Pulmonary/Respiratory Diseases



Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists

#artificialintelligence

We developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt's discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4–28 years) and 3 senior radiology residents, from 3 academic institutions.


How Alexa can help keep you healthy this flu season

USATODAY - Tech Top Stories

Smart speakers are becoming more and more common inside of homes, offering a convenient way to get the weather, manage your calendar, and answer any questions you may have. But this year, your Amazon Echo can also help you prepare for the upcoming flu season. Conceptualized and developed by Seattle Children's Hospital and Boston Children's Hospital, the Flu Doctor skill provides a convenient way to educate yourself (and your family) about the flu vaccine. "We know that search is increasingly going to be voice-enabled and we know increasingly more and more of us are incorporating smart speakers into our lives," Dr. Wendy Sue Swanson, general pediatrician and Chief of Digital Innovation at Seattle Children's Hospital, tells Reviewed. "The benefit of Flu Doctor is to learn more about the flu in your home, in a way that maybe you hadn't before using Alexa."


Changing Course: Rethinking How AI Can Interpret X-Rays

#artificialintelligence

Can high-resolution images offer better accuracy in AI support for decision making than the standard low-resolution images used in most deep learning models today? That's a question that researchers[1] from SURFsara B.V., Intel's AI group, and Dell EMC's AI group recently tackled. The answer, it turns out, is yes. This debate around image resolution highlights the occasions when hosting AI algorithms on CPUs can give better results and can help us understand the details that are critical for fine-tuning of all machine learning work, on all machines. Chest x-ray exams are one of the most frequent and cost-effective medical imaging examinations available -- far cheaper and more accessible than chest CT imaging (Computerized Axial Tomography, commonly called CAT scans or CT scans).


AdventHealth opens new AI-powered clinical command center

#artificialintelligence

AdventHealth's Central Florida Division has launched a new high-tech command center powered with GE Healthcare technology. WHY IT MATTERS The center uses artificial intelligence to help the nonprofit health system ensure efficient patient care across nine Central Florida hospitals, including algorithms that inform and guide decision-making across a multitude of areas. These include patient transfers between units and facilities, dispatch of ambulances and helicopters, and prioritization of placement and treatment across AdventHealth medical campuses in Orange, Seminole, and Osceola counties. The 12,000-square-foot center – referred to by the health system as "Mission Control" and billed as the biggest of its kind – is staffed 24 hours a day and features 60 monitors that continually display information such as near-time information such as patient bed status, as well as helicopter and ambulance status and movements. AdventHealth already leverages real-time data to boost outcomes, having built analytics dashboards for nurses to enable proactive quality improvement-- an application that has impacted CLABSI scores, CAUTI scores, as well as flu vaccine and pneumo vaccine compliance rates.


Google devises conversational AI that works better for people with ALS and accents

#artificialintelligence

Google AI researchers working with the ALS Therapy Development Institute today shared details about Project Euphonia, a speech-to-text transcription service for people with speaking impairments. They also say their approach can improve automatic speech recognition for people with non-native English accents as well. People with amyotrophic lateral sclerosis (ALS) often have slurred speech, but existing AI systems are typically trained on voice data without any affliction or accent. The new approach is successful primarily due to the introduction of small amounts of data that represents people with accents and ALS. "We show that 71% of the improvement comes from only 5 minutes of training data," according to a paper published on arXiv July 31 titled "Personalizing ASR for Dysarthric and Accented Speech with Limited Data."


Machine learning can avoid unnecessary CT use in PE patients

#artificialintelligence

"Systematic attempts to curb unnecessary imaging for PE evaluation have focused on the use of existing predictive PE risk scoring tools, such as Wells or rGeneva, as CDS tools to inform the decision to perform advanced imaging, but in practice have had a disappointing influence on CT imaging yield or use," the authors wrote. However, they went on to say that their method is different and "might be used as an automated clinical decision-support tool for patients referred for CT PE imaging to improve CT use."


What are the opportunities for AI in healthcare and what Big Data challenges lie ahead? - MedCity News

#artificialintelligence

"Writing a simple query that indicates how many patients diagnosed with non-small cell lung cancer were former smokers with cancer diagnosed specifically for the left lung is, actually, quite burdensome. The indication of'left lung' is very hard to find in imaging data sets coming from PACS systems in hospitals. It is often a manually curated effort where a human says, 'This is a left lung; this is a right lung,' but, if you flip the image, you end up some of the false positives and false negatives.Life Image is essentially using [Cloud] AutoML functionality to identify that label. But, more important than the label, is going to be the classification around it. Once you know if it's a left lung, you need to determine how many other left lungs exist in your data set and if there is a pattern at the pixel level associated with that. The labeling, classification, and normalization across multiple different vendors is a really hard problem to solve."


Adaptively stacking ensembles for influenza forecasting with incomplete data

arXiv.org Machine Learning

Seasonal influenza infects between 10 and 50 million people in the United States every year, overburdening hospitals during weeks of peak incidence. Named by the CDC as an important tool to fight the damaging effects of these epidemics, accurate forecasts of influenza and influenza-like illness (ILI) forewarn public health officials about when, and where, seasonal influenza outbreaks will hit hardest. Multi-model ensemble forecasts---weighted combinations of component models---have shown positive results in forecasting. Ensemble forecasts of influenza outbreaks have been static, training on all past ILI data at the beginning of a season, generating a set of optimal weights for each model in the ensemble, and keeping the weights constant. We propose an adaptive ensemble forecast that (i) changes model weights week-by-week throughout the influenza season, (ii) only needs the current influenza season's data to make predictions, and (iii) by introducing a prior distribution, shrinks weights toward the reference equal weighting approach and adjusts for observed ILI percentages that are subject to future revisions. We investigate the prior's ability to impact adaptive ensemble performance and, after finding an optimal prior via a cross-validation approach, compare our adaptive ensemble's performance to equal-weighted and static ensembles. Applied to forecasts of short-term ILI incidence at the regional and national level in the US, our adaptive model outperforms a naive equal-weighted ensemble, and has similar or better performance to the static ensemble, which requires multiple years of training data. Adaptive ensembles are able to quickly train and forecast during epidemics, and provide a practical tool to public health officials looking for forecasts that can conform to unique features of a specific season.


AI diagnoses lung cancers in 20 seconds

#artificialintelligence

Russian researchers from the Peter the Great St. Petersburg Polytechnic University (SPbPU) and radiologists from St. Petersburg Clinical Research for Specialized Types of Medical Care developed AI software that can distinguish and subsequently mark lung cancers on a CT scan within 20 seconds. The AI software, dubbed Doctor AI-zimov, can detect lung nodules as small as 2 millimeters on CT scans, according to a prepared statement issued by SPbPU. "Initially, we set up an algorithm to search for nodules starting from 6 millimeters, because radiologists themselves start the treatment of tumors of this size. But the system is so smart that it was able to find nodules of even smaller size," said lead researcher Lev Utkin, PhD, of the SPbPU Research Laboratory of Neural Network Technologies and Artificial Intelligence in St. Petersburg, Russia. Utkin and colleagues trained the software on 1,000 CT scans sourced from the Lung Image Database Consortium.