Preoperatively predicting non-home discharge after surgery for gynecologic malignancy

Abstract

Objective: Returning home after surgery is a desirable patient-centered outcome associated with decreased costs compared to non-home discharge. Our objective was to develop a preoperative risk-scoring model predicting non-home discharge after surgery for gynecologic malignancy.

Methods: Women who underwent surgery involving hysterectomy for gynecologic malignancy from 2013 to 2015 were identified from the Michigan Surgical Quality Collaborative database. Patients were divided by discharge destination, and a multivariable logistic regression model was developed to create a nomogram to assign case-specific risk scores. The model was validated using the National Surgical Quality Improvement Program (NSQIP) database.

Results: Non-home discharge occurred in 3.1% of 2134 women. The proportion of non-home discharges did not differ by cancer diagnosis (uterine 3.5%, ovarian 2.5%, and cervical 1.6%, p = 0.2). Skilled nursing facilities were the most common non-home destination (68.2%). Among patients with comorbidities (hypertension, diabetes, coronary artery disease, chronic obstructive pulmonary disease /dyspnea, arrhythmia, and history of deep vein thrombosis/pulmonary embolism), non-home discharge was more common in women with 1 (adjusted OR [aOR] 3.4; p = 0.03) or ≥2 of these comorbidities (aOR 5.1; p = 0.003) compared to none. Non-home discharge was more common after laparotomy (aOR 6.7; p < 0.0001) than laparoscopy, and in those aged ≥70 years (aOR 3.4; p < 0.0001) with American Society of Anesthesiologists class ≥ 3 (aOR 4.5; p = 0.0004) and dependent functional status (aOR 8.7; p < 0.0001). The model C-statistic was 0.89. When the model was applied to 4248 eligible patients from the NSQIP dataset, the C-statistic was 0.84 (95% CI: 0.79-0.89).

Conclusions: Non-home discharge after surgery for gynecologic malignancy was predicted with high accuracy in this retrospective analysis.

Keywords: Discharge destination; Gynecologic malignancy; Hysterectomy; Prediction; Risk model.