Dataset Information

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

ABSTRACT:

Background

Lifelong 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.

Methods

Patients 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.

Results

761 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).

Conclusion

This study presents ANN models that stratify the 5-year risk of endograft complications or mortality using routinely available pre-operative data.

SUBMITTER: Karthikesalingam A

PROVIDER: S-EPMC4503678 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Karthikesalingam Alan A Attallah Omneya O Ma Xianghong X Bahia Sandeep Singh SS Thompson Luke L Vidal-Diez Alberto A Choke Edward C EC Bown Matt J MJ Sayers Robert D RD Thompson Matt M MM Holt Peter J PJ

PloS one 20150715 7

<h4>Background</h4>Lifelong 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.<h4>Methods</h4>Patients undergoing EVAR at 2 centres wer ...[more]

PMID: 26176943

Similar Datasets

Project description:ObjectivePatients who undergo endovascular abdominal aortic aneurysm repair (EVR) remain at risk for reintervention and rupture. We sought to define the 5-year rate of reintervention and rupture after EVR in the Vascular Quality Initiative (VQI).MethodsWe identified all patients in the VQI who underwent EVR from 2003 to 2015. We linked patients in the VQI to Medicare claims for long-term outcomes. We stratified patients on baseline clinical and procedural characteristics to identify those at risk for reintervention. Our primary outcomes were 5-year rates of reintervention and late aneurysm rupture after EVR. We assessed these with Kaplan-Meier survival estimation.ResultsWe studied 12,911 patients who underwent EVR. The mean age was 75.5 years, 79.9% were male, 3.9% were black, and 89.1% of operations were performed electively. The 5-year rate of reintervention for the entire cohort was 21%, and the 5-year rate of late aneurysm rupture was 3%. Reintervention rates varied across categories of EVR urgency. Patients who underwent EVR electively had the lowest 5-year rate of reintervention at 20%. Those who underwent surgery for symptomatic aneurysms had higher rates of reintervention at 25%. Patients undergoing EVR emergently for rupture had the highest rate of reintervention, 27% at 4 years (log-rank across the three groups, P < .001). Black race and aneurysm size of 6.0 cm or greater were associated with significantly elevated reintervention rates (black, 31% vs white, 20% [log-rank, P < .001]; aneurysm size 6.0 cm or greater, 27% vs all others, <20% [log-rank, P < .001]). There were no significant associations between age or gender and the 5-year rate of reintervention.ConclusionsMore than one in five Medicare patients undergo reintervention within 5 years after EVR in the VQI; late rupture remains low at 3%. Black patients, those with large aneurysms, and those who undergo EVR urgently and emergently have a higher likelihood of adverse outcomes and should be the focus of diligent long-term surveillance.

Project description:BackgroundEndovascular aneurysm sealing (EVAS), using the Nellix endovascular aneurysm sealing system, has been associated with high reintervention and migration rates. However, prior reports have suggested that EVAS might be related to a lower all-cause mortality compared with endovascular aneurysm repair (EVAR). In the present study, we examined the 5-year all-cause mortality trends after EVAS and EVAR.MethodsWe compared the 333 EVAS patients in the EVAS-1 Nellix U.S. investigational device exemption trial with 16,497 infrarenal EVAR controls from the Vascular Quality Initiative, treated between 2014 and 2016, after applying the exclusion criteria from the investigational device exemption trial (ie, hemodialysis, creatinine >2.0 mg/dL, rupture). As a secondary analysis, we stratified the patients by aneurysm diameter (<5.5 cm and ≥5.5 cm). We calculated propensity scores after adjusting for demographics, comorbidities, and anatomic characteristics and applied inverse probability weighting to compare the risk-adjusted long-term mortality using Kaplan-Meier and Cox regression analyses.ResultsAfter weighting, the EVAS group had experienced similar 5-year mortality compared with the controls from the Vascular Quality Initiative (EVAS vs EVAR, 18% vs 14%; hazard ratio [HR], 1.1; 95% confidence interval [CI], 0.71-1.7; P = .70). The subgroup analysis demonstrated that for patients with an aneurysm diameter of <5.5 cm, EVAS was associated with higher 5-year mortality compared with EVAR (19% vs 11%; HR, 2.4; 95% CI, 1.7-4.7; P = .013). In patients with an aneurysm diameter of ≥5.5 cm, EVAS was associated with lower mortality within the first 2 years (2-year mortality: HR, 0.29; 95% CI, 0.13-0.62; P = .002). However, compared with EVAR, EVAS was associated with higher mortality between 2 and 5 years (HR, 1.9; 95% CI, 1.2-3.0; P = .005), with no mortality difference at 5 years (18% vs 17%; HR, 0.82; 95% CI, 0.4-1.4; P = .46).ConclusionsWithin the overall population, EVAS was associated with similar 5-year mortality compared with EVAR. EVAS was associated with higher mortality for those with small aneurysms (<5.5 cm). For those with larger aneurysms (≥5.5 cm), EVAS was initially associated with lower mortality within the first 2 years, although this advantage was lost thereafter, with higher mortality after 2 years. Future studies are required to evaluate the specific causes of death and to elucidate the potential beneficial mechanism behind sac obliteration that leads to this potential initial survival benefit. This could help guide the development of future grafts with better proximal fixation and sealing that also incorporate sac obliteration.

Project description:ObjectiveThe accurate measurement of reintervention after endovascular aneurysm repair (EVAR) is critical during postoperative surveillance. The purpose of this study was to compare reintervention rates after EVAR from three different data sources: the Vascular Quality Initiative (VQI) alone, VQI linked to Medicare claims (VQI-Medicare), and a "gold standard" of clinical chart review supplemented with telephone interviews.MethodsWe reviewed the medical records of 729 patients who underwent EVAR at our institution between 2003 and 2013. We excluded patients without follow-up reported to the VQI (n = 68 [9%]) or without Medicare claims information (n = 114 [16%]). All patients in the final analytic cohort (n = 547) had follow-up information available from all three data sources (VQI alone, VQI linked to Medicare, and chart review). We then compared reintervention rates between the three data sources. Our primary end points were the agreement between the three data sources and the Kaplan-Meier estimated rate of reintervention at 1 year, 2 years, and 3 years after EVAR. For gold standard assessment, we supplemented chart review with telephone interview as necessary to assess reintervention.ResultsVQI data alone identified 12 reintervention events in the first year after EVAR. Chart review confirmed all 12 events and identified 18 additional events not captured by the VQI. VQI-Medicare data successfully identified all 30 of these events within the first year. VQI-Medicare also documented four reinterventions in this time period that did not occur on the basis of patient interview (4/547 [0.7%]). The agreement between chart review and VQI-Medicare data at 1 year was excellent (κ = 0.93). At 3 years, there were 81 (18%) reinterventions detected by VQI-Medicare and 70 (16%) detected by chart review for a sensitivity of 92%, specificity of 96%, and κ of 0.80. Kaplan-Meier survival analysis demonstrated similar reintervention rates after 3 years between VQI-Medicare and chart review (log-rank, P = .59).ConclusionsChart review after EVAR demonstrated a 6% 1-year and 16% 3-year reintervention rate, and almost all (92%) of these events were accurately captured using VQI-Medicare data. Linking VQI data with Medicare claims allows an accurate assessment of reintervention rates after EVAR without labor-intensive physician chart review.

Project description:Endovascular aneurysm repair (EVAR) is commonly used as a minimally invasive technique for repairing infrarenal aortic aneurysms. There have been recent concerns that a subset of high-risk patients experience unfavorable outcomes with this intervention. To determine whether such a high-risk cohort exists and to identify the characteristics of these patients, we analyzed the outcomes of Medicare patients treated with EVAR from 2000-2006.We identified 66,943 patients who underwent EVAR from Inpatient Medicare database. The overall 30-day mortality was 1.6%. A risk model for perioperative mortality was developed by randomly selecting 44,630 patients; the other one third of the dataset was used to validate the model. The model was deemed reliable (Hosmer-Lemeshow statistics were P = .25 for the development, P = .24 for the validation model) and accurate (c = 0.735 and c = 0.731 for the development and the validation model, respectively).In our scoring system, where scores ranged between 1 and 7, the following were identified as significant baseline factors that predict mortality: renal failure with dialysis (score = 7); renal failure without dialysis (score = 3); clinically significant lower extremity ischemia (score = 5); patient age >or=85 years (score = 3), 75-84 years (score = 2), 70-74 years (score = 1); heart failure (score = 3); chronic liver disease (score = 3); female gender (score = 2); neurological disorders (score = 2); chronic pulmonary disease (score = 2); surgeon experience in EVAR <3 procedures (score = 1); and hospital annual volume in EVAR <7 procedures (score = 1). The majority of Medicare patients who were treated (96.6%, n = 64,651) had a score of 9 or less, which correlated with a mortality <5%. Only 3.4% of patients had a mortality >or=5% and 0.8% of patients (n = 509) had a score of 13 or higher, which correlated with a mortality >10%.We conclude that there is a high-risk cohort of patients that should not be treated with EVAR because of prohibitively high mortality; however, this cohort is small. Our scoring system, which is based on patient and institutional factors, provides criteria that can be easily used by clinicians to quantify perioperative risk for EVAR candidates.

Project description:ObjectiveEffective strategies to reduce costs associated with endovascular aneurysm repair (EVAR) remain elusive for many medical centers. In this study, targeted interventions to reduce inpatient EVAR costs were identified and implemented.MethodsFrom June 2015 to February 2016, we analyzed the EVAR practice at a high-volume academic medical center to identify, to rank, and ultimately to reduce procedure-related costs. In this analysis, per-patient direct costs to the hospital were compared before (September 2013-May 2015) and after (March 2016-January 2017) interventions were implemented. Improvement efforts concentrated on three categories that accounted for a majority of costs: implants, rooming costs, and computed tomography scans performed during the index hospitalization.ResultsCosts were compared between 141 EVAR procedures before implementation (PRE period) and 47 EVAR procedures after implementation (POST period). Based on data obtained through the Society for Vascular Surgery EVAR Cost Demonstration Project, it was determined that implantable device costs were higher than those at peer institutions. New purchasing strategies were implemented, resulting in a 30.8% decrease in per-case device costs between the PRE and POST periods. Care pathways were modified to reduce use of and costs for computed tomography scans obtained during the index hospitalization. Compared with baseline, per-case imaging costs decreased by 92.9% (P < .001), including a 99.0% (P = .001) reduction in postprocessing costs. Care pathways were also implemented to reduce preprocedural rooming for patients traveling long distances the day before surgery, resulting in a 50% decrease in utilization rate (35.4% PRE to 17.0% POST; P = .021), without having a significant impact on median postprocedural length of stay (PRE, 2 days [interquartile range, 1-11 days]; POST, 2 days [1-7 days]; P = .185). Medication costs also decreased by 38.2% (P < .001) as a hospital-wide effort.ConclusionsExcessive costs associated with EVAR threaten the sustainability of these procedures in health care organizations. Targeted cost reduction efforts can effectively reduce expenses without compromising quality or limiting patients' access.

Dataset Information

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

Background

Methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets