BEGIN:VCALENDAR
PRODID:-//github.com/ical-org/ical.net//NONSGML ical.net 4.0//EN
VERSION:2.0
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20241103T020000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250309T020000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DESCRIPTION:Program: Health Informatics Information Technology Session: Bi
 g Data HIIT Poster Session 1 Author: Debbie Humphries See all authors and
  presenters → Abstract Background Hospital-based secondary prevention red
 uces morbidity and mortality from patient deterioration. Traditional scor
 ing systems\, including Systemic Inflammatory Response Syndrome (SIRS)\, 
 Modified Early Warning Score (MEWS)\, Quick Sequential Organ Failure Asse
 ssment (qSOFA)\, and Sequential Organ Failure Assessment (SOFA)\, have va
 riable success. Artificial intelligence (AI) may improve these strategies
  by identifying subtle physiological trends\, allowing early intervention
 s preventing deterioration. Objective Evaluate an AI-based alert system’s
  performance in detecting patient deterioration compared to traditional s
 coring methods and explore how AI integration could improve secondary pre
 vention. Methods A retrospective analysis was conducted on hospitalized p
 atient data flagged by an AI system designed to predict clinical deterior
 ation and intensive care unit (ICU) admission within 24 hours. The AI mon
 itored vital signs (temperature\, heart rate\, blood pressure\, respirato
 ry rate) and laboratory parameters. To validate AI alerts\, we retrospect
 ively calculated SIRS\, MEWS\, qSOFA\, and SOFA scores at the time alerts
  occurred. Predictive performance (accuracy\, precision\, recall\, F1-sco
 re) for ICU admissions was compared. Pearson correlations assessed relati
 onships between vital signs and ICU outcomes. Results Of AI-flagged patie
 nts\, 42.9% required ICU admission\, with alerts occurring on average 22.
 2 hours prior. SIRS and MEWS each demonstrated 78.6% accuracy\, 71.4% pre
 cision\, and 83.3% recall\; qSOFA showed higher precision (100%) but lowe
 r recall (50%). Temperature negatively correlated (-0.532)\, while heart 
 rate positively correlated (0.300) with ICU admission. Discussion/Conclus
 ions The AI alert enabled earlier detection than traditional indices alon
 e\, potentially facilitating earlier interventions and improved resource 
 allocation. Integrating AI into existing clinical scoring can strengthen 
 secondary prevention efforts and enhance patient care quality.\n\nSpeaker
 :\nDebbie Humphries\n\nAdmission:\nRegistrationFees: APHA Event Registrat
 ion is Required\n\nDetails URL:\nhttps://medicine.yale.edu/event/evaluati
 ng-an-artificial-intelligence-alert-system-for-early-detection-of-patient
 -deterioration/\n
DTEND;TZID=America/New_York:20251104T113000
DTSTAMP:20260514T223514Z
DTSTART;TZID=America/New_York:20251104T103000
GEO:38.903500;-77.022987
LOCATION:801 Allen Y Lew Pl NW\, Washington\, DC\, United States
SEQUENCE:0
STATUS:Confirmed
SUMMARY:4081.0 - Evaluating an artificial intelligence alert system for ea
 rly detection of patient deterioration: A secondary prevention approach i
 n hospital care
UID:c3e68837-4e6c-40c3-b3fa-89034ff06e5d
END:VEVENT
END:VCALENDAR