Real Time Central Assessment of Kidney Transplant Indication Biopsies by Microarrays: The INTERCOMEX Study


The authors conducted a prospective trial to assess the feasibility of real time central molecular assessment of kidney transplant biopsy samples from 10 North American or European centers. Biopsy samples taken 1 day to 34 years posttransplantation were stabilized in RNAlater, sent via courier overnight at ambient temperature to the central laboratory, and processed (29 h workflow) using microarrays to assess T cell– and antibody-mediated rejection (TCMR and ABMR, respectively). Of 538 biopsy samples submitted, 519 (96%) were sufficient for microarray analysis (average length, 3 mm). Automated reports were generated without knowledge of histology and HLA antibody, with diagnoses assigned based on Molecular Microscope Diagnostic System (MMDx) classifier algorithms and signed out by one observer. Agreement between MMDx and histology (balanced accuracy) was 77% for TCMR, 77% for ABMR, and 76% for no rejection.

Amplifying intelligent drug design


'The idea of understanding a disease from an evolutionary viewpoint to inform drug design still resonates today in how Exscientia is approaching the design of anticancer agents. 'I spent a season at the GlaxoWellcome labs in Stevenage making the compounds I'd designed, and vividly remember the excitement of discovering the first molecule we'd made was active.' These included topics such as the druggable genome, ligand efficiency and network pharmacology – all of which are familiar topics to drug discovery chemists today. An early success involved feeding historical data for the project that discovered erectile dysfunction drug tadalafil (Cialis) into the evolutionary drug design model.

Google could soon get access to genetic patient data

Daily Mail

By building a neural network, Google's algorithms can interpret huge amounts of genetic, health, and environmental data to predict a persons health status, such as their level of risk of heart attack (stock image) It was created after Google bought University College London spinout, DeepMind, for £400 million in 2014. By building a neural network, these algorithms can interpret huge amounts of genetic, health, and environmental data to predict a persons health status, such as their level of risk of heart attack. Google announced the first of its NHS collaborations in February 2016, saying it was building an app to help hospital staff monitor patients with kidney disease. ', With personalisation as their ultimate'goal', Google intend to use the machine learning algorithms which track our digital footprint and target users with personalised advertising based on their preferences.

DeepMind's kidney disease-fighting Streams app is coming to a new hospital


Google's DeepMind, the British artificial intelligence firm behind the human-besting AlphaGo software, launched a healthcare platform in partnership with the U.K.'s Moorfields Eye Hospital and Royal Free London in 2015. Starting this month, doctors and nurses at Musgrove Park will get DeepMind's Streams app for iPhone, which helps spot early signs of acute kidney injury. "This is all about early detection of seriously unwell patients so that we can immediately escalate care, ensure a very rapid response, and make sure they are treated quickly by the right specialist doctor," Luke Gompels, a consultant in medicine at Musgrove Park Hospital, told the BBC. Last year, it acquired Hark, a task management app optimized for hospital environments that was co-developed by students from Imperial College London and the National Institute for Health Research.

Google DeepMind's NHS deal under scrutiny - BBC News


A deal between Google's artificial intelligence firm DeepMind and the UK's NHS had serious "inadequacies", an academic paper has suggested. More than a million patient records were shared with DeepMind to build an app to alert doctors about patients at risk of acute kidney injury (AKI). In a statement, the ICO told the BBC: "Our investigation into the sharing of patient information between the Royal Free NHS Trust and Deep Mind is close to conclusion. It revealed that more than 26 doctors and nurses at the Royal Free are now using Streams and that each day it alerts them to 11 patients at risk of AKI.

Tokyo court clears ex-Novartis employee of Diovan drug ad exaggeration charge

The Japan Times

A former employee of the Japanese unit of Swiss pharmaceutical giant Novartis AG was found not guilty Thursday of exaggerating advertising claims for the blood pressure-lowering drug Diovan. Besides clearing 66-year-old Nobuo Shirahashi of a violation under a pharmaceutical affairs law that bans fraudulent and exaggerated advertising, the Tokyo District Court also found the Tokyo-based sales arm Novartis Pharma K.K. While acknowledging that clinical trial data for the drug were manipulated, presiding Judge Yasuo Tsujikawa determined that the drugmaker's published research paper based on the data was not an advertisement that falls under the purview of the pharmaceutical law. He supplied the research team with manipulated data concerning patients who were not administered the drug.

Novel biomarkers increase power to predict therapeutic response in lupus


The research team hypothesized that a targeted panel of urinary biomarkers reflecting initial resident and inflammatory cell activation (cytokines), signals for homing to the kidney (chemokines), activation of inflammatory cells (growth factors), and damage to resident cells, combined with artificial intelligence/machine learning modeling, might provide an early LN decision-support tool that could predict outcomes better than standard biomarkers alone. Outcome models using novel biomarkers plus traditional clinical markers demonstrated greater AUC and significance compared to models developed with traditional markers alone ([AUC 0.79; P 0.001] vs. [AUC 0.61; P 0.05], respectively). The combined models also demonstrated greater power to correctly predict LN therapy outcomes (responder versus non-responder) than models using only traditional markers (76% vs. 27%, respectively [P 0.002]). The team identified chemokines, cytokines, and markers of cellular damage as most predictive of LN therapy response.

Will medical AI save the NHS? - Raconteur


"Healthcare is one of the highest cost areas for all modern economies, which makes it ripe for AI as providers look for efficiency to care for patients," says Dan Housman, chief technology officer at ConvergeHEALTH by Deloitte. Babylon is an AI-based app using speech recognition to check patients' symptoms and connect them with GPs Tweaking performance is the difference between a podium or an also-ran finish, and now the same skills and techniques are being used by its Applied Technologies division to improve health outcomes. Its first visible effort is a collaboration with London's Royal Free Hospital to develop an app for speedier recognition of acute kidney injury, which causes 40,000 deaths a year. It is also developing the Hark system that improves hospital medical efficiency.

BioData Mining


Most biological network inference methods focus on the definition of gene regulatory networks, in which edges represent direct regulatory interactions between genes [2–4]. Two approaches to functional network inference: one based on the expression profile similarity and the other based on the extraction of knowledge from machine learning models. The specific focus of this paper is the network inference from rule-based machine learning models, these have been successfully applied before to extract knowledge from genetic data [17] and identify disease risk factors in a bladder cancer study [18]. To address these questions, we propose in this article a new network inference protocol, called FuNeL (Functional Network Learning).

Why Google wants your medical records - BBC News


Projects include a tie-up with London Moorfields eye hospital, which will see it using one million eye scans to train its artificial intelligence system to diagnose potential sight issues, and development of an app to help doctors spot kidney disease. In May it was revealed that Google's DeepMind, had been given access to the healthcare data of up to 1.6 million patients from three hospitals run by London's Royal Free Trust in order to develop an app, called Streams, that would notify doctors should someone be at risk of developing acute kidney injury (AKI). Some were also bemused when it became apparent that the deal with Google's AI firm would not actually involve any artificial intelligence. In the case of the Royal Free, the BBC understands that 148 people have withdrawn their consent, a tiny fraction of the patients involved.