Automated controlled-case studies and root-cause analysis for hospital quality improvement

12051,024

15/756596

August 25, 2016

A risk-adjusted assessment of a target facility's quality measures (e.g. mortality rate, length of stay, readmission rate, complications rate, etc.) is determined with respect to the quality measures of a broader population base. Patient cohorts are identified corresponding to particular ailments or treatments, and the target facility's risk-adjusted quality measures are determined for each cohort. When a particular quality measure for a target cohort indicates poor performance, factors that are determined to be relevant to the patients' outcomes are identified and used to create a control group of patients in the broader population who exhibit similar factors but had better outcomes than the patients of the target cohort. The care process (treatments, medications, interventions, etc.) that each of the target patients received is compared to the care process that each of the control patients received, to identify potential root-causes of the poorer performance.

KONINKLIJKE PHILIPS N.V. (Eindhoven, NL)

KONINKLIIJKE PHILIPS N.V. (Eindhoven, NL)

1. A method for generating one or more recommendations for improved performance to a medical facility using a medical performance analysis system, comprising: generating a predictive model based on electronic medical records of patients of a general population, the electronic medical records received from a plurality of other medical facilities, the predictive model configured to receive patient characteristics for each target patient of a target patient group and provide a predicted outcome for each target patient; determining, for the target patient group and a target ailment, whether a medical facility's outcomes are abnormal based on a risk-adjusted score for each of a plurality of quality measures compared to patient outcomes at a plurality of other medical facilities, wherein the determination is based on the performance model and the predicted outcome for each patient of the target patient group, and wherein the plurality of quality measures includes mortality rate, length of stay, complication rate, and infection rate; determining relevant patient factors from a plurality of patient factors that characterize the target patient group; selecting, based on the relevant patient factors, one or more other patients that experienced better outcomes than the target patient group; identifying one or more differences in treatment between the one or more other patients and the target patient group; generating one or more recommendations for improved performance by the medical facility based on the identified differences in treatment, wherein the recommendation comprises a display of a plurality of quality measures for the medical facility, wherein the quality measures comprise an indication of the medical facility's performance relative to the performance of the plurality of medical facilities, and further wherein the provided one or more recommendations for improved performance comprises a recommendation to administer a beta blocker; providing, via the display, the one or more recommendations for improved performance, comprising optionally providing a presentation of the medical facility's outcomes compared to the outcomes at the plurality of other medical facilities; and administering, by one or more clinicians of the medical facility, the provided one or more recommendations for improved performance, comprising administrating, by one or more clinicians of the medical facility, a beta blocker to one or more target patients of the target patient group.

2. The method of claim 1 , wherein identifying one or more differences in treatment between the one or more other patients and the target patient group comprises determining a relative impact of potential performance improvements at the medical facility with regard to the target patient group, based on a relative volume of the target patient group.

3. The method of claim 1 , further comprising identifying a similarity factor for each patient with the target ailment in the plurality of other facilities compared to the target patients, wherein said selecting step further comprises selecting one or more other patients based on the identified similarity factors.

7353238 April 2008 Gliklich
7617115 November 2009 McNair
8620690 December 2013 Hu et al.
8762169 June 2014 Mohlenbrock et al.
20050261941 November 2005 Scarlat
20070244724 October 2007 Pendergast et al.
20080154637 June 2008 Capelli et al.
20090119130 May 2009 Kimmel
20130262360 October 2013 Geleijnse
20130304499 November 2013 Rangadass
20140088990 March 2014 Nawana
20140236630 August 2014 Murata
20140244295 August 2014 Carroll et al.
20140324472 October 2014 Delaney
20150032467 January 2015 Rapp
20150213223 July 2015 Amarasingham

A predictive analytics approach to reducing 30-day avoidable readmissions among patients, Issac Shams, Healthcare Systems Engineering Group, Wayne State University, Detroit, MI 48201 (Year: 2015). cited by examiner
Horwitz et al. “Hospital-wide (all-condition) 30-day risk-standardized readmission measure”, Yale New Haven Health Services Corporation/Center for Outcomes Research & Evaluation, Retrieved Sep. 10, 2011: 2012. cited by applicant
Norén, G. Niklas, et al. “Temporal pattern discovery in longitudinal electronic patient records”, Data Mining and Knowledge Discovery 20.3 (2010): 361-387. cited by applicant
M. Markatou, et al., “Case-based reasoning in comparative effectiveness research”, IBM Journal of Research and Development, vol. 56, issue 5, 2012. cited by applicant
Fritsche, L., et al. “Recognition of critical situations from time series of laboratory results by case-based reasoning”, Journal of the American Medical Informatics Association 9.5 (2002): 520-528. cited by applicant
Fisher, Elliott S., et al. “The implications of regional variations in Medicare spending. Part 1: the content, quality, and accessibility of care.” Annals of internal medicine 138.4 (2003): 273-287. cited by applicant

edspgr.12051024