A machine learning contest enhances automated freezing of gait detection and reveals time-of-day effects.

Freezing of gait (FOG) is a debilitating problem that markedly impairs the mobility and independence of 38-65% of people with Parkinson's disease. During a FOG episode, patients report that their feet are suddenly and inexplicably "glued" to the floor. The lack of a widely applicable, objective FOG detection method obstructs research and treatment. To address this problem, we organized a 3-month machine-learning contest, inviting experts from around the world to develop wearable sensor-based FOG detection algorithms. 1,379 teams from 83 countries submitted 24,862 solutions. The winning solutions demonstrated high accuracy, high specificity, and good precision in FOG detection, with strong correlations to gold-standard references. When applied to continuous 24/7 data, the solutions revealed previously unobserved patterns in daily living FOG occurrences. This successful endeavor underscores the potential of machine learning contests to rapidly engage AI experts in addressing critical medical challenges and provides a promising means for objective FOG quantification.

Comment on "Does the 5-2-1 criteria identify patients with advanced Parkinson's disease? Real-world screening accuracy and burden of 5-2-1-positive patients in 7 countries".

The 5-2-1 criteria are intended to help general neurologists identify patients with advanced Parkinson's disease who may benefit from treatment optimisation, such as with a device-aided therapy. Although the 5-2-1 criteria claim to address an unmet need, we urge readers to cautiously interpret the results of this validation study.

CAP2 contributes to Parkinson's disease diagnosed by neutrophil extracellular trap-related immune activity.

Introduction: Neutrophil extracellular traps (NETs) constitute a crucial element of the immune system, and dysfunction in immune responses is implicated in the susceptibility and progression of Parkinson's disease (PD). Nevertheless, the mechanism connecting PD and NETs remains unclear. This study aims to uncover potential NETs-related immune biomarkers and elucidate their role in PD pathogenesis. Methods: Through differential gene analysis of PD and NETs in GSE7621 datasets, we identified two PD subtypes and explored potential biological pathways. Subsequently, using ClusterWGCNA, we pinpointed pertinent genes and developed clinical diagnostic models. We then optimized the chosen model and evaluated its association with immune infiltration. Validation was conducted using the GSE20163 dataset. Screening the single-cell dataset GSE132758 revealed cell populations associated with the identified gene. Results: Our findings identified XGB as the optimal diagnostic model, with CAP2 identified as a pivotal gene. The risk model effectively predicted overall diagnosis rates, demonstrating a robust correlation between infiltrating immune cells and genes related to the XGB model. Discussion: In conclusions, we identified PD subtypes and diagnostic genes associated with NETs, highlighting CAP2 as a pivotal gene. These findings have significant implications for understanding potential molecular mechanisms and treatments for PD.

Identification and validation of N-acetylputrescine in combination with non-canonical clinical features as a Parkinson's disease biomarker panel.

Parkinson's disease is a progressive neurodegenerative disorder in which loss of dopaminergic neurons in the substantia nigra results in a clinically heterogeneous group with variable motor and non-motor symptoms with a degree of misdiagnosis. Only 3-25% of sporadic Parkinson's patients present with genetic abnormalities that could represent a risk factor, thus environmental, metabolic, and other unknown causes contribute to the pathogenesis of Parkinson's disease, which highlights the critical need for biomarkers. In the present study, we prospectively collected and analyzed plasma samples from 194 Parkinson's disease patients and 197 age-matched non-diseased controls. N-acetyl putrescine (NAP) in combination with sense of smell (B-SIT), depression/anxiety (HADS), and acting out dreams (RBD1Q) clinical measurements demonstrated combined diagnostic utility. NAP was increased by 28% in Parkinsons disease patients and exhibited an AUC of 0.72 as well as an OR of 4.79. The clinical and NAP panel demonstrated an area under the curve, AUC = 0.9 and an OR of 20.4. The assessed diagnostic panel demonstrates combinatorial utility in diagnosing Parkinson's disease, allowing for an integrated interpretation of disease pathophysiology and highlighting the use of multi-tiered panels in neurological disease diagnosis.

Associations of sleep disorders with serum neurofilament light chain levels in Parkinson's disease.

BACKGROUND: Sleep disorders are a prevalent non-motor symptom of Parkinson's disease (PD), although reliable biological markers are presently lacking. OBJECTIVES: To explore the associations between sleep disorders and serum neurofilament light chain (NfL) levels in individuals with prodromal and early PD. METHODS: The study contained 1113 participants, including 585 early PD individuals, 353 prodromal PD individuals, and 175 healthy controls (HCs). The correlations between sleep disorders (including rapid eye movement sleep behavior disorder (RBD) and excessive daytime sleepiness (EDS)) and serum NfL levels were researched using multiple linear regression models and linear mixed-effects models. We further investigated the correlations between the rates of changes in daytime sleepiness and serum NfL levels using multiple linear regression models. RESULTS: In baseline analysis, early and prodromal PD individuals who manifested specific behaviors of RBD showed significantly higher levels of serum NfL. Specifically, early PD individuals who experienced nocturnal dream behaviors (ß = 0.033; P = 0.042) and movements of arms or legs during sleep (ß = 0.027; P = 0.049) showed significantly higher serum NfL levels. For prodromal PD individuals, serum NfL levels were significantly higher in individuals suffering from disturbed sleep (ß = 0.038; P = 0.026). Our longitudinal findings support these baseline associations. Serum NfL levels showed an upward trend in early PD individuals who had a higher total RBDSQ score (ß = 0.002; P = 0.011) or who were considered as probable RBD (ß = 0.012; P = 0.009) or who exhibited behaviors on several sub-items of the RBDSQ. In addition, early PD individuals who had a high total ESS score (ß = 0.001; P = 0.012) or who were regarded to have EDS (ß = 0.013; P = 0.007) or who exhibited daytime sleepiness in several conditions had a trend toward higher serum NfL levels. CONCLUSION: Sleep disorders correlate with higher serum NfL, suggesting a link to PD neuronal damage. Early identification of sleep disorders and NfL monitoring are pivotal in detecting at-risk PD patients promptly, allowing for timely intervention. Regular monitoring of NfL levels holds promise for tracking both sleep disorders and disease progression, potentially emerging as a biomarker for evaluating treatment outcomes.

Tau- and α-synuclein-targeted gold nanoparticles: applications, opportunities, and future outlooks in the diagnosis and therapy of neurodegenerative diseases.

The use of nanomaterials in medicine offers multiple opportunities to address neurodegenerative disorders such as Alzheimer's and Parkinson's disease. These diseases are a significant burden for society and the health system, affecting millions of people worldwide without sensitive and selective diagnostic methodologies or effective treatments to stop their progression. In this sense, the use of gold nanoparticles is a promising tool due to their unique properties at the nanometric level. They can be functionalized with specific molecules to selectively target pathological proteins such as Tau and α-synuclein for Alzheimer's and Parkinson's disease, respectively. Additionally, these proteins are used as diagnostic biomarkers, wherein gold nanoparticles play a key role in enhancing their signal, even at the low concentrations present in biological samples such as blood or cerebrospinal fluid, thus enabling an early and accurate diagnosis. On the other hand, gold nanoparticles act as drug delivery platforms, bringing therapeutic agents directly into the brain, improving treatment efficiency and precision, and reducing side effects in healthy tissues. However, despite the exciting potential of gold nanoparticles, it is crucial to address the challenges and issues associated with their use in the medical field before they can be widely applied in clinical settings. It is critical to ensure the safety and biocompatibility of these nanomaterials in the context of the central nervous system. Therefore, rigorous preclinical and clinical studies are needed to assess the efficacy and feasibility of these strategies in patients. Since there is scarce and sometimes contradictory literature about their use in this context, the main aim of this review is to discuss and analyze the current state-of-the-art of gold nanoparticles in relation to delivery, diagnosis, and therapy for Alzheimer's and Parkinson's disease, as well as recent research about their use in preclinical, clinical, and emerging research areas.

Machine learning for the detection and diagnosis of cognitive impairment in Parkinson's Disease: A systematic review.

BACKGROUND: Parkinson's Disease is the second most common neurological disease in over 60s. Cognitive impairment is a major clinical symptom, with risk of severe dysfunction up to 20 years post-diagnosis. Processes for detection and diagnosis of cognitive impairments are not sufficient to predict decline at an early stage for significant impact. Ageing populations, neurologist shortages and subjective interpretations reduce the effectiveness of decisions and diagnoses. Researchers are now utilising machine learning for detection and diagnosis of cognitive impairment based on symptom presentation and clinical investigation. This work aims to provide an overview of published studies applying machine learning to detecting and diagnosing cognitive impairment, evaluate the feasibility of implemented methods, their impacts, and provide suitable recommendations for methods, modalities and outcomes. METHODS: To provide an overview of the machine learning techniques, data sources and modalities used for detection and diagnosis of cognitive impairment in Parkinson's Disease, we conducted a review of studies published on the PubMed, IEEE Xplore, Scopus and ScienceDirect databases. 70 studies were included in this review, with the most relevant information extracted from each. From each study, strategy, modalities, sources, methods and outcomes were extracted. RESULTS: Literatures demonstrate that machine learning techniques have potential to provide considerable insight into investigation of cognitive impairment in Parkinson's Disease. Our review demonstrates the versatility of machine learning in analysing a wide range of different modalities for the detection and diagnosis of cognitive impairment in Parkinson's Disease, including imaging, EEG, speech and more, yielding notable diagnostic accuracy. CONCLUSIONS: Machine learning based interventions have the potential to glean meaningful insight from data, and may offer non-invasive means of enhancing cognitive impairment assessment, providing clear and formidable potential for implementation of machine learning into clinical practice.

Ligand Profiling as a Diagnostic Tool to Differentiate Patient-Derived α-Synuclein Polymorphs.

Amyloid fibrils are characteristic of many neurodegenerative diseases, including Alzheimer's and Parkinson's diseases. While different diseases may have fibrils formed of the same protein, the supramolecular morphology of these fibrils is disease-specific. Here, a method is reported to distinguish eight morphologically distinct amyloid fibrils based on differences in ligand binding properties. Eight fibrillar polymorphs of α-synuclein (αSyn) were investigated: five generated de novo using recombinant αSyn and three generated using protein misfolding cyclic amplification (PMCA) of recombinant αSyn seeded with brain homogenates from deceased patients diagnosed with Parkinson's disease (PD), multiple system atrophy (MSA), and dementia with Lewy bodies (DLB). Fluorescence binding assays were carried out for each fibril using a toolkit of six different ligands. The fibril samples were separated into five categories based on a binary classification of whether they bound specific ligands or not. Quantitative binding measurements then allowed every fibrillar polymorph to be uniquely identified, and the PMCA fibrils derived from PD, MSA, and DLB patients could be unambiguously distinguished. This approach constitutes a novel and operationally simple method to differentiate amyloid fibril morphologies and to identify disease states using PMCA fibrils obtained by seeding with patient samples.

Molecular beacon-based detection of circulating microRNA-containing extracellular vesicle as an α-synucleinopathy biomarker.

Early and precise diagnosis of α-synucleinopathies is challenging but critical. In this study, we developed a molecular beacon-based assay to evaluate microRNA-containing extracellular vesicles (EVs) in plasma. We recruited 1203 participants including healthy controls (HCs) and patients with isolated REM sleep behavior disorder (iRBD), α-synucleinopathies, or non-α-synucleinopathies from eight centers across China. Plasma miR-44438-containing EV levels were significantly increased in α-synucleinopathies, including those in the prodromal stage (e.g., iRBD), compared to both non-α-synucleinopathy patients and HCs. However, there are no significant differences between Parkinson's disease (PD) and multiple system atrophy. The miR-44438-containing EV levels negatively correlated with age and the Hoehn and Yahr stage of PD patients, suggesting a potential association with disease progression. Furthermore, a longitudinal analysis over 16.3 months demonstrated a significant decline in miR-44438-containing EV levels in patients with PD. These results highlight the potential of plasma miR-44438-containing EV as a biomarker for early detection and progress monitoring of α-synucleinopathies.

Harnessing Graphdiyne for Selective Cu2+ Detection: A Promising Tool for Parkinson's Disease Diagnostics and Pathogenesis.

Cu2+ accelerates the viral-like propagation of α-synuclein fibrils and plays a key role in the pathogenesis of Parkinson's disease (PD). Therefore, the accurate detection of Cu2+ is essential for the diagnosis of PD and other neurological diseases. The Cu2+ detection process is impeded by substances that have similar electrochemical properties. In this study, graphdiyne (GDY), a new kind of carbon allotrope with strong electron-donating ability, was utilized for the highly selective detection of Cu2+ by taking advantage of its outstanding adsorption capacity for Cu2+. Density functional theory (DFT) calculations show that Cu atoms are adsorbed in the cavity of GDY, and the absorption energy between Cu and C atoms is higher than that of graphene (GR), indicating that the cavity of GDY is favorable for the adsorption of Cu atoms and electrochemical sensing. The GDY-based electrochemical sensor can effectively avoid the interference of amino acids, metal ions and neurotransmitters and has a high sensitivity of 9.77 µA·µM-1·cm-2, with a minimum detectable concentration of 200 nM. During the investigating pathogenesis and therapeutic process of PD with α-synuclein as the diagnostic standard, the concentration of Cu2+ in cells before and after L-DOPA and GSH treatments were examined, and it was found that Cu2+ exhibits high potential as a biomarker for PD. This study not only harnesses the favorable adsorption of the GDY and Cu2+ to improve the specificity of ion detection but also provide clues for deeper understanding of the role of Cu2+ in neurobiology and neurological diseases.

Parkinson's disease with anxiety: clinical characteristics and their correlation with oxidative stress, inflammation, and pathological proteins.

OBJECTIVE: This study was performed to explore the differences in the clinical characteristics and oxidative stress indicators, inflammatory factors, and pathological proteins in serum between Parkinson's disease (PD) with anxiety (PD-A) and with no anxiety (PD-NA) patients, and further correlations among clinical characteristics and above variables were analyzed in PD-A and PD-NA groups. METHODS: A total of 121 patients with PD were enrolled in this study and assessed by the Hamilton Anxiety Scale (14 items) (HAMA-14). These patients were divided into PD-A and PD-NA groups according to a cut-off point of 7 of HAMA-14. Demographic variables were collected, and clinical symptoms were assessed by multiple rating scales. The levels of free radicals, inflammatory factors, and pathological proteins in serum were measured by chemical colorimetric method and enzyme-linked immunosorbent assay (ELISA). The differences of above variables were compared between PD-A and PD-NA groups, and the correlations of clinical symptoms with the abovevariables were analyzed in PD-A and PD-NA groups. RESULTS: The frequency of PD-A was 62.81%. PD-A group exhibited significantly impaired motor dysfunction and multiple non-motor symptoms, including fatigue, sleep behavior disorder, restless leg syndrome and autonomic dysfunction, and dramatically compromised activities of daily living compard with PD-NA group. PD-A group displayed prominently increasedlevels of hydroxyl radical (·OH) and tumor necrosis factor (TNF)-α, and a decreased nitric oxide (NO) level in serum compared with PD-NA group (P<0.001, P = 0.001, P= 0.027, respectively). ·OH, NO, and TNF-α were identified as the risk factors of PD-A (OR = 1.005, P = 0.036; OR = 0.956, P = 0.017; OR = 1.039, P = 0.033, respectively). In PD patients, HAMA-14 score was significantly and positively correlated with the levels of ·OH and TNF-α in serum (P<0.001, P = 0.002, respectively). In PD-A group, ·OH level was significantly and negatively correlated with Aß1-42 level, while TNF-α level was significantly and positively correlated with P-tau (S396) level in serum. CONCLUSIONS: The frequency of PD-A is high. PD-A patients present more severe motor dysfunction and multiple non-motor symptoms, and poorer activities of daily living. The increased levels of ·OH and TNF-α levels and the decreased NO level in serum are all associated with more severe anxiety in PD patients.Findings from this study may provide in-depth insights into the clinical characteristics, underlying mechanisms of PD-A, and potential correlations among anxiety, oxidative stress, inflammation, and cognitive decline in PD patients.

Distinct retinal reflectance spectra from retinal hyperspectral imaging in Parkinson's disease.

BACKGROUND: Recent developments in the retinal hyperspectral imaging method have indicated its potential in addressing challenges posed by neurodegenerative disorders, such as Alzheimer's disease. This human clinical study is the first to assess reflectance spectra obtained from this imaging as a tool for diagnosing patients with Parkinson's disease (PD). METHODS: Retinal hyperspectral imaging was conducted on a total of 40 participants, including 20 patients with PD and 20 controls. Following preprocessing, retinal reflectance spectra were computed for the macular retina defined by four rectangular regions. Linear discriminant analysis classifiers underwent training to discern patients with PD from control participants. To assess the performance of the selected features, nested leave-one-out cross-validation was employed using machine learning. The indicated values include the area under the curve (AUC) and the corresponding 95% confidence interval (CI). RESULTS: Retinal reflectance spectra of PD patients exhibited variations in the spectral regions, particularly at shorter wavelengths (superonasal retina, wavelength < 490 nm; inferonasal retina, wavelength < 510 nm) when compared to those of controls. Retinal reflectance spectra yielded an AUC of 0.60 (95% CI: 0.43-0.78) and 0.60 (95% CI: 0.43-0.78) for the superonasal and inferonasal retina, respectively, distinguishing individuals with and without PD. CONCLUSION: Reflectance spectra obtained from retinal hyperspectral imaging tended to decrease at shorter wavelengths across a broad spectral range in PD patients. Further investigations building upon these preliminary findings are imperative to focus on the retinal spectral signatures associated with PD pathological hallmarks, including α-synuclein.

Parkinson's Kinetigraph for Wearable Sensor Detection of Clinically Unrecognized Early-Morning Akinesia in Parkinson's Disease: A Case Report-Based Observation.

Early-morning off periods, causing early-morning akinesia, can lead to significant motor and nonmotor morbidity in levodopa-treated fluctuating Parkinson's disease (PD) cases. Despite validated bedside scales in clinical practice, such early-morning off periods may remain undetected unless specific wearable technologies, such as the Parkinson's KinetiGraph™ (PKG) watch, are used. We report five PD cases for whom the PKG detected early-morning off periods that were initially clinically undetected and as such, untreated. These five cases serve as exemplars of this clinical gap in care. Post-PKG assessment, clinicians were alerted and targeted therapies helped abolish the early-morning off periods.

ATST-Net: A method to identify early symptoms in the upper and lower extremities of PD.

Bradykinesia, a core symptom of motor disorders in Parkinson's disease (PD), is a major criterion for screening early PD patients in clinical practice. Currently, many studies have proposed automatic assessment schemes for bradykinesia in PD. However, existing schemes suffer from problems such as dependence on professional equipment, single evaluation tasks, difficulty in obtaining samples and low accuracy. This paper proposes a manual feature extraction- and neural network-based method to evaluate bradykinesia, effectively solving the problem of a small sample size. This method can automatically assess finger tapping (FT), hand movement (HM), toe tapping (TT) and bilateral foot sensitivity tasks (LA) through a unified model. Data were obtained from 120 individuals, including 93 patients with Parkinson's disease and 27 age- and sex-matched normal controls (NCs). Manual feature extraction and Attention Time Series Two-stream Networks (ATST-Net) were used for classification. Accuracy rates of 0.844, 0.819, 0.728, and 0.768 were achieved for FT, HM, TT, and LA, respectively. To our knowledge, this study is the first to simultaneously evaluate the upper and lower limbs using a unified model that has significant advantages in both model training and transfer learning.

Photodynamic-Assisted Electrochemiluminescence Enhancement toward Advanced BODIPY for Precision Diagnosis of Parkinson.

Nowadays, signal enhancement is imperative to increase sensitivity of advanced ECL devices for expediting their promising applications in clinic. In this work, photodynamic-assisted electrochemiluminescence (PDECL) device was constructed for precision diagnosis of Parkinson, where an advanced emitter was prepared by electrostatically linking 2,6-dimethyl-8-(3-carboxyphenyl)4,4'-difluoroboradiazene (BET) with 1-butyl-3-methylimidazole tetrafluoroborate ([BMIm][BF4]). Specifically, protoporphyrin IX (PPIX) can trigger the photodynamic reaction under light irradiation with a wavelength of 450 nm to generate lots of singlet oxygen (1O2), showing a 2.43-fold magnification in the ECL responses. Then, the aptamer (Apt) was assembled on the functional BET-[BMIm] for constructing a "signal off" ECL biosensor. Later on, the PPIX was embedded into the G-quadruplex (G4) of the Apt to magnify the ECL signals for bioanalysis of α-synuclein (α-syn) under light excitation. In the optimized surroundings, the resulting PDECL sensor has a broad linear range of 100.0 aM ∼ 10.0 fM and a low limit of detection (LOD) of 63 aM, coupled by differentiating Parkinson patients from normal individuals according to the receiver operating characteristic (ROC) curve analysis of actual blood samples. Such research holds great promise for synthesis of other advanced luminophores, combined with achieving an early clinical diagnosis.

Identification of Prodromal Parkinson Disease: We May Be Able to But Should We?

Parkinson disease (PD) remains a progressive and incurable disease. Research over the past decade provides strong evidence of a detectible phase before the clinical diagnosis, known as the prodromal phase of PD (pPD). In this article, we review the debate about disclosure of risk of progression to PD and related disorders to individuals through the perspectives of the pillars of medical ethics: beneficence, nonmaleficence, autonomy, and justice. There is evidence that lifestyle modification may have positive effects on onset and progression of PD, providing justification of potential benefit. From a societal perspective, a diagnosis of pPD could allow targeted recruitment to disease-modifying trials. Regarding nonmaleficence, direct evidence that catastrophic reactions are scarce is largely derived from studies of monogenic conditions, which may not be generalizable. Diagnosis of PD can be traumatic, and appropriate communication and evaluation of circumstances to weigh up disclosure is crucial. Future research should therefore examine the potential harms of early and of false-positive diagnoses and specifically examine these matters in diverse populations. Autonomy balances the right to know and the right not to know, so an individualized patient-centered approach and shared decision-making is essential, acknowledging that knowledge of being in the prodromal phase could prolong autonomy in the longer term. Distributive justice brings focus toward health care and related planning at the individual and societal level and affects the search for disease modification in PD. We must acknowledge that waiting for established disease states is likely to be too little, too late and results in failures of expensive trials and wasted participant and researcher effort. Ultimately, clinicians must arrive at a decision with the patient that solicits and integrates patients' goals, taking into account their individual life circumstances, perspectives, and philosophies, recognizing that one size cannot fit all.

Enhancing recruitment of individuals living with frailty, multimorbidity and cognitive impairment to Parkinson's research: experiences from the PRIME-UK cross-sectional study.

BACKGROUND AND OBJECTIVES: People with parkinsonism who are older, living in a care home, with frailty, multimorbidity or impaired capacity to consent are under-represented in research, limiting its generalisability. We aimed to evaluate more inclusive recruitment strategies. METHODS: From one UK centre, we invited people with parkinsonism to participate in a cross-sectional study. Postal invitations were followed by telephone reminders and additional support to facilitate participation. Personal consultees provided information on the views regarding research participation of adults with impaired capacity. These approaches were evaluated: (i) using external data from the Parkinson's Real World Impact assesSMent (PRISM) study and Clinical Practice Research Datalink (CPRD), a sample of all cases in UK primary care, and (ii) comparing those recruited with or without intensive engagement. RESULTS: We approached 1,032 eligible patients, of whom 542 (53%) consented and 477 (46%) returned questionnaires. The gender ratio in PRIME-UK (65% male) closely matched CPRD (61% male), unlike in the PRISM sample (46%). Mean age of PRIME participants was 75.9 (SD 8.5) years, compared to 75.3 (9.5) and 65.4 (8.9) years for CPRD and PRISM, respectively. More intensive engagement enhanced recruitment of women (13.3%; 95% CI 3.8, 22.9%; P = 0.005), care home residents (6.2%; 1.1, 11.2%; P = 0.004), patients diagnosed with atypical parkinsonism (13.7%; 5.4, 19.9%; P < 0.001), and those with a higher frailty score (mean score 0.2, 0.1, 0.2; P < 0.001). CONCLUSIONS: These recruitment strategies resulted in a less biased and more representative sample, with greater inclusion of older people with more complex parkinsonism.