Ensemble learning-assisted prediction of prolonged hospital length of stay after spine correction surgery : a multi-center cohort study
© 2024. The Author(s)..
PURPOSE: This research aimed to develop a machine learning model to predict the potential risk of prolonged length of stay in hospital before operation, which can be used to strengthen patient management.
METHODS: Patients who underwent posterior spinal deformity surgery (PSDS) from eleven medical institutions in China between 2015 and 2022 were included. Detailed preoperative patient data, including demographics, medical history, comorbidities, preoperative laboratory results, and surgery details, were collected from their electronic medical records. The cohort was randomly divided into a training dataset and a validation dataset with a ratio of 70:30. Based on Boruta algorithm, nine different machine learning algorithms and a stack ensemble model were trained after hyperparameters tuning visualization and evaluated on the area under the receiver operating characteristic curve (AUROC), precision-recall curve, calibration, and decision curve analysis. Visualization of Shapley Additive exPlanations method finally contributed to explaining model prediction.
RESULTS: Of the 162 included patients, the K Nearest Neighbors algorithm performed the best in the validation group compared with other machine learning models (yielding an AUROC of 0.8191 and PRAUC of 0.6175). The top five contributing variables were the preoperative hemoglobin, height, body mass index, age, and preoperative white blood cells. A web-based calculator was further developed to improve the predictive model's clinical operability.
CONCLUSIONS: Our study established and validated a clinical predictive model for prolonged postoperative hospitalization duration in patients who underwent PSDS, which offered valuable prognostic information for preoperative planning and postoperative care for clinicians. Trial registration ClinicalTrials.gov identifier NCT05867732, retrospectively registered May 22, 2023, https://classic.
CLINICALTRIALS: gov/ct2/show/NCT05867732.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:19 |
|---|---|
| Enthalten in: |
Journal of orthopaedic surgery and research - 19(2024), 1 vom: 02. Feb., Seite 112 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Li, Wenle [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Clinical Study |
|---|
| Anmerkungen: |
Date Completed 12.02.2024 Date Revised 12.02.2024 published: Electronic ClinicalTrials.gov: NCT05867732 Citation Status MEDLINE |
|---|
| doi: |
10.1186/s13018-024-04576-4 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM367977168 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM367977168 | ||
| 003 | DE-627 | ||
| 005 | 20240212232109.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240203s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s13018-024-04576-4 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1289.xml |
| 035 | |a (DE-627)NLM367977168 | ||
| 035 | |a (NLM)38308336 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Li, Wenle |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Ensemble learning-assisted prediction of prolonged hospital length of stay after spine correction surgery |b a multi-center cohort study |
| 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 12.02.2024 | ||
| 500 | |a Date Revised 12.02.2024 | ||
| 500 | |a published: Electronic | ||
| 500 | |a ClinicalTrials.gov: NCT05867732 | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2024. The Author(s). | ||
| 520 | |a PURPOSE: This research aimed to develop a machine learning model to predict the potential risk of prolonged length of stay in hospital before operation, which can be used to strengthen patient management | ||
| 520 | |a METHODS: Patients who underwent posterior spinal deformity surgery (PSDS) from eleven medical institutions in China between 2015 and 2022 were included. Detailed preoperative patient data, including demographics, medical history, comorbidities, preoperative laboratory results, and surgery details, were collected from their electronic medical records. The cohort was randomly divided into a training dataset and a validation dataset with a ratio of 70:30. Based on Boruta algorithm, nine different machine learning algorithms and a stack ensemble model were trained after hyperparameters tuning visualization and evaluated on the area under the receiver operating characteristic curve (AUROC), precision-recall curve, calibration, and decision curve analysis. Visualization of Shapley Additive exPlanations method finally contributed to explaining model prediction | ||
| 520 | |a RESULTS: Of the 162 included patients, the K Nearest Neighbors algorithm performed the best in the validation group compared with other machine learning models (yielding an AUROC of 0.8191 and PRAUC of 0.6175). The top five contributing variables were the preoperative hemoglobin, height, body mass index, age, and preoperative white blood cells. A web-based calculator was further developed to improve the predictive model's clinical operability | ||
| 520 | |a CONCLUSIONS: Our study established and validated a clinical predictive model for prolonged postoperative hospitalization duration in patients who underwent PSDS, which offered valuable prognostic information for preoperative planning and postoperative care for clinicians. Trial registration ClinicalTrials.gov identifier NCT05867732, retrospectively registered May 22, 2023, https://classic | ||
| 520 | |a CLINICALTRIALS: gov/ct2/show/NCT05867732 | ||
| 650 | 4 | |a Clinical Study | |
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Multicenter Study | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Multimodal | |
| 650 | 4 | |a Posterior spinal deformity surgery | |
| 650 | 4 | |a Postoperative length of stay | |
| 650 | 4 | |a Spinal deformity | |
| 700 | 1 | |a Zhang, Yusi |e verfasserin |4 aut | |
| 700 | 1 | |a Zhou, Xin |e verfasserin |4 aut | |
| 700 | 1 | |a Quan, Xubin |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Binghao |e verfasserin |4 aut | |
| 700 | 1 | |a Hou, Xuewen |e verfasserin |4 aut | |
| 700 | 1 | |a Xu, Qizhong |e verfasserin |4 aut | |
| 700 | 1 | |a He, Weiheng |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Liang |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Xiaozhu |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Yang |e verfasserin |4 aut | |
| 700 | 1 | |a Xiang, Tianyu |e verfasserin |4 aut | |
| 700 | 1 | |a Li, Runmin |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Qiang |e verfasserin |4 aut | |
| 700 | 1 | |a Wu, Shi-Nan |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Kai |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Wencai |e verfasserin |4 aut | |
| 700 | 1 | |a Zheng, Jialiang |e verfasserin |4 aut | |
| 700 | 1 | |a Luan, Haopeng |e verfasserin |4 aut | |
| 700 | 1 | |a Yu, Xiaolin |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Anfa |e verfasserin |4 aut | |
| 700 | 1 | |a Xu, Chan |e verfasserin |4 aut | |
| 700 | 1 | |a Luo, Tongqing |e verfasserin |4 aut | |
| 700 | 1 | |a Hu, Zhaohui |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of orthopaedic surgery and research |d 2006 |g 19(2024), 1 vom: 02. Feb., Seite 112 |w (DE-627)NLM167010948 |x 1749-799X |7 nnns |
| 773 | 1 | 8 | |g volume:19 |g year:2024 |g number:1 |g day:02 |g month:02 |g pages:112 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1186/s13018-024-04576-4 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 19 |j 2024 |e 1 |b 02 |c 02 |h 112 | ||