Derivation and Validation of the Cancer READMIT Score: A Readmission Risk Scoring System for Patients With Solid Tumor Malignancies

Adult Cancer Patients' Perceptions of Factors That Influence Hospital Admissions

PURPOSE/AIMS

To explore cancer patients' perceptions of factors that influence hospital readmissions.

DESIGN

A cross-sectional, prospective design was employed utilizing a 1-time survey and brief interviews to measure patients' perceptions and unplanned hospital admissions.

METHODS AND VARIABLES

The principal investigator collected data from medical record review, the Hospital Admission Survey, and interviews to measure patient characteristics and perceptions of influencing factors that contributed to an unplanned hospital admission upon admission. Data were analyzed using descriptive statistics to categorize patient perceptions of influencing factors of unplanned hospital admissions.

RESULTS

The top reasons for admission were symptoms of uncontrolled gastrointestinal, pain, fever, and respiratory problems. The majority perceived the admission was unavoidable and wanted to avoid an admission. Perceived influencing factors were related to survey categories of 1) communication (ie, cannot reach physician anytime, cannot get a next-day appointment, medical problems are out of control, advised to go to the emergency department) and 2) home environment (ie, unable to adequately manage symptoms at home and hospital admission is the best place for care). Other survey categories of patient education and palliative care were not perceived as influencing or contributing factors.

CONCLUSIONS

These findings highlight opportunities for clinical nurse specialists to target these vulnerable patients and provide expert consultation to address potential barriers and gaps in utilization of appropriate supportive services that may reduce unplanned hospital admissions.

Thirty-Day Unplanned Hospital Readmissions in Patients With Cancer and the Impact of Social Determinants of Health: A Machine Learning Approach

PURPOSE

Develop a cancer-specific machine learning (ML) model that accurately predicts 30-day unplanned readmissions in patients with solid tumors.

METHODS

The initial cohort included patients 18 years or older diagnosed with a solid tumor. Two distinct cohorts were generated: one with and one without detailed social determinants of health (SDOHs) data. For each cohort, data were temporally partitioned in 70% (training), 20% (validation), and 10% (testing). Tree-based ML models were developed and validated on each cohort. The metrics used to evaluate the model's performance were receiver operating characteristic curve (ROC), area under the ROC curve, precision, recall (R), accuracy, and area under the precision-recall curve.

RESULTS

We included 13,717 patients in this study in two cohorts (5,059 without SDOH data and 8,658 with SDOH data). Unplanned 30-day readmission occurred in 21.3% of the cases overall. The five main non-SDOH factors most highly associated with an unplanned 30-day readmission (R, 0.74; IQR, 0.58-0.76) were: number of previous unplanned readmissions; higher Charlson comorbidity score; nonelective index admission; discharge to anywhere other than home, hospice, or nursing facility; and higher anion gap during the admission. Neighborhood crime index, neighborhood median home values, annual income, neighborhood median household income, and wealth index were the main five SDOH factors important for predicting a high risk for an unplanned hospital readmission (R, 0.66; IQR, 0.56-0.72). The models were not directly comparable.

CONCLUSION

Key drivers of unplanned readmissions in patients with cancer are complex and involve both clinical factors and SDOH. We developed a cancer-specific ML model that with reasonable accuracy identified patients with cancer at high risk for an unplanned hospital readmission.

Association Between Postdischarge Medical Oncology Follow-Up Appointments and Downstream Health Care Use: A Single-Institution Experience

PURPOSE:

There is limited understanding of the role of postdischarge medical oncology follow-up during care transition periods. Our study describes the care transition patterns and the association between postdischarge medical oncology appointments and downstream health care use at a tertiary academic center.

METHODS:

We conducted a retrospective cohort study of 25,135 medical oncology admissions between 2018 and 2020 at Yale New Haven Hospital. We examined the association between postdischarge medical oncology appointment timing with 30-day all-cause readmissions and emergency department (ED) visits using multivariable logistic regression models and propensity score–matched analyses.

RESULTS:

Compared with admissions without appointment within 30 days, admissions with postdischarge medical oncology appointment within 30 days were associated with lower rates of all-cause 30-day readmission (odds ratio [OR] = 0.56, 95% CI, 0.52 to 0.59; P < .001) and ED visit (OR = 0.56, 95% CI, 0.52 to 0.59; P < .001). Admissions with appointment ≤ 14 days were associated with lower rates of 30-day readmission (OR = 0.28, 95% CI, 0.25 to 0.32; P < .001) and ED visit (OR = 0.56, 95% CI, 0.52 to 0.63; P < .001) compared with those with appointment within 15-30 days. Similar patterns in health care use were seen with propensity score matching. Subgroup analyses of cancer types with the most admissions observed similar trends between 30-day readmission and ED visits with appointment timing.

CONCLUSION:

Timely postdischarge medical oncology appointments were associated with significantly lower likelihood of 30-day readmission and ED visits, suggesting a potential role for postdischarge follow-up as an intervention to decrease health care use.