Developing a machine learning model for bleeding prediction in patients with cancer-associated thrombosis receiving anticoagulation therapy
Copyright © 2024 International Society on Thrombosis and Haemostasis. Published by Elsevier Inc. All rights reserved..
BACKGROUND: Only 1 conventional score is available for assessing bleeding risk in patients with cancer-associated thrombosis (CAT): the CAT-BLEED score.
OBJECTIVES: Our aim was to develop a machine learning-based risk assessment model for predicting bleeding in CAT and to evaluate its predictive performance in comparison to that of the CAT-BLEED score.
METHODS: We collected 488 attributes (clinical data, biochemistry, and International Classification of Diseases, 10th Revision, diagnosis) in 1080 unique patients with CAT. We compared CAT-BLEED score, Ridge and Lasso logistic regression, random forest, and Extreme Gradient Boosting (XGBoost) algorithms for predicting major bleeding or clinically relevant nonmajor bleeding occurring 1 to 90 days, 1 to 365 days, and 90 to 455 days after venous thromboembolism (VTE).
RESULTS: The predictive performances of Lasso logistic regression, random forest, and XGBoost were higher than that of the CAT-BLEED score in the prediction of bleeding occurring 1 to 90 days and 1 to 365 days after VTE. For predicting major bleeding or clinically relevant nonmajor bleeding 1 to 90 days after VTE, the CAT-BLEED score achieved a mean area under the receiver operating characteristic curve (AUROC) of 0.48 ± 0.13, while Lasso logistic regression and XGBoost both achieved AUROCs of 0.64 ± 0.12. For predicting bleeding 1 to 365 days after VTE, the CAT-BLEED score achieved a mean AUROC of 0.47 ± 0.08, while Lasso logistic regression and XGBoost achieved AUROCs of 0.64 ± 0.08 and 0.59 ± 0.08, respectively.
CONCLUSION: This is the first machine learning-based risk model for bleeding prediction in patients with CAT receiving anticoagulation therapy. Its predictive performance was higher than that of the conventional CAT-BLEED score. With further development, this novel algorithm might enable clinicians to perform personalized anticoagulation strategies with improved clinical outcomes.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:22 |
|---|---|
| Enthalten in: |
Journal of thrombosis and haemostasis : JTH - 22(2024), 4 vom: 31. März, Seite 1094-1104 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Grdinic, Aleksandra G [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Anticoagulants |
|---|
| Anmerkungen: |
Date Completed 25.03.2024 Date Revised 25.03.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.jtha.2023.12.034 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM366748165 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM366748165 | ||
| 003 | DE-627 | ||
| 005 | 20240325234611.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240108s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.jtha.2023.12.034 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1346.xml |
| 035 | |a (DE-627)NLM366748165 | ||
| 035 | |a (NLM)38184201 | ||
| 035 | |a (PII)S1538-7836(24)00005-9 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Grdinic, Aleksandra G |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Developing a machine learning model for bleeding prediction in patients with cancer-associated thrombosis receiving anticoagulation therapy |
| 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 25.03.2024 | ||
| 500 | |a Date Revised 25.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2024 International Society on Thrombosis and Haemostasis. Published by Elsevier Inc. All rights reserved. | ||
| 520 | |a BACKGROUND: Only 1 conventional score is available for assessing bleeding risk in patients with cancer-associated thrombosis (CAT): the CAT-BLEED score | ||
| 520 | |a OBJECTIVES: Our aim was to develop a machine learning-based risk assessment model for predicting bleeding in CAT and to evaluate its predictive performance in comparison to that of the CAT-BLEED score | ||
| 520 | |a METHODS: We collected 488 attributes (clinical data, biochemistry, and International Classification of Diseases, 10th Revision, diagnosis) in 1080 unique patients with CAT. We compared CAT-BLEED score, Ridge and Lasso logistic regression, random forest, and Extreme Gradient Boosting (XGBoost) algorithms for predicting major bleeding or clinically relevant nonmajor bleeding occurring 1 to 90 days, 1 to 365 days, and 90 to 455 days after venous thromboembolism (VTE) | ||
| 520 | |a RESULTS: The predictive performances of Lasso logistic regression, random forest, and XGBoost were higher than that of the CAT-BLEED score in the prediction of bleeding occurring 1 to 90 days and 1 to 365 days after VTE. For predicting major bleeding or clinically relevant nonmajor bleeding 1 to 90 days after VTE, the CAT-BLEED score achieved a mean area under the receiver operating characteristic curve (AUROC) of 0.48 ± 0.13, while Lasso logistic regression and XGBoost both achieved AUROCs of 0.64 ± 0.12. For predicting bleeding 1 to 365 days after VTE, the CAT-BLEED score achieved a mean AUROC of 0.47 ± 0.08, while Lasso logistic regression and XGBoost achieved AUROCs of 0.64 ± 0.08 and 0.59 ± 0.08, respectively | ||
| 520 | |a CONCLUSION: This is the first machine learning-based risk model for bleeding prediction in patients with CAT receiving anticoagulation therapy. Its predictive performance was higher than that of the conventional CAT-BLEED score. With further development, this novel algorithm might enable clinicians to perform personalized anticoagulation strategies with improved clinical outcomes | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a anticoagulation | |
| 650 | 4 | |a bleeding | |
| 650 | 4 | |a cancer-associated thrombosis | |
| 650 | 4 | |a machine learning | |
| 650 | 4 | |a risk assessment model | |
| 650 | 7 | |a Anticoagulants |2 NLM | |
| 700 | 1 | |a Radovanovic, Sandro |e verfasserin |4 aut | |
| 700 | 1 | |a Gleditsch, Jostein |e verfasserin |4 aut | |
| 700 | 1 | |a Jørgensen, Camilla Tøvik |e verfasserin |4 aut | |
| 700 | 1 | |a Asady, Elia |e verfasserin |4 aut | |
| 700 | 1 | |a Pettersen, Heidi Hassel |e verfasserin |4 aut | |
| 700 | 1 | |a Delibasic, Boris |e verfasserin |4 aut | |
| 700 | 1 | |a Ghanima, Waleed |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of thrombosis and haemostasis : JTH |d 2003 |g 22(2024), 4 vom: 31. März, Seite 1094-1104 |w (DE-627)NLM126285683 |x 1538-7836 |7 nnns |
| 773 | 1 | 8 | |g volume:22 |g year:2024 |g number:4 |g day:31 |g month:03 |g pages:1094-1104 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.jtha.2023.12.034 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 22 |j 2024 |e 4 |b 31 |c 03 |h 1094-1104 | ||