Dynamic readmission prediction using routine postoperative laboratory results after radical cystectomy.

OBJECTIVE: To determine if the addition of electronic health record data enables better risk stratification and readmission prediction after radical cystectomy. Despite efforts to reduce their frequency and severity, complications and readmissions following radical cystectomy remain common. Leveraging readily available, dynamic information such as laboratory results may allow for improved prediction and targeted interventions for patients at risk of readmission. METHODS: We used an institutional electronic medical records database to obtain demographic, clinical, and laboratory data for patients undergoing radical cystectomy. We characterized the trajectory of common postoperative laboratory values during the index hospital stay using support vector machine learning techniques. We compared models with and without laboratory results to assess predictive ability for readmission. RESULTS: Among 996 patients who underwent radical cystectomy, 259 patients (26%) experienced a readmission within 30 days. During the first week after surgery, median daily values for white blood cell count, urea nitrogen, bicarbonate, and creatinine differentiated readmitted and nonreadmitted patients. Inclusion of laboratory results greatly increased the ability of models to predict 30-day readmissions after cystectomy. CONCLUSIONS: Common postoperative laboratory values may have discriminatory power to help identify patients at higher risk of readmission after radical cystectomy. Dynamic sources of physiological data such as laboratory values could enable more accurate identification and targeting of patients at greatest readmission risk after cystectomy. This is a proof of concept study that suggests further exploration of these techniques is warranted.

The Fate of Radical Cystectomy Patients after Hospital Discharge: Understanding the Black Box of the Pre-readmission Interval.

BACKGROUND: Radical cystectomy has one of the highest 30-d hospital readmission rates but circumstances leading to readmission remain poorly understood. OBJECTIVE: To examine the postdischarge period and better understand hospital readmission after radical cystectomy. DESIGN, SETTING, AND PARTICIPANTS: We conducted a retrospective cohort study of patients treated with radical cystectomy for bladder cancer from 2005 to 2012 using our institutional database. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: We assessed patient communication with any healthcare system after hospital discharge based on timing, methods, and concern types. Logistic regression and Cox proportional-hazards analyses were used to compare postdischarge concerns among readmitted and nonreadmitted patients. We internally validated the logistic model using a bootstrap resampling technique. RESULTS AND LIMITATIONS: One-hundred patients (23%) were readmitted within 30 d of index discharge. Readmitted patients were more likely to use the emergency department with initial concerns compared with nonreadmitted patients (27% vs 1.0%, p<0.001). Patients who took longer to first communicate their concerns and who were able to tolerate their symptoms longer had lower odds of readmission. Patients who reported infection (adjusted hazard ratio: 2.8, 95% confidence interval: 1.4-5.8) and failure to thrive concerns (adjusted hazard ratio: 4.4, 95% confidence interval: 2.0-9.3) were more likely to be readmitted compared with those who communicated noninfectious wounds and/or urinary concerns. CONCLUSIONS: Radical cystectomy patients who contact the health system soon after discharge or communicated infectious or failure to thrive symptoms (fever, poor oral intake, or vomiting) are more likely to experience readmission as opposed to those that endorse pain, constipation, or ostomy issues. Better understanding of this pre-readmission interval can optimize postdischarge practices. PATIENT SUMMARY: We looked at bladder cancer patients who had surgery and the reasons why they were readmitted to hospital. We found patients who had a fever or difficulty with eating and maintaining their weight had the highest chance of being readmitted.