Using machine learning to extract information and predict outcomes from reports of randomised trials of smoking cessation interventions in the Human Behaviour-Change Project.

Background: Using reports of randomised trials of smoking cessation interventions as a test case, this study aimed to develop and evaluate machine learning (ML) algorithms for extracting information from study reports and predicting outcomes as part of the Human Behaviour-Change Project. It is the first of two linked papers, with the second paper reporting on further development of a prediction system.

Methods: Researchers manually annotated 70 items of information ('entities') in 512 reports of randomised trials of smoking cessation interventions covering intervention content and delivery, population, setting, outcome and study methodology using the Behaviour Change Intervention Ontology.

Evaluation of the success of predicted dental changes with clear-aligner treatment: A pilot study.

Objective: This pilot study concerned evaluation of the success of predicted dental changes in patients presenting with Class I malocclusions who were submitted to treatment aligners, using the superimposition.

Methods: The digital models were superimposed and analyzed using 3DSlicer 5.0 software.

Influence of pain duration and severity on oral health-related quality of life and patient satisfaction during adult treatment with clear aligners.

Background: This study aims to compare the impact of pain on quality of life and patient satisfaction during treatment with aligners.

Methods: Ninety-four subjects in active treatment were invited to answer self-reported questions concerning pain severity and duration, occurrence of other signs and symptoms, and level of satisfaction with their treatment. Also, the OHIP-14 questionnaire was applied to assess patients' OHRQoL.

Automated Feature Selection from Medical Literature.

We propose an automated approach to rank the most salient variables related to a certain clinical phenomenon from scientific literature. Our solution is an automated approach to improve the efficiency of the collection of different health-related measures from a population, and to accelerate the discovery of novel associations and dependencies between health-related concepts.

Outcome Prediction from Behaviour Change Intervention Evaluations using a Combination of Node and Word Embedding.

Findings from randomized controlled trials (RCTs) of behaviour change interventions encode much of our knowledge on intervention efficacy under defined conditions. Predicting outcomes of novel interventions in novel conditions can be challenging, as can predicting differences in outcomes between different interventions or different conditions. To predict outcomes from RCTs, we propose a generic framework of combining the information from two sources - i) the instances (comprised of surrounding text and their numeric values) of relevant attributes, namely the intervention, setting and population characteristics of a study, and ii) abstract representation of the categories of these attributes themselves.

Knowledge Extraction and Prediction from Behavior Science Randomized Controlled Trials: A Case Study in Smoking Cessation.

Due to the fast pace at which randomized controlled trials are published in the health domain, researchers, consultants and policymakers would benefit from more automatic ways to process them by both extracting relevant information and automating the meta-analysis processes. In this paper, we present a novel methodology based on natural language processing and reasoning models to 1) extract relevant information from RCTs and 2) predict potential outcome values on novel scenarios, given the extracted knowledge, in the domain of behavior change for smoking cessation.

An autonomous debating system.

Artificial intelligence (AI) is defined as the ability of machines to perform tasks that are usually associated with intelligent beings. Argument and debate are fundamental capabilities of human intelligence, essential for a wide range of human activities, and common to all human societies. The development of computational argumentation technologies is therefore an important emerging discipline in AI research.

Integrin alpha5 in human breast cancer is a mediator of bone metastasis and a therapeutic target for the treatment of osteolytic lesions.

Bone metastasis remains a major cause of mortality and morbidity in breast cancer. Therefore, there is an urgent need to better select high-risk patients in order to adapt patient's treatment and prevent bone recurrence. Here, we found that integrin alpha5 (ITGA5) was highly expressed in bone metastases, compared to lung, liver, or brain metastases.

The Human Behaviour-Change Project: An artificial intelligence system to answer questions about changing behaviour.

Changing behaviour is necessary to address many of the threats facing human populations.  However, identifying behaviour change interventions likely to be effective in particular contexts as a basis for improving them presents a major challenge. The Human Behaviour-Change Project harnesses the power of artificial intelligence and behavioural science to organise global evidence about behaviour change to predict outcomes in common and unknown behaviour change scenarios.

Information Extraction of Behavior Change Intervention Descriptions.

We describe an information extraction (IE) approach for knowledge base population of behavior change scientific intervention findings. In this paper, we focus on building a system able to characterize the specific intervention techniques that are undertaken within behavior change intervention studies. We have investigated three different configurations of a general information retrieval based framework for information extraction: a) an unsupervised approach that hinges on specification of a query for each attribute to be extracted and a few parameters for rule-based post-processing; b) a semi-supervised approach, which uses a part of the ground-truth annotations as a training set to automatically learn optimal representation of the queries; and c) a supervised approach that replaces the rule-based post processing by a text classifier.

[Biology of metastases and molecular mechanisms of their formation].

Metastasis in cancer patients is often associated with a poor prognosis. However, we still have limited knowledge of the underlying molecular mechanisms, due to the great complexity of the biological processes involved in the formation of metastases. During tumor progression, the metastatic cells acquire genetic and epigenetic modifications allowing them to adapt to the various environments they will encounter (in the circulation and the host microenvironment) and to resist to the antitumor therapeutic agents.

Distinct expression profiles and functions of Kindlins in breast cancer.

Background: Kindlin-1, - 2, and - 3 are the three members of the Kindlin family. They are best known as regulators of integrin functions, contributing to fundamental biological processes such as cell survival, adhesion and migration. Their deregulation leads to diverse pathologies including a broad range of cancers in which both, tumor-promoting and tumor-inhibiting functions have been described.

VOPP1 promotes breast tumorigenesis by interacting with the tumor suppressor WWOX.

Background: The WW domain-containing oxidoreductase (WWOX) gene, frequently altered in breast cancer, encodes a tumor suppressor whose function is mediated through its interactions with cancer-related proteins, such as the pro-apoptotic protein p73α.

Results: To better understand the involvement of WWOX in breast tumorigenesis, we performed a yeast two-hybrid screen and co-immunoprecipitation assays to identify novel partners of this protein. We characterized the vesicular overexpressed in cancer pro-survival protein 1 (VOPP1) as a new regulator of WWOX.

The iron chelator deferasirox synergises with chemotherapy to treat triple-negative breast cancers.

To ensure their high proliferation rate, tumor cells have an iron metabolic disorder causing them to have increased iron needs, making them more susceptible to iron deprivation. This vulnerability could be a therapeutic target. In breast cancers, the development of new therapeutic approaches is urgently needed for patients with triple-negative tumors, which frequently relapse after chemotherapy and suffer from a lack of targeted therapies.

Vandetanib as a potential new treatment for estrogen receptor-negative breast cancers.

The receptor tyrosine kinase RET is implicated in the progression of luminal breast cancers (BC) but its role in estrogen receptor (ER) negative tumors is unknown. Here we investigated the expression of RET in breast cancer patients tumors and patient-derived xenografts (PDX) and evaluated the therapeutic potential of Vandetanib, a tyrosin kinase inhibitor with strong activity against RET, EGFR and VEGFR2, in ER negative breast cancer PDX. The RT-PCR analysis of RET expression in breast tumors of 446 patients and 57 PDX, showed elevated levels of RET in ER+ and HER2+ subtypes and in a small subgroup of triple-negative breast cancers (TNBC).

A patient with severe respiratory failure caused by novel human coronavirus.

We report a case of a 45-year-old patient who developed severe acute respiratory distress syndrome accompanied by renal failure. An infection with a novel human coronavirus was confirmed and found to be the reason for rapidly progressive respiratory failure of our patient.

Clinical features and virological analysis of a case of Middle East respiratory syndrome coronavirus infection.

Background: The Middle East respiratory syndrome coronavirus (MERS-CoV) is an emerging virus involved in cases and case clusters of severe acute respiratory infection in the Arabian Peninsula, Tunisia, Morocco, France, Italy, Germany, and the UK. We provide a full description of a fatal case of MERS-CoV infection and associated phylogenetic analyses.

Methods: We report data for a patient who was admitted to the Klinikum Schwabing (Munich, Germany) for severe acute respiratory infection.

A novel extracorporeal CO(2) removal system: results of a pilot study of hypercapnic respiratory failure in patients with COPD.

Background: Hypercapnic respiratory failure in patients with COPD frequently requires mechanical ventilatory support. Extracorporeal CO2 removal (ECCO2R) techniques have not been systematically evaluated in these patients.

Methods: This is a pilot study of a novel ECCO2R device that utilizes a single venous catheter with high CO2 removal rates at low blood flows.

Contact investigation of a case of human novel coronavirus infection treated in a German hospital, October-November 2012.

On 24 October 2012, a patient with acute respiratory distress syndrome of unknown origin and symptom onset on 5 October was transferred from Qatar to a specialist lung clinic in Germany. Late diagnosis on 20 November of an infection with the novel Coronavirus (NCoV) resulted in potential exposure of a considerable number of healthcare workers. Using a questionnaire we asked 123 identified contacts (120 hospital and three out-of-hospital contacts) about exposure to the patient.

Assays for laboratory confirmation of novel human coronavirus (hCoV-EMC) infections.

We present a rigorously validated and highly sensitive confirmatory real-time RT-PCR assay (1A assay) that can be used in combination with the previously reported upE assay. Two additional RT-PCR assays for sequencing are described, targeting the RdRp gene (RdRpSeq assay) and N gene (NSeq assay), where an insertion/deletion polymorphism might exist among different hCoV-EMC strains. Finally, a simplified and biologically safe protocol for detection of antibody response by immunofluorescence microscopy was developed using convalescent patient serum.

A methodological approach to unravel organ-specific breast cancer metastasis.

Breast cancer is the most commonly diagnosed and the second highest cause of cancer-related mortality. Although major breakthroughs have emerged during the past decades concerning the characterization of major malignant tumors hallmarks, little is known about the molecular process that sustains the most deadly feature of cancer: metastasis to distant organs. In fact, this colonization of tumor cells to secondary sites is not random but rather orientated, and depends on several signalling events that are not fully elucidated yet.

Role of the focal adhesion protein kindlin-1 in breast cancer growth and lung metastasis.

Background: Fermitin family member 1 (FERMT1, Kindlin-1) is an epithelial-specific regulator of integrin functions and is associated with Kindler syndrome, a genetic disorder characterized by skin blistering, atrophy, and photosensitivity. However, the possible role of kindlin-1 in cancer remains unknown.

Methods: Kindlin-1 expression was quantified in several human cancers using quantitative real-time polymerase chain reaction and published microarray datasets.