Higher quality and lower cost from improving hospital discharge decision making

Abstract

This paper reports research on improving decisions about hospital discharges – decisions that are now made by physicians based on mainly subjective evaluations of patients’ discharge status. We report an experiment on uptake of our clinical decision support software (CDSS) which presents physicians with evidence-based discharge criteria that can be effectively utilized at the point of care where the discharge decision is made. One experimental treatment we report prompts physician attentiveness to the CDSS by replacing the default option of universal “opt in” to patient discharge with the alternative default option of “opt out” from the CDSS recommendations to discharge or not to discharge the patient on each day of hospital stay. We also report results from experimental treatments that implement the CDSS under varying conditions of time pressure on the subjects. The experiment was conducted using resident physicians and fourth-year medical students at a university medical school as subjects.

Incentivizing cost-effective reductions in hospital readmission rates

“…The EMR+CDSS treatment significantly decreases readmissions compared to the EMR treatment. This finding is consistent with the research findings of Cox, et al (2014).…”

“…Using a three-by-two experimental design defined over three payment mechanisms (fee-for-service, bonus and bundled payments) and two information conditions (EMR and EMR+CDSS), our research indicates that the P4P mechanisms used in our experiment combined with the clinical decision support system (Cox et al 2014) can be used to make more cost-effective and evidence-based hospital discharge decisions. The largest reduction in average LOS resulted from the bundled payment mechanisms combined with the CDSS information, where the LOS fell by nearly two days.…”

“…The probit econometric model used to construct the clinical decision support system developed in Cox, et al (2014) provided an anchoring point for the experimental data by providing an objective measure of when a patient should be discharged regardless of the P4P mechanism utilized. Given the heterogeneity in the risk types among the 30 patient records used in the experiment we randomly selected the first experimental day on which the subject was asked to make a discharge decision to be between one and four days before the first day that the patient should have been discharged according to the decision support system.…”

“…Experiment 2 was conducted in an environment that included the clinical decision support system (CDSS) described in Cox, et al (2014). In addition to the EMR information presented to subjects in Experiment 1, the information presented to subjects in Experiment 2 included the CDSS information screens and dynamically updated recommendations on whether to discharge a patient on each “experiment day” which corresponded to a 24 hour day in the electronic medical record for a patient.…”

“…The CDSS makes one of three recommendations for each patient on each experiment day: (1) do not discharge the patient, (2) physician judgment, or (3) discharge the patient. Information and discharge recommendation screens for the CDSS are shown in Cox, et al (2014). 24 …”