Computer Recognizes Abnormal Heart Sounds In Children
Computer Recognizes Abnormal Heart Sounds In Children

ÄÄÇ»ÅÍ°¡ ¾î¸°¾ÆÀ̵éÀÇ ºñÁ¤»ó ½ÉÀåÀ½À» ¾Ë¾Æ³½´Ù.



DALLAS, June 5 – An electronic stethoscope and a personal computer were used to distinguish innocent heart murmurs from those that may indicate a serious problem, and may help doctors render better medical decisions, researchers report in today¡¯s Circulation: Journal of the American Heart Association.

´Þ¶ó½º 6¿ù5ÀÏ- ÀüÀÚûÁø½Ã½ºÅÛ°ú °³Àοë ÄÄÇ»ÅÍ°¡ ½É°¢ÇÑ ¹®Á¦·Î ÁöÀûµÇ´Â ½ÉÀåÀ¸·ÎºÎÅÍ Á¤»óÀûÀÎ ½ÉÀâÀ½À» ±¸ºÐÇϴµ¥ ÀÌ¿ëµÇ¸ç, ±×°ÍµéÀÌ ´õ ³ªÀº ÀÇÇÐÀû °áÁ¤À» Çϴµ¥ ÀÇ»çµéÀ» µµ¿ï ¼ö ÀÖÀ» °ÍÀ̶ó´Â ¿¬±¸ ·¹Æ÷Æ®°¡ ¿À´Ã ¹ßÇàµÇ¾ú´Ù. : ¹Ì±¹½ÉÀåÇùȸ Àú³Î


¡°This technology offers great promise for the development of an accurate device for high-volume, low-cost screening for heart murmurs,¡± says lead author Curt G. DeGroff, M.D., a pediatric cardiologist at The Children¡¯s Hospital and assistant professor in the department of pediatrics at the University of Colorado Health Sciences Center.

¡°ÀÌ·± ±â¼úÀº ½ÉÀâÀ½À» °¡·Á³»´Âµ¥ ³ôÀº º¼·ý, ÀûÀº ºñ¿ëÀ¸·Î Á¤¹ÐÇÑ ÀåºñÀÇ °³¹ßÀ» À§ÇÑ ¾à¼ÓÀ» Á¦°øÇÑ´Ù.


Studies estimate that a heart murmur can be heard in 77 percent to 95 percent of children at some time during childhood.

¿¬±¸ÇÑ ¹Ù¿¡ ÀÇÇÏ¸é ½ÉÀâÀ½Àº À¯³â½ÃÀý ±â°£ µ¿¾È ¶§¶§·Î ¾î¸°¾ÆÀ̵éÀÇ 77%¿¡¼­ 95%±îÁö µé·ÁÁú ¼ö ÀÖ´Ù°í ÃßÃøÇÏ°í ÀÖ´Ù.


A heart murmur is an extra heart sound heard with each heartbeat. Less than 1 percent of heart murmurs are a sign of problems such as those caused by defective heart valves or a malformed heart.

½ÉÀâÀ½Àº °¢ ½É¹Úµ¿°ú ÇÔ²² µé¸®´Â Ưº°ÇÑ ½ÉÀå¼Ò¸®ÀÌ´Ù. ½ÉÀâÀ½ÀÇ 1%ÀÌÇÏ°¡ ½ÉÀå¹ëºê¿¡ ¹®Á¦°¡ Àְųª, ±âÇü½ÉÀå¿¡ ÀÇÇØ ¿øÀÎÀÌ µÇ´Â ¹®Á¦µéÀÌ´Ù.


¡°Early recognition of a heart murmur is important. But equally important, is to avoid identifying a child with a healthy heart as having an abnormal heart murmur,¡± says DeGroff.

ÀÏÂï ½ÉÀâÀ½À» ¾Ë¾Æä´Â °ÍÀÌ Áß¿äÇÏ´Ù. ±×·¯³ª µ¿µîÇÏ°Ô Áß¿äÇÑ °ÍÀº ºñÁ¤»óÀûÀÎ ½ÉÀâÀ½À» °¡Áø Á¤»óÀûÀÎ ½ÉÀåÀÇ ¾ÆÀ̵éÀ» ½Äº°ÇØ ³õ´Â °ÍÀÌ´Ù.


Listening to the heart is the primary tool for distinguishing heart murmurs. But the human ear cannot appreciate many of the subtleties of heart sounds and the interpretation of the sounds is prone to error, says DeGroff.

½ÉÀå¼Ò¸®¸¦ µè´Â °ÍÀº ½ÉÀâÀ½À» ±¸ºÐÇØ ³»´Â °Í¿¡ °¡Àå ±âº»ÀûÀÎ °ÍÀÌ´Ù. ±×·¯³ª Àΰ£ÀÇ ±Í´Â ½ÉÀå¼Ò¸® °¡¿îµ¥ ¸¹Àº ¹Ì¹¦ÇÑ °ÍµéÀ» ½Äº°ÇØ ³¾ ¼ö ¾ø°í, ½ÉÀå¼Ò¸®ÀÇ Çؼ®Àº ¿À·ù¸¦ ³¾ ¼ö°¡ ÀÖ´Ù°í DeGroff´Â ¸»ÇÑ´Ù.


An artificial neural network (ANN) – a computer program which can recognize complex patterns – was developed by co-investigator Roop L. Mahajan, Ph.D., a professor of mechanical engineering at the University of Colorado, Boulder, and other colleagues.

Àΰø½Å°æ³×Æ®¿öÅ©(ANN) – ÄÄÇ»ÅÍ ÇÁ·Î±×·¥À¸·Î¼­ º¹ÀâÇÑ ÆÐÅÏÀ» ¾Ë¾Æ³¾ ¼ö ÀÖ´Ù –Àº Roop L. Mahajan ¹Ú»ç(ÄÝ·Î¶óµµ ´ëÇÐÀÇ ¿ªÇп£Áö´Ï¾î¸µ ±³¼ö)¿Í ´Ù¸¥ µ¿·áµé¿¡ ÀÇÇØ °³¹ßµÇ¾ú´Ù.


ANNs are valuable tools that can learn complex interactions and identify subtle relationships that may not be apparent to humans. Studies of ANNs in cardiology have been mainly concerned with the evaluation of electrocardiogram (ECG) signals.

ANNÀº Àΰ£¿¡°Ô º¹ÀâÇÑ »óÈ£ÀÛ¿ëÀ» ¹è¿ï¼ö ÀÖ°í, ¸í¹éÇÏ°Ô µÇÁö ¾ÊÀ» ¹Ì¹¦ÇÑ °ü°è¼ºÀ» È®ÀÎÇÒ ¼ö ÀÖ´Â °¡Ä¡ÀÖ´Â ÅøÀÌ´Ù.  ½ÉÀåÇп¡¼­ÀÇ ANNÀÇ ¿¬±¸µéÀº ÁÖ·Î ECG ÆÄÇüÀÇ °¡Ä¡¿¡ ÁÖ·Î °ü°èµÇ¾î ÀÖ´Ù.


Their use on heart sounds has been examined in a few studies with limited results and applicability.

½ÉÀå¼Ò¸®¸¦ »ç¿ëÇÏ´Â ±×°ÍµéÀº Á¦ÇÑµÈ °á°úµé°ú Àû¿ëÈ­µÈ ¸î°¡Áö ¿¬±¸ ³»¿¡¼­ Àû¿ëµÇ¾ú´Ù.


Here, researchers used heart sound recordings from 69 patients – 37 with abnormal heart murmurs and 32 with innocent murmurs – to train the network. Using a special mathematical model, they converted the sound recordings into the energy-per-unit of frequency interval to take advantage of the computer¡¯s pattern-recognition capabilities.

¿©±â, ¿¬±¸¿øµéÀº ¿¬½ÀÇϱâ À§ÇØ 69¸íÀÇ È¯ÀÚµé·ÎºÎÅÍ ³ìÀ½µÈ ½ÉÀå¼Ò¸®¸¦ »ç¿ëÇß´Ù. - 37¸íÀº ºñÁ¤»óÀûÀÎ ½ÉÀâÀ½ÀÌ°í, 32¸íÀº º´ÀÌ ¾ø´Â »ç¶÷ÀÌ´Ù. – Ưº°ÇÑ ¼öÇÐÀû ¸ðµ¨À» »ç¿ëÇÏ¿©, ±×µéÀº ÄÄÇ»ÅÍ ÆÐÅÏÀÇ Æò±ÕÄ¡¸¦ ÃëÇϱâ À§ÇÑ ÁÖÆļöº° °£°ÝÀÇ ´ÜÀ§´ç ¿¡³ÊÁö·Î ³ìÀ½µÈ ¼Ò¸®¸¦ Àüȯ½ÃÄ×´Ù


¡°The mathematical signature for each child and the patterns for innocent and abnormal murmurs are different,¡± Mahajan explains.  

¡°°¢ ¾î¸°¾ÆÀÌÀÇ ¼öÇÐÀû ¼öÄ¡¿Í Á¤»óÄ¡ÀÇ ÆÐÅÏ°ú ºñÁ¤»ó ½ÉÀâÀ½Àº ´Ù¸£´Ù¡±°í MahajanÀº ¼³¸íÇÑ´Ù.

The researchers fed samples of the heart recordings back to the ANN model and adjusted the frequency range and sensitivity of the signals to improve the computer¡¯s ability to differentiate between the abnormal and innocent murmurs. They also re-entered the data to mathematically mimic consultations with multiple experts.

¿¬±¸¿øÀº ³ìÀ½µÈ ½ÉÀåÀ½ÀÇ °ßº»À» ANN ¸ðµ¨¿¡ Çǵå¹éÇÏ°í, °³¼±ÇÏ´Â ½ÅÈ£ÀÇ ÁÖÆļö ¹üÀ§¿Í ºñÁ¤»óÀûÀÌ°í °áÁ¡¾ø´Â ½ÉÀâÀ½À» ±¸º°Çϱâ À§ÇÑ ÄÄÇ»ÅÍÀÇ ´É·ÂÀ» Á¤ºñÇß´Ù. ±×µéµµ ´Ù¾çÇÑ Àü¹®°¡¿ÍÀÇ ¼öÇлó ¸ð¹æÀÇ »ó´ã¿¡ µ¥ÀÌÅ͵éÀ» ´Ù½Ã ±âÀÔÇß´Ù.

translated by JSKim.


   ÀüÀÚûÁø±â¿Í ÀϹÝûÁø±âÀÇ ¼Ò¸®ºñ±³ (³í¹®¿ä¾à)

gstec

   °æµ¿¸ÆÀÌ µÎ²¨¿ï¼ö·Ï Ä¡¸Å À§Çè

gstec


Copyright 1999-2024 Zeroboard / skin by piatty