Development and prospective validation of a model estimating risk of readmission in cancer patients

Abstract

An unplanned readmission risk model developed specifically for cancer patients performs well when validated prospectively. The specificity of the model for cancer patients, EMR incorporation, and prospective validation justify use of the model in future studies designed to reduce and prevent readmissions.

Vital Sign Abnormalities on Discharge Do Not Predict 30-Day Readmission

“…Studies have identified many risk factors for hospital readmission within 30 days, including age, race, lack of a regular health care provider, major surgery, medical comorbidities, length of hospital stay, previous admission(s) in the past year, failure to transfer critical information to the outpatient setting, premature hospital discharge, and the higher number of medications prescribed at hospital discharge. [4][5][6][7] Newer readmission risk models, such as the cancer specific model developed by Schmidt and colleagues 8 have acceptable predictive ability (C statistic = 0.70) and are superior to the clinical judgement of health care providers in identifying patients at the highest risk of hospital readmission. 8,9 General-purpose hospital readmission risk assessment models are diverse, ranging from in depth multidisciplinary patient interviews to more simplistic screening tool using a few variables.…”

“…[4][5][6][7] Newer readmission risk models, such as the cancer specific model developed by Schmidt and colleagues 8 have acceptable predictive ability (C statistic = 0.70) and are superior to the clinical judgement of health care providers in identifying patients at the highest risk of hospital readmission. 8,9 General-purpose hospital readmission risk assessment models are diverse, ranging from in depth multidisciplinary patient interviews to more simplistic screening tool using a few variables. 6,[10][11][12] These risk assessment models use factors such as illness severity, hospitalization in the past year, emergency department visits, age, ethnicity, and socioeconomic status to predict hospital readmissions.…”

Explainable Tree-Based Predictions for Unplanned 30-Day Readmission of Patients With Cancer Using Clinical Embeddings

“…A few studies have been conducted to identify the likelihood of unplanned readmission and the associated risk factors in general medicine and a variety of specialties. 13 , 20 , 21 , 23 - 34 With the advancement of artificial intelligence and computational technologies, more complex algorithms can be used, and the predictions become more individualized. For instance, using deep learning on a rich set of EHRs, Rajkomar et al 32 achieved approximately 10% AUROC improvement in predicting 30-day unplanned readmission at discharge than traditional approaches.…”

“…A more recent work using explainable gradient-boosted trees approach also achieved similar performance, with an AUROC of 0.76 and the ability to generate personalized predictions. 13 For oncological models, Schmidt et al 21 were the first to develop a statistical model using logistic regression with validation c-statistics of 0.70. However, the prospective analysis was descriptive, and no prospective predictive performance was reported.…”

“…We assigned input features into three groups: baseline factors, discharge factors, and clinical embeddings. The features were identified based on the literature 13 , 19 - 21 and potential clinical relevance. In the first group, we identified multiple baseline factors that are typically available shortly (within 24 hours) after admission: age at admission, gender, number of admissions to the study institution in the past 6 months, presence of emergency treatment center visit to the study institution in the past 30 days, service line (admission department: hematology, medical oncology, surgery, and others), primary insurance (MEDICARE, MEDI-CAL, and others), and bone marrow transplant type (allogeneic or autologous for hematology only).…”