Hospital characteristics, rather than surgical volume, predict length of stay following colorectal cancer surgery

Vicendese, Don; Marvelde, Luc te; McNair, Peter; Whitfield, Kathryn; English, Dallas R.; Taieb, Souhaib Ben; Hyndman, Rob; Thomas, Robert J. S.

doi:10.1111/1753-6405.12932

Cited by 12 publications

(10 citation statements)

References 71 publications

(153 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nearly all rectal cancer and > 95% of colon cancer cases are discussed in multidisciplinary teams regardless of hospital volume [ 31 ]. Moreover, rectal cancer surgery in Sweden has also been centralized over the last 20 years to ensure adequate case volumes to safeguard surgical quality [ 32 ]. These aspects must be considered when assessing any causal relationship between procedure volume and FTR.…”

Section: Discussionmentioning

confidence: 99%

Center‐Level Procedure Volume Does Not Predict Failure‐to‐Rescue After Severe Complications of Oncologic Colon and Rectal Surgery

et al. 2021

View full text Add to dashboard Cite

Background The relationship between hospital surgical volume and outcome after colorectal cancer surgery has thoroughly been studied. However, few studies have assessed hospital surgical volume and failure-to-rescue (FTR) after colon and rectal cancer surgery. The aim of the current study is to evaluate FTR following colorectal cancer surgery between clinics based on procedure volume. Methods Patients undergoing colorectal cancer surgery in Sweden from January 2015 to January 2020 were recruited through the Swedish Colorectal Cancer Registry. The primary endpoint was FTR, defined as the proportion of patients with 30-day mortality after severe postoperative complications in colorectal cancer surgery. Severe postoperative complications were defined as Clavien–Dindo ≥ 3. FTR incidence rate ratios (IRR) were calculated comparing center volume stratified in low-volume (≤ 200 cases/year) and high-volume centers (> 200 cases/year), as well as with an alternative stratification comparing low-volume (< 50 cases/year), medium-volume (50–150 cases/year) and high-volume centers (> 150 cases/year). Results A total of 23,351 patients were included in this study, of whom 2964 suffered severe postoperative complication(s). Adjusted IRR showed no significant differences between high- and low-volume centers with an IRR of 0.97 (0.75–1.26, p = 0.844) in high-volume centers in the first stratification and an IRR of 2.06 (0.80–5.31, p = 0.134) for high-volume centers and 2.15 (0.83–5.56, p = 0.116) for medium-volume centers in the second stratification. Conclusion This nationwide retrospectively analyzed cohort study fails to demonstrate a significant association between hospital surgical volume and FTR after colorectal cancer surgery. Future studies should explore alternative characteristics and their correlation with FTR to identify possible interventions for the improvement of quality of care after colorectal cancer surgery.

show abstract

Section: Discussionmentioning

confidence: 99%

Center‐Level Procedure Volume Does Not Predict Failure‐to‐Rescue After Severe Complications of Oncologic Colon and Rectal Surgery

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Prior research has used a limited number of variables to investigate LOS, mortality and readmission following CRC surgery [1,4,25,37,43,46,57,58]. This study includes a larger number of variables (47) including demographics, periand post-operative outcomes, surgical approaches, complications and mortality.…”

Section: Comparison Between All Variables and Selected Variablesmentioning

confidence: 99%

Data Analytics and Artificial Intelligence in Predicting Length of Stay, Readmission, and Mortality: A Population-Based Study of Surgical Management of Colorectal Cancer

Masum

Hopgood

Stefan

et al. 2021

Preprint

View full text Add to dashboard Cite

Data analytics and artificial intelligence (AI) have been used to predict patient outcomes after colorectal cancer surgery. A prospectively maintained colorectal cancer database was used, covering 4336 patients who underwent colorectal cancer surgery between 2003 and 2019. The 47 patient parameters included demographics, peri- and post-operative outcomes, surgical approaches, complications, and mortality. Data analytics were used to compare the importance of each variable and AI prediction models were built for length of stay (LOS), readmission, and mortality. Accuracies of at least 80% have been achieved. The significant predictors of LOS were age, ASA grade, operative time, presence or absence of a stoma, robotic or laparoscopic approach to surgery, and complications. The model with support vector regressor (SVR) algorithms predicted the LOS with an accuracy of 83% and mean absolute error (MAE) of 9.69 days. The significant predictors of readmission were age, laparoscopic procedure, stoma performed, preoperative nodal (N) stage, operation time, operation mode, previous surgery type, LOS, and the specific procedure. A BI-LSTM model predicted readmission with 87.5% accuracy, 84% sensitivity, and 90% specificity. The significant predictors of mortality were age, ASA grade, BMI, the formation of a stoma, preoperative TNM staging, neoadjuvant chemotherapy, curative resection, and LOS. Classification predictive modelling predicted three different colorectal cancer mortality measures (overall mortality, and 31- and 91-days mortality) with 80-96% accuracy, 84-93% sensitivity, and 75-100% specificity. A model using all variables performed only slightly better than one that used just the most significant ones.

show abstract

“…For stroke patients, however, there is a significant inverse linear association between LOS at the ED and hospital LOS [ 7 ]. ED crowding and hospital occupancy at entry are predicted to have longer LOS [ 5 , 8 ], however, there are other hospital characteristics that play a role in determining it [ 9 , 10 ].…”

Section: Introductionmentioning

confidence: 99%

The prediction of hospital length of stay using unstructured data

Chrusciel

Girardon

Roquette

et al. 2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Objective This study aimed to assess the performance improvement for machine learning-based hospital length of stay (LOS) predictions when clinical signs written in text are accounted for and compared to the traditional approach of solely considering structured information such as age, gender and major ICD diagnosis. Methods This study was an observational retrospective cohort study and analyzed patient stays admitted between 1 January to 24 September 2019. For each stay, a patient was admitted through the Emergency Department (ED) and stayed for more than two days in the subsequent service. LOS was predicted using two random forest models. The first included unstructured text extracted from electronic health records (EHRs). A word-embedding algorithm based on UMLS terminology with exact matching restricted to patient-centric affirmation sentences was used to assess the EHR data. The second model was primarily based on structured data in the form of diagnoses coded from the International Classification of Disease 10th Edition (ICD-10) and triage codes (CCMU/GEMSA classifications). Variables common to both models were: age, gender, zip/postal code, LOS in the ED, recent visit flag, assigned patient ward after the ED stay and short-term ED activity. Models were trained on 80% of data and performance was evaluated by accuracy on the remaining 20% test data. Results The model using unstructured data had a 75.0% accuracy compared to 74.1% for the model containing structured data. The two models produced a similar prediction in 86.6% of cases. In a secondary analysis restricted to intensive care patients, the accuracy of both models was also similar (76.3% vs 75.0%). Conclusions LOS prediction using unstructured data had similar accuracy to using structured data and can be considered of use to accurately model LOS.

show abstract

Hospital characteristics, rather than surgical volume, predict length of stay following colorectal cancer surgery

Cited by 12 publications

References 71 publications

Center‐Level Procedure Volume Does Not Predict Failure‐to‐Rescue After Severe Complications of Oncologic Colon and Rectal Surgery

Center‐Level Procedure Volume Does Not Predict Failure‐to‐Rescue After Severe Complications of Oncologic Colon and Rectal Surgery

Data Analytics and Artificial Intelligence in Predicting Length of Stay, Readmission, and Mortality: A Population-Based Study of Surgical Management of Colorectal Cancer

The prediction of hospital length of stay using unstructured data

Contact Info

Product

Resources

About