Artificial intelligence can predict risk of complications after endovascular aneurysm repair
Ngày 18/07/2022 08:12 | Lượt xem: 2476

Artificial intelligence (AI) models can be developed to predict the risk of postoperative complications after endovascular aneurysm repair (EVAR) with “high accuracy,” research presented at this year’s Society for Vascular Surgery (SVS) Vascular Annual Meeting (VAM 2022; 15–18 June, Boston, USA) demonstrated.

“Complications after EVAR can be fatal,” Becky Long (Central Michigan University, Saginaw, USA) informed attendees, noting in her presentation that patient follow-up for surveillance imaging is becoming more challenging as fewer patients are seen, particularly after the first year. 

The aim of Long’s study was to develop an AI model to predict the complication probability of individual patients to better identify those needing more intensive surveillance. The research involved collecting preoperative computed tomography angiography (CTA) 3D reconstruction images of abdominal aortic aneurysm (AAA) from 273 patients who underwent EVAR from 2011‒2020. 

Of these patients, 48 had postoperative complications including endoleak, AAA rupture, graft limb occlusion, renal artery occlusion, neck dilation, pelvic ischaemia, and graft migration. 

Using a deep convolutional neural network model, the researchers utilised the 3D CT images to predict the risk of complications after EVAR. The model was built with Tensorflow software and run on the Google Colab Platform. 

A training subset of 40 randomly selected patients with complications and 189 without were used to train the AI model. Eight positive and 36 negative cases tested its performance and prediction accuracy. Data downsampling was used to alleviate data imbalance and data augmentation methodology to further boost the model’s performance. 

Long’s presentation reported that successful training was completed on the 229 cases in the training set and then applied to predict the complication probability of each individual in the held-out performance testing cases. 

The model provides a complication sensitivity of 100% and identified all the patients who later developed complications after EVAR. Of 36 patients without complications, 16 (44%) were falsely predicted to develop complications. 

The results, therefore, demonstrated excellent sensitivity for identifying patients who would benefit from more stringent surveillance and also alleviate the need for surveillance in 56% of patients unlikely to develop complications, the presentation will show. 

This, Long concluded, demonstrates that AI models can be developed to predict the risk of postoperative complications with high accuracy. 

“Compared to existing methods, the model developed in this study did not require any expert-annotated data but only the AAA CTA images as inputs,” Long’s presentation showed. “This model can play an assistive role in identifying all patients at high risk for post- EVAR complications and the need for greater compliance in surveillance.”

Print Chia sẽ qua facebook bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair Chia sẽ qua google bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair Chia sẽ qua twitter bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair Chia sẽ qua MySpace bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair Chia sẽ qua LinkedIn bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair Chia sẽ qua stumbleupon bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair Chia sẽ qua icio bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair Chia sẽ qua digg bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair Chia sẽ qua yahoo bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair Chia sẽ qua yahoo bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair Chia sẽ qua yahoo bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair Chia sẽ qua yahoo bài: Artificial intelligence can predict risk of complications after endovascular aneurysm repair

Tin tức liên quan

CUSTOMER REVIEWS

  • I am Nguyen Thanh Sang, born in 1990. Since the examination and treatment at the clinic Duc Tin, I am very grateful to the Doctor for explaining and sharing about my illness. During the treatment time in the clinic I was very caring staff of the clinic. Now my illness has improved in a good way. Expect more and more clinic to be able to save many patients.

    I sincerely thank you !. Tel: 0938303275

  • Huynh Thi Muoi, born in 1940, was examined and treated at Duc Tin Clinic. I am very pleased about how to serve and care patients of the clinic. The doctor is committed to explaining and sharing with the patient.

    Huynh Thi Muoi sincerely thank you! Phone number: 0972868746

  • As I said Duc Tin surgical clinin is where my family trust, hope to visit. Physicians caring, thoughtful, gentle to the patient. Nurses and staff clinic polite, cheerful and thoughtful. This clinic clean, sterile, so I would love to. Tel: +84949914060.

  • The doctor is very caring, attentive and very gentle nurse, courteous, affable with me. The clinic is clean, comfortable, polite. I enjoyed this faith. Every visit I was very relieved disease. Tel: 0839820792.

  • I was patient, had to clinics of Dr. Le Duc Tin. I see very conscientious doctor patient care, answer any questions and very dedicated staff from the receptionist to the children tested, nursing. Clinics very clean and spacious. I'm very satisfied. Tel: +841227880829.

Search
Customer support

    Phone: (028) 3981 2678
    Mobile: 0903 839 878 - 0909 384 389

TOP