of reverse (southward) migration of H. zea from the continental United States to Puerto Rico. Our study highlights the implications for IPM and IRM programs and the need for management strategies that account for both northward and southward migration patterns.

Modeling Instantaneous Firing Rate of Deep Brain Stimulation Target Neuronal Ensembles in the Basal Ganglia and Thalamus.

OBJECTIVE: Deep brain stimulation (DBS) is an effective treatment for movement disorders, including Parkinson disease and essential tremor. However, the underlying mechanisms of DBS remain elusive. Despite the capability of existing models in interpreting experimental data qualitatively, there are very few unified computational models that quantitatively capture the dynamics of the neuronal activity of varying stimulated nuclei-including subthalamic nucleus (STN), substantia nigra pars reticulata (SNr), and ventral intermediate nucleus (Vim)-across different DBS frequencies. MATERIALS AND METHODS: Both synthetic and experimental data were used in the model fitting; the synthetic data were generated by an established spiking neuron model that was reported in our previous work, and the experimental data were provided using single-unit microelectrode recordings (MERs) during DBS (microelectrode stimulation). Based on these data, we developed a novel mathematical model to represent the firing rate of neurons receiving DBS, including neurons in STN, SNr, and Vim-across different DBS frequencies. In our model, the DBS pulses were filtered through a synapse model and a nonlinear transfer function to formulate the firing rate variability. For each DBS-targeted nucleus, we fitted a single set of optimal model parameters consistent across varying DBS frequencies. RESULTS: Our model accurately reproduced the firing rates observed and calculated from both synthetic and experimental data. The optimal model parameters were consistent across different DBS frequencies. CONCLUSIONS: The result of our model fitting was in agreement with experimental single-unit MER data during DBS. Reproducing neuronal firing rates of different nuclei of the basal ganglia and thalamus during DBS can be helpful to further understand the mechanisms of DBS and to potentially optimize stimulation parameters based on their actual effects on neuronal activity.

Subthalamic and pallidal neurons are modulated during externally cued movements in Parkinson's disease.

External sensory cues can reduce freezing of gait in people with Parkinson's disease (PD), yet the role of the basal ganglia in these movements is unclear. We used microelectrode recordings to examine modulations in single unit (SU) and oscillatory local field potentials (LFP) during auditory-cued rhythmic pedaling movements of the feet. We tested five blocks of increasing cue frequencies (1 Hz, 1.5 Hz, 2 Hz, 2.5 Hz, and 3 Hz) in 24 people with PD undergoing deep brain stimulation surgery of the subthalamic nucleus (STN) or globus pallidus internus (GPi). Single unit firing and beta band LFPs (13-30 Hz) in response to movement onsets or cue onsets were examined. We found that the timing accuracy of foot pedaling decreased with faster cue frequencies. Increasing cue frequencies also attenuated firing rates in both STN and GPi neurons. Peak beta power in the GPi and STN showed different responses to the task. GPi beta power showed persistent suppression with fast cues and phasic modulation with slow cues. STN beta power showed enhanced beta synchronization following movement. STN beta power also correlated with rate of pedaling. Overall, we showed task-related responses in the GPi and STN during auditory-cued movements with differential roles in sensory and motor control. The results suggest a role for both input and output basal ganglia nuclei in auditory rhythmic pacing of gait-like movements in PD.

Hail netting excludes key insect pests and protects from fruit damage in a commercial Minnesota apple orchard.

Exclusion netting in some European and North American apple (Malus domestica Borkhausen, Rosaceae, Rosales) orchards has been documented to be an effective method of control for multiple insect pest species. By minimizing reliance on insecticides, these orchards have reduced costs, risks to the environment and non-target species, and reduced the risk of insecticide resistance. This study examined the use of commercially available hail netting (DrapeNet®; Prosser, WA) as a pest exclusion strategy under conditions in Minnesota, USA. In 2021 and 2022, we assessed the efficacy of hail netting as a tool for pest suppression in orchards by monitoring pest species in netted and open plots crossed with and without insecticide applications. Our findings show that both of the major pest species in Minnesota, the codling moth (Cydia pomonella L.; Lepidoptera: Tortricidae) and the apple maggot (Rhagoletis pomonella Walsh; Diptera: Tephritidae), were significantly reduced inside the netting compared to open plots by 94% and 96%, respectively. For a secondary pest, the red-banded leafroller (Argyrotaenia velutinana Walker; Lepidoptera: Tortricidae), moth populations were reduced by 56%. We also found that insecticide application alone did not significantly reduce pest pressure in these species. Additionally, we investigated the subsequent effects of hail netting on fruit quality and yield. The use of hail netting and insecticide application resulted in significantly higher proportions of high-quality fruit at harvest. However, netting did not significantly influence yield. These findings suggest that hail netting can be used to control Midwest apple insect pests with limited insecticide applications while maintaining high fruit quality.

Extended Sentinel Monitoring of Helicoverpa zea Resistance to Cry and Vip3Aa Toxins in Bt Sweet Corn: Assessing Changes in Phenotypic and Allele Frequencies of Resistance.

Transgenic corn and cotton that produce Cry and Vip3Aa toxins derived from Bacillus thuringiensis (Bt) are widely planted in the United States to control lepidopteran pests. The sustainability of these Bt crops is threatened because the corn earworm/bollworm, Helicoverpa zea (Boddie), is evolving a resistance to these toxins. Using Bt sweet corn as a sentinel plant to monitor the evolution of resistance, collaborators established 146 trials in twenty-five states and five Canadian provinces during 2020-2022. The study evaluated overall changes in the phenotypic frequency of resistance (the ratio of larval densities in Bt ears relative to densities in non-Bt ears) in H. zea populations and the range of resistance allele frequencies for Cry1Ab and Vip3Aa. The results revealed a widespread resistance to Cry1Ab, Cry2Ab2, and Cry1A.105 Cry toxins, with higher numbers of larvae surviving in Bt ears than in non-Bt ears at many trial locations. Depending on assumptions about the inheritance of resistance, allele frequencies for Cry1Ab ranged from 0.465 (dominant resistance) to 0.995 (recessive resistance). Although Vip3Aa provided high control efficacy against H. zea, the results show a notable increase in ear damage and a number of surviving older larvae, particularly at southern locations. Assuming recessive resistance, the estimated resistance allele frequencies for Vip3Aa ranged from 0.115 in the Gulf states to 0.032 at more northern locations. These findings indicate that better resistance management practices are urgently needed to sustain efficacy the of corn and cotton that produce Vip3Aa.

Beta band oscillations in the motor thalamus are modulated by visuomotor coordination in essential tremor patients.

Introduction: Beta oscillations in sensorimotor structures contribute to the planning, sequencing, and stopping of movements, functions that are typically associated with the role of the basal ganglia. The presence of beta oscillations (13-30 Hz) in the cerebellar zone of the thalamus (the ventral intermediate nucleus - Vim) indicates that this rhythm may also be involved in cerebellar functions such as motor learning and visuomotor adaptation. Methods: To investigate the possible role of Vim beta oscillations in visuomotor coordination, we recorded local field potential (LFP) and multiunit activity from the Vim of essential tremor (ET) patients during neurosurgery for the implantation of deep brain stimulation (DBS) electrodes. Using a computer, patients performed a visuomotor adaptation task that required coordinating center-out movements with incongruent visual feedback imposed by inversion of the computer display. Results: The results show that, in ET, Vim beta oscillations of the LFP were lower during the incongruent center-out task than during the congruent orientation. Vim firing rates increased significantly during periods of low beta power, particularly on approach to the peripheral target. In contrast, beta power in the subthalamic nucleus of Parkinson's disease (PD) patients did not differ significantly between the incongruent and the congruent orientation of the center-out task. Discussion: The findings support the hypothesis that beta oscillations of the Vim are modulated by novel visuomotor tasks. The inverse relationship between the power of Vim-LFP beta oscillations and Vim firing rates suggest that the suppression of beta oscillations may facilitate information throughput to the thalamocortical circuit by modulation of Vim firing rates.

Top-down control of human motor thalamic neuronal activity during the auditory oddball task.

The neurophysiology of selective attention in visual and auditory systems has been studied in animal models but not with single unit recordings in human. Here, we recorded neuronal activity in the ventral intermediate nucleus as well as the ventral oral anterior, and posterior nuclei of the motor thalamus in 25 patients with parkinsonian (n = 6) and non-parkinsonian tremors (n = 19) prior to insertion of deep brain stimulation electrodes while they performed an auditory oddball task. In this task, patients were requested to attend and count the randomly occurring odd or "deviant" tones, ignore the frequent standard tones and report the number of deviant tones at trial completion. The neuronal firing rate decreased compared to baseline during the oddball task. Inhibition was specific to auditory attention as incorrect counting or wrist flicking to the deviant tones did not produce such inhibition. Local field potential analysis showed beta (13-35 Hz) desynchronization in response to deviant tones. Parkinson's disease patients off medications had more beta power than the essential tremor group but less neuronal modulation of beta power to the attended tones, suggesting that dopamine modulates thalamic beta oscillations for selective attention. The current study demonstrated that ascending information to the motor thalamus can be suppressed during auditory attending tasks, providing indirect evidence for the searchlight hypothesis in humans. These results taken together implicate the ventral intermediate nucleus in non-motor cognitive functions, which has implications for the brain circuitry for attention and the pathophysiology of Parkinson's disease.

Long-Term Recording of Subthalamic Aperiodic Activities and Beta Bursts in Parkinson's Disease.

BACKGROUND: Local field potentials (LFPs) represent the summation of periodic (oscillations) and aperiodic (fractal) signals. Although previous studies showed changes in beta band oscillations and burst characteristics of the subthalamic nucleus (STN) in Parkinson's disease (PD), how aperiodic activity in the STN is related to PD pathophysiology is unknown. OBJECTIVES: The study aimed to characterize the long-term effects of STN-deep brain stimulation (DBS) and dopaminergic medications on aperiodic activities and beta bursts. METHODS: A total of 10 patients with PD participated in this longitudinal study. Simultaneous bilateral STN-LFP recordings were conducted in six separate visits during a period of 18 months using the Activa PC + S device in the off and on dopaminergic medication states. We used irregular-resampling auto-spectral analysis to separate oscillations and aperiodic components (exponent and offset) in the power spectrum of STN-LFP signals in beta band. RESULTS: Our results revealed a systematic increase in both the exponent and the offset of the aperiodic spectrum over 18 months following the DBS implantation, independent of the dopaminergic medication state of patients with PD. In contrast, beta burst durations and amplitudes were stable over time and were suppressed by dopaminergic medications. CONCLUSIONS: These findings indicate that oscillations and aperiodic activities reflect at least partially distinct yet complementary neural mechanisms, which should be considered in the design of robust biomarkers to optimize adaptive DBS. Given the link between increased gamma-aminobutyric acidergic (GABAergic) transmission and higher aperiodic activity, our findings suggest that long-term STN-DBS may relate to increased inhibition in the basal ganglia. © 2022 International Parkinson and Movement Disorder Society.

Hail netting: an economically competitive IPM alternative to insecticides for Midwest apple production.

Apple orchards are highly managed agricultural ecosystems where growers typically rely on insecticides to minimize the risk of pest-related fruit losses. Apple growers practicing integrated pest management require cost-effective alternatives to conventional insecticides for control of major pests such as codling moth (Cydia pomonella L.) and apple maggot (Rhagoletis pomonella Walsh). Exclusion netting has been shown to effectively control multiple insect pest species, limit fruit damage and reduce the use of insecticides while also conferring consumer and environmental benefits. In this study, partial budgeting was applied to explore the financial efficacy of using a hail netting (DrapeNet®) system as a sustainable pest management strategy for Midwest U.S. apple (Malus x domestica). The cost of the hail netting was compared to a common Midwest insecticide spray regimen for apples using yield and quality data from a field study at two Minnesota apple orchards in 2021-2022. The PB analysis indicated that the netting system was an economically competitive alternative to conventional insecticide applications. The economic results were robust across a range of apple prices and yields suggesting that Minnesota apple growers can benefit economically from the application of hail netting for sustainable pest management.

Corrigendum: Modeling-informed Engineered Genetic Incompatibility strategies to overcome resistance in the invasive Drosophila suzukii.

[This corrects the article DOI: 10.3389/finsc.2022.1063789.].

Long-Term Follow-Up on Bilateral Posterior Hypothalamic Deep Brain Stimulation for Treating Refractory Aggressive Behavior in a Patient with Cri du Chat Syndrome: Analysis of Clinical Data, Intraoperative Microdialysis, and Imaging Connectomics.

Posterior hypothalamic-deep brain stimulation (pHyp-DBS) has been reported as a successful treatment for reducing refractory aggressive behaviors in patients with distinct primary diagnoses. Here, we report on a patient with cri du chat syndrome presenting severe self-injury and aggressive behaviors toward others, who was treated with pHyp-DBS. Positive results were observed at long-term follow-up in aggressive behavior and quality of life. Intraoperative microdialysis and imaging connectomics analysis were performed to investigate possible mechanisms of action. Our results suggest the involvement of limbic and motor areas and alterations in main neurotransmitter levels in the targeted area that are associated with positive results following treatment.

Persistent synaptic inhibition of the subthalamic nucleus by high frequency stimulation.

BACKGROUND: Deep brain stimulation (DBS) provides symptomatic relief in a growing number of neurological indications, but local synaptic dynamics in response to electrical stimulation that may relate to its mechanism of action have not been fully characterized. OBJECTIVE: The objectives of this study were to (1) study local synaptic dynamics during high frequency extracellular stimulation of the subthalamic nucleus (STN), and (2) compare STN synaptic dynamics with those of the neighboring substantia nigra pars reticulata (SNr). METHODS: Two microelectrodes were advanced into the STN and SNr of patients undergoing DBS surgery for Parkinson's disease (PD). Neuronal firing and evoked field potentials (fEPs) were recorded with one microelectrode during stimulation from an adjacent microelectrode. RESULTS: Inhibitory fEPs could be discerned within the STN and their amplitudes predicted bidirectional effects on neuronal firing (p = .013). There were no differences between STN and SNr inhibitory fEP dynamics at low stimulation frequencies (p > .999). However, inhibitory neuronal responses were sustained over time in STN during high frequency stimulation but not in SNr (p < .001) where depression of inhibitory input was coupled with a return of neuronal firing (p = .003). INTERPRETATION: Persistent inhibitory input to the STN suggests a local synaptic mechanism for the suppression of subthalamic firing during high frequency stimulation. Moreover, differences in the resiliency versus vulnerability of inhibitory inputs to the STN and SNr suggest a projection source- and frequency-specificity for this mechanism. The feasibility of targeting electrophysiologically-identified neural structures may provide insight into how DBS achieves frequency-specific modulation of neuronal projections.

Pest population dynamics are related to a continental overwintering gradient.

Overwintering success is an important determinant of arthropod populations that must be considered as climate change continues to influence the spatiotemporal population dynamics of agricultural pests. Using a long-term monitoring database and biologically relevant overwintering zones, we modeled the annual and seasonal population dynamics of a common pest, Helicoverpa zea (Boddie), based on three overwintering suitability zones throughout North America using four decades of soil temperatures: the southern range (able to persist through winter), transitional zone (uncertain overwintering survivorship), and northern limits (unable to survive winter). Our model indicates H. zea population dynamics are hierarchically structured with continental-level effects that are partitioned into three geographic zones. Seasonal populations were initially detected in the southern range, where they experienced multiple large population peaks. All three zones experienced a final peak between late July (southern range) and mid-August to mid-September (transitional zone and northern limits). The southern range expanded by 3% since 1981 and is projected to increase by twofold by 2099 but the areas of other zones are expected to decrease in the future. These changes suggest larger populations may persist at higher latitudes in the future due to reduced low-temperature lethal events during winter. Because H. zea is a highly migratory pest, predicting when populations accumulate in one region can inform synchronous or lagged population development in other regions. We show the value of combining long-term datasets, remotely sensed data, and laboratory findings to inform forecasting of insect pests.

Exclusion and Repulsion of Popillia japonica (Coleoptera: Scarabaeidae) Using Selected Coverings on High Tunnel Structures for Primocane Red Raspberry.

In temperate climates, there has been an increasing interest by fruit growers to implement the use of high tunnels, using a variety of coverings, to extend the season for fruit production. High tunnels also provide an opportunity to enhance insect pest management, via physical exclusion, and thus support reductions in insecticide use. Due to increasing pest pressure by the Japanese beetle, Popillia japonica Newman, in Midwest U.S. raspberry, a 3-year study (2017−2019) was conducted to evaluate the efficacy of selected high tunnel coverings to suppress adult beetle populations and minimize adult feeding injury. During each year of the study, P. japonica adult beetles were significantly reduced under poly-based coverings, with the ends open, and when a fine, nylon-mesh was used to cover the ends (p < 0.05). The poly-based covering also resulted in moderately higher ambient temperatures, which may have influenced beetle movement, including a "repellency effect" that encouraged beetles to exit the high tunnel structures. Although P. japonica adults are known to feed on raspberry flower clusters, including fruit, the majority (73−92%) of beetle feeding in this study was observed on the foliage. The impact of high tunnels on P. japonica are discussed within the context of developing sustainable Integrated Pest Management (IPM) programs for raspberry production.

Propensity for resistance development in the invasive berry pest, spotted-wing drosophila (Drosophila suzukii), under laboratory selection.

BACKGROUND: Over the past 14 years, the invasive vinegar fly, spotted-wing drosophila (Drosophila suzukii), has become one of the most damaging fruit pests in the United States. With regional economic losses estimated as high as $500 million for moderate infestations, D. suzukii control represents an often-untenable cost to growers. Management relies heavily on chemical control, which may be applied up to nine times in one season. The widespread use of chemical controls has led to concerns about insecticide resistance, and resistant field populations have already been documented in California and Michigan. RESULTS: We cultured sub-populations of three different Minnesota field populations of D. suzukii in the laboratory and exposed them to increasing concentrations of two commonly-used insecticides, zeta-cypermethrin (pyrethroid) and spinetoram (spinosyn). Over the exposure period, the sub-populations experienced an 8- to 45-fold increase in insecticide concentration. We saw significant increases in the median lethal concentration (LC50 ) values of one sub-population exposed to zeta-cypermethrin and one exposed to spinetoram. Across the spinetoram exposures, we also observed significant reductions in the top mortality values for three different sub-populations. CONCLUSION: Our results suggest that field populations of D. suzukii can develop resistance to zeta-cypermethrin and spinetoram in short periods of time under laboratory selection but that resistance to spinosyns occurs more readily than to pyrethroids. These results support other studies that have documented spinosyn resistance in field populations and in laboratory selections. Resistance evolution to spinosyns is a particularly important issue, as they represent one of few organic insecticide options for D. suzukii. © 2022 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Evaluating invasion risk and population dynamics of the brown marmorated stink bug across the contiguous United States.

BACKGROUND: Invasive species threaten the productivity and stability of natural and managed ecosystems. Predicting the spread of invaders, which can aid in early mitigation efforts, is a major challenge, especially in the face of climate change. While ecological niche models are effective tools to assess habitat suitability for invaders, such models have rarely been created for invasive pest species with rapidly expanding ranges. Here, we leveraged a national monitoring effort from 543 sites over 3 years to assess factors mediating the occurrence and abundance of brown marmorated stink bug (BMSB, Halyomorpha halys), an invasive insect pest that has readily established throughout much of the United States. RESULTS: We used maximum entropy models to estimate the suitable habitat of BMSB under several climate scenarios, and generalized boosted models to assess environmental factors that regulated BMSB abundance. Our models captured BMSB distribution and abundance with high accuracy, and predicted a 70% increase in suitable habitat under future climate scenarios. However, environmental factors that mediated the geographical distribution of BMSB were different from those driving abundance. While BMSB occurrence was most affected by winter precipitation and proximity to populated areas, BMSB abundance was influenced most strongly by evapotranspiration and solar photoperiod. CONCLUSION: Our results suggest that linking models of establishment (occurrence) and population dynamics (abundance) offers a more effective way to forecast the spread and impact of BMSB and other invasive species than simply occurrence-based models, allowing for targeted mitigation efforts. Implications of distribution shifts under climate change are discussed. © 2022 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Single-neuron bursts encode pathological oscillations in subcortical nuclei of patients with Parkinson's disease and essential tremor.

Deep brain stimulation procedures offer an invaluable opportunity to study disease through intracranial recordings from awake patients. Here, we address the relationship between single-neuron and aggregate-level (local field potential; LFP) activities in the subthalamic nucleus (STN) and thalamic ventral intermediate nucleus (Vim) of patients with Parkinson's disease (n = 19) and essential tremor (n = 16), respectively. Both disorders have been characterized by pathologically elevated LFP oscillations, as well as an increased tendency for neuronal bursting. Our findings suggest that periodic single-neuron bursts encode both pathophysiological beta (13 to 33 Hz; STN) and tremor (4 to 10 Hz; Vim) LFP oscillations, evidenced by strong time-frequency and phase-coupling relationships between the bursting and LFP signals. Spiking activity occurring outside of bursts had no relationship to the LFP. In STN, bursting activity most commonly preceded the LFP oscillation, suggesting that neuronal bursting generated within STN may give rise to an aggregate-level LFP oscillation. In Vim, LFP oscillations most commonly preceded bursting activity, suggesting that neuronal firing may be entrained by periodic afferent inputs. In both STN and Vim, the phase-coupling relationship between LFP and high-frequency oscillation (HFO) signals closely resembled the relationships between the LFP and single-neuron bursting. This suggests that periodic single-neuron bursting is likely representative of a higher spatial and temporal resolution readout of periodic increases in the amplitude of HFOs, which themselves may be a higher resolution readout of aggregate-level LFP oscillations. Overall, our results may reconcile "rate" and "oscillation" models of Parkinson's disease and shed light on the single-neuron basis and origin of pathophysiological oscillations in movement disorders.

Are smartphones and machine learning enough to diagnose tremor?

BACKGROUND: Patients with essential tremor (ET), Parkinson's disease (PD) and dystonic tremor (DT) can be difficult to classify and often share similar characteristics. OBJECTIVES: To use ubiquitous smartphone accelerometers with and without clinical features to automate tremor classification using supervised machine learning, and to use unsupervised learning to evaluate if natural clusterings of patients correspond to assigned clinical diagnoses. METHODS: A supervised machine learning classifier was trained to classify 78 tremor patients using leave-one-out cross-validation to estimate performance on unseen accelerometer data. An independent cohort of 27 patients were also studied. Next, we focused on a subset of 48 patients with both smartphone-based tremor measurements and detailed clinical assessment metrics and compared two separate machine learning classifiers trained on these data. RESULTS: The classifier yielded a total accuracy of 74.4% and F1-score of 0.74 for a trinary classification with an area under the curve of 0.904, average F1-score of 0.94, specificity of 97% and sensitivity of 84% in classifying PD from ET or DT. The algorithm classified ET from non-ET with 88% accuracy, but only classified DT from non-DT with 29% accuracy. A poorer performance was found in the independent cohort. Classifiers trained on accelerometer and clinical data respectively obtained similar results. CONCLUSIONS: Machine learning classifiers achieved a high accuracy of PD, however moderate accuracy of ET, and poor accuracy of DT classification. This underscores the difficulty of using AI to classify some tremors due to lack of specificity in clinical and neuropathological features, reinforcing that they may represent overlapping syndromes.