Answers are grounded in this paper and cite their sources.
Hospital pharmacists cannot personally review every discharging patient for medication-related readmission risk; time is limited and risk is unevenly distributed. This paper presents an AI prioritization model, trained on 101,766 real hospital encounters from 130 US hospitals, that identifies the 20% of patients most likely to be readmitted within 30 days. This flagged group has a 19.54% readmission rate versus 11.16% overall (a 1.75x concentration of risk) and captures 35.0% of all readmissions despite being only one-fifth of patients. Flagged patients also carry a higher medication burden (16.9 vs 15.9 medications on average) and more prior hospitalizations, both directly actionable by a pharmacist at discharge. Combining this targeting with a published reduction in readmissions from pharmacist-led discharge medication reconciliation (27%) and the AHRQ-reported average cost of a 30-day readmission (USD 16,300), this framework suggests an estimated USD 1.72M to USD 13.75M in avoided annual cost depending on regional patient volume. Limitations and an implementation plan are discussed.
No takes yet. Share an insight, caveat, or question.
Nezar Abdilah Prakasa (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: