Uncertainty-aware deep learning for trustworthy prediction of long-term outcome after endovascular thrombectomy
© 2024. The Author(s)..
Acute ischemic stroke (AIS) is a leading global cause of mortality and morbidity. Improving long-term outcome predictions after thrombectomy can enhance treatment quality by supporting clinical decision-making. With the advent of interpretable deep learning methods in recent years, it is now possible to develop trustworthy, high-performing prediction models. This study introduces an uncertainty-aware, graph deep learning model that predicts endovascular thrombectomy outcomes using clinical features and imaging biomarkers. The model targets long-term functional outcomes, defined by the three-month modified Rankin Score (mRS), and mortality rates. A sample of 220 AIS patients in the anterior circulation who underwent endovascular thrombectomy (EVT) was included, with 81 (37%) demonstrating good outcomes (mRS ≤ 2). The performance of the different algorithms evaluated was comparable, with the maximum validation under the curve (AUC) reaching 0.87 using graph convolutional networks (GCN) for mRS prediction and 0.86 using fully connected networks (FCN) for mortality prediction. Moderate performance was obtained at admission (AUC of 0.76 using GCN), which improved to 0.84 post-thrombectomy and to 0.89 a day after stroke. Reliable uncertainty prediction of the model could be demonstrated.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:14 |
|---|---|
| Enthalten in: |
Scientific reports - 14(2024), 1 vom: 06. März, Seite 5544 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Martín Vicario, Celia [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 08.03.2024 Date Revised 09.03.2024 published: Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1038/s41598-024-55761-8 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM369382056 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM369382056 | ||
| 003 | DE-627 | ||
| 005 | 20240309232437.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240307s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1038/s41598-024-55761-8 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1321.xml |
| 035 | |a (DE-627)NLM369382056 | ||
| 035 | |a (NLM)38448445 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Martín Vicario, Celia |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Uncertainty-aware deep learning for trustworthy prediction of long-term outcome after endovascular thrombectomy |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 08.03.2024 | ||
| 500 | |a Date Revised 09.03.2024 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2024. The Author(s). | ||
| 520 | |a Acute ischemic stroke (AIS) is a leading global cause of mortality and morbidity. Improving long-term outcome predictions after thrombectomy can enhance treatment quality by supporting clinical decision-making. With the advent of interpretable deep learning methods in recent years, it is now possible to develop trustworthy, high-performing prediction models. This study introduces an uncertainty-aware, graph deep learning model that predicts endovascular thrombectomy outcomes using clinical features and imaging biomarkers. The model targets long-term functional outcomes, defined by the three-month modified Rankin Score (mRS), and mortality rates. A sample of 220 AIS patients in the anterior circulation who underwent endovascular thrombectomy (EVT) was included, with 81 (37%) demonstrating good outcomes (mRS ≤ 2). The performance of the different algorithms evaluated was comparable, with the maximum validation under the curve (AUC) reaching 0.87 using graph convolutional networks (GCN) for mRS prediction and 0.86 using fully connected networks (FCN) for mortality prediction. Moderate performance was obtained at admission (AUC of 0.76 using GCN), which improved to 0.84 post-thrombectomy and to 0.89 a day after stroke. Reliable uncertainty prediction of the model could be demonstrated | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Rodríguez Salas, Dalia |e verfasserin |4 aut | |
| 700 | 1 | |a Maier, Andreas |e verfasserin |4 aut | |
| 700 | 1 | |a Hock, Stefan |e verfasserin |4 aut | |
| 700 | 1 | |a Kuramatsu, Joji |e verfasserin |4 aut | |
| 700 | 1 | |a Kallmuenzer, Bernd |e verfasserin |4 aut | |
| 700 | 1 | |a Thamm, Florian |e verfasserin |4 aut | |
| 700 | 1 | |a Taubmann, Oliver |e verfasserin |4 aut | |
| 700 | 1 | |a Ditt, Hendrik |e verfasserin |4 aut | |
| 700 | 1 | |a Schwab, Stefan |e verfasserin |4 aut | |
| 700 | 1 | |a Dörfler, Arnd |e verfasserin |4 aut | |
| 700 | 1 | |a Muehlen, Iris |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Scientific reports |d 2011 |g 14(2024), 1 vom: 06. März, Seite 5544 |w (DE-627)NLM215703936 |x 2045-2322 |7 nnns |
| 773 | 1 | 8 | |g volume:14 |g year:2024 |g number:1 |g day:06 |g month:03 |g pages:5544 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1038/s41598-024-55761-8 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 14 |j 2024 |e 1 |b 06 |c 03 |h 5544 | ||