Establishment of a predictive model for the risk of deep vein thrombosis after orthopedic surgery in the lower extremities and its verification

ZHANG Jiangnan; LI Ronghua; ZHOU Hongmei; XU Minyi; CAI Liangyu

doi:10.7619/jcmp.20231971

Journal of Clinical Medicine in Practice > 2023 > 27(23): 73-78. > DOI: 10.7619/jcmp.20231971

ZHANG Jiangnan, LI Ronghua, ZHOU Hongmei, XU Minyi, CAI Liangyu. Establishment of a predictive model for the risk of deep vein thrombosis after orthopedic surgery in the lower extremities and its verification[J]. Journal of Clinical Medicine in Practice, 2023, 27(23): 73-78. DOI: 10.7619/jcmp.20231971

Citation:

PDF (1671 KB)

Establishment of a predictive model for the risk of deep vein thrombosis after orthopedic surgery in the lower extremities and its verification

Department of Anesthesiology, Wuxi Traditional Chinese Medicine Hospital of Jiangsu Province, Wuxi, Jiangsu, 214071

More Information

Received Date: June 19, 2023
Revised Date: September 08, 2023
Available Online: December 25, 2023

Graphical Abstract

Abstract

Abstract

Objective
To construct and validate a predictive model for the risk of deep vein thrombosis (DVT) after lower extremity orthopedic surgery.
Methods
Clinical records of hospitalized patients who underwent lower extremity orthopedic surgery in Wuxi Traditional Chinese Medicine Hospital from January 2017 to October 2019 were collected. The univariate and multivariate analysis with the backward stepwise method were applied to screen variables and build a nomogram prediction model, and the performance of the nomogram was evaluated with respect to its discriminant capability, calibration ability, and clinical utility.
Results
A total of 5 773 hospitalized patients with orthopedic surgery of lower extremity were included in the study, with the incidence of DVT of 0.9%. Through single factor and multi-factor stepwise regression analysis, 5 variables were selected from 31 variables to construct the prediction model, including age, mean corpuscular hemoglobin concentration(MCHC), D-dimer, platelet distribution width(PDW), and thrombin time (TT). The receiver operating characteristic (ROC) curve showed that areas under the ROC curve in the training and validation cohort were 0.859 and 0.857, respectively. The model had good calibration ability and clinical practicability.
Conclusion
The DVT risk prediction model constructed in this study has good differentiation ability, calibration ability and clinical practicability, which is helpful for doctors to classify DVT patients after lower extremity orthopedic surgery and formulate early treatment plan.
- orthopedic surgery of lower extremity,
- deep venous thrombosis,
- risk prediction model,
- machine learning,
- D-dimer,
- artificial intelligence

FullText(HTML)

References (21)

References

[1]	DOLL H, GENTILE B, BUSH E N, et al. Evaluation of the measurement properties of four performance outcome measures in patients with elective hip replacements, elective knee replacements, or hip fractures[J]. Value Health, 2018, 21(9): 1104-1114. doi: 10.1016/j.jval.2018.02.006
[2]	GEERTS W H, PINEO G F, HEIT J A, et al. Prevention of venous thromboembolism: the seventh ACCP conference on antithrombotic and thrombolytic therapy[J]. Chest, 2004, 126(3 Suppl): 338S-400S.
[3]	王虎, 付亚辉, 尚昆, 等. 单一下肢骨折患者住院期间深静脉血栓发生率及分布特点[J]. 骨科临床与研究杂志, 2017, 2(3): 142-148. https://www.cnki.com.cn/Article/CJFDTOTAL-GKLC201703006.htm
[4]	王义龙, 姚永远, 贺海明, 等. 超声联合神经刺激器下腰丛-坐骨神经阻滞对老年下肢骨科手术患者的作用及其SAS评分的影响[J]. 检验医学与临床, 2018, 15(12): 1723-1726. https://www.cnki.com.cn/Article/CJFDTOTAL-JYYL201812009.htm
[5]	NGARMUKOS S, KIM K I, WONGSAK S, et al. Asia-Pacific venous thromboembolism consensus in knee and hip arthroplasty and hip fracture surgery: part 1. Diagnosis and risk factors[J]. Knee Surg Relat Res, 2021, 33(1): 18. doi: 10.1186/s43019-021-00099-y
[6]	SCARVELIS D, WELLS P S. Diagnosis and treatment of deep-vein thrombosis[J]. CMAJ, 2006, 175(9): 1087-1092. doi: 10.1503/cmaj.060366
[7]	BATES S M, JAESCHKE R, STEVENS S M, et al. Diagnosis of DVT: antithrombotic therapy and prevention of thrombosis, 9th Ed: American college of chest physicians evidence-based clinical practice guidelines[J]. Chest, 2012, 141(2 Suppl): e351S-e418S.
[8]	LIU H, YUAN H, WANG Y M, et al. Prediction of venous thromboembolism with machine learning techniques in young-middle-aged inpatients[J]. Sci Rep, 2021, 11(1): 12868. doi: 10.1038/s41598-021-92287-9
[9]	LINNEMANN B, WEINGARZ L, SCHINDEWOLF M, et al. Prevalence of established risk factors for venous thromboembolism according to age[J]. J Vasc Surg Venous Lymphat Disord, 2014, 2(2): 131-139. doi: 10.1016/j.jvsv.2013.09.006
[10]	RILEY R D, ENSOR J, SNELL K I E, et al. Calculating the sample size required for developing a clinical prediction model[J]. BMJ, 2020, 368: m441.
[11]	SILVERSTEIN M D, HEIT J A, MOHR D N, et al. Trends in the incidence of deep vein thrombosis and pulmonary embolism: a 25-year population-based study[J]. Arch Intern Med, 1998, 158(6): 585-593. doi: 10.1001/archinte.158.6.585
[12]	张颖, 潘亚娟, 刘艳, 等. 术中干预对骨科患者术后住院期间发生下肢深静脉血栓的预防作用[J]. 血管与腔内血管外科杂志, 2022, 8(12): 1513-1517. https://www.cnki.com.cn/Article/CJFDTOTAL-XGQW202307014.htm
[13]	WU J X, QING J H, YAO Y, et al. Performance of age-adjusted D-dimer values for predicting DVT before the knee and hip arthroplasty[J]. J Orthop Surg Res, 2021, 16(1): 82. doi: 10.1186/s13018-020-02172-w
[14]	BROEN K, SCHOLTES B, VOSSEN R. Predicting the need for further thrombosis diagnostics in suspected DVT is increased by using age adjusted D-dimer values[J]. Thromb Res, 2016, 145: 107-108. doi: 10.1016/j.thromres.2016.08.011
[15]	WANG X F, JIANG Z, LI Y F, et al. Prevalence of preoperative Deep Venous Thrombosis (DVT) following elderly intertrochanteric fractures and development of a risk prediction model[J]. BMC Musculoskelet Disord, 2022, 23(1): 417. doi: 10.1186/s12891-022-05381-y
[16]	REZENDE S M, LIJFERING W M, ROSENDAAL F R, et al. Hematologic variables and venous thrombosis: red cell distribution width and blood monocyte count are associated with an increased risk[J]. Haematologica, 2014, 99(1): 194-200. doi: 10.3324/haematol.2013.083840
[17]	CONTRERAS-LUJÁN E E, GARCÍA-GUERRERO E E, LÓPEZ-BONILLA O R, et al. Evaluation of machine learning algorithms for early diagnosis of deep venous thrombosis[J]. Math Comput Appl, 2022, 27(2): 24.
[18]	戎毅, 王浩阗, 李绍烁, 等. 机器学习筛选生物标志物诊治下肢深静脉血栓的研究进展[J]. 分子诊断与治疗杂志, 2023, 15(2): 357-360. https://www.cnki.com.cn/Article/CJFDTOTAL-YXYQ202302043.htm
[19]	PENG G X, WANG Q, SUN H, et al. Development and prospective validation of a novel risk score for predicting the risk of lower extremity deep vein thrombosis among multiple trauma patients[J]. Thromb Res, 2021, 201: 116-122. doi: 10.1016/j.thromres.2021.02.020
[20]	RABINOVICH A, DUCRUET T, KAHN S R, et al. Development of a clinical prediction model for the postthrombotic syndrome in a prospective cohort of patients with proximal deep vein thrombosis[J]. J Thromb Haemost, 2018, 16(2): 262-270. doi: 10.1111/jth.13909
[21]	JANSSEN K J, VERGOUWE Y, DONDERS A R, et al. Dealing with missing predictor values when applying clinical prediction models[J]. Clin Chem, 2009, 55(5): 994-1001. doi: 10.1373/clinchem.2008.115345

Cited By

Get Citation

PDF

XML

Article views (137) PDF downloads (10)

Turn off MathJax

Article Contents

Abstract

References

Establishment of a predictive model for the risk of deep vein thrombosis after orthopedic surgery in the lower extremities and its verification

Abstract

References

Catalog

Export File

Citation

Format

Content