BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:ORIE Colloquium: Hamsa Sridhar Bastani (Stanford) - Data-Drive
 n Operations and Incentives in Healthcare
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260907T235635Z
UID:tag:localist.com\,2008:EventInstance_1721491
DTSTART:20151218T160000Z
DTEND:20151218T170000Z
DESCRIPTION:We present two papers motivated by rising concerns about health
 care quality and costs.\n \nFirst\, we introduce a new statistical decisio
 n-making algorithm to enable medical decision-makers to personalize treatm
 ent choices at the individual-level and thereby improve patient outcomes. 
 We formulate this problem as a multi-armed bandit with high-dimensional co
 variates\, and present a new efficient bandit algorithm based on the LASSO
  estimator. Our regret analysis establishes that our algorithm achieves ne
 ar-optimal performance\; the key step is proving a new oracle inequality t
 hat guarantees the convergence of the LASSO estimator despite the non-i.i.
 d. data induced by the bandit policy. We evaluate our algorithm on the rea
 l-world clinical problem of warfarin dosing. Our algorithm outperforms exi
 sting bandit methods as well as physicians to correctly dose a majority of
  patients.\n \nSecond\, Medicare has initiated several pay-for-performance
  mechanisms to encourage medical decision-makers to adopt such data-driven
  methods for improving patient outcomes. However\, these initiatives may b
 e undermined if hospitals engage in upcoding\, the practice of mis-reporti
 ng patient outcomes to increase reimbursement. We empirically estimate tha
 t over 11\,000 hospital-acquired infections are upcoded a year\, drawing i
 nto question the effectiveness and fairness of Medicare’s pay-for-perfor
 mance initiatives. We make several policy recommendations based on our res
 ults.
GEO:42.443451;-76.481506
LOCATION:Frank H. T. Rhodes Hall\, 253
SUMMARY:ORIE Colloquium: Hamsa Sridhar Bastani (Stanford) - Data-Driven Ope
 rations and Incentives in Healthcare
URL;VALUE=URI:https://events.cornell.edu/event/orie_colloquium_hamsa_sridha
 r_bastani_stanford_
CATEGORIES:Seminar
END:VEVENT
END:VCALENDAR