Data Mining and Deep Learning for Predicting the Displacement of “Step-Like” Landslides

Landslide displacement prediction is one of the unsolved challenges in the field of geological hazards, especially in reservoir areas. Affected by rainfall and cyclic fluctuations in reservoir water levels, a large number of landslide disasters have developed in the Three Gorges Reservoir Area. In this article, the Baishuihe landslide was taken as the research object. Firstly, based on time series theory, the landslide displacement was decomposed into three parts (trend term, periodic term, and random term) by Variational Mode Decomposition (VMD). Next, the landslide was divided into three deformation states according to the deformation rate. A data mining algorithm was introduced for selecting the triggering factors of periodic displacement, and the Fruit Fly Optimization Algorithm–Back Propagation Neural Network (FOA-BPNN) was applied to the training and prediction of periodic and random displacements. The results show that the displacement monitoring curve of the Baishuihe landslide has a “step-like” trend. Using VMD to decompose the displacement of a landslide can indicate the triggering factors, which has clear physical significance. In the proposed model, the R2 values between the measured and predicted displacements of ZG118 and XD01 were 0.977 and 0.978 respectively. Compared with previous studies, the prediction model proposed in this article not only ensures the calculation efficiency but also further improves the accuracy of the prediction results, which could provide guidance for the prediction and prevention of geological disasters.

AI-Based Prediction and Prevention of Psychological and Behavioral Changes in Ex-COVID-19 Patients

The COVID-19 pandemic has adverse consequences on human psychology and behavior long after initial recovery from the virus. These COVID-19 health sequelae, if undetected and left untreated, may lead to more enduring mental health problems, and put vulnerable individuals at risk of developing more serious psychopathologies. Therefore, an early distinction of such vulnerable individuals from those who are more resilient is important to undertake timely preventive interventions. The main aim of this article is to present a comprehensive multimodal conceptual approach for addressing these potential psychological and behavioral mental health changes using state-of-the-art tools and means of artificial intelligence (AI). Mental health COVID-19 recovery programs at post-COVID clinics based on AI prediction and prevention strategies may significantly improve the global mental health of ex-COVID-19 patients. Most COVID-19 recovery programs currently involve specialists such as pulmonologists, cardiologists, and neurologists, but there is a lack of psychiatrist care. The focus of this article is on new tools which can enhance the current limited psychiatrist resources and capabilities in coping with the upcoming challenges related to widespread mental health disorders. Patients affected by COVID-19 are more vulnerable to psychological and behavioral changes than non-COVID populations and therefore they deserve careful clinical psychological screening in post-COVID clinics. However, despite significant advances in research, the pace of progress in prevention of psychiatric disorders in these patients is still insufficient. Current approaches for the diagnosis of psychiatric disorders largely rely on clinical rating scales, as well as self-rating questionnaires that are inadequate for comprehensive assessment of ex-COVID-19 patients’ susceptibility to mental health deterioration. These limitations can presumably be overcome by applying state-of-the-art AI-based tools in diagnosis, prevention, and treatment of psychiatric disorders in acute phase of disease to prevent more chronic psychiatric consequences.

The Dynamic Digital Twin: diagnosis, treatment, prediction and prevention of disease during the life course (Preprint)

UNSTRUCTURED A Digital Twin (DT), which is defined originally as a virtual representation of a physical asset, system or process, is a new concept in healthcare. DT in healthcare cannot be a single technology, but a domain adapted multi-modal modelling approach, which incorporates the acquisition, management, analysis, prediction, and interpretation of the data, aiming to improve medical decision making. However, there are many challenges and barriers that has to be overcome before a DT can be used in healthcare. In this viewpoint paper, we address these challenges, and envision a dynamic DT in healthcare for optimizing individual patient health care journeys. We describe how we can commit multiple domains to developing this DT. With our cross-domain definition of the DT, we aim to define future goals, trade-offs, and methods, which guide the development of the dynamic DT and the implementation strategies in healthcare.

Vaginal health in women and the possibility of predicting preterm birth through microbiome analysis

Background: With the recent development of next-generation sequencing technology, the microbiome in the body is being revealed in detail. It is also possible to describe the normal vaginal microenvironment and, more specifically, any changes in pregnancy. Moreover, we present the hypothesis that the microbiome is a contributing factor to preterm birth (PTB).Current Concepts: High estrogen status stimulates the maturation and proliferation of vaginal epithelial cells and the accumulation of glycogen, which promotes lactic acid production and maintains the vaginal environment at an acidic pH. The vaginas of most premenopausal women are predominantly colonized by Lactobacillus which plays an important role in local defense. Recently, it has also been reported that there are several specific types of Lactobacillus species, while other anaerobes, including Gardnerella and Atopobium also coexist in the vagina. Vaginal dysbiosis is defined as various expressions of microorganisms, secretion of specific metabolites, and changes in pH. During pregnancy, a multitude of microbiome changes occur in the oral cavity, gut, vagina, and placenta. The risk of PTB increases if the microbiome changes to one of dysbiosis. It is possible to analyze the characteristic microbiome composition related to PTB and to develop biomarkers predicting PTB. It is necessary to educate patients based on these findings.Discussion and Conclusion: Microbiome analysis has contributed significantly to understanding the association between women’s vaginal health and PTB. Continued research will also contribute to public health by assisting in the prediction and prevention of PTB.

Addressing Fouling by Qualifying Chemical Additives Using Novel Technologies

Fouling of heat exchangers and production of stable emulsions in desalting units can present significant challenges in refinery operations. Often these difficulties occur due to the concurrent processing of two or more crude oils that are incompatible under process conditions. This paper describes a significant development in laboratory techniques for studying these issues and evaluating mitigation strategies. Asphaltenes compatibility was evaluated for oil mixtures that may be co-processed in the refinery using a deposition flow rig, and the results were compared with those obtained with more conventional tests: blending stability analysis by light scattering and various screening methods. The flow rig mimics the process conditions (elevated pressure, high temperature, flow-induced shear) and identifies whether deposition or precipitation will occur. The former can cause fouling of heat exchangers whereas the latter produces solids that can stabilize emulsions in the desalter. By varying the proportions of oils that were co-injected into the deposition flow rig, the range within which mixtures were unstable was found. By flowing through a capillary (to mimic a heat exchanger) and in-line filter, it was possible to identify whether precipitation of suspended flocs or fouling of the heat exchanger itself was the likely issue for each mixture. Emulsion-stability tests were conducted using a pressurized rig with an ersatz separator to mimic the desalting unit; results were compared with those obtained in conventional, ambient-pressure bottle tests. Oil(s) and refinery wash water were injected, mixed under representative shear, and allowed to separate within the typical residence time of the desalter. Chemical additives were tested to identify those that were effective at controlling any observed problems. Results obtained in either flow rig (using representative pressure, temperature, and shear) did not always match those obtained using conventional methods. Asphaltenes fouling occurred under conditions where it was not predicted by screening tests that were conducted at conditions not representative of the process and did not occur under conditions where it was predicted. Differences were also observed between the emulsion stability observed in bottle versus rig tests, though these should be viewed as complementary techniques. This paper presents new laboratory techniques for the prediction and prevention of refinery fouling and emulsion stability. They mimic conditions in the facilities much better than those typically used to date.

P-OGC44 Multi-omic cohort study of Barrett’s oesophagus reveals structural variation and retrotransposon activity to occur early in cancer evolution

Background Barrett’s oesophagus (BE) is the main risk factor for the development of oesophageal adenocarcinoma (OAC), yet few patients ever go on to progress to cancer. The acquisition of events during the metaplasia-dysplasia-cancer sequence is poorly characterised. We present a large, unbiased, multi-omics analysis of a cross-sectional cohort of pre-cancer samples, with the aim of providing a comprehensive insight into the diversity and molecular changes driving the disease to cancer. Methods We generated and integrated the genomic (50x), transcriptomic and epigenomic (850K EPIC array) landscapes of snap-frozen endoscopic biopsies from 146 patients with a range of outcomes (27 long-standing non-dysplastic; 12 prior to progression to dysplasia; 14 low-grade; 25 high-grade; 21 intramucosal carcinoma; 47 cases of BE taken adjacent to OAC) and 642 person years of follow-up. All biopsies were reviewed independently by 3 pathologists and had associated annotation with detailed clinical information. Results The total number of structural variants (SV) captured the most variance between samples. Complex SVs and LINE-1 retrotransposon activity were observed even before dysplasia had developed and increased with progression. Increasing SV burden was associated with chromothripsis (12%, 18/146) and breakage-fusion bridges (BFBs; 8%, 13/146). In more than 50% of these, the BFBs were in chromosome 17, harbouring the oncogenes ERBB2 and CDK12, for which expression was significantly higher. With progression there was increased expression of genes related to cell-cycle checkpoint, DNA repair and chromosomal instability, and the epigenetic silencing of genes in WNT-signalling and cell-cycle pathways. Conclusions Genomic complexity occurs very early in the natural history of BE and increasing genomic instability appears to tip the balance towards cancer. This may inform the potential for progression to cancer beyond the clinically discernible phenotype. Efforts to better understand the triggers for chromosomal breakages and rearrangements that underly progression will aid clinical prediction and prevention strategies.