RESUMO
Objective: Build and validate a clinical decision support (CDS) algorithm for discharge decisions regarding referral for post-acute care (PAC) and to what site of care. Materials and Methods: Case studies derived from EHR data were judged by 171 interdisciplinary experts and prediction models were generated. Results: A two-step algorithm emerged with area under the curve (AUC) in validation of 91.5% (yes/no refer) and AUC 89.7% (where to refer). Discussion: CDS for discharge planning (DP) decisions may remove subjectivity, and variation in decision-making. CDS could automate the assessment process and alert clinicians of high need patients earlier in the hospital stay. Conclusion: Our team successfully built and validated a two-step algorithm to support discharge referral decision-making from EHR data. Getting patients the care and support they need may decrease readmissions and other adverse events. Further work is underway to test the effects of the CDS on patient outcomes in two hospitals.
Assuntos
Algoritmos , Registros Eletrônicos de Saúde , Registros de Enfermagem , Alta do Paciente , Encaminhamento e Consulta , Cuidados Semi-Intensivos , Idoso , Área Sob a Curva , Tomada de Decisões , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Análise de RegressãoRESUMO
Objective: Compare patient characteristics and acute healthcare utilization between patients identified as in need of post-acute care (PAC) by the clinical decision support (CDS) algorithm yet were discharged home without services, to those where the CDS and hospital clinicians agreed on no referral. Methods: Retrospective analysis of hospital administrative and clinical data for 1,366 patients. Results: 30-day acute healthcare utilization rates are significantly higher for those patients flagged as in need of PAC referral. There are also significant differences in patient characteristics based on referral risk. Discussion: Clinicians were blinded to the algorithm enabling the comparison of usual care to decision support. Future work will examine the effect of sharing algorithm advice with clinicians on PAC referral rates and utilization. Conclusion: The CDS algorithm clearly identified patients with high-risk characteristics and those who will go on to utilize acute care resources. Providing CDS to discharge planners may improve patient outcomes.