Neuronetwork Approach in the Early Diagnosis of Depression.

BACKGROUND: Depression is a common mental illness, with around 280 million people suffering from depression worldwide. At present, the main way to quantify the severity of depression is through psychometric scales, which entail subjectivity on the part of both patient and clinician. In the last few years, deep (machine) learning is emerging as a more objective approach for measuring depression severity. We now investigate how neural networks might serve for the early diagnosis of depression. SUBJECTS AND METHODS: We searched Medline (Pubmed) for articles published up to June 1, 2023. The search term included Depression AND Diagnostics AND Artificial Intelligence. We did not search for depression studies of machine learning other than neural networks, and selected only those papers attesting to diagnosis or screening for depression. RESULTS: Fifty-four papers met our criteria, among which 14 using facial expression recordings, 14 using EEG, 5 using fMRI, and 5 using audio speech recording analysis, whereas 6 used multimodality approach, two were the text analysis studies, and 8 used other methods. CONCLUSIONS: Research methodologies include both audio and video recordings of clinical interviews, task performance, including their subsequent conversion into text, and resting state studies (EEG, MRI, fMRI). Convolutional neural networks (CNN), including 3D-CNN and 2D-CNN, can obtain diagnostic data from the videos of the facial area. Deep learning in relation to EEG signals is the most commonly used CNN. fMRI approaches use graph convolutional networks and 3D-CNN with voxel connectivity, whereas the text analyses use CNNs, including LSTM (long/short-term memory). Audio recordings are analyzed by a hybrid CNN and support vector machine model. Neural networks are used to analyze biomaterials, gait, polysomnography, ECG, data from wrist wearable devices, and present illness history records. Multimodality studies analyze the fusion of audio features with visual and textual features using LSTM and CNN architectures, a temporal convolutional network, or a recurrent neural network. The accuracy of different hybrid and multimodality models is 78-99%, relative to the standard clinical diagnoses.

The Efficacy of Mobile Phone-Based Interventions for the Treatment of Depression: A Systematic Meta-Review of Meta-Analyses of Randomized Controlled Trials.

BACKGROUND: Depression is ranked by the World Health Organization as the single largest contributor to global disability. The shortage of health care resources, conditions of social distancing during the present pandemic, and the continuing need of patients with subclinical depression and in remission for supportive therapies, all together motivate a search for new approaches to deliver appropriate and timeous treatment for depression. SUBJECTS AND METHODS: We conducted a systematic literature search of meta-analyses and systematic reviews on the topic of mobile apps for the treatment of depression using the Medline (Pubmed) database during the period ending March 30th, 2022. This review was managed following the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines and entailed a search strategy using key-words related to depressive states and mobile phone apps for depression treatment and management. RESULTS: A total of 15 full-text articles met the inclusion criteria for the current systematic review. 13 of the 15 studies reported on the effectiveness of mobile apps for treating depression, finding a significant reduction in depressive symptoms with small-to-medium positive effect size. Patients with severe depression experienced greater benefits from a behavioral activation app, whereas those with mild depression responded better to a mindfulness app. The impact of clinicians' support is difficult to isolated completely from the particular interventions' effects. CONCLUSIONS: Mobile-based intervention apps present a convenient tool for prevention and supportive therapy of depression. The use of mobile apps may act as an efficient intervention to reduce depression in adult patients regardless the potential contributing factors of gender or co-morbidities, but the role of mobile apps should be contrasted with other digital interventions.

Occurrence of the amphibians in the Volga, Don River basins and adjacent territories (Russia): research in 1996-2020.

BACKGROUND: Knowledge about the distribution of living organisms on Earth is very important for many areas of biological science and understanding of the surrounding world. However, much of the existing distributional data are scattered throughout a multitude of sources, such as taxonomic publications, checklists and natural history collections and often, bringing them together is difficult. A very successful attempt to solve this problem is the GBIF project, which allows a huge number of researchers to publish data in one place in a single standard. Our dataset represents a significant addition to the occurrences of amphibians in the Volga, Don riverine basins and adjacent territories.The dataset contains up-to-date information on amphibian occurrences in the Volga river basin and adjacent territories, located for the most part on the Russian plain of European Russia. The dataset is based on our own studies that were conducted in the years 1996-2020. The dataset consists of 5,030 incident records, all linked to geographical coordinates. A total of 13 amphibian species belonging to nine genera and six families have been registered within the studied territory, although the distribution of amphibian species in this region of Russia has not yet been fully studied. This is especially relevant with the spread of cryptic species that can only be identified using molecular genetic research methods.The main purpose of publishing a database is to make our data available in the global biodiversity system to a wide range of users. The data can be used by researchers, as well as helping the authorities to manage their territory more efficiently. NEW INFORMATION: All occurrences are published in GBIF for the first time. Most of the data are stored in field diaries and we would like to make it available to everyone by adding it in the global biodiversity database (GBIF).