Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Deep Neural Network”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4Linked to original sources
PubMed2026

Systematic evaluation of one-dimensional-to-two-dimensional near-infrared spectroscopy transformations with deep learning for quantifying coconut sap adulteration.

Near-infrared (NIR) spectroscopy have limitations when combined with deep learning (DL) algorithms because they rely on low-dimensional datasets. Therefore, we investigated the potential of transforming one-dimensional (1D) NIR spectra into two-dimensional (2D) spectrograms using synchronous and asynchronous techniques and the continuous wavelet transform (CWT) and their effectiveness by integrating with DL for detecting adulteration in coconut sap. NIR spectra (12,500-4000 cm-1) were collected from binary mixtures (0%-100%;w/w). The performance of all DL (convolutional neural networks-CNN, AlexNet and ResNet) models was compared with that of partial least squares (PLS). The models were ranked in the mentioned order based on their performances: 2D-CWT > 2D-asynchronous > 2D-synchronous > 1D/2D-PLS. The important features of the best model can be explained and visualized using gradient-weighted-class-activation-mapping. The findings highlight that the 1D-to-2D NIR data transformation combined with DL is a highly robust approach because it addresses the feature representation gap in NIR data and effectively captures the spatial-spectral correlations.

Spectroscopy, Near-Infrared↗
PubMed2025

Phylogenetic Methods Meet Deep Learning.

Deep learning (DL) has been widely used in various scientific fields, but its integration into phylogenetics has been slower, primarily due to the complex nature of phylogenetic data. The studies that apply DL to sequencing data often limit analyses to four-taxon trees. Many of these studies serve as "proof of principle" and perform similarly to traditional phylogeny reconstruction methods. New ways of using training data, such as encoding with compact bijective ladderized vectors or transformers, enable the handling of much larger trees and genomic data sets. This short perspective focuses on the application of DL in phylogenetics, introducing prevalent DL architectures. We highlight potential problems in the field by discussing the risks of using simulation-based training data and emphasize the importance of reproducibility and robustness in computational estimates. Finally, we explore promising research areas, including the combination of phylogenetics and population genetics in DL, the analysis of neighbor dependencies, and the potential to significantly reduce computational cost compared to traditional methods. This perspective illustrates the potential of DL in complementing traditional phylogeny reconstruction methods and aiding the advancement of phylogenetic analysis, especially in performing computationally demanding tasks such as model selection or estimating branch support values.

Humans↗
PubMed1997

[Intraoperative EEG monitoring using a neural network].

OBJECTIVE: To introduce a new EEG parameter for monitoring a patient's cerebral status during anaesthesia. METHOD: EEG epochs (channel C3 P3, duration 30 see per epoch) yield patterns used as the training input of a self-organising neural network (neural gas algorithm). Each pattern contains spectral components. An additional "suppression parameter" reflects the proportion of flat curves during an EEG epoch and reduces the shortcomings of spectral analysis. The enhanced pattern vector enables the recognition of burst-suppression periods representing depressed cerebral activity during anaesthesia. Following training with 25549 EEG epochs ¿recorded in 196 consenting patients in the period beginning 5 minutes before induction of anaesthesia to extubation¿ the network knows 125 basic patterns (neural clusters). The neural clusters are responsible for different stages of anaesthesia: some neurons are activated by EEG epochs of awake patients, others are stimulated by deep stages. The homogeneity of the EEG epochs of cluster is checked. The portion of the EEG epochs not recognised by the network (7.5%) contains heterogeneous and sporadic patterns (mainly outlines caused by artefacts). RESULTS: In comparison with commonly used variables of anaesthesiological EEG monitoring (spectral edge or median frequency) neural discriminant analysis achieves better discrimination between awake and deeply anaesthetised stages (reclassification of 96% vs. 70%). On the basis of 56 complete sequences of patterns (from the beginning of the infusion of anaesthetics to the occurrence of burst suppression) a trend value of between 0.0 and 100.0 is assigned to each neural cluster. In contrast to existing methods, induction of anaesthesia causes a strictly linear increase in the electroencephalographic trend. CONCLUSIONS: Detailed neural cluster and discriminant analysis on the basis of the model described leads to an improved EEG parameter which better reflects the hypnotic effects of anaesthetic agents and arousal reactions caused by pain stimuli. Misclassifications of awake and anaesthetised stages are reduced. The neural network learns to recognize the complex changes in EEG patterns during induction of anaesthesia with different agents.

Adult↗
PubMed2024

NovoBoard: A Comprehensive Framework for Evaluating the False Discovery Rate and Accuracy of De Novo Peptide Sequencing.

De novo peptide sequencing is one of the most fundamental research areas in mass spectrometry-based proteomics. Many methods have often been evaluated using a couple of simple metrics that do not fully reflect their overall performance. Moreover, there has not been an established method to estimate the false discovery rate (FDR) of de novo peptide-spectrum matches. Here we propose NovoBoard, a comprehensive framework to evaluate the performance of de novo peptide-sequencing methods. The framework consists of diverse benchmark datasets (including tryptic, nontryptic, immunopeptidomics, and different species) and a standard set of accuracy metrics to evaluate the fragment ions, amino acids, and peptides of the de novo results. More importantly, a new approach is designed to evaluate de novo peptide-sequencing methods on target-decoy spectra and to estimate and validate their FDRs. Our FDR estimation provides valuable information to assess the reliability of new peptides identified by de novo sequencing tools, especially when no ground-truth information is available to evaluate their accuracy. The FDR estimation can also be used to evaluate the capability of de novo peptide sequencing tools to distinguish between de novo peptide-spectrum matches and random matches. Our results thoroughly reveal the strengths and weaknesses of different de novo peptide-sequencing methods and how their performances depend on specific applications and the types of data.

Peptides↗
PubMed1996

Effects of cerebellar lesions on saccade simulations.

Experimental studies involving cerebellar lesions have been important tools for learning about the operation of the saccadic eye movement system. These studies have been used to further develop a neural network model for horizontal saccadic eye movement control. The neural control mechanism is first order time optimal, initiated by the deep layers of the superior colliculus and terminated by the cerebellar fastigial nucleus. The neural circuit consists of neurons in the paramedian pontine reticular formation (burst, tonic and pause cells), the vestibular nucleus, abducens nucleus, oculomotor nucleus, cerebellum, substantia nigra, nucleus reticularis tegmenti pontis, the thalamus, the deep layers of the superior colliculus and the oculomotor plant for each eye. Agonist burst cell activity is initiated with maximal firing due to an error between the target and eye position, and continues until the internal eye position in the cerebellar vermis reaches the desired position, then decays to zero. The cerebellar vermis is responsible for adapting the duration of maximal firing based on the initial position of the eye. There are two sets of neural integrators in the neural network. One operates within the cerebellar vermis to predict the width of the pulse, and the other within the paramedian pontine reticular formation to maintain the eyes at their destination. Antagonist neural activity is inhibited during the agonist burst activity. After the agonist burst, antagonist neural activity rises with a stochastic rebound burst and from input from the fastigial nucleus, then falls to a tonic firing level necessary to keep the eye at its destination. The onset of the antagonist tonic firing is stochastic, weakly coordinated with the end of the agonist burst, and under cerebellar control. A common mechanism of action is described, based on cerebellar gating, through the fastigial nucleus, that explains a number of different saccadic eye movement types, including dynamic overshoot, glissadic overshoot and undershoot, and undershoot. A linear homeomorphic oculomotor muscle model is used in the simulations of the operation of the neural network. Each of the neural sites in the model fire similar to experimental data, and simulate fast eye movements.

Cerebellum↗
PubMed2004

Markovian architectural bias of recurrent neural networks.

In this paper, we elaborate upon the claim that clustering in the recurrent layer of recurrent neural networks (RNNs) reflects meaningful information processing states even prior to training [1], [2]. By concentrating on activation clusters in RNNs, while not throwing away the continuous state space network dynamics, we extract predictive models that we call neural prediction machines (NPMs). When RNNs with sigmoid activation functions are initialized with small weights (a common technique in the RNN community), the clusters of recurrent activations emerging prior to training are indeed meaningful and correspond to Markov prediction contexts. In this case, the extracted NPMs correspond to a class of Markov models, called variable memory length Markov models (VLMMs). In order to appreciate how much information has really been induced during the training, the RNN performance should always be compared with that of VLMMs and NPMs extracted before training as the "null" base models. Our arguments are supported by experiments on a chaotic symbolic sequence and a context-free language with a deep recursive structure. Index Terms-Complex symbolic sequences, information latching problem, iterative function systems, Markov models, recurrent neural networks (RNNs).

Markov Chains↗
PubMed2026

High-accuracy SNV calling for bacterial isolates using deep learning with AccuSNV.

Accurate detection of mutations within bacterial species is critical for fundamental studies of microbial evolution, reconstruction of transmission events, and identification of antimicrobial resistance mutations. Although many tools have been developed to identify single-nucleotide variants (SNVs) from whole-genome sequencing, they often suffer from high false-positive rates owing to the complexity of bacterial genomes and the need for different filtering cutoffs across sample types and sequencing depths. As data sets increase in size, the manual filtering required for high accuracy presents a significant obstacle. Here, we present AccuSNV, a novel deep learning-based tool for high-precision and automated bacterial SNV calling. Unlike traditional methods that process one sample at a time, AccuSNV leverages a convolutional neural network (CNN) that integrates alignment information across multiple samples, enhancing precision through learned across-sample patterns. We evaluate AccuSNV against seven popular SNV-calling tools using simulated data from six bacterial species with varied sequencing depths, numbers of isolates, mutations, and divergence levels. To further validate its real-world utility, we test AccuSNV on multiple curated bacterial data sets containing reported SNVs. In both simulated and real-world scenarios, AccuSNV consistently achieves the best performance. Moreover, AccuSNV provides comprehensive user-friendly downstream analysis modules and outputs, including mutation annotation information, phylogenetic inference, d N/d S calculations, and optional manual filtering. Together with the automated deep learning-based calling, these features make AccuSNV broadly accessible to users with different levels of computational expertise.

Deep Learning↗
PubMed2005

Neuroanatomical approaches of the tectum-reticular pathways and immunohistochemical evidence for serotonin-positive perikarya on neuronal substrates of the superior colliculus and periaqueductal gray matter involved in the elaboration of the defensive behavior and fear-induced analgesia.

Deep layers of the superior colliculus, the dorsal periaqueductal gray matter and the inferior colliculus are midbrain structures involved in the generation of defensive behavior and fear-induced anti-nociception. Local injections of the GABA(A) antagonist bicuculline into these structures have been used to produce this defense reaction. Serotonin is thought to be the main neurotransmitter to modulate such defense reaction in mammals. This study is the first attempt to employ immunohistochemical techniques to locate serotonergic cells in the same midbrain sites from where defense reaction is evoked by chemical stimulation with bicuculline. The blockade of GABA(A) receptors in the neural substrates of the dorsal mesencephalon was followed by vigorous defensive reactions and increased nociceptive thresholds. Light microscopy immunocytochemistry with streptavidin method was used for the localization of the putative cells of defensive behavior with antibodies to serotonin in the rat's midbrain. Neurons positive to serotonin were found in the midbrain sites where defensive reactions were evoked by microinjection of bicuculline. Serotonin was localized to somata and projections of the neural networks of the mesencephalic tectum. Immunohistochemical studies showed that the sites in which neuronal perikarya positive to serotonin were identified in intermediate and deep layers of the superior colliculus, and in the dorsal and ventral columns of the periaqueductal gray matter are the same which were activated during the generation of defense behaviors, such as alertness, freezing, and escape reactions, induced by bicuculline. These findings support the contention that serotonin and GABAergic neurons may act in concert in the modulation of defense reaction in the midbrain tectum. Our neuroanatomical findings indicate a direct neural pathway connecting the dorsal midbrain and monoaminergic nuclei of the descending pain inhibitory system, with profuse synaptic terminals mainly in the pontine reticular formation, gigantocellularis nucleus, and nucleus raphe magnus. The midbrain tectum-gigantocellularis complex and midbrain tectum-nucleus raphe magnus neural pathways may provide an alternative output allowing the organization of the fear-induced anti-nociception by mesencephalic networks.

Aggression↗
PubMed2003

Organization of neural networks in the neocortex.

Implanted semimicroelectrodes were used in conscious cats to record spike discharges from groups of close-lying neurons, i.e., multineuron activity, in the deep layers of the frontal and motor areas of the cortex at different levels of food motivation. Spike activity was extracted from 4-7 neurons and interneuronal interactions were studied by cross-correlation analysis between neighboring neurons in each zone (local networks) and between neurons in two zones (distributed networks) with analysis epochs of 0-100 msec. The results showed that neurons in local networks can be divided into two subgroups: neurons with high-amplitude spikes and a predominance of output (divergent) connections and neurons with low-amplitude spikes and a predominance of input (convergent) connections. Local networks are based on powerful monosynaptic connections (with delays of up to 2 msec) between large and small neurons. Most connections in distributed networks were between small neurons in local networks of the frontal cortex and large neurons in local networks in the motor cortex. Food deprivation for 24 h mainly affected late (with delays of 2-100 msec) cross-correlation interneuronal relationships in both local and distributed networks.

Animals↗
PubMed2006

A hybrid neural learning algorithm using evolutionary learning and derivative free local search method.

In this paper we investigate a hybrid model based on the Discrete Gradient method and an evolutionary strategy for determining the weights in a feed forward artificial neural network. Also we discuss different variants for hybrid models using the Discrete Gradient method and an evolutionary strategy for determining the weights in a feed forward artificial neural network. The Discrete Gradient method has the advantage of being able to jump over many local minima and find very deep local minima. However, earlier research has shown that a good starting point for the discrete gradient method can improve the quality of the solution point. Evolutionary algorithms are best suited for global optimisation problems. Nevertheless they are cursed with longer training times and often unsuitable for real world application. For optimisation problems such as weight optimisation for ANNs in real world applications the dimensions are large and time complexity is critical. Hence the idea of a hybrid model can be a suitable option. In this paper we propose different fusion strategies for hybrid models combining the evolutionary strategy with the discrete gradient method to obtain an optimal solution much quicker. Three different fusion strategies are discussed: a linear hybrid model, an iterative hybrid model and a restricted local search hybrid model. Comparative results on a range of standard datasets are provided for different fusion hybrid models.

Algorithms↗
PubMed2005

High-frequency stimulation in Parkinson's disease: more or less?

Deep-brain stimulation at high frequency is now considered the most effective neurosurgical therapy for movement disorders. An electrode is chronically implanted in a particular area of the brain and, when continuously stimulated, it significantly alleviates motor symptoms. In Parkinson's disease, common target nuclei of high-frequency stimulation (HFS) are ventral thalamic nuclei and basal ganglia nuclei, such as the internal segment of the pallidum and the subthalamic nucleus (STN), with a preference for the STN in recent years. Two fundamental mechanisms have been proposed to underlie the beneficial effects of HFS: silencing or excitation of STN neurons. Relying on recent experimental data, we suggest that both are instrumental: HFS switches off a pathological disrupted activity in the STN (a 'less' mechanism) and imposes a new type of discharge in the upper gamma-band frequency that is endowed with beneficial effects (a 'more' mechanism). The intrinsic capacity of basal ganglia and particular STN neurons to generate oscillations and shift rapidly from a physiological to a pathogenic pattern is pivotal in the operation of these circuits in health and disease.

Animals↗
PubMed2026

The Use of Deep Learning in RNA Therapeutic Development.

Ribonucleic acid (RNA)-based therapeutics have emerged as promising methods of disease treatment due to their ability to target the human genome and influence protein production, their versatility, and their relative lack of toxicity compared to other gene therapies. However, the RNA therapeutic design space is extremely large, encompassing multiple variables, including codon identities, secondary structure, and design of specific regions. RNA therapeutic optimization is difficult due to the impracticality of exploring such a vast design space experimentally. To address this limitation, deep learning methods have been employed to optimize RNA therapeutic development. In this review, we examine the application of deep learning models across three key aspects of RNA therapeutic development (RNA structure prediction, CRISPR activity, and RNA delivery), highlighting major contributions in these fields and analyzing how deep learning model architectures could affect model performance. We then discuss challenges associated with using deep learning for RNA therapeutics, such as computational and data limitations. Finally, we offer perspectives on areas for future exploration, such as emerging model architectures and methods of integration with more advanced high-throughput screening techniques. Ultimately, this review provides an overview of how deep learning is used in RNA therapeutic development and how it can evolve in the future.

Deep Learning↗
PubMedDate not supplied

Functional organization of local neural networks in the cat neocortex. Relationship to the level of food motivation.

Implanted semimicroelectrodes were used to record multineuron activity--spike discharges from groups of close-lying neurons--in the deep layers of the frontal and motor cortex in conscious cats with different levels of food motivation. Spike activity from 4-7 neurons was extracted from multineuron activity, and interneuron interactions were studied by cross-correlation analysis. Neurons in local networks were divided into two subgroups: neurons with high-amplitude spikes with a predominance of output (divergent) connections, and neurons with low-amplitude spikes and a predominance of input (convergent) connections. Food deprivation lasting 24 h affected mainly the nature of interneuron interactions in the range of late cross-correlational connections (with delays of 2-100 msec).

Animals↗
PubMed2026

Artificial intelligence (AI) uses in stereotactic radiosurgery (SRS): diagnosis with brain metastasis (BM) - A systematic review.

BACKGROUND: Brain metastases (BM) are the most common intracranial tumors in adults, and stereotactic radiosurgery (SRS) has become a mainstay of management. However, several diagnostic challenges persist in the SRS pathway, particularly the differentiation of radiation necrosis (RN) from true tumor progression, which conventional MRI and even advanced imaging techniques often cannot reliably resolve. Recent advances in artificial intelligence (AI) offer the potential to address these diagnostic limitations. This systematic review synthesizes current literature on AI applications for MRI-based diagnostic decision support in BM patients undergoing SRS, with a focus on radiomics and deep learning tools for distinguishing RN from progression, classifying molecular and histologic subtypes, and predicting treatment response. METHODS: A systematic review was performed in accordance with PRISMA guidelines. PubMed, Web of Science, and Scopus were searched using a targeted query combining terms related to AI, brain metastasis, diagnosis or imaging, and SRS. After screening 483 records and applying strict inclusion and exclusion criteria, 18 studies published between 2015 and 2025 were included. Data were extracted on study design, cohort characteristics, imaging modality, AI methodology, validation strategy, and reported diagnostic performance. RESULTS: Among the 18 included studies, AI models demonstrated strong performance across diagnostic tasks in the BM-SRS pathway. The differentiation of RN from true tumor progression was the most extensively studied application, addressed by 14 of 18 studies, with reported AUCs ranging from 0.71 to 0.94. Support vector machines, random-forest ensembles, convolutional neural networks, and transformer-based multimodal architectures were widely used. The literature evolved from single-sequence radiomic classifiers in 2018 to multimodal deep learning frameworks fusing imaging with clinical and genomic data in 2025. Contrast-enhanced T1-weighted MRI was the dominant imaging input, and texture-based radiomic features (GLCM, GLSZM, GLDM, and wavelet-derived features) were the most consistently predictive. The highest-performing models reached AUCs of 0.85-0.91 through multimodal integration of imaging with clinical and genomic features, and consistently outperformed expert neuroradiologist read on matched cases. Remaining studies addressed longitudinal segmentation-based detection of local failure and adverse radiation effects, BRAF mutation status in melanoma BM, early Gamma Knife treatment response, and primary tumor histology classification, with more variable performance. CONCLUSION: AI models, particularly those integrating MRI-derived radiomic features with clinical and genomic data, show high accuracy in supporting diagnostic decisions for BM patients treated with SRS. The post-SRS differentiation of radiation necrosis from true tumor progression has reached the greatest level of maturity and is closest to clinical translation, with potential to reduce unnecessary biopsies, personalize surveillance intervals, and rationalize treatment-pathway decisions. Other diagnostic applications, including molecular subtyping and primary tumor histology classification, remain exploratory and require further multicenter validation. Integration of AI tools into multidisciplinary tumor-board workflows, combined with prospective validation and standardized reporting, will be essential to realize the full clinical benefits of AI in SRS for brain metastases.

Humans↗
PubMed2026

A nonlinear multi-omics data integration and classification model based on pathway self-attention and graph convolutional networks.

The abundance of omics data has significantly advanced the development of multi-omics data integration techniques. Non-linear embedding approaches for data integration have gradually become the mainstream in multi-omics research, as these approaches can substantially improve cancer analysis by enhancing the quality of the embeddings. However, current multi-omics data integration methods are typically confined to omics measurements, neglecting domain-specific prior knowledge encompassing biological pathways. In this study, we proposed a multi-omics integrated classification model, PathTransGCN, based on pathway self-attention and graph convolutional networks (GCN). The model integrated biological pathway information into multi-omics data analysis with the aim of enhancing the accuracy of cancer classification. Multi-omics data for breast cancer (BRCA), non-small cell lung cancer (NSCLC), and low-grade glioma (LGG) were obtained from The Cancer Genome Atlas (TCGA) and UCSC Xena databases. These data included gene mutations, DNA methylation, copy number variations, and gene expression, and were used to assess the model's generalizability across different cancers. First, PathTransGCN employed a pathway self-attention module to learn latent representations of samples across different pathways, thereby obtaining multi-omics integration vectors. Concurrently, a patient similarity network (PSN) was constructed using the similarity network fusion (SNF) approach. Second, the integrated vectors and the PSN were jointly fed into a GCN for end-to-end training, enabling precise classification of cancer subtypes. Through multi-omics data analysis of the BRCA dataset, PathTransGCN outperformed several popular algorithms (such as MoGCN and DeePathNet) in the five-class classification of cancer subtypes, achieving an accuracy rate of 87.6% and an F1 score of 86.4%. Moreover, the model demonstrated robust generalization capabilities across both NSCLC and LGG datasets, while effectively identifying key disease-associated biomarkers at the pathway level. Experimental results demonstrate that PathTransGCN exhibits outstanding performance in integrating omics data and delivering interpretable classification outcomes, presenting significant potential for clinical applications.

Humans↗
PubMed2003

A two-stage unsupervised learning algorithm reproduces multisensory enhancement in a neural network model of the corticotectal system.

Multisensory enhancement (MSE) is the augmentation of the response to sensory stimulation of one modality by stimulation of a different modality. It has been described for multisensory neurons in the deep superior colliculus (DSC) of mammals, which function to detect, and direct orienting movements toward, the sources of stimulation (targets). MSE would seem to improve the ability of DSC neurons to detect targets, but many mammalian DSC neurons are unimodal. MSE requires descending input to DSC from certain regions of parietal cortex. Paradoxically, the descending projections necessary for MSE originate from unimodal cortical neurons. MSE, and the puzzling findings associated with it, can be simulated using a model of the corticotectal system. In the model, a network of DSC units receives primary sensory input that can be augmented by modulatory cortical input. Connection weights from primary and modulatory inputs are trained in stages one (Hebb) and two (Hebb-anti-Hebb), respectively, of an unsupervised two-stage algorithm. Two-stage training causes DSC units to extract information concerning simulated targets from their inputs. It also causes the DSC to develop a mixture of unimodal and multisensory units. The percentage of DSC multisensory units is determined by the proportion of cross-modal targets and by primary input ambiguity. Multisensory DSC units develop MSE, which depends on unimodal modulatory connections. Removal of the modulatory influence greatly reduces MSE but has little effect on DSC unit responses to stimuli of a single modality. The correspondence between model and data suggests that two-stage training captures important features of self-organization in the real corticotectal system.

Algorithms↗
PubMed2002

Beyond the iron mask: towards better recognition and treatment of depression associated with Parkinson's disease.

This review examines the frequency of depression complicating Parkinson's disease (PD), its aetiology and clinical features, and also how it may be recognised and treated. Studies investigating the frequency of depression in PD have yielded figures ranging between 2.7% and 70%. Methodological differences account for much of the disparity. The aetiology of depression in PD is complex, and probably relates to both biological and exogenous factors. Dysfunction of multiple neurotransmitter systems, including the serotonergic system, may be involved. Mood disturbances resulting from deep brain stimulation of the subthalamic nucleus may provide a fruitful area for future research, and assist our understanding of the neural networks involved in mediating depression. Several recent studies have confirmed that depression in the PD patient is a major determinant of quality of life and that this is closely related to dysfunction in other clinically important health areas. The validity for many existing scales in the screening, diagnosis, and monitoring of depression in the PD patient has not been established. The Montgomery-Asberg Depression Rating Scale and the Hamilton Rating Scale for Depression appear to have good diagnostic sensitivity and specificity when compared with DSM-IV criteria. Recommendations for the optimal drug treatment of depression in PD are difficult to give, due to an inexplicable dearth of sizeable, placebo-controlled studies. A majority of physicians would probably now opt for a selective serotonin reuptake inhibitor in the depressed PD patient. There is no good evidence that these drugs are associated with a worsening of motor features, but they should probably not be coprescribed with selegiline, because of the risk of causing a potentially serious serotonin syndrome. Several studies have suggested that depression in the PD patient is associated with a more rapid deterioration in cognitive and motor functions, perhaps as a surrogate marker for more extensive brainstem cell loss.

Antidepressive Agents↗
PubMed2005

[Auto sleep staging and sleep quality estimation based on BP neural network].

To estimate the sleep quality, a 3-layer BP neural network was studied. The EEG complexity and the power spectrum of sleep-multigraph served as the input vector of the network . All-night sleep-stage scoring was performed. Then several parameters (sleep period, shallow sleep period, deep sleep period, REM period, ratio of the wakeful period and sleep one) were defined to estimate the sleep quality. The experiments revealed that the estimated sleep condition was the same as the subjects' impression. The data on six cases of all-night sleep show that this method is available to estimate the sleep quality.

Electroencephalography↗