MSGID: 1:317/3 64a794ed   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    AI finds a way to people's hearts (literally!)    
    Unveiling a groundbreaking and accurate AI-based method to classify   
   cardiac function and disease using chest X-Rays    
      
     Date:   
         July 6, 2023   
     Source:   
         Osaka Metropolitan University   
     Summary:   
         Scientists have successfully developed a model that utilizes   
         AI to accurately classify cardiac functions and valvular heart   
         diseases from chest radiographs. The Area Under the Curve, or AUC,   
         of the AI classification showed a high level of accuracy, exceeding   
         0.85 for almost all indicators and reaching 0.92 for detecting   
         left ventricular ejection fraction -- an important measure for   
         monitoring cardiac function.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
      
   ==========================================================================   
   FULL STORY   
   ==========================================================================   
   AI (artificial intelligence) may sound like a cold robotic system, but   
   Osaka Metropolitan University scientists have shown that it can deliver   
   heartwarming -- or, more to the point, "heart-warning" -- support. They   
   unveiled an innovative use of AI that classifies cardiac functions   
   and pinpoints valvular heart disease with unprecedented accuracy,   
   demonstrating continued progress in merging the fields of medicine and   
   technology to advance patient care. The results will be published in   
   The Lancet Digital Health.   
      
   Valvular heart disease, one cause of heart failure, is often   
   diagnosed using echocardiography. This technique, however, requires   
   specialized skills, so there is a corresponding shortage of qualified   
   technicians. Meanwhile, chest radiography is one of the most common tests   
   to identify diseases, primarily of the lungs. Even though the heart is   
   also visible in chest radiographs, little was known heretofore about the   
   ability of chest radiographs to detect cardiac function or disease. Chest   
   radiographs, or chest X-Rays, are performed in many hospitals and very   
   little time is required to conduct them, making them highly accessible   
   and reproducible. Accordingly, the research team led by Dr. Daiju Ueda,   
   from the Department of Diagnostic and Interventional Radiology at the   
   Graduate School of Medicine of Osaka Metropolitan University, reckoned   
   that if cardiac function and disease could be determined from chest   
   radiographs, this test could serve as a supplement to echocardiography.   
      
   Dr. Ueda's team successfully developed a model that utilizes AI to   
   accurately classify cardiac functions and valvular heart diseases from   
   chest radiographs.   
      
   Since AI trained on a single dataset faces potential bias, leading to   
   low accuracy, the team aimed for multi-institutional data. Accordingly,   
   a total of 22,551 chest radiographs associated with 22,551 echocardiograms   
   were collected from 16,946 patients at four facilities between 2013 and   
   2021. With the chest radiographs set as input data and the echocardiograms   
   set as output data, the AI model was trained to learn features connecting   
   both datasets.   
      
   The AI model was able to categorize precisely six selected types of   
   valvular heart disease, with the Area Under the Curve, or AUC, ranging   
   from 0.83 to 0.92. (AUC is a rating index that indicates the capability of   
   an AI model and uses a value range from 0 to 1, with the closer to 1, the   
   better.) The AUC was 0.92 at a 40% cut-off for detecting left ventricular   
   ejection fraction -- an important measure for monitoring cardiac function.   
      
   "It took us a very long time to get to these results, but I believe this   
   is significant research," stated Dr. Ueda. "In addition to improving   
   the efficiency of doctors' diagnoses, the system might also be used   
   in areas where there are no specialists, in night-time emergencies,   
   and for patients who have difficulty undergoing echocardiography."   
       * RELATED_TOPICS   
             o Health_&_Medicine   
                   # Heart_Disease # Mesothelioma # Stroke_Prevention #   
                   Diseases_and_Conditions   
             o Computers_&_Math   
                   # Computer_Modeling # Mathematical_Modeling # Mathematics   
                   # Information_Technology   
       * RELATED_TERMS   
             o Defibrillation o Artificial_heart o CPR o Electrocardiogram   
             o Heart_failure o Heart o Heart_rate o South_Beach_diet   
      
   ==========================================================================   
      
    Print   
      
    Email   
      
    Share   
   ==========================================================================   
   ****** 1 ****** ***** 2 ***** **** 3 ****   
   *** 4 *** ** 5 ** Breaking this hour   
   ==========================================================================   
       * First_Snapshots_of_Fermion_Pairs *   
       Why_No_Kangaroos_in_Bali;_No_Tigers_in_Australia   
       * New_Route_for_Treating_Cancer:_Chromosomes *   
       Giant_Stone_Artefacts_Found:_Prehistoric_Tools   
       * Astonishing_Secrets_of_Tunicate_Origins *   
       Most_Distant_Active_Supermassive_Black_Hole *   
       Creative_People_Enjoy_Idle_Time_More_Than_Others   
       * Restoring_Fragile_X_Protein_Production *   
       Earth's_Solid_Metal_Sphere_Is_'Textured' *   
       Elephants_Vary_Their_Dinner_Menu_Day-To-Day   
      
   Trending Topics this week   
   ==========================================================================   
   HEALTH_&_MEDICINE Patient_Education_and_Counseling Birth_Defects   
   Cholesterol MIND_&_BRAIN Educational_Psychology Stroke Autism   
   LIVING_&_WELL Fitness Healthy_Aging Nutrition   
      
      
   ==========================================================================   
      
   Strange & Offbeat   
   ==========================================================================   
   HEALTH_&_MEDICINE Holograms_for_Life:_Improving_IVF_Success   
   Grocery_Store_Carts_Set_to_Help_Diagnose_Common_Heart_Rhythm_Disorder_and   
   Prevent_Stroke DNA_Can_Fold_Into_Complex_Shapes_to_Execute_New_Functions   
   MIND_&_BRAIN AI_Tests_Into_Top_1%_for_Original_Creative_Thinking   
   Everyone's_Brain_Has_a_Pain_Fingerprint_--_New_Research_Has_Revealed_for_the   
   First_Time   
   Scientists_Discover_Spiral-Shaped_Signals_That_Organize_Brain_Activity   
   LIVING_&_WELL Illusions_Are_in_the_Eye,_Not_the_Mind   
   Amputees_Feel_Warmth_in_Their_Missing_Hand   
   Why_Do_Champagne_Bubbles_Rise_the_Way_They_Do?_Scientists'_New_Discovery_Is   
   Worthy_of_a_Toast Story Source: Materials provided by   
   Osaka_Metropolitan_University. Note: Content may be edited for style   
   and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Daiju Ueda et al. Artificial intelligence-based model to classify   
      cardiac   
         functions from chest radiographs: a multi-institutional,   
         retrospective model development and validation study. The Lancet   
         Digital Health, 2023 DOI: 10.1016/S2589-7500(23)00107-3   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/07/230706190150.htm   
      
   --- up 1 year, 18 weeks, 3 days, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 218/700 226/30 227/114   
   SEEN-BY: 229/110 112 113 307 317 400 426 428 470 664 700 291/111 292/854   
   SEEN-BY: 298/25 305/3 317/3 320/219 396/45 5075/35   
   PATH: 317/3 229/426