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

General General

Application of non-mydriatic fundus examination and artificial intelligence to promote the screening of diabetic retinopathy in the endocrine clinic: an observational study of T2DM patients in Tianjin, China.

In Therapeutic advances in chronic disease

Background : We aimed to determine the role of non-mydriatic fundus examination and artificial intelligence (AI) in screening diabetic retinopathy (DR) in patients with diabetes in the Metabolic Disease Management Center (MMC) in Tianjin, China.

Methods : Adult patients with type 2 diabetes mellitus who were first treated by MMC in Tianjin First Central Hospital and Tianjin 4th Center Hospital were divided into two groups according to the time that MMC was equipped with the non-mydriatic ophthalmoscope and AI system and could complete fundus examination independently (the former was the control group, the latter was the observation group). The observation indices were as follows: the incidence of DR, the fundus screening rate of the two groups, and fundus screening of diabetic patients with different course of disease.

Results : A total of 5039 patients were enrolled in this study. The incidence rate of DR was 18.6%, 29.8%, and 49.6% in patients with diabetes duration of ⩽1 year, 1-5 years, and >5 years, respectively. The screening rate of fundus in the observation group was significantly higher compared with the control group (81.3% versus 28.4%, χ2 = 1430.918, p < 0.001). The DR screening rate of the observation group was also significantly higher compared with the control group in patients with diabetes duration of ⩽1 year (77.3% versus 20.6%; χ2 = 797.534, p < 0.001), 1-5 years (82.5% versus 31.0%; χ2 = 197.124, p < 0.001) and ⩾5 years (86.9% versus 37.1%; χ2 = 475.609, p < 0.001).

Conclusions : In the case of limited medical resources, MMC can carry out one-stop examination, treatment, and management of DR through non-mydratic fundus examination and AI assistance, thus incorporating the DR screening process into the endocrine clinic, so as to facilitate early diagnosis.

Hao Zhaohu, Cui Shanshan, Zhu Yanjuan, Shao Hailin, Huang Xiao, Jiang Xia, Xu Rong, Chang Baocheng, Li Huanming


artificial intelligence, diabetic retinopathy, fundus screening, non-mydratic fundus examination

General General

Infrared Spectrometry as a High-Throughput Phenotyping Technology to Predict Complex Traits in Livestock Systems.

In Frontiers in genetics ; h5-index 62.0

High-throughput phenotyping technologies are growing in importance in livestock systems due to their ability to generate real-time, non-invasive, and accurate animal-level information. Collecting such individual-level information can generate novel traits and potentially improve animal selection and management decisions in livestock operations. One of the most relevant tools used in the dairy and beef industry to predict complex traits is infrared spectrometry, which is based on the analysis of the interaction between electromagnetic radiation and matter. The infrared electromagnetic radiation spans an enormous range of wavelengths and frequencies known as the electromagnetic spectrum. The spectrum is divided into different regions, with near- and mid-infrared regions being the main spectral regions used in livestock applications. The advantage of using infrared spectrometry includes speed, non-destructive measurement, and great potential for on-line analysis. This paper aims to review the use of mid- and near-infrared spectrometry techniques as tools to predict complex dairy and beef phenotypes, such as milk composition, feed efficiency, methane emission, fertility, energy balance, health status, and meat quality traits. Although several research studies have used these technologies to predict a wide range of phenotypes, most of them are based on Partial Least Squares (PLS) and did not considered other machine learning (ML) techniques to improve prediction quality. Therefore, we will discuss the role of analytical methods employed on spectral data to improve the predictive ability for complex traits in livestock operations. Furthermore, we will discuss different approaches to reduce data dimensionality and the impact of validation strategies on predictive quality.

Bresolin Tiago, Dórea João R R


beef cattle, dairy cattle, mid-infrared, near-infrared, novel phenotypes, spectral information

General General

The Molecular Basis of JAZ-MYC Coupling, a Protein-Protein Interface Essential for Plant Response to Stressors.

In Frontiers in plant science

The jasmonic acid (JA) signaling pathway is one of the primary mechanisms that allow plants to respond to a variety of biotic and abiotic stressors. Within this pathway, the JAZ repressor proteins and the basic helix-loop-helix (bHLH) transcription factor MYC3 play a critical role. JA is a volatile organic compound with an essential role in plant immunity. The increase in the concentration of JA leads to the decoupling of the JAZ repressor proteins and the bHLH transcription factor MYC3 causing the induction of genes of interest. The primary goal of this study was to identify the molecular basis of JAZ-MYC coupling. For this purpose, we modeled and validated 12 JAZ-MYC3 3D in silico structures and developed a molecular dynamics/machine learning pipeline to obtain two outcomes. First, we calculated the average free binding energy of JAZ-MYC3 complexes, which was predicted to be -10.94 +/-2.67 kJ/mol. Second, we predicted which ones should be the interface residues that make the predominant contribution to the free energy of binding (molecular hotspots). The predicted protein hotspots matched a conserved linear motif SL••FL•••R, which may have a crucial role during MYC3 recognition of JAZ proteins. As a proof of concept, we tested, both in silico and in vitro, the importance of this motif on PEAPOD (PPD) proteins, which also belong to the TIFY protein family, like the JAZ proteins, but cannot bind to MYC3. By mutating these proteins to match the SL••FL•••R motif, we could force PPDs to bind the MYC3 transcription factor. Taken together, modeling protein-protein interactions and using machine learning will help to find essential motifs and molecular mechanisms in the JA pathway.

Oña Chuquimarca Samara, Ayala-Ruano Sebastián, Goossens Jonas, Pauwels Laurens, Goossens Alain, Leon-Reyes Antonio, Ángel Méndez Miguel


JAZ, MYC, computer, hotspots, machine learning, modeling, plant defense

General General

Contrasting Classical and Machine Learning Approaches in the Estimation of Value-Added Scores in Large-Scale Educational Data.

In Frontiers in psychology ; h5-index 92.0

There is no consensus on which statistical model estimates school value-added (VA) most accurately. To date, the two most common statistical models used for the calculation of VA scores are two classical methods: linear regression and multilevel models. These models have the advantage of being relatively transparent and thus understandable for most researchers and practitioners. However, these statistical models are bound to certain assumptions (e.g., linearity) that might limit their prediction accuracy. Machine learning methods, which have yielded spectacular results in numerous fields, may be a valuable alternative to these classical models. Although big data is not new in general, it is relatively new in the realm of social sciences and education. New types of data require new data analytical approaches. Such techniques have already evolved in fields with a long tradition in crunching big data (e.g., gene technology). The objective of the present paper is to competently apply these "imported" techniques to education data, more precisely VA scores, and assess when and how they can extend or replace the classical psychometrics toolbox. The different models include linear and non-linear methods and extend classical models with the most commonly used machine learning methods (i.e., random forest, neural networks, support vector machines, and boosting). We used representative data of 3,026 students in 153 schools who took part in the standardized achievement tests of the Luxembourg School Monitoring Program in grades 1 and 3. Multilevel models outperformed classical linear and polynomial regressions, as well as different machine learning models. However, it could be observed that across all schools, school VA scores from different model types correlated highly. Yet, the percentage of disagreements as compared to multilevel models was not trivial and real-life implications for individual schools may still be dramatic depending on the model type used. Implications of these results and possible ethical concerns regarding the use of machine learning methods for decision-making in education are discussed.

Levy Jessica, Mussack Dominic, Brunner Martin, Keller Ulrich, Cardoso-Leite Pedro, Fischbach Antoine


longitudinal data, machine learning, model comparison, school effectiveness, value-added modeling

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


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


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