During the COVID-19 pandemic, a 13.6 per cent reduction in the number of surgical procedures performed was observed in 2020. Despite great pressure on healthcare, the COVID-19 pandemic did not... Show moreDuring the COVID-19 pandemic, a 13.6 per cent reduction in the number of surgical procedures performed was observed in 2020. Despite great pressure on healthcare, the COVID-19 pandemic did not cause an increase in adverse surgical outcomes, and oncological surgery-related duration of hospital and ICU stay were significantly shorter.Background The COVID-19 pandemic caused disruption of regular healthcare leading to reduced hospital attendances, repurposing of surgical facilities, and cancellation of cancer screening programmes. This study aimed to determine the impact of COVID-19 on surgical care in the Netherlands. Methods A nationwide study was conducted in collaboration with the Dutch Institute for Clinical Auditing. Eight surgical audits were expanded with items regarding alterations in scheduling and treatment plans. Data on procedures performed in 2020 were compared with those from a historical cohort (2018-2019). Endpoints included total numbers of procedures performed and altered treatment plans. Secondary endpoints included complication, readmission, and mortality rates. Results Some 12 154 procedures were performed in participating hospitals in 2020, representing a decrease of 13.6 per cent compared with 2018-2019. The largest reduction (29.2 per cent) was for non-cancer procedures during the first COVID-19 wave. Surgical treatment was postponed for 9.6 per cent of patients. Alterations in surgical treatment plans were observed in 1.7 per cent. Time from diagnosis to surgery decreased (to 28 days in 2020, from 34 days in 2019 and 36 days in 2018; P < 0.001). For cancer-related procedures, duration of hospital stay decreased (5 versus 6 days; P < 0.001). Audit-specific complications, readmission, and mortality rates were unchanged, but ICU admissions decreased (16.5 versus 16.8 per cent; P < 0.001). Conclusion The reduction in the number of surgical operations was greatest for those without cancer. Where surgery was undertaken, it appeared to be delivered safely, with similar complication and mortality rates, fewer admissions to ICU, and a shorter hospital stay.Lay Summary COVID-19 has had a significant impact on healthcare worldwide. Hospital visits were reduced, operating facilities were used for COVID-19 care, and cancer screening programmes were cancelled. This study describes the impact of the COVID-19 pandemic on Dutch surgical healthcare in 2020. Patterns of care in terms of changed or delayed treatment are described for patients who had surgery in 2020, compared with those who had surgery in 2018-2019. The study found that mainly non-cancer surgical treatments were cancelled during months with high COVID-19 rates. Outcomes for patients undergoing surgery were similar but with fewer ICU admissions and shorter hospital stay. These data provide no insight into the burden endured by patients who had postponed or cancelled operations. Show less
Bosch, T. van den; Warps, A.L.K.; Babberich, M.P.M.D.T.; Stamm, C.; Geerts, B.F.; Vermeulen, L.; ... ; Dutch ColoRectal Audit 2021
Question Can big-data analysis of clinical audits help to find new risk factors and predict adverse events associated with colorectal cancer surgery? Findings This cohort study found that machine... Show moreQuestion Can big-data analysis of clinical audits help to find new risk factors and predict adverse events associated with colorectal cancer surgery? Findings This cohort study found that machine learning applied to a clinical audit containing 62 501 records and 103 preoperative variables of surgically treated patients with colorectal cancer outperformed conventional scores in predicting 30-day postoperative mortality but with similar performance as a preexisting case-mix model. New risk factors for several other adverse events may be identified. Meaning This study suggests that machine learning methods may be of additional value in analyzing quality indicators in colorectal cancer surgery, thereby providing directions to optimize case-mix corrections for benchmarking in clinical auditing.Importance Quality improvement programs for colorectal cancer surgery have been introduced with benchmarking based on quality indicators, such as mortality. Detailed (pre)operative characteristics may offer relevant information for proper case-mix correction. Objective To investigate the added value of machine learning to predict quality indicators for colorectal cancer surgery and identify previously unrecognized predictors of 30-day mortality based on a large, nationwide colorectal cancer registry that collected extensive data on comorbidities. Design, Setting, and Participants All patients who underwent resection for primary colorectal cancer registered in the Dutch ColoRectal Audit between January 1, 2011, and December 31, 2016, were included. Multiple machine learning models (multivariable logistic regression, elastic net regression, support vector machine, random forest, and gradient boosting) were made to predict quality indicators. Model performance was compared with conventionally used scores. Risk factors were identified by logistic regression analyses and Shapley additive explanations (ie, SHAP values). Statistical analysis was performed between March 1 and September 30, 2020. Main Outcomes and Measures The primary outcome of this cohort study was 30-day mortality. Prediction models were trained on a training set by performing 5-fold cross-validation, and outcomes were measured by the area under the receiver operating characteristic curve on the test set. Machine learning was further used to identify risk factors, measured by odds ratios and SHAP values. Results This cohort study included 62 501 records, most patients were male (35 116 [56.2%]), were aged 61 to 80 years (41 560 [66.5%]), and had an American Society of Anesthesiology score of II (35 679 [57.1%]). A 30-day mortality rate of 2.7% (n = 1693) was found. The area under the curve of the best machine learning model for 30-day mortality (0.82; 95% CI, 0.79-0.85) was significantly higher than the American Society of Anesthesiology score (0.74; 95% CI, 0.71-0.77; P < .001), Charlson Comorbidity Index (0.66; 95% CI, 0.63-0.70; P < .001), and preoperative score to predict postoperative mortality (0.73; 95% CI, 0.70-0.77; P < .001). Hypertension, myocardial infarction, chronic obstructive pulmonary disease, and asthma were comorbidities with a high risk for increased mortality. Machine learning identified specific risk factors for a complicated course, intensive care unit admission, prolonged hospital stay, and readmission. Laparoscopic surgery was associated with a decreased risk for all adverse outcomes. Conclusions and Relevance This study found that machine learning methods outperformed conventional scores to predict 30-day mortality after colorectal cancer surgery, identified specific patient groups at risk for adverse outcomes, and provided directions to optimize benchmarking in clinical audits.This cohort study investigates the ability of machine learning to predict quality indicators for colorectal cancer surgery and identify previously unrecognized predictors of 30-day mortality based on a large nationwide colorectal cancer registry that collected extensive data on comorbidities. Show less
