Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

A Four-Step Method for the Development of an ADHD-VR Digital Game Diagnostic Tool Prototype for Children Using a DL Model.

In Frontiers in psychiatry

Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder among children resulting in disturbances in their daily functioning. Virtual reality (VR) and machine learning technologies, such as deep learning (DL) application, are promising diagnostic tools for ADHD in the near future because VR provides stimuli to replace real stimuli and recreate experiences with high realism. It also creates a playful virtual environment and reduces stress in children. The DL model is a subset of machine learning that can transform input and output data into diagnostic values using convolutional neural network systems. By using a sensitive and specific ADHD-VR diagnostic tool prototype for children with DL model, ADHD can be diagnosed more easily and accurately, especially in places with few mental health resources or where tele-consultation is possible. To date, several virtual reality-continuous performance test (VR-CPT) diagnostic tools have been developed for ADHD; however, they do not include a machine learning or deep learning application. A diagnostic tool development study needs a trustworthy and applicable study design and conduct to ensure the completeness and transparency of the report of the accuracy of the diagnostic tool. The proposed four-step method is a mixed-method research design that combines qualitative and quantitative approaches to reduce bias and collect essential information to ensure the trustworthiness and relevance of the study findings. Therefore, this study aimed to present a brief review of a ADHD-VR digital game diagnostic tool prototype with a DL model for children and the proposed four-step method for its development.

Wiguna Tjhin, Wigantara Ngurah Agung, Ismail Raden Irawati, Kaligis Fransiska, Minayati Kusuma, Bahana Raymond, Dirgantoro Bayu

2020

Indonesia, attention-deficit/hyperactivity disorder, diagnostic tool, digital game, machine learning, neuropsychological test, virtual reality

General General

Erratum: Addendum: Molecular Generation for Desired Transcriptome Changes With Adversarial Autoencoders.

In Frontiers in pharmacology

[This corrects the article .].

Shayakhmetov Rim, Kuznetsov Maksim, Zhebrak Alexander, Kadurin Artur, Nikolenko Sergey, Aliper Alexander, Polykovskiy Daniil

2020

adversarial autoencoders, conditional generation, deep learning, drug discovery, gene expression, generative models, representation learning

General General

Application of Artificial Intelligence in Early Diagnosis of Spontaneous Preterm Labor and Birth.

In Diagnostics (Basel, Switzerland)

This study reviews the current status and future prospective of knowledge on the use of artificial intelligence for the prediction of spontaneous preterm labor and birth ("preterm birth" hereafter). The summary of review suggests that different machine learning approaches would be optimal for different types of data regarding the prediction of preterm birth: the artificial neural network, logistic regression and/or the random forest for numeric data; the support vector machine for electrohysterogram data; the recurrent neural network for text data; and the convolutional neural network for image data. The ranges of performance measures were 0.79-0.94 for accuracy, 0.22-0.97 for sensitivity, 0.86-1.00 for specificity, and 0.54-0.83 for the area under the receiver operating characteristic curve. The following maternal variables were reported to be major determinants of preterm birth: delivery and pregestational body mass index, age, parity, predelivery systolic and diastolic blood pressure, twins, below high school graduation, infant sex, prior preterm birth, progesterone medication history, upper gastrointestinal tract symptom, gastroesophageal reflux disease, Helicobacter pylori, urban region, calcium channel blocker medication history, gestational diabetes mellitus, prior cone biopsy, cervical length, myomas and adenomyosis, insurance, marriage, religion, systemic lupus erythematosus, hydroxychloroquine sulfate, and increased cerebrospinal fluid and reduced cortical folding due to impaired brain growth.

Lee Kwang-Sig, Ahn Ki Hoon

2020-Sep-22

artificial intelligence, early diagnosis, preterm birth

oncology Oncology

Unveiling COVID-19 from CHEST X-Ray with Deep Learning: A Hurdles Race with Small Data.

In International journal of environmental research and public health ; h5-index 73.0

The possibility to use widespread and simple chest X-ray (CXR) imaging for early screening of COVID-19 patients is attracting much interest from both the clinical and the AI community. In this study we provide insights and also raise warnings on what is reasonable to expect by applying deep learning to COVID classification of CXR images. We provide a methodological guide and critical reading of an extensive set of statistical results that can be obtained using currently available datasets. In particular, we take the challenge posed by current small size COVID data and show how significant can be the bias introduced by transfer-learning using larger public non-COVID CXR datasets. We also contribute by providing results on a medium size COVID CXR dataset, just collected by one of the major emergency hospitals in Northern Italy during the peak of the COVID pandemic. These novel data allow us to contribute to validate the generalization capacity of preliminary results circulating in the scientific community. Our conclusions shed some light into the possibility to effectively discriminate COVID using CXR.

Tartaglione Enzo, Barbano Carlo Alberto, Berzovini Claudio, Calandri Marco, Grangetto Marco

2020-Sep-22

COVID-19, chest X-ray, classification, deep learning

General General

Neurophysiological and Genetic Findings in Patients With Juvenile Myoclonic Epilepsy.

In Frontiers in integrative neuroscience

Objective : Transcranial magnetic stimulation (TMS), a non-invasive procedure, stimulates the cortex evaluating the central motor pathways. The response is called motor evoked potential (MEP). Polyphasia results when the response crosses the baseline more than twice (zero crossing). Recent research shows MEP polyphasia in patients with generalized genetic epilepsy (GGE) and their first-degree relatives compared with controls. Juvenile Myoclonic Epilepsy (JME), a GGE type, is not well studied regarding polyphasia. In our study, we assessed polyphasia appearance probability with TMS in JME patients, their healthy first-degree relatives and controls. Two genetic approaches were applied to uncover genetic association with polyphasia.

Methods : 20 JME patients, 23 first-degree relatives and 30 controls underwent TMS, obtaining 10-15 MEPs per participant. We evaluated MEP mean number of phases, proportion of MEP trials displaying polyphasia for each subject and variability between groups. Participants underwent whole exome sequencing (WES) via trio-based analysis and two-case scenario. Extensive bioinformatics analysis was applied.

Results : We identified increased polyphasia in patients (85%) and relatives (70%) compared to controls (47%) and significantly higher mean number of zero crossings (i.e., occurrence of phases) (patients 1.49, relatives 1.46, controls 1.22; p < 0.05). Trio-based analysis revealed a candidate polymorphism, p.Glu270del,in SYT14 (Synaptotagmin 14), in JME patients and their relatives presenting polyphasia. Sanger sequencing analysis in remaining participants showed no significant association. In two-case scenario, a machine learning approach was applied in variants identified from odds ratio analysis and risk prediction scores were obtained for polyphasia. The results revealed 61 variants of which none was associated with polyphasia. Risk prediction scores indeed showed lower probability for non-polyphasic subjects on having polyphasia and higher probability for polyphasic subjects on having polyphasia.

Conclusion : Polyphasia was present in JME patients and relatives in contrast to controls. Although no known clinical symptoms are linked to polyphasia this neurophysiological phenomenon is likely due to common cerebral electrophysiological abnormality. We did not discover direct association between genetic variants obtained and polyphasia. It is likely these genetic traits alone cannot provoke polyphasia, however, this predisposition combined with disturbed brain-electrical activity and tendency to generate seizures may increase the risk of developing polyphasia, mainly in patients and relatives.

Stefani Stefani, Kousiappa Ioanna, Nicolaou Nicoletta, Papathanasiou Eleftherios S, Oulas Anastasis, Fanis Pavlos, Neocleous Vassos, Phylactou Leonidas A, Spyrou George M, Papacostas Savvas S

2020

genetics, juvenile myoclonic epilepsy, neurophysiology, polymorphism, polyphasia, transcranial magnetic stimulation, whole exome sequencing

General General

General Distributed Neural Control and Sensory Adaptation for Self-Organized Locomotion and Fast Adaptation to Damage of Walking Robots.

In Frontiers in neural circuits

Walking animals such as invertebrates can effectively perform self-organized and robust locomotion. They can also quickly adapt their gait to deal with injury or damage. Such a complex achievement is mainly performed via coordination between the legs, commonly known as interlimb coordination. Several components underlying the interlimb coordination process (like distributed neural control circuits, local sensory feedback, and body-environment interactions during movement) have been recently identified and applied to the control systems of walking robots. However, while the sensory pathways of biological systems are plastic and can be continuously readjusted (referred to as sensory adaptation), those implemented on robots are typically static. They first need to be manually adjusted or optimized offline to obtain stable locomotion. In this study, we introduce a fast learning mechanism for online sensory adaptation. It can continuously adjust the strength of sensory pathways, thereby introducing flexible plasticity into the connections between sensory feedback and neural control circuits. We combine the sensory adaptation mechanism with distributed neural control circuits to acquire the adaptive and robust interlimb coordination of walking robots. This novel approach is also general and flexible. It can automatically adapt to different walking robots and allow them to perform stable self-organized locomotion as well as quickly deal with damage within a few walking steps. The adaptation of plasticity after damage or injury is considered here as lesion-induced plasticity. We validated our adaptive interlimb coordination approach with continuous online sensory adaptation on simulated 4-, 6-, 8-, and 20-legged robots. This study not only proposes an adaptive neural control system for artificial walking systems but also offers a possibility of invertebrate nervous systems with flexible plasticity for locomotion and adaptation to injury.

Miguel-Blanco Aitor, Manoonpong Poramate

2020

central pattern generator, forward model, legged robot control, lesion-induced plasticity, neural circuits, serotonin, synaptic plasticity, walking machines