Assessing REM Sleep Behaviour Disorder: From Machine Learning Classification to the Definition of a Continuous Dissociation Index

Machine Learning Predicts Phenoconversion from Polysomnography in Isolated REM Sleep Behavior Disorder

Isolated rapid eye movement (REM) sleep behavior disorder (iRBD) is a prodromal stage of alpha-synucleinopathies. This study aimed at developing a fully-automated machine learning framework for the prediction of phenoconversion in patients with iRBD by using data recorded during polysomnography (PSG). A total of 66 patients with iRBD were included, of whom 18 converted to an overt alpha-synucleinopathy within 2.7 ± 1.0 years. For each patient, a baseline PSG was available. Sleep stages were scored automatically, and time and frequency domain features were derived from electromyography (EMG) and electroencephalography (EEG) signals in REM and non-REM sleep. Random survival forest was employed to predict the time to phenoconversion, using a four-fold cross-validation scheme and by testing several combinations of features. The best test performances were obtained when considering EEG features in REM sleep only (Harrel's C-index: 0.723 ± 0.113; Uno's C-index: 0.741 ± 0.11; integrated Brier score: 0.174 ± 0.06). Features describing EEG slowing had high importance for the machine learning model. This is the first study employing machine learning applied to PSG to predict phenoconversion in patients with iRBD. If confirmed in larger cohorts, these findings might contribute to improving the design of clinical trials for neuroprotective treatments.

Deep Learning for hand tracking in Parkinson's Disease video-based assessment: Current and future perspectives

BACKGROUND

Parkinson's Disease (PD) demands early diagnosis and frequent assessment of symptoms. In particular, analysing hand movements is pivotal to understand disease progression. Advancements in hand tracking using Deep Learning (DL) allow for the automatic and objective disease evaluation from video recordings of standardised motor tasks, which are the foundation of neurological examinations. In view of this scenario, this narrative review aims to describe the state of the art and the future perspective of DL frameworks for hand tracking in video-based PD assessment.

METHODS

A rigorous search of PubMed, Web of Science, IEEE Explorer, and Scopus until October 2023 using primary keywords such as parkinson, hand tracking, and deep learning was performed to select eligible by focusing on video-based PD assessment through DL-driven hand tracking frameworks RESULTS:: After accurate screening, 23 publications met the selection criteria. These studies used various solutions, from well-established pose estimation frameworks, like OpenPose and MediaPipe, to custom deep architectures designed to accurately track hand and finger movements and extract relevant disease features. Estimated hand tracking data were then used to differentiate PD patients from healthy individuals, characterise symptoms such as tremors and bradykinesia, or regress the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) by automatically assessing clinical tasks such as finger tapping, hand movements, and pronation-supination.

CONCLUSIONS

DL-driven hand tracking holds promise for PD assessment, offering precise, objective measurements for early diagnosis and monitoring, especially in a telemedicine scenario. However, to ensure clinical acceptance, standardisation and validation are crucial. Future research should prioritise large open datasets, rigorous validation on patients, and the investigation of new frontiers such as tracking hand-hand and hand-object interactions for daily-life tasks assessment.

The parasomnia defense in sleep-related homicide: A systematic review and a critical analysis of the medical literature

This review critically analyzes the forensic application of the Parasomnia Defense in homicidal incidents, drawing from medical literature on disorders of arousal (DOA) and rapid-eye-movement sleep behavior disorder (RBD). A systematic search of PubMed, Scopus, Embase, and Cochrane databases was conducted until October 16, 2022. We screened English-language articles in peer-reviewed journals discussing murders committed during sleep with a Parasomnia Defense. We followed PRISMA guidelines, extracting event details, diagnosis methods, factors influencing the acts, perpetrator behavior, timing, motives, concealment, mental experiences, victim demographics, and court verdicts. Three sleep experts evaluated each case. We selected ten homicides, four attempted homicides, and one homicide/attempted homicide that met inclusion/exclusion criteria. Most cases were suspected DOA as unanimously confirmed by experts. RBD cases were absent. Among aggressors, a minority reported dream-like experiences. Victims were primarily female family members killed in or near the bed by hands and/or with sharp objects. Objective sleep data and important crime scene details were often missing. Verdicts were ununiform. Homicides during DOA episodes, though rare, are documented, validating the Parasomnia Defense's use in forensics. RBD-related fatal aggression seems very uncommon. However, cases often lack diagnostic clarity. We propose updated guidelines to enhance future reporting and understanding of such incidents.

Chronotype-Dependent Sleep Loss Is Associated with a Lower Amplitude in Circadian Rhythm and a Higher Fragmentation of REM Sleep in Young Healthy Adults

In modern society, the time and duration of sleep on workdays are primarily determined by external factors, e.g., the alarm clock. This can lead to a misalignment of the intrinsically determined sleep timing, which is dependent on the individual chronotype, resulting in reduced sleep quality. Although this is highly relevant given the high incidence of sleep disorders, little is known about the effect of this misalignment on sleep architecture. Using Fitbit trackers and questionnaire surveys, our study aims to elucidate sleep timing, sleep architecture, and subjective sleep quality in young healthy adults (n = 59) under real-life conditions (average of 82.4 ± 9.7 days). Correlations between variables were calculated to identify the direction of relationships. On workdays, the midpoint of sleep was earlier, the sleep duration was shorter, and tiredness upon waking was higher than on free days. A higher discrepancy between sleep duration on workdays and free days was associated with a lower stability of the circadian rhythm of REM sleep and also with a higher fragmentation of REM sleep. Similarly, a higher tiredness upon waking on free days, thus under intrinsically determined sleep timing conditions, was associated with a lower proportion and a higher fragmentation of REM sleep. This suggests that the misalignment between extrinsically and intrinsically determined sleep timing affects the architecture of sleep stages, particularly REM sleep, which is closely connected to sleep quality.

Quantification of REM sleep without atonia: A review of study methods and meta-analysis of their performance for the diagnosis of RBD

The present review focuses on REM sleep without atonia (RSWA) scoring methods. In consideration of the numerous papers published in the last decade, that used different methods for the quantification of RSWA, their systematic revision is an emerging need. We made a search using the PubMed, Embase, Scopus and Web of Science Databases, from 2010 until December 2021, combining the search term "RSWA" with "scoring methods", "IRBD", "alfasyn disease", and "neurodegenerative disease", and with each of the specific sleep disorders, diagnosed according to current criteria, with the identification of the references of interest for the topic. Furthermore, a Meta-analysis of the diagnostic performance of RSWA scoring methods, in terms of sensitivity and specificity, was carried out. The comparison of the hierarchical summary receiver-operating characteristic curves obtained for visual methods and that obtained for the automated REM sleep atonia index (RAI), shows substantially similar prediction areas indicating a comparable performance. This systematic review and meta-analysis support the validity of a series of visual methods and of the automated RAI in the quantification of RSWA with the purpose to guide clinicians in the interpretation of their results and their correct and efficient use within the diagnostic work-up for REM sleep behavior disorder.

A Machine Learning Approach for Detecting Idiopathic REM Sleep Behavior Disorder

Background and purpose: Growing evidence suggests that Machine Learning (ML) models can assist the diagnosis of neurological disorders. However, little is known about the potential application of ML in diagnosing idiopathic REM sleep behavior disorder (iRBD), a parasomnia characterized by a high risk of phenoconversion to synucleinopathies. This study aimed to develop a model using ML algorithms to identify iRBD patients and test its accuracy. Methods: Data were acquired from 32 participants (20 iRBD patients and 12 controls). All subjects underwent a video-polysomnography. In all subjects, we measured the components of heart rate variability (HRV) during 24 h recordings and calculated night-to-day ratios (cardiac autonomic indices). Discriminating performances of single HRV features were assessed. ML models based on Logistic Regression (LR), Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) were trained on HRV data. The utility of HRV features and ML models for detecting iRBD was evaluated by area under the ROC curve (AUC), sensitivity, specificity and accuracy corresponding to optimal models. Results: Cardiac autonomic indices had low performances (accuracy 63-69%) in distinguishing iRBD from control subjects. By contrast, the RF model performed the best, with excellent accuracy (94%), sensitivity (95%) and specificity (92%), while XGBoost showed accuracy (91%), specificity (83%) and sensitivity (95%). The mean triangular index during wake (TIw) was the best discriminating feature between iRBD and HC, with 81% accuracy, reaching 84% accuracy when combined with VLF power during sleep using an LR model. Conclusions: Our findings demonstrated that ML algorithms can accurately identify iRBD patients. Our model could be used in clinical practice to facilitate the early detection of this form of RBD.