Mon. May 10th, 2021

    Bowling Ball vs 600 Feet Drop!

    What happens when you drop stuff like a bowling ball and a car from a 1000 feet above ground?!
    How Ridiculous

    Khristian Flohr



    Mark Rober

    How Ridiculous




    How Ridiculous

    How Ridiculous

    How Ridiculous

    How Ridiculous

    New Merch –
    follow all of these or i will kick you
    • Facebook –
    • Twitter –
    • Instagram –


    Buy 1

    Get a free slap with every bottle


    Buy 2

    Buy 2 Bottles get a car


    Buy 3

    Buy 3 Bottles get a house


    Buy 4

    Buy 4 Bottles get a wife


    Researchers develop new AI-based strategy to assess beef freshness

    Although beef is one of the most consumed foods around the world, eating it when it’s past its prime is not only unsavory, but also poses some serious health risks. Unfortunately, available methods to check for beef freshness have various disadvantages that keep them from being useful to the public. For example, chemical analysis or microbial population evaluations take too much time and require the skills of a professional. On the other hand, non-destructive approaches based on near-infrared spectroscopy require expensive and sophisticated equipment. Could artificial intelligence be the key to a more cost-effective way to assess the freshness of beef?

    At Gwangju Institute of Science and Technology (GIST), Korea, a team of scientists led by Associate Processors Kyoobin Lee and Jae Gwan Kim have developed a new strategy that combines deep learning with diffuse reflectance spectroscopy (DRS), a relatively inexpensive optical technique. “Unlike other types of spectroscopy, DRS does not require complex calibration; instead, it can be used to quantify part of the molecular composition of a sample using just an affordable and easily configurable spectrometer,” explains Lee. The findings of their study are now published in Food Chemistry.

    To determine the freshness of beef samples, they relied on DRS measurements to estimate the proportions of different forms of myoglobin in the meat. Myoglobin and its derivatives are the proteins mainly responsible for the color of meat and its changes during the decomposition process. However, manually converting DRS measurements into myoglobin concentrations to finally decide upon the freshness of a sample is not a very accurate strategy–and this is where deep learning comes into play.

    Convolutional neural networks (CNN) are widely used artificial intelligence algorithms that can learn from a pre-classified dataset, referred to as ‘training set,’ and find hidden patterns in the data to classify new inputs. To train the CNN, the researchers gathered data on 78 beef samples during their spoilage process by regularly measuring their pH (acidity) alongside their DRS profiles. After manually classifying the DRS data based on the pH values as ‘fresh,’ ‘normal,’ or ‘spoiled,’ they fed the algorithm the labelled DRS dataset and also fused this information with myoglobin estimations.

    By providing both myoglobin and spectral information, our trained deep learning algorithm could correctly classify the freshness of beef samples in a matter of seconds in about 92% of cases.”

    Jae Gwan Kim, Associate Processor, GIST

    Besides its accuracy, the strengths of this novel strategy lie in its speed, low cost, and non-destructive nature. The team believes it may be possible to develop small, portable spectroscopic devices so that everyone can easily assess the freshness of their beef, even at home. Moreover, similar spectroscopy and CNN-based techniques could also be extended to other products, such as fish or pork. In the future, with any luck, it will be easier and more accessible to identify and avoid questionable meat.

    Journal reference:

    Shin, S., et al. (2021) Rapid and non-destructive spectroscopic method for classifying beef freshness using a deep spectral network fused with myoglobin information. Food Chemistry.

    Published at Fri, 02 Apr 2021 00:00:26 +0000

    By mfuente from Pixabay

    Anxiety depression mental health

    Physicians who spend less time charting after-hours and those who have better organizational support for their electronic health records (EHRs) are less likely to report that they feel burned out, according to a large-scale study published April 23 in the Journal of the American Medical Informatics Association.

    Among the physicians who responded to the surveys used in the study, doctors who spent 5 hours or less a week on after-hours charting were twice as likely to report lower levels of burnout than those who charted after-hours for 6 or more hours per week.

    The same was true for respondents who said their healthcare organizations had done a great job with EHR implementation, training, and support.

    The researchers used data from the KLAS Arch Collaborative, which was started in 2017 to measure and establish a benchmark for the clinician EHR experience. (KLAS is an independent health information technology firm that publishes survey results on various types of software.)

    Since then, more than 200 healthcare organizations have participated in the Arch Collaborative. About two thirds of the 25,000 physician respondents in the study were affiliated with academic medical centers or large healthcare systems, and less than 5% were physicians in ambulatory care practices.

    In 2018, Arch added a question about physician burnout to its survey. It also measures after-hours charting by asking how many hours per week physicians spend on this activity.

    In the study, the likelihood of experiencing symptoms of burnout became more common with each increase in time spent on after-hours charting. The largest jumps occurred between 0-5 hours (57% of the sample) and 6-15 hours (35%).

    Just more than one third (35%) of the respondents agreed that their organization provided excellent EHR support, and 9% strongly agreed. The correlation with lower burnout in this cohort was independent of how much after-hours charting the respondents did, the study shows.

    Overall, 30% of the physicians reported symptoms of burnout — a considerably lower number than the 42% of doctors who reported burnout in a recent report on the problem by Medscape. The researchers said this disparity could have been related to differences in the burnout measurement and study design.

    The researchers did not look at how burnout was correlated with the type of EHR used. More than two third (69%) of the respondents used the Epic EHR, followed by Cerner at 15.8%. Nearly 52% of the respondents had been using an EHR for at least 5 years.

    Although no demographic data was available on the respondents, the study used the length of time a doctor had been in practice as a proxy for age in adjusting the data for confounding factors. A third of the respondents had been practicing medicine for 25 or more years; 28.6%, for 15-24 years; 31%, for 5-14 years; and 5.3%, for 0-4 years.

    Big Differences Among Specialties

    There were significant differences among specialties in reported burnout, after-hours charting, and organizational EHR support.

    The specialties with the highest levels of burnout were family medicine (34%), hematology/oncology (33%), internal medicine (32%), neurology (31%), cardiology (30%), and pediatrics and pulmonology (28%). The specialties with the lowest levels of burnout were psychiatry (22%), anesthesiology (24%), and orthopedics (25%).

    Among doctors who charted after-hours for 5 or fewer hours per week, most specialties reported lower levels of burnout than did doctors in the same specialties who charted longer outside the office. This was especially notable for ob/gyns and pediatricians. Among the doctors who said their healthcare organizations had done a great job of implementing and supporting their EHR, all specialties had lower levels of burnout, particularly cardiology and neurology.

    Forty-three percent of the physicians did 6 or more hours of weekly after-hours charting. There were large differences among specialties. At the high end were hematology/oncology (60%), pulmonology (56%), and family medicine and internal medicine (53%). At the low end were radiology (12%), anesthesiology (14%), hospital medicine (34%), and psychiatry (37%).

    Forty-four percent of all respondents approved of their organization’s EHR support. The leaders in this area included hospital medicine (54%), pediatrics (50%), anesthesiology (49%), and family medicine and internal medicine (47%). The specialties least satisfied with their organization’s EHR performance included radiology (35%), orthopedics (37%), cardiology (38%), and pulmonology (39%).

    For more news, follow Medscape on Facebook, Twitter, Instagram, YouTube, and LinkedIn

    Read More

    50 thoughts on “Researchers develop new AI-based strategy to assess beef freshness”
    1. ﷽ إِنَّ اللَّهَ وَمَلائِكَتَهُ يُصَلُّونَ عَلَى النَّبِيِّ يَا أَيُّهَا الَّذِينَ آَمَنُوا صَلُّوا عَلَيْهِ وَسَلِّمُوا تَسْلِيمًا.

    Leave a Reply