BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:US/Central
BEGIN:DAYLIGHT
DTSTART:20190310T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20191103T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190916T210240Z
UID:77737E70-8449-41D0-8155-600CE0A3CA7F
DTSTART;TZID=US/Central:20190814T153000
DTEND;TZID=US/Central:20190814T170000
DESCRIPTION:Digitalize human beings using biosensors to track our complex p
 hysiologic system\, process the large amount of data generated with artifi
 cial intelligence (AI) and change clinical practice towards individualized
  medicine: these are the goals of digital medicine. At Scripps\, we are a 
 team of computer scientists\, engineers\, and clinical researchers\, in pa
 rtnership with health industries\, and we propose new solutions to analyze
  large longitudinal data using statistical learning and deep convolutional
  neural networks to address different cardiovascular health issues.\n\nOne
  of the greatest contributors to premature mortality worldwide is hyperten
 sion. Lowering blood pressure (BP) by just a few mmHg can bring substantia
 l clinical benefits\, but it is hard to assess the “true” BP for an in
 dividual\, since it fluctuates significantly. With a dataset of 16 million
  BP measurements\, we unveil the BP patterns and provide insights on the c
 linical relevance of these changes.\n\nAnother prevalent health issue is a
 trial fibrillation (AF)\, the most common sustained cardiac arrhythmia\, a
 ssociated with stroke\, heart failure and coronary artery disease. AF dete
 ction from single-lead electrocardiography (ECG) recordings is still an op
 en problem\, as AF events may be episodic and the signal noisy. We conduct
  a thoughtful analysis of recent convolutional neural network architecture
 s developed in the computer vision field\, redesigned to be suitable for a
  one-dimensional signal\, and we evaluate their performance in the detecti
 on of AF using 200 thousand seconds of ECG\, highlighting the potential an
 d pitfall of this technology.\n\nLooking to the future\, we investigate ne
 w applications for wearable devices and advanced processing in the All of 
 Us Research Program\, an unprecedented research effort to gather data from
  one million people in the USA to accelerate the advent of precision medic
 ine.\n\nCo-sponsored by: CH04120 - Madison Section Chapter\,EMB18\n\nSpeak
 er(s): Dr Giorgio Quer\, \n\nRoom: Conference Room 104\, Bldg: Madison Cen
 tral Library\, 201 W Mifflin St\, Madison\, Wisconsin\, United States\, 53
 703
LOCATION:Room: Conference Room 104\, Bldg: Madison Central Library\, 201 W 
 Mifflin St\, Madison\, Wisconsin\, United States\, 53703
ORGANIZER:tothnj@ieee.org
SEQUENCE:5
SUMMARY:Machine Learning in Digital Medicine
URL;VALUE=URI:https://events.vtools.ieee.org/m/202521
X-ALT-DESC:Description: <br /><p>Digitalize human beings using biosensors t
 o track our complex physiologic system\, process the large amount of data 
 generated with artificial intelligence (AI) and change clinical practice t
 owards individualized medicine: these are the goals of digital medicine. A
 t Scripps\, we are a team of computer scientists\, engineers\, and clinica
 l researchers\, in partnership with health industries\, and we propose new
  solutions to analyze large longitudinal data using statistical learning a
 nd deep convolutional neural networks to address different cardiovascular 
 health issues.</p>\n<p>One of the greatest contributors to premature morta
 lity worldwide is hypertension. Lowering blood pressure (BP) by just a few
  mmHg can bring substantial clinical benefits\, but it is hard to assess t
 he &ldquo\;true&rdquo\; BP for an individual\, since it fluctuates signifi
 cantly. With a dataset of 16 million BP measurements\, we unveil the BP pa
 tterns and provide insights on the clinical relevance of these changes.</p
 >\n<p>Another prevalent health issue is atrial fibrillation (AF)\, the mos
 t common sustained cardiac arrhythmia\, associated with stroke\, heart fai
 lure and coronary artery disease. AF detection from single-lead electrocar
 diography (ECG) recordings is still an open problem\, as AF events may be 
 episodic and the signal noisy. We conduct a thoughtful analysis of recent 
 convolutional neural network architectures developed in the computer visio
 n field\, redesigned to be suitable for a one-dimensional signal\, and we 
 evaluate their performance in the detection of AF using 200 thousand secon
 ds of ECG\, highlighting the potential and pitfall of this technology.</p>
 \n<p>Looking to the future\, we investigate new applications for wearable 
 devices and advanced processing in the All of Us Research Program\, an unp
 recedented research effort to gather data from one million people in the U
 SA to accelerate the advent of precision medicine.</p>
END:VEVENT
END:VCALENDAR