åǥÁö

[GT] ½º¸¶Æ®ÆùÀ¸·Î ³úÁ¹ÁßÀ» »çÀü¿¡ Áø´ÜÇÏ´Â ±â¼ú

Ææ½Çº£À̴ϾÆÁÖ¸³´ëÇб³(Penn State)¿Í ÈÞ½ºÅÏ °¨¸® º´¿ø(Houston Methodist Hospital)ÀÇ ¿¬±¸¿øµéÀÌ È¹±âÀûÀÎ »õ·Î¿î µµ±¸¸¦ ¸¸µé¾ú´Ù. ½º¸¶Æ® Æù°ú »óÈ£ ÀÛ¿ëÀ» ÅëÇØ °¨ÁöµÇ´Â ȯÀÚÀÇ ¾ð¾î ´É·Â ÀÌ»ó°ú ¾È¸é ±ÙÀ°ÀÇ ¿òÁ÷ÀÓ¸¸À¸·Î ¼ö ºÐ À̳»¿¡ ÀÀ±Þ½Ç ÀÇ»çÀÇ Á¤È®µµ·Î ³úÁ¹ÁßÀ» Áø´ÜÇÒ ¼ö ÀÖ´Â µµ±¸°¡ ±×°ÍÀÌ´Ù.



¾î¶² ½Å±â¼úÀÌ ¼¼»óÀ» ±ØÀûÀ¸·Î º¯È­½Ãų±î? ¼¼°è ÃÖ°íÀÇ ¿¬±¸¼Ò¿¡¼­ ³ª¿À´Â ³î¶ó¿î Çõ½ÅÀ» µ¶Á¡ ¼Ò°³ÇÕ´Ï´Ù.

 

 

Ææ½Çº£À̴ϾÆÁÖ¸³´ëÇб³(Penn State)¿Í ÈÞ½ºÅÏ °¨¸® º´¿ø(Houston Methodist Hospital)ÀÇ ¿¬±¸¿øµéÀÌ È¹±âÀûÀÎ »õ·Î¿î µµ±¸¸¦ ¸¸µé¾ú´Ù. ½º¸¶Æ® Æù°ú »óÈ£ ÀÛ¿ëÀ» ÅëÇØ °¨ÁöµÇ´Â ȯÀÚÀÇ ¾ð¾î ´É·Â ÀÌ»ó°ú ¾È¸é ±ÙÀ°ÀÇ ¿òÁ÷ÀÓ¸¸À¸·Î ¼ö ºÐ À̳»¿¡ ÀÀ±Þ½Ç ÀÇ»çÀÇ Á¤È®µµ·Î ³úÁ¹ÁßÀ» Áø´ÜÇÒ ¼ö ÀÖ´Â µµ±¸°¡ ±×°ÍÀÌ´Ù.

 

ȯÀÚ°¡ ³úÁ¹Áß Áõ»óÀ» °æÇèÇϸé 1ºÐ, 1ÃÊ°¡ Áß¿äÇÏ´Ù. ±×·¯³ª ³úÁ¹Áß Áø´Ü°ú °ü·ÃÇÏ¿© ÀÀ±Þ½Ç ÀÇ»ç´Â ¿É¼ÇÀÌ Á¦ÇѵǾî ÀÖ´Ù. ºñ½Î°í ½Ã°£ÀÌ ¸¹ÀÌ °É¸®´Â ¹æ»ç´É ±â¹Ý ½ºÄµÀ» À§ÇØ È¯ÀÚ¸¦ º¸³»°Å³ª ÀÓ»ó Áø´Ü Å×½ºÆ®¸¦ Áï½Ã ¼öÇàÇÒ ¼ö ¾ø´Â ½Å°æ°ú Àü¹®ÀÇ¿¡°Ô ÀüÈ­¸¦ °Ç´Ù.

 

ÀÌ ¿¬±¸ÆÀÀÇ »õ·Î¿î Á¢±Ù ¹æ½ÄÀº Àü»ê ¾È¸é µ¿ÀÛ ºÐ¼®°ú ÀÚ¿¬¾î 󸮸¦ »ç¿ëÇÏ¿© ȯÀÚÀÇ ¾ó±¼À̳ª À½¼ºÀÇ ÀÌ»ó(¿¹¸¦ µé¾î, óÁø »´ ¶Ç´Â ºÒºÐ¸í ÇÑ ¸»)À» ½Äº°ÇÏ¿© ³úÁ¹ÁßÀÌ ÀǽɵǴ ½ÇÁ¦ ÀÀ±Þ½Ç ȯÀÚ Áß ³úÁ¹ÁßÀÇ Á¸À縦 È®ÀÎÇÏ´Â ÃÖÃÊÀÇ ¹æ¹ýÀÌ´Ù.

 

°á°ú´Â ÀÀ±Þ½Ç Àǻ簡 ȯÀÚÀÇ Áß¿äÇÑ ´ÙÀ½ ´Ü°è¸¦ º¸´Ù ½Å¼ÓÇÏ°Ô °áÁ¤ÇÏ´Â µ¥ µµ¿òÀÌ µÉ ¼ö ÀÖ´Ù. ÀÌ°ÍÀº ÀÀ±Þ »óȲ¿¡¼­ ³úÁ¹Áß Áø´ÜÀ» µ½´Â ÀΰøÁö´ÉÀÇ Ã¹ ¹ø° ÀÀ¿ë ÇÁ·Î±×·¥ Áß ÇϳªÀÌ´Ù. ±×¸®°í ±Ã±ØÀûÀ¸·Î ÀÌ ¾ÖÇø®ÄÉÀ̼ÇÀº °£º´ÀÎÀ̳ª ȯÀÚ°¡ º´¿ø¿¡ ​​µµÂøÇϱâ Àü¿¡ ÀÚü Æò°¡¸¦ ³»¸®´Â µ¥ È°¿ëµÉ ¼ö ÀÖ´Ù.

 

ÄÄÇ»ÅÍ ¸ðµ¨À» ÈƷýÃÅ°±â À§ÇØ ¿¬±¸¿øµéÀº Åػ罺 ÈÞ½ºÅÏ °¨¸®±³ º´¿ø¿¡¼­ ³úÁ¹Áß Áõ»óÀ» °æÇèÇÏ°í ÀÖ´Â 80¸íÀÇ ÀÌ»óÀÇ È¯ÀڷκÎÅÍ µ¥ÀÌÅÍ ¼¼Æ®¸¦ ±¸ÃàÇß´Ù. °¢ ȯÀÚ´Â ½º¸¶Æ®Æù¿¡ ³ìÀ½µÇ´Â µ¿¾È À½¼º ¹× ÀÎÁö ÀÇ»ç¼ÒÅëÀ» ºÐ¼®Çϱâ À§ÇÑ À½¼º Å×½ºÆ®¸¦ ¼öÇàÇϵµ·Ï ¿äû¹Þ¾Ò´Ù.

 

ÀÚ¿¬½º·¯¿î ȯ°æ¿¡¼­ ¾È¸é µ¥ÀÌÅ͸¦ ¼öÁýÇϸé ÀÌ ÀÛ¾÷Àº ´õ °­·ÂÇØÁö°í ½ÇÁ¦ ÀÓ»ó ÀÀ¿ë ÇÁ·Î±×·¥¿¡¼­ À¯¿ëÇÏ°Ô È°¿ëµÇ¾î, ±Ã±ØÀûÀ¸·Î ³úÁ¹ÁßÀÇ ¿ø°Ý Áø´Ü ¹× ÀÚü Æò°¡¿¡ ÀÌ ¹æ¹ýÀ» ½ÇÁ¦·Î »ç¿ëÇÒ ¼ö ÀÖ´Ù.

 

ÈÞ½ºÅÏ °¨¸® º´¿øÀÇ µ¥ÀÌÅÍ ¼¼Æ®¿¡¼­ ¸ðµ¨À» Å×½ºÆ® ÇÑ °á°ú, ¿¬±¸¿øµéÀº CT ½ºÄµ°ú °°Àº Ãß°¡ Å×½ºÆ®¸¦ »ç¿ëÇÏ´Â ÀÀ±Þ½Ç ÀÇ»çÀÇ ÀÓ»ó Áø´Ü¿¡ ÇÊÀûÇÏ´Â ¼º´ÉÀ¸·Î 79%ÀÇ Á¤È®µµ¸¦ ´Þ¼ºÇßÀ½À» ¹ß°ßÇß´Ù. Áß¿äÇÑ °ÍÀº ÀÌ µµ±¸¸¦ »ç¿ëÇϸé 4ºÐ ¸¸¿¡ ȯÀÚ¸¦ Áø´Ü³»¸± ¼ö ÀÖ¾î ³úÁ¹Áß Áø´Ü¿¡ ±ÍÁßÇÑ ½Ã°£À» Àý¾àÇÒ ¼ö ÀÖ´Ù!

 

³úÁ¹ÁßÀÌ ÁøÇàµÇ´Â ¸ÅºÐ¸¶´Ù ¼ö¹é ¸¸ °³ÀÇ ´º·±ÀÌ Á׾±â ¶§¹®¿¡ ÀÌ°ÍÀº ¸Å¿ì Áß¿äÇÏ´Ù. ½ÉÇÑ ³úÁ¹ÁßÀÇ °æ¿ì ȯÀÚ°¡ ÀÀ±Þ½Ç¿¡ µé¾î°¡´Â ¼ø°£ºÎÅÍ ÀÇ»ç´Â ºÐ¸íÈ÷ ³úÁ¹ÁßÀ» ÀνÄÇÑ´Ù. ±×·¯³ª ¿¬±¸¿¡ µû¸£¸é ³úÁ¹ÁßÀÇ ´ëºÎºÐÀº ÃÖÁ¾ ÆÇÁ¤¿¡ ¾Õ¼± Áø´Ü °úÁ¤¿¡¼­ ¸î ½Ã°£ Áö¿¬µÉ ¼ö ÀÖÀ¸¸ç ±×¶§±îÁö ȯÀÚ´Â °¡´ÉÇÑ ÃÖ»óÀÇ Ä¡·á¸¦ ¹ÞÀ» ¼ö ¾ø´Ù. µû¶ó¼­ ³úÁ¹ÁßÀ» ÀÏÂï ½Äº°ÇÒ¼ö·Ï ȯÀÚ¿¡°Ô ´õ ÁÁÀº ¿É¼ÇÀÌ °¡´ÉÇÏ´Ù. À̸¦ À§Çؼ­´Â ³úÁ¹Áß Á¶±â Áø´ÜÀÌ ÇʼöÀÌ´Ù!

 

½Ã½ºÅÛÀÌ ³úÁ¹Áß Ãʱ⠴ܰ迡¼­ÀÇ Áø´ÜÀ» Çâ»ó½Ãų ¼ö ÀÖ´Ù¸é, ÇØ´ç ȯÀÚ´Â ÀûÀýÇÑ ¼öÁØÀÇ ¸®½ºÅ©¿¡¸¸ ³ëÃâµÇ°í º´¿øÀº ÀáÀçÀû ȯÀÚµéÀ» ³õÄ¡Áö ¾ÊÀ» °ÍÀÌ´Ù.

 

¿À´Ã³¯ ³úÁ¹Áß¿¡ ´ëÇÑ ÈǸ¢ÇÑ Ä¡·á¹ý, ÀǾàÇ° ¹× ÇÁ·Î¼¼½º°¡ ÀÖ´Ù. ±×·¯³ª ¿ì¸®´Â ¿©ÀüÈ÷ ¸Å¿ì ¿ø½ÃÀûÀÌ°í ºÎÁ¤È®ÇÑ Áø´ÜÀ» °¡Áö°í ÀÖ´Ù. ÀÌ »õ·Î¿î ½Ã½ºÅÛÀº ÀÌ·¯ÇÑ Áø´Ü °ÝÂ÷¸¦ ÇØ°áÇÏ´Â µ¥ ÀÏÁ¶¸¦ ÇÒ °ÍÀ¸·Î º¸ÀδÙ.

 

References
Penn State University
, October 2020, ¡°New tool can diagnose strokes with a smartphone,¡± by Jessica Hallman. © 2020 The Pennsylvania State University. All rights reserved.


To view or purchase this article, please visit:
https://news.psu.edu/story/636014/2020/10/20/research/new-tool-can-diagnose-strokes-smartphone
New tool can diagnose strokes with a smartphone chr(124)_pipe Penn State University (psu.edu)

A new tool has been created by researchers at Penn State and Houston Methodist Hospital.  It can diagnose a stroke with the accuracy of an emergency room physician within minutes based only on abnormalities in a patient¡¯s speech ability and facial muscular movements that are detected via interactions with a smartphone.

 

When a patient experiences the symptoms of a stroke, every minute counts.  But when it comes to diagnosing a stroke, emergency room physicians have limited options: send the patient for expensive and time-consuming radioactivity-based scans or call in a neurologist, who may not be immediately available to perform clinical diagnostic tests.

 

The team¡¯s novel approach is the first to identify the presence of stroke among actual emergency room patients suspected of stroke by using computational facial motion analysis and natural language processing to identify abnormalities in a patient¡¯s face or voice, such as a drooping cheek or slurred speech.

 

The results could help emergency room physicians to more quickly determine critical next steps for the patient.  This is one of the first applications of AI to help with stroke diagnosis in emergency settings.  And ultimately, the application could be utilized by caregivers or patients to make self-assessments before reaching the hospital.

 

To train the computer model, the researchers built a dataset from more than 80 patients experiencing stroke symptoms at Houston Methodist Hospital in Texas.  Each patient was asked to perform a speech test to analyze their speech and cognitive-communication while being recorded on an Apple iPhone.

 

The acquisition of facial data in natural settings makes this work robust and useful for real-world clinical applications, and ultimately empower this method for remote diagnosis of stroke and self-assessment.

 

Testing the model on the Houston Methodist dataset, the researchers found that its performance achieved 79 percent accuracy which is comparable to clinical diagnostics by emergency room doctors, who use additional tests such as CT scans.  Importantly, the tool could save valuable time in diagnosing a stroke, with the ability to assess a patient in as little as four minutes!

 

This is critical because there are millions of neurons dying every minute during a stroke.  In severe strokes, this is obvious to physicians from the moment the patient enters the emergency room, but studies suggest that in the majority of strokes, a diagnosis can be delayed by hours, and by that time a patient may not be eligible for the best possible treatments. The earlier you can identify a stroke, the better options (we have) for the patients. That¡¯s what makes an early diagnosis essential!

 

If the system can improve diagnostics at the front end, then the right patients can be exposed to the right levels of risk and hospitals will not miss patients who would potentially benefit.

 

Today there are great therapeutics, medicines, and procedures for strokes, but we still have very primitive and inaccurate diagnostics.  This new system is intended to address this diagnostic gap.

 

References
Penn State University
, October 2020, ¡°New tool can diagnose strokes with a smartphone,¡± by Jessica Hallman. © 2020 The Pennsylvania State University. All rights reserved.

 

To view or purchase this article, please visit:
https://news.psu.edu/story/636014/2020/10/20/research/new-tool-can-diagnose-strokes-smartphone
New tool can diagnose strokes with a smartphone chr(124)_pipe Penn State University (psu.edu)