AI-Prioritized Pharmacist Review to Reduce Preventable Hospital Readmissions in Diabetes Care

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.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-17
DOI
https://doi.org/10.5281/zenodo.24304172
Primary Topic
Pharmaceutical Practices and Patient Outcomes
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

AI-Prioritized Pharmacist Review to Reduce Preventable Hospital Readmissions in Diabetes Care

Nezar Abdilah Prakasa
2 links
Zenodo (CERN European Organization for Nuclear Research)
Pharmaceutical Practices and Patient Outcomes
preprint

AI-Prioritized Pharmacist Review to Reduce Preventable Hospital Readmissions in Diabetes Care

Nezar Abdilah Prakasa
preprint en

Abstract

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.

Zenodo (CERN European Organization for Nuclear Research)
Good health and well-being
Pharmaceutical Practices and Patient Outcomes
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon