Predicting aortic complications after endovascular aneurysm repair

Karthikesalingam, Alan; Holt, Peter; Vidal‐Diez, Alberto; Choke, Edward; Patterson, Benjamin O.; Thompson, Luke; Ghatwary, T.; Bown, Matthew J.; Sayers, Rob; Thompson, Matt

doi:10.1002/bjs.9177

Cited by 61 publications

(22 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results were compared with current clinical method such as; SGVI (St George Vascular Institute), which showed that the proposed method has superior performance. The seven features ANN of the proposed method have greater predictive ability in classifying low and high risk patients than the SGVI score [ 91 ]. Concordance index, estimated AUC, and p -value of the predictive model using the selected features show good clinical sense.…”

Section: Discussionmentioning

confidence: 99%

Feature selection through validation and un-censoring of endovascular repair survival data for predicting the risk of re-intervention

Attallah

Karthikesalingam²,

Holt³

et al. 2017

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

BackgroundFeature selection (FS) process is essential in the medical area as it reduces the effort and time needed for physicians to measure unnecessary features. Choosing useful variables is a difficult task with the presence of censoring which is the unique characteristic in survival analysis. Most survival FS methods depend on Cox’s proportional hazard model; however, machine learning techniques (MLT) are preferred but not commonly used due to censoring. Techniques that have been proposed to adopt MLT to perform FS with survival data cannot be used with the high level of censoring. The researcher’s previous publications proposed a technique to deal with the high level of censoring. It also used existing FS techniques to reduce dataset dimension. However, in this paper a new FS technique was proposed and combined with feature transformation and the proposed uncensoring approaches to select a reduced set of features and produce a stable predictive model.MethodsIn this paper, a FS technique based on artificial neural network (ANN) MLT is proposed to deal with highly censored Endovascular Aortic Repair (EVAR). Survival data EVAR datasets were collected during 2004 to 2010 from two vascular centers in order to produce a final stable model. They contain almost 91% of censored patients. The proposed approach used a wrapper FS method with ANN to select a reduced subset of features that predict the risk of EVAR re-intervention after 5 years to patients from two different centers located in the United Kingdom, to allow it to be potentially applied to cross-centers predictions. The proposed model is compared with the two popular FS techniques; Akaike and Bayesian information criteria (AIC, BIC) that are used with Cox’s model.ResultsThe final model outperforms other methods in distinguishing the high and low risk groups; as they both have concordance index and estimated AUC better than the Cox’s model based on AIC, BIC, Lasso, and SCAD approaches. These models have p-values lower than 0.05, meaning that patients with different risk groups can be separated significantly and those who would need re-intervention can be correctly predicted.ConclusionThe proposed approach will save time and effort made by physicians to collect unnecessary variables. The final reduced model was able to predict the long-term risk of aortic complications after EVAR. This predictive model can help clinicians decide patients’ future observation plan.Electronic supplementary materialThe online version of this article (doi:10.1186/s12911-017-0508-3) contains supplementary material, which is available to authorized users.

show abstract

Section: Discussionmentioning

confidence: 99%

Feature selection through validation and un-censoring of endovascular repair survival data for predicting the risk of re-intervention

Attallah

Karthikesalingam²,

Holt³

et al. 2017

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…Increasing aneurysm diameter also increases the risk of complications and reinterventions after elective endovascular repair. 17 , 18 Although the anatomical assessment of suitability for EVAR is defined primarily by neck length, diameter and angle, and access artery characteristics, it was neck length that was the most common factor precluding EVAR (<10 mm in 23%, <15 mm in 33%). For each increase of 15 mm in neck length, 30-day mortality decreased by a factor of ∼20%, with a similar effect on 24 h mortality.…”

Section: Discussionmentioning

confidence: 99%

“…This would be consistent with the relevance of these two parameters in predicting complications after elective aneurysm repair. 17 , 18 …”

Section: Discussionmentioning

confidence: 99%

The effect of aortic morphology on peri-operative mortality of ruptured abdominal aortic aneurysm

Anjum¹,

Thompson²,

Azhar³

et al. 2015

European Heart Journal

View full text Add to dashboard Cite

AimsTo investigate whether aneurysm shape and extent, which indicate whether a patient with ruptured abdominal aortic aneurysm (rAAA) is eligible for endovascular repair (EVAR), influence the outcome of both EVAR and open surgical repair.Methods and resultsThe influence of six morphological parameters (maximum aortic diameter, aneurysm neck diameter, length and conicality, proximal neck angle, and maximum common iliac diameter) on mortality and reinterventions within 30 days was investigated in rAAA patients randomized before morphological assessment in the Immediate Management of the Patient with Rupture: Open Versus Endovascular strategies (IMPROVE) trial. Patients with a proven diagnosis of rAAA, who underwent repair and had their admission computerized tomography scan submitted to the core laboratory, were included. Among 458 patients (364 men, mean age 76 years), who had either EVAR (n = 177) or open repair (n = 281) started, there were 155 deaths and 88 re-interventions within 30 days of randomization analysed according to a pre-specified plan. The mean maximum aortic diameter was 8.6 cm. There were no substantial correlations between the six morphological variables. Aneurysm neck length was shorter in those undergoing open repair (vs. EVAR). Aneurysm neck length (mean 23.3, SD 16.1 mm) was inversely associated with mortality for open repair and overall: adjusted OR 0.72 (95% CI 0.57, 0.92) for each 16 mm (SD) increase in length. There were no convincing associations of morphological parameters with reinterventions.ConclusionShort aneurysm necks adversely influence mortality after open repair of rAAA and preclude conventional EVAR. This may help explain why observational studies, but not randomized trials, have shown an early survival benefit for EVAR.Clinical trial registration:ISRCTN 48334791.

show abstract

“…The risk of endograft-related complications is heterogeneous[ 8 ] and a minority of patients fall within a high-risk cohort[ 8 ]. Endograft complications and reinterventions are related to pre-operative aneurysm morphology[ 17 , 18 ], but current statistical models have proved insufficiently discriminatory for clinical use. Furthermore, existing risk models have not proved capable of predicting limb complications such as stenosis or occlusion, which remain a source of morbidity.…”

Section: Introductionmentioning

confidence: 99%

An Artificial Neural Network Stratifies the Risks of Reintervention and Mortality after Endovascular Aneurysm Repair; a Retrospective Observational study

Karthikesalingam¹,

Attallah

et al. 2015

PLoS ONE

View full text Add to dashboard Cite

BackgroundLifelong surveillance after endovascular repair (EVAR) of abdominal aortic aneurysms (AAA) is considered mandatory to detect potentially life-threatening endograft complications. A minority of patients require reintervention but cannot be predictively identified by existing methods. This study aimed to improve the prediction of endograft complications and mortality, through the application of machine-learning techniques.MethodsPatients undergoing EVAR at 2 centres were studied from 2004-2010. Pre-operative aneurysm morphology was quantified and endograft complications were recorded up to 5 years following surgery. An artificial neural networks (ANN) approach was used to predict whether patients would be at low- or high-risk of endograft complications (aortic/limb) or mortality. Centre 1 data were used for training and centre 2 data for validation. ANN performance was assessed by Kaplan-Meier analysis to compare the incidence of aortic complications, limb complications, and mortality; in patients predicted to be low-risk, versus those predicted to be high-risk.Results761 patients aged 75 +/- 7 years underwent EVAR. Mean follow-up was 36+/- 20 months. An ANN was created from morphological features including angulation/length/areas/diameters/volume/tortuosity of the aneurysm neck/sac/iliac segments. ANN models predicted endograft complications and mortality with excellent discrimination between a low-risk and high-risk group. In external validation, the 5-year rates of freedom from aortic complications, limb complications and mortality were 95.9% vs 67.9%; 99.3% vs 92.0%; and 87.9% vs 79.3% respectively (p<0.001)ConclusionThis study presents ANN models that stratify the 5-year risk of endograft complications or mortality using routinely available pre-operative data.

show abstract

Predicting aortic complications after endovascular aneurysm repair

Abstract: The risk score uses commonly available morphological data to stratify the rate of complications after EVAR. The proposals for rationalized surveillance could provide clinical and economic benefits.

Cited by 61 publications

References 53 publications

Feature selection through validation and un-censoring of endovascular repair survival data for predicting the risk of re-intervention

Feature selection through validation and un-censoring of endovascular repair survival data for predicting the risk of re-intervention

The effect of aortic morphology on peri-operative mortality of ruptured abdominal aortic aneurysm

An Artificial Neural Network Stratifies the Risks of Reintervention and Mortality after Endovascular Aneurysm Repair; a Retrospective Observational study

Contact Info

Product

Resources

About