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

General General

How wide is the application of genetic big data in biomedicine.

In Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie

In the era of big data, massive genetic data, as a new industry, has quickly swept almost all industries, especially the pharmaceutical industry. As countries around the world start to build their own gene banks, scientists study the data to explore the origins and migration of humans. Moreover, big data encourage the development of cancer therapy and bring good news to cancer patients. Big datum has been involved in the study of many diseases, and it has been found that analyzing diseases at the gene level can lead to more beneficial treatment options than ordinary treatments. This review will introduce the development of extensive data in medical research from the perspective of big data and tumor, neurological and psychiatric diseases, cardiovascular diseases, other applications and the development direction of big data in medicine.

Liu Yanan, Li Na, Zhu Xiao, Qi Yi


Angiocardiopathy, Artificial intelligence, Cancer, Genetic big data, Neurological and psychiatric disorders, Precision medicine

Pathology Pathology

Meta-analysis of voice disorders databases and applied machine learning techniques.

In Mathematical biosciences and engineering : MBE

Background and Objective: Voice disorders are pathological conditions that directly affect voice production. Computer based diagnosis may play a major role in the early detection and in tracking and even development of efficient pathological speech diagnosis, based on a computerized acoustic evaluation. The health of the Voice is assessed by several acoustic parameters. The exactness of these parameters is often linked to algorithms used to estimate them for speech noise identification. That is why main effort of the scientists is to study acoustic parameters and to apply classification methods that achieve a high precision in discrimination. The primary aim of this paper is for a meta-analysis on voice disorder databases i.e. SVD, MEEI and AVPD and machine learning techniques applied on it. Materials and Methods: This field of study was systematically reviewed in compliance with PRISMA guidelines. A search was performed with a set of formulated keywords on three databases i.e. Science Direct, PubMed, and IEEE Xplore. A proper screening and analysis of articles were performed after which several articles were also excluded. Results: Forty-five studies that fulfills the eligibility criteria were included in this meta-analysis. After applying eligibility criteria on the peer reviewed and research article and studies that were published in authentic journals and conferences proceedings till June 2020 were chosen for further full-text screening. In general, only those articles that used voice recordings from SVD, MEEI and AVPD databases as a dataset is included in this meta-analysis. Conclusion : We discussed the strengths and weaknesses of SVD, MEEI and AVPD. After detailed analysis of the studies including the techniques used and outcome measurements, it was also concluded that Support Vector Machine (SVM) is the most common used algorithm for the detection of voice disorders. Other than was also noticed that researchers focus on supervised techniques for the clinical diagnosis of voice disorder rather than using unsupervised techniques. It was also concluded that more work needs to be on voice pathology detection using AVPD database.

Syed Sidra Abid, Rashid Munaf, Hussain Samreen


** AVPD , MEEI , SVD , machine learning technique , voice disorder **

General General

Information Aware max-norm Dirichlet networks for predictive uncertainty estimation.

In Neural networks : the official journal of the International Neural Network Society

Precise estimation of uncertainty in predictions for AI systems is a critical factor in ensuring trust and safety. Deep neural networks trained with a conventional method are prone to over-confident predictions. In contrast to Bayesian neural networks that learn approximate distributions on weights to infer prediction confidence, we propose a novel method, Information Aware Dirichlet networks, that learn an explicit Dirichlet prior distribution on predictive distributions by minimizing a bound on the expected max norm of the prediction error and penalizing information associated with incorrect outcomes. Properties of the new cost function are derived to indicate how improved uncertainty estimation is achieved. Experiments using real datasets show that our technique outperforms, by a large margin, state-of-the-art neural networks for estimating within-distribution and out-of-distribution uncertainty, and detecting adversarial examples.

Tsiligkaridis Theodoros


Deep learning, Dirichlet, Neural networks, Predictive uncertainty, Uncertainty quantification

General General

Ultimate jumping of coalesced droplets on superhydrophobic surfaces.

In Journal of colloid and interface science

HYPOTHESIS : Jumping of coalesced droplets on superhydrophobic surfaces (SHSs) is widely used for enhanced condensation, anti-icing/frosting, and self-cleaning due to its superior droplet transport capability. However, because only a tiny fraction (about 5%) of the released excess surface energy during coalescence can be transformed into jumping kinetic energy, the jumping is very weak, limiting its application.

METHODS : We experimentally propose enhanced jumping methods, use machine learning to design structures that achieve ultimate jumping, and finally combine experiments and simulations to investigate the mechanism of the enhanced jumping.

FINDING : We find that a more orderly flow inside the droplets through the structure is the key to improve energy transfer efficiency and that the egg tray-like structure enables the droplet to jump with an energy transfer efficiency 10.6 times higher than that of jumping on flat surfaces. This energy transfer efficiency is very close to the theoretical limit, i.e., almost all the released excess surface energy is transformed into jumping kinetic energy after overcoming viscous dissipation. The ultimate jumping enhances the application of water droplet jumping and enables other low surface energy fluid such as R22, R134a, Gasoline, and Ethanol, which cannot jump on a flat surface, to jump.

Yuan Zhiping, Gao Sihang, Hu ZhiFeng, Dai Liyu, Hou Huimin, Chu Fuqiang, Wu Xiaomin


ADAM, Coalescence-induced droplet jumping, Energy transfer efficiency, Enhanced jumping, Machine learning, Superhydrophobic surface

General General

Water quality prospective in Twenty First Century: Status of water quality in major river basins, contemporary strategies and impediments: A review.

In Environmental pollution (Barking, Essex : 1987)

Water quality improvement is one of the top priorities in the global agenda endorsed by United Nation. In this review manuscript, a holistic view of water quality degradation such as concerned pollutants, source of pollution, and its consequences in major river basins around the globe (at least 1 from each continent and a total of 16 basins) is presented. Additionally, nine contemporary techniques such as field scale evaluation, watershed scale evaluation, strategies to identify critical source areas, optimization strategies for placement of best management practices (BMPs), social component in watershed modeling, machine learning algorithms to address water quality problems in complex natural systems concomitant with spatial heterogeneity, establishing a total maximum daily loads (TMDLs), remote sensing in monitoring water quality, and developing water quality index are discussed. Next, the existing barriers to improve water quality are classified into primary and secondary impediments. A detail discussion of three primary impediments (climate change, urbanization and industrial activities, and agriculture) and ten secondary impediments (availability of water quality data, complexity of system, lack of skilled person, environmental legislation, fragmented mandate, limitation in resources, environmental awareness, resistance to change, alteration of nutrient ratio by river damming, and emerging pollutants) are illustrated. Finally, considering all the existing knowledge gaps pertaining to contemporary strategies, a future direction of water quality research is outlined to significantly improve the water quality around the globe.

Giri Subhasis


Best management practices, Climate change, Critical source areas, Eutrophication, Machine learning algorithms, Remote sensing, Urbanization, Water quality criteria, Water quality index

Radiology Radiology

Imaging genomics for accurate diagnosis and treatment of tumors: A cutting edge overview.

In Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie

Imaging genomics refers to the establishment of the connection between invasive gene expression features and non-invasive imaging features. Tumor imaging genomics can not only understand the macroscopic phenotype of tumor, but also can deeply analyze the cellular and molecular characteristics of tumor tissue. In recent years, tumor imaging genomics has been a key in the field of medicine. The incidence of cancer in China has increased significantly, which is the main reason of disease death of urban residents. With the rapid development of imaging medicine, depending on imaging genomics, many experts have made remarkable achievements in tumor screening and diagnosis, prognosis evaluation, new treatment targets and understanding of tumor biological mechanism. This review analyzes the relationship between tumor radiology and gene expression, which provides a favorable direction for clinical staging, prognosis evaluation and accurate treatment of tumors.

Liu Zhen, Wu Kefeng, Wu Binhua, Tang Xiaoning, Yuan Huiqing, Pang Hao, Huang Yongmei, Zhu Xiao, Luo Hui, Qi Yi


Artificial intelligence, Cancer, Computed tomography, Imaging genomics, Magnetic resonance, Radiogenomics