A1Check: the External Validation of a Machine Learning Model Predicting Colorectal Anastomotic Leakage
Study Details
Study Description
Brief Summary
Anastomotic leakage is a severe complication that can arise following a colorectal resection. It impairs both the short- and long term outcome, and negatively influences cancer recurrence rates. Its detrimental effects resound in healthcare costs of a patient after anastomotic leakage, 71.978,- EUR, versus patients with an uncomplicated course, 17.647,- EUR. Despite multiple innovation within the field of colorectal surgery, incidence of colorectal anastomotic leakage did not reduce in the past decade. Mitigation strategies as prehabilitation, intraoperative optimization, selective bowel decontamination and reconstruction techniques are promising but do not completely eliminate the risk of leakage. The only true prevention of colorectal anastomotic leakage is the omission of an anastomosis and implies an ostomy, which in itself has a negative impact on quality of life. A stoma is associated with stoma-related morbidity and should therefore be avoided in patient who do not need it. Predicting anastomotic leakage intra-operatively, just before the construction of the anastomosis, may offer a solution. A stoma will then only be constructed in those at high risk of anastomotic leakage. Currently, there are prediction models for anastomotic leakage base on conventional multivariate logistic regression analysis, however these are not useful for clinical practice due to suboptimal results. Machine learning algorithms on the other hand, take well into account the multifactorial nature of complications and might thus be able to predict anastomotic leakage more accurately. The machine learning model we created proved to be well capable of making accurate predictions. This model was developed based on the a database containing both pre- and intra-operative data from 2,483 patients. Before these models can be used in daily practice, external validation is essential. Our models should be tested on unseen data from patients treated in centers that were not previously involved in the database that was used to train the model in order to achieve high reproducibility. Our hypothesis is that with our model we can accurately predict anastomotic leakage intra-operatively during colorectal surgery.
| Condition or Disease | Intervention/Treatment | Phase |
|---|---|---|
|
Detailed Description
Study procedure The aim of the study is to externally validate a machine learning model predicting colorectal anastomotic leakage. The prediction model that will be externally validated, is developed on a prospective database. This database contained data of 2,483 colorectal cancer patients who underwent a surgical procedure between January 2016 and April 2021 in 14 hospitals, both rural and academic in four different countries (the Netherlands, Italy, Belgium, Australia). Some 189 patients (7.6%) developed colorectal anastomotic leakage. The models predicted risk of colorectal anastomotic leakage intraoperatively, just prior to the construction of the anastomosis, using a total of 31 variables. These variables contain both preoperatively available data and the variables regarding the intraoperative condition of the patient. The models were internally validated using 10-fold cross validation and subsequently tested on 20% of unseen data of the database. The area under the curve - receiver operating characteristics (AUROC) of the best performing machine learning model on the test set was 0.84, with a sensitivity of 0.86, specificity of 0.78, a positive predictive value of 0.24 and a negative predictive value of 0.99.
During this prospective simulation study there are no direct benefits or risks for participating patients. This prospective simulation study will be non-interventional, the prediction models do not alter the original daily practice and in this phase, it is not intended to be used as a diagnostic device. Intraoperatively, just prior to the construction of the anastomosis, the prediction model will predict, using patient, tumor, and intraoperatively variables (listed in the Data Dictionary paragraph), the probability of anastomotic leakage. SAS VIYA is used for deplopment of the machine learning model. During the prospective simulation study, the scores of these predictions are only available to the principle and research investigators, and thus unknown to the participating hospitals or operating surgeons in order to prevent any influence on current daily practice in this stage of the research. Thirty days postoperatively, data of the patients regarding the occurrence of anastomotic leakage will be collected. AUROC, sensitivity, specificity, and accuracy then will be calculated based on the number of patients assessed as true positive, true negative, false positive or false negative. After a minimum of 100 events and 100 non-events, the external validation is completed and the final AUROC, sensitivity and specificity scores will be presented.
Quality assurance plan, data checks, source data verification Data will be handled confidentially and anonymously. Data will be pseudo-anonymized for the principal investigator and the research investigators. Pseudo-anonymized data are entered in a Castor database. A data dictionary is attached to the original dataset with metadata to describe the data. All participating hospitals have a Data Sharing Agreement to safely share data of included patients with the principal investigator and the research investigators. A data management plan will be created according to our institute's polices with the assistance of a data management expert, along with the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guidelines.The characteristics of the collected and generated data is clinical data extracted from the electronic health records. This contains continuous, nominal, and dichotomous variables. Data will not be reused or coupled to existing data. Informed consent of patients is necessary to predict the outcome using the developed model. Privacy policies and laws are applicable to this project. The project will also comply with all data protection principles as is defined in the General Data Protection Regulation. The anonymized dataset can be accessed via a Castor database. Long term data will be saved in the Amsterdam UMC repository with help of the research data management (RDM) department. The data will be saved for five years after the project has ended.
Data dictionary
The following variables will be collected from included patients:
-
Patient and tumor characteristics Age; sex; body mass index; American Society of Anesthesiologists (ASA) classification; intoxications (smoking and/or alcohol consumption); medical history of diabetes; steroid use (not nasal); hemoglobin; benign or malignant disease. If there is malignant disease: TNM-stage, tumor distance from anal verge, neoadjuvant treatment.
-
Perioperative characteristics Surgical procedure, surgical approach; conversion; occurrence of intraoperative event (hypoxic events, hypercarbia, bradycardia, hypotension, embolism, reanimation, more extensive resection than planned, serosa lesions, bladder and ureteral injuries, intraoperative bleeding, splenectomy) iii. Characteristics just prior to the creation of the anastomosis Patient temperature; time of antibiotic administration; administration of vasopressors; blood loss; O2 saturation; mean arterial pressure; fluid administration; urine production; presence of fecal contamination; subjective assessment of local perfusion; epidural analgesia; door movements; time from incision until the creation of the anastomosis, intention to create stoma.
-
Postoperative characteristics Colorectal anastomotic leakage within 30 days and length of hospital stay.
Standard Operating procedures Patients eligible for inclusion are detected in the first multidisciplinary team meeting. If eligible, the surgeon will inform and discuss this study with the patient in the preoperative consultation for surgery. If the patient consent on participation, a written informed consent is required. The patient may withdraw this consent at any time.
Sample size calculation In the participating hospitals around 100 to 400 colorectal resections are performed annually, with an approximate incidence of anastomotic leakage of 5 to 15%. Multiple studies demonstrated a minimum of 100 events and 100 nonevents as an appropriate sample size for external validation. With an expected total of 1,200 patients included annually and a leakage percentage around 10%, including 100 events takes approximately one to two year.
Handling missing data The machine learning model will make a prediction in patients with more than 80% of the required data available. Missing data are imputed using predictive mean matching with ten iterations.
Statistical analysis plan The external validation will be performed on at least 100 events (anastomotic leakage) and 100 non-events (no anastomotic leakage). The machine learning model with the best predictive performance in terms of AUROC will be used as the implementation model. Colorectal anastomotic leakage rate will be compared in a multivariate logistic regression model. All analyses will be carried out under supervision of an clinical epidemiologist.
Study Design
Arms and Interventions
| Arm | Intervention/Treatment |
|---|---|
| Adult patients undergoing colorectal resection with the construction of an anastomosis The exposure of interest in the current study regards the occurrence of anastomotic leakage in patients undergoing colorectal resection with the construction of an anastomosis. Information on the exposure of interest is gained by obtaining data from the patient files. |
Procedure: Colorectal resection
Patients undergoing a colorectal resection with the construction of a primary anastomosis
|
Outcome Measures
Primary Outcome Measures
- Colorectal anastomotic leakage [the occurrence of the primary outcome is assessed after 30 days postoperatively.]
colorectal anastomotic leakage is defined according to Reisinger: "clinically relevant anastomotic leakage is defined as extra luminal presence of contrast fluid on contrast-enhanced CT scans and/or leakage when relaparotomy was performed, requiring reintervention or treatment."
Secondary Outcome Measures
- Length of Hospital Stay [The length of hospital stay is assessed 90 days postoperatively]
To evaluate the impact of anastomotic leakage on length of stay, the duration of a patient's hospital stay after undergoing a colorectal resection is investigated.
Other Outcome Measures
- The predictive performance of the prediction model [30 days postoperatively.]
the predicted probability of anastomotic leakage for every participant will be evaluated with the actual outcome after 30 days postoperatively. The discrimination of the external validation cohort is reported with the area under the curve - receiver operating characteristic, the sensitivity, specificity, and accuracy. Calibration of the prediction model will be visualized in a calibration plot.
Eligibility Criteria
Criteria
Inclusion Criteria:
-
patients undergoing colorectal resection with the construction of an anastomosis
-
patients with the age of 18 years or older
-
patients able to give informed consent
Exclusion Criteria:
-
when more than 25% of the target variables are missing on which the machine learning model bases the prediction
-
non-elective surgeries
Contacts and Locations
Locations
| Site | City | State | Country | Postal Code | |
|---|---|---|---|---|---|
| 1 | Tjongerschans ziekenhuis | Heerenveen | Friesland | Netherlands | 8441PW |
| 2 | Gelre Ziekenhuis | Apeldoorn | Gelderland | Netherlands | 7334DZ |
| 3 | Slingeland Ziekenhuis | Doetinchem | Gelderland | Netherlands | 7009BL |
| 4 | Zuyderland MC | Heerlen | Limburg | Netherlands | 6419PC |
| 5 | ZGT | Almelo | Overijssel | Netherlands | 7609PP |
| 6 | Deventer ziekenhuis | Deventer | Overijssel | Netherlands | 7418SE |
| 7 | Medisch Spectrum Twente | Enschede | Overijssel | Netherlands | 7512KZ |
| 8 | Meander MC | Amersfoort | Utrecht | Netherlands | 3813TZ |
Sponsors and Collaborators
- Freek Daams
- SAS Institute
Investigators
- Principal Investigator: Freek Daams, MD PhD, Amsterdam UMC, location VUmc
Study Documents (Full-Text)
None provided.More Information
Additional Information:
Publications
- Abis GSA, Stockmann HBAC, Bonjer HJ, van Veenendaal N, van Doorn-Schepens MLM, Budding AE, Wilschut JA, van Egmond M, Oosterling SJ; SELECT trial study group. Randomized clinical trial of selective decontamination of the digestive tract in elective colorectal cancer surgery (SELECT trial). Br J Surg. 2019 Mar;106(4):355-363. doi: 10.1002/bjs.11117. Epub 2019 Feb 25.
- Branagan G, Finnis D; Wessex Colorectal Cancer Audit Working Group. Prognosis after anastomotic leakage in colorectal surgery. Dis Colon Rectum. 2005 May;48(5):1021-6. doi: 10.1007/s10350-004-0869-4.
- Bruns ERJ, van Rooijen SJ, Argillander TE, van der Zaag ES, van Grevenstein WMU, van Duijvendijk P, Buskens CJ, Bemelman WA, van Munster BC, Slooter GD, van den Heuvel B. Improving Outcomes in Oncological Colorectal Surgery by Prehabilitation. Am J Phys Med Rehabil. 2019 Mar;98(3):231-238. doi: 10.1097/PHM.0000000000001025.
- Collins GS, Ogundimu EO, Altman DG. Sample size considerations for the external validation of a multivariable prognostic model: a resampling study. Stat Med. 2016 Jan 30;35(2):214-26. doi: 10.1002/sim.6787. Epub 2015 Nov 9.
- Fujita S, Teramoto T, Watanabe M, Kodaira S, Kitajima M. Anastomotic leakage after colorectal cancer surgery: a risk factor for recurrence and poor prognosis. Jpn J Clin Oncol. 1993 Oct;23(5):299-302.
- Huisman DE, Reudink M, van Rooijen SJ, Bootsma BT, van de Brug T, Stens J, Bleeker W, Stassen LPS, Jongen A, Feo CV, Targa S, Komen N, Kroon HM, Sammour T, Lagae EAGL, Talsma AK, Wegdam JA, de Vries Reilingh TS, van Wely B, van Hoogstraten MJ, Sonneveld DJA, Veltkamp SC, Verdaasdonk EGG, Roumen RMH, Slooter GD, Daams F. LekCheck: A Prospective Study to Identify Perioperative Modifiable Risk Factors for Anastomotic Leakage in Colorectal Surgery. Ann Surg. 2022 Jan 1;275(1):e189-e197. doi: 10.1097/SLA.0000000000003853.
- Ingwersen EW, van der Beek PJK, Dekker JWT, van Dieren S, Daams F. One Decade of Declining Use of Defunctioning Stomas After Rectal Cancer Surgery in the Netherlands: Are We on the Right Track? Dis Colon Rectum. 2023 Jan 6. doi: 10.1097/DCR.0000000000002625. Online ahead of print.
- Koedam TWA, Bootsma BT, Deijen CL, van de Brug T, Kazemier G, Cuesta MA, Furst A, Lacy AM, Haglind E, Tuynman JB, Daams F, Bonjer HJ; COLOR COLOR II study group. Oncological Outcomes After Anastomotic Leakage After Surgery for Colon or Rectal Cancer: Increased Risk of Local Recurrence. Ann Surg. 2022 Feb 1;275(2):e420-e427. doi: 10.1097/SLA.0000000000003889.
- La Regina D, Di Giuseppe M, Lucchelli M, Saporito A, Boni L, Efthymiou C, Cafarotti S, Marengo M, Mongelli F. Financial Impact of Anastomotic Leakage in Colorectal Surgery. J Gastrointest Surg. 2019 Mar;23(3):580-586. doi: 10.1007/s11605-018-3954-z. Epub 2018 Sep 13.
- Mirnezami A, Mirnezami R, Chandrakumaran K, Sasapu K, Sagar P, Finan P. Increased local recurrence and reduced survival from colorectal cancer following anastomotic leak: systematic review and meta-analysis. Ann Surg. 2011 May;253(5):890-9. doi: 10.1097/SLA.0b013e3182128929.
- Moons KG, Altman DG, Reitsma JB, Ioannidis JP, Macaskill P, Steyerberg EW, Vickers AJ, Ransohoff DF, Collins GS. Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med. 2015 Jan 6;162(1):W1-73. doi: 10.7326/M14-0698.
- Reisinger KW, Poeze M, Hulsewe KW, van Acker BA, van Bijnen AA, Hoofwijk AG, Stoot JH, Derikx JP. Accurate prediction of anastomotic leakage after colorectal surgery using plasma markers for intestinal damage and inflammation. J Am Coll Surg. 2014 Oct;219(4):744-51. doi: 10.1016/j.jamcollsurg.2014.06.011. Epub 2014 Jun 25.
- Stam WT, Ingwersen EW, Ali M, Spijkerman JT, Kazemier G, Bruns ERJ, Daams F. Machine learning models in clinical practice for the prediction of postoperative complications after major abdominal surgery. Surg Today. 2023 Feb 25. doi: 10.1007/s00595-023-02662-4. Online ahead of print.
- van Rooijen SJ, Huisman D, Stuijvenberg M, Stens J, Roumen RMH, Daams F, Slooter GD. Intraoperative modifiable risk factors of colorectal anastomotic leakage: Why surgeons and anesthesiologists should act together. Int J Surg. 2016 Dec;36(Pt A):183-200. doi: 10.1016/j.ijsu.2016.09.098. Epub 2016 Oct 15.
- Vergouwe Y, Steyerberg EW, Eijkemans MJ, Habbema JD. Substantial effective sample sizes were required for external validation studies of predictive logistic regression models. J Clin Epidemiol. 2005 May;58(5):475-83. doi: 10.1016/j.jclinepi.2004.06.017.
- 2021.0626