Predicting delayed discharge in a multimodal Enhanced Recovery Pathway

Developing a decision support tool to predict delayed discharge from hospitals using machine learning

BACKGROUND

The growing demand for healthcare services challenges patient flow management in health systems. Alternative Level of Care (ALC) patients who no longer need acute care yet face discharge barriers contribute to prolonged stays and hospital overcrowding. Predicting these patients at admission allows for better resource planning, reducing bottlenecks, and improving flow. This study addresses three objectives: identifying likely ALC patients, key predictive features, and preparing guidelines for early ALC identification at admission.

METHODS

Data from Nova Scotia Health (2015-2022) covering patient demographics, diagnoses, and clinical information was extracted. Data preparation involved managing outliers, feature engineering, handling missing values, transforming categorical variables, and standardizing. Data imbalance was addressed using class weights, random oversampling, and the Synthetic Minority Over-Sampling Technique (SMOTE). Three ML classifiers, Random Forest (RF), Artificial Neural Network (ANN), and eXtreme Gradient Boosting (XGB), were tested to classify patients as ALC or not. Also, to ensure accurate ALC prediction at admission, only features available at that time were used in a separate model iteration.

RESULTS

Model performance was assessed using recall, F1-Score, and AUC metrics. The XGB model with SMOTE achieved the highest performance, with a recall of 0.95 and an AUC of 0.97, excelling in identifying ALC patients. The next best models were XGB with random oversampling and ANN with class weights. When limited to admission-only features, the XGB with SMOTE still performed well, achieving a recall of 0.91 and an AUC of 0.94, demonstrating its effectiveness in early ALC prediction. Additionally, the analysis identified diagnosis 1, patient age, and entry code as the top three predictors of ALC status.

CONCLUSIONS

The results demonstrate the potential of ML models to predict ALC status at admission. The findings support real-time decision-making to improve patient flow and reduce hospital overcrowding. The ALC guideline groups patients first by diagnosis, then by age, and finally by entry code, categorizing prediction outcomes into three probability ranges: below 30%, 30-70%, and above 70%. This framework assesses whether ALC status can be accurately predicted at admission or during the patient's stay before discharge.

Obstetric and medical factors rather than psychosocial characteristics explain why eligible women do not complete the enhanced recovery after elective caesarean (EREC) pathway: A prospective cohort study

BACKGROUND

An Australian health-service implemented an 'enhanced recovery after elective caesarean' pathway with next-day discharge.

PROBLEM

Previous anecdotal reports indicated that a large percentage of eligible women were not discharged the next day and therefore were not regarded as having completed the pathway. Psychosocial factors were expected to be the leading reason for prolonged hospitalisation.

AIM

The study objectives were to: enumerate the percentage of women assessed as eligible for EREC who subsequently did not complete the pathway and the reasons; and to describe women's antenatal satisfaction with preparation, preferences, and perceived support. Women who completed the pathway versus those who did not were compared on antenatal biopsychosocial characteristics.

METHODS

This exploratory prospective cohort study enrolled consenting eligible women from antenatal clinics and used patient records and questionnaire data. Comparative statistical techniques were used.

FINDINGS

62 % of women did not complete the pathway, with medical and obstetric factors being the most common reasons (80 %). There was statistically significant evidence of lower antenatal stress levels for those who completed EREC (median=5) relative to those who did not (median=8; P = 0.035); although these findings may not be of clinical importance. Antenatally, 51 % of women felt prepared for early discharge, 36 % needed more information, 19 % disliked hospital, 93 % agreed that family togetherness after birth was important. Most agreed that staff (76 %) and family (67 %) supported the pathway.

CONCLUSION

This study indicated that a large percentage of women assessed as eligible did not complete EREC and that obstetric and medical factors, rather than psychosocial characteristics, largely explained this. This provides reassurance to clinicians and women that discharge home is working as intended and is useful for planning similar models of care. Higher stress levels in the antenatal period were demonstrated for women who did not complete EREC suggesting the need for further research into how to support these women.

The association of social vulnerability with colorectal enhanced recovery program failure

Background

Enhanced recovery programs (ERPs) improve outcomes, but over 20 % of patients fail ERP and the contribution of social vulnerability is unknown. This study aimed to characterize the association between social vulnerability and ERP adherence and failure.

Methods

This was a retrospective cohort study of colorectal surgery patients between 2015 and 2020 utilizing ACS-NSQIP data. Patients who failed ERP (LOS > 6 days) were compared to patients not failing ERP. The CDC's social vulnerability index (SVI) was used to assess social vulnerability.

Result

273 of 1191 patients (22.9 %) failed ERP. SVI was a significant predictor of ERP failure (OR 4.6, 95 % CI 1.3-16.8) among those with >70 % ERP component adherence. SVI scores were significantly higher among patients non-adherent with 3 key ERP components: preoperative block (0.58 vs. 0.51, p < 0.01), early diet (0.57 vs. 0.52, p = 0.04) and early foley removal (0.55 vs. 0.50, p < 0.01).

Conclusions

Higher social vulnerability was associated with non-adherence to 3 key ERP components as well as ERP failure among those who were adherent with >70 % of ERP components. Social vulnerability needs to be recognized, addressed, and included in efforts to further improve ERPs.

Key message

Social vulnerability is associated with non-adherence to enhanced recovery components and ERP failure among those with high ERP adherence. Social vulnerability needs to be addressed in efforts to improve ERPs.

ECCO Topical Review: Roadmap to Optimal Peri-Operative Care in IBD

BACKGROUND AND AIMS

Despite the advances in medical therapies, a significant proportion of patients with inflammatory bowel diseases [IBD] require surgical intervention. This Topical Review aims to offer expert consensus practice recommendations for peri-operative care to optimize outcomes of IBD patients who undergo surgery.

METHODS

A multidisciplinary panel of IBD healthcare providers systematically reviewed aspects relevant to peri-operative care in IBD. Consensus statements were developed using Delphi methodology.

RESULTS

A total of 20 current practice positions were developed following systematic review of the current literature covering use of medication in the peri-operative period, nutritional assessment and intervention, physical and psychological rehabilitation and prehabilitation, and immediate postoperative care.

CONCLUSION

Peri-operative planning and optimization of the patient are imperative to ensure favourable outcomes and reduced morbidity. This Topical Review provides practice recommendations applicable in the peri-operative period in IBD patients undergoing surgery.

Impact of Urinary Catheterization on Postoperative Outcomes After Roux-En-Y Gastric Bypass Surgery in Propensity-Matched Cohorts

BACKGROUND

The impact of urinary catheter avoidance in bariatric enhanced recovery after surgery (ERAS) protocols is yet to be established. The purpose of the current study is to determine whether urinary catheter use in patients undergoing Roux-en-Y gastric bypass (RYGB) procedures has an effect on postoperative outcomes.

METHODS

An institutional database was utilized to identify adult patients undergoing primary minimally invasive RYGB surgery. Outcomes included incidence of urinary tract infection (UTI) within 30 days postoperatively, 30-day readmission rates, proportion of patients discharged after postoperative day 1 (delayed discharge), length of stay (LOS), and operating room time. These were compared between propensity-matched groups with and without urinary catheter placement.

RESULTS

There were no significant differences in postoperative UTI's (2.2% for both cohorts, P = .593) or 30-day readmission rates for patients with and without urinary catheters (6.6% and 4.4%, respectively, P = .260). Mean LOS (1.7 vs. 1.5 days, P = .001) and the proportion of patients having a delayed discharge (47.3% vs. 33.7%, P = .001) was greater in patients with a catheter. Operating room time was longer in the urinary catheter group (221.8 vs. 207.9 minutes, P = .002).

DISCUSSION

Avoidance of indwelling urinary catheters in RYGB surgical patients decreased delayed discharges and LOS without affecting readmission or reoperation rates. Therefore, we recommend that avoidance of urinary catheters in routine RYGB surgery be considered for inclusion into standardized ERAS protocols. Urinary catheters should continue to be utilized in select cases, however, as these were not shown to affect rate of UTIs.

Inflammatory Bowel Diseases Benefit from Enhanced Recovery After Surgery [ERAS] Protocol: A Systematic Review with Practical Implications

BACKGROUND

Enhanced Recovery After Surgery [ERAS] is widely adopted in patients undergoing colorectal surgery, with demonstrated benefits. Few studies have assessed the feasibility, safety, and effectiveness of ERAS in patients with inflammatory bowel diseases [IBD]. The aim of this study was to investigate the current adoption and outcomes of ERAS in IBD.

METHODS

This PRISMA-compliant systematic review of the literature included all articles reporting on adult patients with IBD who underwent colorectal surgery within an ERAS pathway. PubMed/MEDLINE, Cochrane Library, and Web of Science were searched. Endpoints included ERAS adoption, perioperative outcomes, and ERAS items more consistently reported, with associated evidence levels [EL] [PROSPERO CRD42021238653].

RESULTS

Out of 217 studies, 16 totalling 2347 patients were included. The median number of patients treated was 50.5. Malnutrition and anaemia optimisation were only included as ERAS items in six and four articles, respectively. Most of the studies included the following items: drinking clear fluids until 2 h before the surgery, fluid restriction, nausea prophylaxis, early feeding, and early mobilisation. Only two studies included postoperative stoma-team and IBD-team evaluation before discharge. Highest EL were observed for ileocaecal Crohn's disease resection [EL2]. Median in-hospital stay was 5.2 [2.9-10.7] days. Surgical site infections and anastomotic leaks ranged between 3.1-23.5% and 0-3.4%, respectively. Complications occurred in 5.7-48%, and mortality did not exceed 1%.

CONCLUSIONS

Evidence on ERAS in IBD is lacking, but this group of patients might benefit from consistent adoption of the pathway. Future studies should define if IBD-specific ERAS pathways and selection criteria are needed.

Insufficient Post-operative Energy Intake Is Associated With Failure of Enhanced Recovery Programs After Laparoscopic Colorectal Cancer Surgery: A Prospective Cohort Study

Background: Although enhanced recovery after surgery (ERAS) has been proven to be beneficial after laparoscopic colorectal surgery, some of the patients may fail to complete the ERAS program during hospitalization. This prospective study aims to evaluate the risk factors associated with ERAS failure after laparoscopic colorectal cancer surgery.

Methods: This is a prospective study from a single tertiary referral hospital. Patients diagnosed with colorectal cancer who met the inclusion criteria were included in this study. Demographic and clinicopathological characteristics were collected. Post-operative activity time and 6-min walking distance (6MWD) were measured. Patients were divided into ERAS failure group and ERAS success according to decreased post-operative activity and 6MWD. Factors associated with ERAS failure were investigated by univariate and multivariate analysis.

Results: A total of 91 patients with colorectal cancer were included. The incidence of ERAS failure is 28.6% among all patients. Patients in ERAS failure group experienced higher rate of post-operative ileus and prolonged hospital stay (p < 0.001). Multivariate analysis revealed that older age (p = 0.006), body mass index ≥25.5 kg/m² (p = 0.037), smoking (p = 0.002), operative time (p = 0.048), and post-operative energy intake <18.5 kcal/kg•d (p = 0.045) were independent risk factors of ERAS failure after laparoscopic colorectal surgery.

Conclusions: Our findings indicated that a proportion of patients may fail the ERAS program after laparoscopic colorectal surgery. We for the first time showed that post-operative energy intake was an independent risk factor for ERAS failure. This may provide evidence for further investigation on precise measurement of nutritional status and selected high-risk patients for enhanced nutrition support.

The revision partial knee classification system: understanding the causative pathology and magnitude of further surgery following partial knee arthroplasty

AIMS

Joint registries classify all further arthroplasty procedures to a knee with an existing partial arthroplasty as revision surgery, regardless of the actual procedure performed. Relatively minor procedures, including bearing exchanges, are classified in the same way as major operations requiring augments and stems. A new classification system is proposed to acknowledge and describe the detail of these procedures, which has implications for risk, recovery, and health economics.

METHODS

Classification categories were proposed by a surgical consensus group, then ranked by patients, according to perceived invasiveness and implications for recovery. In round one, 26 revision cases were classified by the consensus group. Results were tested for inter-rater reliability. In round two, four additional cases were added for clarity. Round three repeated the survey one month later, subject to inter- and intrarater reliability testing. In round four, five additional expert partial knee arthroplasty surgeons were asked to classify the 30 cases according to the proposed revision partial knee classification (RPKC) system.

RESULTS

Four classes were proposed: PR1, where no bone-implant interfaces are affected; PR2, where surgery does not include conversion to total knee arthroplasty, for example, a second partial arthroplasty to a native compartment; PR3, when a standard primary total knee prosthesis is used; and PR4 when revision components are necessary. Round one resulted in 92% inter-rater agreement (Kendall's W 0.97; p < 0.005), rising to 93% in round two (Kendall's W 0.98; p < 0.001). Round three demonstrated 97% agreement (Kendall's W 0.98; p < 0.001), with high intra-rater reliability (interclass correlation coefficient (ICC) 0.99; 95% confidence interval 0.98 to 0.99). Round four resulted in 80% agreement (Kendall's W 0.92; p < 0.001).

CONCLUSION

The RPKC system accounts for all procedures which may be appropriate following partial knee arthroplasty. It has been shown to be reliable, repeatable and pragmatic. The implications for patient care and health economics are discussed. Cite this article: Bone Jt Open 2021;2(8):638-645.

Failure of enhanced recovery after surgery in laparoscopic colorectal surgery: a systematic review

PURPOSE

Enhanced recovery after surgery programs has been applied extensively in laparoscopic colorectal surgery. However, several studies have found that some patients fail from ERAS programs. It is important to identify these patients so that remedial action can be taken in a timely manner. The aim of this study was to perform a systematic review of ERAS failure and related risk factors following laparoscopic colorectal surgery.

METHODS

A literature search of the PubMed, EMBASE, OVID, and Cochrane databases was performed. The search strategy involved terms related to ERAS, failure, and colorectal surgery. The main outcomes were definitions of ERAS failure and related risk factors.

RESULTS

Seven studies including 1463 patients were analyzed. The definition of ERAS failure was mostly associated with a prolonged postoperative length-of-stay (poLOS). Twenty-four kinds of identified risk factors were divided into three parts, the operative part, the pathophysiological part, and the ERAS elements, of which operative factors including more intraoperative blood loss and longer operative duration were the most frequently identified.

CONCLUSIONS

ERAS failure was mostly related to a prolonged poLOS, and operative factors were the most frequently identified risk factors for ERAS failure following laparoscopic colorectal surgery. These findings will help physicians to take remedial action in a timely manner. Nonetheless, high-quality randomized controlled trials following a standardized framework for evaluating ERAS programs are needed in the future.

Prolonged Postoperative Ileus Significantly Increases the Cost of Inpatient Stay for Patients Undergoing Elective Colorectal Surgery: Results of a Multivariate Analysis of Prospective Data at a Single Institution

BACKGROUND

Prolonged postoperative ileus is a common major complication after abdominal surgery. Retrospective data suggest that ileus doubles the cost of inpatient stay. However, current economic impact data are based on retrospective studies that rely on clinical coding to diagnose ileus.

OBJECTIVE

The aim of this study was to determine the economic burden of ileus for patients undergoing elective colorectal surgery.

DESIGN

Economic data were audited from a prospective database of patients who underwent surgery at Auckland City Hospital between September 2012 and June 2014.

SETTINGS

Auckland City Hospital is a large tertiary referral center, using an enhanced recovery after surgery protocol.

PATIENTS

Patients were prospectively diagnosed with prolonged postoperative ileus using a standardized definition.

MAIN OUTCOME MEASURES

The cost of inpatient stay was analyzed with regard to patient demographics and operative and postoperative factors. A multivariate analysis was performed to determine the cost of ileus when accounting for other significant covariates.

RESULTS

Economic data were attained from 325 patients, and 88 patients (27%) developed ileus. The median inpatient cost (New Zealand dollars) for patients with prolonged ileus, including complication rates and length of stay, was $27,981 (interquartile range= $20,198 to $42,174) compared with $16,317 (interquartile range = $10,620 to $23,722) for other patients, a 71% increase in cost (p < 0.005). Ileus increased all associated healthcare costs, including medical/nursing care, radiology, medication, laboratory costs, and allied health (p < 0.05). Multivariate analysis showed that ileus remained a significant financial burden (p < 0.005) when considering rates of major complications and length of stay.

LIMITATIONS

This is a single-institution study, which may impact the generalizability of our results.

CONCLUSIONS

Prolonged ileus causes a substantial financial burden on the healthcare system, in addition to greater complication rates and length of stay in these patients. This is the first study to assess the financial impact of prolonged ileus, diagnosed prospectively using a standardized definition. See Video Abstract at http://links.lww.com/DCR/A825.

The Reporting on ERAS Compliance, Outcomes, and Elements Research (RECOvER) Checklist: A Joint Statement by the ERAS® and ERAS® USA Societies

BACKGROUND

Enhanced recovery after surgery (ERAS) programs are multimodal care pathways designed to minimize the physiological and psychological impact of surgery for patients. Increased compliance with ERAS guidelines is associated with improved patient outcomes across surgical types. As ERAS programs have proliferated, an unintentional effect has been significant variation in how ERAS-related studies are reported in the literature.

METHODS

To improve the quality of ERAS reporting, ERAS® USA and the ERAS® Society launched an effort to create an instrument to assist authors in manuscript preparation. Criteria to include were selected by a combination of literature review and expert opinion. The final checklist was refined by group consensus.

RESULTS

The Societies present the Reporting on ERAS Compliance, Outcomes, and Elements Research (RECOvER) Checklist. The tool contains 20 items including best practices for reporting clinical pathways, compliance auditing, and formatting guidelines.

CONCLUSIONS

The RECOvER Checklist is intended to provide a standardized framework for the reporting of ERAS-related studies. The checklist can also assist reviewers in evaluating the quality of ERAS-related manuscripts. Authors are encouraged to include the RECOvER Checklist when submitting ERAS-related studies to peer-reviewed journals.