A multicentre international study has demonstrated for the first time that diagnosis of obstructive coronary artery disease can be improved by using deep learning analysis of upright and supine single photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI).
According to the Centers for Disease Control and Prevention, coronary artery disease is the most common type of heart disease, killing more than 370,000 people in the United States annually. SPECT MPI, which is widely used for its diagnosis, shows how well the heart muscle is pumping and examines blood flow through the heart during exercise and at rest. On new cameras with a patient imaged in sitting position, two positions (semi-upright and supine) are routinely used to mitigate attenuation artifacts. The current quantitative standard for analysing MPI data is to calculate the combined total perfusion deficit (TPD) from these 2 positions. Visually, physicians need to reconcile information available from 2 views. 
Deep convolutional neural networks, often referred to as deep learning (DL), go beyond machine learning using algorithms. They directly analyse visual data, learn from them, and make intelligent findings based on the image information.
For this study, DL analysis of data from the two-position stress MPI was compared with the standard TPD analysis of 1,160 patients without known coronary artery disease. Patients underwent stress MPI with the nuclear medicine radiotracer technetium (99mTc) sestamibi. New-generation solid-state SPECT scanners in four different centres were used, and images were quantified at the Cedars-Sinai Medical Centre in Los Angeles, California. All patients had on-site clinical reads and invasive coronary angiography correlations within six months of MPI.
Obstructive disease was defined as at least 70 percent narrowing of the three major coronary arteries and at least 50 percent for the left main coronary artery. During the validation procedure, four different DL models were trained (each using data from three centers) and then were evaluated on the one center left aside. Predictions for 4 centers were merged to have an overall estimation of the multicenter performance.
The study revealed that 718 (62 percent) patients and 1,272 of 3,480 (37 percent) arteries had obstructive disease. Per-patient sensitivity improved from 61.8 percent with TPD to 65.6 percent with DL, and per-vessel sensitivity improved from 54.6 percent with TPD to 59.1 percent with DL. In addition, DL had a sensitivity of 84.8 percent, versus 82.6 percent for an on-site clinical read.
The results clearly show that DL improves MPI interpretation over current methods.
“These findings were demonstrated for the first time in a rigorous, repeated external validation,” points out Piotr J. Slomka, PhD, at Cedars-Sinai Medical Center, affirming that “the latest developments in artificial intelligence can be efficiently leveraged to enhance the accuracy of existing nuclear medicine techniques.”
Society of Nuclear Medicine and Molecular Imaging https://tinyurl.com/y5q537lm

Reversibly paralysing and heavily sedating hospitalized patients with severe breathing problems do not improve outcomes in most cases, according to a National Institutes of Health-funded clinical trial conducted at dozens of North American hospitals and led by clinician-scientists at the University of Pittsburgh and University of Colorado schools of medicine.
The trial—which was stopped early due to futility—settles a long-standing debate in the critical care medicine community about whether it is better to paralyse and sedate patients in acute respiratory distress to aid mechanical ventilation or avoid heavy sedation to improve recovery.
“It’s been a conundrum—on the one hand, really well-done studies have shown that temporarily paralysing the patient to improve mechanical breathing saves lives. But you can’t paralyse without heavy sedation, and studies also show heavy sedation results in worse recovery. You can’t have both—so what’s a clinician to do?” said senior author Derek Angus, M.D., M.P.H., who holds the Mitchell P. Fink Endowed Chair of the Pitt School of Medicine’s Department of Critical Care Medicine. “Our trial finally settles it—light sedation with intermittent, short-term paralysis if necessary is as good as deep sedation with continuous paralysis.”
The Re-evaluation Of Systemic Early neuromuscular blockade (ROSE) trial is the first of the new National Heart, Lung, and Blood Institute’s (NHLBI) Prevention & Early Treatment of Acute Lung Injury (PETAL) Network. PETAL develops and conducts randomized controlled clinical trials to prevent or treat patients who have, or who are at risk for, acute lung injury or acute respiratory distress syndrome. The trial network places particular emphasis on early detection by requiring every network member institute include both critical care and emergency medicine, acute care or trauma principal investigators to ensure that critical health issues are recognized and triaged as fast as possible to improve patients’ odds of recovery before they are even transferred to the intensive care unit.
Angus, who also directs Pitt’s Clinical Research, Investigation, and Systems Modeling of Acute Illness (CRISMA) Center, said the trial results make him confident when he says that avoiding paralysis and deep sedation is the best practice for most patients hospitalized with breathing problems. However, he notes that future trials will be needed to tease out whether there is a subpopulation of patients with acute respiratory distress syndrome who still benefit from neuromuscular blockade.
UPMChttps://tinyurl.com/yxc95rrl

New research has shown how surgical gowns used in hospitals are retaining superbug Clostridium difficile (C. difficile), even after being treated with the recommended amount of disinfectant.
The research, led by the University of Plymouth, tested single-use hospital surgical gowns (made of polypropylene) that had been infected with three different strains of C. difficile, a bacteria that can cause severe diarrhea, bowel complications and even death.
After treating infected items for ten minutes with disinfectant containing 1,000 parts per million of chlorine – the amount and time recommended by the Department of Health and Social Care– the team found that all strains of C. difficile spores still survived on the gowns and did not reduce, allowing them to potentially transfer to other items.
The research took place because the gowns were suspected to be contributing to C. difficile transmission in a USA hospital. Contaminated gowns from the USA hospital were tested for presence of C. difficile and a deadly 027 type strain was isolated, showing that the gowns can pick up and retain the spores.
In this study, new gowns had the bacteria ‘spiked’ onto them for testing purposes.
Three strains of C. difficile were tested including R20291, which caused severe outbreaks in UK hospitals between 2003 and 2006. This strain is known to cause mortality in patients as it is becoming resistant to the main antibiotic treatments, vancomycin and metronidazole.
To examine the ability of C. difficile to adhere to, and subsequently transfer from, hospital surgical gowns, spores were applied directly to the surgical gowns in water for 10 seconds, 30 seconds, 1 minute, 5 minutes and 10 minutes before being removed and discarded. This was designed to mimic transfer of infectious bodily fluids in the clinical setting and assess the potential for onward transmission to patients.
There was no significant difference between the amount of spores recovered from the gowns and the contact time of the spores to the gowns; suggesting that the spore transfer between surfaces occurred within the first 10 seconds of contact.
The items were then treated with 1,000 ppm chlorine-releasing disinfectant, sodium dichloroisocyanurate (NaDCC) to try and tackle the bug.
Principal investigator and study lead Dr Tina Joshi, part of the Institute of Translational and Stratified Medicine (ITSMed) at the University of Plymouth, explains that this work can be applied to hospitals anywhere in the world, and should help inform future guidelines on infection control and biocides (bacteria killers). She said:
“C. difficile is a really nasty superbug and it’s so important that hospitals stop it from spreading. This study shows that even when we think an item has been suitably cleaned, it hasn’t been necessarily – 1,000 parts per million of chlorine just isn’t enough as the bacteria survived and grew after disinfection.
“As well as possibly upping the concentration of the biocide, the research highlights the need for appropriate hygiene practices. Gowns should not be worn outside of isolated areas as our work has shown that C. difficile spores are good at sticking to clinical surfaces, and can so easily be transferred, causing infections in patients. In an age where infections are becoming resistant to antibiotics, it’s worrying to think that other bacteria are becoming resistant to biocides. So the best thing we can do is ensure that infection control procedures are robust and standardized.”
University of Plymouthhttps://tinyurl.com/yxpr4dhf